Compare commits

...

766 Commits

Author SHA1 Message Date
Siying Dong 36039fe744 Update db.h 2018-02-26 17:17:54 -08:00
Siying Dong 97c469c3c3 Update comments in DB::Close() 2018-02-26 13:43:58 -08:00
Anand Ananthabhotla dfbe52e099 Fix the Logger::Close() and DBImpl::Close() design pattern
Summary:
The recent Logger::Close() and DBImpl::Close() implementation rely on
calling the CloseImpl() virtual function from the destructor, which will
not work. Refactor the implementation to have a private close helper
function in derived classes that can be called by both CloseImpl() and
the destructor.
Closes https://github.com/facebook/rocksdb/pull/3528

Reviewed By: gfosco

Differential Revision: D7049303

Pulled By: anand1976

fbshipit-source-id: 76a64cbf403209216dfe4864ecf96b5d7f3db9f4
2018-02-23 13:57:26 -08:00
Siying Dong 30649dc6a1 Have a different function when ROCKSDB_JEMALLOC=0
Summary:
Some sanitizer is not happy with parameter name with ROCKSDB_JEMALLOC not set. Use another function instead.
Closes https://github.com/facebook/rocksdb/pull/3536

Differential Revision: D7064849

Pulled By: siying

fbshipit-source-id: c6ae94e044686176af1259df9172453d52c2f9d5
2018-02-23 11:42:33 -08:00
Maysam Yabandeh 90eca1e616 WritePrepared Txn: optimize SubBatchCnt
Summary:
Make use of the index in WriteBatchWithIndex to also count the number of sub-batches. This eliminates the need to separately scan the batch to count the number of sub-batches once a duplicate key is detected.
Closes https://github.com/facebook/rocksdb/pull/3529

Differential Revision: D7049947

Pulled By: maysamyabandeh

fbshipit-source-id: 81cbf12c4e662541c772c7265a8f91631e25c7cd
2018-02-22 18:12:26 -08:00
Zhongyi Xie 243220d08a Update HISTORY.md to 5.12.0
Summary: Closes https://github.com/facebook/rocksdb/pull/3532

Differential Revision: D7062828

Pulled By: miasantreble

fbshipit-source-id: d36967a1cfbcaeeeb33b9f0e09e15dea85b08b70
2018-02-22 16:47:01 -08:00
Siying Dong 4624edc440 RocksDBOptionsParser::Parse()'s ignore_unknown_options argument only ingores options from higher version.
Summary:
RocksDB should always be able to parse an option file generated using the same or lower version. Unknown option should only happen if it is from a higher version. Change the behavior of RocksDBOptionsParser::Parse()'s behavior with ignore_unknown_options=true so that unknown option from a lower or the same version will never be skipped.
Closes https://github.com/facebook/rocksdb/pull/3527

Differential Revision: D7048851

Pulled By: siying

fbshipit-source-id: e261caea12f6515611a4a29f39acf2b619df2361
2018-02-22 13:28:12 -08:00
Igor Sugak aba3409740 Back out "[codemod] - comment out unused parameters"
Reviewed By: igorsugak

fbshipit-source-id: 4a93675cc1931089ddd574cacdb15d228b1e5f37
2018-02-22 12:43:17 -08:00
David Lai f4a030ce81 - comment out unused parameters
Reviewed By: everiq, igorsugak

Differential Revision: D7046710

fbshipit-source-id: 8e10b1f1e2aecebbfb229c742e214db887e5a461
2018-02-22 09:44:23 -08:00
Andrew Kryczka b092977643 BackupEngine gluster-friendly file naming convention
Summary:
Use the rsync tempfile naming convention in our `BackupEngine`. The temp file follows the format, `.<filename>.<suffix>`, which is later renamed to `<filename>`. We fix `tmp` as the `<suffix>` as we don't need to use random bytes for now. The benefit is gluster treats this tempfile naming convention specially and applies hashing only to `<filename>`, so the file won't need to be linked or moved when it's renamed. Our gluster team suggested this will make things operationally easier.
Closes https://github.com/facebook/rocksdb/pull/3463

Differential Revision: D6893333

Pulled By: ajkr

fbshipit-source-id: fd7622978f4b2487fce33cde40dd3124f16bcaa8
2018-02-21 17:42:07 -08:00
Maysam Yabandeh 828211e901 WritePrepared Txn: fix non-emptied PreparedHeap bug
Summary:
Under a certain sequence of accessing PreparedHeap, there was a bug that would not successfully empty the heap. This would result in performance issues when the heap content is moved to old_prepared_ after max_evicted_seq_ advances the orphan prepared sequence numbers. The patch fixed the bug and add more unit tests. It also does more logging when the unlikely scenarios are faced
Closes https://github.com/facebook/rocksdb/pull/3526

Differential Revision: D7038486

Pulled By: maysamyabandeh

fbshipit-source-id: f1e40bea558f67b03d2a29131fcb8734c65fce97
2018-02-21 13:42:23 -08:00
Sagar Vemuri 8ada876dfe Add rocksdb.iterator.internal-key property
Summary:
Added a new iterator property: `rocksdb.iterator.internal-key` to get the internal-key (converted to user key) at which the iterator stopped.
Closes https://github.com/facebook/rocksdb/pull/3525

Differential Revision: D7033694

Pulled By: sagar0

fbshipit-source-id: d51e6c00f5e9d766c6276ef79774b81c6c5216f8
2018-02-20 19:12:09 -08:00
jsteemann e9c31ab159 save redundant key lookup in map of locked keys
Summary:
In case it is found that a key is already marked as locked in a
stripe's map of locked keys, it is not necessary to look it up
again using `std::unordered_map<std::string, ...>::at(size_t)`.

Instead, we can use the already found position using the iterator
produced by the previous `find` operation. Reusing the iterator
will avoid having to hash the key again and do additional "random"
memory lookups in the map of keys (though the data will very
likely sit available in caches here already due to the previous
find operation)
Closes https://github.com/facebook/rocksdb/pull/3505

Differential Revision: D7036446

Pulled By: sagar0

fbshipit-source-id: cced51547b2bd2d49394f6bc8c5896f09fa80f68
2018-02-20 17:44:44 -08:00
Andrew Kryczka 1960e73e21 fix handling of empty string as checkpoint directory
Summary:
- made `CreateCheckpoint` properly return `InvalidArgument` when called with an empty directory. Previously it triggered an assertion failure due to a bug in the logic.
- made `ldb` set empty `checkpoint_dir` if that's what the user specifies, so that we can use it to properly test `CreateCheckpoint` in the future.

Differential Revision: D6874562

fbshipit-source-id: dcc1bd41768261d9338987fa7711444289707ed7
2018-02-20 16:44:00 -08:00
Igor Sugak 5263da6396 fix shift UBSAN error in col_buf_encoder.cc
Summary:
Add a static cast to perform the left shift as with an unsigned type.

make ubsan_check
Closes https://github.com/facebook/rocksdb/pull/3517

Reviewed By: sagar0

Differential Revision: D7016044

Pulled By: igorsugak

fbshipit-source-id: baf72f6197edd8f7220d010b15a23d6de6a72c49
2018-02-20 16:44:00 -08:00
Po-Chuan Hsieh ab446dc22d Fix build with USE_RTTI=0
Summary:
utilities/column_aware_encoding_util.cc:61:23: error: cannot use dynamic_cast with -fno-rtti
  table_reader_.reset(dynamic_cast<BlockBasedTable*>(table_reader.release()));
                      ^
1 error generated.

It was added as a [local patch](https://svnweb.freebsd.org/ports/head/databases/rocksdb/files/patch-utilities-column_aware_encoding_util.cc) on FreeBSD since RocksDB 5.8.
It also fixes #2707.
Closes https://github.com/facebook/rocksdb/pull/3514

Differential Revision: D7005571

Pulled By: siying

fbshipit-source-id: 351a9055d21d0accdd7a932e8e7bfcd3c8e22068
2018-02-16 10:41:49 -08:00
Maysam Yabandeh c178da053b WritePrepared Txn: optimizations for sysbench update_noindex
Summary:
These are optimization that we applied to improve sysbech's update_noindex performance.
1. Make use of LIKELY compiler hint
2. Move std::atomic so the subclass
3. Make use of skip_prepared in non-2pc transactions.
Closes https://github.com/facebook/rocksdb/pull/3512

Differential Revision: D7000075

Pulled By: maysamyabandeh

fbshipit-source-id: 1ab8292584df1f6305a4992973fb1b7933632181
2018-02-16 08:42:31 -08:00
Mike Kolupaev 97307d888f Fix deadlock in ColumnFamilyData::InstallSuperVersion()
Summary:
Deadlock: a memtable flush holds DB::mutex_ and calls ThreadLocalPtr::Scrape(), which locks ThreadLocalPtr mutex; meanwhile, a thread exit handler locks ThreadLocalPtr mutex and calls SuperVersionUnrefHandle, which tries to lock DB::mutex_.

This deadlock is hit all the time on our workload. It blocks our release.

In general, the problem is that ThreadLocalPtr takes an arbitrary callback and calls it while holding a lock on a global mutex. The same global mutex is (at least in some cases) locked by almost all ThreadLocalPtr methods, on any instance of ThreadLocalPtr. So, there'll be a deadlock if the callback tries to do anything to any instance of ThreadLocalPtr, or waits for another thread to do so.

So, probably the only safe way to use ThreadLocalPtr callbacks is to do only do simple and lock-free things in them.

This PR fixes the deadlock by making sure that local_sv_ never holds the last reference to a SuperVersion, and therefore SuperVersionUnrefHandle never has to do any nontrivial cleanup.

I also searched for other uses of ThreadLocalPtr to see if they may have similar bugs. There's only one other use, in transaction_lock_mgr.cc, and it looks fine.
Closes https://github.com/facebook/rocksdb/pull/3510

Reviewed By: sagar0

Differential Revision: D7005346

Pulled By: al13n321

fbshipit-source-id: 37575591b84f07a891d6659e87e784660fde815f
2018-02-16 08:13:34 -08:00
Andrew Kryczka 0454f781c2 fix advance reservation of arena block addresses
Summary:
Calling `std::vector::reserve()` causes memory to be reallocated and then data to be moved. It was called prior to adding every block. This reallocation could be done a huge amount of times, e.g., for users with large index blocks.

Instead, we can simply use `std::vector::emplace_back()` in such a way that preserves the no-memory-leak guarantee, while letting the vector decide when to reallocate space. Now I see reallocation/moving happen O(logN) times, rather than O(N) times, where N is the final size of vector.
Closes https://github.com/facebook/rocksdb/pull/3508

Differential Revision: D6994228

Pulled By: ajkr

fbshipit-source-id: ab7c11e13ff37c8c6c8249be7a79566a4068cd27
2018-02-15 19:41:52 -08:00
Yi Wu 989d12313c Legocastle job to report lite build binary size to scuba
Summary:
Add a legocastle job to continuously build the last 10 commits every 4 hours and report lite build binary size to scuba.
Closes https://github.com/facebook/rocksdb/pull/3511

Differential Revision: D7001730

Pulled By: yiwu-arbug

fbshipit-source-id: 7c8ca87c46d663c786a0d32be69ebbe7b19a5eb9
2018-02-15 17:27:24 -08:00
Maysam Yabandeh 8eb1d445c3 Unbreak MemTableRep API change
Summary:
The MemTableRep API was broken by this commit: 813719e952
This patch reverts the changes and instead adds InsertKey (and etc.) overloads to extend the MemTableRep API without breaking the existing classes that inherit from it.
Closes https://github.com/facebook/rocksdb/pull/3513

Differential Revision: D7004134

Pulled By: maysamyabandeh

fbshipit-source-id: e568d91fe1e17dd76c0c1f6c7dd51a18633b1c4f
2018-02-15 17:27:24 -08:00
jsteemann 4e7a182d09 Several small "fixes"
Summary:
- removed a few unneeded variables
- fused some variable declarations and their assignments
- fixed right-trimming code in string_util.cc to not underflow
- simplifed an assertion
- move non-nullptr check assertion before dereferencing of that pointer
- pass an std::string function parameter by const reference instead of by value (avoiding potential copy)
Closes https://github.com/facebook/rocksdb/pull/3507

Differential Revision: D7004679

Pulled By: sagar0

fbshipit-source-id: 52944952d9b56dfcac3bea3cd7878e315bb563c4
2018-02-15 16:57:37 -08:00
Zhongyi Xie c88c57cde1 Tweak external file ingestion seqno logic under universal compaction
Summary:
Right now it is possible that a file gets assigned to L0 but also assigned the seqno from a higher level which it doesn't fit
Under the current impl, it is possibe that seqno in lower levels (Ln) can be equal to smallest seqno of higher levels (Ln-1), which is undesirable from universal compaction's point of view.
This should fix the intermittent failure of `ExternalSSTFileBasicTest.IngestFileWithGlobalSeqnoPickedSeqno`
Closes https://github.com/facebook/rocksdb/pull/3411

Differential Revision: D6813802

Pulled By: miasantreble

fbshipit-source-id: 693d0462fa94725ccfb9d8858743e6d2d9992d14
2018-02-15 14:13:39 -08:00
jsteemann 6a30b98fdc fix wrong indentation
Summary:
Somehow the indentation was incorrect in this file.
The only change in this PR is to get it right again in order to make the code more readable.
Please reject if you think it's not worth it.
Closes https://github.com/facebook/rocksdb/pull/3504

Differential Revision: D6996011

Pulled By: miasantreble

fbshipit-source-id: 060514a3a8c910d34bad795b36eb4d278512b154
2018-02-15 11:13:37 -08:00
Fosco Marotto ba6ee1f749 Fix 2 more unused reference errors VS2017
Summary:
As in #3425
Closes https://github.com/facebook/rocksdb/pull/3497

Differential Revision: D6979588

Pulled By: gfosco

fbshipit-source-id: e9fb32d04ad45575dfe9de1d79348d158e474197
2018-02-14 11:12:36 -08:00
Siying Dong b3c5351335 Direct I/O writable file should do fsync in Close()
Summary:
We don't do fsync() after truncate in direct I/O writeable file (in fact we don't do any fsync ever). This can cause metadata not persistent to disk after the file is generated. We call it instead.
Closes https://github.com/facebook/rocksdb/pull/3500

Differential Revision: D6981482

Pulled By: siying

fbshipit-source-id: 7e2b591b7e5dd1b96fc0775515b8b9e6092980ef
2018-02-13 16:27:11 -08:00
Igor Sugak d08d05cb62 fix UBSAN errors in fault_injection_test
Summary:
This fixes shift and signed-integer-overflow UBSAN checks in fault_injection_test by using a larger and unsigned type.
Closes https://github.com/facebook/rocksdb/pull/3498

Reviewed By: siying

Differential Revision: D6981116

Pulled By: igorsugak

fbshipit-source-id: 3688f62cce570534b161e9b5f42109ebc9ae5a2c
2018-02-13 14:12:40 -08:00
Siying Dong dadf01672a Rename one of the two LevelIterator
Summary:
A new LevelIterator was recently created. Rename the old one to make unity build happy. It's also not a good idea to have two classes in the same name anyway.
Closes https://github.com/facebook/rocksdb/pull/3499

Differential Revision: D6979325

Pulled By: siying

fbshipit-source-id: 3a032d93fe205650a08e92e5262594731ec726bb
2018-02-13 13:57:58 -08:00
Siying Dong 74748611a8 Suppress UBSAN error in finer guanularity
Summary:
Now we suppress alignment UBSAN error as a whole. Suppressing 3-way CRC and murmurhash feels a better idea than turning off alignment check as a whole.
Closes https://github.com/facebook/rocksdb/pull/3495

Differential Revision: D6971273

Pulled By: siying

fbshipit-source-id: 080b59fed6df494b9f622ef7cb5d42d39e6a8cdf
2018-02-13 12:18:07 -08:00
Fosco Marotto 3c380fdffd Adding blog post for 5.10.2 release
Summary: Closes https://github.com/facebook/rocksdb/pull/3464

Differential Revision: D6906184

Pulled By: gfosco

fbshipit-source-id: 415934d7b1dd8dd226b6619bfb71781184d55cd9
2018-02-13 11:56:59 -08:00
Siying Dong b555ed30a4 Customized BlockBasedTableIterator and LevelIterator
Summary:
Use a customzied BlockBasedTableIterator and LevelIterator to replace current implementations leveraging two-level-iterator. Hope the customized logic will make code easier to understand. As a side effect, BlockBasedTableIterator reduces the allocation for the data block iterator object, and avoid the virtual function call to it, because we can directly reference BlockIter, a final class. Similarly, LevelIterator reduces virtual function call to the dummy iterator iterating the file metadata. It also enabled further optimization.

The upper bound check is also moved from index block to data block. This implementation fits this iterator better. After the change, forwared iterator is slightly optimized to ensure we trim those iterators.

The two-level-iterator now is only used by partitioned index, so it is simplified.
Closes https://github.com/facebook/rocksdb/pull/3406

Differential Revision: D6809041

Pulled By: siying

fbshipit-source-id: 7da3b9b1d3c8e9d9405302c15920af1fcaf50ffa
2018-02-12 17:12:25 -08:00
Maysam Yabandeh 8a04ee4fd1 WritePrepared Txn: use TransactionDBWriteOptimizations (2nd attempt)
Summary:
TransactionDB::Write can receive some optimization hints from the user. One is to skip the concurrency control mechanism. WritePreparedTxnDB is currently ignoring such hints. This patch optimizes WritePreparedTxnDB::Write for skip_concurrency_control and skip_duplicate_key_check hints.
Closes https://github.com/facebook/rocksdb/pull/3496

Differential Revision: D6971784

Pulled By: maysamyabandeh

fbshipit-source-id: cbab10ad538fa2b8bcb47e37c77724afe6e30f03
2018-02-12 16:43:40 -08:00
Andrew Kryczka ee1c802675 Add delay before flush in CompactRange to avoid write stalling
Summary:
- Refactored logic for checking write stall condition to a helper function: `GetWriteStallConditionAndCause`. Now it is decoupled from the logic for updating WriteController / stats in `RecalculateWriteStallConditions`, so we can reuse it for predicting whether write stall will occur.
- Updated `CompactRange` to first check whether the one additional immutable memtable / L0 file would cause stalling before it flushes. If so, it waits until that is no longer true.
- Updated `bg_cv_` to be signaled on `SetOptions` calls. The stall conditions `CompactRange` cares about can change when (1) flush finishes, (2) compaction finishes, or (3) options dynamically change. The cv was already signaled for (1) and (2) but not yet for (3).
Closes https://github.com/facebook/rocksdb/pull/3381

Differential Revision: D6754983

Pulled By: ajkr

fbshipit-source-id: 5613e03f1524df7192dc6ae885d40fd8f091d972
2018-02-12 15:42:47 -08:00
Andrew Kryczka 0a0fad447b db_bench separate options for partition index and filters
Summary:
Some workloads (like my current benchmarking) may want partitioned indexes without partitioned filters. Particularly, when `-optimize_filters_for_hits=true`, the total index size may be larger than the total filter size, so it can make sense to hold all filters in-memory but not all indexes.
Closes https://github.com/facebook/rocksdb/pull/3492

Differential Revision: D6970092

Pulled By: ajkr

fbshipit-source-id: b7fa1828e1d13829339aefb90fd56eb7c5337f61
2018-02-12 14:57:13 -08:00
Zhongyi Xie 3f1bb07351 make flush_reason_ atomic to keep TSAN happy
Summary: Closes https://github.com/facebook/rocksdb/pull/3487

Differential Revision: D6967098

Pulled By: miasantreble

fbshipit-source-id: 48e0accf2e3b3f589ddb797ff8083c8520269bf0
2018-02-12 13:28:18 -08:00
Siying Dong ef29d2a234 Explictly fail writes if key or value is not smaller than 4GB
Summary:
Right now, users will encounter unexpected bahavior if they use key or value larger than 4GB. We should explicitly fail the queriers.
Closes https://github.com/facebook/rocksdb/pull/3484

Differential Revision: D6953895

Pulled By: siying

fbshipit-source-id: b60491e1af064fc5d52971956661f6c18ceac24f
2018-02-09 14:57:54 -08:00
Yi Wu fe228da0a9 WritePrepared Txn: Support merge operator
Summary:
CompactionIterator invoke MergeHelper::MergeUntil() to do partial merge between snapshot boundaries. Previously it only depend on sequence number to tell snapshot boundary, but we also need to make use of snapshot_checker to verify visibility of the merge operands to the snapshots. For example, say there is a snapshot with seq = 2 but only can see data with seq <= 1. There are three merges, each with seq = 1, 2, 3. A correct compaction output would be (1),(2+3). Without taking snapshot_checker into account when generating merge result, compaction will generate output (1+2),(3).

By filtering uncommitted keys with read callback, the read path already take care of merges well and don't need additional updates.
Closes https://github.com/facebook/rocksdb/pull/3475

Differential Revision: D6926087

Pulled By: yiwu-arbug

fbshipit-source-id: 8f539d6f897cfe29b6dc27a8992f68c2a629d40a
2018-02-09 14:57:54 -08:00
Chinmay Kamat 9fc72d6f16 Compilation fixes for powerpc build, -Wparentheses-equality error and missing header guards
Summary:
This pull request contains miscellaneous compilation fixes.

Thanks,
Chinmay
Closes https://github.com/facebook/rocksdb/pull/3462

Differential Revision: D6941424

Pulled By: sagar0

fbshipit-source-id: fe9c26507bf131221f2466740204bff40a15614a
2018-02-09 14:12:43 -08:00
jsteemann d62af7fa4f fix a typo (of a potential vi user)
Summary: Closes https://github.com/facebook/rocksdb/pull/3481

Differential Revision: D6939089

Pulled By: siying

fbshipit-source-id: ccce3ae10cc5ff50a74b85804afd044b21a3c3e2
2018-02-09 12:58:07 -08:00
Zhongyi Xie 945f618ba5 log flush reason for better debugging experience
Summary:
It's always a mystery from the logs why flush was triggered -- user triggered it manually, WriteBufferManager triggered it,  logs were full, write buffer was full, etc.
This PR logs Flush reason whenever a flush is scheduled.
Closes https://github.com/facebook/rocksdb/pull/3401

Differential Revision: D6788142

Pulled By: miasantreble

fbshipit-source-id: a867e54d493c06adf5172bd36a180fb3faae3511
2018-02-09 12:12:43 -08:00
Andrew Kryczka e78715c29a Eliminate a memcpy for uncompressed blocks
Summary:
`ReadBlockFromFile` uses a stack buffer to hold small data blocks before passing them to the compression library, which outputs uncompressed data in a heap buffer. In the case of `kNoCompression` there is a `memcpy` to copy from stack buffer to heap buffer.

This PR optimizes `ReadBlockFromFile` to skip the stack buffer for files whose blocks are known to be uncompressed. We determine this using the SST file property, "compression_name", if it's available.
Closes https://github.com/facebook/rocksdb/pull/3472

Differential Revision: D6920848

Pulled By: ajkr

fbshipit-source-id: 5c753e804efc178b9229ae5dbe6a4adc32031f07
2018-02-07 15:57:37 -08:00
Siying Dong a0931b3185 Fix UBSAN Error in WritePreparedTransactionTest
Summary:
WritePreparedTransactionTest has the UBSAN error because the wrong order of its parent class construction. Fix it.
Closes https://github.com/facebook/rocksdb/pull/3478

Differential Revision: D6928975

Pulled By: siying

fbshipit-source-id: 13edfd5cb9cf73f1ac5ae3b6f53061d32783733d
2018-02-07 14:57:35 -08:00
Siying Dong 821e0b1683 Disable options_settable_test in UBSAN and fix UBSAN failure in blob_…
Summary:
…db_test

options_settable_test won't pass UBSAN so disable it.
blob_db_test fails in UBSAN as SnapshotList doesn't initialize all the fields in dummy snapshot. Fix it. I don't understand why only blob_db_test fails though.
Closes https://github.com/facebook/rocksdb/pull/3477

Differential Revision: D6928681

Pulled By: siying

fbshipit-source-id: e31dd300fcdecdfd4f6af279a0987fd0cdec5122
2018-02-07 14:42:26 -08:00
Siying Dong 1336a7742d Disable alignment check in UBSAN
Summary:
Disable alignment check in UBSAN for now. Now we can't get signals to meaningful failures. We can reenable it after we figure out how we can suppress failures in finer grain manner.
Closes https://github.com/facebook/rocksdb/pull/3473

Differential Revision: D6925971

Pulled By: siying

fbshipit-source-id: a0f1a242cde866abbc5c1eeee9ff8d1d7d582ac4
2018-02-07 10:58:01 -08:00
Maysam Yabandeh 8feee28020 Add skip_cc option to TransactionDB::Write
Summary:
Compared to DB::Write, TransactionDB::Write has the additional overhead of creating and initializing an internal transaction object, as well as the overhead of locking/unlocking the keys. This patch extends the TransactionDB::Write with an skip_cc option to allow the users to indicate that the write batch do not conflict with others and the concurrency control and its overhead can be skipped. TransactionDB::Write by default calls DB::Write when skip_cc is set, which works for WriteCommitted WritePolicy. Any other flavor of TransactionDB that is not compatible with this default behavior (such as WritePreparedTxnDB) can extend ::Write and implement their own approach for taking into account the skip_cc optimization.
Closes https://github.com/facebook/rocksdb/pull/3457

Differential Revision: D6877318

Pulled By: maysamyabandeh

fbshipit-source-id: 56f4e21db87ff71492db4e376fb7c2b03dfeab6b
2018-02-06 15:28:24 -08:00
Maysam Yabandeh 8f8eb4f1c0 Fix leak report by asan on DuplicateKeys test
Summary:
Deletes the transaction object at the end of the test.
Verified by:
- COMPILE_WITH_ASAN=1 make -j32 transaction_test
- ./transaction_test --gtest_filter="DBA**Duplicate*"
Closes https://github.com/facebook/rocksdb/pull/3470

Differential Revision: D6916473

Pulled By: maysamyabandeh

fbshipit-source-id: 8303df25408635d5d3ac2b25f309a3d15957c937
2018-02-06 14:26:35 -08:00
Yi Wu 81736d8afe WritePrepared Txn: update compaction_iterator_test and db_iterator_test
Summary:
Update compaction_iterator_test with write-prepared transaction DB related tests. Transaction related tests are group in CompactionIteratorWithSnapshotCheckerTest. The existing test are duplicated to make them also test with dummy SnapshotChecker that will say every key is visible to every snapshot (this is okay, we still compare sequence number to verify visibility). Merge related tests are disabled and will be revisit in another PR.

Existing db_iterator_tests are also duplicated to test with dummy read_callback that will say every key is committed.
Closes https://github.com/facebook/rocksdb/pull/3466

Differential Revision: D6909253

Pulled By: yiwu-arbug

fbshipit-source-id: 2ae4656b843a55e2e9ff8beecf21f2832f96cd25
2018-02-06 14:12:13 -08:00
Zhongyi Xie 2f29991701 split RandomizedHarnessTest more ways
Summary:
RandomizedHarnessTest enumerates different combinations of test type, compression type, restart interval, etc. For some combinations it takes very long to finish, causing the test to time out in test infrastructure.
This PR split the test input into smaller trunks in the hope that they will fit in the timeout window. Another possibility is to reduce `num_entries` of course
Closes https://github.com/facebook/rocksdb/pull/3467

Differential Revision: D6910235

Pulled By: miasantreble

fbshipit-source-id: 717246ee5d21a8a48ad82d4d9c04f9051a66f07f
2018-02-06 13:58:18 -08:00
Maysam Yabandeh 88d8b2a2f5 WritePrepared Txn: Duplicate Keys, Txn Part
Summary:
This patch takes advantage of memtable being able to detect duplicate <key,seq> and returning TryAgain to handle duplicate keys in WritePrepared Txns. Through WriteBatchWithIndex's index it detects existence of at least a duplicate key in the write batch. If duplicate key was reported, it then pays the cost of counting the number of sub-patches by iterating over the write batch and pass it to DBImpl::Write. DB will make use of the provided batch_count to assign proper sequence numbers before sending them to the WAL. When later inserting the batch to the memtable, it increases the seq each time memtbale reports a duplicate (a sub-patch in our counting) and tries again.
Closes https://github.com/facebook/rocksdb/pull/3455

Differential Revision: D6873699

Pulled By: maysamyabandeh

fbshipit-source-id: db8487526c3a5dc1ddda0ea49f0f979b26ae648d
2018-02-05 18:43:24 -08:00
Anand Ananthabhotla 4b124fb9d3 Handle error return from WriteBuffer()
Summary:
There are a couple of places where we swallow any error from
WriteBuffer() - in SwitchMemtable() and DBImpl::CloseImpl(). Propagate
the error up in those cases rather than ignoring it.
Closes https://github.com/facebook/rocksdb/pull/3404

Differential Revision: D6879954

Pulled By: anand1976

fbshipit-source-id: 2ef88b554be5286b0a8bad7384ba17a105395bdb
2018-02-05 13:59:34 -08:00
Agam Brahma c3401846ef Minor typo in comment (s/pro/pri)
Summary: Closes https://github.com/facebook/rocksdb/pull/3460

Differential Revision: D6895365

Pulled By: miasantreble

fbshipit-source-id: 04f633d1971b1f542ac28118b738ceb0242a0228
2018-02-03 18:27:14 -08:00
Mike Kolupaev cb5b8f2090 Fix use-after-free in tailing iterator with merge operator
Summary:
ForwardIterator::SVCleanup() sometimes didn't pin superversion when it was supposed to. See the added test for the scenario. Here's the ASAN output of the added test without the fix (using `COMPILE_WITH_ASAN=1 make`): https://pastebin.com/9rD0Ywws
Closes https://github.com/facebook/rocksdb/pull/3415

Differential Revision: D6817414

Pulled By: al13n321

fbshipit-source-id: bc80c44ea78a3a1fa885dfa448a26111f91afb24
2018-02-02 21:26:28 -08:00
Tamir Duberstein cd5092e168 Suppress unused warnings
Summary:
- Use `__unused__` everywhere
- Suppress unused warnings in Release mode
    + This currently affects non-MSVC builds (e.g. mingw64).
Closes https://github.com/facebook/rocksdb/pull/3448

Differential Revision: D6885496

Pulled By: miasantreble

fbshipit-source-id: f2f6adacec940cc3851a9eee328fafbf61aad211
2018-02-02 12:27:07 -08:00
Ben Clay a247617e6f Java: Add copy constructors for various option classes
Summary:
Add Java-side copy constructors for:
- Options
- DBOptions
- ColumnFamilyOptions
- WriteOptions

along with unit tests to assert the copy worked.

NOTE: Unit tests are failing in travis but it looks like a global timeout issue. These tests pass.
Closes https://github.com/facebook/rocksdb/pull/3450

Differential Revision: D6874425

Pulled By: sagar0

fbshipit-source-id: 5bde68ea5b5225e071faea2628bf8bbf10bd65ab
2018-02-02 10:57:28 -08:00
Prashant D 6e5b341e8b options: Fix coverity issues
Summary:
options/cf_options.cc:
 77      memtable_insert_with_hint_prefix_extractor(

CID 1396208 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member info_log_level is not initialized in this constructor nor in any functions that it calls.
Closes https://github.com/facebook/rocksdb/pull/3106

Differential Revision: D6874689

Pulled By: sagar0

fbshipit-source-id: b5cd2d13915fd86d87260050f9c5d117615bbe30
2018-02-01 14:27:42 -08:00
Jun Wu e502839e25 crc32: suppress -Wimplicit-fallthrough warnings
Summary:
Workaround a bunch of "implicit-fallthrough" compiler errors, like:

```
util/crc32c.cc:533:7: error: this statement may fall through [-Werror=implicit-fallthrough=]
   crc = _mm_crc32_u64(crc, *(uint64_t*)(buf + offset));
       ^
util/crc32c.cc:1016:9: note: in expansion of macro ‘CRCsinglet’
         CRCsinglet(crc0, next, -2 * 8);
         ^~~~~~~~~~
util/crc32c.cc:1017:7: note: here
       case 1:
```
Closes https://github.com/facebook/rocksdb/pull/3339

Reviewed By: sagar0

Differential Revision: D6874736

Pulled By: quark-zju

fbshipit-source-id: eec9f3bc135e12fca336928d01711006d5c3cb16
2018-02-01 14:27:42 -08:00
Fosco Marotto ba8aa8fdc8 Upgrade Appveyor to VS2017
Summary:
Per some discussions, this will switch our Appveyor testing to use Visual Studio 2017.
Closes https://github.com/facebook/rocksdb/pull/3445

Differential Revision: D6874918

Pulled By: gfosco

fbshipit-source-id: c5a0032ca9f37f0d3baeae35c59d850d528c3176
2018-02-01 13:57:01 -08:00
Andrew Kryczka b78ed0460b fix ReadaheadRandomAccessFile/iterator prefetch bug
Summary:
`ReadaheadRandomAccessFile` is used by iterators for file reads in several cases, like in compaction when `compaction_readahead_size > 0` or `use_direct_io_for_flush_and_compaction == true`, or in user iterator when `ReadOptions::readahead_size > 0`. `ReadaheadRandomAccessFile` maintains an internal buffer for readahead data. It assumes that, if the buffer's length is less than `ReadaheadRandomAccessFile::readahead_size_`, which is fixed in the constructor, then EOF has been reached so it doesn't try reading further.

Recently, d938226af4 started calling `RandomAccessFile::Prefetch` with various lengths: 8KB, 16KB, etc. When the `RandomAccessFile` is a `ReadaheadRandomAccessFile`, it triggers the above condition and incorrectly determines EOF. If a block is partially in the readahead buffer and EOF is incorrectly decided, the result is a truncated data block.

The problem is reproducible:

```
TEST_TMPDIR=/data/compaction_bench ./db_bench -benchmarks=fillrandom -write_buffer_size=1048576 -target_file_size_base=1048576 -block_size=18384 -use_direct_io_for_flush_and_compaction=true
...
put error: Corruption: truncated block read from /data/compaction_bench/dbbench/000014.sst offset 20245, expected 10143 bytes, got 8427
```
Closes https://github.com/facebook/rocksdb/pull/3454

Differential Revision: D6869405

Pulled By: ajkr

fbshipit-source-id: 87001c299e7600a37c0dcccbd0368e0954c929cf
2018-02-01 09:42:09 -08:00
Maysam Yabandeh 813719e952 WritePrepared Txn: Duplicate Keys, Memtable part
Summary:
Currently DB does not accept duplicate keys (keys with the same user key and the same sequence number). If Memtable returns false when receiving such keys, we can benefit from this signal to properly increase the sequence number in the rare cases when we have a duplicate key in the write batch written to DB under WritePrepared transactions.
Closes https://github.com/facebook/rocksdb/pull/3418

Differential Revision: D6822412

Pulled By: maysamyabandeh

fbshipit-source-id: adea3ce5073131cd38ed52b16bea0673b1a19e77
2018-01-31 18:57:07 -08:00
Yi Wu e62a763752 Blob DB: miscellaneous changes
Summary:
* Expose garbage collection related options
* Minor logging and counter name update
* Remove unused constants.
Closes https://github.com/facebook/rocksdb/pull/3451

Differential Revision: D6867077

Pulled By: yiwu-arbug

fbshipit-source-id: 6c3272a9c9d78b125a0bd6b2e56d00d087cdd6c8
2018-01-31 18:13:23 -08:00
Andrew Kryczka 1edac32b77 Update rocksdb.read.block.get.micros when block cache disabled
Summary:
Previously `ReadBlockFromFile` for data blocks was only measured when reading a block to populate block cache. This PR adds the corresponding measurements for users who disabled block cache.
Closes https://github.com/facebook/rocksdb/pull/3442

Differential Revision: D6848671

Pulled By: ajkr

fbshipit-source-id: bb4bbe1797fa2cc1d9a5bad44891af2b55384b41
2018-01-31 14:26:52 -08:00
Zhongyi Xie 5eccf0b9d5 add -fno-sanitize-recover option to force exit on errors
Summary:
By default if ubsan detects any problem, it outputs a “runtime error:” message, and in most cases continues executing the program.
In order to make test abort on errors, option `-fno-sanitize-recover` is needed. [link](https://clang.llvm.org/docs/UndefinedBehaviorSanitizer.html)
Closes https://github.com/facebook/rocksdb/pull/3447

Differential Revision: D6854654

Pulled By: miasantreble

fbshipit-source-id: c48e892b0b38307029df38a67adda0e24257e481
2018-01-31 12:13:00 -08:00
Fosco Marotto 6efa8e270c Update endif/else behavior for unreachable code error on Windows.
Summary:
Per #3367
Closes https://github.com/facebook/rocksdb/pull/3389

Differential Revision: D6766126

Pulled By: gfosco

fbshipit-source-id: e441a15e8aec6747c613d68f4f0621b605eb48a0
2018-01-31 12:13:00 -08:00
Fosco Marotto 5400800a56 Work around VS2017 warning for unused reference
Summary:
For #3407
Closes https://github.com/facebook/rocksdb/pull/3425

Differential Revision: D6836900

Pulled By: gfosco

fbshipit-source-id: 7bcaf7a1beeeeabb7c05584f2745e7b4a2473497
2018-01-31 11:58:10 -08:00
Andrew Kryczka ab5ab36ac2 fix DBTest2.ReadAmpBitmapLiveInCacheAfterDBClose file ID support check
Summary:
Updated the test case to handle tmpfs mounted at directories different from "/dev/shm/".
Closes https://github.com/facebook/rocksdb/pull/3440

Differential Revision: D6848213

Pulled By: ajkr

fbshipit-source-id: 465e9dbf0921d0930161f732db6b3766bb030589
2018-01-30 16:50:42 -08:00
Maysam Yabandeh ec225d2e97 Make WithParamInterface virtual in transaction_test
Summary:
Without this patch, ubsan_check is currently failing with this error:
```
utilities/transactions/write_prepared_transaction_test.cc:369:63: runtime error: member call on address 0x0000051649f8 which does not point to an object of type 'WithParamInterface'
0x0000051649f8: note: object has invalid vptr
```
Tested by `COMPILE_WITH_UBSAN=1 make -j32 transaction_test` and running `./write_prepared_transaction_test --gtest_filter=TwoWriteQueues/SnapshotConcurrentAccessTest.SnapshotConcurrentAccessTest1/0`
Closes https://github.com/facebook/rocksdb/pull/3444

Differential Revision: D6850087

Pulled By: maysamyabandeh

fbshipit-source-id: 5b254da8504b8757f7aec8a820ad464154da1a1d
2018-01-30 16:26:56 -08:00
Huachao Huang ab43ff58b5 Delete files in multiple ranges at once
Summary:
Using `DeleteFilesInRange` to delete files in a lot of ranges can be slow, because
`VersionSet::LogAndApply` is expensive.

This PR adds a new `DeleteFilesInRange` function to delete files in multiple
ranges at once.

Close https://github.com/facebook/rocksdb/issues/2951
Closes https://github.com/facebook/rocksdb/pull/3431

Differential Revision: D6849228

Pulled By: ajkr

fbshipit-source-id: daeedcabd8def4b1d9ee95a58266dee77b5d68cb
2018-01-30 13:56:39 -08:00
Fosco Marotto 77dc069eb9 Change size_t cast in table_test
Summary:
Fixes this build error on master (macOS):

```
table/table_test.cc:972:27: error: implicit conversion loses integer precision: 'size_t' (aka 'unsigned long') to
      'unsigned int' [-Werror,-Wshorten-64-to-32]
```
Closes https://github.com/facebook/rocksdb/pull/3434

Reviewed By: maysamyabandeh

Differential Revision: D6840354

Pulled By: gfosco

fbshipit-source-id: fffac6aefbbdd134ce1299453c5590aa855a5fc8
2018-01-30 11:12:51 -08:00
Andrew Kryczka f3fe6f883b fix for checkpoint directory with trailing slash(es)
Summary:
previously if `checkpoint_dir` contained a trailing slash, we'd attempt to create the `.tmp` directory under `checkpoint_dir` due to simply concatenating `checkpoint_dir + ".tmp"`. This failed because `checkpoint_dir` hadn't been created yet and our directory creation is non-recursive. This PR fixes the issue by always creating the `.tmp` directory in the same parent as `checkpoint_dir` by stripping trailing slashes before concatenating.
Closes https://github.com/facebook/rocksdb/pull/3275

Differential Revision: D6574952

Pulled By: ajkr

fbshipit-source-id: a6daa6777a901eac2460cd0140c9515f7241aefc
2018-01-29 21:11:42 -08:00
Yi Wu 4bdf06e78f Fix DBFlushTest::ManualFlushWithMinWriteBufferNumberToMerge dead lock
Summary:
In the test, there can be a dead lock between background flush thread and foreground main thread as following:
* background flush thread:
  - holding db mutex, while
  - waiting on "DBImpl::FlushMemTableToOutputFile:BeforeInstallSV" sync point.
* foreground thread:
  - waiting for db mutex to write "key2"

Fixing by let background flush thread wait without holding db mutex.
Closes https://github.com/facebook/rocksdb/pull/3436

Differential Revision: D6841334

Pulled By: yiwu-arbug

fbshipit-source-id: b020768ac94e166e40953c5d09e505515a5f244d
2018-01-29 18:56:47 -08:00
Maysam Yabandeh 3073b1c573 Split SnapshotConcurrentAccessTest into 20 sub tests
Summary:
SnapshotConcurrentAccessTest sometimes times out when running on the test infra. This patch splits the test into smaller sub-tests to avoid the timeout. It also benefits from lower run-time of each sub-test and increases the coverage of the test. The overall run-time of each final sub-test is at most half of the original test so we should no longer see a timeout.
Closes https://github.com/facebook/rocksdb/pull/3435

Differential Revision: D6839427

Pulled By: maysamyabandeh

fbshipit-source-id: d53fdb157109e2438ca7fe447d0cf4b71f304bd8
2018-01-29 17:12:55 -08:00
Sagar Vemuri e6605e5302 Tests for dynamic universal compaction options
Summary:
Added a test for three dynamic universal compaction options, in the realm of read amplification:
- size_ratio
- min_merge_width
- max_merge_width

Also updated DynamicUniversalCompactionSizeAmplification by adding a check on compaction reason.
Found a bug in compaction reason setting while working on this PR, and fixed in #3412 .

TODO for later: Still to add tests for these options: compression_size_percent, stop_style and trivial_move.
Closes https://github.com/facebook/rocksdb/pull/3419

Differential Revision: D6822217

Pulled By: sagar0

fbshipit-source-id: 074573fca6389053cbac229891a0163f38bb56c4
2018-01-29 16:42:45 -08:00
Zhongyi Xie 3fe0937180 Use block cache to track memory usage when ReadOptions.fill_cache=false
Summary:
ReadOptions.fill_cache is set in compaction inputs and can be set by users in their queries too. It tells RocksDB not to put a data block used to block cache.

The memory used by the data block is, however, not trackable by users.

To make the system more manageable, we can cost the block to block cache while using it, and then release it after using.
Closes https://github.com/facebook/rocksdb/pull/3333

Differential Revision: D6670230

Pulled By: miasantreble

fbshipit-source-id: ab848d3ed286bd081a13ee1903de357b56cbc308
2018-01-29 14:43:10 -08:00
Siying Dong e2d4b0efb1 db_bench: sanity check CuckooTable with mmap_read option
Summary:
This is to avoid run time error. Fail the db_bench immediately if cuckoo table is used but mmap_read is not specified.
Closes https://github.com/facebook/rocksdb/pull/3420

Differential Revision: D6838284

Pulled By: siying

fbshipit-source-id: 20893fa28d40fadc31e4ff154bed02f5a1bad341
2018-01-29 14:27:32 -08:00
Mark Isaacson b8eb32f8cf Suppress lint in old files
Summary: Grandfather in super old lint issues to make a clean slate for moving forward that allows us to have stronger enforcement on new issues.

Reviewed By: yiwu-arbug

Differential Revision: D6821806

fbshipit-source-id: 22797d31ec58e9eb0255d3b66fedfcfcb0dc127c
2018-01-29 12:56:42 -08:00
Andrew Kryczka 9f7ccc8445 fix db_bench filluniquerandom key count assertion
Summary:
It failed every time. I guess people usually ran with assertions disabled.
Closes https://github.com/facebook/rocksdb/pull/3422

Differential Revision: D6822984

Pulled By: ajkr

fbshipit-source-id: 2e90db75618b26ac1c46ddfa9e03c095c7bf16e3
2018-01-29 11:43:21 -08:00
Mamy Ratsimbazafy 3f666f79af Add Nim to the list of language bindings
Summary: Closes https://github.com/facebook/rocksdb/pull/3428

Differential Revision: D6834061

Pulled By: maysamyabandeh

fbshipit-source-id: edca5b5b8330e0fee646c7434b9631da76670240
2018-01-29 09:57:46 -08:00
Ben Darnell 65cd6cd4b6 Rewrite comments on use_fsync option
Summary:
This replaces a vague warning about the mostly-obsolete ext3 filesystem with
a more detailed note about a historical bug in the still-relevant ext4.

Fixes #3410
Closes https://github.com/facebook/rocksdb/pull/3421

Differential Revision: D6834881

Pulled By: siying

fbshipit-source-id: 7771ef5c89a54c0ac17821680779c48178d0b400
2018-01-29 09:57:46 -08:00
Maysam Yabandeh 46acdc9883 Split HarnessTest_Randomized to avoid timeout
Summary:
Split HarnessTest_Randomized to two tests
Closes https://github.com/facebook/rocksdb/pull/3424

Differential Revision: D6826006

Pulled By: maysamyabandeh

fbshipit-source-id: 59c9a11c7da092206effce6e4fa3792f9c66bef2
2018-01-29 07:41:44 -08:00
Yi Wu 439855a774 StackableDB optionally take shared ownership of the underlying DB
Summary:
Allow StackableDB optionally takes a shared_ptr on construction and thus hold shared ownership of the underlying DB.
Closes https://github.com/facebook/rocksdb/pull/3423

Differential Revision: D6824163

Pulled By: yiwu-arbug

fbshipit-source-id: dbdc30c42e007533a987ef413785e192340f03eb
2018-01-26 15:28:44 -08:00
Maysam Yabandeh 4927b4e662 Rounddown in FilePrefetchBuffer::Prefetch
Summary:
FilePrefetchBuffer::Prefetch is currently rounds the offset up which does not fit its new use cases in prefetching index/filter blocks, as it would skips over some the offsets that were requested to be prefetched. This patch rounds down instead.

Fixes #3180
Closes https://github.com/facebook/rocksdb/pull/3413

Differential Revision: D6816392

Pulled By: maysamyabandeh

fbshipit-source-id: 3aaeaf59c55d72b61dacfae6d4a8e65eccb3c553
2018-01-26 12:57:25 -08:00
Sagar Vemuri 7fcc1d0ddf Incorrect Universal Compaction reason
Summary:
While writing tests for dynamic Universal Compaction options, I found that the compaction reasons we set for size-ratio based and sorted-run based universal compactions are swapped with each other. Fixed it.
Closes https://github.com/facebook/rocksdb/pull/3412

Differential Revision: D6820540

Pulled By: sagar0

fbshipit-source-id: 270a188968ba25b2c96a8339904416c4c87ff5b3
2018-01-26 11:12:40 -08:00
Andrew Kryczka 0e6e405fec db_bench support for memtable in-place update
Summary: Closes https://github.com/facebook/rocksdb/pull/3416

Differential Revision: D6820606

Pulled By: ajkr

fbshipit-source-id: 5035ffb33ade8d50520cafeb685ee8c8fcf1cca8
2018-01-26 10:57:49 -08:00
Sagar Vemuri d938226af4 Improve performance of long range scans with readahead
Summary:
This change improves the performance of iterators doing long range scans (e.g. big/full table scans in MyRocks) by using readahead and prefetching additional data on each disk IO. This prefetching is automatically enabled on noticing more than 2 IOs for the same table file during iteration. The readahead size starts with 8KB and is exponentially increased on each additional sequential IO, up to a max of 256 KB. This helps in cutting down the number of IOs needed to complete the range scan.

Constraints:
- The prefetched data is stored by the OS in page cache. So this currently works only for non direct-reads use-cases i.e applications which use page cache. (Direct-I/O support will be enabled in a later PR).
- This gets currently enabled only when ReadOptions.readahead_size = 0 (which is the default value).

Thanks to siying for the original idea and implementation.

**Benchmarks:**
Data fill:
```
TEST_TMPDIR=/data/users/$USER/benchmarks/iter ./db_bench -benchmarks=fillrandom -num=1000000000 -compression_type="none" -level_compaction_dynamic_level_bytes
```
Do a long range scan: Seekrandom with large number of nexts
```
TEST_TMPDIR=/data/users/$USER/benchmarks/iter ./db_bench -benchmarks=seekrandom -duration=60 -num=1000000000 -use_existing_db -seek_nexts=10000 -statistics -histogram
```

Page cache was cleared before each experiment with the command:
```
sudo sh -c "echo 3 > /proc/sys/vm/drop_caches"
```
```
Before:
seekrandom   :   34020.945 micros/op 29 ops/sec;   32.5 MB/s (1636 of 1999 found)
With this change:
seekrandom   :    8726.912 micros/op 114 ops/sec;  126.8 MB/s (5702 of 6999 found)
```
~3.9X performance improvement.

Also verified with strace and gdb that the readahead size is increasing as expected.
```
strace -e readahead -f -T -t -p <db_bench process pid>
```
Closes https://github.com/facebook/rocksdb/pull/3282

Differential Revision: D6586477

Pulled By: sagar0

fbshipit-source-id: 8a118a0ed4594fbb7f5b1cafb242d7a4033cb58c
2018-01-25 21:41:53 -08:00
Ben Darnell 65d431639b Update comments about default WALRecoveryMode
Summary:
The default changed in 6a14f7a976 but this comment was not updated.
Closes https://github.com/facebook/rocksdb/pull/3409

Differential Revision: D6808264

Pulled By: maysamyabandeh

fbshipit-source-id: 0d7e2a054eb181e9a144fcb783cf0b2c77219bc0
2018-01-25 18:12:08 -08:00
Siying Dong 1039133f2d BlockBasedTable::NewDataBlockIterator to always return BlockIter
Summary:
This is a pre-cleaning up before a major block based table iterator refactoring. BlockBasedTable::NewDataBlockIterator() will always return BlockIter. This simplifies the logic and code and enable further refactoring and optimization.
Closes https://github.com/facebook/rocksdb/pull/3398

Differential Revision: D6780165

Pulled By: siying

fbshipit-source-id: 273f7dc896724f682c0118fb69a359d9cc4418b4
2018-01-25 14:57:18 -08:00
Yi Wu c7226428dd WritePrepared Txn: Fix DBIterator and add test
Summary:
In DBIter, Prev() calls FindValueForCurrentKey() to search the current value backward. If it finds that there are too many stale value being skipped, it falls back to FindValueForCurrentKeyUsingSeek(), seeking directly to the key with snapshot sequence. After introducing read_callback, however, the key it seeks to might not be visible, according to read_callback. It thus needs to keep searching forward until the first visible value.
Closes https://github.com/facebook/rocksdb/pull/3382

Differential Revision: D6756148

Pulled By: yiwu-arbug

fbshipit-source-id: 064e39b1eec5e083af1c10142600f26d1d2697be
2018-01-23 16:57:11 -08:00
Kamalalochana Subbaiah d6fdd59c63 CMake changes for CRC32 Optimization on PowerPC
Summary: Closes https://github.com/facebook/rocksdb/pull/2869

Differential Revision: D6791359

Pulled By: ajkr

fbshipit-source-id: fdd38df603d84bbcce8d85dd1729d5caa256e6be
2018-01-23 16:57:11 -08:00
Yi Wu 35d8e65a04 Make Iterator::SeekForPrev pure virtual
Summary:
To prevent user who implement the Iterator interface fail to implement SeekForPrev by mistake.
Closes https://github.com/facebook/rocksdb/pull/3402

Differential Revision: D6790681

Pulled By: yiwu-arbug

fbshipit-source-id: bd75b8ced30208982e0a1414d34384d93496827a
2018-01-23 16:12:19 -08:00
Yi Wu d46e832e94 Assert last reference before destroy ColumnFamilyData
Summary:
In ColumnFamilySet destructor, assert it hold the last reference to cfd before destroy them.

Closes #3112
Closes https://github.com/facebook/rocksdb/pull/3397

Differential Revision: D6777967

Pulled By: yiwu-arbug

fbshipit-source-id: 60b19070e0c194b3b6146699140c1d68777866cb
2018-01-23 15:12:28 -08:00
Yi Wu edc258127e DB::DumpSupportInfo should log all supported compression types
Summary:
DB::DumpSupportInfo should log all supported compression types.
Closes #3146
Closes https://github.com/facebook/rocksdb/pull/3396

Differential Revision: D6777019

Pulled By: yiwu-arbug

fbshipit-source-id: 5b17f1ffb2d71224e52f7d9c045434746c789fb0
2018-01-23 14:44:12 -08:00
Nathan VanBenschoten ec0167eecb Fix WriteBatch rep_ format for RangeDeletion records
Summary:
This is a small amount of general cleanup I made while experimenting with https://github.com/facebook/rocksdb/issues/3391.
Closes https://github.com/facebook/rocksdb/pull/3392

Differential Revision: D6788365

Pulled By: yiwu-arbug

fbshipit-source-id: 2716e5aabd5424a4dfdaa954361a62c8eb721ae2
2018-01-23 12:57:32 -08:00
Sagar Vemuri 0ea7170d7d Remove old misleading comments
Summary:
FIFO and Universal compaction options were recently made dynamic, but I forgot to update these comments. These would mislead anyone who is reading the code.
Closes https://github.com/facebook/rocksdb/pull/3399

Differential Revision: D6786358

Pulled By: sagar0

fbshipit-source-id: 57cfc412f63deaee29bbd82b863304821d60057d
2018-01-23 10:27:41 -08:00
Yi Wu 7e3d3326ce Blob DB: dump blob_db_options.min_blob_size
Summary:
min_blob_size was missing from BlobDBOptions::Dump.
Closes https://github.com/facebook/rocksdb/pull/3400

Differential Revision: D6781525

Pulled By: yiwu-arbug

fbshipit-source-id: 40d9b391578d7f8c91bd89f4ce2eda5064864c25
2018-01-22 22:41:27 -08:00
Siying Dong 7291a3f813 Improve fallocate size in compaction output
Summary:
Now in leveled compaction, we allocate solely based on output target file size. If the total input size is smaller than the number, we should use the total input size instead. Also, cap the allocate size to 1GB.
Closes https://github.com/facebook/rocksdb/pull/3385

Differential Revision: D6762363

Pulled By: siying

fbshipit-source-id: e30906f6e9bff3ec847d2166e44cb49c92f98a13
2018-01-22 16:43:46 -08:00
Islam AbdelRahman c615689bb5 Support skipping bloom filters for SstFileWriter
Summary:
Add an option for SstFileWriter to skip building bloom filters
Closes https://github.com/facebook/rocksdb/pull/3360

Differential Revision: D6709120

Pulled By: IslamAbdelRahman

fbshipit-source-id: 964d4bce38822a048691792f447bcfbb4b6bd809
2018-01-22 14:42:18 -08:00
Bernard Spil 6f5ba0bf5b Fix building on FreeBSD
Summary:
FreeBSD uses jemalloc as the base malloc implementation.
The patch has been functional on FreeBSD as of the MariaDB 10.2 port.
Closes https://github.com/facebook/rocksdb/pull/3386

Differential Revision: D6765742

Pulled By: yiwu-arbug

fbshipit-source-id: d55dbc082eecf640ef3df9a21f26064ebe6587e8
2018-01-19 17:12:43 -08:00
Yi Wu f2f034ef3b Blob DB: fix crash when DB full but no candidate file to evict
Summary:
When blob_files is empty, std::min_element will return blobfiles.end(), which cannot be dereference. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3387

Differential Revision: D6764927

Pulled By: yiwu-arbug

fbshipit-source-id: 86f78700132be95760d35ac63480dfd3a8bbe17a
2018-01-19 16:26:50 -08:00
Yi Wu 5568aec421 Fix DBTest::SoftLimit TSAN failure
Summary:
Fix data race found by TSAN around WriteStallListener: https://gist.github.com/yiwu-arbug/027d2448b903648f2f0f40b05258d80f
Closes https://github.com/facebook/rocksdb/pull/3384

Differential Revision: D6762167

Pulled By: yiwu-arbug

fbshipit-source-id: cd3a5c9f806de390bd1af6077ea6dbbc8bcaec09
2018-01-19 12:57:15 -08:00
Siying Dong 47ad6b81ff Add 5.10.fb to tools/check_format_compatible.sh
Summary: Closes https://github.com/facebook/rocksdb/pull/3383

Differential Revision: D6762375

Pulled By: siying

fbshipit-source-id: dc1e0dc9718ffb59ffe42e2a2c844b67f935a5fb
2018-01-19 12:42:07 -08:00
Yi Wu f1cb83fcf4 Fix Flush() keep waiting after flush finish
Summary:
Flush() call could be waiting indefinitely if min_write_buffer_number_to_merge is used. Consider the sequence:
1. User call Flush() with flush_options.wait = true
2. The manual flush started in the background
3. New memtable become immutable because of writes. The new memtable will not trigger flush if min_write_buffer_number_to_merge is not reached.
4. The manual flush finish.

Because of the new memtable created at step 3 not being flush, previous logic of WaitForFlushMemTable() keep waiting, despite the memtables it intent to flush has been flushed.

Here instead of checking if there are any more memtables to flush, WaitForFlushMemTable() also check the id of the earliest memtable. If the id is larger than that of latest memtable at the time flush was initiated, it means all the memtable at the time of flush start has all been flush.
Closes https://github.com/facebook/rocksdb/pull/3378

Differential Revision: D6746789

Pulled By: yiwu-arbug

fbshipit-source-id: 35e698f71c7f90b06337a93e6825f4ea3b619bfa
2018-01-18 17:45:16 -08:00
topilski b9873162f0 Fixed get version on windows, moved throwing exceptions into cc file.
Summary:
Fixes for msys2 and mingw, hide exceptions into cpp  file.
Closes https://github.com/facebook/rocksdb/pull/3377

Differential Revision: D6746707

Pulled By: yiwu-arbug

fbshipit-source-id: 456b38df80bc48b8386a2cf87f669b5a4f9999a4
2018-01-18 14:56:56 -08:00
jonasf 4decff6fa8 Add possibility to change ttl on open DB
Summary:
We have seen cases where it could be good to change TTL on already open DB.
Change ttl in TtlCompactionFilterFactory on open db.
Next time a filter is created, it will filter accroding to the set TTL.

Is this something that could be useful for others?
Any downsides?
Closes https://github.com/facebook/rocksdb/pull/3292

Differential Revision: D6731993

Pulled By: miasantreble

fbshipit-source-id: 73b94d69237b11e8730734389052429d621a6b1e
2018-01-18 10:42:15 -08:00
Andrew Kryczka 46e599fc6b fix live WALs purged while file deletions disabled
Summary:
When calling `DisableFileDeletions` followed by `GetSortedWalFiles`, we guarantee the files returned by the latter call won't be deleted until after file deletions are re-enabled. However, `GetSortedWalFiles` didn't omit files already planned for deletion via `PurgeObsoleteFiles`, so the guarantee could be broken.

We fix it by making `GetSortedWalFiles` wait for the number of pending purges to hit zero if file deletions are disabled. This condition is eventually met since `PurgeObsoleteFiles` is guaranteed to be called for the existing pending purges, and new purges cannot be scheduled while file deletions are disabled. Once the condition is met, `GetSortedWalFiles` simply returns the content of DB and archive directories, which nobody can delete (except for deletion scheduler, for which I plan to fix this bug later) until deletions are re-enabled.
Closes https://github.com/facebook/rocksdb/pull/3341

Differential Revision: D6681131

Pulled By: ajkr

fbshipit-source-id: 90b1e2f2362ea9ef715623841c0826611a817634
2018-01-17 17:42:04 -08:00
Andrew Kryczka 266d85fbec fix DBTest.AutomaticConflictsWithManualCompaction
Summary:
After af92d4ad11, only exclusive manual compaction can have conflict. dc360df81e updated the conflict-checking test case accordingly. But we missed the point that exclusive manual compaction can only conflict with automatic compactions scheduled after it, since it waits on pending automatic compactions before it begins running.

This PR updates the test case to ensure the automatic compactions are scheduled after the manual compaction starts but before it finishes, thus ensuring a conflict. I also cleaned up the test case to use less space as I saw it cause out-of-space error on travis.
Closes https://github.com/facebook/rocksdb/pull/3375

Differential Revision: D6735162

Pulled By: ajkr

fbshipit-source-id: 020530a4e150a4786792dce7cec5d66b420cb884
2018-01-16 23:12:00 -08:00
Yi Wu dc360df81e Fix multiple build failures
Summary:
* Fix DBTest.CompactRangeWithEmptyBottomLevel lite build failure
* Fix DBTest.AutomaticConflictsWithManualCompaction failure introduce by #3366
* Fix BlockBasedTableTest::IndexUncompressed should be disabled if snappy is disabled
* Fix ASAN failure with DBBasicTest::DBClose test
Closes https://github.com/facebook/rocksdb/pull/3373

Differential Revision: D6732313

Pulled By: yiwu-arbug

fbshipit-source-id: 1eb9b9d9a8d795f56188fa9770db9353f6fdedc5
2018-01-16 17:30:39 -08:00
Bartek Wrona bf6f03f3cd Issue #3370 Broken CMakeLists.txt
Summary:
Issue #3370 Simple fixes to make RocksDB project working also as a submodule of other bigger one.
Closes https://github.com/facebook/rocksdb/pull/3372

Differential Revision: D6729595

Pulled By: ajkr

fbshipit-source-id: eee2589e7a7c4322873dff8510eebd050301c54c
2018-01-16 14:26:50 -08:00
Sunguck Lee af92d4ad11 Avoid too frequent MaybeScheduleFlushOrCompaction() call
Summary:
If there's manual compaction in the queue, then "HaveManualCompaction(compaction_queue_.front())" will return true, and this cause too frequent MaybeScheduleFlushOrCompaction().

https://github.com/facebook/rocksdb/issues/3198
Closes https://github.com/facebook/rocksdb/pull/3366

Differential Revision: D6729575

Pulled By: ajkr

fbshipit-source-id: 96da04f8fd33297b1ccaec3badd9090403da29b0
2018-01-16 13:12:12 -08:00
Anand Ananthabhotla d0f1b49ab6 Add a Close() method to DB to return status when closing a db
Summary:
Currently, the only way to close an open DB is to destroy the DB
object. There is no way for the caller to know the status. In one
instance, the destructor encountered an error due to failure to
close a log file on HDFS. In order to prevent silent failures, we add
DB::Close() that calls CloseImpl() which must be implemented by its
descendants.
The main failure point in the destructor is closing the log file. This
patch also adds a Close() entry point to Logger in order to get status.
When DBOptions::info_log is allocated and owned by the DBImpl, it is
explicitly closed by DBImpl::CloseImpl().
Closes https://github.com/facebook/rocksdb/pull/3348

Differential Revision: D6698158

Pulled By: anand1976

fbshipit-source-id: 9468e2892553eb09c4c41b8723f590c0dbd8ab7d
2018-01-16 11:08:57 -08:00
Sagar Vemuri 68829ed89c Revert Snappy version upgrade
Summary:
Java static builds are again broken, this time due Snappy version upgrade introduced in 90c1d81975 (#3331).

This is due to two reasons:
1. The new Snappy packages should now be downloaded from https://github.com/google/snappy/archive/<pkg.tar.gz> instead of https://github.com/google/snappy/releases/download/<pkg.tar.gz> which we are using now.
1. In addition to the the above URL change, Snappy changed its build from using autotools to CMake based : https://github.com/google/snappy/blame/e69d9f880677f2aa3488c80b953ec4309f0dfa2e/README.md#L65-L72

So more changes are needed if we are going to upgrade to 1.1.7. Hence reverting the version upgrade until we figure them out.
Closes https://github.com/facebook/rocksdb/pull/3363

Differential Revision: D6716983

Pulled By: sagar0

fbshipit-source-id: f451a1bc5eb0bb090f4da07bc3e5ba72cf89aefa
2018-01-12 23:41:43 -08:00
Andrew Kryczka 43549c7d59 Prevent unnecessary calls to PurgeObsoleteFiles
Summary:
Split `JobContext::HaveSomethingToDelete` into two functions: itself and `JobContext::HaveSomethingToClean`. Now we won't call `DBImpl::PurgeObsoleteFiles` in cases where we really just need to call `JobContext::Clean`. The change is needed because I want to track pending calls to `PurgeObsoleteFiles` for a bug fix, which is much simpler if we only call it after `FindObsoleteFiles` finds files to delete.
Closes https://github.com/facebook/rocksdb/pull/3350

Differential Revision: D6690609

Pulled By: ajkr

fbshipit-source-id: 61502e7469288afe16a663a1b7df345baeaf246f
2018-01-12 13:27:08 -08:00
Andrew Kryczka ba295cda29 replace DBTest.HugeNumbersOfLevel with a more targeted test case
Summary:
This test often causes out-of-space error when run on travis. We don't want such stress tests in our unit test suite.

The bug in #596, which this test intends to expose, can be repro'd as long as the bottommost level(s) are empty when CompactRange is called. I rewrote the test to cover this simple case without writing a lot of data.
Closes https://github.com/facebook/rocksdb/pull/3362

Differential Revision: D6710417

Pulled By: ajkr

fbshipit-source-id: 9a1ec85e738c813ac2fee29f1d5302065ecb54c5
2018-01-12 11:12:09 -08:00
Sagar Vemuri e446d14093 Fix PowerPC dynamic java build
Summary:
Java build on PPC64le has been broken since a few months, due to #2716. Fixing it with the least amount of changes.
(We should cleanup a little around this code when time permits).

This should fix the build failures seen in http://140.211.168.68:8080/job/Rocksdb/ .
Closes https://github.com/facebook/rocksdb/pull/3359

Differential Revision: D6712938

Pulled By: sagar0

fbshipit-source-id: 3046e8f072180693de2af4762934ec1ace309ca4
2018-01-12 10:57:14 -08:00
Andrew Kryczka 6d7e3b9faf fix Gemfile.lock nokogiri dependencies
Summary:
I installed the ruby dependencies and ran `bundle update nokogiri`. It depends on a newer version of "mini_portile2" which I missed in 9c2f64e148. Now `bundle install` works again.
Closes https://github.com/facebook/rocksdb/pull/3361

Differential Revision: D6710164

Pulled By: ajkr

fbshipit-source-id: 9a08d6cc6400ef495b715b3d68b04ce3f3367031
2018-01-11 20:11:32 -08:00
Peter (Stig) Edwards 45828c7215 Consider an increase to buffer size when reading option file, from 4K to 8K.
Summary:
Hello and thank you for RocksDB,

While looking into the buffered io used when an `OPTIONS` file is read I noticed the `OPTIONS` files produced by RocksDB 5.8.8 (and head of master) were just over 4096 bytes in size, resulting in the version of glibc I am using (glibc-2.17-196.el7) (on the filesystem used) being passed a 4K buffer for the `fread_unlocked` call and 2 system call reads using a 4096 buffer being used to read the contents of the `OPTIONS` file.

  If the buffer size is increased to 8192 then 1 system call read is used to read the contents.

  As I think the buffer size is just used for reading `OPTIONS` files, and I thought it likely that `OPTIONS` files have increased in size (as more options are added), I thought I would suggest an increase.

[  If the comments from the top of the `OPTIONS` file are removed, and white space from the start of lines is removed then the size can be reduced to be under 4K, but as more options are added the size seems likely to grow again. ]

Create a new database:

```
> ./ldb --create_if_missing --db=/tmp/rdb_tmp put 1 1
OK
```

The OPTIONS file is 4252 bytes:

```
> stat /tmp/rdb_tmp/OPTIONS* | head -n 2
  File: ‘/tmp/rdb_tmp/OPTIONS-000005’
  Size: 4252            Blocks: 16         IO Block: 4096   regular file
```

Before, the 4096 byte buffer is used from 2 system read calls:

```
> strace -f ./ldb --try_load_options --db=/tmp/rdb_tmp get DOES_NOT_EXIST 2>&1 |
    grep -A 1 'RocksDB option file'
read(3, "# This is a RocksDB option file."..., 4096) = 4096
read(3, "e\n  metadata_block_size=4096\n  c"..., 4096) = 156
```

ltrace shows 4096 passed to fread_unlocked

```
> ltrace -S -f ./ldb --try_load_options --db=/tmp/rdb_tmp get DOES_NOT_EXIST 2>&1 |
    grep -C 3 'RocksDB option file'
[pid 51013] fread_unlocked(0x7ffd5fbf2d50, 1, 4096, 0x7fd2e084e780 <unfinished ...>
[pid 51013] fstat@SYS(3, 0x7ffd5fbf28f0)         = 0
[pid 51013] mmap@SYS(nil, 4096, 3, 34, -1, 0)    = 0x7fd2e318c000
[pid 51013] read@SYS(3, "# This is a RocksDB option file."..., 4096) = 4096
[pid 51013] <... fread_unlocked resumed> )       = 4096
...
```

After, the 8192 byte buffer is used from 1 system read call:

```
> strace -f ./ldb --try_load_options --db=/tmp/rdb_tmp get DOES_NOT_EXIST 2>&1 | grep -A 1 'RocksDB option file'
read(3, "# This is a RocksDB option file."..., 8192) = 4252
read(3, "", 4096)                       = 0
```

ltrace shows 8192 passed to fread_unlocked

```
> ltrace -S -f ./ldb --try_load_options --db=/tmp/rdb_tmp get DOES_NOT_EXIST 2>&1 | grep -C 3 'RocksDB option file'
[pid 146611] fread_unlocked(0x7ffcfba382f0, 1, 8192, 0x7fc4e844e780 <unfinished ...>
[pid 146611] fstat@SYS(3, 0x7ffcfba380f0)        = 0
[pid 146611] mmap@SYS(nil, 4096, 3, 34, -1, 0)   = 0x7fc4eaee0000
[pid 146611] read@SYS(3, "# This is a RocksDB option file."..., 8192) = 4252
[pid 146611] read@SYS(3, "", 4096)               = 0
[pid 146611] <... fread_unlocked resumed> )      = 4252
[pid 146611] feof(0x7fc4e844e780)                = 1
```
Closes https://github.com/facebook/rocksdb/pull/3294

Differential Revision: D6653684

Pulled By: ajkr

fbshipit-source-id: 222f25f5442fefe1dcec18c700bd9e235bb63491
2018-01-11 18:57:41 -08:00
Changli Gao 0a7ba0e548 Fix memleak when DB::DeleteFile()
Summary:
Because the corresponding read_first_record_cache_ item wasn't
erased, memory leaked.
Closes https://github.com/facebook/rocksdb/pull/1712

Differential Revision: D4363654

Pulled By: ajkr

fbshipit-source-id: 7da1adcfc8c380e4ffe05b8769fc2221ad17a225
2018-01-11 18:57:33 -08:00
Andrew Kryczka 9c2f64e148 Update Gemfile.lock
Summary:
bump nokogiri number
Closes https://github.com/facebook/rocksdb/pull/3358

Differential Revision: D6708596

Pulled By: ajkr

fbshipit-source-id: 6662c3ba4994374ecf8a13928e915b655a980b70
2018-01-11 16:57:25 -08:00
Bo Liu 204af1eccc add WriteBatch::WriteBatch(std::string&&)
Summary:
to save a string copy for some use cases.

The change is pretty straightforward, please feel free to let me know if you want to suggest any tests for it.
Closes https://github.com/facebook/rocksdb/pull/3349

Differential Revision: D6706828

Pulled By: yiwu-arbug

fbshipit-source-id: 873ce4442937bdc030b395c7f99228eda7f59eb7
2018-01-11 15:43:56 -08:00
Adam Retter d4da02d147 Add Jenkins for PPC64le build status badge
Summary: Closes https://github.com/facebook/rocksdb/pull/3356

Differential Revision: D6706909

Pulled By: sagar0

fbshipit-source-id: 6e4757d9eceab3e8a6c1b83c1be4108e86576cb2
2018-01-11 14:57:45 -08:00
Adam Retter a53c571d2d FreeBSD build support for RocksDB and RocksJava
Summary:
Tested on a clean FreeBSD 11.01 x64.

Closes https://github.com/facebook/rocksdb/pull/1423
Closes https://github.com/facebook/rocksdb/pull/3357

Differential Revision: D6705868

Pulled By: sagar0

fbshipit-source-id: cbccbbdafd4f42922512ca03619a5d5583a425fd
2018-01-11 13:29:55 -08:00
Dmitri Smirnov b010116d82 Eliminate some redundant block reads.
Summary:
Re-use metadata for reading Compression Dictionary on BlockBased
  table open, this saves two reads from disk.
  This helps to our 999 percentile in 5.6.1 where prefetch buffer is  not present.
Closes https://github.com/facebook/rocksdb/pull/3354

Differential Revision: D6695753

Pulled By: ajkr

fbshipit-source-id: bb8acd9e9e66e65b89c548ab8940570ae360333c
2018-01-10 17:11:58 -08:00
Andrew Kryczka 0c6e8be9e2 Fix directory name for db_basic_test
Summary:
It was using the same directory as `db_options_test` so transiently failed when unit tests were run in parallel.
Closes https://github.com/facebook/rocksdb/pull/3352

Differential Revision: D6691649

Pulled By: ajkr

fbshipit-source-id: bee433484fec4faedd5cadf2db3c92fdcc99a170
2018-01-10 15:41:46 -08:00
Anand Ananthabhotla 199405192d Add a BlockBasedTableOption to turn off index block compression.
Summary:
Add a new bool option index_uncompressed in BlockBasedTableOptions.
Closes https://github.com/facebook/rocksdb/pull/3303

Differential Revision: D6686161

Pulled By: anand1976

fbshipit-source-id: 748b46993d48a01e5f89b6bd3e41f06a59ec6054
2018-01-10 15:11:59 -08:00
Andrew Kryczka bafec6bb30 Fix checkpoint_test directory setup/cleanup
Summary:
- Change directory name from "db_test" to "checkpoint_test". Previously it used the same directory as `db_test`
- Systematically cleanup snapshot and snapshot staging directories before each test. Previously a failed test run caused subsequent runs to fail, particularly when the first failure caused "snapshot.tmp" to not be cleaned up.
Closes https://github.com/facebook/rocksdb/pull/3351

Differential Revision: D6691015

Pulled By: ajkr

fbshipit-source-id: 4fc2ac2e21ff2617ea0e96297c5132b5f2eefd79
2018-01-10 12:26:49 -08:00
Siying Dong a478e85697 Remove GCC parameter "-march=native" for ARM
Summary:
Most popular versions of GCC can't identify platform on ARM if "-march=native" is specified. Remove it to unblock most people.
Closes https://github.com/facebook/rocksdb/pull/3346

Differential Revision: D6690544

Pulled By: siying

fbshipit-source-id: bbaba9fe2645b6b37144b36ea75beeff88992b49
2018-01-09 18:27:03 -08:00
Sagar Vemuri 677f249d6d Fix Travis build failures in CMake RocksJava
Summary:
Fixed RocksJava travis build failure due to a missing file in java/CMakeLists.txt. (from #3332).
Closes https://github.com/facebook/rocksdb/pull/3344

Differential Revision: D6686472

Pulled By: sagar0

fbshipit-source-id: dd3281dff1342c3a7235c402890420aa56db0fe3
2018-01-09 16:42:15 -08:00
Siying Dong 6aa95f4d0f Fix a wrong log formatting
Summary:
I experienced weird segfault because of this mismatch of type in log formatting. Fix it.
Closes https://github.com/facebook/rocksdb/pull/3345

Differential Revision: D6687224

Pulled By: siying

fbshipit-source-id: c51fb1c008b7ebc3efdc353a4adad3e8f5b3e9de
2018-01-09 14:58:33 -08:00
Andrew Kryczka 0f0d2ab95a fix DBImpl instance variable naming
Summary:
got confused while reading `FindObsoleteFiles` due to thinking it's a local variable, so renamed it properly
Closes https://github.com/facebook/rocksdb/pull/3342

Differential Revision: D6684797

Pulled By: ajkr

fbshipit-source-id: a4df0aae1cccce99d4dd4d164aadc85b17707132
2018-01-09 12:56:58 -08:00
Yi Wu 46ec52499e Fix db_bench write being disabled in lite build
Summary:
The macro was added by mistake in #2372
Closes https://github.com/facebook/rocksdb/pull/3343

Differential Revision: D6681356

Pulled By: yiwu-arbug

fbshipit-source-id: 4180172fb0eaef4189c07f219241e0c261c03461
2018-01-09 10:57:29 -08:00
Maysam Yabandeh 00b33c2474 WritePrepared Txn: address some pending TODOs
Summary:
This patch addresses a couple of minor TODOs for WritePrepared Txn such as double checking some assert statements at runtime as well, skip extra AddPrepared in non-2pc transactions, and safety check for infinite loops.
Closes https://github.com/facebook/rocksdb/pull/3302

Differential Revision: D6617002

Pulled By: maysamyabandeh

fbshipit-source-id: ef6673c139cb49f64c0879508d2f573b78609aca
2018-01-09 08:57:20 -08:00
Chris Lu 24e2c1640d add support for allow_ingest_behind in C API
Summary:
https://github.com/facebook/rocksdb/wiki/Creating-and-Ingesting-SST-files

Need to expose these functions in the C API to be used by Go bindings.
Closes https://github.com/facebook/rocksdb/pull/3011

Differential Revision: D6679563

Pulled By: sagar0

fbshipit-source-id: 536f844ddaeb0172c6d7e416d2a75e8f9e57c8ef
2018-01-08 17:26:31 -08:00
Adam Retter 398d72fa61 Add autotune and #getBytesPerSecond() to RocksJava RateLimiter
Summary: Closes https://github.com/facebook/rocksdb/pull/3332

Differential Revision: D6667680

Pulled By: ajkr

fbshipit-source-id: b2bb6889257850a4eb6f6cbd7106f62df7b82730
2018-01-08 12:30:52 -08:00
Yi Wu 30a017feca Blob DB: avoid having a separate read of checksum
Summary:
Previously on a blob db read, we are making a read of the blob value, and then make another read to get CRC checksum. I'm combining the two read into one.

readrandom db_bench with 1G database with base db size of 13M, value size 1k:
`./db_bench --db=/home/yiwu/tmp/db_bench --use_blob_db --value_size=1024 --num=1000000 --benchmarks=readrandom --use_existing_db --cache_size=32000000`
master: throughput 234MB/s, get micros p50 5.984 p95 9.998 p99 20.817 p100 787
this PR: throughput 261MB/s, get micros p50 5.157 p95 9.928 p99 20.724 p100 190
Closes https://github.com/facebook/rocksdb/pull/3301

Differential Revision: D6615950

Pulled By: yiwu-arbug

fbshipit-source-id: 052410c6d8539ec0cc305d53793bbc8f3616baa3
2018-01-05 16:41:58 -08:00
Sagar Vemuri 3e955fad09 Fix zstd/zdict include path for java static build
Summary:
With the ZSTD dictionary generator support added in #3057
`PORTABLE=1 ROCKSDB_NO_FBCODE=1 make rocksdbjavastatic` fails as it can't find zdict.h. Specifically due to:
https://github.com/facebook/rocksdb/blob/e3a06f12d27fd50af7b6c5941973f529601f9a3e/util/compression.h#L39
In java static builds zstd code gets directly downloaded from https://github.com/facebook/zstd , and in there zdict.h is under dictBuilder directory. So, I modified libzstd.a target to use `make install` to collect all the header files into a single location and used that as the zstd's include path.
Closes https://github.com/facebook/rocksdb/pull/3260

Differential Revision: D6669850

Pulled By: sagar0

fbshipit-source-id: f8a7562a670e5aed4c4fb6034a921697590d7285
2018-01-05 15:41:46 -08:00
Dmitri Smirnov 84ddbd186a Make Windows dep switches compatible with other builds
Summary:
Make dependacies switches compatible with other OS builds
  TODO: Make find_package work for Windows.
Closes https://github.com/facebook/rocksdb/pull/3322

Differential Revision: D6667637

Pulled By: sagar0

fbshipit-source-id: 5afcd7bbfe69465310a4fbc8e589f01e506b95f5
2018-01-05 14:56:54 -08:00
Adam Retter 90c1d81975 Update javastatic dependencies
Summary:
1. Snappy 1.1.7
2. LZ4 1.8.0
3. ZSTD  1.3.3
Closes https://github.com/facebook/rocksdb/pull/3331

Differential Revision: D6667933

Pulled By: ajkr

fbshipit-source-id: 21c526609df7580481195a389d31f733e2695e65
2018-01-05 12:11:44 -08:00
Maysam Yabandeh 1c9ada59cc Remove assert(s.ok()) from ::DeleteFile
Summary:
DestroyDB that is used in tests loops over the files returned by ::GetChildren and delete them one by one. Such files might be already deleted in the file system (during DeleteObsoleteFileImpl for example) but will get actually deleted with a delay sometimes before ::DeleteFile is called on the file name. We have some test failures where FaultInjectionTestEnv::DeleteFile fails on assert(s.ok()) during DestroyDB. This patch removes the assert statement to fix that.
Closes https://github.com/facebook/rocksdb/pull/3324

Differential Revision: D6659545

Pulled By: maysamyabandeh

fbshipit-source-id: 4c9552fbcd494dcf3e61d475c11fc965c4388b2c
2018-01-04 11:11:45 -08:00
Andrew Kryczka ea8ccd2267 fix powerpc java static build
Summary:
added support for C and asm files as required for e612e31740.
Closes https://github.com/facebook/rocksdb/pull/3299

Differential Revision: D6612479

Pulled By: ajkr

fbshipit-source-id: 6263ed7c1602f249460421825c76b5721f396163
2018-01-03 12:41:37 -08:00
Adam Retter 00e5e1ef7f Fixes the build on Windows
Summary:
As discovered during v5.9.2 release, and forward-ported.
Closes https://github.com/facebook/rocksdb/pull/3323

Differential Revision: D6657209

Pulled By: siying

fbshipit-source-id: b560d9f8ddb89e0ffaff7c895ec80f68ddf7dab4
2018-01-03 12:27:12 -08:00
Siying Dong ccc095a016 Speed up BlockTest.BlockReadAmpBitmap
Summary:
BlockTest.BlockReadAmpBitmap is too slow and times out in some environments. Speed it up by:
(1) improve the way the verification is done. With this it is 5 times faster
(2) run fewer tests for large blocks. This cut it down by another 10 times.
Now it can finish in similar time as other tests.
Closes https://github.com/facebook/rocksdb/pull/3313

Differential Revision: D6643711

Pulled By: siying

fbshipit-source-id: c2397d666eab5421a78ca87e1e45491e0f832a6d
2018-01-02 10:41:28 -08:00
burtonli b5c99cc908 Disable onboard cache for compaction output
Summary:
FILE_FLAG_WRITE_THROUGH is for disabling device on-board cache in windows API, which should be disabled if user doesn't need system cache.
There was a perf issue related with this, we found during memtable flush, the high percentile latency jumps significantly. During profiling, we found those high latency (P99.9) read requests got queue-jumped by write requests from memtable flush and takes 80ms or even more time to wait, even when SSD overall IO throughput is relatively low.

After enabling FILE_FLAG_WRITE_THROUGH, we rerun the test found high percentile latency drops a lot without observable impact on writes.

Scenario 1: 40MB/s + 40MB/s  R/W compaction throughput

 Original | FILE_FLAG_WRITE_THROUGH | Percentage reduction
---------------------------------------------------------------
P99.9 | 56.897 ms | 35.593 ms | -37.4%
P99 | 3.905 ms | 3.896 ms | -2.8%

Scenario 2:  14MB/s + 14MB/s R/W compaction throughput, cohosted with 100+ other rocksdb instances have manually triggered memtable flush operations (memtable is tiny), creating a lot of randomized the small file writes operations during test.

Original | FILE_FLAG_WRITE_THROUGH | Percentage reduction
---------------------------------------------------------------
P99.9 | 86.227   ms | 50.436 ms | -41.5%
P99 | 8.415   ms | 3.356 ms | -60.1%
Closes https://github.com/facebook/rocksdb/pull/3225

Differential Revision: D6624174

Pulled By: miasantreble

fbshipit-source-id: 321b86aee9d74470840c70e5d0d4fa9880660a91
2017-12-21 18:41:34 -08:00
Andrew Kryczka f00e176c5b fix ForwardIterator reference to temporary object
Summary:
Fixes the following ASAN error:

```
==2108042==ERROR: AddressSanitizer: stack-use-after-scope on address 0x7fc50ae9b868 at pc 0x7fc5112aff55 bp 0x7fff9eb9dc10 sp 0x7fff9eb9dc08
=== How to use this, how to get the raw stack trace, and more: fburl.com/ASAN ===
READ of size 8 at 0x7fc50ae9b868 thread T0
SCARINESS: 23 (8-byte-read-stack-use-after-scope)
     #0 rocksdb/dbformat.h:164                   rocksdb::InternalKeyComparator::user_comparator() const
     #1 librocksdb_src_rocksdb_lib.so+0x1429a7d  rocksdb::RangeDelAggregator::InitRep(std::vector<...> const&)
     #2 librocksdb_src_rocksdb_lib.so+0x142ceae  rocksdb::RangeDelAggregator::AddTombstones(std::unique_ptr<...>)
     #3 librocksdb_src_rocksdb_lib.so+0x1382d88  rocksdb::ForwardIterator::RebuildIterators(bool)
     #4 librocksdb_src_rocksdb_lib.so+0x1382362  rocksdb::ForwardIterator::ForwardIterator(rocksdb::DBImpl*, rocksdb::ReadOptions const&, rocksdb::ColumnFamilyData*, rocksdb::SuperVersion*)
     #5 librocksdb_src_rocksdb_lib.so+0x11f433f  rocksdb::DBImpl::NewIterator(rocksdb::ReadOptions const&, rocksdb::ColumnFamilyHandle*)
     #6 rocksdb/src/include/rocksdb/db.h:382     rocksdb::DB::NewIterator(rocksdb::ReadOptions const&)
     #7 rocksdb/db_range_del_test.cc:807         rocksdb::DBRangeDelTest_TailingIteratorRangeTombstoneUnsupported_Test::TestBody()
    #18 rocksdb/db_range_del_test.cc:1006        main

Address 0x7fc50ae9b868 is located in stack of thread T0 at offset 104 in frame
     #0 librocksdb_src_rocksdb_lib.so+0x13825af  rocksdb::ForwardIterator::RebuildIterators(bool)
```
Closes https://github.com/facebook/rocksdb/pull/3300

Differential Revision: D6612989

Pulled By: ajkr

fbshipit-source-id: e7ea2ed914c1b80a8a29d71d92440a6bd9cbcc80
2017-12-20 16:12:04 -08:00
Maysam Yabandeh 02a2c11732 Blog post for WritePrepared Txn
Summary:
Blog post to introduce the next generation of transaction engine at RocksDB.
Closes https://github.com/facebook/rocksdb/pull/3296

Differential Revision: D6612932

Pulled By: maysamyabandeh

fbshipit-source-id: 5bfa91ce84e937f5e4346bbda5a4725d0a7fd131
2017-12-20 11:42:15 -08:00
Maysam Yabandeh 0ef3fdd732 Disable need_log_sync on bg err
Summary:
When there is a background error PreprocessWrite returns without marking the logs synced. If we keep need_log_sync to true, it would try to sync them at the end, which would break the logic. The patch would unset need_log_sync if the logs end up not being marked for sync in PreprocessWrite.
Closes https://github.com/facebook/rocksdb/pull/3293

Differential Revision: D6602347

Pulled By: maysamyabandeh

fbshipit-source-id: 37ee04209e8dcfd78de891654ce50d0954abeb38
2017-12-20 08:12:24 -08:00
Wouter Beek 58b841b356 FIXED: string buffers potentially too small to fit formatted write
Summary:
This fixes the following warnings when compiled with GCC7:

util/transaction_test_util.cc: In static member function ‘static rocksdb::Status rocksdb::RandomTransactionInserter::DBGet(rocksdb::DB*, rocksdb::Transaction*, rocksdb::ReadOptions&, uint16_t, uint64_t, bool, uint64_t*, std::__cxx11::string*, bool*)’:
util/transaction_test_util.cc:75:8: error: ‘snprintf’ output may be truncated before the last format character [-Werror=format-truncation=]
 Status RandomTransactionInserter::DBGet(
        ^~~~~~~~~~~~~~~~~~~~~~~~~
util/transaction_test_util.cc:84:11: note: ‘snprintf’ output between 5 and 6 bytes into a destination of size 5
   snprintf(prefix_buf, sizeof(prefix_buf), "%.4u", set_i + 1);
   ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
util/transaction_test_util.cc: In static member function ‘static rocksdb::Status rocksdb::RandomTransactionInserter::Verify(rocksdb::DB*, uint16_t, uint64_t, bool, rocksdb::Random64*)’:
util/transaction_test_util.cc:245:8: error: ‘snprintf’ output may be truncated before the last format character [-Werror=format-truncation=]
 Status RandomTransactionInserter::Verify(DB* db, uint16_t num_sets,
        ^~~~~~~~~~~~~~~~~~~~~~~~~
util/transaction_test_util.cc:268:13: note: ‘snprintf’ output between 5 and 6 bytes into a destination of size 5
     snprintf(prefix_buf, sizeof(prefix_buf), "%.4u", set_i + 1);
     ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Closes https://github.com/facebook/rocksdb/pull/3295

Differential Revision: D6609411

Pulled By: maysamyabandeh

fbshipit-source-id: 33f0add471056eb59db2f8bd4366e6dfbb1a187d
2017-12-20 08:12:22 -08:00
yingsu00 f54d7f5fea Port 3 way SSE4.2 crc32c implementation from Folly
Summary:
**# Summary**

RocksDB uses SSE crc32 intrinsics to calculate the crc32 values but it does it in single way fashion (not pipelined on single CPU core). Intel's whitepaper () published an algorithm that uses 3-way pipelining for the crc32 intrinsics, then use pclmulqdq intrinsic to combine the values. Because pclmulqdq has overhead on its own, this algorithm will show perf gains on buffers larger than 216 bytes, which makes RocksDB a perfect user, since most of the buffers RocksDB call crc32c on is over 4KB. Initial db_bench show tremendous CPU gain.

This change uses the 3-way SSE algorithm by default. The old SSE algorithm is now behind a compiler tag NO_THREEWAY_CRC32C. If user compiles the code with NO_THREEWAY_CRC32C=1 then the old SSE Crc32c algorithm would be used. If the server does not have SSE4.2 at the run time the slow way (Non SSE) will be used.

**# Performance Test Results**
We ran the FillRandom and ReadRandom benchmarks in db_bench. ReadRandom is the point of interest here since it calculates the CRC32 for the in-mem buffers. We did 3 runs for each algorithm.

Before this change the CRC32 value computation takes about 11.5% of total CPU cost, and with the new 3-way algorithm it reduced to around 4.5%. The overall throughput also improved from 25.53MB/s to 27.63MB/s.

1) ReadRandom in db_bench overall metrics

    PER RUN
    Algorithm | run | micros/op | ops/sec |Throughput (MB/s)
    3-way      |  1   | 4.143   | 241387 | 26.7
    3-way      |  2   | 3.775   | 264872 | 29.3
    3-way      | 3    | 4.116   | 242929 | 26.9
    FastCrc32c|1  | 4.037   | 247727 | 27.4
    FastCrc32c|2  | 4.648   | 215166 | 23.8
    FastCrc32c|3  | 4.352   | 229799 | 25.4

     AVG
    Algorithm     |    Average of micros/op |   Average of ops/sec |    Average of Throughput (MB/s)
    3-way           |     4.01                               |      249,729                 |      27.63
    FastCrc32c  |     4.35                              |     230,897                  |      25.53

 2)   Crc32c computation CPU cost (inclusive samples percentage)
    PER RUN
    Implementation | run |  TotalSamples   | Crc32c percentage
    3-way                 |  1    |  4,572,250,000 | 4.37%
    3-way                 |  2    |  3,779,250,000 | 4.62%
    3-way                 |  3    |  4,129,500,000 | 4.48%
    FastCrc32c       |  1    |  4,663,500,000 | 11.24%
    FastCrc32c       |  2    |  4,047,500,000 | 12.34%
    FastCrc32c       |  3    |  4,366,750,000 | 11.68%

 **# Test Plan**
     make -j64 corruption_test && ./corruption_test
      By default it uses 3-way SSE algorithm

     NO_THREEWAY_CRC32C=1 make -j64 corruption_test && ./corruption_test

    make clean && DEBUG_LEVEL=0 make -j64 db_bench
    make clean && DEBUG_LEVEL=0 NO_THREEWAY_CRC32C=1 make -j64 db_bench
Closes https://github.com/facebook/rocksdb/pull/3173

Differential Revision: D6330882

Pulled By: yingsu00

fbshipit-source-id: 8ec3d89719533b63b536a736663ca6f0dd4482e9
2017-12-19 18:26:49 -08:00
Yi Wu e763e1b623 BlobDB: dump blob db options on open
Summary:
We dump blob db options on blob db open, but it was removed by mistake in #3246. Adding it back.
Closes https://github.com/facebook/rocksdb/pull/3298

Differential Revision: D6607177

Pulled By: yiwu-arbug

fbshipit-source-id: 2a4aacbfa52fd8f1878dc9e1fbb95fe48faf80c0
2017-12-19 16:57:12 -08:00
Yi Wu 48cf8da2bb BlobDB: update blob_db_options.bytes_per_sync behavior
Summary:
Previously, if blob_db_options.bytes_per_sync, there is a background job to call fsync() for every bytes_per_sync bytes written to a blob file. With the change we simply pass bytes_per_sync as env_options_ to blob files so that sync_file_range() will be used instead.
Closes https://github.com/facebook/rocksdb/pull/3297

Differential Revision: D6606994

Pulled By: yiwu-arbug

fbshipit-source-id: 452424be52e32ba92f5ea603b564e9b88929af47
2017-12-19 16:41:41 -08:00
Yi Wu 06149429d9 WritePrepared Txn: Return NotSupported on iterator refresh
Summary:
A proper implementation of Iterator::Refresh() for WritePreparedTxnDB would require release and acquire another snapshot. Since MyRocks don't make use of Iterator::Refresh(), we just simply mark it as not supported.
Closes https://github.com/facebook/rocksdb/pull/3290

Differential Revision: D6599931

Pulled By: yiwu-arbug

fbshipit-source-id: 4e1632d967316431424f6e458254ecf9a97567cf
2017-12-18 22:29:30 -08:00
Andrew Kryczka 1563801bce blog post for auto-tuned rate limiter
Summary:
Wrote the blog post.
Closes https://github.com/facebook/rocksdb/pull/3289

Differential Revision: D6599031

Pulled By: ajkr

fbshipit-source-id: 77ee553196f225f20c56112d2c015b6fa14f1b83
2017-12-18 17:56:50 -08:00
Yi Wu 2190e96727 Remove incorrect comment
Summary:
We actually create individual compaction filter from compaction filter factory per sub-compaction in `CompactionJob::ProcessKeyValueCompaction`: https://github.com/facebook/rocksdb/blob/master/db/compaction_job.cc#L742
The comment seems incorrect.
Closes https://github.com/facebook/rocksdb/pull/3288

Differential Revision: D6598455

Pulled By: yiwu-arbug

fbshipit-source-id: a6bc059a9103b87a73ae6ec4bb01ca33f5d48cf5
2017-12-18 17:56:47 -08:00
Maysam Yabandeh 0faa026db6 WritePrepared Txn: make buck tests parallel
Summary:
The TSAN version of tests could take quite long. Make the buck tests parallel to avoid timeouts.
Closes https://github.com/facebook/rocksdb/pull/3280

Differential Revision: D6581594

Pulled By: maysamyabandeh

fbshipit-source-id: 3f8476d8c69f0183e394fa8a2089dd8d4e90c90c
2017-12-18 14:42:09 -08:00
Maysam Yabandeh 78c2eedb4f fix release order in validateNumberOfEntries
Summary:
ScopedArenaIterator should be defined after range_del_agg so that it destructs the assigned iterator, which depends on range_del_agg, before it range_del_agg is already destructed.
Closes https://github.com/facebook/rocksdb/pull/3281

Differential Revision: D6592332

Pulled By: maysamyabandeh

fbshipit-source-id: 89a15d8ed13d0fc856b0c47dce3d91778738dbac
2017-12-18 14:27:28 -08:00
Guo Xiao aa6509d8e4 Fix build for linux
Summary:
* Include `unistd.h` for `sleep(3)`
* Include `sys/time.h` for `gettimeofday(3)`
* Include `utils/random.h` for `Random64`

Error messages:

utilities/persistent_cache/hash_table_bench.cc: In constructor ‘rocksdb::HashTableBenchmark::HashTableBenchmark(rocksdb::HashTableImpl<long unsigned int, std::__cxx11::basic_string<char> >*, size_t, size_t, size_t, size_t)’:
utilities/persistent_cache/hash_table_bench.cc:76:28: error: ‘sleep’ was not declared in this scope
       /* sleep override */ sleep(1);
                            ^~~~~
utilities/persistent_cache/hash_table_bench.cc:76:28: note: suggested alternative: ‘strsep’
       /* sleep override */ sleep(1);
                            ^~~~~
                            strsep
utilities/persistent_cache/hash_table_bench.cc: In member function ‘void rocksdb::HashTableBenchmark::RunRead()’:
utilities/persistent_cache/hash_table_bench.cc:107:5: error: ‘Random64’ was not declared in this scope
     Random64 rgen(time(nullptr));
     ^~~~~~~~
utilities/persistent_cache/hash_table_bench.cc:107:5: note: suggested alternative: ‘random_r’
     Random64 rgen(time(nullptr));
     ^~~~~~~~
     random_r
utilities/persistent_cache/hash_table_bench.cc:110:18: error: ‘rgen’ was not declared in this scope
       size_t k = rgen.Next() % max_prepop_key;
                  ^~~~
utilities/persistent_cache/hash_table_bench.cc: In static member function ‘static uint64_t rocksdb::HashTableBenchmark::NowInMillSec()’:
utilities/persistent_cache/hash_table_bench.cc:153:5: error: ‘gettimeofday’ was not declared in this scope
     gettimeofday(&tv, /*tz=*/nullptr);
     ^~~~~~~~~~~~
make[2]: *** [CMakeFiles/hash_table_bench.dir/build.make:63: CMakeFiles/hash_table_bench.dir/utilities/persistent_cache/hash_table_bench.cc.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:3346: CMakeFiles/hash_table_bench.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
Closes https://github.com/facebook/rocksdb/pull/3283

Differential Revision: D6594850

Pulled By: ajkr

fbshipit-source-id: fd83957338c210cdfd253763347aafd39476824f
2017-12-18 12:28:03 -08:00
Maysam Yabandeh a6d3c762df WritePrepared Txn: non-2pc write in one round
Summary:
Currently non-2pc writes do the 2nd dummy write to actually commit the transaction. This was necessary to ensure that publishing the commit sequence number will be done only from one queue (the queue that does not write to memtable). This is however not necessary when we have only one write queue, which is actually the setup that would be used by non-2pc writes. This patch eliminates the 2nd write when two_write_queues are disabled by updating the commit map in the 1st write.
Closes https://github.com/facebook/rocksdb/pull/3277

Differential Revision: D6575392

Pulled By: maysamyabandeh

fbshipit-source-id: 8ab458f7ca506905962f9166026b2ec81e749c46
2017-12-18 08:19:43 -08:00
Anand Ananthabhotla fccc12f386 Add a histogram stat for memtable flush
Summary:
Add a new histogram stat called rocksdb.db.flush.micros for memtable
flush
Closes https://github.com/facebook/rocksdb/pull/3269

Differential Revision: D6559496

Pulled By: anand1976

fbshipit-source-id: f5c771ba2568630458751795e8c37a493ff9b14d
2017-12-15 18:57:00 -08:00
Maysam Yabandeh 95583e1532 db_stress: skip snapshot check if cf is dropped
Summary:
We added a new verification that ensures a value that snapshot reads when is released is the same as when it was created. This test however fails when the cf is dropped in between. The patch skips the tests if that was the case.
Closes https://github.com/facebook/rocksdb/pull/3279

Differential Revision: D6581584

Pulled By: maysamyabandeh

fbshipit-source-id: afe37d371c0f91818d2e279b3949b810e112e8eb
2017-12-15 16:28:04 -08:00
Yi Wu 237b292515 BlobDB: Remove the need to get sequence number per write
Summary:
Previously we store sequence number range of each blob files, and use the sequence number range to check if the file can be possibly visible by a snapshot. But it adds complexity to the code, since the sequence number is only available after a write. (The current implementation get sequence number by calling GetLatestSequenceNumber(), which is wrong.) With the patch, we are not storing sequence number range, and check if snapshot_sequence < obsolete_sequence to decide if the file is visible by a snapshot (previously we check if first_sequence <= snapshot_sequence < obsolete_sequence).
Closes https://github.com/facebook/rocksdb/pull/3274

Differential Revision: D6571497

Pulled By: yiwu-arbug

fbshipit-source-id: ca06479dc1fcd8782f6525b62b7762cd47d61909
2017-12-15 13:27:30 -08:00
Andrew Kryczka a79c7c05e8 fix backup meta-file buffer overrun
Summary:
- check most times after calling snprintf that the buffer didn't fill up. Previously we'd proceed and use `buf_size - len` as the length in subsequent calls, which underflowed as those are unsigned size_t.
- replace some memcpys with snprintf for consistency
Closes https://github.com/facebook/rocksdb/pull/3255

Differential Revision: D6541464

Pulled By: ajkr

fbshipit-source-id: 8610ea6a24f38e0a37c6d17bc65b7c712da6d932
2017-12-15 12:29:16 -08:00
Andrew Kryczka 5a7e08468a fix ThreadStatus for bottom-pri compaction threads
Summary:
added `ThreadType::BOTTOM_PRIORITY` which is used in the `ThreadStatus` object to indicate the thread is used for bottom-pri compactions. Previously there was a bug where we mislabeled such threads as `ThreadType::LOW_PRIORITY`.
Closes https://github.com/facebook/rocksdb/pull/3270

Differential Revision: D6559428

Pulled By: ajkr

fbshipit-source-id: 96b1a50a9c19492b1a5fd1b77cf7061a6f9f1d1c
2017-12-14 14:57:49 -08:00
Orvid King b4d88d7128 Fix the build with MSVC 2017
Summary:
There were a few places where MSVC's implicit truncation warnings were getting triggered, which was causing the MSVC build to fail due to warnings being treated as errors. This resolves the issues by making the truncations in some places explicit, and by making it so there are no truncations of literals.

Fixes #3239
Supersedes #3259
Closes https://github.com/facebook/rocksdb/pull/3273

Reviewed By: yiwu-arbug

Differential Revision: D6569204

Pulled By: Orvid

fbshipit-source-id: c188cf1cf98d9acb6d94b71875041cc81f8ff088
2017-12-14 12:02:22 -08:00
Siying Dong def6a00740 Print out compression type of new SST files in logging
Summary: Closes https://github.com/facebook/rocksdb/pull/3264

Differential Revision: D6552768

Pulled By: siying

fbshipit-source-id: 6303110aff22f341d5cff41f8d2d4f138a53652d
2017-12-14 10:27:43 -08:00
Siying Dong 6b77c07379 NUMBER_BLOCK_COMPRESSED, etc, shouldn't be treated as timer counter
Summary:
NUMBER_BLOCK_DECOMPRESSED and NUMBER_BLOCK_COMPRESSED are not reported unless the stats level contain detailed timers, which is wrong. They are normal counters. Fix it.
Closes https://github.com/facebook/rocksdb/pull/3263

Differential Revision: D6552519

Pulled By: siying

fbshipit-source-id: 40899ccea7b2856bb39752616657c0bfd432f6f9
2017-12-14 10:27:43 -08:00
Maysam Yabandeh cd2e5cae7f WritePrepared Txn: make db_stress transactional
Summary:
Add "--use_txn" option to use transactional API in db_stress, default being WRITE_PREPARED policy, which is the main intention of modifying db_stress. It also extend the existing snapshots to verify that before releasing a snapshot a read from it returns the same value as before.
Closes https://github.com/facebook/rocksdb/pull/3243

Differential Revision: D6556912

Pulled By: maysamyabandeh

fbshipit-source-id: 1ae31465be362d44bd06e635e2e9e49a1da11268
2017-12-13 11:57:29 -08:00
Maysam Yabandeh 546a63272f disableWAL with WriteImplWALOnly
Summary:
Currently WriteImplWALOnly simply returns when disableWAL is set. This is an incorrect behavior since it does not allocated the sequence number, which is a side-effect of writing to the WAL. This patch fixes the issue.
Closes https://github.com/facebook/rocksdb/pull/3262

Differential Revision: D6550974

Pulled By: maysamyabandeh

fbshipit-source-id: 745a83ae8f04e7ca6c8ffb247d6ef16c287c52e7
2017-12-13 07:57:44 -08:00
Maysam Yabandeh 35dfbd58dd WritePrepared Txn: GC old_commit_map_
Summary:
Garbage collect entries from old_commit_map_ when the corresponding snapshots are released.
Closes https://github.com/facebook/rocksdb/pull/3247

Differential Revision: D6528478

Pulled By: maysamyabandeh

fbshipit-source-id: 15d1566d85d4ac07036bc0dc47418f6c3228d4bf
2017-12-13 07:57:43 -08:00
Zhongyi Xie 51c2ea0feb Reduce heavy hitter for Get operation
Summary:
This PR addresses the following heavy hitters in `Get` operation by moving calls to `StatisticsImpl::recordTick` from `BlockBasedTable` to `Version::Get`

- rocksdb.block.cache.bytes.write
- rocksdb.block.cache.add
- rocksdb.block.cache.data.miss
- rocksdb.block.cache.data.bytes.insert
- rocksdb.block.cache.data.add
- rocksdb.block.cache.hit
- rocksdb.block.cache.data.hit
- rocksdb.block.cache.bytes.read

The db_bench statistics before and after the change are:

|1GB block read|Children      |Self  |Command          |Shared Object        |Symbol|
|---|---|---|---|---|---|
|master:     |4.22%     |1.31%  |db_bench  |db_bench  |[.] rocksdb::StatisticsImpl::recordTick|
|updated:    |0.51%     |0.21%  |db_bench  |db_bench  |[.] rocksdb::StatisticsImpl::recordTick|
|     	     |0.14%     |0.14%  |db_bench  |db_bench  |[.] rocksdb::GetContext::record_counters|

|1MB block read|Children      |Self  |Command          |Shared Object        |Symbol|
|---|---|---|---|---|---|
|master:    |3.48%     |1.08%  |db_bench  |db_bench  |[.] rocksdb::StatisticsImpl::recordTick|
|updated:    |0.80%     |0.31%  |db_bench  |db_bench  |[.] rocksdb::StatisticsImpl::recordTick|
|    	     |0.35%     |0.35%  |db_bench  |db_bench  |[.] rocksdb::GetContext::record_counters|
Closes https://github.com/facebook/rocksdb/pull/3172

Differential Revision: D6330532

Pulled By: miasantreble

fbshipit-source-id: 2b492959e00a3db29e9437ecdcc5e48ca4ec5741
2017-12-12 21:11:33 -08:00
Islam AbdelRahman 9089373a01 Fix DeleteScheduler::MarkAsTrash() handling existing trash
Summary:
DeleteScheduler::MarkAsTrash() don't handle existing .trash files correctly
This cause rocksdb to not being able to delete existing .trash files on restart
Closes https://github.com/facebook/rocksdb/pull/3261

Differential Revision: D6548003

Pulled By: IslamAbdelRahman

fbshipit-source-id: c3800639412e587a690062c63076a5a08881e0e6
2017-12-12 18:17:13 -08:00
Yi Wu 7393ef779c Fix BlockFetcher ASAN error
Summary:
Some call sites of BlockFetcher create temporary ReadOptions and pass to BlockFetcher. The temporary object will be gone after BlockFetcher construction but BlockFetcher keep its reference, causing stack-use-after-scope. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3258

Differential Revision: D6547152

Pulled By: yiwu-arbug

fbshipit-source-id: 6b49e9dd46bb72307f5d8f88ea15faacff35b9bc
2017-12-12 12:12:38 -08:00
Souvik Banerjee 4bcb7fb148 Update transaction_test_util.cc
Summary:
Fixes a compile error on gcc 7.2.1 (-Werror=format-truncation=).
Closes https://github.com/facebook/rocksdb/pull/3248

Differential Revision: D6546515

Pulled By: yiwu-arbug

fbshipit-source-id: bd78cca63f2af376faceccb1838d2d4cc9208fef
2017-12-12 12:12:38 -08:00
Yi Wu e3a06f12d2 WritePrepared Txn: fix compaction filter snapshot checks
Summary:
Add snapshot_checker check whenever we need to check sequence against snapshots and decide what to do with an input key. The changes are related to one of:
* compaction filter
* single delete
* delete at bottom level
* merge
Closes https://github.com/facebook/rocksdb/pull/3251

Differential Revision: D6537850

Pulled By: yiwu-arbug

fbshipit-source-id: 3faba40ed5e37779f4a0cb7ae78af9546659c7f2
2017-12-12 11:12:24 -08:00
Siying Dong a9c8d4ef15 Fix memory issue introduced by 2f1a3a4d74
Summary: Closes https://github.com/facebook/rocksdb/pull/3256

Differential Revision: D6541714

Pulled By: siying

fbshipit-source-id: 40efd89b68587a9d58cfe6f4eebd771c2d9f1542
2017-12-11 18:27:28 -08:00
Zhongyi Xie bb5ed4b1d1 exclude DynamicUniversalCompactionOptions from ROCKSDB_LITE
Summary:
since [SetOptions](https://github.com/facebook/rocksdb/blob/master/db/db_impl.cc#L494) is not supported in ROCKSDB_LITE
Right now unit test under lite is broken
Closes https://github.com/facebook/rocksdb/pull/3253

Differential Revision: D6539428

Pulled By: miasantreble

fbshipit-source-id: 13172b8ecbd75682330726498ea198969bc3e637
2017-12-11 16:28:20 -08:00
Siying Dong 0d5692e02b Switch version to 5.10
Summary: Closes https://github.com/facebook/rocksdb/pull/3252

Differential Revision: D6539373

Pulled By: siying

fbshipit-source-id: ce7c3d3fe625852179055295da9cf7bc80755025
2017-12-11 15:42:01 -08:00
Siying Dong 2f1a3a4d74 Refactor ReadBlockContents()
Summary:
Divide ReadBlockContents() to multiple sub-functions. Maintaining the input and intermediate data in a new class BlockFetcher.
I hope in general it makes the code easier to maintain.
Another motivation to do it is to clearly divide the logic before file reading and after file reading. The refactor will help us evaluate how can we make I/O async in the future.
Closes https://github.com/facebook/rocksdb/pull/3244

Differential Revision: D6520983

Pulled By: siying

fbshipit-source-id: 338d90bc0338472d46be7a7682028dc9114b12e9
2017-12-11 15:27:32 -08:00
Yi Wu 9a27ac5d89 Fix drop column family data race
Summary:
A data race is caught by tsan_crash test between compaction and DropColumnFamily:
https://gist.github.com/yiwu-arbug/5a2b4baae05eeb99ae1719b650f30a44 Compaction checks if the column family has been dropped on each key input, while user can issue DropColumnFamily which updates cfd->dropped_, causing the data race. Fixing it by making cfd->dropped_ an atomic.
Closes https://github.com/facebook/rocksdb/pull/3250

Differential Revision: D6535991

Pulled By: yiwu-arbug

fbshipit-source-id: 5571df020beae7fa7db6fff5ad0d598f49962895
2017-12-11 13:57:48 -08:00
Zhongyi Xie fcc8a6574d Make Universal compaction options dynamic
Summary:
Let me know if more test coverage is needed
Closes https://github.com/facebook/rocksdb/pull/3213

Differential Revision: D6457165

Pulled By: miasantreble

fbshipit-source-id: 3f944abff28aa7775237f1c4f61c64ccbad4eea9
2017-12-11 13:27:06 -08:00
Yi Wu 250a51a3f9 BlobDB: refactor DB open logic
Summary:
Refactor BlobDB open logic. List of changes:

Major:
* On reopen, mark blob files found as immutable, do not use them for writing new keys.
* Not to scan the whole file to find file footer. Instead just seek to the end of the file and try to read footer.

Minor:
* Move most of the real logic from blob_db.cc to blob_db_impl.cc.
* Not to hold shared_ptr of event listeners in global maps in blob_db.cc
* Some changes to BlobFile interface.
* Improve logging and error handling.
Closes https://github.com/facebook/rocksdb/pull/3246

Differential Revision: D6526147

Pulled By: yiwu-arbug

fbshipit-source-id: 9dc4cdd63359a2f9b696af817086949da8d06952
2017-12-11 12:12:38 -08:00
Prashant D 6a183d1ae8 Fix coverity issues compaction_job, compaction_picker
Summary:
db/compaction_job.cc:
  ReportStartedCompaction(compaction);

CID 1419863 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member bottommost_level_ is not initialized in this constructor nor in any functions that it calls.

db/compaction_picker_universal.cc:
7struct InputFileInfo {
   	2. uninit_member: Non-static class member level is not initialized in this constructor nor in any functions that it calls.

CID 1405355 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
4. uninit_member: Non-static class member index is not initialized in this constructor nor in any functions that it calls.
 38  InputFileInfo() : f(nullptr) {}

db/dbformat.h:
 ParsedInternalKey()
 84      : sequence(kMaxSequenceNumber)  // Make code analyzer happy

CID 1168095 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member type is not initialized in this constructor nor in any functions that it calls.
 85  {}  // Intentionally left uninitialized (for speed)
Closes https://github.com/facebook/rocksdb/pull/3091

Differential Revision: D6534558

Pulled By: yiwu-arbug

fbshipit-source-id: 5ada975956196d267b3f149386842af71eda7553
2017-12-11 11:57:15 -08:00
Andrew Kryczka e3814a8608 revert fbcode build behavior
Summary: Closes https://github.com/facebook/rocksdb/pull/3242

Differential Revision: D6514255

Pulled By: ajkr

fbshipit-source-id: c39fa8e745866b052649d02bf339e794d77e96a3
2017-12-07 16:12:52 -08:00
Dmitri Smirnov fe608e32ab Fix a race condition in WindowsThread (port::Thread)
Summary:
Fix a race condition when we create a thread and immediately destroy
 This case should be supported.
  What happens is that the thread function needs the Data instance
  to actually run but has no shared ownership and must rely on the
  WindowsThread instance to continue existing.
  To address this we change unique_ptr to shared_ptr and then
  acquire an additional refcount for the threadproc which destroys it
  just before the thread exit.
  We choose to allocate shared_ptr instance on the heap as this allows
  the original thread to continue w/o waiting for the new thread to start
  running.
Closes https://github.com/facebook/rocksdb/pull/3240

Differential Revision: D6511324

Pulled By: yiwu-arbug

fbshipit-source-id: 4633ff7996daf4d287a9fe34f60c1dd28cf4ff36
2017-12-07 13:42:53 -08:00
Prashant D 34aa245dd8 Fix coverity issues version, write_batch
Summary:
db/version_builder.cc:
117        base_vstorage_->InternalComparator();

CID 1351713 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member field level_zero_cmp_.internal_comparator is not initialized in this constructor nor in any functions that it calls.

db/version_edit.h:
145  FdWithKeyRange()
146      : fd(),
147        smallest_key(),
148        largest_key() {

CID 1418254 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member file_metadata is not initialized in this constructor nor in any functions that it calls.
149  }

db/version_set.cc:
120    }

CID 1322789 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
4. uninit_member: Non-static class member curr_file_level_ is not initialized in this constructor nor in any functions that it calls.
121  }

db/write_batch.cc:
 939    assert(cf_mems_);

CID 1419862 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
3. uninit_member: Non-static class member rebuilding_trx_seq_ is not initialized in this constructor nor in any functions that it calls.
 940  }
Closes https://github.com/facebook/rocksdb/pull/3092

Differential Revision: D6505666

Pulled By: yiwu-arbug

fbshipit-source-id: fd2c68948a0280772691a419d72ac7e190951d86
2017-12-07 11:57:36 -08:00
Prashant D baff91c1ad table: Fix coverity issues
Summary:
table/block.cc:
420  }

CID 1396127 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
7. uninit_member: Non-static class member restart_offset_ is not initialized in this constructor nor in any functions that it calls.
421}

table/block_based_table_builder.cc:

CID 1418259 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
7. uninit_member: Non-static class member compressed_cache_key_prefix_size is not initialized in this constructor nor in any functions that it calls.

table/block_based_table_reader.h:
   	3. uninit_member: Non-static class member index_type is not initialized in this constructor nor in any functions that it calls.

CID 1396147 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
5. uninit_member: Non-static class member hash_index_allow_collision is not initialized in this constructor nor in any functions that it calls.
413        global_seqno(kDisableGlobalSequenceNumber) {}
414

table/cuckoo_table_reader.cc:
 55  if (hash_funs == user_props.end()) {
 56    status_ = Status::Corruption("Number of hash functions not found");
   	5. uninit_member: Non-static class member is_last_level_ is not initialized in this constructor nor in any functions that it calls.
   	7. uninit_member: Non-static class member identity_as_first_hash_ is not initialized in this constructor nor in any functions that it calls.
   	9. uninit_member: Non-static class member use_module_hash_ is not initialized in this constructor nor in any functions that it calls.
   	11. uninit_member: Non-static class member num_hash_func_ is not initialized in this constructor nor in any functions that it calls.
   	13. uninit_member: Non-static class member key_length_ is not initialized in this constructor nor in any functions that it calls.
   	15. uninit_member: Non-static class member user_key_length_ is not initialized in this constructor nor in any functions that it calls.
   	17. uninit_member: Non-static class member value_length_ is not initialized in this constructor nor in any functions that it calls.
   	19. uninit_member: Non-static class member bucket_length_ is not initialized in this constructor nor in any functions that it calls.
   	21. uninit_member: Non-static class member cuckoo_block_size_ is not initialized in this constructor nor in any functions that it calls.
   	23. uninit_member: Non-static class member cuckoo_block_bytes_minus_one_ is not initialized in this constructor nor in any functions that it calls.

CID 1322785 (#2 of 2): Uninitialized scalar field (UNINIT_CTOR)
25. uninit_member: Non-static class member table_size_ is not initialized in this constructor nor in any functions that it calls.
 57    return;

table/plain_table_index.h:
   	2. uninit_member: Non-static class member index_size_ is not initialized in this constructor nor in any functions that it calls.

CID 1322801 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
4. uninit_member: Non-static class member sub_index_size_ is not initialized in this constructor nor in any functions that it calls.
128        huge_page_tlb_size_(huge_page_tlb_size) {}
129
Closes https://github.com/facebook/rocksdb/pull/3113

Differential Revision: D6505719

Pulled By: yiwu-arbug

fbshipit-source-id: 38f44d8f9dfefb4c2e25d83b8df25a5201c75618
2017-12-07 11:57:36 -08:00
Andrew Kryczka 2e3a00987e fix ASAN for DeleteFilesInRange test case
Summary:
error message was

```
==3095==ERROR: AddressSanitizer: stack-use-after-scope on address 0x7ffd18216c40 at pc 0x0000005edda1 bp 0x7ffd18215550 sp 0x7ffd18214d00
...
Address 0x7ffd18216c40 is located in stack of thread T0 at offset 1952 in frame
     #0 internal_repo_rocksdb/db_compaction_test.cc:1520 rocksdb::DBCompactionTest_DeleteFileRangeFileEndpointsOverlapBug_Test::TestBody()
```

It was unsafe to have slices referring to the temporary string objects' buffers, as those strings were destroyed before the slices were used. Fixed it by assigning the strings returned by `Key()` to local variables.
Closes https://github.com/facebook/rocksdb/pull/3238

Differential Revision: D6507864

Pulled By: ajkr

fbshipit-source-id: dd07de1a0070c6748c1ab4f3d7bd31f9a81889d0
2017-12-07 11:12:43 -08:00
Yi Wu e1c569c324 Fix clang-analyzer false-positive on ldb_cmd.cc
Summary:
clang-analyzer complaint about db_ being nullptr, but it couldn't be because it checks exec_stats before proceed. Add an assert to get around the false-positive.

Test Plan
`make analyze`
Closes https://github.com/facebook/rocksdb/pull/3236

Differential Revision: D6505417

Pulled By: yiwu-arbug

fbshipit-source-id: e5b65764ea994dd9e4bab3e697b97dc70dc22cab
2017-12-06 22:58:46 -08:00
Sagar Vemuri bbef8c3884 Log GetCurrentTime failures during Flush and Compaction
Summary:
`GetCurrentTime()` is used to populate `creation_time` table property during flushes and compactions. It is safe to ignore `GetCurrentTime()` failures here but they should be logged.

(Note that `creation_time` property was introduced as part of TTL-based FIFO compaction in #2480.)

Tes Plan:
`make check`
Closes https://github.com/facebook/rocksdb/pull/3231

Differential Revision: D6501935

Pulled By: sagar0

fbshipit-source-id: 376adcf4ab801d3a43ec4453894b9a10909c8eb6
2017-12-06 20:56:53 -08:00
Sagar Vemuri d51fcb21f4 Blob DB: Add db_bench options
Summary:
Adding more BlobDB db_bench options which are needed for benchmarking.
Closes https://github.com/facebook/rocksdb/pull/3230

Differential Revision: D6500711

Pulled By: sagar0

fbshipit-source-id: 91d63122905854ef7c9148a0235568719146e6c5
2017-12-06 20:44:12 -08:00
Andrew Kryczka 53a516ab58 update history for recent commits
Summary:
I browsed through the history since 5.9 was released and found some changes worth mentioning in HISTORY.md.
Closes https://github.com/facebook/rocksdb/pull/3237

Differential Revision: D6506472

Pulled By: ajkr

fbshipit-source-id: 627ce9f94ca33df9f0f231a9c5ced3624b05506c
2017-12-06 19:56:17 -08:00
Andrew Kryczka 78d1a5ec72 Preserve overlapping file endpoint invariant
Summary:
Fix for #2833.

- In `DeleteFilesInRange`, use `GetCleanInputsWithinInterval` instead of `GetOverlappingInputs` to make sure we get a clean cut set of files to delete.
- In `GetCleanInputsWithinInterval`, support nullptr as `begin_key` or `end_key`.
- In `GetOverlappingInputsRangeBinarySearch`, move the assertion for non-empty range away from `ExtendFileRangeWithinInterval`, which should be allowed to return an empty range (via `end_index < begin_index`).
Closes https://github.com/facebook/rocksdb/pull/2843

Differential Revision: D5772387

Pulled By: ajkr

fbshipit-source-id: e554e8461823c6be82b21a9262a2da02b3957881
2017-12-06 18:56:54 -08:00
Yi Wu a7d32776f0 Fix write_callback_test compile error
Summary:
Rename shadow variable name db_impl.

Fixing #3227
Closes https://github.com/facebook/rocksdb/pull/3235

Differential Revision: D6504051

Pulled By: yiwu-arbug

fbshipit-source-id: 186c9378dabb11f8d6db56f45c95cc3b029fcb88
2017-12-06 17:12:27 -08:00
Yi Wu 7f04af32a5 ldb to allow db with --try_load_options and without an options file
Summary:
This is to fix tools/check_format_compatible.sh. The tool try to open
old versions of rocksdb with the provided options file. When options
file is missing (e.g. rocksdb 2.2), it should still proceed with default
options.
Closes https://github.com/facebook/rocksdb/pull/3232

Differential Revision: D6503955

Pulled By: yiwu-arbug

fbshipit-source-id: e44cfcce7ddc7d12cf83466ed3f3fe7624aa78b8
2017-12-06 16:42:26 -08:00
Yi Wu b5798bd324 Add missing recent versions to format compatible test
Summary:
Add recent versions for format compatible test. We should probably update the script to auto include available versions (by looking at include/rocksdb/versions.h and deduce branch names), but we can do it later.
Closes https://github.com/facebook/rocksdb/pull/3233

Differential Revision: D6503631

Pulled By: yiwu-arbug

fbshipit-source-id: e2b01d1ef6e784ff6ffa1bd75d741755e3c69a8c
2017-12-06 16:13:50 -08:00
Yi Wu 20995c5729 Make iterator invalid on Merge error
Summary:
Since #1665, on merge error, iterator will be set to corrupted status, but it doesn't invalidate the iterator. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3226

Differential Revision: D6499094

Pulled By: yiwu-arbug

fbshipit-source-id: 80222930f949e31f90a6feaa37ddc3529b510d2c
2017-12-06 11:56:39 -08:00
Maysam Yabandeh 36911f55dd WritePrepared Txn: stress test
Summary:
Augment the existing MySQLStyleTransactionTest to check for more core case scenarios. The changes showed effective in revealing the bugs reported in https://github.com/facebook/rocksdb/pull/3205 and https://github.com/facebook/rocksdb/pull/3101
Closes https://github.com/facebook/rocksdb/pull/3222

Differential Revision: D6476862

Pulled By: maysamyabandeh

fbshipit-source-id: 5068497702d67ffc206a58ed96f8578fbb510137
2017-12-06 09:42:28 -08:00
Flarnie Marchan 1b0c58d7e7 Add Code of Conduct
Summary:
In the past Facebook didn't promote including a Code of Conduct when creating new projects, and many projects skipped this important document. Let's fix it. :)

**why make this change?:**
Facebook Open Source provides a Code of Conduct statement for all
projects to follow, to promote a welcoming and safe open source community.

Exposing the COC via a separate markdown file is a standard being
promoted by Github via the Community Profile in order to meet their Open
Source Guide's recommended community standards.

As you can see, adding this file will improve [the rocksdb community profile](https://github.com/facebook/rocksdb/community)
checklist and increase the visibility of our COC.

**test plan:**
Viewing it on my branch -
<img width="1008" alt="screen shot 2017-12-03 at 5 05 45 pm" src="https://user-images.githubusercontent.com/1114467/33532198-66012a56-d84c-11e7-8fab-29ed410bd600.png">
<img width="1015" alt="screen shot 2017-12-03 at 5 05 59 pm" src="https://user-images.githubusercontent.com/1114467/33532199-661813d8-d84c-11e7-941e-94754dd481e5.png">

**issue:**
internal task t23481323
Closes https://github.com/facebook/rocksdb/pull/3219

Reviewed By: yiwu-arbug

Differential Revision: D6494234

Pulled By: flarnie

fbshipit-source-id: 55b59db335cc5546f3a1c968322b9281a3dc3aaf
2017-12-05 18:42:35 -08:00
Adam Novak a37d734596 Add ROCKSDB_DISABLE_* environment variables
Summary:
Should fix #3036.
Closes https://github.com/facebook/rocksdb/pull/3042

Differential Revision: D6452921

Pulled By: sagar0

fbshipit-source-id: eaf11e43fee1f8747006530cfc0c7a358f1c2f0f
2017-12-05 15:12:46 -08:00
Alex Robinson 4634c735a8 Update DBOptions::IncreaseParallelism to use newer background settings
Summary:
The Options header file recommends using max_background_jobs rather than
directly setting max_background_compactions or max_background_flushes.

I've personally seen a performance problem where stalls were happening
because the one background flushing thread was blocked that was fixed
by this change -
https://github.com/cockroachdb/cockroach/issues/19699#issuecomment-347672485
Closes https://github.com/facebook/rocksdb/pull/3208

Differential Revision: D6473178

Pulled By: ajkr

fbshipit-source-id: 67c892ceb7b1909d251492640cb15a0f2262b7ed
2017-12-04 01:56:15 -08:00
Andrew Kryczka 57056bb606 gflags in cmake on linux
Summary:
We should use it if available otherwise the tools builds never work. Thanks to #3212, we can set -DGFLAGS=1 and it'll be independent of the namespace with which gflags was compiled.
Closes https://github.com/facebook/rocksdb/pull/3214

Differential Revision: D6462214

Pulled By: ajkr

fbshipit-source-id: db4e5f1b905322e3119554a9d01b57532c499384
2017-12-01 18:28:24 -08:00
Andrew Kryczka 63f1c0a57d fix gflags namespace
Summary:
I started adding gflags support for cmake on linux and got frustrated that I'd need to duplicate the build_detect_platform logic, which determines namespace based on attempting compilation. We can do it differently -- use the GFLAGS_NAMESPACE macro if available, and if not, that indicates it's an old gflags version without configurable namespace so we can simply hardcode "google".
Closes https://github.com/facebook/rocksdb/pull/3212

Differential Revision: D6456973

Pulled By: ajkr

fbshipit-source-id: 3e6d5bde3ca00d4496a120a7caf4687399f5d656
2017-12-01 10:42:05 -08:00
Maysam Yabandeh 18dcf7f98d WritePrepared Txn: PreReleaseCallback
Summary:
Add PreReleaseCallback to be called at the end of WriteImpl but before publishing the sequence number. The callback is used in WritePrepareTxn to i) update the commit map, ii) update the last published sequence number in the 2nd write queue. It also ensures that all the commits will go to the 2nd queue.
These changes will ensure that the commit map is updated before the sequence number is published and used by reading snapshots. If we use two write queues, the snapshots will use the seq number published by the 2nd queue. If we use one write queue (the default, the snapshots will use the last seq number in the memtable, which also indicates the last published seq number.
Closes https://github.com/facebook/rocksdb/pull/3205

Differential Revision: D6438959

Pulled By: maysamyabandeh

fbshipit-source-id: f8b6c434e94bc5f5ab9cb696879d4c23e2577ab9
2017-11-30 23:50:45 -08:00
Nikhil Benesch 3e40a5e832 add missing config checks to CMakeLists.txt
Summary:
Bring CMakeLists.txt back up to parity with build_detect_platform.
Closes https://github.com/facebook/rocksdb/pull/3211

Differential Revision: D6452908

Pulled By: ajkr

fbshipit-source-id: 93f5f336ad7eff6ecf65dec47bfaf114dd24cfb2
2017-11-30 22:57:00 -08:00
Andres Suarez fad14050ae Remove import use from TARGETS
Summary:
We're moving away from `import`. The equivalent internal construct that
gets the directory from `fbcode/` is `package_name()`. This is a
Skylark friendly wrapper around [`get_base_path`].

The additional whitespace change is from running `python ./buckifier/buckify_rocksdb.py`.

[`get_base_path`]: https://buckbuild.com/function/get_base_path.html
Closes https://github.com/facebook/rocksdb/pull/3210

Reviewed By: yiwu-arbug

Differential Revision: D6451242

Pulled By: zertosh

fbshipit-source-id: 445757261de0ec89d5d332c1ba9af097086326dc
2017-11-30 15:27:34 -08:00
Yi Wu 54095d3389 TARGETS file not include tests in opt mode
Summary:
Do not build the tests in opt mode, since SyncPoint and other test code will not be included.
Closes https://github.com/facebook/rocksdb/pull/3204

Differential Revision: D6431154

Pulled By: yiwu-arbug

fbshipit-source-id: c404ef042c1a6f679e5c1dc57600b3d8cb52fc28
2017-11-30 10:56:58 -08:00
zhangjinpeng1987 ffacaaa3ea fix Seek with lower_bound
Summary:
When Seek a key less than `lower_bound`, should return `lower_bound`.
ajkr PTAL
Closes https://github.com/facebook/rocksdb/pull/3199

Differential Revision: D6421126

Pulled By: ajkr

fbshipit-source-id: a06c825830573e0040630704f6bcb3f7f48626f7
2017-11-29 22:56:29 -08:00
Andrew Kryczka ed3af9ef99 improve ldb CLI option support
Summary:
- Made CLI arguments take precedence over options file when both are provided. Note some of the CLI args are not settable via options file, like `--compression_max_dict_bytes`, so it's necessary to allow both ways of providing options simultaneously.
- Changed `PrepareOptionsForOpenDB` to update the proper `ColumnFamilyOptions` if one exists for the user's `--column_family_name` argument. I supported this only in the base class, `LDBCommand`, so it works for the general arguments. Will defer adding support for subcommand-specific arguments.
- Made the command fail if `--try_load_options` is provided and loading options file returns NotFound. I found the previous behavior of silently continuing confusing.
Closes https://github.com/facebook/rocksdb/pull/3144

Differential Revision: D6270544

Pulled By: ajkr

fbshipit-source-id: 7c2eac9f9b38720523d74466fb9e78db53561367
2017-11-28 17:28:58 -08:00
Andrew Kryczka c85f8ccca3 convert null terminator in ascii dump
Summary:
The ASCII output is almost always useless to me as the first '\0' byte in the key or value causes it to stop printing. Since all characters are already surrounded by spaces, "\ 0" (how we display a backslash followed by a zero) and "\0" (how this PR displays a null terminator) are distinguishable. My assumption is the value of seeing all the bytes outweighs the value of the alignment we had before, where we always had one character followed by one space.
Closes https://github.com/facebook/rocksdb/pull/3203

Differential Revision: D6428651

Pulled By: ajkr

fbshipit-source-id: aafc978a51e9ea029cfe3e763e2bb0e1751b9ccf
2017-11-28 17:28:58 -08:00
Prashant D c1ed005a21 tools: Fix coverity issues
Summary:
tools/ldb_cmd.cc:
```
310  ignore_unknown_options_ = IsFlagPresent(flags, ARG_IGNORE_UNKNOWN_OPTIONS);

CID 1322798 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
5. uninit_member: Non-static class member db_ttl_ is not initialized in this constructor nor in any functions that it calls.
311}
```
Closes https://github.com/facebook/rocksdb/pull/3122

Differential Revision: D6428576

Pulled By: sagar0

fbshipit-source-id: d77f04dd201f7f1d9f59ef88a215ee7ad7b934e9
2017-11-28 15:27:41 -08:00
Prashant D 81cf262ff5 utilities/backupable : Fix coverity issues
Summary:
1. Class BackupMeta
```
52      : timestamp_(0), size_(0), meta_filename_(meta_filename),

CID 1168103 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member sequence_number_ is not initialized in this constructor nor in any functions that it calls.
153        file_infos_(file_infos), env_(env) {}
```
2. class BackupEngineImpl
```
513  }
        7. uninit_member: Non-static class member latest_backup_id_ is not initialized in this constructor nor in any functions that it calls.

CID 1322803 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
9. uninit_member: Non-static class member latest_valid_backup_id_ is not initialized in this constructor nor in any functions that it calls.
514}
```
3. struct BackupAfterCopyOrCreateWorkItem
```
368  struct BackupAfterCopyOrCreateWorkItem {
369    std::future<CopyOrCreateResult> result;
        1. member_decl: Class member declaration for shared.
370    bool shared;
        3. member_decl: Class member declaration for needed_to_copy.
371    bool needed_to_copy;
        5. member_decl: Class member declaration for backup_env.
372    Env* backup_env;
373    std::string dst_path_tmp;
374    std::string dst_path;
375    std::string dst_relative;
        2. uninit_member: Non-static class member shared is not initialized in this constructor nor in any functions that it calls.
        4. uninit_member: Non-static class member needed_to_copy is not initialized in this constructor nor in any functions that it calls.

CID 1396122 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
6. uninit_member: Non-static class member backup_env is not initialized in this constructor nor in any functions that it calls.
376    BackupAfterCopyOrCreateWorkItem() {}
```
4. struct CopyOrCreateWorkItem
```
318  struct CopyOrCreateWorkItem {
319    std::string src_path;
320    std::string dst_path;
321    std::string contents;
        1. member_decl: Class member declaration for src_env.
322    Env* src_env;
        3. member_decl: Class member declaration for dst_env.
323    Env* dst_env;
        5. member_decl: Class member declaration for sync.
324    bool sync;
        7. member_decl: Class member declaration for rate_limiter.
325    RateLimiter* rate_limiter;
        9. member_decl: Class member declaration for size_limit.
326    uint64_t size_limit;
327    std::promise<CopyOrCreateResult> result;
328    std::function<void()> progress_callback;
329
        2. uninit_member: Non-static class member src_env is not initialized in this constructor nor in any functions that it calls.
        4. uninit_member: Non-static class member dst_env is not initialized in this constructor nor in any functions that it calls.
        6. uninit_member: Non-static class member sync is not initialized in this constructor nor in any functions that it calls.
        8. uninit_member: Non-static class member rate_limiter is not initialized in this constructor nor in any functions that it calls.

CID 1396123 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
10. uninit_member: Non-static class member size_limit is not initialized in this constructor nor in any functions that it calls.
330    CopyOrCreateWorkItem() {}
```
5. struct RestoreAfterCopyOrCreateWorkItem
```
struct RestoreAfterCopyOrCreateWorkItem {
410    std::future<CopyOrCreateResult> result;
        1. member_decl: Class member declaration for checksum_value.
411    uint32_t checksum_value;

CID 1396153 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member checksum_value is not initialized in this constructor nor in any functions that it calls.
412    RestoreAfterCopyOrCreateWorkItem() {}
```
Closes https://github.com/facebook/rocksdb/pull/3131

Differential Revision: D6428556

Pulled By: sagar0

fbshipit-source-id: a86675444543eff028e3cae6942197a143a112c4
2017-11-28 14:43:28 -08:00
kapitan-k 75d57a5d53 C API: Add some block based table options
Summary: Closes https://github.com/facebook/rocksdb/pull/3159

Differential Revision: D6428220

Pulled By: sagar0

fbshipit-source-id: 60508d09b5281f54b907a1c40e9631fc08343131
2017-11-28 14:12:44 -08:00
Prashant D b45fbc1175 utilities: Fix coverity issues
Summary:
```
utilities/persistent_cache/block_cache_tier_file.cc
64struct CacheRecordHeader {
   	2. uninit_member: Non-static class member magic_ is not initialized in this constructor nor in any functions that it calls.
   	4. uninit_member: Non-static class member crc_ is not initialized in this constructor nor in any functions that it calls.
   	6. uninit_member: Non-static class member key_size_ is not initialized in this constructor nor in any functions that it calls.

CID 1396161 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
8. uninit_member: Non-static class member val_size_ is not initialized in this constructor nor in any functions that it calls.
 65  CacheRecordHeader() {}
 66  CacheRecordHeader(const uint32_t magic, const uint32_t key_size,
 67                    const uint32_t val_size)
 68      : magic_(magic), crc_(0), key_size_(key_size), val_size_(val_size) {}
 69
   	1. member_decl: Class member declaration for magic_.
 70  uint32_t magic_;
   	3. member_decl: Class member declaration for crc_.
 71  uint32_t crc_;
   	5. member_decl: Class member declaration for key_size_.
 72  uint32_t key_size_;
   	7. member_decl: Class member declaration for val_size_.
 73  uint32_t val_size_;
 74};

utilities/simulator_cache/sim_cache.cc:
157        miss_times_(0),

CID 1396124 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member stats_ is not initialized in this constructor nor in any functions that it calls.
158        hit_times_(0) {}
159
```
Closes https://github.com/facebook/rocksdb/pull/3155

Differential Revision: D6427237

Pulled By: sagar0

fbshipit-source-id: 97e493da5fc043c5b9a3e0d33103442cffb75aad
2017-11-28 13:27:08 -08:00
Prashant D 7b57510a17 utilities: Fix coverity issues in blob_db and col_buf_decoder
Summary:
utilities/blob_db/blob_db_impl.cc
265                    : bdb_options_.blob_dir;
   	3. uninit_member: Non-static class member env_ is not initialized in this constructor nor in any functions that it calls.
   	5. uninit_member: Non-static class member ttl_extractor_ is not initialized in this constructor nor in any functions that it calls.
   	7. uninit_member: Non-static class member open_p1_done_ is not initialized in this constructor nor in any functions that it calls.

CID 1418245 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
9. uninit_member: Non-static class member debug_level_ is not initialized in this constructor nor in any functions that it calls.
266}

   	4. past_the_end: Function end creates an iterator.

CID 1418258 (#1 of 1): Using invalid iterator (INVALIDATE_ITERATOR)
5. deref_iterator: Dereferencing iterator file_nums.end() though it is already past the end of its container.

utilities/col_buf_decoder.h:
     nullable_(nullable),
   	2. uninit_member: Non-static class member remain_runs_ is not initialized in this constructor nor in any functions that it calls.
   	4. uninit_member: Non-static class member run_val_ is not initialized in this constructor nor in any functions that it calls.

CID 1396134 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
6. uninit_member: Non-static class member last_val_ is not initialized in this constructor nor in any functions that it calls.
 46        big_endian_(big_endian) {}
Closes https://github.com/facebook/rocksdb/pull/3134

Differential Revision: D6340607

Pulled By: sagar0

fbshipit-source-id: 25c52566e2ff979fe6c7abb0f40c27fc16597054
2017-11-28 12:27:57 -08:00
Tamir Duberstein cf0d6aa007 CMake cross platform Java support and add JNI to travis
Summary:
Rewrite `java/CMakeLists.txt` to take advantage of CMake's cross platform
Java support.

adamretter
Closes https://github.com/facebook/rocksdb/pull/2301

Differential Revision: D5070724

Pulled By: sagar0

fbshipit-source-id: 999aee9bd39da2b24a5fe493a2eb0e9af6072dc7
2017-11-28 12:27:53 -08:00
Yi Wu 78279350aa Blob DB: Add statistics
Summary:
Adding a list of blob db counters.

Also remove WaStats() which doesn't expose the stats and can be substitute by (BLOB_DB_BYTES_WRITTEN / BLOB_DB_BLOB_FILE_BYTES_WRITTEN).
Closes https://github.com/facebook/rocksdb/pull/3193

Differential Revision: D6394216

Pulled By: yiwu-arbug

fbshipit-source-id: 017508c8ff3fcd7ea7403c64d0f9834b24816803
2017-11-28 11:58:49 -08:00
Yi Wu 3cf562be31 Fix IOError on WAL write doesn't propagate to write group follower
Summary:
This is a simpler version of #3097 by removing all unrelated changes.

Fixing the bug where concurrent writes may get Status::OK while it actually gets IOError on WAL write. This happens when multiple writes form a write batch group, and the leader get an IOError while writing to WAL. The leader failed to pass the error to followers in the group, and the followers end up returning Status::OK() while actually writing nothing. The bug only affect writes in a batch group. Future writes after the batch group will correctly return immediately with the IOError.
Closes https://github.com/facebook/rocksdb/pull/3201

Differential Revision: D6421644

Pulled By: yiwu-arbug

fbshipit-source-id: 1c2a455c5b73f6842423785eb8a9dbfbb191dc0e
2017-11-28 11:42:48 -08:00
Andrew Kryczka 1bdb44de95 optimize file ingestion checks for range deletion overlap
Summary:
Before we were checking every file in the level which was unnecessary. We can piggyback onto the code for checking point-key overlap, which already opens all the files that could possibly contain overlapping range deletions. This PR makes us check just the range deletions from those files, so no extra ones will be opened.
Closes https://github.com/facebook/rocksdb/pull/3179

Differential Revision: D6358125

Pulled By: ajkr

fbshipit-source-id: 00e200770fdb8f3cc6b1b2da232b755e4ba36279
2017-11-28 11:27:02 -08:00
Jeffrey Dallatezza 022c598abb Fix minor typo in comment
Summary:
mean -> meant
Closes https://github.com/facebook/rocksdb/pull/3202

Differential Revision: D6426443

Pulled By: sagar0

fbshipit-source-id: adaf07218580ee6903986fa5686de92f43f420e1
2017-11-28 11:27:02 -08:00
Phani Shekhar Mantripragada 4b65cfc723 Support for block_cache num_shards and other config via option string.
Summary:
Problem: Option string accepts only cache_size as parameter for block_cache which is specified as "block_cache=1M".
It doesn't accept other parameters like num_shards etc.

Changes :
1) ParseBlockBasedTableOption in block_based_table_factory is edited to accept cache options in the format "block_cache=<cache_size>:<num_shard_bits>:<strict_capacity_limit>:<high_pri_pool_ratio>".
Options other than cache_size are optional to maintain backward compatibility. The changes are valid for block_cache_compressed as well.
For example, "block_cache=1M:6:true:0.5", "block_cache=1M:6:true", "block_cache=1M:6" and "block_cache=1M" are all valid option strings.

2) Corresponding unit tests are added.
Closes https://github.com/facebook/rocksdb/pull/3108

Differential Revision: D6420997

Pulled By: sagar0

fbshipit-source-id: cdea8b785688d2802907974af27225ccc1c0cd43
2017-11-28 10:48:53 -08:00
Griffin Smith 2f09524762 Expose all remaining read and write options via the C API
Summary:
Expose read and write options via the C API
Closes https://github.com/facebook/rocksdb/pull/3185

Differential Revision: D6389658

Pulled By: sagar0

fbshipit-source-id: 1848912750329a476805b3cb2f315e7b71f61472
2017-11-28 10:28:46 -08:00
Maysam Yabandeh b72b3c6f51 WritePrepared Txn: Add MultiGet to DB
Summary:
This patch implements MultiGet API for WritePreparedTxnDB and update the existing unit tests.
Closes https://github.com/facebook/rocksdb/pull/3196

Differential Revision: D6401493

Pulled By: maysamyabandeh

fbshipit-source-id: 51501a1e32645fc2da8680e77a50035f6530f2cc
2017-11-27 08:56:21 -08:00
Yi Wu f0dde49cda Blob DB: Fix GC handling for inlined blob
Summary:
Garbage collection checks if the offset in blob index matches the offset of the blob value in the file. If it is a mismatch, the value is the current version. However it failed to check if the blob index is an inlined type, which don't even have an offset. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3194

Differential Revision: D6394270

Pulled By: yiwu-arbug

fbshipit-source-id: 7c2b9d795f1116f55f4d728086980f9b6e88ea78
2017-11-24 11:56:47 -08:00
Maysam Yabandeh e59cb2a19b Add seq_per_batch to WriteWithCallbackTest
Summary:
Augment WriteWithCallbackTest to also test when seq_per_batch is true.
Closes https://github.com/facebook/rocksdb/pull/3195

Differential Revision: D6398143

Pulled By: maysamyabandeh

fbshipit-source-id: 7bc4218609355ec20fed25df426a8455ec2390d3
2017-11-22 13:56:44 -08:00
Zhongyi Xie 5fac4729cc make compaction_readahead_size_ thread safe
Summary:
this should fix the failing tsan_check
Closes https://github.com/facebook/rocksdb/pull/3192

Differential Revision: D6390004

Pulled By: miasantreble

fbshipit-source-id: 6cadfc6f68febb1a77b0abcdb5416570dad926a5
2017-11-21 20:11:38 -08:00
Griffin Smith fe187e7e6c Add Elixir to the list of language bindings
Summary: Closes https://github.com/facebook/rocksdb/pull/3183

Differential Revision: D6386140

Pulled By: maysamyabandeh

fbshipit-source-id: ca71d54edd741c3b7d9676ee2bcf584a5d49bc35
2017-11-21 10:13:14 -08:00
Sagar Vemuri 8954f830a0 Blob DB: db_bench flag to control BlobDB's garbage collection
Summary:
flag: blob_db_enable_gc, to control BlobDb's enable_garbage_collection.
Closes https://github.com/facebook/rocksdb/pull/3190

Differential Revision: D6383395

Pulled By: sagar0

fbshipit-source-id: 4134e835150748c425b8187264273a54c6d8381c
2017-11-20 23:26:15 -08:00
anand1976 d394a6bb48 Add a ticker stat for number of keys skipped during iteration
Summary:
This diff adds a new ticker stat, NUMBER_ITER_SKIP, to count the
number of internal keys skipped during iteration. Keys can be skipped
due to deletes, or lower sequence number, or higher sequence number
than the one requested.

Also, fix the issue when StatisticsData is naturally aligned on cacheline boundary,
padding becomes a zero size array, which the Windows compiler doesn't
like. So add a cacheline worth of padding in that case to keep it happy.
We cannot conditionally add padding as gcc doesn't allow using sizeof
in preprocessor directives.
Closes https://github.com/facebook/rocksdb/pull/3177

Differential Revision: D6353897

Pulled By: anand1976

fbshipit-source-id: 441d5a09af9c4e22e7355242dfc0c7b27aa0a6c2
2017-11-20 21:26:37 -08:00
Sagar Vemuri 578f36e431 Blob DB: Remove some redundant log lines
Summary:
Saw some redundant log lines when trying to benchmark blob db. So, removed the lines from blob_file.cc, and let the lines in blob_db_impl.cc take the lead.
Closes https://github.com/facebook/rocksdb/pull/3189

Differential Revision: D6381726

Pulled By: sagar0

fbshipit-source-id: 5f0b1e56fe4bc3b715d89ea9b5749bd935cd0606
2017-11-20 21:11:34 -08:00
Zhongyi Xie a6c6b8b38c Revert "No need for Restart Interval for meta blocks"
Summary:
See [issue 3169](https://github.com/facebook/rocksdb/issues/3169) for more information

This reverts commit 593d3de371.
Closes https://github.com/facebook/rocksdb/pull/3188

Differential Revision: D6379271

Pulled By: miasantreble

fbshipit-source-id: 88f9ed67ba52237ad9b6f7251db83672b62d7537
2017-11-20 16:42:03 -08:00
Maysam Yabandeh 30285ee31c Fix calculating filter partition target size
Summary:
block_size_deviation is in percentage while the partition size is in bytes. The current code fails to take that into account resulting into very large target size for filter partitions.
Closes https://github.com/facebook/rocksdb/pull/3187

Differential Revision: D6376069

Pulled By: maysamyabandeh

fbshipit-source-id: 276546fc68f50e0da32c462abb46f6cf676db9b2
2017-11-20 13:26:57 -08:00
Giorgio Azzinnaro 0996e140bd Added ProfaneDB
Summary:
Added my project [ProfaneDB](https://profanedb.gitlab.io/) which uses RocksDB as the main storage engine
Closes https://github.com/facebook/rocksdb/pull/3182

Differential Revision: D6370847

Pulled By: ajkr

fbshipit-source-id: ff4bb6bdbc6e42fdb88bd793a84a0e04c129b6ae
2017-11-19 10:11:44 -08:00
Maysam Yabandeh 0213990b3a Move static variables out of the header file
Summary:
Static variables in header files will be instantiated in every file that includes the header file. This patch moves some of them from options_helper.h to its .cc files. It also moves the static variable out of the offset_of since the template function could also lead to multiple instantiation perhaps due to inlining.

Fixes https://github.com/facebook/rocksdb/issues/3176
Closes https://github.com/facebook/rocksdb/pull/3178

Differential Revision: D6363794

Pulled By: maysamyabandeh

fbshipit-source-id: d0a07f061b4d992ab4e0de2706e622131d258fdd
2017-11-17 17:12:27 -08:00
Gustav Davidsson 2d04ed65e4 Make trash-to-DB size ratio limit configurable
Summary:
Allow users to configure the trash-to-DB size ratio limit, so
that ratelimits for deletes can be enforced even when larger portions of
the database are being deleted.
Closes https://github.com/facebook/rocksdb/pull/3158

Differential Revision: D6304897

Pulled By: gdavidsson

fbshipit-source-id: a28dd13059ebab7d4171b953ed91ce383a84d6b3
2017-11-17 11:58:17 -08:00
Zhongyi Xie 32e31d49d1 Make DBOption compaction_readahead_size dynamic
Summary: Closes https://github.com/facebook/rocksdb/pull/3004

Differential Revision: D6056141

Pulled By: miasantreble

fbshipit-source-id: 56df1630f464fd56b07d25d38161f699e0528b7f
2017-11-16 17:57:25 -08:00
Andrew Kryczka e27f60b1c8 distinguish kZSTDNotFinalCompression in compression string
Summary:
This confused some users who were getting compression type from the logs.
Closes https://github.com/facebook/rocksdb/pull/3153

Differential Revision: D6294964

Pulled By: ajkr

fbshipit-source-id: 3c813376d33682dc6ccafc9a78df1a2e2528985e
2017-11-15 19:41:59 -08:00
Yi Wu dd49f89466 Fix TARGETS lint warnings.
Summary:
Fix buckifier script and regenerate TARGETS file with no lint warnings.
Closes https://github.com/facebook/rocksdb/pull/3170

Differential Revision: D6328993

Pulled By: yiwu-arbug

fbshipit-source-id: 17d0e4ed92f676f35fed76659386611cc72b00b2
2017-11-15 14:28:34 -08:00
Yi Wu bbcd3b0bd2 Suppress valgrind "unimplemented functionality" error
Summary:
Add ROCKSDB_VALGRIND_RUN macro and suppress false-positive "unimplemented functionality" throw by valgrind for steam hints.

Another approach would be add a valgrind suppress file. Valgrind is suppose to print the suppression when given "--gen-suppressions=all" param, which is suppose to be the content for the suppression file. But it doesn't print.
Closes https://github.com/facebook/rocksdb/pull/3174

Differential Revision: D6338786

Pulled By: yiwu-arbug

fbshipit-source-id: 3559efa5f3b92d40d09ad6ac82bc7b59f86c75aa
2017-11-15 14:28:34 -08:00
Maysam Yabandeh 54b43563be WritePrepared Txn: Refactoring WriteCallback
Summary:
Refactor the logic around WriteCallback in the write path to clarify when and how exactly we advance the sequence number and making sure it is consistent across the code.
Closes https://github.com/facebook/rocksdb/pull/3168

Differential Revision: D6324312

Pulled By: maysamyabandeh

fbshipit-source-id: 9a34f479561fdb2a5d01ef6d37a28908d03bbe33
2017-11-15 08:27:06 -08:00
Maysam Yabandeh 53863b76f9 WritePrepared Txn: fix bug with Rollback seq
Summary:
The sequence number was not properly advanced after a rollback marker. The patch extends the existing unit tests to detect the bug and also fixes it.
Closes https://github.com/facebook/rocksdb/pull/3157

Differential Revision: D6304291

Pulled By: maysamyabandeh

fbshipit-source-id: 1b519c44a5371b802da49c9e32bd00087a8da401
2017-11-15 08:27:06 -08:00
Maysam Yabandeh 175d5d6a9e Properly destruct rebuilding_trx_
Summary:
When testing rebuilding_trx_ in MemTableInserter might still be set before the tests finishes which would cause ASAN alarms for leaks. This patch deletes the pointers in MemTableInserter destructor.
Closes https://github.com/facebook/rocksdb/pull/3162

Differential Revision: D6317113

Pulled By: maysamyabandeh

fbshipit-source-id: a68be70709a4fff7ac2b768660119311968f9c21
2017-11-14 08:56:50 -08:00
Yi Wu 9871ea4357 Regression test build binaries with PORTABLE=1
Summary:
We hit "Illegal instruction" error in regression test with "shlx" instruction. Setting PORTABLE=1 to resolve it.
Closes https://github.com/facebook/rocksdb/pull/3165

Differential Revision: D6321972

Pulled By: yiwu-arbug

fbshipit-source-id: cc9fe0dbd4698d1b66a750a0b062f66899862719
2017-11-13 21:26:24 -08:00
Yi Wu 42564ada53 Blob DB: not using PinnableSlice move assignment
Summary:
The current implementation of PinnableSlice move assignment have an issue #3163. We are moving away from it instead of try to get the move assignment right, since it is too tricky.
Closes https://github.com/facebook/rocksdb/pull/3164

Differential Revision: D6319201

Pulled By: yiwu-arbug

fbshipit-source-id: 8f3279021f3710da4a4caa14fd238ed2df902c48
2017-11-13 18:12:20 -08:00
Maysam Yabandeh 2515266725 WritePrepared Txn: Refactoring TrackKeys
Summary:
This patch clarifies and refactors the logic around tracked keys in transactions.
Closes https://github.com/facebook/rocksdb/pull/3140

Differential Revision: D6290258

Pulled By: maysamyabandeh

fbshipit-source-id: 03b50646264cbcc550813c060b180fc7451a55c1
2017-11-11 13:14:20 -08:00
Maysam Yabandeh 2edc92bc28 WritePrepared Txn: cross-compatibility test
Summary:
Add tests to ensure that WritePrepared and WriteCommitted policies are cross compatible when the db WAL is empty. This is important when the admin want to switch between the policies. In such case, before the switch the admin needs to empty the WAL by i) committing/rollbacking all the pending transactions, ii) FlushMemTables
Closes https://github.com/facebook/rocksdb/pull/3118

Differential Revision: D6227247

Pulled By: maysamyabandeh

fbshipit-source-id: bcde3d92c1e89cda3b9cfa69f6a20af5d8993db7
2017-11-11 11:28:37 -08:00
Maysam Yabandeh 857adf388f WritePrepared Txn: Refactor conf params
Summary:
Summary of changes:
- Move seq_per_batch out of Options
- Rename concurrent_prepare to two_write_queues
- Add allocate_seq_only_for_data_
Closes https://github.com/facebook/rocksdb/pull/3136

Differential Revision: D6304458

Pulled By: maysamyabandeh

fbshipit-source-id: 08e685bfa82bbc41b5b1c5eb7040a8ca6e05e58c
2017-11-10 17:28:12 -08:00
Andrew Kryczka 07c2738ffa prefer enabling cpu features via -march/-mcpu
Summary:
If possible, use -march or -mcpu to get enable all features available on the local CPU or architecture. Only if this is impossible, we will manually set -msse4.2. It should be safe as there'll be a warning printed if `USE_SSE` is set and the provided flags are insufficient to support SSE4.2.
Closes https://github.com/facebook/rocksdb/pull/3156

Differential Revision: D6304703

Pulled By: ajkr

fbshipit-source-id: 030a53491263300cae7fafb429114d87acc828ef
2017-11-10 16:57:11 -08:00
Dmitri Smirnov f8e2db0717 Fix crashes, address test issues and adjust windows test script
Summary:
Add per-exe execution capability
  Add fix parsing of groups/tests
  Add timer test exclusion

 Fix unit tests
  Ifdef threadpool specific tests that do not pass on Vista threadpool.
  Remove spurious outout from prefix_test so test case listing works
  properly.
  Fix not using standard test directories results in file creation errors
  in sst_dump_test.

  BlobDb fixes:
    In C++ end() iterators can not be dereferenced. They are not valid.
	When deleting blob_db_ set it to nullptr before any other code executes.
	Not fixed:. On Windows you can not delete a file while it is open.
	[ RUN      ] BlobDBTest.ReadWhileGC
	d:\dev\rocksdb\rocksdb\utilities\blob_db\blob_db_test.cc(75): error: DestroyBlobDB(dbname_, options, bdb_options)
	IO error: Failed to delete: d:/mnt/db\testrocksdb-17444/blob_db_test/blob_dir/000001.blob: Permission denied
	d:\dev\rocksdb\rocksdb\utilities\blob_db\blob_db_test.cc(75): error: DestroyBlobDB(dbname_, options, bdb_options)
	IO error: Failed to delete: d:/mnt/db\testrocksdb-17444/blob_db_test/blob_dir/000001.blob: Permission denied

  write_batch
    Should not call front() if there is a chance the container is empty
Closes https://github.com/facebook/rocksdb/pull/3152

Differential Revision: D6293274

Pulled By: sagar0

fbshipit-source-id: 318c3717c22087fae13b18715dffb24565dbd956
2017-11-10 10:41:57 -08:00
Shaohua Li eefd75a228 Stream
Summary:
Add a simple policy for NVMe write time life hint
Closes https://github.com/facebook/rocksdb/pull/3095

Differential Revision: D6298030

Pulled By: shligit

fbshipit-source-id: 9a72a42e32e92193af11599eb71f0cf77448e24d
2017-11-10 09:26:24 -08:00
kapitan-k f1c5eaba56 updated c ingestexternalfileoptions for ingest behind
Summary: Closes https://github.com/facebook/rocksdb/pull/3151

Differential Revision: D6293861

Pulled By: ajkr

fbshipit-source-id: f8db0a71509d1cd8237f2d377bf9e1bb0464bdbf
2017-11-09 18:15:09 -08:00
Andrew Kryczka 93f69cb93a use bottommost compression when base level is bottommost
Summary:
The previous compression type selection caused unexpected behavior when the base level was also the bottommost level. The following sequence of events could happen:

- full compaction generates files with `bottommost_compression` type
- now base level is bottommost level since all files are in the same level
- any compaction causes files to be rewritten `compression_per_level` type since bottommost compression didn't apply to base level

I changed the code to make bottommost compression apply to base level.
Closes https://github.com/facebook/rocksdb/pull/3141

Differential Revision: D6264614

Pulled By: ajkr

fbshipit-source-id: d7aaa8675126896684154a1f2c9034d6214fde82
2017-11-09 17:42:00 -08:00
Yi Wu 5e9e5a4702 Blob DB: Fix race condition between flush and write
Summary:
A race condition will happen when:
* a user thread writes a value, but it hits the write stop condition because there are too many un-flushed memtables, while holding blob_db_impl.write_mutex_.
* Flush is triggered and call flush begin listener and try to acquire blob_db_impl.write_mutex_.

Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3149

Differential Revision: D6279805

Pulled By: yiwu-arbug

fbshipit-source-id: 0e3c58afb78795ebe3360a2c69e05651e3908c40
2017-11-08 19:42:22 -08:00
Yi Wu ca75f0a64a Blob DB: Fix release build
Summary:
`compression` shadow the method name in `BlobFile`. Rename it.
Closes https://github.com/facebook/rocksdb/pull/3148

Differential Revision: D6274498

Pulled By: yiwu-arbug

fbshipit-source-id: 7d293596530998b23b6b8a8940f983f9b6343a98
2017-11-08 13:14:20 -08:00
Yi Wu 4f9f124347 Blob DB: use compression in file header instead of global options
Summary:
To fix the issue of failing to decompress existing value after reopen DB with a different compression settings.
Closes https://github.com/facebook/rocksdb/pull/3142

Differential Revision: D6267260

Pulled By: yiwu-arbug

fbshipit-source-id: c7cf7f3e33b0cd25520abf4771cdf9180cc02a5f
2017-11-07 17:42:17 -08:00
Andrew Kryczka 114896c4e0 db_bench compression options
Summary:
- moved existing compression options to `InitializeOptionsGeneral` since they cannot be set through options file
- added flag for `zstd_max_train_bytes` which was recently introduced by #3057
Closes https://github.com/facebook/rocksdb/pull/3128

Differential Revision: D6240460

Pulled By: ajkr

fbshipit-source-id: 27dbebd86a55de237ba6a45cc79cff9214e82ebc
2017-11-07 14:00:03 -08:00
Andrew Kryczka 65c95d9c59 support db_bench compact benchmark on bottommost files
Summary:
Without this option, running the compact benchmark on a DB containing only bottommost files simply returned immediately.
Closes https://github.com/facebook/rocksdb/pull/3138

Differential Revision: D6256660

Pulled By: ajkr

fbshipit-source-id: e3b64543acd503d821066f4200daa201d4fb3a9d
2017-11-07 10:57:24 -08:00
Manuel Ung e03377c7fd Add lock wait time as a perf context counter
Summary:
Adds two new counters:

`key_lock_wait_count` counts how many times a lock was blocked by another transaction and had to wait, instead of being granted the lock immediately.
`key_lock_wait_time` counts the time spent acquiring locks.
Closes https://github.com/facebook/rocksdb/pull/3107

Differential Revision: D6217332

Pulled By: lth

fbshipit-source-id: 55d4f46da5550c333e523263422fd61d6a46deb9
2017-11-06 10:57:19 -08:00
Yi Wu be410dede8 Fix PinnableSlice move assignment
Summary:
After move assignment, we need to re-initialized the moved PinnableSlice.

Also update blob_db_impl.cc to not reuse the moved PinnableSlice since it is supposed to be in an undefined state after move.
Closes https://github.com/facebook/rocksdb/pull/3127

Differential Revision: D6238585

Pulled By: yiwu-arbug

fbshipit-source-id: bd99f2e37406c4f7de160c7dee6a2e8126bc224e
2017-11-03 18:13:21 -07:00
Sagar Vemuri a6d8e30c05 Remove unnecessary status check in TableCache::NewIterator
Summary:
While investigating the usage of `new_table_iterator_nanos` perf counter, I saw some code was wrapper around with unnecessary status check ... so removed it.
Closes https://github.com/facebook/rocksdb/pull/3120

Differential Revision: D6229181

Pulled By: sagar0

fbshipit-source-id: f8a44fe67f5a05df94553fdb233b21e54e88cc34
2017-11-03 14:42:08 -07:00
Prashant D 4c8f336401 util: Fix coverity issues
Summary:
util/concurrent_arena.h:
CID 1396145 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member free_begin_ is not initialized in this constructor nor in any functions that it calls.
 94    Shard() : allocated_and_unused_(0) {}

util/dynamic_bloom.cc:
	1. Condition hash_func == NULL, taking true branch.

CID 1322821 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
3. uninit_member: Non-static class member data_ is not initialized in this constructor nor in any functions that it calls.
47      hash_func_(hash_func == nullptr ? &BloomHash : hash_func) {}
48

util/file_reader_writer.h:
204 private:
205  AlignedBuffer buffer_;
   	member_not_init_in_gen_ctor: The compiler-generated constructor for this class does not initialize buffer_offset_.
206  uint64_t buffer_offset_;

CID 1418246 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
member_not_init_in_gen_ctor: The compiler-generated constructor for this class does not initialize buffer_len_.
207  size_t buffer_len_;
208};

util/thread_local.cc:
341#endif

CID 1322795 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
3. uninit_member: Non-static class member pthread_key_ is not initialized in this constructor nor in any functions that it calls.
342}

40struct ThreadData {
   	2. uninit_member: Non-static class member next is not initialized in this constructor nor in any functions that it calls.

CID 1400668 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
4. uninit_member: Non-static class member prev is not initialized in this constructor nor in any functions that it calls.
 41  explicit ThreadData(ThreadLocalPtr::StaticMeta* _inst) : entries(), inst(_inst) {}
 42  std::vector<Entry> entries;
   	1. member_decl: Class member declaration for next.
 43  ThreadData* next;
   	3. member_decl: Class member declaration for prev.
 44  ThreadData* prev;
 45  ThreadLocalPtr::StaticMeta* inst;
 46};
Closes https://github.com/facebook/rocksdb/pull/3123

Differential Revision: D6233566

Pulled By: sagar0

fbshipit-source-id: aa2068790ea69787a0035c0db39d59b0c25108db
2017-11-03 14:42:08 -07:00
Andrew Kryczka cfb120f737 fix CopyFile status checks
Summary:
copied from internal diff D6156261
Closes https://github.com/facebook/rocksdb/pull/3124

Differential Revision: D6230167

Pulled By: ajkr

fbshipit-source-id: 17926bb1152d607556364e3aacfec0ef3c115748
2017-11-03 11:57:10 -07:00
Yi Wu d956169563 Fix clang build error
Summary:
Fix cast from size_t to unsigned int.
Closes https://github.com/facebook/rocksdb/pull/3125

Differential Revision: D6232863

Pulled By: yiwu-arbug

fbshipit-source-id: 4c6131168b1faec26f7820b2cf4a09c242d323b7
2017-11-03 11:26:54 -07:00
Yi Wu 2581c0a5a1 Blob DB: Fix BlobDBTest::SnapshotAndGarbageCollection asan failure
Summary:
Fix unreleased snapshot at the end of the test.
Closes https://github.com/facebook/rocksdb/pull/3126

Differential Revision: D6232867

Pulled By: yiwu-arbug

fbshipit-source-id: 651ca3144fc573ea2ab0ab20f0a752fb4a101d26
2017-11-03 10:26:59 -07:00
Andrew Kryczka 24ad430600 pass key/value samples through zstd compression dictionary generator
Summary:
Instead of using samples directly, we now support passing the samples through zstd's dictionary generator when `CompressionOptions::zstd_max_train_bytes` is set to nonzero. If set to zero, we will use the samples directly as the dictionary -- same as before.

Note this is the first step of #2987, extracted into a separate PR per reviewer request.
Closes https://github.com/facebook/rocksdb/pull/3057

Differential Revision: D6116891

Pulled By: ajkr

fbshipit-source-id: 70ab13cc4c734fa02e554180eed0618b75255497
2017-11-02 22:56:36 -07:00
Andrew Kryczka c4c1f961e7 dynamically change current memtable size
Summary:
Previously setting `write_buffer_size` with `SetOptions` would only apply to new memtables. An internal user wanted it to take effect immediately, instead of at an arbitrary future point, to prevent OOM.

This PR makes the memtable's size mutable, and makes `SetOptions()` mutate it. There is one case when we preserve the old behavior, which is when memtable prefix bloom filter is enabled and the user is increasing the memtable's capacity. That's because the prefix bloom filter's size is fixed and wouldn't work as well on a larger memtable.
Closes https://github.com/facebook/rocksdb/pull/3119

Differential Revision: D6228304

Pulled By: ajkr

fbshipit-source-id: e44bd9d10a5f8c9d8c464bf7436070bb3eafdfc9
2017-11-02 22:28:10 -07:00
Zhongyi Xie 30e4e01e05 add missing else
Summary: Closes https://github.com/facebook/rocksdb/pull/3121

Differential Revision: D6229415

Pulled By: miasantreble

fbshipit-source-id: 57c7ad2fddf5dd6b8d7e3aaf6f62348151327dfb
2017-11-02 22:28:06 -07:00
Prashant D 602fe9454c Fix coverity issues in include/rocksdb
Summary:
include/rocksdb/metadata.h:
struct ColumnFamilyMetaData {

CID 1322804 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member file_count is not initialized in this constructor nor in any functions that it calls.

struct SstFileMetaData {
        2. uninit_member: Non-static class member size is not initialized in this constructor nor in any functions that it calls.
        4. uninit_member: Non-static class member smallest_seqno is not initialized in this constructor nor in any functions that it calls.
        6. uninit_member: Non-static class member largest_seqno is not initialized in this constructor nor in any functions that it calls.
        8. uninit_member: Non-static class member num_reads_sampled is not initialized in this constructor nor in any functions that it calls.

CID 1322807 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
10. uninit_member: Non-static class member being_compacted is not initialized in this constructor nor in any functions that it calls.

include/rocksdb/sst_file_writer.h:
struct ExternalSstFileInfo {
        2. uninit_member: Non-static class member sequence_number is not initialized in this constructor nor in any functions that it calls.
        4. uninit_member: Non-static class member file_size is not initialized in this constructor nor in any functions that it calls.
        6. uninit_member: Non-static class member num_entries is not initialized in this constructor nor in any functions that it calls.

CID 1351697 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
8. uninit_member: Non-static class member version is not initialized in this constructor nor in any functions that it calls.
 31  ExternalSstFileInfo() {}

include/rocksdb/utilities/transaction.h:
explicit Transaction(const TransactionDB* db) {}
        2. uninit_member: Non-static class member log_number_ is not initialized in this constructor nor in any functions that it calls.

CID 1396133 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
4. uninit_member: Non-static class member field txn_state_._M_i is not initialized in this constructor nor in any functions that it calls.
473  Transaction() {}
Closes https://github.com/facebook/rocksdb/pull/3100

Differential Revision: D6227651

Pulled By: sagar0

fbshipit-source-id: 5caa4a2cf9471d1f9c3c073f81473636e1f0aa14
2017-11-02 17:56:48 -07:00
Yi Wu 62578d80c1 Blob DB: Add compaction filter to remove expired blob index entries
Summary:
After adding expiration to blob index in #3066, we are now able to add a compaction filter to cleanup expired blob index entries.
Closes https://github.com/facebook/rocksdb/pull/3090

Differential Revision: D6183812

Pulled By: yiwu-arbug

fbshipit-source-id: 9cb03267a9702975290e758c9c176a2c03530b83
2017-11-02 17:27:38 -07:00
Sagar Vemuri 76c3fbd651 Add Memtable Read Tier to RocksJava
Summary:
This options was introduced in the C++ API in #1953 .
Closes https://github.com/facebook/rocksdb/pull/3064

Differential Revision: D6139010

Pulled By: sagar0

fbshipit-source-id: 164de11d539d174cf3afe7cd40e667049f44b0bc
2017-11-02 17:27:37 -07:00
Yi Wu 7bfa88037e Blob DB: fix snapshot handling
Summary:
Blob db will keep blob file if data in the file is visible to an active snapshot. Before this patch it checks whether there is an active snapshot has sequence number greater than the earliest sequence in the file. This is problematic since we take snapshot on every read, if it keep having reads, old blob files will not be cleanup. Change to check if there is an active snapshot falls in the range of [earliest_sequence, obsolete_sequence) where obsolete sequence is
1. if data is relocated to another file by garbage collection, it is the latest sequence at the time garbage collection finish
2. otherwise, it is the latest sequence of the file
Closes https://github.com/facebook/rocksdb/pull/3087

Differential Revision: D6182519

Pulled By: yiwu-arbug

fbshipit-source-id: cdf4c35281f782eb2a9ad6a87b6727bbdff27a45
2017-11-02 15:58:27 -07:00
Yi Wu f662f8f0b6 Blob DB: option to enable garbage collection
Summary:
Add an option to enable/disable auto garbage collection, where we keep counting how many keys have been evicted by either deletion or compaction and decide whether to garbage collect a blob file.

Default disable auto garbage collection for now since the whole logic is not fully tested and we plan to make major change to it.
Closes https://github.com/facebook/rocksdb/pull/3117

Differential Revision: D6224756

Pulled By: yiwu-arbug

fbshipit-source-id: cdf53bdccec96a4580a2b3a342110ad9e8864dfe
2017-11-02 15:58:27 -07:00
Yi Wu 167ba599ec Blob DB: Fix flaky BlobDBTest::GCExpiredKeyWhileOverwriting test
Summary:
The test intent to wait until key being overwritten until proceed with garbage collection. It failed to wait for `PutUntil` finally finish. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3116

Differential Revision: D6222833

Pulled By: yiwu-arbug

fbshipit-source-id: fa9b57a772b92a66cf250b44e7975c43f62f45c5
2017-11-02 13:27:34 -07:00
Sagar Vemuri 25ac1697b4 Blob DB: Evict oldest blob file when close to blob db size limit
Summary:
Evict oldest blob file and put it in obsolete_files list when close to blob db size limit. The file will be delete when the `DeleteObsoleteFiles` background job runs next time.
For now I set `kEvictOldestFileAtSize` constant, which controls when to evict the oldest file, at 90%. It could be tweaked or made into an option if really needed; I didn't want to expose it as an option pre-maturely as there are already too many :) .
Closes https://github.com/facebook/rocksdb/pull/3094

Differential Revision: D6187340

Pulled By: sagar0

fbshipit-source-id: 687f8262101b9301bf964b94025a2fe9d8573421
2017-11-02 12:11:21 -07:00
Prashant D 3c208e7616 HistogramStat: Handle divide by zero situation
Summary:
The num() might return cur_num as 0 and we are making sure that
cur_num will not be 0 down the path. The mult variable is being set to
100.0/cur_num which makes program crash when cur_num is 0.
Closes https://github.com/facebook/rocksdb/pull/3105

Differential Revision: D6222594

Pulled By: ajkr

fbshipit-source-id: 986154709897ff4dbbeb0e8aa81eb8c0b2a2db76
2017-11-02 11:41:50 -07:00
Maysam Yabandeh 25fbd9a996 Remove the experimental notes about partitioning
Summary:
This patch will remove the existing comments that declare partitioning indexes and filters as experimental.
Closes https://github.com/facebook/rocksdb/pull/3115

Differential Revision: D6222227

Pulled By: maysamyabandeh

fbshipit-source-id: 6179ec43b22c518494051b674d91c9e1b54d4ac0
2017-11-02 11:14:30 -07:00
Maysam Yabandeh 60d83df23d WritePrepared Txn: Move DB class to its own file
Summary:
Move  WritePreparedTxnDB from pessimistic_transaction_db.h to its own header, write_prepared_txn_db.h
Closes https://github.com/facebook/rocksdb/pull/3114

Differential Revision: D6220987

Pulled By: maysamyabandeh

fbshipit-source-id: 18893fb4fdc6b809fe117dabb544080f9b4a301b
2017-11-02 11:14:30 -07:00
Andrew Kryczka 6778690b51 fix duplicate definition of GetEntryType()
Summary:
It's also defined in db/dbformat.cc per 7fe3b32896
Closes https://github.com/facebook/rocksdb/pull/3111

Differential Revision: D6219140

Pulled By: ajkr

fbshipit-source-id: 0f2b14e41457334a4665c6b7e3f42f1a060a0f35
2017-11-01 22:56:17 -07:00
Andrew Kryczka cd124215df release 5.9
Summary:
updated HISTORY.md and version.h for the release.
Closes https://github.com/facebook/rocksdb/pull/3110

Differential Revision: D6218645

Pulled By: ajkr

fbshipit-source-id: 99ab8473e9088b02d7596e92351cce7a60a99e93
2017-11-01 21:26:14 -07:00
Maysam Yabandeh 02693f64fc WritePrepared Txn: ValidateSnapshot
Summary:
Implements ValidateSnapshot for WritePrepared txns and also adds a unit test to clarify the contract of this function.
Closes https://github.com/facebook/rocksdb/pull/3101

Differential Revision: D6199405

Pulled By: maysamyabandeh

fbshipit-source-id: ace509934c307ea5d26f4bbac5f836d7c80fd240
2017-11-01 19:11:09 -07:00
Mikhail Antonov 7fe3b32896 Added support for differential snapshots
Summary:
The motivation for this PR is to add to RocksDB support for differential (incremental) snapshots, as snapshot of the DB changes between two points in time (one can think of it as diff between to sequence numbers, or the diff D which can be thought of as an SST file or just set of KVs that can be applied to sequence number S1 to get the database to the state at sequence number S2).

This feature would be useful for various distributed storages layers built on top of RocksDB, as it should help reduce resources (time and network bandwidth) needed to recover and rebuilt DB instances as replicas in the context of distributed storages.

From the API standpoint that would like client app requesting iterator between (start seqnum) and current DB state, and reading the "diff".

This is a very draft PR for initial review in the discussion on the approach, i'm going to rework some parts and keep updating the PR.

For now, what's done here according to initial discussions:

Preserving deletes:
 - We want to be able to optionally preserve recent deletes for some defined period of time, so that if a delete came in recently and might need to be included in the next incremental snapshot it would't get dropped by a compaction. This is done by adding new param to Options (preserve deletes flag) and new variable to DB Impl where we keep track of the sequence number after which we don't want to drop tombstones, even if they are otherwise eligible for deletion.
 - I also added a new API call for clients to be able to advance this cutoff seqnum after which we drop deletes; i assume it's more flexible to let clients control this, since otherwise we'd need to keep some kind of timestamp < -- > seqnum mapping inside the DB, which sounds messy and painful to support. Clients could make use of it by periodically calling GetLatestSequenceNumber(), noting the timestamp, doing some calculation and figuring out by how much we need to advance the cutoff seqnum.
 - Compaction codepath in compaction_iterator.cc has been modified to avoid dropping tombstones with seqnum > cutoff seqnum.

Iterator changes:
 - couple params added to ReadOptions, to optionally allow client to request internal keys instead of user keys (so that client can get the latest value of a key, be it delete marker or a put), as well as min timestamp and min seqnum.

TableCache changes:
 - I modified table_cache code to be able to quickly exclude SST files from iterators heep if creation_time on the file is less then iter_start_ts as passed in ReadOptions. That would help a lot in some DB settings (like reading very recent data only or using FIFO compactions), but not so much for universal compaction with more or less long iterator time span.

What's left:

 - Still looking at how to best plug that inside DBIter codepath. So far it seems that FindNextUserKeyInternal only parses values as UserKeys, and iter->key() call generally returns user key. Can we add new API to DBIter as internal_key(), and modify this internal method to optionally set saved_key_ to point to the full internal key? I don't need to store actual seqnum there, but I do need to store type.
Closes https://github.com/facebook/rocksdb/pull/2999

Differential Revision: D6175602

Pulled By: mikhail-antonov

fbshipit-source-id: c779a6696ee2d574d86c69cec866a3ae095aa900
2017-11-01 18:56:43 -07:00
Maysam Yabandeh 17731a43a6 WritePrepared Txn: Optimize for recoverable state
Summary:
GetCommitTimeWriteBatch is currently used to store some state as part of commit in 2PC. In MyRocks it is specifically used to store some data that would be needed only during recovery. So it is not need to be stored in memtable right after each commit.
This patch enables an optimization to write the GetCommitTimeWriteBatch only to the WAL. The batch will be written to memtable during recovery when the WAL is replayed. To cover the case when WAL is deleted after memtable flush, the batch is also buffered and written to memtable right before each memtable flush.
Closes https://github.com/facebook/rocksdb/pull/3071

Differential Revision: D6148023

Pulled By: maysamyabandeh

fbshipit-source-id: 2d09bae5565abe2017c0327421010d5c0d55eaa7
2017-11-01 17:26:46 -07:00
Maysam Yabandeh c1cf94c787 WritePrepared Txn: sort indexes before batch collapse
Summary:
The collapse of duplicate keys in write batch needs to sort the indexes of duplicate keys since it only checks the index in the batch with the head of the list of duplicate keys.
Closes https://github.com/facebook/rocksdb/pull/3093

Differential Revision: D6186800

Pulled By: maysamyabandeh

fbshipit-source-id: abc9ae8c2f1840445a5584f925cf86ecc6f37154
2017-11-01 08:56:57 -07:00
Yi Wu f6082d1944 Blob DB: cleanup unused options
Summary:
* cleanup num_concurrent_simple_blobs. We don't do concurrent writes (by taking write_mutex_) so it doesn't make sense to have multiple non TTL files open. We can revisit later when we want to improve writes.
* cleanup eviction callback. we don't have plan to use it now.
* rename s/open_simple_blob_files_/open_non_ttl_file_/ and s/open_blob_files_/open_ttl_files_/ to avoid confusion.
Closes https://github.com/facebook/rocksdb/pull/3088

Differential Revision: D6182598

Pulled By: yiwu-arbug

fbshipit-source-id: 99e6f5e01fa66d31309cdb06ce48502464bac6ad
2017-10-31 16:42:08 -07:00
Sagar Vemuri f5078dde2d Blob DB: Initialize all fields in Blob Header, Footer and Record structs
Summary:
Fixing un-itializations caught by valgrind.
Closes https://github.com/facebook/rocksdb/pull/3103

Differential Revision: D6200195

Pulled By: sagar0

fbshipit-source-id: bf35a3fb03eb1d308e4c5ce30dee1e345d7b03b3
2017-10-31 16:42:08 -07:00
Shaohua Li 33c7d4ccd9 Make writable_file_max_buffer_size dynamic
Summary:
The DBOptions::writable_file_max_buffer_size can be changed dynamically.
Closes https://github.com/facebook/rocksdb/pull/3053

Differential Revision: D6152720

Pulled By: shligit

fbshipit-source-id: aa0c0cfcfae6a54eb17faadb148d904797c68681
2017-10-31 13:56:35 -07:00
Prashant D c1be8d86c6 Fix removed structurally dead return statement
Summary:
There seems to be a typo mistake in env ReuseWritableFile func
where status is being returned twice.
Closes https://github.com/facebook/rocksdb/pull/3099

Differential Revision: D6196204

Pulled By: ajkr

fbshipit-source-id: abb6e3e1c1e772dd485fc39e7f1b9d502fa188fe
2017-10-31 01:26:13 -07:00
Andrew Kryczka 4d43c6a6a4 db_stress snapshot compatibility with reopens
Summary:
- Release all snapshots before crashing and reopening the DB. Without this, we may attempt to release snapshots from an old DB using a new DB. That tripped an assertion.
- Release multiple snapshots in the same operation if needed. Without this, we would sometimes leak snapshots.
Closes https://github.com/facebook/rocksdb/pull/3098

Differential Revision: D6194923

Pulled By: ajkr

fbshipit-source-id: b9c89bcca7ebcbb6c7802c616f9d1175a005aadf
2017-10-31 01:26:08 -07:00
Andrew Kryczka b7bc9cc038 fix tracking oldest snapshot for bottom-level compaction
Summary:
The assertion was caught by `MySQLStyleTransactionTest/MySQLStyleTransactionTest.TransactionStressTest/5` when run in a loop. The caller doesn't track whether the released snapshot is oldest, so let this function handle that case.
Closes https://github.com/facebook/rocksdb/pull/3080

Differential Revision: D6185257

Pulled By: ajkr

fbshipit-source-id: 4b3015c11db5d31e46521a00af568546ef4558cd
2017-10-30 00:55:58 -07:00
Yi Wu 792ef10ca8 Return Status::InvalidArgument if user request sync write while disabling WAL
Summary:
write_options.sync = true and write_options.disableWAL is incompatible. When WAL is disabled, we are not able to persist the write immediately. Return an error in this case to avoid misuse of the options.
Closes https://github.com/facebook/rocksdb/pull/3086

Differential Revision: D6176822

Pulled By: yiwu-arbug

fbshipit-source-id: 1eb10028c14fe7d7c13c8bc12c0ef659f75aa071
2017-10-28 22:11:18 -07:00
Andrew Kryczka 6a9335dbbb always drop tombstones compacted to bottommost level
Summary:
Problem was in bottommost compaction, when an L0->L0 compaction happened and L0 was bottommost. Then we'd preserve tombstones according to `Compaction::KeyNotExistsBeyondOutputLevel`, while zeroing seqnum according to `CompactionIterator::PrepareOutput`, thus triggering the assertion in `PrepareOutput`. To fix, we can just drop tombstones in L0->L0 when the output is "bottommost", i.e., the compaction includes the oldest L0 file and there's nothing at lower levels.
Closes https://github.com/facebook/rocksdb/pull/3085

Differential Revision: D6175742

Pulled By: ajkr

fbshipit-source-id: 8ab19a2e001496f362e9eb0a71757e2f6ecfdb3b
2017-10-27 15:56:35 -07:00
Yi Wu 84a04af9a9 TableProperty::oldest_key_time defaults to 0
Summary:
We don't propagate TableProperty::oldest_key_time on compaction and just write the default value to SST files. It is more natural to default the value to 0.

Also revert db_sst_test back to before #2842.
Closes https://github.com/facebook/rocksdb/pull/3079

Differential Revision: D6165702

Pulled By: yiwu-arbug

fbshipit-source-id: ca3ce5928d96ae79a5beb12bb7d8c640a71478a0
2017-10-27 15:00:05 -07:00
Islam AbdelRahman 05993155ef Mark files as trash by using .trash extension
Summary:
SstFileManager move files that need to be deleted into a trash directory.
Deprecate this behaviour and instead add ".trash" extension to files that need to be deleted
Closes https://github.com/facebook/rocksdb/pull/2970

Differential Revision: D5976805

Pulled By: IslamAbdelRahman

fbshipit-source-id: 27374ece4315610b2792c30ffcd50232d4c9a343
2017-10-27 13:27:12 -07:00
Yi Wu 3ebb7ba7b9 Blob DB: update blob file format
Summary:
Changing blob file format and some code cleanup around the change. The change with blob log format are:
* Remove timestamp field in blob file header, blob file footer and blob records. The field is not being use and often confuse with expiration field.
* Blob file header now come with column family id, which always equal to default column family id. It leaves room for future support of column family.
* Compression field in blob file header now is a standalone byte (instead of compact encode with flags field)
* Blob file footer now come with its own crc.
* Key length now being uint64_t instead of uint32_t
* Blob CRC now checksum both key and value (instead of value only).
* Some reordering of the fields.

The list of cleanups:
* Better inline comments in blob_log_format.h
* rename ttlrange_t and snrange_t to ExpirationRange and SequenceRange respectively.
* simplify blob_db::Reader
* Move crc checking logic to inside blob_log_format.cc
Closes https://github.com/facebook/rocksdb/pull/3081

Differential Revision: D6171304

Pulled By: yiwu-arbug

fbshipit-source-id: e4373e0d39264441b7e2fbd0caba93ddd99ea2af
2017-10-27 13:27:12 -07:00
Dmitri Smirnov 682db81385 Enable cacheline_aligned_alloc() to allocate from jemalloc if enabled.
Summary:
Reuse WITH_JEMALLOC option in preparation for module search unification.
  Move jemalloc overrides into a separate .cc
  Remote obsolete JEMALLOC_NOINIT option.
Closes https://github.com/facebook/rocksdb/pull/3078

Differential Revision: D6174826

Pulled By: yiwu-arbug

fbshipit-source-id: 9970a0289b4490272d15853920d9d7531af91140
2017-10-27 13:27:12 -07:00
Prashant D d9240b548c Fix coverity uninitialized fields warnings in lru_cache
Summary:
Coverity uninitialized member variable warnings in lru_cache
Closes https://github.com/facebook/rocksdb/pull/3082

Differential Revision: D6173062

Pulled By: sagar0

fbshipit-source-id: 7bcfc653457bd362d46045d06527838c9a6adad6
2017-10-27 11:26:43 -07:00
Prashant D 50e95a63dd Fix coverity issues column_family, compaction_db/iterator
Summary:
db/column_family.h :
79  ColumnFamilyHandleInternal()

CID 1322806 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member internal_cfd_ is not initialized in this constructor nor in any functions that it calls.
 80      : ColumnFamilyHandleImpl(nullptr, nullptr, nullptr) {}

db/compacted_db_impl.cc:
 18CompactedDBImpl::CompactedDBImpl(
 19  const DBOptions& options, const std::string& dbname)
 20  : DBImpl(options, dbname) {
   	2. uninit_member: Non-static class member cfd_ is not initialized in this constructor nor in any functions that it calls.
   	4. uninit_member: Non-static class member version_ is not initialized in this constructor nor in any functions that it calls.

CID 1396120 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
6. uninit_member: Non-static class member user_comparator_ is not initialized in this constructor nor in any functions that it calls.
 21}

db/compaction_iterator.cc:
9. uninit_member: Non-static class member current_user_key_sequence_ is not initialized in this constructor nor in any functions that it calls.
11. uninit_member: Non-static class member current_user_key_snapshot_ is not initialized in this constructor nor in any functions that it calls.

CID 1419855 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
13. uninit_member: Non-static class member current_key_committed_ is not initialized in this constructor nor in any functions that it calls.
Closes https://github.com/facebook/rocksdb/pull/3084

Differential Revision: D6172999

Pulled By: sagar0

fbshipit-source-id: 084d73393faf8022c01359cfb445807b6a782460
2017-10-27 11:26:42 -07:00
Prashant D 47166baeac Fix coverity uninitialized fields warnings
Pulled By: ajkr

Differential Revision: D6170448

fbshipit-source-id: 5fd6d1608fc0df27c94d9f5059315ce7f79b8f5c
2017-10-26 21:11:50 -07:00
Prashant D 67b29e26be Fix coverity issue for MutableDBOptions default constructor
Summary:
228MutableDBOptions::MutableDBOptions()
229    : max_background_jobs(2),
230      base_background_compactions(-1),
231      max_background_compactions(-1),
232      avoid_flush_during_shutdown(false),
233      delayed_write_rate(2 * 1024U * 1024U),
234      max_total_wal_size(0),
235      delete_obsolete_files_period_micros(6ULL * 60 * 60 * 1000000),
236      stats_dump_period_sec(600),
   	2. uninit_member: Non-static class member bytes_per_sync is not initialized in this constructor nor in any functions that it calls.

CID 1419857 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
4. uninit_member: Non-static class member wal_bytes_per_sync is not initialized in this constructor nor in any functions that it calls.
237      max_open_files(-1) {}
Closes https://github.com/facebook/rocksdb/pull/3069

Differential Revision: D6170424

Pulled By: ajkr

fbshipit-source-id: 1f94e86b87611ad2330b8b1707911150978d68b8
2017-10-26 20:56:45 -07:00
Andrew Kryczka 95667383db implement lower bound for iterators
Summary:
- for `SeekToFirst()`, just convert it to a regular `Seek()` if lower bound is specified
- for operations that iterate backwards over user keys (`SeekForPrev`, `SeekToLast`, `Prev`), change `PrevInternal` to check whether user key went below lower bound every time the user key changes -- same approach we use to ensure we stay within a prefix when `prefix_same_as_start=true`.
Closes https://github.com/facebook/rocksdb/pull/3074

Differential Revision: D6158654

Pulled By: ajkr

fbshipit-source-id: cb0e3a922e2650d2cd4d1c6e1c0f1e8b729ff518
2017-10-26 17:27:42 -07:00
Yi Wu 5a2a6483dc Blob DB: Inline small values in base DB
Summary:
Adding the `min_blob_size` option to allow storing small values in base db (in LSM tree) together with the key. The goal is to improve performance for small values, while taking advantage of blob db's low write amplification for large values.

Also adding expiration timestamp to blob index. It will be useful to evict stale blob indexes in base db by adding a compaction filter. I'll work on the compaction filter in future patches.

See blob_index.h for the new blob index format. There are 4 cases when writing a new key:
* small value w/o TTL: put in base db as normal value (i.e. ValueType::kTypeValue)
* small value w/ TTL: put (type, expiration, value) to base db.
* large value w/o TTL: write value to blob log and put (type, file, offset, size, compression) to base db.
* large value w/TTL: write value to blob log and put (type, expiration, file, offset, size, compression) to base db.
Closes https://github.com/facebook/rocksdb/pull/3066

Differential Revision: D6142115

Pulled By: yiwu-arbug

fbshipit-source-id: 9526e76e19f0839310a3f5f2a43772a4ad182cd0
2017-10-26 12:30:54 -07:00
Andrew Kryczka 9b18cc2363 single-file bottom-level compaction when snapshot released
Summary:
When snapshots are held for a long time, files may reach the bottom level containing overwritten/deleted keys. We previously had no mechanism to trigger compaction on such files. This particularly impacted DBs that write to different parts of the keyspace over time, as such files would never be naturally compacted due to second-last level files moving down. This PR introduces a mechanism for bottommost files to be recompacted upon releasing all snapshots that prevent them from dropping their deleted/overwritten keys.

- Changed `CompactionPicker` to compact files in `BottommostFilesMarkedForCompaction()`. These are the last choice when picking. Each file will be compacted alone and output to the same level in which it originated. The goal of this type of compaction is to rewrite the data excluding deleted/overwritten keys.
- Changed `ReleaseSnapshot()` to recompute the bottom files marked for compaction when the oldest existing snapshot changes, and schedule a compaction if needed. We cache the value that oldest existing snapshot needs to exceed in order for another file to be marked in `bottommost_files_mark_threshold_`, which allows us to avoid recomputing marked files for most snapshot releases.
- Changed `VersionStorageInfo` to track the list of bottommost files, which is recomputed every time the version changes by `UpdateBottommostFiles()`. The list of marked bottommost files is first computed in `ComputeBottommostFilesMarkedForCompaction()` when the version changes, but may also be recomputed when `ReleaseSnapshot()` is called.
- Extracted core logic of `Compaction::IsBottommostLevel()` into `VersionStorageInfo::RangeMightExistAfterSortedRun()` since logic to check whether a file is bottommost is now necessary outside of compaction.
Closes https://github.com/facebook/rocksdb/pull/3009

Differential Revision: D6062044

Pulled By: ajkr

fbshipit-source-id: 123d201cf140715a7d5928e8b3cb4f9cd9f7ad21
2017-10-25 16:30:37 -07:00
Sagar Vemuri 96e3a600ba Return write error on reaching blob dir size limit
Summary:
I found that we continue accepting writes even when the blob db goes beyond the configured blob directory size limit. Now, we return an error for writes on reaching `blob_dir_size` limit and if `is_fifo` is set to false. (We cannot just drop any file when `is_fifo` is true.)

Deleting the oldest file when `is_fifo` is true will be handled in a later PR.
Closes https://github.com/facebook/rocksdb/pull/3060

Differential Revision: D6136156

Pulled By: sagar0

fbshipit-source-id: 2f11cb3f2eedfa94524fbfa2613dd64bfad7a23c
2017-10-25 16:30:37 -07:00
Islam AbdelRahman addfe1ef4b Fix tombstone scans in SeekForPrev outside prefix
Summary:
When doing a Seek() or SeekForPrev() we should stop the moment we see a key with a different prefix as start if ReadOptions:: prefix_same_as_start was set to true

Right now we don't stop if we encounter a tombstone outside the prefix while executing SeekForPrev()
Closes https://github.com/facebook/rocksdb/pull/3067

Differential Revision: D6149638

Pulled By: IslamAbdelRahman

fbshipit-source-id: 7f659862d2bf552d3c9104a360c79439ceba2f18
2017-10-25 15:12:00 -07:00
zach shipko 386a57e6ef Fix build on OpenBSD
Summary:
A few simple changes to allow RocksDB to be built on OpenBSD. Let me know if any further changes are needed.
Closes https://github.com/facebook/rocksdb/pull/3061

Differential Revision: D6138800

Pulled By: ajkr

fbshipit-source-id: a13a17b5dc051e6518bd56a8c5efd1d24dd81b0c
2017-10-24 13:27:38 -07:00
zawlazaw 57fcdc264a added missing subcodes and improved error message for missing enum values
Summary:
Java's `Status.SubCode` was out of sync with `include/rocksdb/status.h:SubCode`.

When running out of disc space this led to an `IllegalArgumentException` because of an invalid status code, rather than just returning the corresponding status code without an exception.

I added the missing status codes.

By this, we keep the behaviour of throwing an `IllegalArgumentException` in case of newly added status codes that are defined in C but not in Java.

We could think of an alternative strategy: add in Java another code "UnknownCode" which acts as a catch-all for all those status codes that are not yet mirrored from C to Java. This approach would never throw an exception but simply return a non-OK status-code.

I think the current approach of throwing an Exception in case of a C/Java inconsistency is fine, but if you have some opinion on the alternative strategy, then feel free to comment here.
Closes https://github.com/facebook/rocksdb/pull/3050

Differential Revision: D6129682

Pulled By: sagar0

fbshipit-source-id: f2bf44caad650837cffdcb1f93eb793b43580c66
2017-10-23 16:42:07 -07:00
Yi Wu 66a2c44ef4 Add DB::Properties::kEstimateOldestKeyTime
Summary:
With FIFO compaction we would like to get the oldest data time for monitoring. The problem is we don't have timestamp for each key in the DB. As an approximation, we expose the earliest of sst file "creation_time" property.

My plan is to override the property with a more accurate value with blob db, where we actually have timestamp.
Closes https://github.com/facebook/rocksdb/pull/2842

Differential Revision: D5770600

Pulled By: yiwu-arbug

fbshipit-source-id: 03833c8f10bbfbee62f8ea5c0d03c0cafb5d853a
2017-10-23 15:27:27 -07:00
Dmitri Smirnov d2a65c59e1 Fix unused var warnings in Release mode
Summary:
MSVC does not support unused attribute at this time. A separate assignment line fixes the issue probably by being counted as usage for MSVC and it no longer complains about unused var.
Closes https://github.com/facebook/rocksdb/pull/3048

Differential Revision: D6126272

Pulled By: maysamyabandeh

fbshipit-source-id: 4907865db45fd75a39a15725c0695aaa17509c1f
2017-10-23 14:27:04 -07:00
Maysam Yabandeh 63822eb761 Enable two write queues for transactions
Summary:
Enable concurrent_prepare flag for WritePrepared transactions and extend the existing transaction tests with this config.
Closes https://github.com/facebook/rocksdb/pull/3046

Differential Revision: D6106534

Pulled By: maysamyabandeh

fbshipit-source-id: 88c8d21d45bc492beb0a131caea84a2ac5e7d38c
2017-10-23 14:27:04 -07:00
Sagar Vemuri a02ed12638 Exclude DBTest.DynamicFIFOCompactionOptions test under RocksDB Lite
Summary:
This test shouldn't be enabled under the lite version; and this fixes the failing contrun test due to #3006.
Closes https://github.com/facebook/rocksdb/pull/3056

Differential Revision: D6114681

Pulled By: sagar0

fbshipit-source-id: dc5243549ae6b1353cec7edb820c771d95f66dda
2017-10-20 17:11:39 -07:00
Maysam Yabandeh 3ef55d2c7c Split CompactionFilterWithValueChange
Summary:
The test currently times out when it is run under tsan. This patch split it into 4 tests.
Closes https://github.com/facebook/rocksdb/pull/3047

Differential Revision: D6106515

Pulled By: maysamyabandeh

fbshipit-source-id: 03a28cdf8b1c097be2361b1b0cc3dc1acf2b5d63
2017-10-20 15:42:07 -07:00
Andrew Kryczka d75793d6b4 db_stress support long-held snapshots
Summary:
Add options to `db_stress` (correctness testing tool) to randomly acquire snapshot and release it after some period of time. It's useful for correctness testing of #3009, as well as other parts of compaction that behave differently depending on which snapshots are held.
Closes https://github.com/facebook/rocksdb/pull/3038

Differential Revision: D6086501

Pulled By: ajkr

fbshipit-source-id: 3ec0d8666c78ac507f1f808887c4ff759ba9b865
2017-10-20 15:26:59 -07:00
Andrew Kryczka f8b5bb2fd8 remove unused code
Summary:
fixup 6a541afcc4. This code didn't do anything because (1) `bytes_per_sync` is assigned in `EnvOptions`'s constructor; and (2) `OptimizeForCompactionTableWrite`'s return value was ignored, even though its only purpose is to return something.
Closes https://github.com/facebook/rocksdb/pull/3055

Differential Revision: D6114132

Pulled By: ajkr

fbshipit-source-id: ea4831770930e9cf83518e13eb2e1934d1f5487c
2017-10-20 14:11:52 -07:00
Andrew Kryczka 57fd4a823b update HISTORY with recent changes
Summary:
We should mention these:

- `EventListener::OnStallConditionsChanged()` in 01542400a8
- `DeleteRange()` fix in 966b32b57c
Closes https://github.com/facebook/rocksdb/pull/3054

Differential Revision: D6113989

Pulled By: ajkr

fbshipit-source-id: d5e058e1ab07570df22936e8d5939fb30fb4d381
2017-10-20 13:56:49 -07:00
raistlin ee2b1ec1e8 Fix unstable floating point exception
Summary:
Fix unstable floating point exception, tested on Windows, 64-bit build.
The problem appeared in `SetCapacity()` method at line

`high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;`

`high_pri_pool_ratio_` was not initialized at that moment, because
`SetHighPriorityPoolRatio()` is called after `SetCapacity()`. So,
`high_pri_pool_ratio_` contained garbage, which caused "Floating point
exception" sometimes.
Closes https://github.com/facebook/rocksdb/pull/3052

Differential Revision: D6111161

Pulled By: yiwu-arbug

fbshipit-source-id: d170329111ad12b4bf9bbcf37bcb6411523438ae
2017-10-20 10:12:49 -07:00
Sagar Vemuri f0804db7f7 Make FIFO compaction options dynamically configurable
Summary:
ColumnFamilyOptions::compaction_options_fifo and all its sub-fields can be set dynamically now.

Some of the ways in which the fifo compaction options can be set are:
- `SetOptions({{"compaction_options_fifo", "{max_table_files_size=1024}"}})`
- `SetOptions({{"compaction_options_fifo", "{ttl=600;}"}})`
- `SetOptions({{"compaction_options_fifo", "{max_table_files_size=1024;ttl=600;}"}})`
- `SetOptions({{"compaction_options_fifo", "{max_table_files_size=51;ttl=49;allow_compaction=true;}"}})`

Most of the code has been made generic enough so that it could be reused later to make universal options (and other such nested defined-types) dynamic with very few lines of parsing/serializing code changes.
Introduced a few new functions like `ParseStruct`, `SerializeStruct` and `GetStringFromStruct`.
The duplicate code in `GetStringFromDBOptions` and `GetStringFromColumnFamilyOptions` has been moved into `GetStringFromStruct`. So they become just simple wrappers now.
Closes https://github.com/facebook/rocksdb/pull/3006

Differential Revision: D6058619

Pulled By: sagar0

fbshipit-source-id: 1e8f78b3374ca5249bb4f3be8a6d3bb4cbc52f92
2017-10-19 15:26:36 -07:00
Dmitri Smirnov ebab2e2d42 Enable MSVC W4 with a few exceptions. Fix warnings and bugs
Summary: Closes https://github.com/facebook/rocksdb/pull/3018

Differential Revision: D6079011

Pulled By: yiwu-arbug

fbshipit-source-id: 988a721e7e7617967859dba71d660fc69f4dff57
2017-10-19 10:57:12 -07:00
Sagar Vemuri b74999458f Update RocksDB Authors File
Summary: Update RocksDB Authors File.

Reviewed By: yiwu-arbug

Differential Revision: D6075453

fbshipit-source-id: dff52f483aab33c41de391f145a8273acfd6cbde
2017-10-18 14:42:10 -07:00
Gihwan Oh 7deed2b43c Fix a typo in a comment
Summary:
instad of for specific level -> instead of a specific level
Closes https://github.com/facebook/rocksdb/pull/3040

Differential Revision: D6090811

Pulled By: sagar0

fbshipit-source-id: 499edef0a6f596c448f61791e6aca8f5cce08e9c
2017-10-18 12:32:28 -07:00
Maysam Yabandeh 7e38238981 WritePrepared Txn: Disable GC during recovery
Summary:
Disables GC during recovery of a WritePrepared txn db to avoid GCing uncommitted key values.
Closes https://github.com/facebook/rocksdb/pull/2980

Differential Revision: D6000191

Pulled By: maysamyabandeh

fbshipit-source-id: fc4d522c643d24ebf043f811fe4ecd0dd0294675
2017-10-18 09:11:50 -07:00
Nikhil Benesch 7891af8b53 expose a hook to skip tables during iteration
Summary:
As discussed on the mailing list (["Skipping entire SSTs while iterating"](https://groups.google.com/forum/#!topic/rocksdb/ujHCJVLrHlU)), this patch adds a `table_filter` to `ReadOptions` that allows specifying a callback to be executed during iteration before each table in the database is scanned. The callback is passed the table's properties; the table is scanned iff the callback returns true.

This can be used in conjunction with a `TablePropertiesCollector` to dramatically speed up scans by skipping tables that are known to contain irrelevant data for the scan at hand.

We're using this [downstream in CockroachDB](https://github.com/cockroachdb/cockroach/blob/master/pkg/storage/engine/db.cc#L2009-L2022) already. With this feature, under ideal conditions, we can reduce the time of an incremental backup in  from hours to seconds.

FYI, the first commit in this PR fixes a segfault that I unfortunately have not figured out how to reproduce outside of CockroachDB. I'm hoping you accept it on the grounds that it is not correct to return 8-byte aligned memory from a call to `malloc` on some 64-bit platforms; one correct approach is to infer the necessary alignment from `std::max_align_t`, as done here. As noted in the first commit message, the bug is tickled by having a`std::function` in `struct ReadOptions`. That is, the following patch alone is enough to cause RocksDB to segfault when run from CockroachDB on Darwin.

```diff
 --- a/include/rocksdb/options.h
+++ b/include/rocksdb/options.h
@@ -1546,6 +1546,13 @@ struct ReadOptions {
   // Default: false
   bool ignore_range_deletions;

+  // A callback to determine whether relevant keys for this scan exist in a
+  // given table based on the table's properties. The callback is passed the
+  // properties of each table during iteration. If the callback returns false,
+  // the table will not be scanned.
+  // Default: empty (every table will be scanned)
+  std::function<bool(const TableProperties&)> table_filter;
+
   ReadOptions();
   ReadOptions(bool cksum, bool cache);
 };
```

/cc danhhz
Closes https://github.com/facebook/rocksdb/pull/2265

Differential Revision: D5054262

Pulled By: yiwu-arbug

fbshipit-source-id: dd6b28f2bba6cb8466250d8c5c542d3c92785476
2017-10-17 22:12:00 -07:00
Yi Wu eaaef91178 Blob DB: Store blob index as kTypeBlobIndex in base db
Summary:
Blob db insert blob index to base db as kTypeBlobIndex type, to tell apart values written by plain rocksdb or blob db. This is to make it possible to migrate from existing rocksdb to blob db.

Also with the patch blob db garbage collection get away from OptimisticTransaction. Instead it use a custom write callback to achieve similar behavior as OptimisticTransaction. This is because we need to pass the is_blob_index flag to DBImpl::Get but OptimisticTransaction don't support it.
Closes https://github.com/facebook/rocksdb/pull/3000

Differential Revision: D6050044

Pulled By: yiwu-arbug

fbshipit-source-id: 61dc72ab9977625e75f78cd968e7d8a3976e3632
2017-10-17 17:28:11 -07:00
Yi Wu 0552029b5c Blob DB: not writing sequence number as blob record footer
Summary:
Previously each time we write a blob we write blog_record_header + key + value + blob_record_footer to blob log. The footer only contains a sequence and a crc for the sequence number. The sequence number was used in garbage collection to verify the value is recent. After #2703 we moved to use optimistic transaction and no longer use sequence number from the footer. Remove the footer altogether.

There's another usage of sequence number and we are keeping it: Each blob log file keep track of sequence number range of keys in it, and use it to check if it is reference by a snapshot, before being deleted.
Closes https://github.com/facebook/rocksdb/pull/3005

Differential Revision: D6057585

Pulled By: yiwu-arbug

fbshipit-source-id: d6da53c457a316e9723f359a1b47facfc3ffe090
2017-10-17 12:13:08 -07:00
zhangjinpeng1987 966b32b57c fix delete range bug
Summary:
Fix this [issue](https://github.com/facebook/rocksdb/issues/2989).
ajkr PTAL

Close #2989
Closes https://github.com/facebook/rocksdb/pull/3017

Differential Revision: D6078541

Pulled By: yiwu-arbug

fbshipit-source-id: ef3db87b37b9156f83ca468aa39dea1f6dbde49d
2017-10-17 11:13:19 -07:00
Nikhil Benesch c0208dffbe arena: derive alignment unit from std::max_align_t
Summary:
As raised in #2265, the arena allocator will return memory that is improperly aligned to store a `std::function` on macOS. Oddly, I'm unable to tickle this bug without adding a `std::function` field to `struct ReadOptions`—but my proposal in #2265 does exactly that.

In any case, here's a simple reproduction. Apply this bogus patch to get a `std::function` into `struct ReadOptions`

```
 --- a/include/rocksdb/options.h
+++ b/include/rocksdb/options.h
@@ -1035,6 +1035,8 @@ struct ReadOptions {
   // Default: 0
   uint64_t max_skippable_internal_keys;

+  std::function<void()> foo;
+
   ReadOptions();
   ReadOptions(bool cksum, bool cache);
 };
```

then compile `db_properties_test` *with ubsan* and run `ReadLatencyHistogramByLevel`:

```
$ make COMPILE_WITH_UBSAN=1 db_properties_test
$ ./db_properties_test --gtest_filter=DBPropertiesTest.ReadLatencyHistogramByLevel
```

ubsan will complain about several misaligned accesses:

```
Note: Google Test filter = DBPropertiesTest.ReadLatencyHistogramByLevel
[==========] Running 1 test from 1 test case.
[----------] Global test environment set-up.
[----------] 1 test from DBPropertiesTest
[ RUN      ] DBPropertiesTest.ReadLatencyHistogramByLevel
util/coding.h:372:12: runtime error: load of misaligned address 0x00010d85516c for type 'const unsigned long', which requires 8 byte alignment
0x00010d85516c: note: pointer points here
  01 00 34 57 00 00 00 00  02 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  78 24 82 0a 01 00 00 00
              ^
util/coding.h:362:3: runtime error: store to misaligned address 0x7fff5733fac4 for type 'unsigned long', which requires 8 byte alignment
0x7fff5733fac4: note: pointer points here
  01 00 00 00 00 00 00 00  02 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  80 1d 96 0d 01 00 00 00
              ^
util/coding.h:372:12: runtime error: load of misaligned address 0x00010d85516c for type 'const unsigned long', which requires 8 byte alignment
0x00010d85516c: note: pointer points here
  01 00 34 57 00 00 00 00  02 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  78 24 82 0a 01 00 00 00
              ^
version_set.cc:854: runtime error: constructor call on misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
version_set.cc:512: runtime error: constructor call on misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
version_set.cc:505: runtime error: constructor call on misaligned address 0x00010dbfa5e8 for type 'rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
options.h:931: runtime error: constructor call on misaligned address 0x00010dbfa5e8 for type 'rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
options.h:931: runtime error: constructor call on misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
functional:1583: runtime error: constructor call on misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1585:9: runtime error: member access within misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1585:9: runtime error: store to misaligned address 0x00010dbfa648 for type '__base *' (aka '__base<void ()> *'), which requires 16 byte alignment
0x00010dbfa648: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
db/version_set.cc:864:29: runtime error: upcast of misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:521:12: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:521:12: runtime error: load of misaligned address 0x00010dbfa5d8 for type 'rocksdb::TableCache *', which requires 16 byte alignment
0x00010dbfa5d8: note: pointer points here
 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00
              ^
db/version_set.cc:522:9: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:522:9: runtime error: reference binding to misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
db/version_set.cc:522:24: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:522:38: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:522:57: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:522:57: runtime error: load of misaligned address 0x00010dbfa678 for type 'rocksdb::RangeDelAggregator *', which requires 16 byte alignment
0x00010dbfa678: note: pointer points here
 01 00 00 00  d0 a1 bf 0d 01 00 00 00  00 00 00 00 00 00 00 00  f8 db 70 0a 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:523:54: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:523:54: runtime error: load of misaligned address 0x00010dbfa668 for type 'rocksdb::HistogramImpl *', which requires 16 byte alignment
0x00010dbfa668: note: pointer points here
 01 00 00 00  c8 88 a5 0d 01 00 00 00  00 00 00 00 01 00 00 00  d0 a1 bf 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:524:9: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:524:47: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:524:62: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/table_cache.cc:228:33: runtime error: reference binding to misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
table/block_based_table_reader.cc:1554:41: runtime error: reference binding to misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
table/block_based_table_reader.cc:1396:21: runtime error: reference binding to misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
include/rocksdb/options.h:931:8: runtime error: reference binding to misaligned address 0x00010dbfa628 for type 'const std::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1584:13: runtime error: load of misaligned address 0x00010dbfa648 for type '__base *const' (aka '__base<void ()> *const'), which requires 16 byte alignment
0x00010dbfa648: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  c8 a5 97 0d 01 00 00 00  38 36 9b 0d
              ^
table/block_based_table_reader.cc:1555:24: runtime error: reference binding to misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
db/table_cache.cc:244:54: runtime error: load of misaligned address 0x00010dbfa618 for type 'const bool', which requires 16 byte alignment
0x00010dbfa618: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
db/table_cache.cc:246:49: runtime error: reference binding to misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
db/version_set.cc:532:12: runtime error: member access within misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
db/version_set.cc:532:12: runtime error: member access within misaligned address 0x00010dbfa5e8 for type 'const rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
db/version_set.cc:532:26: runtime error: load of misaligned address 0x00010dbfa5f8 for type 'const rocksdb::Slice *const', which requires 16 byte alignment
0x00010dbfa5f8: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
version_set.cc:493: runtime error: member call on misaligned address 0x00010dbfa5c8 for type 'rocksdb::(anonymous namespace)::LevelFileIteratorState', which requires 16 byte alignment
0x00010dbfa5c8: note: pointer points here
 00 00 00 00  a0 db 70 0a 01 00 00 00  00 00 00 00 00 00 00 00  90 14 98 0d 01 00 00 00  00 00 00 00
              ^
version_set.cc:493: runtime error: member call on misaligned address 0x00010dbfa5e8 for type 'rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
options.h:931: runtime error: member call on misaligned address 0x00010dbfa5e8 for type 'rocksdb::ReadOptions', which requires 16 byte alignment
0x00010dbfa5e8: note: pointer points here
 00 00 00 00  01 01 ff ff ff ff ff ff  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
options.h:931: runtime error: member call on misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
functional:1765: runtime error: member call on misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1766:9: runtime error: member access within misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1766:9: runtime error: load of misaligned address 0x00010dbfa648 for type '__base *' (aka '__base<void ()> *'), which requires 16 byte alignment
0x00010dbfa648: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  c8 a5 97 0d 01 00 00 00  38 36 9b 0d
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1766:27: runtime error: member access within misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1768:14: runtime error: member access within misaligned address 0x00010dbfa628 for type 'std::__1::function<void ()>', which requires 16 byte alignment
0x00010dbfa628: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00
              ^
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/functional:1768:14: runtime error: load of misaligned address 0x00010dbfa648 for type '__base *' (aka '__base<void ()> *'), which requires 16 byte alignment
0x00010dbfa648: note: pointer points here
 00 00 00 00  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  c8 a5 97 0d 01 00 00 00  38 36 9b 0d
              ^
[       OK ] DBPropertiesTest.ReadLatencyHistogramByLevel (1599 ms)
[----------] 1 test from DBPropertiesTest (1599 ms total)

[----------] Global test environment tear-down
[==========] 1 test from 1 test case ran. (1599 ms total)
[  PASSED  ] 1 test.
```

So it seems the root cause is that the internal implementation of `std::function` on macOS (and perhaps with libc++ generally?) requires 16-byte aligned memory, but the arena allocator only guarantees that the returned memory will be `sizeof(void*)` aligned, which is only 8-byte alignment on my machine. This patch solves the problem by adjusting the allocator to derive the necessary alignment from `alignof(std::max_align_t)`, which is properly 16 bytes on my machine.

As I mentioned in #2265, none of RocksDB's tests will cause this unaligned access to actually abort the process, but, on macOS, linking CockroachDB against a version of RocksDB with the above patch and letting it run for just a few seconds will cause a SIGABRT.

```
Process 19792 stopped
* thread #2, stop reason = EXC_BAD_ACCESS (code=EXC_I386_GPFLT)
    frame #0: 0x0000000004f5e78f cockroach`DBNewIter + 95
cockroach`DBNewIter:
->  0x4f5e78f <+95>:  callq  *0x28(%rax)
    0x4f5e792 <+98>:  jmp    0x4f5e79e                 ; <+110>
    0x4f5e794 <+100>: movq   -0x50(%rbp), %rcx
    0x4f5e798 <+104>: movq   %rax, %rdi
(lldb) bt
* thread #2, stop reason = EXC_BAD_ACCESS (code=EXC_I386_GPFLT)
  * frame #0: 0x0000000004f5e78f cockroach`DBNewIter + 95
```

I'd get you a backtrace, but [Go doesn't include cgo debug information on macOS](https://github.com/golang/go/issues/6942). I've also tried building against libc++ on Linux, where debug information would be available, but I can't seem to trigger the bug there.

In any case, this PR both fixes the segfault in CockroachDB and fixes the warnings reported by ubsan.
Closes https://github.com/facebook/rocksdb/pull/2347

Differential Revision: D5108596

Pulled By: yiwu-arbug

fbshipit-source-id: bd5e4323b2ce915ed4fe78e123cb8996aec75a00
2017-10-17 11:13:19 -07:00
Changli Gao b8cea7cc27 VersionBuilder: Erase with iterators for better performance
Summary: Closes https://github.com/facebook/rocksdb/pull/3007

Differential Revision: D6077701

Pulled By: yiwu-arbug

fbshipit-source-id: a6fd5b8a23f4feb1660b9ce027f651a7e90352b3
2017-10-17 10:12:37 -07:00
codeeply f7843f30a8 Move ~Comparator define to comparator.h
Summary:
When I impl my own comparator, and build in release mode.
The following compile error occurs.
undefined reference to `typeinfo for rocksdb::Comparator'

This fix allows users build with RTTI off when has their own comparator.
Closes https://github.com/facebook/rocksdb/pull/3008

Differential Revision: D6077354

Pulled By: yiwu-arbug

fbshipit-source-id: 914c26dbab72f0ad1f0e15f8666a3fb2f10bfed8
2017-10-17 09:58:13 -07:00
Yi Wu 8e63cad078 fix lite build
Summary:
* make `checksum_type_string_map` available for lite
* comment out `FilesPerLevel` in lite mode.
* travis and legocastle lite build also build `all` target and run tests
Closes https://github.com/facebook/rocksdb/pull/3015

Differential Revision: D6069822

Pulled By: yiwu-arbug

fbshipit-source-id: 9fe92ac220e711e9e6ed4e921bd25ef4314796a0
2017-10-17 08:57:09 -07:00
Andrew Kryczka 731895214b db_bench randomtransaction print throughput
Summary:
print throughput in MB/s upon finishing randomtransaction benchmark
Closes https://github.com/facebook/rocksdb/pull/3016

Differential Revision: D6070426

Pulled By: ajkr

fbshipit-source-id: 69df43beed4c374a36d826e761ca3a83e1fdcbf5
2017-10-16 18:42:25 -07:00
Yi Wu 60c09f5fbb print more table_options to info log
Summary:
print more table_options to info log
Closes https://github.com/facebook/rocksdb/pull/3003

Differential Revision: D6054490

Pulled By: yiwu-arbug

fbshipit-source-id: 8e6f96e08bdc906077b6c62ade419d7cb739110f
2017-10-13 14:42:26 -07:00
Yi Wu 10ba50e9eb Blob DB: Move BlobFile definition to a separate file
Summary:
simply move BlobFile definition from blob_db_impl.h to blob_file.h.
Closes https://github.com/facebook/rocksdb/pull/3002

Differential Revision: D6050143

Pulled By: yiwu-arbug

fbshipit-source-id: a8fb6e094fe39bdeace6279569834bc65aa64a34
2017-10-13 14:42:26 -07:00
Yi Wu 31d3e41810 PinnableSlice move assignment
Summary:
Allow `std::move(pinnable_slice)`.
Closes https://github.com/facebook/rocksdb/pull/2997

Differential Revision: D6036782

Pulled By: yiwu-arbug

fbshipit-source-id: 583fb0419a97e437ff530f4305822341cd3381fa
2017-10-12 18:28:24 -07:00
Sagar Vemuri cc67b22d6e Add OptionsUtil class to java/CMakeLists.txt
Summary:
Adding OptionsUtil java class and options_util.cc to java/CMakeLists.txt, which were missed accidentally when they were introduced in #2898.
Closes https://github.com/facebook/rocksdb/pull/2985

Differential Revision: D6015878

Pulled By: sagar0

fbshipit-source-id: 1abbd46db4aebad1e07ea53523eacbdcb12823e1
2017-10-12 16:57:05 -07:00
Adam Retter 560e984995 Added CompactionFilterFactory support to RocksJava
Summary:
This PR also includes some cleanup, bugfixes and refactoring of the Java API. However these are really pre-cursors on the road to CompactionFilterFactory support.
Closes https://github.com/facebook/rocksdb/pull/1241

Differential Revision: D6012778

Pulled By: sagar0

fbshipit-source-id: 0774465940ee99001a78906e4fed4ef57068ad5c
2017-10-12 11:12:16 -07:00
Andrew Kryczka 8dd0a7e11a add comment in SuperVersion referencing logic
Summary:
The referencing logic is super confusing so added a comment at the part that took me longest to figure out.
Closes https://github.com/facebook/rocksdb/pull/2996

Differential Revision: D6034969

Pulled By: ajkr

fbshipit-source-id: 9cc2e744c1f79d6d57d378f86ed59238a5f583db
2017-10-11 15:12:31 -07:00
Yi Wu fb4ae4d810 fix DBImpl::NewInternalIterator super-version leak on failure
Summary:
Close #2955
Closes https://github.com/facebook/rocksdb/pull/2960

Differential Revision: D5962872

Pulled By: yiwu-arbug

fbshipit-source-id: a6472d5c015bea3dc476c572ff5a5c90259e6059
2017-10-11 14:57:43 -07:00
Kefu Chai 019aa7074c cmake: pass "-msse4.2" to when building crc32c.cc if HAVE_SSE42
Summary:
it turns out that, with older GCC shipped from centos7, the SSE42
intrinsics are not available even with "target" specified. so we
need to pass "-msse42" for checking compiler's sse4.2 support and
for building crc32c.cc which uses sse4.2 intrinsics for crc32.

Signed-off-by: Kefu Chai <tchaikov@gmail.com>
Closes https://github.com/facebook/rocksdb/pull/2950

Differential Revision: D6032298

Pulled By: siying

fbshipit-source-id: 124c946321043661b3fb0a70b6cdf4c9c5126ab4
2017-10-11 12:26:46 -07:00
Yi Wu 38bbc879a5 fix travis failure for ccache command not found
Summary:
Travis don't have ccache installed on Mac. Only run the ccache command when it exists.
https://docs.travis-ci.com/user/caching/#ccache-cache
Closes https://github.com/facebook/rocksdb/pull/2990

Differential Revision: D6028837

Pulled By: yiwu-arbug

fbshipit-source-id: 1e2d1c7f37be2c73773258c1fd5f24eebe7a06c6
2017-10-10 22:26:33 -07:00
Zhongyi Xie 0f3b36964e Fix counter for memtable updates
Summary:
Right now in `PutCFImpl` we always increment NUMBER_KEYS_UPDATED counter for both in-place update or insertion. This PR fixes this by using the correct counter for either case.
Closes https://github.com/facebook/rocksdb/pull/2986

Differential Revision: D6016300

Pulled By: miasantreble

fbshipit-source-id: 0aed327522e659450d533d1c47d3a9f568fac65d
2017-10-10 21:26:11 -07:00
Andrew Kryczka 70aa942153 fix file numbers after repair
Summary:
The file numbers assigned post-repair were sometimes smaller than older files' numbers due to `LogAndApply` saving the wrong next file number in the manifest.

- Mark the highest file seen during repair as used before `LogAndApply` so the correct next file number will be stored.
- Renamed `MarkFileNumberUsedDuringRecovery` to `MarkFileNumberUsed` since now it's used during repair in addition to during recovery
- Added `TEST_Current_Next_FileNo` to expose the next file number for the unit test.
Closes https://github.com/facebook/rocksdb/pull/2988

Differential Revision: D6018083

Pulled By: ajkr

fbshipit-source-id: 3f25cbf74439cb8f16dd12af90b67f9f9f75e718
2017-10-10 13:12:37 -07:00
Jay Patel 1a61ba179e compaction picker to use max_bytes_for_level_multiplier_additional
Summary:
Hi,
As part of some optimization, we're using multiple DB locations (tmpfs and spindle) to store data and configured max_bytes_for_level_multiplier_additional. But, max_bytes_for_level_multiplier_additional is not used to compute the actual size for the level while picking the DB location. So, even if DB location does not have space, RocksDB mistakenly puts the level at that location.

Can someone pls. verify the fix? Let me know any other changes required.

Thanks,
Jay
Closes https://github.com/facebook/rocksdb/pull/2704

Differential Revision: D5992515

Pulled By: ajkr

fbshipit-source-id: cbbc6c0e0a7dbdca91c72e0f37b218c4cec57e28
2017-10-09 22:59:02 -07:00
Zhongyi Xie e2548366e1 add GetLiveFiles and GetLiveFilesMetaData for BlobDB
Summary: Closes https://github.com/facebook/rocksdb/pull/2976

Differential Revision: D5994759

Pulled By: miasantreble

fbshipit-source-id: 985c31dccb957cb970c302f813cd07a1e8cb6438
2017-10-09 19:56:04 -07:00
Yi Wu 8c392a31d7 WritePrepared Txn: Iterator
Summary:
On iterator create, take a snapshot, create a ReadCallback and pass the ReadCallback to the underlying DBIter to check if key is committed.
Closes https://github.com/facebook/rocksdb/pull/2981

Differential Revision: D6001471

Pulled By: yiwu-arbug

fbshipit-source-id: 3565c4cdaf25370ba47008b0e0cb65b31dfe79fe
2017-10-09 17:15:28 -07:00
Sagar Vemuri 5a38e18627 Make some WriteOptions defaults more explicit
Summary:
Some WriteOptions defaults were not clearly documented. So, added comments to make the defaults more explicit.
Closes https://github.com/facebook/rocksdb/pull/2984

Differential Revision: D6014500

Pulled By: sagar0

fbshipit-source-id: a28078818e335e42b303c1fc6fbfec692ed16c7c
2017-10-09 16:36:52 -07:00
Yi Wu 17c6325e8a WritePrepare Txn: Cancel flush/compaction before destruction
Summary:
On WritePreparedTxnDB destruct there could be running compaction/flush holding a SnapshotChecker, which holds a pointer back to WritePreparedTxnDB. Make sure those jobs finished before destructing WritePreparedTxnDB.

This is caught by TransactionTest::SeqAdvanceTest.
Closes https://github.com/facebook/rocksdb/pull/2982

Differential Revision: D6002957

Pulled By: yiwu-arbug

fbshipit-source-id: f1e70390c9798d1bd7959f5c8e2a1c14100773c3
2017-10-06 20:55:53 -07:00
Maysam Yabandeh ec6c5383d0 WritePrepared Txn: end-to-end tests
Summary:
Enable WritePrepared policy for existing transaction tests.
Closes https://github.com/facebook/rocksdb/pull/2972

Differential Revision: D5993614

Pulled By: maysamyabandeh

fbshipit-source-id: d1eb53e2920c4e2a56434bb001231c98426f3509
2017-10-06 14:26:45 -07:00
Sagar Vemuri da29eba43b Enable WAL for blob index
Summary:
Enabled WAL, during GC, for blob index which is stored on regular RocksDB.
Closes https://github.com/facebook/rocksdb/pull/2975

Differential Revision: D5997384

Pulled By: sagar0

fbshipit-source-id: b76c1487d8b5be0e36c55e8d77ffe3d37d63d85b
2017-10-06 10:59:31 -07:00
Yi Wu d1b74b0c82 WritePrepared Txn: Compaction/Flush
Summary:
Update Compaction/Flush to support WritePreparedTxnDB: Add SnapshotChecker which is a proxy to query WritePreparedTxnDB::IsInSnapshot. Pass SnapshotChecker to DBImpl on WritePreparedTxnDB open. CompactionIterator use it to check if a key has been committed and if it is visible to a snapshot. In CompactionIterator:
* check if key has been committed. If not, output uncommitted keys AS-IS.
* use SnapshotChecker to check if key is visible to a snapshot when in need.
* do not output key with seq = 0 if the key is not committed.
Closes https://github.com/facebook/rocksdb/pull/2926

Differential Revision: D5902907

Pulled By: yiwu-arbug

fbshipit-source-id: 945e037fdf0aa652dc5ba0ad879461040baa0320
2017-10-06 10:41:53 -07:00
Adrien Schildknecht 01542400a8 Inform caller when rocksdb is stalling writes
Summary:
Add a new function in Listener to let the caller know when rocksdb
is stalling writes.
Closes https://github.com/facebook/rocksdb/pull/2897

Differential Revision: D5860124

Pulled By: schischi

fbshipit-source-id: ee791606169aa64f772c86f817cebf02624e05e1
2017-10-05 18:11:43 -07:00
Yi Wu cc20ec3689 WritePrepared Txn: Test sequence number 0 is visible
Summary:
Compaction will output keys with sequence number 0, if it is visible to
earliest snapshot. Adding a test to make sure IsInSnapshot() report sequence number 0 is
visible to any snapshot.
Closes https://github.com/facebook/rocksdb/pull/2974

Differential Revision: D5990665

Pulled By: yiwu-arbug

fbshipit-source-id: ef50ebc777ff8ca688771f3ab598c7a609b0b65e
2017-10-05 16:26:44 -07:00
Andrew Kryczka 5a6ad9d52a release build treat warnings as errors
Summary:
fixing warnings is important, especially for release code.
Closes https://github.com/facebook/rocksdb/pull/2971

Differential Revision: D5980596

Pulled By: ajkr

fbshipit-source-id: 04f4ea3fb005dcda33d60342e4361e380bc4dfb1
2017-10-05 12:41:52 -07:00
Maysam Yabandeh 4e3c3d8c6a WritePrepared Txn: duplicate keys
Summary:
With WriteCommitted, when the write batch has duplicate keys, the txn db simply inserts them to the db with different seq numbers and let the db ignore/merge the duplicate values at the read time. With WritePrepared all the entries of the batch are inserted with the same seq number which prevents us from benefiting from this simple solution.

This patch applies a hackish solution to unblock the end-to-end testing. The hack is to be replaced with a proper solution soon. The patch simply detects the duplicate key insertions, and mark the previous one as obsolete. Then before writing to the db it rewrites the batch eliminating the obsolete keys. This would incur a memcpy cost. Furthermore handing duplicate merge would require to do FullMerge instead of simply ignoring the previous value, which is not handled by this patch.
Closes https://github.com/facebook/rocksdb/pull/2969

Differential Revision: D5976337

Pulled By: maysamyabandeh

fbshipit-source-id: 114e65b66f137d8454ff2d1d782b8c05da95f989
2017-10-05 07:41:02 -07:00
Andrew Kryczka 1026e794a3 rate limit auto-tuning
Summary:
Dynamic adjustment of rate limit according to demand for background I/O. It increases by a factor when limiter is drained too frequently, and decreases by the same factor when limiter is not drained frequently enough. The parameters for this behavior are fixed in `GenericRateLimiter::Tune`. Other changes:

- make rate limiter's `Env*` configurable for testing
- track num drain intervals in RateLimiter so we don't have to rely on stats, which may be shared across different DB instances from the ones that share the RateLimiter.
Closes https://github.com/facebook/rocksdb/pull/2899

Differential Revision: D5858704

Pulled By: ajkr

fbshipit-source-id: cc2bac30f85e7f6fd63655d0a6732ef9ed7403b1
2017-10-04 19:15:01 -07:00
Adam Kupczyk 75f7f42d41 Added CPU prefetch for skiplist
Summary:
This change causes following changes result of test:
./db_bench --writes 10000000 --benchmarks="fillrandom" --compression_type none
from
fillrandom   :       3.177 micros/op 314804 ops/sec;   34.8 MB/s
to
fillrandom   :       2.777 micros/op 360087 ops/sec;   39.8 MB/s
Closes https://github.com/facebook/rocksdb/pull/2961

Differential Revision: D5977822

Pulled By: yiwu-arbug

fbshipit-source-id: 1ea77707bffa978b1592b0c5d0fe76bfa1930f8d
2017-10-04 18:12:52 -07:00
Manuel Ung 88ed1f6ea6 Allow upgrades from nullptr to some merge operator
Summary:
Currently, RocksDB does not allow reopening a preexisting DB with no merge operator defined, with a merge operator defined. This means that if a DB ever want to add a merge operator, there's no way to do so currently.

Fix this by adding a new verification type `kByNameAllowFromNull` which will allow old values to be nullptr, and new values to be non-nullptr.
Closes https://github.com/facebook/rocksdb/pull/2958

Differential Revision: D5961131

Pulled By: lth

fbshipit-source-id: 06179bebd0d90db3d43690b5eb7345e2d5bab1eb
2017-10-04 09:57:23 -07:00
Andrew Kryczka 5b2cb64bfb Prevent threads from respawning during joining
Summary:
Previously the thread pool might be non-empty after joining since concurrent submissions could spawn new threads. This problem didn't affect our background flush/compaction thread pools because the `shutting_down_` flag prevented new jobs from being submitted during/after joining. But I wanted to be able to reuse the `ThreadPool` without such external synchronization.
Closes https://github.com/facebook/rocksdb/pull/2953

Differential Revision: D5951920

Pulled By: ajkr

fbshipit-source-id: 0efec7d0056d36d1338367da75e8b0c089bbc973
2017-10-03 16:27:28 -07:00
Andrew Kryczka 821887036e pin L0 filters/indexes for compaction outputs
Summary:
We need to tell the iterator the compaction output file's level so it can apply proper optimizations, like pinning filter and index blocks when user enables `pin_l0_filter_and_index_blocks_in_cache` and the output file's level is zero.
Closes https://github.com/facebook/rocksdb/pull/2949

Differential Revision: D5945597

Pulled By: ajkr

fbshipit-source-id: 2389decf9026ffaa32d45801a77d002529f64a62
2017-10-03 16:27:28 -07:00
Maysam Yabandeh 283d60761e fix valgrind leak report in unit test
Summary:
I cannot locally reproduce the valgrind leak report but based on my code inspection not deleting txn1 might be the reason.
```
==197848== 2,990 (544 direct, 2,446 indirect) bytes in 1 blocks are definitely lost in loss record 15 of 16
==197848==    at 0x4C2D06F: operator new(unsigned long) (in /usr/local/fbcode/gcc-5-glibc-2.23/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==197848==    by 0x7D5B31: rocksdb::WritePreparedTxnDB::BeginTransaction(rocksdb::WriteOptions const&, rocksdb::TransactionOptions const&, rocksdb::Transaction*) (pessimistic_transaction_db.cc:173)
==197848==    by 0x7D80C1: rocksdb::PessimisticTransactionDB::Initialize(std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> > const&) (pessimistic_transaction_db.cc:115)
==197848==    by 0x7DC42F: rocksdb::WritePreparedTxnDB::Initialize(std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> > const&) (pessimistic_transaction_db.cc:151)
==197848==    by 0x7D8CA0: rocksdb::TransactionDB::WrapDB(rocksdb::DB*, rocksdb::TransactionDBOptions const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> > const&, rocksdb::TransactionDB**) (pessimistic_transaction_db.cc:275)
==197848==    by 0x7D9F26: rocksdb::TransactionDB::Open(rocksdb::DBOptions const&, rocksdb::TransactionDBOptions const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::vector<rocksdb::ColumnFamilyDescriptor, std::allocator<rocksdb::ColumnFamilyDescriptor> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> >*, rocksdb::TransactionDB**) (pessimistic_transaction_db.cc:227)
==197848==    by 0x7DB349: rocksdb::TransactionDB::Open(rocksdb::Options const&, rocksdb::TransactionDBOptions const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, rocksdb::TransactionDB**) (pessimistic_transaction_db.cc:198)
==197848==    by 0x52ABD2: rocksdb::TransactionTest::ReOpenNoDelete() (transaction_test.h:87)
==197848==    by 0x51F7B8: rocksdb::WritePreparedTransactionTest_BasicRecoveryTest_Test::TestBody() (write_prepared_transaction_test.cc:843)
==197848==    by 0x857557: HandleSehExceptionsInMethodIfSupported<testing::Test, void> (gtest-all.cc:3824)
==197848==    by 0x857557: void testing::internal::HandleExceptionsInMethodIfSupported<testing::Test, void>(testing::Test*, void (testing::Test::*)(), char const*) (gtest-all.cc:3860)
==197848==    by 0x84E7EB: testing::Test::Run() [clone .part.485] (gtest-all.cc:3897)
==197848==    by 0x84E9BC: Run (gtest-all.cc:3888)
==197848==    by 0x84E9BC: testing::TestInfo::Run() [clone .part.486] (gtest-all.cc:4072)
```
Closes https://github.com/facebook/rocksdb/pull/2963

Differential Revision: D5968856

Pulled By: maysamyabandeh

fbshipit-source-id: 2ac512bbcad37dc8eeeffe4f363978913354180c
2017-10-03 14:58:07 -07:00
Sagar Vemuri 377e004048 Fix DBOptionsTest.SetBytesPerSync test when run with no compression
Summary:
Also made the test more easier to understand:
- changed the value size to ~1MB.
- switched to NoCompression. We don't anyway need compression in this test for dynamic options.

The test failures started happening starting from: #2893 .
Closes https://github.com/facebook/rocksdb/pull/2957

Differential Revision: D5959392

Pulled By: sagar0

fbshipit-source-id: 2d55641e429246328bc6d10fcb9ef540d6ce07da
2017-10-03 13:42:11 -07:00
Yi Wu 92ccae7123 speedup 'make check'
Summary:
Make SnapshotConcurrentAccessTest run in the beginning of the queue.

Test Plan
`make all check -j64` on devserver
Closes https://github.com/facebook/rocksdb/pull/2962

Differential Revision: D5965871

Pulled By: yiwu-arbug

fbshipit-source-id: 8cb5a47c2468be0fbbb929226a143ec5848bfaa9
2017-10-03 12:11:49 -07:00
Yi Wu d1cab2b64e Add ValueType::kTypeBlobIndex
Summary:
Add kTypeBlobIndex value type, which will be used by blob db only, to insert a (key, blob_offset) KV pair. The purpose is to
1. Make it possible to open existing rocksdb instance as blob db. Existing value will be of kTypeIndex type, while value inserted by blob db will be of kTypeBlobIndex.
2. Make rocksdb able to detect if the db contains value written by blob db, if so return error.
3. Make it possible to have blob db optionally store value in SST file (with kTypeValue type) or as a blob value (with kTypeBlobIndex type).

The root db (DBImpl) basically pretended kTypeBlobIndex are normal value on write. On Get if is_blob is provided, return whether the value read is of kTypeBlobIndex type, or return Status::NotSupported() status if is_blob is not provided. On scan allow_blob flag is pass and if the flag is true, return wether the value is of kTypeBlobIndex type via iter->IsBlob().

Changes on blob db side will be in a separate patch.
Closes https://github.com/facebook/rocksdb/pull/2886

Differential Revision: D5838431

Pulled By: yiwu-arbug

fbshipit-source-id: 3c5306c62bc13bb11abc03422ec5cbcea1203cca
2017-10-03 09:11:23 -07:00
Andrew Kryczka 880411f54c disable populating block cache for in-place updates
Summary:
There's no point populating the block cache during this read. The key we read is guaranteed to be overwritten with a new `kValueType` key immediately afterwards, so can't be accessed again. A user was seeing high turnover of data blocks, at least partially due to this.
Closes https://github.com/facebook/rocksdb/pull/2959

Differential Revision: D5961672

Pulled By: ajkr

fbshipit-source-id: e7cb27c156c5db3b32af355c780efb99dbdf087c
2017-10-02 20:41:24 -07:00
Maysam Yabandeh d27258d3a6 WritePrepared Txn: Rollback
Summary:
Implement the rollback of WritePrepared txns. For each modified value, it reads the value before the txn and write it back. This would cancel out the effect of transaction. It also remove the rolled back txn from prepared heap.
Closes https://github.com/facebook/rocksdb/pull/2946

Differential Revision: D5937575

Pulled By: maysamyabandeh

fbshipit-source-id: a6d3c47f44db3729f44b287a80f97d08dc4e888d
2017-10-02 19:59:27 -07:00
Sagar Vemuri bb38cd03a9 Limit number of merge operands in Cassandra merge operator
Summary:
Now that RocksDB supports conditional merging during point lookups (introduced in #2923), Cassandra value merge operator can be updated to pass in a limit. The limit needs to be passed in from the Cassandra code.
Closes https://github.com/facebook/rocksdb/pull/2947

Differential Revision: D5938454

Pulled By: sagar0

fbshipit-source-id: d64a72d53170d8cf202b53bd648475c3952f7d7f
2017-10-02 16:11:40 -07:00
Aliaksei Sandryhaila cf51d3eb73 Remove an "unused" variable
Summary:
PR 2893 introduced a variable that is only used in TEST_SYNC_POINT_CALLBACK. When RocksDB is not built in debug mode, this method is not compiled in, and the variable is unused, which triggers a compiler error.

This patch reverts the corresponding part of #2893.
Closes https://github.com/facebook/rocksdb/pull/2956

Reviewed By: yiwu-arbug

Differential Revision: D5955679

Pulled By: asandryh

fbshipit-source-id: ac4a8e85b22da7f02efb117cd2e4a6e07ba73390
2017-10-02 15:26:29 -07:00
Adam Retter 983028f097 RocksJava build target for Docker on ppc64le
Summary:
This enables us to crossbuild pcc64le RocksJava binaries with a suitably old version of glibc (2.17) on CentOS 7.
Closes https://github.com/facebook/rocksdb/pull/2491

Differential Revision: D5955301

Pulled By: sagar0

fbshipit-source-id: 69ef9746f1dc30ffde4063dc764583d8c7ae937e
2017-10-02 11:11:56 -07:00
Siying Dong 2a3363d52e ldb dump can print histogram of value size
Summary:
Make "ldb dump --count_only" print histogram of value size. Also, fix a bug that "ldb dump --path=<db_path>" doesn't work.
Closes https://github.com/facebook/rocksdb/pull/2944

Differential Revision: D5954527

Pulled By: siying

fbshipit-source-id: c620a444ec544258b8d113f5f663c375dd53d6be
2017-10-02 09:41:17 -07:00
Zhongyi Xie 593d3de371 No need for Restart Interval for meta blocks
Summary:
In SST files, restart interval helps us search in data blocks. However, some meta blocks will be read sequentially, so there's no need for restart points. Restart interval will introduce extra space in the block (https://github.com/facebook/rocksdb/blob/master/table/block_builder.cc#L80). We will see if we can remove this redundant space. (Maybe set restart interval to infinite.)
Closes https://github.com/facebook/rocksdb/pull/2940

Differential Revision: D5930139

Pulled By: miasantreble

fbshipit-source-id: 92b1b23c15cffa90378343ac846b713623b19c21
2017-09-29 20:26:20 -07:00
Maysam Yabandeh 2b22baf304 Add a template for issues
Summary:
This template reminds the users to use issues only for bug reports. The template is written according to the github guidelines at https://help.github.com/articles/creating-an-issue-template-for-your-repository/
Closes https://github.com/facebook/rocksdb/pull/2948

Differential Revision: D5943558

Pulled By: maysamyabandeh

fbshipit-source-id: c83b5d211ea8e334107141967689b2f0c453bbc9
2017-09-29 11:41:28 -07:00
Maysam Yabandeh ab0542f5ec Fix for when block.cache_handle is nullptr
Summary:
When using with compressed cache it is possible that the status is ok but the block is not actually added to the block cache. The patch takes this case into account.
Closes https://github.com/facebook/rocksdb/pull/2945

Differential Revision: D5937613

Pulled By: maysamyabandeh

fbshipit-source-id: 5428cf1115e5046b3d01ab78d26cb181122af4c6
2017-09-29 07:56:55 -07:00
Andrew Kryczka 5df172da2f fix deletion-triggered compaction in table builder
Summary:
It was broken when `NotifyCollectTableCollectorsOnFinish` was introduced. That function called `Finish` on each of the `TablePropertiesCollector`s, and `CompactOnDeletionCollector::Finish()` was resetting all its internal state. Then, when we checked whether compaction is necessary, the flag had already been cleared.

Fixed above issue by avoiding resetting internal state during `Finish()`. Multiple calls to `Finish()` are allowed, but callers cannot invoke `AddUserKey()` on the collector after any finishes.
Closes https://github.com/facebook/rocksdb/pull/2936

Differential Revision: D5918659

Pulled By: ajkr

fbshipit-source-id: 4f05e9d80e50ee762ba1e611d8d22620029dca6b
2017-09-28 18:17:30 -07:00
Maysam Yabandeh 385049baf2 WritePrepared Txn: Recovery
Summary:
Recover txns from the WAL. Also added some unit tests.
Closes https://github.com/facebook/rocksdb/pull/2901

Differential Revision: D5859596

Pulled By: maysamyabandeh

fbshipit-source-id: 6424967b231388093b4effffe0a3b1b7ec8caeb0
2017-09-28 16:56:45 -07:00
Yu Shu 8c724f5c7f Default one to rocksdb:x64-windows
Summary:
The default one will try to install rocksdb:x86-windows, which would lead to failing of the build at the last step (CMake Error, Rocksdb only supports x64). Because it will try to install a serials of x86 version package, and those cannot proceed to rocksdb:x86-windows building. By using rocksdb:x64-windows, we can make sure to install x64 version.
Tested on Win10 x64.
Closes https://github.com/facebook/rocksdb/pull/2941

Differential Revision: D5937139

Pulled By: sagar0

fbshipit-source-id: 15637fe23df59326a0e607bd4d5c48733e20bae3
2017-09-28 16:12:24 -07:00
Sagar Vemuri 93c2b91740 Introduce conditional merge-operator invocation in point lookups
Summary:
For every merge operand encountered for a key in the read path we now have the ability to decide whether to look further (to retrieve more merge operands for the key) or stop and invoke the merge operator to return the value. The user needs to override `ShouldMerge()` method with a condition to terminate search when true to avail this facility.

This has a couple of advantages:
1. It helps in limiting the number of merge operands that are looked at to compute a value as part of a user Get operation.
2. It allows to peek at a merge key-value to see if further merge operands need to look at.

Example: Limiting the number of merge operands that are looked at: Lets say you have 10 merge operands for a key spread over various levels. If you only want RocksDB to look at the latest two merge operands instead of all 10 to compute the value, it is now possible with this PR. You can set the condition in `ShouldMerge()` to return true when the size of the operand list is 2. Look at the example implementation in the unit test. Without this PR, a Get might look at all the 10 merge operands in different levels before invoking the merge-operator.

Added a new unit test.
Made sure that there is no perf regression by running benchmarks.

Command line to Load data:
```
TEST_TMPDIR=/dev/shm ./db_bench --benchmarks="mergerandom" --merge_operator="uint64add" --num=10000000
...
mergerandom  :      12.861 micros/op 77757 ops/sec;    8.6 MB/s ( updates:10000000)
```

**ReadRandomMergeRandom bechmark results:**
Command line:
```
TEST_TMPDIR=/dev/shm ./db_bench --benchmarks="readrandommergerandom" --merge_operator="uint64add" --num=10000000
```

Base -- Without this code change (on commit fc7476b):
```
readrandommergerandom :      38.586 micros/op 25916 ops/sec; (reads:3001599 merges:6998401 total:10000000 hits:842235 maxlength:8)
```

With this code change:
```
readrandommergerandom :      38.653 micros/op 25870 ops/sec; (reads:3001599 merges:6998401 total:10000000 hits:842235 maxlength:8)
```
Closes https://github.com/facebook/rocksdb/pull/2923

Differential Revision: D5898239

Pulled By: sagar0

fbshipit-source-id: daefa325019f77968639a75c851d46352c2303ef
2017-09-28 15:58:49 -07:00
Aliaksei Sandryhaila a48a398e7c Use RAII instead of pointers in cf_info_map
Summary:
There is no need for smart pointers in cf_info_map, so use RAII. This should also placate valgrind.
Closes https://github.com/facebook/rocksdb/pull/2943

Differential Revision: D5932941

Pulled By: asandryh

fbshipit-source-id: 2c37df88573a9df2557880a31193926e4425e054
2017-09-28 14:26:47 -07:00
Maysam Yabandeh c70586621c Blog post for 5.8 release
Summary: Closes https://github.com/facebook/rocksdb/pull/2942

Differential Revision: D5932858

Pulled By: maysamyabandeh

fbshipit-source-id: e11f52a0b08d65149bb49d99d1dbc82cb5a96fa0
2017-09-28 10:14:09 -07:00
Andrew Kryczka c2f6e45aa3 prevent nullptr dereference in table reader error case
Summary:
A user encountered segfault on the call to `CacheDependencies()`, probably because `NewIndexIterator()` failed before populating `*index_entry`. Let's avoid the call in that case.
Closes https://github.com/facebook/rocksdb/pull/2939

Differential Revision: D5928611

Pulled By: ajkr

fbshipit-source-id: 484be453dbb00e5e160e9c6a1bc933df7d80f574
2017-09-28 00:12:34 -07:00
Quinn Jarrell 6a541afcc4 Make bytes_per_sync and wal_bytes_per_sync mutable
Summary:
SUMMARY
Moves the bytes_per_sync and wal_bytes_per_sync options from immutableoptions to mutable options. Also if wal_bytes_per_sync is changed, the wal file and memtables are flushed.
TEST PLAN
ran make check
all passed

Two new tests SetBytesPerSync, SetWalBytesPerSync check that after issuing setoptions with a new value for the var, the db options have the new value.
Closes https://github.com/facebook/rocksdb/pull/2893

Reviewed By: yiwu-arbug

Differential Revision: D5845814

Pulled By: TheRushingWookie

fbshipit-source-id: 93b52d779ce623691b546679dcd984a06d2ad1bd
2017-09-27 17:49:45 -07:00
Yi Wu ec48e5c77f Add TransactionDB::SingleDelete()
Summary:
Looks like the API is simply missing. Adding it.
Closes https://github.com/facebook/rocksdb/pull/2937

Differential Revision: D5919955

Pulled By: yiwu-arbug

fbshipit-source-id: 6e2e9c96c29882b0bb4113d1f8efb72bffc57878
2017-09-27 10:27:26 -07:00
Sagar Vemuri 0806801dc8 DestroyDB API
Summary:
Expose DestroyDB API in RocksJava.
Closes https://github.com/facebook/rocksdb/pull/2934

Differential Revision: D5914775

Pulled By: sagar0

fbshipit-source-id: 84af6ea0d2bccdcfb9fe8c07b2f87373f0d5bab6
2017-09-26 16:42:11 -07:00
Maysam Yabandeh aa67bae6cf Break down PinnedDataIteratorRandomized
Summary:
Its timing out under tsan.
Closes https://github.com/facebook/rocksdb/pull/2928

Differential Revision: D5911766

Pulled By: maysamyabandeh

fbshipit-source-id: 2faacc07752ac8713a3a2abb5a4c4b7ae3bdf208
2017-09-26 14:27:30 -07:00
Siying Dong 4748911357 Add LogDevice to USERS.md
Summary: Closes https://github.com/facebook/rocksdb/pull/2927

Differential Revision: D5906613

Pulled By: siying

fbshipit-source-id: 607401e05b27508c816c700864fe81514606e4ef
2017-09-25 15:56:40 -07:00
Zhongyi Xie 1d6700f9e6 Add test kPointInTimeRecoveryCFConsistency
Summary:
Context/problem:

- CFs may be flushed at different times
- A WAL can only be deleted after all CFs have flushed beyond end of that WAL.
- Point-in-time recovery might stop upon reaching the first corruption.
- Some CFs may have already flushed beyond that point, while others haven't. We should fail the Open() instead of proceeding with inconsistent CFs.
Closes https://github.com/facebook/rocksdb/pull/2900

Differential Revision: D5863281

Pulled By: miasantreble

fbshipit-source-id: 180dbaf83d96c804cff49b3c406312a4ae61313e
2017-09-22 17:26:36 -07:00
Yi Wu be97dbb15c Fix WritePreparedTransactionTest::SeqAdvanceTest ASAN failure
Summary: Closes https://github.com/facebook/rocksdb/pull/2922

Differential Revision: D5895310

Pulled By: yiwu-arbug

fbshipit-source-id: 52c635a25d22478ec1eca49b6817551202babac2
2017-09-22 15:26:42 -07:00
Andrew Kryczka 4708a6875c Repair DBs with trailing slash in name
Summary:
Problem:

- `DB::SanitizeOptions` strips trailing slash from `wal_dir` but not `dbname`
- We check whether `wal_dir` and `dbname` refer to the same directory using string equality: https://github.com/facebook/rocksdb/blob/master/db/repair.cc#L258
- Providing `dbname` with trailing slash causes default `wal_dir` to be misidentified as a separate directory.
- Then the repair tries to add all SST files to the `VersionEdit` twice (once for `dbname` dir, once for `wal_dir`) and fails with coredump.

Solution:

- Add a new `Env` function, `AreFilesSame`, which uses device and inode number to check whether files are the same. It's currently only implemented in `PosixEnv`.
- Migrate repair to use `AreFilesSame` to check whether `dbname` and `wal_dir` are same. If unsupported, falls back to string comparison.
Closes https://github.com/facebook/rocksdb/pull/2827

Differential Revision: D5761349

Pulled By: ajkr

fbshipit-source-id: c839d548678b742af1166d60b09abd94e5476238
2017-09-22 12:42:22 -07:00
Andrew Kryczka fc7476bec1 fix populating range deletions in forward iterator
Summary:
fixes #2902
Closes https://github.com/facebook/rocksdb/pull/2917

Differential Revision: D5887175

Pulled By: ajkr

fbshipit-source-id: 364e292c636a3238bfc53b0fb9a01ff2f82dcbb9
2017-09-21 17:56:38 -07:00
Sagar Vemuri c8f3606731 Expose LoadLatestOptions, LoadOptionsFromFile and GetLatestOptionsFileName APIs in RocksJava
Summary:
JNI wrappers for LoadLatestOptions, LoadOptionsFromFile and GetLatestOptionsFileName APIs.
Closes https://github.com/facebook/rocksdb/pull/2898

Differential Revision: D5857934

Pulled By: sagar0

fbshipit-source-id: 68b79e83eab8de9416e3f1fef73e11cf7947e90a
2017-09-21 17:29:13 -07:00
Sagar Vemuri 96a13b4f4b Use jemalloc in rocksdbjni library built via vagrant
Summary:
Problem:
During RocksJava performance testing we found that the rocksdb jni library is not built with jemalloc; instead it was getting built with the default glibc malloc. We saw quite a bit of memory bloat due to this.

Addressed this by installing jemalloc-devel package in the vm that we use to build release jars.
Closes https://github.com/facebook/rocksdb/pull/2916

Differential Revision: D5887018

Pulled By: sagar0

fbshipit-source-id: ace0b5d60234b3a30dcd5d39633e7827a5982a50
2017-09-21 16:42:06 -07:00
PhaniShekhar 65a9cd6168 Use L1 size as estimate for L0 size in LevelCompactionBuilder::GetPathID
Summary:
Fix for [2461](https://github.com/facebook/rocksdb/issues/2461).

Problem: When using multiple db_paths setting with RocksDB, RocksDB incorrectly calculates the size of L1 in LevelCompactionBuilder::GetPathId.

max_bytes_for_level_base is used as L0 size and L1 size is calculated as (L0 size * max_bytes_for_level_multiplier). However, L1 size should be max_bytes_for_level_base.

Solution: Use max_bytes_for_level_base as L1 size. Also, use L1 size as the estimated size of L0.
Closes https://github.com/facebook/rocksdb/pull/2903

Differential Revision: D5885442

Pulled By: maysamyabandeh

fbshipit-source-id: 036da1c9298d173b9b80479cc6661ee4b7a951f6
2017-09-21 15:57:58 -07:00
Andrew Kryczka 8fc3de3c62 make rate limiter a general option
Summary:
it's unsupported in options file, so the flag should be respected by db_bench even when an options file is provided.
Closes https://github.com/facebook/rocksdb/pull/2910

Differential Revision: D5869836

Pulled By: ajkr

fbshipit-source-id: f67f591ae083e95e989f86b6fad50765d2e3d855
2017-09-21 11:11:00 -07:00
Yi Wu 1480e6f7cf Fix TransactionTest::SeqAdvanceTest ASAN failure
Summary:
The test didn't delete txn before creating a new one.
Closes https://github.com/facebook/rocksdb/pull/2913

Differential Revision: D5880236

Pulled By: yiwu-arbug

fbshipit-source-id: 7a4fcaada3d86332292754502cd8f4341143bf4f
2017-09-21 09:56:54 -07:00
Sagar Vemuri 3fc08fa88e Expose max_background_jobs option in RocksJava
Summary:
This option was introduced in the C++ API in RocksDB 5.6 in bb01c1880c . Now, exposing it through RocksJava API.
Closes https://github.com/facebook/rocksdb/pull/2908

Differential Revision: D5864224

Pulled By: sagar0

fbshipit-source-id: 140aa55dcf74b14e4d11219d996735c7fdddf513
2017-09-20 10:26:37 -07:00
Yao Zongyou 8ae81684e9 Update cmake_minimum_required to 2.8.12.
Summary:
Hello,

current master branch declares cmake_minimum_required (VERSION 2.8.11)
but cmake gives the following error:

[  6%] CMake Error at CMakeLists.txt:658 (install):
  install TARGETS given unknown argument "INCLUDES".

CMake Error at src/CMakeLists.txt:658 (install): install TARGETS given unknown argument "INCLUDES".

because this argument not supported on CMake versions prior 2.8.12
Closes https://github.com/facebook/rocksdb/pull/2904

Differential Revision: D5863430

Pulled By: yiwu-arbug

fbshipit-source-id: 0f7230e080add472ad4b87836b3104ea0b971a38
2017-09-19 12:01:09 -07:00
Yi Wu b4596c6174 Fix Get does not return super version on error
Summary:
This is caught when I was testing #2886.
Closes https://github.com/facebook/rocksdb/pull/2907

Differential Revision: D5863153

Pulled By: yiwu-arbug

fbshipit-source-id: 8c54759ba1a0dc101f24ab50423e35731300612d
2017-09-19 12:01:09 -07:00
Orgad Shaneh 34ebadf930 Fix MinGW build
Summary:
snprintf is defined as _snprintf, which doesn't exist in the std
namespace.
Closes https://github.com/facebook/rocksdb/pull/2298

Differential Revision: D5070457

Pulled By: yiwu-arbug

fbshipit-source-id: 6e1659ac3e86170653b174578da5a8ed16812cbb
2017-09-19 10:28:26 -07:00
Pengchao Wang e4234fbdcf collecting kValue type tombstone
Summary:
In our testing cluster, we found large amount tombstone has been promoted to kValue type from kMerge after reaching the top level of compaction. Since we used to only collecting tombstone in merge operator, those tombstones can never be collected.

This PR addresses the issue by adding a GC step in compaction filter, which is only for kValue type records. Since those record already reached the top of compaction (no earlier data exists) we can safely remove them in compaction filter without worrying old data appears.

This PR also removes an old optimization in cassandra merge operator for single merge operands.  We need to do GC even on a single operand, so the optimation does not make sense anymore.
Closes https://github.com/facebook/rocksdb/pull/2855

Reviewed By: sagar0

Differential Revision: D5806445

Pulled By: wpc

fbshipit-source-id: 6eb25629d4ce917eb5e8b489f64a6aa78c7d270b
2017-09-18 16:27:12 -07:00
Maysam Yabandeh 60beefd6e0 WritePrepared Txn: Advance seq one per batch
Summary:
By default the seq number in DB is increased once per written key. WritePrepared txns requires the seq to be increased once per the entire batch so that the seq would be used as the prepare timestamp by which the transaction is identified. Also we need to increase seq for the commit marker since it would give a unique id to the commit timestamp of transactions.

Two unit tests are added to verify our understanding of how the seq should be increased. The recovery path requires much more work and is left to another patch.
Closes https://github.com/facebook/rocksdb/pull/2885

Differential Revision: D5837843

Pulled By: maysamyabandeh

fbshipit-source-id: a08960b93d727e1cf438c254d0c2636fb133cc1c
2017-09-18 14:45:08 -07:00
Maysam Yabandeh c57050b770 Use the default copy constructor in Options
Summary:
Our current implementation of (semi-)copy constructor of DBOptions and ColumnFamilyOptions seems to intend value by value copy, which is what the default copy constructor does anyway. Moreover not using the default constructor has the risk of forgetting to add newly added options.

As an example, allow_2pc seems to be forgotten in the copy constructor which was causing one of the unit tests not seeing its effect.
Closes https://github.com/facebook/rocksdb/pull/2888

Differential Revision: D5846368

Pulled By: maysamyabandeh

fbshipit-source-id: 1ee92a2aeae93886754b7bc039c3411ea2458683
2017-09-15 17:15:10 -07:00
Siying Dong c319792059 Directly refernce perf_context internally.
Summary:
After 7f6c02dda1, the same get_perf_context() is called both of internally and externally. However, I found internally this is not got inlined. I don't know why this is the case, but directly referencing perf_context is the logical way to do.
Closes https://github.com/facebook/rocksdb/pull/2892

Differential Revision: D5843789

Pulled By: siying

fbshipit-source-id: b49777d8809f35847699291bb7f8ea2754c3af49
2017-09-15 17:15:10 -07:00
Yi Wu 6b3c71f6ed Fix DBImpl::NotifyOnCompactionCompleted data race
Summary:
Access of `cfd->current()` needs to hold db mutex. The data race is caught by TSAN but hard to reproduce: https://gist.github.com/yiwu-arbug/0fc6dc0de915297a1740aa9610be9373
Closes https://github.com/facebook/rocksdb/pull/2894

Differential Revision: D5843884

Pulled By: yiwu-arbug

fbshipit-source-id: 0a30a421bc96f51840821538ad6453dc0815a942
2017-09-15 11:56:31 -07:00
Yi Wu f47b4eeb1e Fix memory leak in OptionsTest::OptionsComposeDecompose
Summary:
Fixing asan error.
Closes https://github.com/facebook/rocksdb/pull/2887

Differential Revision: D5838895

Pulled By: yiwu-arbug

fbshipit-source-id: 1662ce9856eb5e6877675347dc2240f2acb6fae8
2017-09-15 11:37:37 -07:00
Ben Clay 382277d0fe JNI support for ReadOptions::iterate_upper_bound
Summary:
Plumbed ReadOptions::iterate_upper_bound through JNI.

Made the following design choices:
* Used Slice instead of AbstractSlice due to the anticipated usecase (key / key prefix). Can change this if anyone disagrees.
* Used Slice instead of raw byte[] which seemed cleaner but necessitated the package-private handle-based Slice constructor. Followed WriteBatch as an example.
* We need a copy constructor for ReadOptions, as we create one base ReadOptions for a particular usecase and clone -> change the iterate_upper_bound on each slice operation. Shallow copy seemed cleanest.
* Hold a reference to the upper bound slice on ReadOptions, in contrast to Snapshot.

Signed a Facebook CLA this morning.
Closes https://github.com/facebook/rocksdb/pull/2872

Differential Revision: D5824446

Pulled By: sagar0

fbshipit-source-id: 74fc51313a10a81ecd348625e2a50ca5b7766888
2017-09-14 18:28:20 -07:00
Siying Dong edcbb36944 Three code-level optimization to Iterator::Next()
Summary:
Three small optimizations:
(1) iter_->IsKeyPinned() shouldn't be called if read_options.pin_data is not true. This may trigger function call all the way down the iterator tree.
(2) reuse the iterator key object in DBIter::FindNextUserEntryInternal(). The constructor of the class has some overheads.
(3) Move the switching direction logic in MergingIterator::Next() to a separate function.

These three in total improves readseq performance by about 3% in my benchmark setting.
Closes https://github.com/facebook/rocksdb/pull/2880

Differential Revision: D5829252

Pulled By: siying

fbshipit-source-id: 991aea10c6d6c3b43769cb4db168db62954ad1e3
2017-09-14 17:57:31 -07:00
Siying Dong 885b1c682e Two small refactoring for better inlining
Summary:
Move uncommon code paths in RangeDelAggregator::ShouldDelete() and IterKey::EnlargeBufferIfNeeded() to a separate function, so that the inlined strcuture can be more optimized.

Optimize it because these places show up in CPU profiling, though minimum. The performance is really hard measure. I ran db_bench with readseq benchmark against in-memory DB many times. The variation is big, but it seems to show 1% improvements.
Closes https://github.com/facebook/rocksdb/pull/2877

Differential Revision: D5828123

Pulled By: siying

fbshipit-source-id: 41a49e229f91e9f8409f85cc6f0dc70e31334e4b
2017-09-14 15:41:49 -07:00
Oleksandr Anyshchenko ffac68367f Added save points for transactions C API
Summary:
Added possibility to set save points in transactions and then rollback to them
Closes https://github.com/facebook/rocksdb/pull/2876

Differential Revision: D5825829

Pulled By: yiwu-arbug

fbshipit-source-id: 62168992340bbcddecdaea3baa2a678475d1429d
2017-09-14 14:18:59 -07:00
Yi Wu 9a970c81af Fix WriteBatchWithIndex::GetFromBatchAndDB not allowing StackableDB
Summary: Closes https://github.com/facebook/rocksdb/pull/2881

Differential Revision: D5829682

Pulled By: yiwu-arbug

fbshipit-source-id: abb8fa14b58cea7c416282f9be19e8b1a7961c6e
2017-09-13 17:26:35 -07:00
Yi Wu a843df668b Fix use-after-free in c_tset
Summary:
Fix asan error introduce by #2823
Closes https://github.com/facebook/rocksdb/pull/2879

Differential Revision: D5828454

Pulled By: yiwu-arbug

fbshipit-source-id: 50777855667f4e7b634279a654c3bfa01a1ac729
2017-09-13 16:12:02 -07:00
Sagar Vemuri 2d6e42122b Remove 'experimental' comment around level_compaction_dynamic_level_bytes option
Summary:
Remove misleading 'experimental' comment around `level_compaction_dynamic_level_bytes` option. This is not experimental anymore and is ready for wider adoption. MyRocks is already using it in production.
Closes https://github.com/facebook/rocksdb/pull/2878

Differential Revision: D5828890

Pulled By: sagar0

fbshipit-source-id: fffb45f4999f689b7eca326e4f4caf472d40c5a9
2017-09-13 15:56:24 -07:00
Andrew Kryczka 464fb36de9 fix hanging after CompactFiles with L0 overlap
Summary:
Bug report: https://www.facebook.com/groups/rocksdb.dev/permalink/1389452781153232/

Non-empty `level0_compactions_in_progress_` was aborting `CompactFiles` after incrementing `bg_compaction_scheduled_`, and in that case we never decremented it. This blocked future compactions and prevented DB close as we wait for scheduled compactions to finish/abort during close.

I eliminated `CompactFiles`'s dependency on `level0_compactions_in_progress_`. Since it takes a contiguous span of L0 files -- through the last L0 file if any L1+ files are included -- it's fine to run in parallel with other compactions involving L0. We make the same assumption in intra-L0 compaction.
Closes https://github.com/facebook/rocksdb/pull/2849

Differential Revision: D5780440

Pulled By: ajkr

fbshipit-source-id: 15b15d3faf5a699aed4b82a58352d4a7bb23e027
2017-09-13 15:41:38 -07:00
Maysam Yabandeh 09713a64b3 WritePrepared Txn: Lock-free CommitMap
Summary:
We had two proposals for lock-free commit maps. This patch implements the latter one that was simpler. We can later experiment with both proposals.

In this impl each entry is an std::atomic of uint64_t, which are accessed via memory_order_acquire/release. In x86_64 arch this is compiled to simple reads and writes from memory.
Closes https://github.com/facebook/rocksdb/pull/2861

Differential Revision: D5800724

Pulled By: maysamyabandeh

fbshipit-source-id: 41abae9a4a5df050a8eb696c43de11c2770afdda
2017-09-13 12:12:11 -07:00
Oleksandr Anyshchenko 72e4190918 Additions for OptimisticTransactionDB in C API
Summary:
Added some bindings for `OptimisticTransactionDB` in C API
Closes https://github.com/facebook/rocksdb/pull/2823

Differential Revision: D5820672

Pulled By: yiwu-arbug

fbshipit-source-id: 7efd17f619cc0741feddd2050b8fc856f9288350
2017-09-13 12:12:11 -07:00
Andrew Kryczka 9d115d3689 regression test for missing init options
Summary:
test the `DBOptions(const Options&)` and `ColumnFamilyOptions(const Options&)` constructors. Actually this'll work better once we refactor `RandomInitDBOptions` / `RandomInitCFOptions` to use the authoritative sources of struct members: `db_options_type_info` / `cf_options_type_info` (internal task T21804189 for this).
Closes https://github.com/facebook/rocksdb/pull/2873

Differential Revision: D5817141

Pulled By: ajkr

fbshipit-source-id: 8567c20feced9d1751fdf1f4383e2af30f7e3591
2017-09-13 11:56:35 -07:00
gladiator f615f5604b fix missing manual_wal_flush for DBOptions ctor
Summary:
currently `ImmutableDBOptions::Dump` use default value for `concurrent_prepare` and `manual_wal_flush`, because DBOptions ctor does not init those member variables.

so in LOG file,  it will be
```
             Options.concurrent_prepare: 0
             Options.manual_wal_flush: 0
```
Closes https://github.com/facebook/rocksdb/pull/2864

Differential Revision: D5816240

Pulled By: ajkr

fbshipit-source-id: 82335e8bcae3dceedc6a99224e7998de5fad1e50
2017-09-12 18:01:08 -07:00
Amy Xu 5785b1fcb8 Fix naming in InternalKey
Summary:
- Switched all instances of SetMinPossibleForUserKey and SetMaxPossibleForUserKey in accordance to InternalKeyComparator's comparison logic
Closes https://github.com/facebook/rocksdb/pull/2868

Differential Revision: D5804152

Pulled By: axxufb

fbshipit-source-id: 80be35e04f2e8abc35cc64abe1fecb03af24e183
2017-09-12 17:17:42 -07:00
Bernhard M. Wiedemann 82860bd55c Use cmake TIMESTAMP function
Summary:
because it is not only platform independent
but also allows to override the build date
This helps to make ceph builds reproducible (that includes a fork of rockdb in a submodule)

Also adds UTC flag, to be independent of timezone.

Requires cmake-2.8.11+ from 2013
Closes https://github.com/facebook/rocksdb/pull/2848

Differential Revision: D5820189

Pulled By: yiwu-arbug

fbshipit-source-id: e3e8c1550e10e238c173f6c5d9ba15f71ad3ce28
2017-09-12 17:17:42 -07:00
Maysam Yabandeh 2d30aaae47 Exclude incompatible options in test
Summary:
options.enable_pipelined_write and options.concurrent_prepare are incompatible and should not be set together.
Closes https://github.com/facebook/rocksdb/pull/2875

Differential Revision: D5818358

Pulled By: maysamyabandeh

fbshipit-source-id: dad862508f00817ab302f8b61729accf38315fb8
2017-09-12 14:58:46 -07:00
Andrew Kryczka f5148ade10 support opening zero backups during engine init
Summary:
There are internal users who open BackupEngine for writing new backups only, and they don't care whether old backups can be read or not. The condition `BackupableDBOptions::max_valid_backups_to_open == 0` should be supported (previously in df74b775e6 I made the mistake of choosing 0 as a special value to disable the limit).
Closes https://github.com/facebook/rocksdb/pull/2819

Differential Revision: D5751599

Pulled By: ajkr

fbshipit-source-id: e73ac19eb5d756d6b68601eae8e43407ee4f2752
2017-09-12 13:26:34 -07:00
Archit Mishra 3c42807794 do not call merge when checking to see if key exists
Summary:
Changes:
* added check for value before merge is called on code path that should check if key exists
Closes https://github.com/facebook/rocksdb/pull/2814

Reviewed By: IslamAbdelRahman

Differential Revision: D5743966

Pulled By: armishra

fbshipit-source-id: 6ac4283bc510c8ca50827d87ef0ba631f2b33b18
2017-09-12 12:02:53 -07:00
Andrew Kryczka 025b85b4ac speedup DBTest.EncodeDecompressedBlockSizeTest
Summary:
it sometimes takes more than 10 minutes (i.e., times out) on our internal CI. mainly because bzip is super slow. so I reduced the amount of  work it tries to do.
Closes https://github.com/facebook/rocksdb/pull/2856

Differential Revision: D5795883

Pulled By: ajkr

fbshipit-source-id: e69f986ae60b44ecc26b6b024abd0f13bdf3a3c5
2017-09-12 11:26:47 -07:00
zawlazaw 044a71e27e Add iterator's SeekForPrev functionality to the java-api
Summary:
As discussed in #2742 , this pull-requests brings the iterator's [SeekForPrev()](https://github.com/facebook/rocksdb/wiki/SeekForPrev) functionality to the java-api. It affects all locations in the code where previously only Seek() was supported.

All code changes are essentially a copy & paste of the already existing implementations for Seek().
**Please Note**: the changes to the C++ code were applied without fully understanding its effect, so please take a closer look. However, since Seek() and SeekForPrev() provide exactly the same signature, I do not expect any mistake here.

The java-tests are extended by new tests for the additional functionality.

Compilation (`make rocksdbjavastatic`) and test (`java/make test`) run without errors.
Closes https://github.com/facebook/rocksdb/pull/2747

Differential Revision: D5721011

Pulled By: sagar0

fbshipit-source-id: c1f951cddc321592c70dd2d32bc04892f3f119f8
2017-09-12 10:56:29 -07:00
Siying Dong 64b6452e0c Make InternalKeyComparator final and directly use it in merging iterator
Summary:
Merging iterator invokes InternalKeyComparator.Compare() frequently to heap merge. By making InternalKeyComparator final and merging iterator to directly use InternalKeyComparator rather than through Iterator interface, we can give compiler a choice to avoid one more virtual function call if possible. I ran readseq benchmark in memory-only use case to make sure the performance at least doesn't regress.

I have to disable the final key word in debug build, as a hack test class depends on overriding the class.
Closes https://github.com/facebook/rocksdb/pull/2860

Differential Revision: D5800461

Pulled By: siying

fbshipit-source-id: ab876f22a09bb5c560740911412336e0e25ccb53
2017-09-11 12:04:21 -07:00
Siying Dong 2dd22e5449 Make DBIter class final
Summary:
DBIter is referenced in ArenaWrappedDBIter, which is a simple wrapper. If DBIter is final, some virtual function call can be avoided. Some functions can even be inlined, like DBIter.value() to ArenaWrappedDBIter.value() and DBIter.key() to ArenaWrappedDBIter.key(). The performance gain is hard to measure. I just ran the memory-only benchmark for readseq and saw it didn't regress. There shouldn't be any harm doing it. Just give compiler more choices.
Closes https://github.com/facebook/rocksdb/pull/2859

Differential Revision: D5799888

Pulled By: siying

fbshipit-source-id: 829788f91310c40282dcfb7e412e6ef489931143
2017-09-11 12:04:21 -07:00
Huachao Huang 2a5915049e Fix missing BYTES_PER_WRITE for pipeline write
Summary: Closes https://github.com/facebook/rocksdb/pull/2862

Differential Revision: D5805638

Pulled By: yiwu-arbug

fbshipit-source-id: 72d38c74395690023a719f400daff01527645a17
2017-09-11 11:41:27 -07:00
Maysam Yabandeh f46464d383 write-prepared txn: call IsInSnapshot
Summary:
This patch instruments the read path to verify each read value against an optional ReadCallback class. If the value is rejected, the reader moves on to the next value. The WritePreparedTxn makes use of this feature to skip sequence numbers that are not in the read snapshot.
Closes https://github.com/facebook/rocksdb/pull/2850

Differential Revision: D5787375

Pulled By: maysamyabandeh

fbshipit-source-id: 49d808b3062ab35e7ae98ad388f659757794184c
2017-09-11 09:14:48 -07:00
Maysam Yabandeh 9a4df72994 WritePrepared Txn: CommitBatch
Summary:
Implements CommitBatch and CommitWithoutPrepare for WritePreparedTxn
Closes https://github.com/facebook/rocksdb/pull/2854

Differential Revision: D5793999

Pulled By: maysamyabandeh

fbshipit-source-id: d8b9858221162c6ac7a1f6912cbd3481d0d8a503
2017-09-08 15:56:39 -07:00
Maysam Yabandeh fce6c892ab Advance max evicted seq in coarser granularity
Summary:
This patch advances the max_evicted_seq_ is larger granularities to reduce the overhead of updating the relevant data structures.

It also refactor the related code and adds testing to that. As part of this patch some of the TODOs for removing usage of non-static const members are also addressed.
Closes https://github.com/facebook/rocksdb/pull/2844

Differential Revision: D5772928

Pulled By: maysamyabandeh

fbshipit-source-id: f4fcc2948be69c034f10812cf922ce5ab82ef98c
2017-09-08 14:41:22 -07:00
Yi Wu dcd36a6aee Make it explicit blob db doesn't support CF
Summary:
Blob db doesn't currently support column families. Return NotSupported status explicitly.
Closes https://github.com/facebook/rocksdb/pull/2825

Differential Revision: D5757438

Pulled By: yiwu-arbug

fbshipit-source-id: 44de9408fd032c98e8ae337d4db4ed37169bd9fa
2017-09-08 11:11:04 -07:00
Andrew Kryczka 3cd7ea2e8a rename stall-related internal stats
Summary:
Some of these names, like `MEMTABLE_COMPACTION`, did not mean anything. Tried to give them descriptive names.
Closes https://github.com/facebook/rocksdb/pull/2852

Differential Revision: D5782822

Pulled By: ajkr

fbshipit-source-id: f2695c4124af4073da4492d7135bae2411220f3a
2017-09-07 18:26:18 -07:00
Siying Dong 0e99323ac2 Fix CLANG Analyze
Summary:
clang analyze shows warnings after we upgrade the CLANG version. Fix them.
Closes https://github.com/facebook/rocksdb/pull/2839

Differential Revision: D5769060

Pulled By: siying

fbshipit-source-id: 3f8e4df715590d8984f6564b608fa08cfdfa5f14
2017-09-07 14:28:06 -07:00
Kefu Chai ba3c58cab6 specify SSE42 'target' attribute for Fast_CRC32()
Summary:
if we enable SSE42 globally when compiling the tree for preparing a
portable binary, which could be running on CPU w/o SSE42 instructions
even the GCC on the building host is able to emit SSE42 code, this leads
to illegal instruction errors on machines not supporting SSE42. to solve
this problem, crc32 detects the supported instruction at runtime, and
selects the supported CRC32 implementation according to the result of
`cpuid`. but intrinics like "_mm_crc32_u64()" will not be available
unless the "target" machine is appropriately specified in the command
line, like "-msse42", or using the "target" attribute.

we could pass "-msse42" only when compiling crc32c.cc, and allow the
compiler to generate the SSE42 instructions, but we are still at the
risk of executing illegal instructions on machines does not support
SSE42 if the compiler emits code that is not guarded by our runtime
detection. and we need to do the change in both Makefile and CMakefile.

or, we can use GCC's "target" attribute to enable the machine specific
instructions on certain function. in this way, we have finer grained
control of the used "target". and no need to change the makefiles. so
we don't need to duplicate the changes on both makefile and cmake as
the previous approach.

this problem surfaces when preparing a package for GNU/Linux distribution,
and we only applies to optimization for SSE42, so using a feature
only available on GCC/Clang is not that formidable.
Closes https://github.com/facebook/rocksdb/pull/2807

Differential Revision: D5786084

Pulled By: siying

fbshipit-source-id: bca5c0f877b8d6fb55f58f8f122254a26422843d
2017-09-07 12:40:57 -07:00
Maysam Yabandeh 7e19a571e9 Remove unused TransactionCallback
Summary:
TransactionCallback was never used. Remove it to avoid confusion.
Closes https://github.com/facebook/rocksdb/pull/2853

Differential Revision: D5787219

Pulled By: maysamyabandeh

fbshipit-source-id: e2b6a89537e3770a269ad38be71c4b0b160a88ac
2017-09-07 12:17:18 -07:00
Andrew Kryczka 10ddd59ba7 fix CompactFiles inclusion of older L0 files
Summary:
if we're moving any L0 files down, we need to include older L0 files since they may contain older versions of the keys being moved down.
Closes https://github.com/facebook/rocksdb/pull/2845

Differential Revision: D5773800

Pulled By: ajkr

fbshipit-source-id: 9f0770a8eaaeea4c87df2e7a2a1d65bf9d7f4f7e
2017-09-06 11:42:25 -07:00
Maysam Yabandeh 79810e2d49 Skip write_prepared_transaction_test in travis
Summary:
The patch skips write_prepared_transaction_test from travis as they time out there. They are still covered in daily runs of tests.
Closes https://github.com/facebook/rocksdb/pull/2836

Differential Revision: D5767203

Pulled By: maysamyabandeh

fbshipit-source-id: 51045ef98a745197136e14b2ec02fc6f38081b75
2017-09-05 15:29:52 -07:00
Yi Wu ab95e293d2 Fix memory leak on blob db open
Summary:
Fixes #2820
Closes https://github.com/facebook/rocksdb/pull/2826

Differential Revision: D5757527

Pulled By: yiwu-arbug

fbshipit-source-id: f495b63700495aeaade30a1da5e3675848f3d72f
2017-09-01 14:13:51 -07:00
Maysam Yabandeh 37ae8cc60f Signal progress of the test to avoid timeout
Summary: Closes https://github.com/facebook/rocksdb/pull/2824

Differential Revision: D5756457

Pulled By: maysamyabandeh

fbshipit-source-id: dff53e945d8ac4ffe6775a2176424fd1a27fc189
2017-09-01 11:28:52 -07:00
Andrew Kryczka 3b23b1d8c6 fix HistogramWindowingImpl copy-{assignment,constructor}
Summary:
their arguments had a typo.
Closes https://github.com/facebook/rocksdb/pull/2821

Differential Revision: D5752408

Pulled By: ajkr

fbshipit-source-id: f2d84489c0c615b12a790f04c42d35cc0dccb02d
2017-09-01 11:11:56 -07:00
Andrew Kryczka 3b9a000c15 fix inclusive-exclusiveness of histogram ToString
Summary:
I spent too much time thinking about histograms lately and realized boundary values fall into the lower bucket, not the upper bucket. It's because we're using `std::map::lower_bound` here: https://github.com/facebook/rocksdb/blob/867fe92e5e65ce501069aa22c538757acfaade34/monitoring/histogram.cc#L53.  Fixed histogram's `ToString()` to reflect this.
Closes https://github.com/facebook/rocksdb/pull/2817

Differential Revision: D5751159

Pulled By: ajkr

fbshipit-source-id: 67432bb45849eec9b5bcc0d095551dbc0ee81766
2017-09-01 10:56:34 -07:00
Dmitri Smirnov 0ec90a7cc2 Add -DPORTABLE=1 to MSVC CI build
Summary:
Add -DPORTABLE=1
  port::cacheline_aligned_alloc() has arguments swapped which prevents every single test from running.
Closes https://github.com/facebook/rocksdb/pull/2815

Differential Revision: D5751661

Pulled By: siying

fbshipit-source-id: e0857d6e138ec46035b3c23d7c3c751901a0a4a0
2017-08-31 16:42:48 -07:00
Andrew Kryczka 4a90cbf429 Include statistics pointer in ImmutableDBOptions::Dump
Summary:
useful when debugging to tell whether a DB has stats enabled, and whether a stats object is shared across DBs.
Closes https://github.com/facebook/rocksdb/pull/2813

Differential Revision: D5741755

Pulled By: ajkr

fbshipit-source-id: 9b9d51dee77d14d415cd5da985d8d61b5b3837c3
2017-08-31 16:27:04 -07:00
Andrew Kryczka b97685aef6 fix backup engine when latest backup corrupt
Summary:
Backup engine is intentionally openable even when some backups are corrupt. Previously the engine could write new backups as long as the most recent backup wasn't corrupt. This PR makes the backup engine able to create new backups even when the most recent one is corrupt.

We now maintain two ID instance variables:

- `latest_backup_id_` is used when creating backup to choose the new ID
- `latest_valid_backup_id_` is used when restoring latest backup since we want most recent valid one
Closes https://github.com/facebook/rocksdb/pull/2804

Differential Revision: D5734148

Pulled By: ajkr

fbshipit-source-id: db440707b31df2c7b084188aa5f6368449e10bcf
2017-08-31 15:41:49 -07:00
Yi Wu 725bc403f8 update dependencies.sh
Summary:
Update dependencies.sh. Also update tbb to 4.3, which is the latest available in TP2.
Closes https://github.com/facebook/rocksdb/pull/2812

Differential Revision: D5741394

Pulled By: yiwu-arbug

fbshipit-source-id: cafa0b7179f9a44669e5ccace818a02b42336781
2017-08-31 15:26:24 -07:00
Kamalalochana Subbaiah e612e31740 Updated CRC32 Power Optimization Changes
Summary:
Support for PowerPC Architecture
Detecting AltiVec Support
Closes https://github.com/facebook/rocksdb/pull/2716

Differential Revision: D5606836

Pulled By: siying

fbshipit-source-id: 720262453b1546e5fdbbc668eff56848164113f3
2017-08-31 14:16:30 -07:00
Dmitri Smirnov 8fa4d108a2 Try to switch to Stduio 2017
Summary: Closes https://github.com/facebook/rocksdb/pull/2802

Differential Revision: D5746710

Pulled By: siying

fbshipit-source-id: daa621ba5fccb84c0d6cdb7755c5e09319c45cb4
2017-08-31 10:30:27 -07:00
Pengchao Wang 825a22c00c garbage collect tombstones in merge operator
Summary:
Remove cassandra tombstone when reaching the max compaction level (full merge). if all columns collected key will be removed in next compaction via compaction filter
Closes https://github.com/facebook/rocksdb/pull/2791

Reviewed By: sagar0

Differential Revision: D5722465

Pulled By: wpc

fbshipit-source-id: 61e9898a5686551653a16383255aeaab3197e65e
2017-08-31 10:11:54 -07:00
Maysam Yabandeh 26ac24f199 Add more unit test to write_prepared txns
Summary: Closes https://github.com/facebook/rocksdb/pull/2798

Differential Revision: D5724173

Pulled By: maysamyabandeh

fbshipit-source-id: fb6b782d933fb4be315b1a231a6a67a66fdc9c96
2017-08-31 09:41:27 -07:00
Sagar Vemuri 06b37eef7b Set defaults for high-pri and low-pri thread pools in regression test script
Summary:
**Summary**:
Set defaults for high-pri and low-pri thread pools in regression test script.

**Reason for this change**:
With #2680 , high-pri and low-pri thread pools get different numbers than before if  `num_high_pri_threads` and `num_low_pri_threads` options are not explicitly passed to db_bench in regression test script ... leading to a false-positive regression.

**Test Plan**:
REMOTE_HOST=udb1671.prn3 TEST_MODE=1 FBSOURCE=~/fbsource ~/fbsource/fbcode/rocks/tools/debug_regression_test.sh viewstate  (with very minor changes to the internals).

Observe P50 and P99 which showed up as regressions in our graphs.

Stats with the commit prior to #2680 , ie. 4f81ab3 :
seekrandomwhilewriting :      75.096 micros/op 13316 ops/sec;  168.6 MB/s (7499074 of 7500000 found)
Microseconds per seek:
Count: 120000000 Average: 1197.7254  StdDev: 33.35
Min: 187  Median: 980.5292  Max: 1816424
Percentiles: **P50: 980.53** P75: 1494.57 **P99: 4185.64** P99.9: 7800.11 P99.99: 15039.64

Stats at #2680, ie. at commit dce6d5a (false-positive regression):
seekrandomwhilewriting :      85.330 micros/op 11719 ops/sec;  148.4 MB/s (7499073 of 7500000 found)
Microseconds per seek:
Count: 120000000 Average: 1362.3261  StdDev: 27.86
Min: 185  Median: 1088.1915  Max: 652760
Percentiles: **P50: 1088.19** P75: 1658.12 **P99: 5361.15** P99.9: 7997.95 P99.99: 11730.07

Stats with the current change on top of dce6d5a :
seekrandomwhilewriting :      77.780 micros/op 12856 ops/sec;  162.8 MB/s (7499102 of 7500000 found)
Microseconds per seek:
Count: 120000000 Average: 1226.6744  StdDev: 17.16
Min: 185  Median: 994.2956  Max: 2553530
Percentiles: **P50: 994.30** P75: 1513.68 **P99: 4284.30** P99.9: 9338.64 P99.99: 23008.86
Closes https://github.com/facebook/rocksdb/pull/2801

Differential Revision: D5742338

Pulled By: sagar0

fbshipit-source-id: cc5d727c1a131f2a7070d1bb892efbe929b976ff
2017-08-30 17:29:34 -07:00
Andrew Kryczka c10cf166fa Dump non-final ZSTD compression type support
Summary: Closes https://github.com/facebook/rocksdb/pull/2810

Differential Revision: D5739947

Pulled By: ajkr

fbshipit-source-id: 09f99718b6b083c2711dcf17f7b68c305f3fd261
2017-08-30 16:41:24 -07:00
Artem Danilov 8a6708f5f2 Extend property map with compaction stats
Summary:
This branch extends existing property map which keeps values in doubles to keep values in strings so that it can be used to provide wider range of properties. The immediate need for that is to provide IO stall stats in an easy parseable way to MyRocks which is also part of this branch.
Closes https://github.com/facebook/rocksdb/pull/2794

Differential Revision: D5717676

Pulled By: Tema

fbshipit-source-id: e34ba5b79ba774697f7b97ce1138d8fd55471b8a
2017-08-30 15:26:55 -07:00
Changli Gao dc5f29f32f EnvWrapper: Forward more functions
Summary: Closes https://github.com/facebook/rocksdb/pull/2789

Differential Revision: D5738335

Pulled By: ajkr

fbshipit-source-id: f371303c42b144d0a0424e9304b0df545f073ad1
2017-08-30 15:26:50 -07:00
Maysam Yabandeh 266ac245af Bumping version to 5.8
Summary: Closes https://github.com/facebook/rocksdb/pull/2738

Differential Revision: D5736261

Pulled By: maysamyabandeh

fbshipit-source-id: 49d27e9ccd786c4056a3d586a060fe460ea883ac
2017-08-30 14:26:12 -07:00
Andrew Kryczka 64185c23ad update HISTORY.md for DeleteRange bug fix
Summary:
fixed in #2799
Closes https://github.com/facebook/rocksdb/pull/2805

Differential Revision: D5734324

Pulled By: ajkr

fbshipit-source-id: a285d4e84bf1018dc2257fd6c3e7c075a7243263
2017-08-29 22:26:47 -07:00
Yi Wu e83d6a02e3 Not using aligned_alloc with gcc4 + asan
Summary:
GCC < 5 + ASAN does not instrument aligned_alloc, which can make ASAN
report false-positive with "free on address which was not malloc" error.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=61693

Also suppress leak warning with LRUCache::DisownData().
Closes https://github.com/facebook/rocksdb/pull/2783

Differential Revision: D5696465

Pulled By: yiwu-arbug

fbshipit-source-id: 87c607c002511fa089b18cc35e24909bee0e74b4
2017-08-29 21:56:02 -07:00
Huachao Huang 0980dc6c9a Fix wrong smallest key of delete range tombstones
Summary:
Since tombstones are not stored in order, we may get a wrong smallest key if we only consider the first added tombstone.
Check https://github.com/facebook/rocksdb/issues/2752 for more details.
Closes https://github.com/facebook/rocksdb/pull/2799

Differential Revision: D5728217

Pulled By: ajkr

fbshipit-source-id: 4a53edb0ca80d2a9fcf10749e52d47d57d6417d3
2017-08-29 18:41:35 -07:00
Andrew Kryczka b767972313 avoid use-after-move error
Summary:
* db/range_del_aggregator.cc (AddTombstone): Avoid a potential
use-after-move bug. The original code would both use and move
`tombstone` in a context where the order of those operations is
not specified.  The fix is to perform the use on a new, preceding
statement.

Author: meyering
Closes https://github.com/facebook/rocksdb/pull/2796

Differential Revision: D5721163

Pulled By: ajkr

fbshipit-source-id: a1d328d6a77a17c6425e8069860a202e615e2f48
2017-08-29 12:11:56 -07:00
Paweł Bylica c41744270a CMake: Fix formatting
Summary:
This if followup of #2195.
Closes https://github.com/facebook/rocksdb/pull/2772

Differential Revision: D5722495

Pulled By: sagar0

fbshipit-source-id: 169d0cef53b03056ea7b9454954a35c707a67d52
2017-08-28 18:41:29 -07:00
Paweł Bylica c21ea8f7a6 CMake: Add support for CMake packages
Summary:
Adds support for CMake packages: https://cmake.org/cmake/help/v3.9/manual/cmake-packages.7.html#creating-packages.

This allow using RocksDB by other CMake projects this way:

```
cmake_minimum_required(VERSION 3.5)
project(rdbt)

find_package(RocksDB CONFIG)

add_executable(rdbt test.cpp)
target_link_libraries(rdbt PRIVATE RocksDB::rocksdb)
```
Closes https://github.com/facebook/rocksdb/pull/2773

Differential Revision: D5722587

Pulled By: sagar0

fbshipit-source-id: 0d90dc4a77b42a617cdbe1348a370e719c282b87
2017-08-28 17:14:37 -07:00
benoitc 5444345588 add Erlang to the list of language bindings
Summary:
small edit of the language binding file to add the Erlang binding.
Closes https://github.com/facebook/rocksdb/pull/2797

Differential Revision: D5722235

Pulled By: sagar0

fbshipit-source-id: 8ecd74996dad4cac19666783256cfa4d9ce09160
2017-08-28 16:43:16 -07:00
Maysam Yabandeh 2972a702a4 Minor updates to FlushWAL blog
Summary: Closes https://github.com/facebook/rocksdb/pull/2792

Differential Revision: D5715365

Pulled By: maysamyabandeh

fbshipit-source-id: 0837b93ea1d4b0a08dfb3cd0d1feb6e098ef26a4
2017-08-27 07:41:02 -07:00
Maysam Yabandeh fbfa3e7a43 WriteAtPrepare: Efficient read from snapshot list
Summary:
Divide the old snapshots to two lists: a few that fit into a cached array and the rest in a vector, which is expected to be empty in normal cases. The former is to optimize concurrent reads from snapshots without requiring locks. It is done by an array of std::atomic, from which std::memory_order_acquire reads are compiled to simple read instructions in most of the x86_64 architectures.
Closes https://github.com/facebook/rocksdb/pull/2758

Differential Revision: D5660504

Pulled By: maysamyabandeh

fbshipit-source-id: 524fcf9a8e7f90a92324536456912a99aaa6740c
2017-08-26 01:00:38 -07:00
Maysam Yabandeh b01f426f56 Blog post for FlushWAL
Summary: Closes https://github.com/facebook/rocksdb/pull/2790

Differential Revision: D5711609

Pulled By: maysamyabandeh

fbshipit-source-id: ea103dac013c0a6a031834541ad67e7d95a80fe8
2017-08-25 16:11:57 -07:00
Yi Wu 503db684f7 make blob file close synchronous
Summary:
Fixing flaky blob_db_test.

To close a blob file, blob db used to add a CloseSeqWrite job to the background thread to close it. Changing file close to be synchronous in order to simplify logic, and fix flaky blob_db_test.
Closes https://github.com/facebook/rocksdb/pull/2787

Differential Revision: D5699387

Pulled By: yiwu-arbug

fbshipit-source-id: dd07a945cd435cd3808fce7ee4ea57817409474a
2017-08-25 10:41:49 -07:00
Yi Wu 3c840d1a6d Allow DB reopen with reduced options.num_levels
Summary:
Allow user to reduce number of levels in LSM by issue a full CompactRange() and put the result in a lower level, and then reopen DB with reduced options.num_levels. Previous this will fail on reopen on when recovery replaying the previous MANIFEST and found a historical file was on a higher level than the new options.num_levels. The workaround was after CompactRange(), reopen the DB with old num_levels, which will create a new MANIFEST, and then reopen the DB again with new num_levels.

This patch relax the check of levels during recovery. It allows DB to open if there was a historical file on level > options.num_levels, but was also deleted.
Closes https://github.com/facebook/rocksdb/pull/2740

Differential Revision: D5629354

Pulled By: yiwu-arbug

fbshipit-source-id: 545903f6b36b6083e8cbaf777176aef2f488021d
2017-08-24 16:10:54 -07:00
Yi Wu 92bfd6c507 Fix DropColumnFamily data race
Summary:
It should hold db mutex while accessing max_total_in_memory_state_.
Closes https://github.com/facebook/rocksdb/pull/2784

Differential Revision: D5696536

Pulled By: yiwu-arbug

fbshipit-source-id: 45430634d7fe11909b38e42e5f169f618681c4ee
2017-08-24 14:56:04 -07:00
Maysam Yabandeh 7fdf735d5d Pinnableslice examples and blog post
Summary: Closes https://github.com/facebook/rocksdb/pull/2788

Differential Revision: D5700189

Pulled By: maysamyabandeh

fbshipit-source-id: 6f043e652093ff904e52f6d35190855781b87673
2017-08-24 12:26:07 -07:00
Andrew Kryczka 7fbb9eccaf support disabling checksum in block-based table
Summary:
store a zero as the checksum when disabled since it's easier to keep block trailer a fixed length.
Closes https://github.com/facebook/rocksdb/pull/2781

Differential Revision: D5694702

Pulled By: ajkr

fbshipit-source-id: 69cea9da415778ba2b600dfd9d0dfc8cb5188ecd
2017-08-23 19:40:47 -07:00
Andrew Kryczka 19cc66dc4f fix clang bug in block-based table reader
Summary:
This is the warning that clang considers a bug and has been causing it to fail:

```
table/block_based_table_reader.cc:240:27: warning: Potential leak of memory pointed to by 'block.value'
    for (; biter.Valid(); biter.Next()) {
                          ^~~~~
```

Actually clang just doesn't have enough knowledge to statically determine it's safe. We can teach it using an assert.
Closes https://github.com/facebook/rocksdb/pull/2779

Differential Revision: D5691225

Pulled By: ajkr

fbshipit-source-id: 3f0d545bf44636953b30ee5243c63239e8f16d8e
2017-08-23 15:12:05 -07:00
Andrew Kryczka 7eba54eb9b test compaction input-level split range tombstone assumption
Summary:
One of the core assumptions of DeleteRange is that files containing portions of the same range tombstone are treated as a single unit from the perspective of compaction picker. Need better tests for this. This PR adds the tests for manual compaction.
Closes https://github.com/facebook/rocksdb/pull/2769

Differential Revision: D5676677

Pulled By: ajkr

fbshipit-source-id: 1b4b3382b300ff7048b872911405fdf900e4fbec
2017-08-23 14:11:32 -07:00
Maysam Yabandeh cd26af3476 Add unit test for WritePrepared skeleton
Summary: Closes https://github.com/facebook/rocksdb/pull/2756

Differential Revision: D5660516

Pulled By: maysamyabandeh

fbshipit-source-id: f3f3d3b5f544007a7fbdd78e49e4738b4437c7ee
2017-08-23 13:56:03 -07:00
mkosieradzki a12479819d Improved transactions support in C API
Summary:
Solves #2632

Added OptimisticTransactionDB to the C API.
Added missing merge operations to Transaction.
Added missing get_for_update operation to transaction

If required I will create tests for this another day.
Closes https://github.com/facebook/rocksdb/pull/2633

Differential Revision: D5600906

Pulled By: yiwu-arbug

fbshipit-source-id: da23e4484433d8f59d471f778ff2ae210e3fe4eb
2017-08-23 12:40:28 -07:00
BH1XUW c10b391314 LANGUAGE-BINDINGS.md: add another rust binding
Summary:
I made another rust binding. 👻

* Use C++ API (instead of C API)
* Try to follow [Rust Guidelines](https://aturon.github.io/README.html)
* Working in progress (the APIs are not stable yet)
Closes https://github.com/facebook/rocksdb/pull/2438

Differential Revision: D5690612

Pulled By: siying

fbshipit-source-id: 11d3956c33b5e5366555afbf3786b782be3046e7
2017-08-23 12:12:21 -07:00
Andres Suarez 90177432e4 Remove leftover references to phutil_module_cache
Reviewed By: mzlee

Differential Revision: D5688624

fbshipit-source-id: c726b4e56bd823b994a7b713488fef93c6f796d0
2017-08-23 12:12:21 -07:00
Andrew Kryczka 234f33a3f9 allow nullptr Slice only as sentinel
Summary:
Allow `Slice` holding nullptr as a sentinel value but not in comparisons. This new restriction eliminates the need for the manual checks in 39ef900551, while still conforming to glibc's `memcmp` API. Thanks siying for the idea. Users may need to migrate, so mentioned it in HISTORY.md.
Closes https://github.com/facebook/rocksdb/pull/2777

Differential Revision: D5686016

Pulled By: ajkr

fbshipit-source-id: 03a2ca3fd9a0ebade9d0d5686c81d59a9534f563
2017-08-23 10:56:06 -07:00
Maysam Yabandeh ccf7f833e3 Use PinnableSlice in Transactions
Summary:
The ::Get from DB is not augmented with an overload method that takes a PinnableSlice instead of a string. Transactions however are not yet upgraded to use the new API. As a result, transaction users such as MyRocks cannot benefit from it. This patch updates the transactional API with a PinnableSlice overload.
Closes https://github.com/facebook/rocksdb/pull/2736

Differential Revision: D5645770

Pulled By: maysamyabandeh

fbshipit-source-id: f6af520df902f842de1bcf99bed3e8dfc43ad96d
2017-08-23 10:11:45 -07:00
Maysam Yabandeh 1dfcdb15f9 Extend pin_l0 to filter partitions
Summary:
This is the continuation of https://github.com/facebook/rocksdb/pull/2661 for filter partitions. When pin_l0 is set (along with cache_xxx), then open table open the filter partitions are loaded into the cache and pinned there.
Closes https://github.com/facebook/rocksdb/pull/2766

Differential Revision: D5671098

Pulled By: maysamyabandeh

fbshipit-source-id: 174f24018f1d7f1129621e7380287b65b67d2115
2017-08-23 07:56:08 -07:00
Andrew Kryczka 39ef900551 stop calling memcmp with nullptrs
Summary:
it doesn't take nullptr according to its declaration in glibc, and calling it in this way causes our sanitizers (ubsan, clang analyze) to fail.
Closes https://github.com/facebook/rocksdb/pull/2776

Differential Revision: D5683260

Pulled By: ajkr

fbshipit-source-id: 114b137ee188172f96eedc43139255cae7bee80a
2017-08-22 16:55:44 -07:00
Chen Shen 78cb6b6112 Provide byte[] version of SstFileWriter.merge to reduce GC Stall
Summary:
In Java API, `SstFileWriter.put/merge/delete` takes `Slice` type of key and value, which is a Java wrapper object around C++ Slice object.  The Slice object inherited [ `finalize`](https://github.com/facebook/rocksdb/blob/3c327ac2d0fd50bbd82fe1f1af5de909dad769e6/java/src/main/java/org/rocksdb/AbstractNativeReference.java#L69) method, which [added huge overhead](https://softwareengineering.stackexchange.com/questions/288715/is-overriding-object-finalize-really-bad/288753#288753) to JVM while creating new SstFile.

To address this issue, this PR overload the merge method to take Java byte array instead of the Slice object, and added unit test for it.

We also benchmark these two different merge function, where we could see GC Stall reduced from 50%  to 1%, and the throughput increased from 50MB to 200MB.
Closes https://github.com/facebook/rocksdb/pull/2746

Reviewed By: sagar0

Differential Revision: D5653145

Pulled By: scv119

fbshipit-source-id: b55ea58554b573d0b1c6f6170f8d9223811bc4f5
2017-08-22 12:55:24 -07:00
Andrew Kryczka 867fe92e5e Scale histogram bucket size by constant factor
Summary:
The goal is to reduce the number of histogram buckets, particularly now that we print these histograms for each column family. I chose 1.5 as the factor. We can adjust it later to either make buckets more granular or make fewer buckets.
Closes https://github.com/facebook/rocksdb/pull/2139

Differential Revision: D4872076

Pulled By: ajkr

fbshipit-source-id: 87790d782a605506c3d24190a028cecbd7aa564a
2017-08-21 17:10:40 -07:00
Paweł Bylica f004307e9b CMake improvements
Summary:
- Allow setting custom installation prefix.
- Add option to disable building tests.
Closes https://github.com/facebook/rocksdb/pull/2195

Differential Revision: D5054239

Pulled By: sagar0

fbshipit-source-id: 2de6bef8b7eafed60a830e1796b262f9e6f79da0
2017-08-21 14:56:50 -07:00
Archit Mishra 09ac6206ab Circumvent ASAN false positive
Summary:
Changes:
* checks if ASAN mode is on, and uses malloc and free in the constructor and destructor
Closes https://github.com/facebook/rocksdb/pull/2767

Differential Revision: D5671243

Pulled By: armishra

fbshipit-source-id: 8e4ad0f7f163400c4effa8617d3b30134119d802
2017-08-21 12:10:43 -07:00
yiwu-arbug 5b68b114f1 Blob db create a snapshot before every read
Summary:
If GC kicks in between

* A Get() reads index entry from base db.
* The Get() read from a blob file

The GC can delete the corresponding blob file, making the key not found. Fortunately we have existing logic to avoid deleting a blob file if it is referenced by a snapshot. So the fix is to explicitly create a snapshot before reading index entry from base db.
Closes https://github.com/facebook/rocksdb/pull/2754

Differential Revision: D5655956

Pulled By: yiwu-arbug

fbshipit-source-id: e4ccbc51331362542e7343175bbcbdea5830f544
2017-08-20 18:26:19 -07:00
yiwu-arbug 4624ae52c9 GC the oldest file when out of space
Summary:
When out of space, blob db should GC the oldest file. The current implementation GC the newest one instead. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/2757

Differential Revision: D5657611

Pulled By: yiwu-arbug

fbshipit-source-id: 56c30a4c52e6ab04551dda8c5c46006d4070b28d
2017-08-20 17:11:06 -07:00
Andrew Kryczka 8ace1f79b5 add counter for deletion dropping optimization
Summary:
add this counter stat to track usage of deletion-dropping optimization. if usage is low, we can delete it to prevent bugs like #2726.
Closes https://github.com/facebook/rocksdb/pull/2761

Differential Revision: D5665421

Pulled By: ajkr

fbshipit-source-id: 881befa2d199838dac88709e7b376a43d304e3d4
2017-08-19 14:10:08 -07:00
Maysam Yabandeh 0d8e992b47 Revert the mistake in version update
Summary:
https://github.com/facebook/rocksdb/pull/2661 mistakenly updates the version. This patch reverts it.
Closes https://github.com/facebook/rocksdb/pull/2760

Differential Revision: D5662089

Pulled By: maysamyabandeh

fbshipit-source-id: f4735e37921c0ced6081a89080c78ac3728aa8bd
2017-08-18 14:29:39 -07:00
Andrew Kryczka 5358a80568 add VerifyChecksum to HISTORY.md
Summary:
it's a new feature that'll be released in 5.8, introduced by PR #2498.
Closes https://github.com/facebook/rocksdb/pull/2759

Differential Revision: D5661923

Pulled By: ajkr

fbshipit-source-id: 9ba9f0d146c453715358ef2dd298aa7765649d7c
2017-08-18 14:29:39 -07:00
Andrew Kryczka ed0a4c93ef perf_context measure user bytes read
Summary:
With this PR, we can measure read-amp for queries where perf_context is enabled as follows:

```
SetPerfLevel(kEnableCount);
Get(1, "foo");
double read_amp = static_cast<double>(get_perf_context()->block_read_byte / get_perf_context()->get_read_bytes);
SetPerfLevel(kDisable);
```

Our internal infra enables perf_context for a sampling of queries. So we'll be able to compute the read-amp for the sample set, which can give us a good estimate of read-amp.
Closes https://github.com/facebook/rocksdb/pull/2749

Differential Revision: D5647240

Pulled By: ajkr

fbshipit-source-id: ad73550b06990cf040cc4528fa885360f308ec12
2017-08-18 11:43:33 -07:00
Maysam Yabandeh 1efc600ddf Preload l0 index partitions
Summary:
This fixes the existing logic for pinning l0 index partitions. The patch preloads the partitions into block cache and pin them if they belong to level 0 and pin_l0 is set.

The drawback is that it does many small IOs when preloading all the partitions into the cache is direct io is enabled. Working for a solution for that.
Closes https://github.com/facebook/rocksdb/pull/2661

Differential Revision: D5554010

Pulled By: maysamyabandeh

fbshipit-source-id: 1e6f32a3524d71355c77d4138516dcfb601ca7b2
2017-08-18 10:56:20 -07:00
Archit Mishra bddd5d3630 Added mechanism to track deadlock chain
Summary:
Changes:
* extended the wait_txn_map to track additional information
* designed circular buffer to store n latest deadlocks' information
* added test coverage to verify the additional information tracked is accurately stored in the buffer
Closes https://github.com/facebook/rocksdb/pull/2630

Differential Revision: D5478025

Pulled By: armishra

fbshipit-source-id: 2b138de7b5a73f5ca554fc3ff8220a3be49f39e7
2017-08-17 18:56:21 -07:00
yiwu-arbug c1384a7076 fix db_stress uint64_t to int32 cast
Summary:
Clang complain about an cast from uint64_t to int32 in db_stress. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/2755

Differential Revision: D5655947

Pulled By: yiwu-arbug

fbshipit-source-id: cfac10e796e0adfef4727090b50975b0d6e2c9be
2017-08-17 17:56:55 -07:00
yiwu-arbug 29877ec7b4 Fix blob db crash during calculating write amp
Summary:
On initial call to BlobDBImpl::WaStats() `all_periods_write_` would be empty, so it will crash when we call pop_front() at line 1627. Apparently it is mean to pop only when `all_periods_write_.size() > kWriteAmplificationStatsPeriods`.

The whole write amp calculation doesn't seems to be correct and it is not being exposed. Will work on it later.

Test Plan
Change kWriteAmplificationStatsPeriodMillisecs to 1000 (1 second) and run db_bench --use_blob_db for 5 minutes.
Closes https://github.com/facebook/rocksdb/pull/2751

Differential Revision: D5648269

Pulled By: yiwu-arbug

fbshipit-source-id: b843d9a09bb5f9e1b713d101ec7b87e54b5115a4
2017-08-17 15:01:09 -07:00
Sagar Vemuri 8f2598ac9d Enable Cassandra merge operator to be called with a single merge operand
Summary:
Updating Cassandra merge operator to make use of a single merge operand when needed. Single merge operand support has been introduced in #2721.
Closes https://github.com/facebook/rocksdb/pull/2753

Differential Revision: D5652867

Pulled By: sagar0

fbshipit-source-id: b9fbd3196d3ebd0b752626dbf9bec9aa53e3e26a
2017-08-17 15:01:09 -07:00
Sagar Vemuri 9a44b4c32c Allow merge operator to be called even with a single operand
Summary:
Added a function `MergeOperator::DoesAllowSingleMergeOperand()` to allow invoking a merge operator even with a single merge operand, if overriden.

This is needed for Cassandra-on-RocksDB work. All Cassandra writes are through merges and this will allow a single merge-value to be updated in the merge-operator invoked via a compaction, if needed, due to an expired TTL.
Closes https://github.com/facebook/rocksdb/pull/2721

Differential Revision: D5608706

Pulled By: sagar0

fbshipit-source-id: f299f9f91c4d1ac26e48bd5906e122c1c5e5f3fc
2017-08-16 23:42:00 -07:00
follitude ac8fb77afd fix some misspellings
Summary:
PTAL ajkr
Closes https://github.com/facebook/rocksdb/pull/2750

Differential Revision: D5648052

Pulled By: ajkr

fbshipit-source-id: 7cd1ddd61364d5a55a10fdd293fa74b2bf89dd98
2017-08-16 21:57:20 -07:00
Andrew Kryczka 23593171c4 minor improvements to db_stress
Summary:
fix some things that made this command hard to use from CLI:

- use default values for `target_file_size_base` and `max_bytes_for_level_base`. previously we were using small values for these but default value of `write_buffer_size`, which led to enormous number of L1 files.
- failure message for `value_size_mult` too big. previously there was just an assert, so in non-debug mode it'd overrun the value buffer and crash mysteriously.
- only print verification success if there's no failure. before it'd print both in the failure case.
- support `memtable_prefix_bloom_size_ratio`
- support `num_bottom_pri_threads` (universal compaction)
Closes https://github.com/facebook/rocksdb/pull/2741

Differential Revision: D5629495

Pulled By: ajkr

fbshipit-source-id: ddad97d6d4ba0884e7c0f933b0a359712514fc1d
2017-08-16 19:13:01 -07:00
Andrew Kryczka af012c0f83 fix deleterange with memtable prefix bloom
Summary:
the range delete tombstones in memtable should be added to the aggregator even when the memtable's prefix bloom filter tells us the lookup key's not there. This bug could cause data to temporarily reappear until the memtable containing range deletions is flushed.

Reported in #2743.
Closes https://github.com/facebook/rocksdb/pull/2745

Differential Revision: D5639007

Pulled By: ajkr

fbshipit-source-id: 04fc6facb6f978340a3f639536f4ca7c0d73dfc9
2017-08-16 19:13:01 -07:00
Andrew Kryczka 1c8dbe2aa2 update scores after picking universal compaction
Summary:
We forgot to recompute compaction scores after picking a universal compaction like we do in level compaction (https://github.com/facebook/rocksdb/blob/a34b2e388ee51173e44f6aa290f1301c33af9e67/db/compaction_picker.cc#L691-L695). This leads to a fairness issue where we waste compactions on CFs/DB instances that don't need it while others can starve.

Previously, ccecf3f4fb fixed the issue for the read-amp-based compaction case; this PR avoids the issue earlier and also for size-ratio-based compactions.
Closes https://github.com/facebook/rocksdb/pull/2688

Differential Revision: D5566191

Pulled By: ajkr

fbshipit-source-id: 010bccb2a107f6a76f3d3022b90aadce5cc48feb
2017-08-16 18:42:33 -07:00
Maysam Yabandeh eb6425303e Update WritePrepared with the pseudo code
Summary:
Implement the main body of WritePrepared pseudo code. This includes PrepareInternal and CommitInternal, as well as AddCommitted which updates the commit map. It also provides a IsInSnapshot method that could be later called form the read path to decide if a version is in the read snapshot or it should other be skipped.

This patch lacks unit tests and does not attempt to offer an efficient implementation. The idea is that to have the API specified so that we can work on related tasks in parallel.
Closes https://github.com/facebook/rocksdb/pull/2713

Differential Revision: D5640021

Pulled By: maysamyabandeh

fbshipit-source-id: bfa7a05e8d8498811fab714ce4b9c21530514e1c
2017-08-16 16:57:47 -07:00
Sagar Vemuri 132306fbf0 Remove PartialMerge implementation from Cassandra merge operator
Summary:
`PartialMergeMulti` implementation is enough for Cassandra, and `PartialMerge` is not required. Implementing both will just duplicate the code.
As per https://github.com/facebook/rocksdb/blob/master/include/rocksdb/merge_operator.h#L130-L135 :

```
  // The default implementation of PartialMergeMulti will use this function
  // as a helper, for backward compatibility.  Any successor class of
  // MergeOperator should either implement PartialMerge or PartialMergeMulti,
  // although implementing PartialMergeMulti is suggested as it is in general
  // more effective to merge multiple operands at a time instead of two
  // operands at a time.
```
Closes https://github.com/facebook/rocksdb/pull/2737

Reviewed By: scv119

Differential Revision: D5633073

Pulled By: sagar0

fbshipit-source-id: ef4fa102c22fec6a0175ed12f5c44c15afe3c8ca
2017-08-15 14:59:34 -07:00
Siying Dong 71598cdc75 Fix false removal of tombstone issue in FIFO and kCompactionStyleNone
Summary:
Similar to the bug fixed by https://github.com/facebook/rocksdb/pull/2726, FIFO with compaction and kCompactionStyleNone during user customized CompactFiles() with output level to be 0 can suffer from the same problem. Fix it by leveraging the bottommost_level_ flag.
Closes https://github.com/facebook/rocksdb/pull/2735

Differential Revision: D5626906

Pulled By: siying

fbshipit-source-id: 2b148d0461c61dbd986d74655e384419ae442158
2017-08-15 13:02:19 -07:00
lxcode 3204a4f64b Fix missing stdlib include required for abort()
Summary:
If ROCKSDB_LITE is defined, a call to abort() is introduced. This call requires stdlib.h.

Build log of unpatched 5.7.1:

http://beefy9.nyi.freebsd.org/data/110amd64-default/447974/logs/rocksdb-lite-5.7.1.log
Closes https://github.com/facebook/rocksdb/pull/2744

Reviewed By: yiwu-arbug

Differential Revision: D5632372

Pulled By: lxcode

fbshipit-source-id: b2a8e692bf14ccf1f875f3a00463e87bba310a2b
2017-08-15 12:32:11 -07:00
Andrew Kryczka 7aa96db7a2 db_stress rolling active window
Summary:
Support a window of `active_width` keys that rolls through `[0, max_key)` over the duration of the test. Operations only affect keys inside the window. This gives us the ability to detect L0->L0 deletion bug (#2722).
Closes https://github.com/facebook/rocksdb/pull/2739

Differential Revision: D5628555

Pulled By: ajkr

fbshipit-source-id: 9cb2d8f4ab1a7c73f7797b8e19f7094970ea8749
2017-08-15 12:02:16 -07:00
Neal Poole dfa6c23c4b Update RocksDBCommonHelper to use escapeshellarg
Summary:
Most of the data used here in shell commands is not generated directly from user input but some data (ie: from environment variables) may have been external influenced. It is a good practice to escape this data before using it in a shell command.

Originally D4800264 but we never quite got it merged.

Reviewed By: yiwu-arbug

Differential Revision: D5595052

fbshipit-source-id: c09d8b47fe35fc6a47afb4933ccad9d56ca8d7be
2017-08-15 06:56:31 -07:00
yiwu-arbug e367774d19 Overload new[] to properly align LRUCacheShard
Summary:
Also verify it fixes gcc7 compile failure #2672 (see also #2699)
Closes https://github.com/facebook/rocksdb/pull/2732

Differential Revision: D5620348

Pulled By: yiwu-arbug

fbshipit-source-id: 87db657ab734f23b1bfaaa9db9b9956d10eaef59
2017-08-14 14:41:56 -07:00
Yi Wu ad42d2fcbb Remove residual arcanist_util directory 2017-08-14 10:51:48 -07:00
Nikhil Benesch 279296f4d8 properly set C[XX]FLAGS during CMake configure-time checks
Summary:
Some compilers require `-std=c++11` for the `cstdint` header to be available. We already have logic to add `-std=c++11` to `CXXFLAGS` when the compiler is not MSVC; simply reorder CMakeLists.txt so that logic happens before the calls to `CHECK_CXX_SOURCE_COMPILES`.

Additionally add a missing `set(CMAKE_REQUIRED_FLAGS, ...)` before a call to `CHECK_C_SOURCE_COMPILES`.
Closes https://github.com/facebook/rocksdb/pull/2535

Differential Revision: D5384244

Pulled By: yiwu-arbug

fbshipit-source-id: 2dbae4297c5d8ab4636e08b1457ffb2d3e37aef4
2017-08-13 21:47:45 -07:00
Nikhil Benesch c5f0c6cc66 compile with correct flags to determine SSE4.2 support
Summary:
With some compilers, `-std=c++11` is necessary for <cstdint> to be
available. Pass this flag via $PLATFORM_CXXFLAGS. Fixes #2488.
Closes https://github.com/facebook/rocksdb/pull/2545

Differential Revision: D5620610

Pulled By: yiwu-arbug

fbshipit-source-id: 2f975b8c1ad52e283e677d9a33543abd064f13ce
2017-08-13 21:47:45 -07:00
Jay 185ade4c0c cmake: support more compression type
Summary:
This pr enables linking all the supported compression libraries via cmake.
Closes https://github.com/facebook/rocksdb/pull/2552

Differential Revision: D5620607

Pulled By: yiwu-arbug

fbshipit-source-id: b6949181f305bfdf04a98f898c92fd0caba0c45a
2017-08-13 21:47:45 -07:00
Andrew Gallagher 5449c0990b rocksdb: make buildable on aarch64
Summary:
- Remove default arch-specified flags.
- Move non-default arch-specific flags to arch-specific param.

Reviewed By: yiwu-arbug

Differential Revision: D5597499

fbshipit-source-id: c53108ac39c73ac36893d3fd9aaf3b5e3080f1ae
2017-08-13 17:13:54 -07:00
Adam Retter a144a9782d Fix for CMakeLists.txt on Windows for RocksJava
Summary: Closes https://github.com/facebook/rocksdb/pull/2730

Differential Revision: D5619256

Pulled By: ajkr

fbshipit-source-id: c80d697eeceab91964259132e58f5cd2219efb93
2017-08-12 16:44:12 -07:00
Andrew Kryczka acf935e40f fix deletion dropping in intra-L0
Summary:
`KeyNotExistsBeyondOutputLevel` didn't consider L0 files' key-ranges. So if a key only was covered by older L0 files' key-ranges, we would incorrectly drop deletions of that key. This PR just skips the deletion-dropping optimization when output level is L0.
Closes https://github.com/facebook/rocksdb/pull/2726

Differential Revision: D5617286

Pulled By: ajkr

fbshipit-source-id: 4bff1396b06d49a828ba4542f249191052915bce
2017-08-11 18:12:38 -07:00
Andrew Kryczka 8254e9b57c make sst_dump compression size command consistent
Summary:
- like other subcommands, reporting compression sizes should be specified with the `--command` CLI arg.
- also added `--compression_types` arg as it's useful to restrict the types of compression used, at least in my dictionary compression experiments.
Closes https://github.com/facebook/rocksdb/pull/2706

Differential Revision: D5589520

Pulled By: ajkr

fbshipit-source-id: 305bb4ebcc95eecc8a85523cd3b1050619c9ddc5
2017-08-11 16:03:44 -07:00
Andrew Kryczka 74f18c1301 db_bench support for non-uniform column family ops
Summary:
Previously we could only select the CF on which to operate uniformly at random. This is a limitation, e.g., when testing universal compaction as all CFs would need to run full compaction at roughly the same time, which isn't realistic.

This PR allows the user to specify the probability distribution for selecting CFs via the `--column_family_distribution` argument.
Closes https://github.com/facebook/rocksdb/pull/2677

Differential Revision: D5544436

Pulled By: ajkr

fbshipit-source-id: 478d56260995236ae90895ce5bd51f38882e185a
2017-08-11 13:57:17 -07:00
Andrew Kryczka 5de98f2d50 approximate histogram stats to save cpu
Summary:
sounds like we're willing to tradeoff minor inaccuracy in stats for speed. start with histogram stats. ticker stats will be harder (and, IMO, we shouldn't change them in this manner) as many test cases rely on them being exactly correct.
Closes https://github.com/facebook/rocksdb/pull/2720

Differential Revision: D5607884

Pulled By: ajkr

fbshipit-source-id: 1b754cda35ea6b252d1fdd5aa3cfb58866506372
2017-08-11 13:13:12 -07:00
yiwu-arbug 3f5888430a Fix c_test ASAN failure
Summary:
Fix c_test missing deletion of write batch pointer.
Closes https://github.com/facebook/rocksdb/pull/2725

Differential Revision: D5613866

Pulled By: yiwu-arbug

fbshipit-source-id: bf3f59a6812178577c9c25bae558ef36414a1f51
2017-08-11 13:00:15 -07:00
yiwu-arbug e5a1b727c0 Fix blob DB transaction usage while GC
Summary:
While GC, blob DB use optimistic transaction to delete or replace the index entry in LSM, to guarantee correctness if there's a normal write writing to the same key. However, the previous implementation doesn't call SetSnapshot() nor use GetForUpdate() of transaction API, instead it do its own sequence number checking before beginning the transaction. A normal write can sneak in after the sequence number check and overwrite the key, and the GC will delete or relocate the old version of the key by mistake. Update the code to property use GetForUpdate() to check the existing index entry.

After the patch the sequence number store with each blob record is useless, So I'm considering remove the sequence number from blob record, in another patch.
Closes https://github.com/facebook/rocksdb/pull/2703

Differential Revision: D5589178

Pulled By: yiwu-arbug

fbshipit-source-id: 8dc960cd5f4e61b36024ba7c32d05584ce149c24
2017-08-11 12:43:17 -07:00
Andrew Kryczka 6f051e0c71 fix corruption_test valgrind
Summary: Closes https://github.com/facebook/rocksdb/pull/2724

Differential Revision: D5613416

Pulled By: ajkr

fbshipit-source-id: ed55fb66ab1b41dfdfe765fe3264a1c87a8acb00
2017-08-11 12:29:14 -07:00
Kent767 ac098a4626 expose set_skip_stats_update_on_db_open to C bindings
Summary:
It would be super helpful to not have to recompile rocksdb to get this performance tweak for mechanical disks.

I have signed the CLA.
Closes https://github.com/facebook/rocksdb/pull/2718

Differential Revision: D5606994

Pulled By: yiwu-arbug

fbshipit-source-id: c05e92bad0d03bd38211af1e1ced0d0d1e02f634
2017-08-11 12:16:45 -07:00
Siying Dong 666a005f9b Support prefetch last 512KB with direct I/O in block based file reader
Summary:
Right now, if direct I/O is enabled, prefetching the last 512KB cannot be applied, except compaction inputs or readahead is enabled for iterators. This can create a lot of I/O for HDD cases. To solve the problem, the 512KB is prefetched in block based table if direct I/O is enabled. The prefetched buffer is passed in totegher with random access file reader, so that we try to read from the buffer before reading from the file. This can be extended in the future to support flexible user iterator readahead too.
Closes https://github.com/facebook/rocksdb/pull/2708

Differential Revision: D5593091

Pulled By: siying

fbshipit-source-id: ee36ff6d8af11c312a2622272b21957a7b5c81e7
2017-08-11 12:16:45 -07:00
yiwu-arbug ad77ee0ea0 Revert "Makefile: correct faligned-new test"
Summary:
This reverting #2699 to fix clang build.
Closes https://github.com/facebook/rocksdb/pull/2723

Differential Revision: D5610207

Pulled By: yiwu-arbug

fbshipit-source-id: 6857f4556d6d18f17b74cf81fa936d1dc0bd364c
2017-08-10 21:14:46 -07:00
Siying Dong b87ee6f773 Use more keys per lock in daily TSAN crash test
Summary:
TSAN shows error when we grab too many locks at the same time. In TSAN crash test, make one shard key cover 2^22 keys so that no many keys will be hold at the same time.
Closes https://github.com/facebook/rocksdb/pull/2719

Differential Revision: D5609035

Pulled By: siying

fbshipit-source-id: 930e5d63fff92dbc193dc154c4c615efbdf06c6a
2017-08-10 17:56:57 -07:00
Stanislav Tkach 25df24254b Add column families related functions (C API)
Summary:
(#2564)
Closes https://github.com/facebook/rocksdb/pull/2669

Differential Revision: D5594151

Pulled By: yiwu-arbug

fbshipit-source-id: 67ae9446342f3323d6ecad8e811f4158da194270
2017-08-10 13:43:54 -07:00
Daniel Black 64f8484356 block_cache_tier: fix gcc-7 warnings
Summary:
Error was:

utilities/persistent_cache/block_cache_tier.cc: In instantiation of ‘void rocksdb::Add(std::map<std::__cxx11::basic_string<char>, double>*, const string&, const T&) [with T = double; std::__cxx11::string = std::__cxx11::basic_string<char>]’:
utilities/persistent_cache/block_cache_tier.cc:147:40:   required from here
utilities/persistent_cache/block_cache_tier.cc:141:23: error: type qualifiers ignored on cast result type [-Werror=ignored-qualifiers]

   stats->insert({key, static_cast<const double>(t)});

fixing like #2562
Closes https://github.com/facebook/rocksdb/pull/2603

Differential Revision: D5600910

Pulled By: yiwu-arbug

fbshipit-source-id: 891a5ec7e451d2dec6ad1b6b7fac545657f87363
2017-08-10 11:58:53 -07:00
Oleksandr Anyshchenko 0cecf8155b Write batch for TransactionDB in C API
Summary: Closes https://github.com/facebook/rocksdb/pull/2655

Differential Revision: D5600858

Pulled By: yiwu-arbug

fbshipit-source-id: cf52f9104e348438bf168dc6bf7af3837faf12ef
2017-08-10 11:58:53 -07:00
FireMail 6a9de43477 Windows.h macro call fix
Summary:
- moved the max call for numeric limits into paranthesis so that max wont be called as macro when including <Windows.h>
Closes https://github.com/facebook/rocksdb/pull/2709

Differential Revision: D5600773

Pulled By: yiwu-arbug

fbshipit-source-id: fd28b6f7c10ddce21bad4030f2db06f965bb08da
2017-08-10 11:39:29 -07:00
jimmyway 23c7d13540 fix comment
Summary:
Signed-off-by: tang.jin <tang.jin@istuary.com>
Closes https://github.com/facebook/rocksdb/pull/2644

Differential Revision: D5600861

Pulled By: yiwu-arbug

fbshipit-source-id: 9516636cb6e77b09fe0ebef78953adf4b7e88cc8
2017-08-09 22:57:01 -07:00
Daniel Black 1fbad84b69 Makefile: correct faligned-new test
Summary:
Commit 4f81ab38bf has the test wrong.

clang doesn't support a -dumpversion option. By lucky coincidence
clang/gcc --version both place a version number at the same output location
when --verison is passed.

Example output (1st line only).

    $ clang --version
    clang version 3.9.1 (tags/RELEASE_391/final)

    $ gcc --version
    gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1)

During the test of the compiler we ensure that a minimum version is met
as Makefile doesn't support patterns.

Also xcode9 doesn't seem affected by https://github.com/facebook/rocksdb/issues/2672
and also doesn't have "clang" as the first part of its output so the
fix implemented here also is Apple clang friendly.

    $ clang --version
    Apple LLVM version 9.0.0 (clang-900.0.31)

Signed-off-by: Daniel Black <daniel.black@au.ibm.com>
Closes https://github.com/facebook/rocksdb/pull/2699

Differential Revision: D5600818

Pulled By: yiwu-arbug

fbshipit-source-id: 3b0f2751becb53c1c35468bf29f3f828e7cf2c2a
2017-08-09 22:42:03 -07:00
Aaron G 7848f0b24c add VerifyChecksum() to db.h
Summary:
We need a tool to check any sst file corruption in the db.
It will check all the sst files in current version and read all the blocks (data, meta, index) with checksum verification. If any verification fails, the function will return non-OK status.
Closes https://github.com/facebook/rocksdb/pull/2498

Differential Revision: D5324269

Pulled By: lightmark

fbshipit-source-id: 6f8a272008b722402a772acfc804524c9d1a483b
2017-08-09 15:58:13 -07:00
Andrew Kryczka 47ed3bfc3b fix WinEnv assertions
Summary: Closes https://github.com/facebook/rocksdb/pull/2702

Differential Revision: D5585389

Pulled By: ajkr

fbshipit-source-id: cb54041eb481d0d759c440f82a8a2c5b34534173
2017-08-08 17:20:52 -07:00
Chang Liu d97a72d63f Try to repair db with wal_dir option, avoid leak some WAL files
Summary:
We should search wal_dir in Repairer::FindFiles function, and avoid use
LogFileNmae(dbname, number) to get WAL file's name, which will get a wrong
WAL filename. as following:

```
[WARN] [/home/liuchang/Workspace/rocksdb/db/repair.cc:310] Log #3: ignoring conversion error: IO error: While opening a file for sequentially reading: /tmp/rocksdbtest-1000/repair_test/000003.log: No such file or directory
```
  I have added a new test case to repair_test.cc, which try to repair db with all WAL options.

Signed-off-by: Chang Liu <liuchang0812@gmail.com>
Closes https://github.com/facebook/rocksdb/pull/2692

Differential Revision: D5575888

Pulled By: ajkr

fbshipit-source-id: 5b93e9f85cddc01663ccecd87631fa723ac466a3
2017-08-08 10:47:57 -07:00
James Page 36375de76f gcc-7/i386: markup intentional fallthroughs
Summary:
Markup i386 code paths resolving compilation
failure under i386 with gcc-7.

Signed-off-by: James Page <james.page@ubuntu.com>
Closes https://github.com/facebook/rocksdb/pull/2700

Differential Revision: D5583047

Pulled By: maysamyabandeh

fbshipit-source-id: fe31bcfeaf7cd2d3f51b55f5ae0b3b0cb3788fbc
2017-08-08 08:56:52 -07:00
Maysam Yabandeh bdc056f8aa Refactor PessimisticTransaction
Summary:
This patch splits Commit and Prepare into lock-related logic and db-write-related logic. It moves lock-related logic to PessimisticTransaction to be reused by all children classes and movies the existing impl of db-write-related to PrepareInternal, CommitSingleInternal, and CommitInternal in WriteCommittedTxnImpl.
Closes https://github.com/facebook/rocksdb/pull/2691

Differential Revision: D5569464

Pulled By: maysamyabandeh

fbshipit-source-id: d1b8698e69801a4126c7bc211745d05c636f5325
2017-08-07 16:12:29 -07:00
Maysam Yabandeh a9a4e89c38 Fix valgrind complaint about initialization
Summary: Closes https://github.com/facebook/rocksdb/pull/2697

Differential Revision: D5573894

Pulled By: maysamyabandeh

fbshipit-source-id: 8fc03ea8ea6f3f3bc0f68b64cf90243a70562dc4
2017-08-07 08:49:52 -07:00
janlzlabs 4ca11b4b07 Update USERS.md
Summary:
I'd like to propose adding my company as a RocksDB user
Closes https://github.com/facebook/rocksdb/pull/2694

Differential Revision: D5572113

Pulled By: ajkr

fbshipit-source-id: 646143b955e3efddee56691cce912d7badaa6e8b
2017-08-06 12:44:40 -07:00
Maysam Yabandeh c9804e007a Refactor TransactionDBImpl
Summary:
This opens space for the new implementations of TransactionDBImpl such as WritePreparedTxnDBImpl that has a different policy of how to write to DB.
Closes https://github.com/facebook/rocksdb/pull/2689

Differential Revision: D5568918

Pulled By: maysamyabandeh

fbshipit-source-id: f7eac866e175daf3793ae79da108f65cc7dc7b25
2017-08-05 17:26:15 -07:00
Sagar Vemuri 20dc5e74f2 Optimize range-delete aggregator call in merge helper.
Summary:
In the condition:
```
if (range_del_agg != nullptr &&
    range_del_agg->ShouldDelete(
        iter->key(),
        RangeDelAggregator::RangePositioningMode::kForwardTraversal) &&
    filter != CompactionFilter::Decision::kRemoveAndSkipUntil) {
...
}
```
it could be possible that all the work done in `range_del_agg->ShouldDelete` is wasted due to not having the right `filter` value later on.
Instead, check `filter` value before even calling `range_del_agg->ShouldDelete`, which is a much more involved function.
Closes https://github.com/facebook/rocksdb/pull/2690

Differential Revision: D5568931

Pulled By: sagar0

fbshipit-source-id: 17512d52360425c7ae9de7675383f5d7bc3dad58
2017-08-05 00:15:35 -07:00
Yi Wu 0d4a2b7330 Avoid blob db call Sync() while writing
Summary:
The FsyncFiles background job call Fsync() periodically for blob files. However it can access WritableFileWriter concurrently with a Put() or Write(). And WritableFileWriter does not support concurrent access. It will lead to WritableFileWriter buffer being flush with same content twice, and blob file end up corrupted. Fixing by simply let FsyncFiles hold write_mutex_.
Closes https://github.com/facebook/rocksdb/pull/2685

Differential Revision: D5561908

Pulled By: yiwu-arbug

fbshipit-source-id: f0bb5bcab0e05694e053b8c49eab43640721e872
2017-08-04 13:12:07 -07:00
Maysam Yabandeh 627c9f1abb Don't add -ljemalloc when DISABLE_JEMALLOC is set
Summary:
fixes #2555
Closes https://github.com/facebook/rocksdb/pull/2684

Differential Revision: D5560527

Pulled By: maysamyabandeh

fbshipit-source-id: 6e1d874ae0b4e699a77203d9d52d0bb8f59013b0
2017-08-04 10:42:32 -07:00
Andrew Kryczka dce6d5a838 db_bench background work thread pool size arguments
Summary:
The background thread pools' sizes weren't easily configurable by `max_background_compactions` and `max_background_flushes` in multi-instance setups. Introduced separate arguments for their sizes.
Closes https://github.com/facebook/rocksdb/pull/2680

Differential Revision: D5550675

Pulled By: ajkr

fbshipit-source-id: bab5f0a7bc5db63bb084d0c10facbe437096367d
2017-08-03 21:41:49 -07:00
Cholerae Hu 4f81ab38bf Makefile: fix for GCC 7+ and clang 4+
Summary:
maysamyabandeh IslamAbdelRahman PTAL

Fix https://github.com/facebook/rocksdb/issues/2672

Signed-off-by: Cholerae Hu <huyingqian@pingcap.com>
Closes https://github.com/facebook/rocksdb/pull/2681

Differential Revision: D5561515

Pulled By: ajkr

fbshipit-source-id: 676187802ebd8a87a6c051bb565818a1bf89d0a9
2017-08-03 20:58:46 -07:00
Yi Wu 92afe830f9 Update all blob db TTL and timestamps to uint64_t
Summary:
The current blob db implementation use mix of int32_t, uint32_t and uint64_t for TTL and expiration. Update all timestamps to uint64_t for consistency.
Closes https://github.com/facebook/rocksdb/pull/2683

Differential Revision: D5557103

Pulled By: yiwu-arbug

fbshipit-source-id: e4eab2691629a755e614e8cf1eed9c3a681d0c42
2017-08-03 17:57:30 -07:00
Alan Somers 5883a1ae24 Fix /bin/bash shebangs
Summary:
"/bin/bash" is a Linuxism.  "/usr/bin/env bash" is portable.
Closes https://github.com/facebook/rocksdb/pull/2646

Differential Revision: D5556259

Pulled By: ajkr

fbshipit-source-id: cbffd38ecdbfffb2438969ec007ab345ed893ccb
2017-08-03 15:56:46 -07:00
Andrew Kryczka cc01985db0 Introduce bottom-pri thread pool for large universal compactions
Summary:
When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs.

This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions.

- Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads.
- Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default.
- Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic.
- Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`).
- Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free.
Closes https://github.com/facebook/rocksdb/pull/2580

Differential Revision: D5422916

Pulled By: ajkr

fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-03 15:43:29 -07:00
Yi Wu 0b814ba92d Allow concurrent writes to blob db
Summary:
I'm going with brute-force solution, just letting Put() and Write() holding a mutex before writing. May improve concurrent writing with finer granularity locking later.
Closes https://github.com/facebook/rocksdb/pull/2682

Differential Revision: D5552690

Pulled By: yiwu-arbug

fbshipit-source-id: 039abd675b5d274a7af6428198d1733cafecef4c
2017-08-03 15:11:26 -07:00
Yi Wu 2c45ada4c4 Blob DB garbage collection should keep keys with newer version
Summary:
Fix the bug where if blob db garbage collection revmoe keys with newer version. It shouldn't delete the key from base db when sequence number in base db is not equal to the one in blob log.
Closes https://github.com/facebook/rocksdb/pull/2678

Differential Revision: D5549752

Pulled By: yiwu-arbug

fbshipit-source-id: abb8649260963b5c389748023970fd746279d227
2017-08-03 13:12:12 -07:00
Maysam Yabandeh 58410aee44 Fix the overflow bug in AwaitState
Summary:
https://github.com/facebook/rocksdb/issues/2559 reports an overflow in AwaitState. nbronson has debugged the issue and presented the fix, which is applied to this patch. Moreover this patch adds more comments to clarify the logic in AwaitState.

I tried with both 16 and 64 threads on update benchmark. The fix lowers cpu usage by 1.6 but also lowers the throughput by 1.6 and 2% respectively. Apparently the bug had favored using the spinning more often.

Benchmarks:
TEST_TMPDIR=/dev/shm/tmpdb time ./db_bench --benchmarks="fillrandom" --threads=16 --num=2000000
TEST_TMPDIR=/dev/shm/tmpdb time ./db_bench --use_existing_db=1 --benchmarks="updaterandom[X3]" --threads=16 --num=2000000
TEST_TMPDIR=/dev/shm/tmpdb time ./db_bench --use_existing_db=1 --benchmarks="updaterandom[X3]" --threads=64 --num=200000

Results
$ cat update-16t-bug.txt | tail -4
updaterandom [AVG    3 runs] : 234117 ops/sec;   51.8 MB/sec
updaterandom [MEDIAN 3 runs] : 233581 ops/sec;   51.7 MB/sec
3896.42user 1539.12system 6:50.61elapsed 1323%CPU (0avgtext+0avgdata 331308maxresident)k
0inputs+0outputs (0major+1281001minor)pagefaults 0swaps
$ cat update-16t-fixed.txt | tail -4
updaterandom [AVG    3 runs] : 230364 ops/sec;   51.0 MB/sec
updaterandom [MEDIAN 3 runs] : 226169 ops/sec;   50.0 MB/sec
3865.46user 1568.32system 6:57.63elapsed 1301%CPU (0avgtext+0avgdata 315012maxresident)k
0inputs+0outputs (0major+1342568minor)pagefaults 0swaps

$ cat update-64t-bug.txt | tail -4
updaterandom [AVG    3 runs] : 261878 ops/sec;   57.9 MB/sec
updaterandom [MEDIAN 3 runs] : 262859 ops/sec;   58.2 MB/sec
926.27user 578.06system 2:27.46elapsed 1020%CPU (0avgtext+0avgdata 475480maxresident)k
0inputs+0outputs (0major+1058728minor)pagefaults 0swaps
$ cat update-64t-fixed.txt | tail -4
updaterandom [AVG    3 runs] : 256699 ops/sec;   56.8 MB/sec
updaterandom [MEDIAN 3 runs] : 256380 ops/sec;   56.7 MB/sec
933.47user 575.37system 2:30.41elapsed 1003%CPU (0avgtext+0avgdata 482340maxresident)k
0inputs+0outputs (0major+1078557minor)pagefaults 0swaps
Closes https://github.com/facebook/rocksdb/pull/2679

Differential Revision: D5553732

Pulled By: maysamyabandeh

fbshipit-source-id: 98b72dc3a8e0f22ea29d4f7c7790af10c369c5bb
2017-08-03 10:43:28 -07:00
Maysam Yabandeh c3d5c4d38a Refactor TransactionImpl
Summary:
This patch refactors TransactionImpl by separating the logic for pessimistic concurrency control from the implementation of how to write the data to rocksdb. The existing implementation is named WriteCommittedTxnImpl as it writes committed data to the db. A template named WritePreparedTxnImpl is also added which will be later completed to provide a an alternative implementation.
Closes https://github.com/facebook/rocksdb/pull/2676

Differential Revision: D5549998

Pulled By: maysamyabandeh

fbshipit-source-id: 16298e86b43ca4849324c1f35c731913c6d17bec
2017-08-03 08:57:22 -07:00
Andrew Kryczka 060ccd4f84 support multiple CFs with OPTIONS file
Summary:
Move an option necessary for running db_bench on multiple CFs into the general initialization area, so it works with both flag-based init and OPTIONS-based init.
Closes https://github.com/facebook/rocksdb/pull/2675

Differential Revision: D5541378

Pulled By: ajkr

fbshipit-source-id: 169926cb4ae95c17974f744faf7cc794d41e5c0a
2017-08-02 16:27:01 -07:00
Sagar Vemuri 3453870677 Fix statistics in RocksJava sample
Summary:
I observed while doing a `make jtest` that the java sample was broken, due to the changes in #2551 .
Closes https://github.com/facebook/rocksdb/pull/2674

Differential Revision: D5539807

Pulled By: sagar0

fbshipit-source-id: 2c7e9d84778099dfa1c611996b444efe3c9fd466
2017-08-01 16:58:26 -07:00
Yi Wu 1900771bd2 Dump Blob DB options to info log
Summary:
* Dump blob db options to info log
* Remove BlobDBOptionsImpl to disallow dynamic cast *BlobDBOptions into *BlobDBOptionsImpl. Move options there to be constants or into BlobDBOptions. The dynamic cast is broken after #2645
* Change some of the default options
* Remove blob_db_options.min_blob_size, which is unimplemented. Will implement it soon.
Closes https://github.com/facebook/rocksdb/pull/2671

Differential Revision: D5529912

Pulled By: yiwu-arbug

fbshipit-source-id: dcd58ca981db5bcc7f123b65a0d6f6ae0dc703c7
2017-08-01 13:01:47 -07:00
奏之章 3218edc573 Fix universal compaction bug
Summary:
this value ``` Compaction::is_trivial_move_ ``` uninitialized .
under universal compaction , we enable ```  CompactionOptionsUniversal::allow_trivial_move  ``` ,
https://github.com/facebook/rocksdb/blob/9b11d4345a0f01fc3de756e01460bf1b0446f326/db/compaction.cc#L245
here is a disastrous bug , some sst trivial move to target level without overlap check ...
THEN , DATABASE DAMAGED , WE GOT A LEVEL WITH OVERLAP !
Closes https://github.com/facebook/rocksdb/pull/2634

Differential Revision: D5530722

Pulled By: siying

fbshipit-source-id: 425ab55bca5967110377d634258360bcf88c200e
2017-07-31 14:27:45 -07:00
Andrew Kryczka 6a36b3a7b9 fix db get/write stats
Summary:
we were passing `record_read_stats` (a bool) as the `hist_type` argument, which meant we were updating either `rocksdb.db.get.micros` (`hist_type == 0`) or `rocksdb.db.write.micros` (`hist_type == 1`) with wrong data.
Closes https://github.com/facebook/rocksdb/pull/2666

Differential Revision: D5520384

Pulled By: ajkr

fbshipit-source-id: 2f7c956aec32f8b58c5c18845ac478e0230c9516
2017-07-31 12:12:03 -07:00
Siying Dong a84cee8127 Add a missing "once" in .h
Summary: Closes https://github.com/facebook/rocksdb/pull/2670

Differential Revision: D5529018

Pulled By: siying

fbshipit-source-id: 10a378933d509035d2dbe502247dd85fcea09789
2017-07-31 12:12:03 -07:00
Siying Dong 21696ba502 Replace dynamic_cast<>
Summary:
Replace dynamic_cast<> so that users can choose to build with RTTI off, so that they can save several bytes per object, and get tiny more memory available.
Some nontrivial changes:
1. Add Comparator::GetRootComparator() to get around the internal comparator hack
2. Add the two experiemental functions to DB
3. Add TableFactory::GetOptionString() to avoid unnecessary casting to get the option string
4. Since 3 is done, move the parsing option functions for table factory to table factory files too, to be symmetric.
Closes https://github.com/facebook/rocksdb/pull/2645

Differential Revision: D5502723

Pulled By: siying

fbshipit-source-id: fd13cec5601cf68a554d87bfcf056f2ffa5fbf7c
2017-07-28 16:27:16 -07:00
Mike Kolupaev e85f2c64cb Prevent empty memtables from using a lot of memory
Summary:
This fixes OOMs that we (logdevice) are currently having in production.

SkipListRep constructor does a couple small allocations from ConcurrentArena (see InlineSkipList constructor). ConcurrentArena would sometimes allocate an entire block for that, which is a few megabytes (we use Options::arena_block_size = 4 MB). So an empty memtable can take take 4 MB of memory. We have ~40k column families (spread across 15 DB instances), so 4 MB per empty memtable easily OOMs a machine for us.

This PR makes ConcurrentArena always allocate from Arena's inline block when possible. So as long as InlineSkipList's initial allocations are below 2 KB there would be no blocks allocated for empty memtables.
Closes https://github.com/facebook/rocksdb/pull/2569

Differential Revision: D5404029

Pulled By: al13n321

fbshipit-source-id: 568ec22a3fd1a485c06123f6b2dfc5e9ef67cd23
2017-07-28 15:58:43 -07:00
Sagar Vemuri ac748c57ed Fix FIFO Compaction with TTL tests
Summary:
- FIFOCompactionWithTTLTest was flaky when run in parallel earlier, and hence it was disabled. Fixed it now.
- Also, faking sleep now instead of really sleeping to make tests more realistic by using TTLs like 1 hour and 1 day.
Closes https://github.com/facebook/rocksdb/pull/2650

Differential Revision: D5506038

Pulled By: sagar0

fbshipit-source-id: deb429a527f045e3e2c5138b547c3e8ac8586aa2
2017-07-28 14:42:59 -07:00
Yi Wu aaf42fe775 Move blob_db/ttl_extractor.h into blob_db/blob_db.h
Summary:
Move blob_db/ttl_extractor.h into blob_db/blob_db.h
Also exclude TTLExtractor from LITE build.
Closes https://github.com/facebook/rocksdb/pull/2665

Differential Revision: D5520009

Pulled By: yiwu-arbug

fbshipit-source-id: 4813dcc272c7cc4bf2cdac285256d9a17d78c7b7
2017-07-28 14:28:21 -07:00
Sagar Vemuri aace46516b Fix license headers in Cassandra related files
Summary:
I might have missed these while doing some recent cassandra code reviews.
Closes https://github.com/facebook/rocksdb/pull/2663

Differential Revision: D5520138

Pulled By: sagar0

fbshipit-source-id: 340930afe9efe03c75f535a1da1f89bd3e53c1f9
2017-07-28 13:56:56 -07:00
Islam AbdelRahman 50a969131f CacheActivityLogger, component to log cache activity into a file
Summary:
Simple component that will add a new entry in a log file every time we lookup/insert a key in SimCache.
API:
```
SimCache::StartActivityLogging(<file_name>, <env>, <optional_max_size>)
SimCache::StopActivityLogging()
```

Sending for review, Still need to add more comments.

I was thinking about a better approach, but I ended up deciding I will use a mutex to sync the writes to the file, since this feature should not be heavily used and only used to collect info that will be analyzed offline. I think it's okay to hold the mutex every time we lookup/add to the SimCache.
Closes https://github.com/facebook/rocksdb/pull/2295

Differential Revision: D5063826

Pulled By: IslamAbdelRahman

fbshipit-source-id: f3b5daed8b201987c9a071146ddd5c5740a2dd8c
2017-07-28 12:36:48 -07:00
Yi Wu 6083bc79f8 Blob DB TTL extractor
Summary:
Introducing blob_db::TTLExtractor to replace extract_ttl_fn. The TTL
extractor can be use to extract TTL from keys insert with Put or
WriteBatch. Change over existing extract_ttl_fn are:
* If value is changed, it will be return via std::string* (rather than Slice*). With Slice* the new value has to be part of the existing value. With std::string* the limitation is removed.
* It can optionally return TTL or expiration.

Other changes in this PR:
* replace `std::chrono::system_clock` with `Env::NowMicros` so that I can mock time in tests.
* add several TTL tests.
* other minor naming change.
Closes https://github.com/facebook/rocksdb/pull/2659

Differential Revision: D5512627

Pulled By: yiwu-arbug

fbshipit-source-id: 0dfcb00d74d060b8534c6130c808e4d5d0a54440
2017-07-27 23:26:04 -07:00
Andrew Kryczka 710411aea6 fix asan/valgrind for TableCache cleanup
Summary:
Breaking commit: d12691b86f

In the above commit, I moved the `TableCache` cleanup logic from `Version` destructor into `PurgeObsoleteFiles`. I missed cleaning up `TableCache` entries for the current `Version` during DB destruction.

This PR adds that logic to `VersionSet` destructor. One unfortunate side effect is now we're potentially deleting `TableReader`s after `column_family_set_.reset()`, which means we can't call `BlockBasedTableReader::Close` a second time as the block cache might already be destroyed.
Closes https://github.com/facebook/rocksdb/pull/2662

Differential Revision: D5515108

Pulled By: ajkr

fbshipit-source-id: 2cb820e19aa813e0d258d17f76b2d7b6b7ee0b18
2017-07-27 20:28:04 -07:00
Yi Wu 3a3fb00b7a TARGETS file not setting sse explicitly
Summary:
We don't need to set them explicitly.
Closes https://github.com/facebook/rocksdb/pull/2660

Differential Revision: D5514141

Pulled By: yiwu-arbug

fbshipit-source-id: 10edebfc3cfe0afc00a34519f87fcea4d65069ae
2017-07-27 17:41:36 -07:00
Siying Dong fca4d6da17 Build fewer tests in Travis platform_dependent tests
Summary:
platform_dependent tests in Travis now builds all tests, which is not needed. Only build those tests we need to run.
Closes https://github.com/facebook/rocksdb/pull/2647

Differential Revision: D5513954

Pulled By: siying

fbshipit-source-id: 4d540b146124e70dd25586c47939d19f93655b0a
2017-07-27 17:29:01 -07:00
Aaron Gao 8f553d3c52 remove unnecessary internal_comparator param in newIterator
Summary:
solved https://github.com/facebook/rocksdb/issues/2604
Closes https://github.com/facebook/rocksdb/pull/2648

Differential Revision: D5504875

Pulled By: lightmark

fbshipit-source-id: c14bb62ccbdc9e7bda9cd914cae4ea0765d882ee
2017-07-27 14:30:42 -07:00
Siying Dong 7f6d012d70 "ccache -C" in Travis
Summary:
This is to work around the problem of build error:

util/threadpool_imp.o: file not recognized: File truncated

Just to make the build go through. We should remove it later if we find the real long-term solution.
Closes https://github.com/facebook/rocksdb/pull/2657

Differential Revision: D5511034

Pulled By: siying

fbshipit-source-id: 229f024bd78ee96799017d4a89be74253058ec30
2017-07-27 13:42:18 -07:00
Andrew Kryczka d12691b86f move TableCache::EraseHandle outside of db mutex
Summary:
Post-compaction work holds onto db mutex for the longest time (found by tracing lock acquires/releases with LTTng and correlating timestamps with our info log). Further experimentation showed `TableCache::EraseHandle` is responsible for ~86% of time mutex is held. We can just release the handle outside the db mutex.
Closes https://github.com/facebook/rocksdb/pull/2654

Differential Revision: D5507126

Pulled By: ajkr

fbshipit-source-id: 703c01ddf2aea16bc0f9e33c08935d78aa6b781d
2017-07-27 12:14:41 -07:00
Andrew Kryczka f33f113683 fix db_bench argument type
Summary:
it should be a bool
Closes https://github.com/facebook/rocksdb/pull/2653

Differential Revision: D5506148

Pulled By: ajkr

fbshipit-source-id: f142f0f3aa8b678c68adef12e5ac6e1e163306f3
2017-07-27 12:14:37 -07:00
Siying Dong e7697b8ce8 Fix LITE unit tests
Summary: Closes https://github.com/facebook/rocksdb/pull/2649

Differential Revision: D5505778

Pulled By: siying

fbshipit-source-id: 7e935603ede3d958ea087ed6b8cfc4121e8797bc
2017-07-26 21:11:47 -07:00
Andres Suarez 3ce20e985b Fix use of RocksDBCommonHelper in cont_integration.sh
Reviewed By: mzlee

Differential Revision: D5472936

fbshipit-source-id: cf75858f879f1192b468a9020005634a5afad880
2017-07-26 19:31:36 -07:00
Siying Dong c281b44829 Revert "CRC32 Power Optimization Changes"
Summary:
This reverts commit 2289d38115.
Closes https://github.com/facebook/rocksdb/pull/2652

Differential Revision: D5506163

Pulled By: siying

fbshipit-source-id: 105e31dd9d99090453a6b9f32c165206cd3affa3
2017-07-26 19:31:36 -07:00
Sagar Vemuri 9980de262c Fix FIFO compaction picker test
Summary:
A FIFO compaction picker test is accidentally testing against an instance of level compaction picker.
Closes https://github.com/facebook/rocksdb/pull/2641

Differential Revision: D5495390

Pulled By: sagar0

fbshipit-source-id: 301962736f629b1c499570fb504cdbe66bacb46f
2017-07-26 12:12:26 -07:00
Kamalalochana Subbaiah 2289d38115 CRC32 Power Optimization Changes
Summary:
Support for PowerPC Architecture
Detecting AltiVec Support
Closes https://github.com/facebook/rocksdb/pull/2353

Differential Revision: D5210948

Pulled By: siying

fbshipit-source-id: 859a8c063d37697addd89ba2b8a14e5efd5d24bf
2017-07-26 09:42:29 -07:00
Maysam Yabandeh 30b58cf71a Remove the orphan assert on !need_log_sync
Summary:
We initially had disabled support for write_options.sync when concurrent_prepare_ is set. We later added this support but the statement that asserts this combination is not used was left there. This patch cleans it up.
Closes https://github.com/facebook/rocksdb/pull/2642

Differential Revision: D5496101

Pulled By: maysamyabandeh

fbshipit-source-id: becbc503446f2a51bee24cc861958c090c724ec2
2017-07-25 18:41:52 -07:00
Yi Wu fe1a5559f3 Fix flaky write_callback_test
Summary:
The test is failing occasionally on the assert: `ASSERT_TRUE(writer->state == WriteThread::State::STATE_INIT)`. This is because the test don't make the leader wait for long enough before updating state for its followers. The patch move the update to `threads_waiting` to the end of `WriteThread::JoinBatchGroup:Wait` callback to avoid this happening.

Also adding `WriteThread::JoinBatchGroup:Start` and have each thread wait there while another thread is linking to the linked-list. This is to make the check of `is_leader` more deterministic.

Also changing two while-loops of `compare_exchange_strong` to plain `fetch_add`, to make it look cleaner.
Closes https://github.com/facebook/rocksdb/pull/2640

Differential Revision: D5491525

Pulled By: yiwu-arbug

fbshipit-source-id: 6e897f122082bd6f98e6d51b31a25e5fd0a3fb82
2017-07-25 16:42:11 -07:00
Yi Wu addbd279c2 5.6.1 release blog post
Summary:
5.6.1 release blog post
Closes https://github.com/facebook/rocksdb/pull/2638

Differential Revision: D5491168

Pulled By: yiwu-arbug

fbshipit-source-id: 14e3a92a03684afa4bd19bfb3ffb053cc09f5d4a
2017-07-25 12:27:22 -07:00
Andrew Gallagher 30edff308e buckification: remove explicit -msse* compiler flags
Summary: These are implied by default platform flags, in particular, `-march=corei7`.

Reviewed By: pixelb

Differential Revision: D5485414

fbshipit-source-id: 85f1329c71fa81a604760844187cc73877fb40e9
2017-07-25 12:09:06 -07:00
Maysam Yabandeh 2b259c9d49 Lower num of iterations in DeadlockCycle test
Summary:
Currently this test times out with tsan. This is likely due to decreased speed with tsan. By lowering the number of iterations we can still catch a bug as the test is run regularly and multiple runs of the test is equivalent with running the test with more iterations.
Closes https://github.com/facebook/rocksdb/pull/2639

Differential Revision: D5490549

Pulled By: maysamyabandeh

fbshipit-source-id: bd69c42a9728d337ac95a06a401088384e51731a
2017-07-25 11:42:26 -07:00
Maysam Yabandeh 277f6f23d4 Release note for partitioned index/filters
Summary: Closes https://github.com/facebook/rocksdb/pull/2637

Differential Revision: D5489751

Pulled By: maysamyabandeh

fbshipit-source-id: 0298f8960d4f86ce67959616615beee4d802c2e4
2017-07-25 10:24:12 -07:00
Andres Suarez 5e731a1382 Remove unused rocksdb arcanist lib
Differential Revision: D5470179

fbshipit-source-id: 475ad3b6a85ead5f8abddefddc607353ea8680af
2017-07-25 04:27:17 -07:00
Thi Doan 9b11d4345a Fix broken links
Summary:
Fixes broken links to the introductory talk I stumbled upon while
reading the documentation.
Closes https://github.com/facebook/rocksdb/pull/2628

Differential Revision: D5483851

Pulled By: sagar0

fbshipit-source-id: 94aab7fb4c4ed2305680a2fbc65b14c7977af6b8
2017-07-24 15:12:45 -07:00
atkawa7 06f1917449 add vcpkg as an windows option
Summary: Closes https://github.com/facebook/rocksdb/pull/2629

Differential Revision: D5483751

Pulled By: sagar0

fbshipit-source-id: 9719ef9edd936dbb89b8988e3f4cb912a234f00e
2017-07-24 15:12:45 -07:00
Islam AbdelRahman ea8ad4f678 Fix compaction div by zero logging
Summary:
We will divide by zero if `stats.micros` is zero, just add a simple check
This happens sometimes during running tests and UBSAN complains
Closes https://github.com/facebook/rocksdb/pull/2631

Differential Revision: D5481455

Pulled By: IslamAbdelRahman

fbshipit-source-id: 69aa24e64e21de15d9e2b8009adf01675fcc6598
2017-07-24 11:58:02 -07:00
kapitan-k 34112aeffd Added db paths to c
Summary: Closes https://github.com/facebook/rocksdb/pull/2613

Differential Revision: D5476064

Pulled By: sagar0

fbshipit-source-id: 6b30a9eacb93a945bbe499eafb90565fa9f1798b
2017-07-24 11:58:02 -07:00
Daniel Black 1d8aa2961c Gcc 7 ParsedInternalKey replace memset with clear function.
Summary:
I haven't looked to see if a class variable inside a loop like this is always initialised.
Closes https://github.com/facebook/rocksdb/pull/2602

Differential Revision: D5475937

Pulled By: IslamAbdelRahman

fbshipit-source-id: 8570b308f9a4b49e2a56ccc9e9b84d7c46568c15
2017-07-24 11:31:15 -07:00
Islam AbdelRahman a4c42e8007 Fix UBSAN issue of passing nullptr to memcmp
Summary:
As explained in the comments, Sometimes we create Slice(nullptr, 0) in our code base which cause us to do calls like
```
memcmp(nullptr, "abc", 0);
```
That's fine since the len is equal 0, but UBSAN is not happy about it
so disable UBSAN for this function and add an assert instead
Closes https://github.com/facebook/rocksdb/pull/2616

Differential Revision: D5458326

Pulled By: IslamAbdelRahman

fbshipit-source-id: cfca32abe30f7d8f760c9f77ecd9543dfb1170dd
2017-07-24 10:54:37 -07:00
Daniel Black 16e0388205 LRUCacheShard cache line size alignment
Summary:
combining #2568 and #2612.
Closes https://github.com/facebook/rocksdb/pull/2620

Differential Revision: D5464394

Pulled By: IslamAbdelRahman

fbshipit-source-id: 9f71d3058dd6adaf02ce3b2de3a81a1228009778
2017-07-24 10:54:37 -07:00
Islam AbdelRahman 216644c61c enable UBSAN macro in TARGETS
Summary:
simply enable the macro in internal build, it wont hurt other sanitizers and will fix UBSAN issues
Closes https://github.com/facebook/rocksdb/pull/2625

Differential Revision: D5475897

Pulled By: IslamAbdelRahman

fbshipit-source-id: 262c6fd5de3c1906f4b29e55b39110f125f41057
2017-07-24 10:54:37 -07:00
Siying Dong e67b35c076 Add Iterator::Refresh()
Summary:
Add and implement Iterator::Refresh(). When this function is called, if the super version doesn't change, update the sequence number of the iterator to the latest one and invalidate the iterator. If the super version changed, recreated the whole iterator. This can help users reuse the iterator more easily.
Closes https://github.com/facebook/rocksdb/pull/2621

Differential Revision: D5464500

Pulled By: siying

fbshipit-source-id: f548bd35e85c1efca2ea69273802f6704eba6ba9
2017-07-24 10:54:37 -07:00
Andrew Kryczka a34b2e388e Fix caching of compaction picker's next index
Summary:
The previous implementation of caching `file_size` index made no sense. It only remembered the original span of locked files starting from beginning of `file_size`. We should remember the index after all compactions that have been considered but rejected. This will reduce the work we do while holding the db mutex.
Closes https://github.com/facebook/rocksdb/pull/2624

Differential Revision: D5468152

Pulled By: ajkr

fbshipit-source-id: ab92a4bffe76f9f174d861bb5812b974d1013400
2017-07-21 20:57:15 -07:00
Sagar Vemuri 72502cf227 Revert "comment out unused parameters"
Summary:
This reverts the previous commit 1d7048c598, which broke the build.

Did a `git revert 1d7048c`.
Closes https://github.com/facebook/rocksdb/pull/2627

Differential Revision: D5476473

Pulled By: sagar0

fbshipit-source-id: 4756ff5c0dfc88c17eceb00e02c36176de728d06
2017-07-21 18:26:26 -07:00
Victor Gao 1d7048c598 comment out unused parameters
Summary: This uses `clang-tidy` to comment out unused parameters (in functions, methods and lambdas) in fbcode. Cases that the tool failed to handle are fixed manually.

Reviewed By: igorsugak

Differential Revision: D5454343

fbshipit-source-id: 5dee339b4334e25e963891b519a5aa81fbf627b2
2017-07-21 14:57:44 -07:00
Pengchao Wang 534c255c7a Cassandra compaction filter for purge expired columns and rows
Summary:
Major changes in this PR:
* Implement CassandraCompactionFilter to remove expired columns and rows (if all column expired)
* Move cassandra related code from utilities/merge_operators/cassandra to utilities/cassandra/*
* Switch to use shared_ptr<> from uniqu_ptr for Column membership management in RowValue. Since columns do have multiple owners in Merge and GC process, use shared_ptr helps make RowValue immutable.
* Rename cassandra_merge_test to cassandra_functional_test and add two TTL compaction related tests there.
Closes https://github.com/facebook/rocksdb/pull/2588

Differential Revision: D5430010

Pulled By: wpc

fbshipit-source-id: 9566c21e06de17491d486a68c70f52d501f27687
2017-07-21 14:57:44 -07:00
Yi Wu 63163a8c6e Remove make_new_version.sh
Summary:
Seems the only function of the script is to create a new branch, which can be done easily. I'm removing it.
Closes https://github.com/facebook/rocksdb/pull/2623

Differential Revision: D5468681

Pulled By: yiwu-arbug

fbshipit-source-id: 87dea5ecc4c85e06941ccbc36993f7f589063878
2017-07-20 20:45:20 -07:00
Yi Wu 0302da47a7 Reduce blob db noisy logging
Summary:
Remove some of the per-key logging by blob db to reduce noise.
Closes https://github.com/facebook/rocksdb/pull/2587

Differential Revision: D5429115

Pulled By: yiwu-arbug

fbshipit-source-id: b89328282fb8b3c64923ce48738c16017ce7feaf
2017-07-20 15:02:31 -07:00
Islam AbdelRahman 3e5ea29a83 Fix Flaky DeleteSchedulerTest::ImmediateDeleteOn25PercDBSize
Summary:
In this test we are deleting 100 files, and we are expecting DeleteScheduler to delete 26 files in the background and 74 files immediately in the foreground

The main purpose of the test is to make sure that we delete files in foreground thread, which is verified in line 546

But sometimes we may end up with 26 files or 25 files in the trash directory because the background thread may be slow and not be able to delete the first file fast enough, so sometimes this test fail.

Remove
```
ASSERT_EQ(CountFilesInDir(trash_dir_), 25);
```
Since it does not have any benefit any way
Closes https://github.com/facebook/rocksdb/pull/2618

Differential Revision: D5458674

Pulled By: IslamAbdelRahman

fbshipit-source-id: 5556a9edfa049db71dce80b8e6ae0fdd25e1e74e
2017-07-20 11:29:01 -07:00
Andrew Kryczka a22b9cc6fe overlapping endpoint fixes in level compaction picker
Summary:
This diff addresses two problems. Both problems cause us to miss scheduling desirable compactions. One side effect is compaction picking can spam logs, as there's no delay after failed attempts to pick compactions.

1. If a compaction pulled in a locked input-level file due to user-key overlap, we would not consider picking another file from the same input level.
2. If a compaction pulled in a locked output-level file due to user-key overlap, we would not consider picking any other compaction on any level.

The code changes are dependent, which is why I solved both problems in a single diff.

- Moved input-level `ExpandInputsToCleanCut` into the loop inside `PickFileToCompact`. This gives two benefits: (1) if it fails, we will try the next-largest file on the same input level; (2) we get the fully-expanded input-level key-range with which we can check for pending compactions in output level.
- Added another call to `ExpandInputsToCleanCut` inside `PickFileToCompact`'s to check for compaction conflicts in output level.
- Deleted call to `IsRangeInCompaction` in `PickFileToCompact`, as `ExpandInputsToCleanCut` also correctly handles the case where original output-level files (i.e., ones not pulled in due to user-key overlap) are pending compaction.
Closes https://github.com/facebook/rocksdb/pull/2615

Differential Revision: D5454643

Pulled By: ajkr

fbshipit-source-id: ea3fb5477d83e97148951af3fd4558d2039e9872
2017-07-19 20:42:00 -07:00
Andrew Kryczka ffd2a2eefd delete ExpandInputsToCleanCut failure log
Summary:
I decided not even to keep it as an INFO-level log as it is too normal for compactions to be skipped due to locked input files. Removing logging here makes us consistent with how we treat locked files that weren't pulled in due to overlap.

We may want some error handling on line 422, which should never happen when called by `LevelCompactionBuilder::PickCompaction`, as `SetupInitialFiles` skips compactions where overlap causes the output level to pull in locked files.
Closes https://github.com/facebook/rocksdb/pull/2617

Differential Revision: D5458502

Pulled By: ajkr

fbshipit-source-id: c2e5f867c0a77c1812ce4242ab3e085b3eee0bae
2017-07-19 20:42:00 -07:00
Islam AbdelRahman 3e6e863b1f Remove arcanist_util directory 2017-07-19 16:49:55 -07:00
Maysam Yabandeh 36651d14ee Moving static AdaptationContext to outside function
Summary:
Moving static AdaptationContext to outside function to bypass tsan's false report with static initializers.

It is because with optimization enabled std::atomic is simplified to as a simple read with no locks. The existing lock produced by static initializer is __cxa_guard_acquire which is apparently not understood by tsan as it is different from normal locks (__gthrw_pthread_mutex_lock).

This is a known problem with tsan:
https://stackoverflow.com/questions/27464190/gccs-tsan-reports-a-data-race-with-a-thread-safe-static-local
https://stackoverflow.com/questions/42062557/c-multithreading-is-initialization-of-a-local-static-lambda-thread-safe

A workaround that I tried was to move the static variable outside the function. It is not a good coding practice since it gives global visibility to variable but it is a hackish workaround until g++ tsan is improved.
Closes https://github.com/facebook/rocksdb/pull/2598

Differential Revision: D5445281

Pulled By: yiwu-arbug

fbshipit-source-id: 6142bd934eb5852d8fd7ce027af593ba697ed41d
2017-07-18 16:58:22 -07:00
Siying Dong 6e3ee015fb Update java/rocksjni.pom
Summary: Closes https://github.com/facebook/rocksdb/pull/2610

Differential Revision: D5445705

Pulled By: siying

fbshipit-source-id: d5f97ffdf5bc18b853c3a106755aca96a650e428
2017-07-18 13:12:23 -07:00
Andrew Kryczka ecff9d5e33 Include write_buffer_manager in ImmutableDBOptions::Dump
Summary:
as titled
Closes https://github.com/facebook/rocksdb/pull/2601

Differential Revision: D5441618

Pulled By: ajkr

fbshipit-source-id: 334b098d90caadd3d07167d051cfb4ae65db98e1
2017-07-18 12:42:42 -07:00
Siying Dong ae28634e9f Remove some left-over BSD headers
Summary: Closes https://github.com/facebook/rocksdb/pull/2608

Differential Revision: D5444797

Pulled By: siying

fbshipit-source-id: 690581d03f37822e059a16085088e8e2d8a45016
2017-07-18 11:56:57 -07:00
Siying Dong 33b1de82a7 Remove format compatibility hack
Summary:
We don't need this format compatibility hack anymore. We should remove it to make things simpler.
Closes https://github.com/facebook/rocksdb/pull/2607

Differential Revision: D5444107

Pulled By: siying

fbshipit-source-id: 7ef587dd0cacfc15a4083a137adba8e6bfddac7e
2017-07-18 11:12:32 -07:00
Maysam Yabandeh 2f375154ea checkout local branch in check_format_compatible.sh
Summary:
For forward_compatible_checkout_objs the local branch is already created in previous step. This patch avoid recreating it. This should address "fatal: A branch named '3.10.fb' already exists." errors.
Closes https://github.com/facebook/rocksdb/pull/2606

Differential Revision: D5443786

Pulled By: maysamyabandeh

fbshipit-source-id: 69d5a67b87677429cf36e3a467bd114d341f3b9c
2017-07-18 10:42:17 -07:00
Maysam Yabandeh ddb22ac59c avoid collision with master branch in check format
Summary:
The new local branch specified with -b cannot be called master. Use tmp prefix to avoid name collision.
Closes https://github.com/facebook/rocksdb/pull/2600

Differential Revision: D5442944

Pulled By: maysamyabandeh

fbshipit-source-id: 4a623d9b21d6cc01bee812b2799790315bdf5f6e
2017-07-18 08:27:33 -07:00
Maysam Yabandeh 0c03a7f17d set the remote for git checkout
Summary:
This will fix the error: "error: pathspec '2.2.fb.branch' did not match any file(s) known to git."

Tested by manually sshing to sandcastle and running the command.
Closes https://github.com/facebook/rocksdb/pull/2599

Differential Revision: D5441130

Pulled By: maysamyabandeh

fbshipit-source-id: a22fd6a52221471bafbba8990394b499535e5812
2017-07-17 19:41:50 -07:00
Andrew Kryczka 7ac184c6d7 Revert cmake -DNDEBUG for non-MSVC
Summary:
Unfortunately we can't use -DNDEBUG yet since we don't properly exclude the test libraries/executables from the non-debug builds on non-MSVC platforms. Previously this was failing on Linux for every build type except `CMAKE_BUILD_TYPE=Debug`.

Reverts a48a62d
Closes https://github.com/facebook/rocksdb/pull/2595

Differential Revision: D5436182

Pulled By: ajkr

fbshipit-source-id: 062f07cc9ce06a073b66054722b27bac1890dca3
2017-07-17 15:08:38 -07:00
Sushma Devendrappa 0655b58582 enable PinnableSlice for RowCache
Summary:
This patch enables using PinnableSlice for RowCache, changes include
not releasing the cache handle immediately after lookup in TableCache::Get, instead pass a Cleanble function which does Cache::RleaseHandle.
Closes https://github.com/facebook/rocksdb/pull/2492

Differential Revision: D5316216

Pulled By: maysamyabandeh

fbshipit-source-id: d2a684bd7e4ba73772f762e58a82b5f4fbd5d362
2017-07-17 15:08:30 -07:00
Yi Wu 00464a3140 Fix column_family_test with LITE build
Summary:
Fix column_family_test with LITE build. I need this patch to fix 5.6 branch.
Closes https://github.com/facebook/rocksdb/pull/2597

Differential Revision: D5437171

Pulled By: yiwu-arbug

fbshipit-source-id: 88b9dc5925a6b47af10c1b41bc5b07c4251a84b5
2017-07-17 15:08:24 -07:00
Chris Lamb b2dd192fed tools/write_stress.cc: Correct "1204" typos.
Summary:
Should be 1024, obviously :)
Closes https://github.com/facebook/rocksdb/pull/2592

Differential Revision: D5435269

Pulled By: ajkr

fbshipit-source-id: c59338a3900798a4733f0b205e534f21215cf049
2017-07-17 11:27:10 -07:00
Daniel Black cbaab30449 table/block.h: change memset
Summary:
In gcc-7 the following is an error identified by -Werror=class-memaccess

In file included from ./table/get_context.h:14:0,
                 from db/version_set.cc:43:
./table/block.h: In constructor ‘rocksdb::BlockReadAmpBitmap::BlockReadAmpBitmap(size_t, size_t, rocksdb::Statistics*)’:
./table/block.h:73:53: error: ‘void* memset(void*, int, size_t)’ clearing an object of type ‘struct std::atomic<unsigned int>’ with no trivial copy-assignment; use value-initialization instead [-Werror=class-memaccess]
     memset(bitmap_, 0, bitmap_size * kBytesPersEntry);
                                                     ^
In file included from ./db/version_set.h:23:0,
                 from db/version_set.cc:12:
/toolchain/include/c++/8.0.0/atomic:684:12: note: ‘struct std::atomic<unsigned int>’ declared here
     struct atomic<unsigned int> : __atomic_base<unsigned int>
            ^~~~~~~~~~~~~~~~~~~~

As a solution the default initializer can be applied in list context.

Signed-off-by: Daniel Black <daniel.black@au.ibm.com>
Closes https://github.com/facebook/rocksdb/pull/2561

Differential Revision: D5398714

Pulled By: siying

fbshipit-source-id: d883fb88ec7535eee60d551038fe91f14488be36
2017-07-17 10:41:56 -07:00
Yedidya Feldblum f1a056e005 CodeMod: Prefer ADD_FAILURE() over EXPECT_TRUE(false), et cetera
Summary:
CodeMod: Prefer `ADD_FAILURE()` over `EXPECT_TRUE(false)`, et cetera.

The tautologically-conditioned and tautologically-contradicted boolean expectations/assertions have better alternatives: unconditional passes and failures.

Reviewed By: Orvid

Differential Revision:
D5432398

Tags: codemod, codemod-opensource

fbshipit-source-id: d16b447e8696a6feaa94b41199f5052226ef6914
2017-07-16 21:26:02 -07:00
Siying Dong 4a2e4891fe Add back the LevelDB license file
Summary: Closes https://github.com/facebook/rocksdb/pull/2591

Differential Revision: D5432696

Pulled By: siying

fbshipit-source-id: a613230ab916de0b279a65ef429ede65460a8db2
2017-07-16 18:42:18 -07:00
Siying Dong a7321fc97f Remove the licensing description in CONTRIBUTING.md
Summary: Closes https://github.com/facebook/rocksdb/pull/2590

Differential Revision: D5432539

Pulled By: siying

fbshipit-source-id: 49902453bba3c95c1fb8354441b2198649e52bf4
2017-07-16 15:57:18 -07:00
Siying Dong 3c327ac2d0 Change RocksDB License
Summary: Closes https://github.com/facebook/rocksdb/pull/2589

Differential Revision: D5431502

Pulled By: siying

fbshipit-source-id: 8ebf8c87883daa9daa54b2303d11ce01ab1f6f75
2017-07-15 16:11:23 -07:00
Islam AbdelRahman 132013366d Make TARGETS file portable
Summary:
Instead of hard coding the path of the internal repo.
Make TARGETS file work anywhere in fbcode
Closes https://github.com/facebook/rocksdb/pull/2586

Differential Revision: D5428122

Pulled By: IslamAbdelRahman

fbshipit-source-id: 21adec82bfbff14ea93532bee789b5f5bbee5b01
2017-07-14 15:45:36 -07:00
Daniel Black ccf5f08f88 Set CACHE_LINE_SIZE for s390, PPC, ARM64
Summary: Closes https://github.com/facebook/rocksdb/pull/2579

Differential Revision: D5427667

Pulled By: maysamyabandeh

fbshipit-source-id: cd0b076aa0cd38d3554516f01723c548713ece61
2017-07-14 15:13:46 -07:00
Daniel Black 67510eeff3 db_crashtest.py: remove need for shell
Summary:
Before:
$ ps -ef

build     1713    16  0 Jul11 ?        00:00:00 make crash_test
build     3437  1713  0 Jul11 ?        00:00:00 python -u tools/db_crashtest.py --simple blackbox
build     3438  3437  0 Jul11 ?        00:00:00 [sh] <defunct>
build     3440     1 99 Jul11 ?        5-03:01:25 ./db_stress --max_background_compactions=1 --max_write_buffer_number=3 --sync=0 --reopen=20 --write_buffer_size=33554432 --delpercent=5 --block_size=16384 --allow_concurrent_me

After:

build      1706     16  0 02:52 ?        00:00:01 make crash_test
build      3432   1706  0 02:55 ?        00:00:00 python -u tools/db_crashtest.py --simple blackbox
build      4452   3432 99 04:35 ?        00:01:42 ./db_stress --max_background_compactions=1 --max_write_buffer_number=3 --sync=0 --reopen=20 --write_buffer_size=33554432 --delpercent=5 --block_size=16384 --allow_concurr
Closes https://github.com/facebook/rocksdb/pull/2571

Differential Revision: D5421580

Pulled By: maysamyabandeh

fbshipit-source-id: d6c3970c38ea0fa23da653f4385e8e25d83f5c9f
2017-07-14 09:11:03 -07:00
Maysam Yabandeh 4267eb00d4 Remove punit tests
Summary: Closes https://github.com/facebook/rocksdb/pull/2577

Differential Revision: D5420460

Pulled By: maysamyabandeh

fbshipit-source-id: 83671ec65513f4223044316e28cd6d33e9d5b531
2017-07-13 17:12:20 -07:00
Yi Wu 5bfb67d90f Enable write rate limit for updaterandom benchmark
Summary:
We have FLAGS_benchmark_write_rate_limit to limit write rate in
db_bench, but it was not in use for updaterandom benchmark.
Closes https://github.com/facebook/rocksdb/pull/2578

Differential Revision: D5420328

Pulled By: yiwu-arbug

fbshipit-source-id: 5fa48c2b88f2f2dc83d615cb9c40c472bc916835
2017-07-13 16:27:38 -07:00
Islam AbdelRahman 20a691d98f Update HISTORY to release 5.7
Summary:
Update HISTORY file to release 5.7
Closes https://github.com/facebook/rocksdb/pull/2576

Differential Revision: D5417716

Pulled By: IslamAbdelRahman

fbshipit-source-id: 3af5e7dd533607162212cf5d63a0121a07d637cd
2017-07-13 13:36:48 -07:00
Siying Dong 98d1a5510b db_bench to by default verify checksum
Summary: Closes https://github.com/facebook/rocksdb/pull/2575

Differential Revision: D5417350

Pulled By: siying

fbshipit-source-id: 4bc11e35a7256167a5a7d2f586f2ac74c0deddb0
2017-07-13 12:14:17 -07:00
Yi Wu 26ce69b195 Update blob db to use ROCKS_LOG_* macro
Summary:
Update blob db to use the newer ROCKS_LOG_* macro.
Closes https://github.com/facebook/rocksdb/pull/2574

Differential Revision: D5414526

Pulled By: yiwu-arbug

fbshipit-source-id: e428753aa5917e8b435cead2db26df586e5d1def
2017-07-13 10:14:04 -07:00
Aaron Gao 43e4eef77f remove unnecessary fadvise
Summary:
We has to remove this line because previously it is only called when use_os_buffer = false. But now we have direct io to replace it.
Closes https://github.com/facebook/rocksdb/pull/2573

Differential Revision: D5412824

Pulled By: yiwu-arbug

fbshipit-source-id: 81f3f0cdf94566bfc09ef2ff123e40cddbe36b36
2017-07-12 18:14:41 -07:00
foolenough 21b17d7686 Fix BlobDB::Get which only get out the value offset
Summary:
Blob db use StackableDB::get which only get out the
value offset, but not the value.
Fix by making BlobDB::Get override the designated getter.
Closes https://github.com/facebook/rocksdb/pull/2553

Differential Revision: D5396823

Pulled By: yiwu-arbug

fbshipit-source-id: 5a7d1cf77ee44490f836a6537225955382296878
2017-07-12 17:57:40 -07:00
奏之章 70440f7a63 Add virtual func IsDeleteRangeSupported
Summary:
this modify allows third-party tables able to support delete range
Closes https://github.com/facebook/rocksdb/pull/2035

Differential Revision: D5407973

Pulled By: ajkr

fbshipit-source-id: 82e364b7dd5a198660788d59543f15b8f95cc418
2017-07-12 16:58:45 -07:00
Daniel Black 7550255c54 Add JAVAC_ARGS as Makefile variable
Summary:
Set to "-Xlint:deprecation -Xlint:unchecked" for non-zero
DEBUG_LEVEL

Shows up a few warnings for later perusal however passes ok.
Closes https://github.com/facebook/rocksdb/pull/2557

Differential Revision: D5408104

Pulled By: sagar0

fbshipit-source-id: 02908602e09b46d33b0dfc0ffd4b11954db03c53
2017-07-12 12:12:43 -07:00
Daniel Black 7a0b5de771 Gcc 7 ignored quantifiers
Summary:
The casting seemed to cause a problem.

I think this might increase it to unsigned long.
Closes https://github.com/facebook/rocksdb/pull/2562

Differential Revision: D5406842

Pulled By: siying

fbshipit-source-id: 736adef31448229a58a1a48bdbe77792f36736e8
2017-07-12 09:41:15 -07:00
Adam Retter 000bf0af38 Improve the design and native object management of Stats in RocksJava
Summary: Closes https://github.com/facebook/rocksdb/pull/2551

Differential Revision: D5399288

Pulled By: sagar0

fbshipit-source-id: dd3df2ed6cc5ae612db0998ea746cc29fccf568e
2017-07-11 23:31:00 -07:00
Islam AbdelRahman 269d383d5d Bump version to 5.7
Summary:
Bump version to 5.7
Closes https://github.com/facebook/rocksdb/pull/2566

Differential Revision: D5400043

Pulled By: IslamAbdelRahman

fbshipit-source-id: 74aae4ff143d370d7d89807e5be08a6ab827da40
2017-07-11 14:29:13 -07:00
Yi Wu c32f27223b Fixes db_bench with blob db
Summary:
* Create info log before db open to make blob db able to log to LOG file.
* Properly destroy blob db.
Closes https://github.com/facebook/rocksdb/pull/2567

Differential Revision: D5400034

Pulled By: yiwu-arbug

fbshipit-source-id: a49cfaf4b5c67d42d4cbb872bd5a9441828c17ce
2017-07-11 14:14:38 -07:00
Daniel Black fcd99d27c9 db_bench_tool: fix buffer size
Summary:
Found by gcc warning:

x86_64-pc-linux-gnu-g++ --version
x86_64-pc-linux-gnu-g++ (GCC) 7.1.1 20170710

tools/db_bench_tool.cc: In member function 'void rocksdb::Benchmark::RandomWithVerify(rocksdb::ThreadState*)':
tools/db_bench_tool.cc:4430:8: error: '%lu' directive output may be truncated writing between 1 and 19 bytes into a region of size between 0 and 66 [-Werror=format-truncation=]
   void RandomWithVerify(ThreadState* thread) {
        ^~~~~~~~~~~~~~~~
tools/db_bench_tool.cc:4430:8: note: directive argument in the range [0, 9223372036854775807]
tools/db_bench_tool.cc:4492:13: note: 'snprintf' output between 37 and 128 bytes into a destination of size 100
     snprintf(msg, sizeof(msg),
     ~~~~~~~~^~~~~~~~~~~~~~~~~~
              "( get:%" PRIu64 " put:%" PRIu64 " del:%" PRIu64 " total:%" \
              ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
              PRIu64 " found:%" PRIu64 ")",
              ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
              gets_done, puts_done, deletes_done, readwrites_, found);
              ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1plus: all warnings being treated as errors
Makefile:1707: recipe for target 'tools/db_bench_tool.o' failed
Closes https://github.com/facebook/rocksdb/pull/2558

Differential Revision: D5398703

Pulled By: siying

fbshipit-source-id: 6ffa552bbd8b59cfc2c36289f86ff9b9acca8ca6
2017-07-11 10:41:06 -07:00
Aaron Gao 87128bd5c5 fix regression test
Summary:
delete the checkout line
Closes https://github.com/facebook/rocksdb/pull/2556

Differential Revision: D5394446

Pulled By: lightmark

fbshipit-source-id: 4afaf35e7ad0378d12169d13a3131a92b428b5d2
2017-07-10 17:17:31 -07:00
Giuseppe Ottaviano 8f927e5f75 Fix undefined behavior in Hash
Summary:
Instead of ignoring UBSan checks, fix the negative shifts in
Hash(). Also add test to make sure the hash values are stable over
time. The values were computed before this change, so the test also
verifies the correctness of the change.
Closes https://github.com/facebook/rocksdb/pull/2546

Differential Revision: D5386369

Pulled By: yiwu-arbug

fbshipit-source-id: 6de4b44461a544d6222cc5d72d8cda2c0373d17e
2017-07-10 12:29:24 -07:00
Adam Retter 643b787c7b Added a note about LZ4 compression dependency
Summary: Closes https://github.com/facebook/rocksdb/pull/2554

Differential Revision: D5391019

Pulled By: siying

fbshipit-source-id: a1d36037ef4c34b9ca77ab2127f3e17242c617cc
2017-07-10 12:12:22 -07:00
Sagar Vemuri 56656e12d6 Temporarily disable FIFOCompactionWithTTLTest
Summary:
FIFOCompactionWithTTLTests are flaky when run in parallel, as there is a time element involved to it. Temporarily disabling them while I investigate a more robust testing solution like, say,  mocking time.
Closes https://github.com/facebook/rocksdb/pull/2548

Differential Revision: D5386084

Pulled By: sagar0

fbshipit-source-id: 262886b25bdf091021d8553e780443a985e9bac4
2017-07-07 20:12:58 -07:00
Maysam Yabandeh b5fb85ec51 fix valgrind init complaint
Summary: Closes https://github.com/facebook/rocksdb/pull/2549

Differential Revision: D5386307

Pulled By: maysamyabandeh

fbshipit-source-id: 3032c95c54755053b6450765ec4dacbecb734f9d
2017-07-07 18:27:08 -07:00
Andrew Kryczka 657df29eaf Add max_background_jobs to db_bench
Summary:
As titled. Also fixed an off-by-one error causing us to add one less range deletion than the user specified.
Closes https://github.com/facebook/rocksdb/pull/2544

Differential Revision: D5383451

Pulled By: ajkr

fbshipit-source-id: cbd5890c33f09bbb5c0c1f4bb952a1add32336e0
2017-07-07 18:13:21 -07:00
Aaron Gao a43c053ad8 remove duplicated utilities/merge_operators/cassandra/test_utils.cc in src.mk
Summary:
target `utilities/merge_operators/cassandra/test_utils.d' given more than once in the same rule
remove the duplicate one
Closes https://github.com/facebook/rocksdb/pull/2542

Differential Revision: D5379570

Pulled By: lightmark

fbshipit-source-id: 353f38d085e9f627c1b3c53acef7a2c4bc71014d
2017-07-06 17:28:57 -07:00
Siying Dong 7c4a9e6c92 Initialize a variable in ldb to make code analysis tool happy
Summary: Closes https://github.com/facebook/rocksdb/pull/2529

Differential Revision: D5378787

Pulled By: siying

fbshipit-source-id: 801ecacc2804f77cb3c9e5e665829e439db68800
2017-07-06 15:56:57 -07:00
Maysam Yabandeh 98669b5356 init filters_in_partition_
Summary:
Valgrind reports that it is not initialized.
Closes https://github.com/facebook/rocksdb/pull/2541

Differential Revision: D5376084

Pulled By: maysamyabandeh

fbshipit-source-id: 55c312f4f506863aa0d25ff92c8c34b57f48b860
2017-07-06 08:48:53 -07:00
Maysam Yabandeh 0013bf14ef fix asan and valgrind leak report in test
Summary: Closes https://github.com/facebook/rocksdb/pull/2537

Differential Revision: D5371433

Pulled By: maysamyabandeh

fbshipit-source-id: 90d3e8bb1a8576f48b1ddf1bdbba5512b5986ba0
2017-07-05 19:11:39 -07:00
Aaron Gao 521b4c28b9 rocksdb 5.5.1 release post
Summary:
https://github.com/facebook/rocksdb/releases/tag/v5.5.1
Closes https://github.com/facebook/rocksdb/pull/2522

Differential Revision: D5365355

Pulled By: lightmark

fbshipit-source-id: 63371a98ebc7429766fd86dc27c1ea35950c98f5
2017-07-05 16:41:30 -07:00
Andrew Kryczka 33042573db Fix GetCurrentTime() initialization for valgrind
Summary:
Valgrind had false positive complaints about the initialization pattern for `GetCurrentTime()`'s argument in #2480. We can instead have the client initialize the time variable before calling `GetCurrentTime()`, and have `GetCurrentTime()` promise to only overwrite it in success case.
Closes https://github.com/facebook/rocksdb/pull/2526

Differential Revision: D5358689

Pulled By: ajkr

fbshipit-source-id: 857b189f24c19196f6bb299216f3e23e7bc4be42
2017-07-05 12:12:00 -07:00
Maysam Yabandeh f6b9d9355e Fix clang error in PartitionedFilterBlockBuilder
Summary: Closes https://github.com/facebook/rocksdb/pull/2536

Differential Revision: D5371271

Pulled By: maysamyabandeh

fbshipit-source-id: f1355ac658a79c9982a24986f0925c9e24fc39d5
2017-07-05 11:16:04 -07:00
Maysam Yabandeh 45b9bb0331 Cut filter partition based on metadata_block_size
Summary:
Currently metadata_block_size controls only index partition size. With this patch a partition is cut after any of index or filter partitions reaches metadata_block_size.
Closes https://github.com/facebook/rocksdb/pull/2452

Differential Revision: D5275651

Pulled By: maysamyabandeh

fbshipit-source-id: 5057e4424b4c8902043782e6bf8c38f0c4f25160
2017-07-02 10:42:12 -07:00
Andrew Kryczka f4ae1bab02 update history for OnBackgroundError and DeleteRange fix
Summary:
Mentioned changes:
- #2477
- #2503
Closes https://github.com/facebook/rocksdb/pull/2528

Differential Revision: D5360185

Pulled By: ajkr

fbshipit-source-id: 59d6ae465bcb0aa0a739317581fa3fc7871c6de6
2017-06-30 16:57:57 -07:00
Siying Dong 1cb8c6de63 Add -enable_pipelined_write to db_bench and add two defaults
Summary:
Expose pipeline write in db_bench and change the default to parallel memtable inserts
Closes https://github.com/facebook/rocksdb/pull/2527

Differential Revision: D5359825

Pulled By: siying

fbshipit-source-id: e30755feb07ff19a731c4058acf101e02de4e197
2017-06-30 15:27:03 -07:00
Maysam Yabandeh 7604b463b5 Update the AddDBStats in LITE
Summary: Closes https://github.com/facebook/rocksdb/pull/2525

Differential Revision: D5356859

Pulled By: maysamyabandeh

fbshipit-source-id: f593adad2a8aab12dcd6ab25db076eca51d30d34
2017-06-30 10:56:50 -07:00
Maysam Yabandeh 1e34d07e18 Simplify and document sync rules for logs_ etc
Summary:
Adding/Correcting inline comments and clarify the sync rules. To make it simple to reason, the rules are a big general which ended up to some extra synchronizations. However such synchronizations are not on the fast path, and they are worth the simplicity.
Closes https://github.com/facebook/rocksdb/pull/2517

Differential Revision: D5348239

Pulled By: maysamyabandeh

fbshipit-source-id: ff2e59fb1e568c122d2cdbf598310f3613b7d212
2017-06-30 09:42:28 -07:00
Andrew Kryczka d310e0f339 Regression test for empty dedicated range deletion file
Summary:
Issue: #2478
Fix: #2503

The bug happened when all of these conditions were satisfied:

- A subcompaction generates no keys
- `RangeDelAggregator::ShouldAddTombstones()` returns true because there's at least one non-obsoleted range deletion in its map
- None of the non-obsolete tombstones overlap with the subcompaction key-range

Under those conditions, we were creating a dedicated file for range deletions which was left empty, thus causing an error in VersionEdit.

I verified this test case fails before the #2503 fix and passes after.
Closes https://github.com/facebook/rocksdb/pull/2521

Differential Revision: D5352568

Pulled By: ajkr

fbshipit-source-id: f619cae39984ce9bb9b7a4e7a9ac0f2bb2ce43e9
2017-06-30 00:11:25 -07:00
Maysam Yabandeh e9f91a5176 Add a fetch_add variation to AddDBStats
Summary:
AddDBStats is in two steps of load and store, which is more efficient than fetch_add. This is however not thread-safe. Currently we have to protect concurrent access to AddDBStats with a mutex which is less efficient that fetch_add.

This patch adds the option to do fetch_add when AddDBStats. The results for my 2pc benchmark on sysbench is:
- vanilla: 68618 tps
- removing mutex on AddDBStats (unsafe): 69767 tps
- fetch_add for all AddDBStats: 69200 tps
- fetch_add only for concurrently access AddDBStats (this patch): 69579 tps
Closes https://github.com/facebook/rocksdb/pull/2505

Differential Revision: D5330656

Pulled By: maysamyabandeh

fbshipit-source-id: af64d7bee135b0e86b4fac323a4f9d9113eaa383
2017-06-29 17:12:19 -07:00
zhangjinpeng1987 c1b375e96a skip generating empty sst
Summary:
When a compaction job output nothing, there is no necessary to generate a empty sst file which will cause `VersionEdit::EncodeTo` failed.
ref https://github.com/facebook/rocksdb/issues/2478
Closes https://github.com/facebook/rocksdb/pull/2503

Differential Revision: D5350799

Pulled By: ajkr

fbshipit-source-id: df0b4fcf3507fe1c3c435208b762e75478e00143
2017-06-29 15:26:52 -07:00
Yi Wu 67b417d624 fix format compatible test
Summary:
The comma "," is not a valid separator for bash arrays.
Closes https://github.com/facebook/rocksdb/pull/2516

Differential Revision: D5348101

Pulled By: yiwu-arbug

fbshipit-source-id: 8f0afdac368e21076eb7366b7df7dbaaf158cf96
2017-06-29 10:42:14 -07:00
Siying Dong afbef65187 Bug fix: Fast CRC Support printing is not honest
Summary:
11c5d4741a introduces a bug that IsFastCrc32Supported() returns wrong result. Fix it. Also fix some FB internal scripts.
Closes https://github.com/facebook/rocksdb/pull/2513

Differential Revision: D5343802

Pulled By: yiwu-arbug

fbshipit-source-id: 057dc7ae3b262fe951413d1190ce60afc788cc05
2017-06-28 21:41:42 -07:00
Mike Kolupaev 397ab11152 Improve Status message for block checksum mismatches
Summary:
We've got some DBs where iterators return Status with message "Corruption: block checksum mismatch" all the time. That's not very informative. It would be much easier to investigate if the error message contained the file name - then we would know e.g. how old the corrupted file is, which would be very useful for finding the root cause. This PR adds file name, offset and other stuff to some block corruption-related status messages.

It doesn't improve all the error messages, just a few that were easy to improve. I'm mostly interested in "block checksum mismatch" and "Bad table magic number" since they're the only corruption errors that I've ever seen in the wild.
Closes https://github.com/facebook/rocksdb/pull/2507

Differential Revision: D5345702

Pulled By: al13n321

fbshipit-source-id: fc8023d43f1935ad927cef1b9c55481ab3cb1339
2017-06-28 21:27:01 -07:00
Siying Dong 18c63af6ef Make "make analyze" happy
Summary:
"make analyze" is reporting some errors. It's complicated to look but it seems to me that they are all false positive. Anyway, I think cleaning them up is a good idea. Some of the changes are hacky but I don't know a better way.
Closes https://github.com/facebook/rocksdb/pull/2508

Differential Revision: D5341710

Pulled By: siying

fbshipit-source-id: 6070e430e0e41a080ef441e05e8ec827d45efab6
2017-06-28 15:42:27 -07:00
Maysam Yabandeh 01534db24c Fix the reported asan issues
Summary:
This is to resolve the asan complains. In the meanwhile I am working on clarifying/revisiting the sync rules.
Closes https://github.com/facebook/rocksdb/pull/2510

Differential Revision: D5338660

Pulled By: yiwu-arbug

fbshipit-source-id: ce6f6e0826d43a2c0bfa4328a00c78f73cd6498a
2017-06-28 13:13:22 -07:00
Sagar Vemuri 1cd45cd1b3 FIFO Compaction with TTL
Summary:
Introducing FIFO compactions with TTL.

FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size.

To address that request:
- Added a new TTL option to FIFO compaction options.
- Updated FIFO compaction score to take TTL into consideration.
- Added a new table property, creation_time, to keep track of when the SST file is created.
- Creation_time is set as below:
  - On Flush: Set to the time of flush.
  - On Compaction: Set to the max creation_time of all the files involved in the compaction.
  - On Repair and Recovery: Set to the time of repair/recovery.
  - Old files created prior to this code change will have a creation_time of 0.
- FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day.
- FIFO compaction will fall back to the prior way of deleting files based on size if:
  - the creation_time of all files involved in compaction is 0.
  - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted.

This feature is not supported if max_open_files != -1 or with table formats other than Block-based.

**Test Plan:**
Added tests.

**Benchmark results:**
Base: FIFO with max size: 100MB ::
```
svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100

readwhilewriting :       1.924 micros/op 519858 ops/sec;   13.6 MB/s (1176277 of 5000000 found)
```

With TTL (a low one for testing) ::
```
svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20

readwhilewriting :       1.902 micros/op 525817 ops/sec;   13.7 MB/s (1185057 of 5000000 found)
```
Example Log lines:
```
2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion
2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files
...
2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK
2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40}
```

SST Files remaining in the dbbench dir, after db_bench execution completed:
```
svemuri@dev15905 ~/rocksdb (fifo-compaction)  $ ls -l /dev/shm//dbbench/*.sst
-rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst
-rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst
-rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst
```
Closes https://github.com/facebook/rocksdb/pull/2480

Differential Revision: D5305116

Pulled By: sagar0

fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
2017-06-27 17:11:48 -07:00
Yi Wu 982cec22af Fix TARGETS file tests list
Summary:
1. The buckifier script assume each test "foo" comes with a .cc file of the same name (i.e. foo.cc). Update cassandra tests to follow this pattern so that the buckifier script can recognize them.
2. add blob_db_test
Closes https://github.com/facebook/rocksdb/pull/2506

Differential Revision: D5331517

Pulled By: yiwu-arbug

fbshipit-source-id: 86f3eba471fc621186ab44cbd073b6162cde8e57
2017-06-27 14:12:02 -07:00
Yi Wu b49b371092 allow numa >= 2.0.8
Summary:
Allow numa >= 2.0.8 in buck TARGET file.
Closes https://github.com/facebook/rocksdb/pull/2504

Differential Revision: D5330550

Pulled By: yiwu-arbug

fbshipit-source-id: 8ffb6167b4ad913877eac16a20a91023b31f8d41
2017-06-27 11:27:02 -07:00
Siying Dong e517bfa2c2 CLANG Tidy
Summary: Closes https://github.com/facebook/rocksdb/pull/2502

Differential Revision: D5326498

Pulled By: siying

fbshipit-source-id: 2f0ac6dc6ca5ddb23cecf67a278c086e52646714
2017-06-27 11:00:59 -07:00
Yi Wu dc3d2e4d21 update compatible test
Summary:
update compatible test to include 5.5 and 5.6 branch.
Closes https://github.com/facebook/rocksdb/pull/2501

Differential Revision: D5325220

Pulled By: yiwu-arbug

fbshipit-source-id: 5f5271491e6dd2d7b2cf73a7142f38a571553bc4
2017-06-27 11:00:59 -07:00
Siying Dong 89468c01d4 Fix Windows build broken by 5c97a7c066
Summary:
A typo conversion fails Windows build. Fix it.
Closes https://github.com/facebook/rocksdb/pull/2500

Differential Revision: D5325962

Pulled By: siying

fbshipit-source-id: 2cefdafc9afbc85f856f403af7c876b622400630
2017-06-26 17:28:22 -07:00
Ewout Prangsma 51778612c9 Encryption at rest support
Summary:
This PR adds support for encrypting data stored by RocksDB when written to disk.

It adds an `EncryptedEnv` override of the `Env` class with matching overrides for sequential&random access files.
The encryption itself is done through a configurable `EncryptionProvider`. This class creates is asked to create `BlockAccessCipherStream` for a file. This is where the actual encryption/decryption is being done.
Currently there is a Counter mode implementation of `BlockAccessCipherStream` with a `ROT13` block cipher (NOTE the `ROT13` is for demo purposes only!!).

The Counter operation mode uses an initial counter & random initialization vector (IV).
Both are created randomly for each file and stored in a 4K (default size) block that is prefixed to that file. The `EncryptedEnv` implementation is such that clients of the `Env` class do not see this prefix (nor data, nor in filesize).
The largest part of the prefix block is also encrypted, and there is room left for implementation specific settings/values/keys in there.

To test the encryption, the `DBTestBase` class has been extended to consider a new environment variable called `ENCRYPTED_ENV`. If set, the test will setup a encrypted instance of the `Env` class to use for all tests.
Typically you would run it like this:

```
ENCRYPTED_ENV=1 make check_some
```

There is also an added test that checks that some data inserted into the database is or is not "visible" on disk. With `ENCRYPTED_ENV` active it must not find plain text strings, with `ENCRYPTED_ENV` unset, it must find the plain text strings.
Closes https://github.com/facebook/rocksdb/pull/2424

Differential Revision: D5322178

Pulled By: sdwilsh

fbshipit-source-id: 253b0a9c2c498cc98f580df7f2623cbf7678a27f
2017-06-26 16:56:24 -07:00
Siying Dong 7061912c23 Trivial typo in HISTORY.md
Summary: Closes https://github.com/facebook/rocksdb/pull/2499

Differential Revision: D5324914

Pulled By: siying

fbshipit-source-id: c69827d4dddafa81e651180633943a3380cdd5bb
2017-06-26 15:57:08 -07:00
Yi Wu 2a9cd87997 Fix jni WriteBatchThreadedTest
Summary:
WriteBatchThreadedTest is failing, at least on Mac. The problem seems to be `wb` is getting GC before we finish write. Explicitly close it seems to fix it.
Closes https://github.com/facebook/rocksdb/pull/2482

Differential Revision: D5307379

Pulled By: yiwu-arbug

fbshipit-source-id: 8ff7f8170451078c941951f5aafae83afffb7933
2017-06-26 15:27:17 -07:00
Aaron Gao 0025a36409 revert perf_context and io_stats to __thread
Summary:
https://github.com/facebook/rocksdb/pull/2380 introduces a regression by replacing __thread with ThreadLocalPtr. Revert the thread local implementation back.
Closes https://github.com/facebook/rocksdb/pull/2485

Differential Revision: D5308050

Pulled By: lightmark

fbshipit-source-id: 2676e9c22edf76e8133d3f4c50e2711e11a95480
2017-06-26 15:27:17 -07:00
Siying Dong 5c97a7c066 Unit Tests for sync, range sync and file close failures
Summary: Closes https://github.com/facebook/rocksdb/pull/2454

Differential Revision: D5255320

Pulled By: siying

fbshipit-source-id: 0080830fa8eb5da6de25e17ba68aee91018c7913
2017-06-26 13:27:58 -07:00
Andrew Kryczka 4cee11f4e3 Intra-L0 blog post
Summary:
as titled
Closes https://github.com/facebook/rocksdb/pull/2497

Differential Revision: D5322732

Pulled By: ajkr

fbshipit-source-id: 35a648a7af737032949ed99f430f4fd865ac9e9c
2017-06-26 13:11:41 -07:00
Siying Dong 857e9960be Improve the error message for I/O related errors.
Summary:
Force people to write something other than file name while returning status for IOError.
Closes https://github.com/facebook/rocksdb/pull/2493

Differential Revision: D5321309

Pulled By: siying

fbshipit-source-id: 38bcf6c19e80831cd3e300a047e975cbb131d822
2017-06-26 12:57:01 -07:00
Siying Dong d757355cbf Fix bug that flush doesn't respond to fsync result
Summary:
With a regression bug was introduced two years ago, by https://github.com/facebook/rocksdb/commit/6e9fbeb27c38329f33ae541302c44c8db8374f8c , we fail to check return status of fsync call. This can cause we miss the information from the file system and can potentially cause corrupted data which we could have been detected.
Closes https://github.com/facebook/rocksdb/pull/2495

Reviewed By: ajkr

Differential Revision: D5321949

Pulled By: siying

fbshipit-source-id: c68117914bb40700198fc37d0e4c63163a8a1031
2017-06-26 12:41:48 -07:00
Maysam Yabandeh 8e6345d2df Update rename of ParanoidCheck
Summary: Closes https://github.com/facebook/rocksdb/pull/2494

Differential Revision: D5317902

Pulled By: maysamyabandeh

fbshipit-source-id: 097330292180816b3d0c9f4cbbdb6f68f0180200
2017-06-24 18:12:03 -07:00
Maysam Yabandeh 499ebb3ab5 Optimize for serial commits in 2PC
Summary:
Throughput: 46k tps in our sysbench settings (filling the details later)

The idea is to have the simplest change that gives us a reasonable boost
in 2PC throughput.

Major design changes:
1. The WAL file internal buffer is not flushed after each write. Instead
it is flushed before critical operations (WAL copy via fs) or when
FlushWAL is called by MySQL. Flushing the WAL buffer is also protected
via mutex_.
2. Use two sequence numbers: last seq, and last seq for write. Last seq
is the last visible sequence number for reads. Last seq for write is the
next sequence number that should be used to write to WAL/memtable. This
allows to have a memtable write be in parallel to WAL writes.
3. BatchGroup is not used for writes. This means that we can have
parallel writers which changes a major assumption in the code base. To
accommodate for that i) allow only 1 WriteImpl that intends to write to
memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes
come via group commit phase which is serial anyway, ii) make all the
parts in the code base that assumed to be the only writer (via
EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are
protected via a stat_mutex_.

Note: the first commit has the approach figured out but is not clean.
Submitting the PR anyway to get the early feedback on the approach. If
we are ok with the approach I will go ahead with this updates:
0) Rebase with Yi's pipelining changes
1) Currently batching is disabled by default to make sure that it will be
consistent with all unit tests. Will make this optional via a config.
2) A couple of unit tests are disabled. They need to be updated with the
serial commit of 2PC taken into account.
3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires
releasing mutex_ beforehand (the same way EnterUnbatched does). This
needs to be cleaned up.
Closes https://github.com/facebook/rocksdb/pull/2345

Differential Revision: D5210732

Pulled By: maysamyabandeh

fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 14:11:29 -07:00
Maysam Yabandeh 0ac4afb975 Sanitize partitioning options
Summary:
We currently do not support partitioning filters if indexes are not partitioned. The patch makes sure that these two are consistent.
Closes https://github.com/facebook/rocksdb/pull/2455

Differential Revision: D5275644

Pulled By: maysamyabandeh

fbshipit-source-id: b61701ac8914c2206d06f5e33ff6f67b24406d1d
2017-06-23 18:30:01 -07:00
jsteemann 521724ba82 fixed wrong type for "allow_compaction" parameter
Summary:
should be boolean, not uint64_t
MSVC complains about it during compilation with error `include\rocksdb\advanced_options.h(77): warning C4800: 'uint64_t': forcing value to bool 'true' or 'false' (performance warning)`
Closes https://github.com/facebook/rocksdb/pull/2487

Differential Revision: D5310685

Pulled By: siying

fbshipit-source-id: 719a33b3dba4f711aa72e3f229013c188015dc86
2017-06-23 09:41:19 -07:00
Andrew Kryczka 71f5bcb730 Introduce OnBackgroundError callback
Summary:
Some users want to prevent rocksdb from entering read-only mode in certain error cases. This diff gives them a callback, `OnBackgroundError`, that they can use to achieve it.

- call `OnBackgroundError` every time we consider setting `bg_error_`. Use its result to assign `bg_error_` but not to change the function's return status.
- classified calls using `BackgroundErrorReason` to give the callback some info about where the error happened
- renamed `ParanoidCheck` to something more specific so we can provide a clear `BackgroundErrorReason`
- unit tests for the most common cases: flush or compaction errors
Closes https://github.com/facebook/rocksdb/pull/2477

Differential Revision: D5300190

Pulled By: ajkr

fbshipit-source-id: a0ea4564249719b83428e3f4c6ca2c49e366e9b3
2017-06-22 19:41:50 -07:00
Siying Dong 88cd2d96e7 Downgrade option sanitiy check level for prefix_extractor
Summary:
With c7004840d2, it's safe to open a DB with different prefix extractor. So it's safe to skip prefix extractor check.
Closes https://github.com/facebook/rocksdb/pull/2474

Differential Revision: D5294700

Pulled By: siying

fbshipit-source-id: eeb500da795eecb29b8c9c56a14cfd4afda12ecc
2017-06-22 16:26:36 -07:00
Siying Dong 6837a17621 Fix Data Race Between CreateColumnFamily() and GetAggregatedIntProperty()
Summary:
CreateColumnFamily() releases DB mutex after adding column family to the set and install super version (to write option file), so if users call GetAggregatedIntProperty() in the middle, then super version will be null and the process will crash. Fix it by skipping those column families without super version installed.

Maybe we should also fix the problem of releasing the lock when reading option file, but it is more risky. so I'm doing a quick and safer fix and we can investigate it later.
Closes https://github.com/facebook/rocksdb/pull/2475

Differential Revision: D5298053

Pulled By: siying

fbshipit-source-id: 4b3c8f91c60400b163fcc6cda8a0c77723be0ef6
2017-06-22 15:56:47 -07:00
Siying Dong af1746751f WriteBufferManager will not trigger flush if much data is already being flushed
Summary:
Even if hard limit hits, flushing more memtable may not help cap the memory usage if already more than half data is scheduled for flush. Not triggering flush instead.
Closes https://github.com/facebook/rocksdb/pull/2469

Differential Revision: D5284249

Pulled By: siying

fbshipit-source-id: 8ab7ba1aba56a634dbe72b318fcab2093063972e
2017-06-21 10:41:37 -07:00
Andrew Kryczka 9467eb6141 Fix flush assertion with tsan
Summary:
DBImpl's instance variables should only be accessed with mutex held. I moved an assert later to uphold this rule.

DBTest.LastWriteBufferDelay test was sporadically failing TSAN because it tried to flush around the same time the db was destroyed, so the variable was accessed simultaneously by two threads.
Closes https://github.com/facebook/rocksdb/pull/2471

Differential Revision: D5286857

Pulled By: ajkr

fbshipit-source-id: 435abd84efa601f667c254e320b0bb5a434b971f
2017-06-20 16:43:44 -07:00
Andrew Kryczka 048446fc74 Fix cassandra ASAN use-after-free
Summary:
When we create a column based on the `string::c_str()`, we need to make sure that char array doesn't get deleted when calls to `string::append()` cause the string to expand.
Closes https://github.com/facebook/rocksdb/pull/2470

Differential Revision: D5285049

Pulled By: ajkr

fbshipit-source-id: f918dd426ff3c024e7a293dcb10448f10b6c98e8
2017-06-20 13:27:16 -07:00
Dmitri Smirnov a21db161c9 Implement ReopenWritibaleFile on Windows and other fixes
Summary:
Make default impl return NoSupported so the db_blob
  tests exist in a meaningful manner.
  Replace std::thread to port::Thread
Closes https://github.com/facebook/rocksdb/pull/2465

Differential Revision: D5275563

Pulled By: yiwu-arbug

fbshipit-source-id: cedf1a18a2c05e20d768c1308b3f3224dbd70ab6
2017-06-20 10:31:13 -07:00
zhangjinpeng1987 c430d69eed fix coredump for release nullptr
Summary:
Coredump will be triggered when ingest external sst file after delete range.
ref https://github.com/facebook/rocksdb/issues/2398
Closes https://github.com/facebook/rocksdb/pull/2463

Differential Revision: D5275599

Pulled By: ajkr

fbshipit-source-id: 0828dbc062ea8c74e913877cd63494fd3478a30d
2017-06-19 11:41:38 -07:00
Andrew Kryczka 0d278456c9 default implementation for InRange
Summary:
it's confusing to implementors of prefix extractor to implement an unused function
Closes https://github.com/facebook/rocksdb/pull/2460

Differential Revision: D5267408

Pulled By: ajkr

fbshipit-source-id: 2f1fe3131efc978f6098ae7a80e52bc7a0b13571
2017-06-18 12:42:42 -07:00
Chen Shen cbd825deea Create a MergeOperator for Cassandra Row Value
Summary:
This PR implements the MergeOperator for Cassandra Row Values.
Closes https://github.com/facebook/rocksdb/pull/2289

Differential Revision: D5055464

Pulled By: scv119

fbshipit-source-id: 45f276ef8cbc4704279202f6a20c64889bc1adef
2017-06-16 14:27:00 -07:00
Maysam Yabandeh 2c98b06bff Remove pin_slice option by making it the default
Summary:
This would simplify db_bench_tool.cc
Closes https://github.com/facebook/rocksdb/pull/2457

Differential Revision: D5259035

Pulled By: maysamyabandeh

fbshipit-source-id: 0a9c3abda624070fe2650200b885ad7e1c60182c
2017-06-15 16:14:08 -07:00
Maysam Yabandeh c80c6115de add db_bench options for partitioning
Summary: Closes https://github.com/facebook/rocksdb/pull/2456

Differential Revision: D5259083

Pulled By: maysamyabandeh

fbshipit-source-id: 1ed1746da7a8baadf4772d023d927c6c4e6b112a
2017-06-15 16:14:08 -07:00
Ben Torfs 6a3377f454 Synchronize statistic enumeration values between statistics.h and java API
Summary: Closes https://github.com/facebook/rocksdb/pull/2209

Differential Revision: D5251951

Pulled By: sagar0

fbshipit-source-id: 03a73d025a7b4a322bb8d8d86f5d249fcd7dd00e
2017-06-14 16:59:42 -07:00
Sagar Vemuri 53dda8797d Do not run RateLimiterTest.Rate test on Travis+Mac OSX.
Summary:
RateLimiterTest.Rate test has been failing continuously since many days on travis in Mac OSX PLATFORM_DEPENDENT test suite.
Check https://travis-ci.org/facebook/rocksdb/pull_requests.

Disabling this test for now, so that we can investigate more in depth.
Closes https://github.com/facebook/rocksdb/pull/2451

Differential Revision: D5250147

Pulled By: sagar0

fbshipit-source-id: d58476a3c2792d20e875754d1516c4bc7174e86c
2017-06-14 14:58:02 -07:00
Yi Wu ae8571f5c2 Fix blob db compression bug
Summary:
`CompressBlock()` will return the uncompressed slice (i.e. `Slice(value_unc)`) if compression ratio is not good enough. This is undesired. We need to always assign the compressed slice to `value`.
Closes https://github.com/facebook/rocksdb/pull/2447

Differential Revision: D5244682

Pulled By: yiwu-arbug

fbshipit-source-id: 6989dd8852c9622822ba9acec9beea02007dff09
2017-06-14 13:56:42 -07:00
Yi Wu 7a380deff7 Update blob_db_test
Summary:
I'm trying to improve unit test of blob db. I'm rewriting blob db test. In this patch:
* Rewrite tests of basic put/write/delete operations.
* Add disable_background_tasks to BlobDBOptionsImpl to allow me not running any background job for basic unit tests.
* Move DestroyBlobDB out from BlobDBImpl to be a standalone function.
* Remove all garbage collection related tests. Will rewrite them in following patch.
* Disabled compression test since it is failing. Will fix in a followup patch.
Closes https://github.com/facebook/rocksdb/pull/2446

Differential Revision: D5243306

Pulled By: yiwu-arbug

fbshipit-source-id: 157c71ad3b699307cb88baa3830e9b6e74f8e939
2017-06-14 13:12:34 -07:00
Sagar Vemuri 89ad9f3adb Allow ignoring unknown options when loading options from a file
Summary:
Added a flag, `ignore_unknown_options`, to skip unknown options when loading an options file (using `LoadLatestOptions`/`LoadOptionsFromFile`) or while verifying options (using `CheckOptionsCompatibility`). This will help in downgrading the db to an older version.

Also added `--ignore_unknown_options` flag to ldb

**Example Use case:**
In MyRocks, if copying from newer version to older version, it is often impossible to start because of new RocksDB options that don't exist in older version, even though data format is compatible.
MyRocks uses these load and verify functions in [ha_rocksdb.cc::check_rocksdb_options_compatibility](https://github.com/facebook/mysql-5.6/blob/e004fd9f416821d043ccc8ad4a345c33ac9953f0/storage/rocksdb/ha_rocksdb.cc#L3348-L3401).

**Test Plan:**
Updated the unit tests.
`make check`

ldb:
$ ./ldb --db=/tmp/test_db --create_if_missing put a1 b1
OK

Now edit /tmp/test_db/<OPTIONS-file> and add an unknown option.

Try loading the options now, and it fails:
$ ./ldb --db=/tmp/test_db --try_load_options get a1
Failed: Invalid argument: Unrecognized option DBOptions:: abcd

Passes with the new --ignore_unknown_options flag
$ ./ldb --db=/tmp/test_db --try_load_options --ignore_unknown_options get a1
b1
Closes https://github.com/facebook/rocksdb/pull/2423

Differential Revision: D5212091

Pulled By: sagar0

fbshipit-source-id: 2ec17636feb47dc0351b53a77e5f15ef7cbf2ca7
2017-06-13 16:58:01 -07:00
hyunwoo 6b5a5dc5d8 fixed typo
Summary:
fixed typo
Closes https://github.com/facebook/rocksdb/pull/2430

Differential Revision: D5242471

Pulled By: IslamAbdelRahman

fbshipit-source-id: 832eb3a4c70221444ccd2ae63217823fec56c748
2017-06-13 16:58:01 -07:00
haoxiang 0f228be3bb fixed typo in util/dynamic_bloom.h
Summary:
fixed a typo in util/dynamic_bloom.h
Closes https://github.com/facebook/rocksdb/pull/2442

Differential Revision: D5242397

Pulled By: IslamAbdelRahman

fbshipit-source-id: c47fd18cc79afff6b022201a0410c0cd47626576
2017-06-13 16:41:36 -07:00
Andrew Kryczka c217e0b9c7 Call RateLimiter for compaction reads
Summary:
Allow users to rate limit background work based on read bytes, written bytes, or sum of read and written bytes. Support these by changing the RateLimiter API, so no additional options were needed.
Closes https://github.com/facebook/rocksdb/pull/2433

Differential Revision: D5216946

Pulled By: ajkr

fbshipit-source-id: aec57a8357dbb4bfde2003261094d786d94f724e
2017-06-13 14:56:46 -07:00
Yi Wu 91e2aa3ce2 write exact sequence number for each put in write batch
Summary:
At the beginning of write batch write, grab the latest sequence from base db and assume sequence number will increment by 1 for each put and delete, and write the exact sequence number with each put. This is assuming we are the only writer to increment sequence number (no external file ingestion, etc) and there should be no holes in the sequence number.

Also having some minor naming changes.
Closes https://github.com/facebook/rocksdb/pull/2402

Differential Revision: D5176134

Pulled By: yiwu-arbug

fbshipit-source-id: cb4712ee44478d5a2e5951213a10b72f08fe8c88
2017-06-13 12:42:36 -07:00
Maysam Yabandeh 6f4154d693 record index partition properties
Summary:
When Partitioning index/filter is enabled the user might need to check the index block size as well as the top-level index size via sst_dump. This patch records i) number of partitions, ii) top-level index size and make it accessible through sst_dump. The number of partitions for filters is the same as that of indexes. The top-level index for filters has a similar size to top-level index for indexes, so it is not repeated.
Closes https://github.com/facebook/rocksdb/pull/2437

Differential Revision: D5224225

Pulled By: maysamyabandeh

fbshipit-source-id: 5324598c75793523aef1bb7ee225a5475e95a9cb
2017-06-13 11:21:32 -07:00
Siying Dong 5d5a28a98c Fix Clang release build broken by 5582123dee
Summary:
5582123dee broken CLANG release build because of an unexpected change. Fix it.
Closes https://github.com/facebook/rocksdb/pull/2443

Differential Revision: D5236297

Pulled By: siying

fbshipit-source-id: 1b410adf13ded149c53e8235e9ea9f3130fb5403
2017-06-13 04:56:35 -07:00
Siying Dong 0175d58c3c Make direct I/O write use incremental buffer
Summary:
Currently for direct I/O, the large maximum buffer is always allocated. This will be wasteful if users flush the data in much smaller chunks. This diff fix this by changing the behavior of incremental buffer works. When we enlarge buffer, we try to copy the existing data in the buffer to the enlarged buffer, rather than flush the buffer first. This can make sure that no extra I/O is introduced because of buffer enlargement.
Closes https://github.com/facebook/rocksdb/pull/2403

Differential Revision: D5178403

Pulled By: siying

fbshipit-source-id: a8fe1e7304bdb8cab2973340022fe80ff83449fd
2017-06-13 04:41:37 -07:00
Anirban Rahut 7a270069b3 GNU C library for struct tm has 2 additional fields.
Summary:
initialize 2 additional fields tm_gmtoff and tm_zone,
otherwise under strict warnings for initialization, we get errors
in myrocks.
Closes https://github.com/facebook/rocksdb/pull/2439

Differential Revision: D5229013

Pulled By: yiwu-arbug

fbshipit-source-id: 9fc1615a1919656f36064791706ed41e10e9db84
2017-06-13 04:41:35 -07:00
Islam AbdelRahman d713471da8 Limit trash directory to be 25% of total DB
Summary:
Update DeleteScheduler to delete files immediately if trash directory is >= 25% of DB size
Closes https://github.com/facebook/rocksdb/pull/2436

Differential Revision: D5230384

Pulled By: IslamAbdelRahman

fbshipit-source-id: 5cbda8ac536a3cc72c774641621edc02c8202482
2017-06-12 16:57:21 -07:00
Orgad Shaneh 9bb91e9328 Dedup release
Summary:
cc tamird sagar0
Closes https://github.com/facebook/rocksdb/pull/2325

Differential Revision: D5098302

Pulled By: sagar0

fbshipit-source-id: 297c5506b5d9b2ed1d7719c8caf0b96cffe503b8
2017-06-12 13:13:06 -07:00
Sagar Vemuri 27b450165e Update HistogramTypes in the Java API
Summary:
This diff syncs the Histogram Types in the Java API with the ones in C++ API (`statistics.h`), and brings it up-to-date.

I also found that the enum ordering between Java and C++ has gotten out-of-sync, a few years back, with the addition of `SUBCOMPACTION_SETUP_TIME`. So updated the order as well.

`READ_NUM_MERGE_OPERANDS` added in #2373 is needed for Cassandra-on-RocksDB work.
Closes https://github.com/facebook/rocksdb/pull/2429

Differential Revision: D5215623

Pulled By: sagar0

fbshipit-source-id: bd136698c48197e53693275eb52acc9198ee5a4e
2017-06-12 12:57:49 -07:00
Andrew Kryczka e97304c681 update history for 5.6
Summary:
- mention range deletion + file ingestion
- move post-5.6 stuff into new section
Closes https://github.com/facebook/rocksdb/pull/2440

Differential Revision: D5229910

Pulled By: ajkr

fbshipit-source-id: 1facfe41993fa1f3b1f6fa7dc77d2b11aa2b317a
2017-06-12 12:30:09 -07:00
Siying Dong 5582123dee Sample number of reads per SST file
Summary:
We estimate number of reads per SST files, by updating the counter per file in sampled read requests. This information can later be used to trigger compactions to improve read performacne.
Closes https://github.com/facebook/rocksdb/pull/2417

Differential Revision: D5193528

Pulled By: siying

fbshipit-source-id: b4241c5ad0eaf444b61afb53f8e6290d9f5da2df
2017-06-12 07:12:08 -07:00
Siying Dong db818d2d1a Fix RocksDB Lite build with CLANG
Summary: Closes https://github.com/facebook/rocksdb/pull/2419

Differential Revision: D5193976

Pulled By: siying

fbshipit-source-id: 62d115edee6043237e9d6ad3c2a05481e162c9eb
2017-06-12 06:41:27 -07:00
Aaron Gao a472c4ae4c update 5.5 change log
Summary:
update bug fixed.
Closes https://github.com/facebook/rocksdb/pull/2434

Differential Revision: D5218601

Pulled By: lightmark

fbshipit-source-id: 1f86b2c93345673612381081537d464e7d12e434
2017-06-09 11:12:10 -07:00
Mike Kolupaev bc09c8a0db Fix crash in PosixWritableFile::Close() when fstat() fails
Summary:
We had a crash in this code: `fstat()` failed; `file_stats` contained garbage, in particular `file_stats.st_blksize == 6`; the expression `file_stats.st_blocks / (file_stats.st_blksize / 512)` divided by zero.
Closes https://github.com/facebook/rocksdb/pull/2420

Differential Revision: D5216110

Pulled By: al13n321

fbshipit-source-id: 6d8fc5e7c4f98c1139e68c7829ebdbac68b0fce0
2017-06-08 19:56:22 -07:00
Yi Wu 6d0f22e42f Fix mock_env.cc uninitialized variable
Summary:
Mingw is complaining about uninitialized variable in mock_env.cc. e.g. https://travis-ci.org/facebook/rocksdb/jobs/240132276
The fix is to initialize the variable.
Closes https://github.com/facebook/rocksdb/pull/2428

Differential Revision: D5211306

Pulled By: yiwu-arbug

fbshipit-source-id: ee02bf0327dcea8590a2aa087f0176fecaf8621c
2017-06-08 17:41:59 -07:00
Sagar Vemuri c2012d488f Java APIs for put, merge and delete in file ingestion
Summary:
Adding SSTFileWriter's newly introduced put, merge and delete apis to the Java api. The C++ APIs were first introduced in #2361.

Add is deprecated in favor of Put.
Merge is especially needed to support streaming for Cassandra-on-RocksDB work in https://issues.apache.org/jira/browse/CASSANDRA-13476.
Closes https://github.com/facebook/rocksdb/pull/2392

Differential Revision: D5165091

Pulled By: sagar0

fbshipit-source-id: 6f0ad396a7cbd2e27ca63e702584784dd72acaab
2017-06-08 17:11:57 -07:00
Yi Wu 85dace2afa Disable DBRangeDelTest::TailingIteratorRangeTombstoneUnsupported for ubsan
Summary:
UBSAN crashes when it run the test. Disabling it for UBSAN.
Closes https://github.com/facebook/rocksdb/pull/2427

Differential Revision: D5210897

Pulled By: yiwu-arbug

fbshipit-source-id: 2f5a876807c98d8db79ab9581965f7e6b29d4163
2017-06-08 12:43:01 -07:00
Maysam Yabandeh d4f7731b61 fix travis error with init time in mockenv
Summary:
/home/travis/build/facebook/rocksdb/env/mock_env.cc: In member function ‘virtual void rocksdb::{anonymous}::TestMemLogger::Logv(const char*, va_list)’:
/home/travis/build/facebook/rocksdb/env/mock_env.cc:391:53: error: ‘t.tm::tm_year’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
                     static_cast<int>(now_tv.tv_usec));
Closes https://github.com/facebook/rocksdb/pull/2418

Differential Revision: D5193597

Pulled By: maysamyabandeh

fbshipit-source-id: 8801a3ef27f33eb419d534f7de747702cdf504a0
2017-06-08 10:41:18 -07:00
Maysam Yabandeh 550a1df72c Fix clang errors by asserting the precondition
Summary:
USE_CLANG=1 make -j32 analyze
The two errors would disappear after the assertion.
Closes https://github.com/facebook/rocksdb/pull/2416

Differential Revision: D5193526

Pulled By: maysamyabandeh

fbshipit-source-id: 16a21f18f68023f862764dd3ab9e00ca60b0eefa
2017-06-06 12:56:52 -07:00
Maysam Yabandeh cc5f9339ee Fix concurrency issue with filter_block_set_
Summary:
filter_block_set_ access must also be protected with mutex.
Closes https://github.com/facebook/rocksdb/pull/2413

Differential Revision: D5193159

Pulled By: maysamyabandeh

fbshipit-source-id: 6987fc219d9a65c20b9c7e52151aef4b8e4882e6
2017-06-06 12:56:52 -07:00
Aaron Gao 2e64f450dc bump version to 5.6
Summary:
Bump version to 5.6 beforehand in master
Closes https://github.com/facebook/rocksdb/pull/2411

Differential Revision: D5186896

Pulled By: lightmark

fbshipit-source-id: 079538e621b1a959c2dc99dada894e9cdb99ef95
2017-06-05 16:15:21 -07:00
Yi Wu afbc2d0d2e Force travis to build with clang on MacOS
Summary:
Attempt to force travis to build with clang on MacOS
Closes https://github.com/facebook/rocksdb/pull/2408

Differential Revision: D5186635

Pulled By: yiwu-arbug

fbshipit-source-id: dbb779eff07b1cb7dbd2092631303cf946316656
2017-06-05 15:41:57 -07:00
Sagar Vemuri b172a3f1a2 Fix warnings while generating RocksJava documentation
Summary:
There are a couple of warnings while building RocksJava, coming from Javadoc generation.
```
Generating target/apidocs/org/rocksdb/RocksDB.html...
src/main/java/org/rocksdb/RocksDB.java:2139: warning: no throws for org.rocksdb.RocksDBException
  public void ingestExternalFile(final List<String> filePathList,
              ^
src/main/java/org/rocksdb/RocksDB.java:2162: warning: no throws for org.rocksdb.RocksDBException
  public void ingestExternalFile(final ColumnFamilyHandle columnFamilyHandle,
              ^
```
Closes https://github.com/facebook/rocksdb/pull/2396

Differential Revision: D5178388

Pulled By: sagar0

fbshipit-source-id: a0ab6696d6de78d089a9a860a559f64cc320019e
2017-06-05 15:28:00 -07:00
Siying Dong 52a7f38b19 WriteOptions.low_pri which can throttle low pri writes if needed
Summary:
If ReadOptions.low_pri=true and compaction is behind, the write will either return immediate or be slowed down based on ReadOptions.no_slowdown.
Closes https://github.com/facebook/rocksdb/pull/2369

Differential Revision: D5127619

Pulled By: siying

fbshipit-source-id: d30e1cff515890af0eff32dfb869d2e4c9545eb0
2017-06-05 15:02:35 -07:00
Adam Retter 26a8a80711 Switch from CentOS 5 to CentOS 6 for crossbuilding RocksJava
Summary:
Updates the statically linked libraries from linking against glibc 2.5, to linking against glibc 2.12.
Closes https://github.com/facebook/rocksdb/pull/2405

Differential Revision: D5184132

Pulled By: sagar0

fbshipit-source-id: 7a8ad4cf7e737ca62f29e58938bd49fa02114541
2017-06-05 12:27:24 -07:00
Yi Wu dba9f3722b Fix db_write_test clang/windows build failure
Summary:
Fix db_write_test clang/windows build failure. Explicitly cast size_t (unsigned long) to uint32_t (unsigned int).
Closes https://github.com/facebook/rocksdb/pull/2407

Differential Revision: D5182995

Pulled By: yiwu-arbug

fbshipit-source-id: aba225a9fccb12d5bfbdc2cd6efc11040706a9d2
2017-06-05 12:27:24 -07:00
hyunwoo c7662a44a4 fixed typo
Summary:
fixed typo
Closes https://github.com/facebook/rocksdb/pull/2376

Differential Revision: D5183630

Pulled By: ajkr

fbshipit-source-id: 133cfd0445959e70aa2cd1a12151bf3c0c5c3ac5
2017-06-05 11:27:34 -07:00
Adam Retter 7e8d95cc0e Fix the Java build which was broken by a4d9c02
Summary: Closes https://github.com/facebook/rocksdb/pull/2406

Differential Revision: D5181091

Pulled By: ajkr

fbshipit-source-id: fd72525da4fb1d50143080a210f8d824cbb968d6
2017-06-04 18:41:33 -07:00
Aaron Gao 7e5fac2c34 remove test dir before exit when current regression is running
Summary:
clean up the current test dir if the last regression test is still running.
Closes https://github.com/facebook/rocksdb/pull/2401

Differential Revision: D5177882

Pulled By: lightmark

fbshipit-source-id: 91d899fcc2bde841948eae71af8584d4bdb35468
2017-06-02 17:26:19 -07:00
Aaron Gao 7f6c02dda1 using ThreadLocalPtr to hide ROCKSDB_SUPPORT_THREAD_LOCAL from public…
Summary:
… headers

https://github.com/facebook/rocksdb/pull/2199 should not reference RocksDB-specific macros (like ROCKSDB_SUPPORT_THREAD_LOCAL in this case) to public headers, `iostats_context.h` and `perf_context.h`. We shouldn't do that because users have to provide these compiler flags when building their binary with RocksDB.

We should hide the thread local global variable inside our implementation and just expose a function api to retrieve these variables. It may break some users for now but good for long term.

make check -j64
Closes https://github.com/facebook/rocksdb/pull/2380

Differential Revision: D5177896

Pulled By: lightmark

fbshipit-source-id: 6fcdfac57f2e2dcfe60992b7385c5403f6dcb390
2017-06-02 17:26:19 -07:00
Mike Kolupaev 138b87eae4 Fix interaction between CompactionFilter::Decision::kRemoveAndSkipUnt…
Summary:
Fixes the following scenario:
 1. Set prefix extractor. Enable bloom filters, with `whole_key_filtering = false`. Use compaction filter that sometimes returns `kRemoveAndSkipUntil`.
 2. Do a compaction.
 3. Compaction creates an iterator with `total_order_seek = false`, calls `SeekToFirst()` on it, then repeatedly calls `Next()`.
 4. At some point compaction filter returns `kRemoveAndSkipUntil`.
 5. Compaction calls `Seek(skip_until)` on the iterator. The key that it seeks to happens to have prefix that doesn't match the bloom filter. Since `total_order_seek = false`, iterator becomes invalid, and compaction thinks that it has reached the end. The rest of the compaction input is silently discarded.

The fix is to make compaction iterator use `total_order_seek = true`.

The implementation for PlainTable is quite awkward. I've made `kRemoveAndSkipUntil` officially incompatible with PlainTable. If you try to use them together, compaction will fail, and DB will enter read-only mode (`bg_error_`). That's not a very graceful way to communicate a misconfiguration, but the alternatives don't seem worth the implementation time and complexity. To be able to check in advance that `kRemoveAndSkipUntil` is not going to be used with PlainTable, we'd need to extend the interface of either `CompactionFilter` or `InternalIterator`. It seems unlikely that anyone will ever want to use `kRemoveAndSkipUntil` with PlainTable: PlainTable probably has very few users, and `kRemoveAndSkipUntil` has only one user so far: us (logdevice).
Closes https://github.com/facebook/rocksdb/pull/2349

Differential Revision: D5110388

Pulled By: lightmark

fbshipit-source-id: ec29101a99d9dcd97db33923b87f72bce56cc17a
2017-06-02 15:11:38 -07:00
Siying Dong 95b0e89b5d Improve write buffer manager (and allow the size to be tracked in block cache)
Summary:
Improve write buffer manager in several ways:
1. Size is tracked when arena block is allocated, rather than every allocation, so that it can better track actual memory usage and the tracking overhead is slightly lower.
2. We start to trigger memtable flush when 7/8 of the memory cap hits, instead of 100%, and make 100% much harder to hit.
3. Allow a cache object to be passed into buffer manager and the size allocated by memtable can be costed there. This can help users have one single memory cap across block cache and memtable.
Closes https://github.com/facebook/rocksdb/pull/2350

Differential Revision: D5110648

Pulled By: siying

fbshipit-source-id: b4238113094bf22574001e446b5d88523ba00017
2017-06-02 14:26:56 -07:00
Andrew Kryczka a4d9c02511 Pass CF ID to MemTableRepFactory
Summary:
Some users want to monitor column family activity in their custom memtable implementations. Previously there was no way to figure out with which column family a memtable is associated. This diff:

- adds an overload to MemTableRepFactory::CreateMemTableRep() that provides the CF ID. For compatibility, its default implementation calls the old overload.
- updates MemTable to create MemTableRep's using the new overload.
Closes https://github.com/facebook/rocksdb/pull/2346

Differential Revision: D5108061

Pulled By: ajkr

fbshipit-source-id: 3a1921214a348dd8ea0f54e1cab3b71c3d46d616
2017-06-02 12:12:06 -07:00
Yi Wu f68d88be51 Fix DBWriteTest::ReturnSequenceNumberMultiThreaded data race
Summary:
rocksdb::Random is not thread-safe. Have one Random for each thread instead.
Closes https://github.com/facebook/rocksdb/pull/2400

Differential Revision: D5173919

Pulled By: yiwu-arbug

fbshipit-source-id: 1a99c7b877f3893eb22355af49e321bcad4e53e6
2017-06-02 11:42:11 -07:00
Andrew Kryczka 215076ef06 Fix TSAN: avoid arena mode with range deletions
Summary:
The range deletion meta-block iterators weren't getting cleaned up properly since they don't support arena allocation. I didn't implement arena support since, in the general case, each iterator is used only once and separately from all other iterators, so there should be no benefit to data locality.

Anyways, this diff fixes up #2370 by treating range deletion iterators as non-arena-allocated.
Closes https://github.com/facebook/rocksdb/pull/2399

Differential Revision: D5171119

Pulled By: ajkr

fbshipit-source-id: bef6f5c4c5905a124f4993945aed4bd86e2807d8
2017-06-01 22:26:49 -07:00
Andrew Kryczka 3a8a848a55 account for L0 size in estimated compaction bytes
Summary:
also changed the `>` in the comparison against `level0_file_num_compaction_trigger` into a `>=` since exactly `level0_file_num_compaction_trigger` can trigger a compaction from L0.
Closes https://github.com/facebook/rocksdb/pull/2179

Differential Revision: D4915772

Pulled By: ajkr

fbshipit-source-id: e38fec6253de6f9a40e61734615c6670d84038aa
2017-06-01 17:56:59 -07:00
Andrew Gallagher 0fae3f5dd3 codemod: format TARGETS with buildifier [5/5] (D5092623)
Reviewed By: igorsugak

fbshipit-source-id: 906b744c179eb932f5a388b39f93209cecd50a80
2017-06-01 17:56:59 -07:00
Aaron Gao 8721996065 add checkpoint support for single db in regression test
Summary:
For level_compaction_style regression test.
Closes https://github.com/facebook/rocksdb/pull/2397

Differential Revision: D5168545

Pulled By: lightmark

fbshipit-source-id: 195e4d84917e7c261d9f4fbe9aee5d104c9cb9a2
2017-06-01 15:56:59 -07:00
Maysam Yabandeh 5a9b4d7435 Retire memenv https://github.com/facebook/rocksdb/pull/2082
Summary:
This is a manual commit of this PR:
Retire InMemoryEnv in favor of MockEnv #2082
With MockEnv doing the same yet being more mature, InMemoryEnv is redundant.

Reviewed By: IslamAbdelRahman

Differential Revision: D5162323

fbshipit-source-id: 59fd0082a891dc99cc531e4da9d68bf891eae3f5
2017-06-01 15:41:20 -07:00
Islam AbdelRahman d6019651b6 sync internal/external TARGETS 2017-06-01 12:31:13 -07:00
Volker Mische bbaba51bbf Add missing index type to C-API
Summary:
When the `TwoLevelIndexSearch` was introduced, it wasn't added to
the C-API.
Closes https://github.com/facebook/rocksdb/pull/2395

Differential Revision: D5165127

Pulled By: maysamyabandeh

fbshipit-source-id: d077f16ab5646c18158d8202a33b0fd076c6c8ad
2017-06-01 11:27:04 -07:00
Daniel Black 292edfd516 travis: test with xcode8.3 (OS X 10.12)
Summary:
Use later xcode version from https://docs.travis-ci.com/user/osx-ci-environment
Closes https://github.com/facebook/rocksdb/pull/2128

Differential Revision: D4907471

Pulled By: yiwu-arbug

fbshipit-source-id: debf8e27baef71a5833c845401b1865bc75ac977
2017-06-01 10:11:50 -07:00
Tamir Duberstein 0dc3040d54 db: avoid #includeing malloc and jemalloc simultaneously
Summary:
This fixes a compilation failure on Linux when the system libc is not
glibc. jemalloc's configure script incorrectly assumes that glibc is
always used on Linux systems, producing glibc-style signatures; when
the system libc is e.g. musl, the following error is observed:

```
  [  0%] Building CXX object CMakeFiles/rocksdb.dir/db/db_impl.cc.o
  In file included from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb.src/table/block.h:19:0,
                   from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb.src/db/db_impl.cc:77:
  /x-tools/x86_64-unknown-linux-musl/x86_64-unknown-linux-musl/sysroot/usr/include/malloc.h:19:8: error: declaration of 'size_t malloc_usable_size(void*)' has a different exception specifier
   size_t malloc_usable_size(void *);
          ^~~~~~~~~~~~~~~~~~
  In file included from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb.src/db/db_impl.cc:20:0:
  /go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:78:33: note: from previous declaration 'size_t malloc_usable_size(void*) throw ()'
   #  define je_malloc_usable_size malloc_usable_size
                                   ^
  /go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:239:41: note: in expansion of macro 'je_malloc_usable_size'
   JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_malloc_usable_size(
                                           ^~~~~~~~~~~~~~~~~~~~~
  CMakeFiles/rocksdb.dir/build.make:350: recipe for target 'CMakeFiles/rocksdb.dir/db/db_impl.cc.o' failed
```

This works around the issue by rearranging the sources such that
jemalloc's headers are never in the same scope as the system's malloc
header. The jemalloc issue has been reported as well, see:
https://github.com/jemalloc/jemalloc/issues/778.

cc tschottdorf
Closes https://github.com/facebook/rocksdb/pull/2188

Differential Revision: D5163048

Pulled By: siying

fbshipit-source-id: c553125458892def175c1be5682b0330d80b2a0d
2017-05-31 22:43:02 -07:00
Aaron Gao 9b3ed83506 fix regression test
Summary:
fix regression test by not reporting stats when building db
Closes https://github.com/facebook/rocksdb/pull/2390

Differential Revision: D5159909

Pulled By: lightmark

fbshipit-source-id: c3f4b9deb9c6799ff84207fd341c529144f8158d
2017-05-31 15:41:45 -07:00
Andrew Kryczka 9c9909bf7d Support ingest file when range deletions exist
Summary:
Previously we returned NotSupported when ingesting files into a database containing any range deletions. This diff adds the support.

- Flush if any memtable contains range deletions overlapping the to-be-ingested file
- Place to-be-ingested file before any level that contains range deletions overlapping it.
- Added support for `Version` to return iterators over range deletions in a given level. Previously, we piggybacked getting range deletions onto `Version`'s `Get()` / `AddIterator()` functions by passing them a `RangeDelAggregator*`. But file ingestion needs to get iterators over range deletions, not populate an aggregator (since the aggregator does collapsing and doesn't expose the actual ranges).
Closes https://github.com/facebook/rocksdb/pull/2370

Differential Revision: D5127648

Pulled By: ajkr

fbshipit-source-id: 816faeb9708adfa5287962bafdde717db56e3f1a
2017-05-31 13:57:19 -07:00
Yi Wu ad19eb8686 Fixing blob db sequence number handling
Summary:
Blob db rely on base db returning sequence number through write batch after DB::Write(). However after recent changes to the write path, DB::Writ()e no longer return sequence number in some cases. Fixing it by have WriteBatchInternal::InsertInto() always encode sequence number into write batch.

Stacking on #2375.
Closes https://github.com/facebook/rocksdb/pull/2385

Differential Revision: D5148358

Pulled By: yiwu-arbug

fbshipit-source-id: 8bda0aa07b9334ed03ed381548b39d167dc20c33
2017-05-31 10:56:45 -07:00
Siying Dong 51ac91f586 Histogram of number of merge operands
Summary:
Add a histogram in statistics to help users understand how many merge operands they merge.
Closes https://github.com/facebook/rocksdb/pull/2373

Differential Revision: D5139983

Pulled By: siying

fbshipit-source-id: 61b9ba8ca83f358530a4833d68f0103b56a0e182
2017-05-31 07:41:44 -07:00
Yi Wu 345878a7fb update blob_db_test
Summary:
Re-enable blob_db_test with some update:
* Commented out delay at the end of GC tests. Will update the logic later with sync point to properly trigger GC.
* Added some helper functions.

Also update make files to include blob_dump tool.
Closes https://github.com/facebook/rocksdb/pull/2375

Differential Revision: D5133793

Pulled By: yiwu-arbug

fbshipit-source-id: 95470b26d0c1f9592ba4b7637e027fdd263f425c
2017-05-30 22:26:13 -07:00
Aaron Gao cbc821c25b change regression rebuild to one level
Summary:
abandon fillseqdeterministic
test locally
Closes https://github.com/facebook/rocksdb/pull/2290

Differential Revision: D5151867

Pulled By: lightmark

fbshipit-source-id: 4c8a24cc937212ffb5ceb9bfaf7288eb8726d0c1
2017-05-30 16:41:21 -07:00
Tamir Duberstein 103d0692ea Avoid unsupported attributes when not building with UBSAN
Summary:
yiwu-arbug see individual commits.
Closes https://github.com/facebook/rocksdb/pull/2318

Differential Revision: D5141520

Pulled By: yiwu-arbug

fbshipit-source-id: 7987c92ab4461eef36afce5a133d3a0ee0c96300
2017-05-30 11:13:01 -07:00
Tamir Duberstein 5fd04566c4 travis: reduce the number of travis builders
Summary:
This collapses all the "platform dependent" tests into a single travis
builder in an effort to reduce overall CI times. These builds currently
take a combined 21-23 minutes, but each one has to compile the library,
so combining them should yield some time savings (5-10 minutes).

Unfortunately the other builders don't duplicate work, so combining
them is unlikely to provide benefit.
Closes https://github.com/facebook/rocksdb/pull/2306

Differential Revision: D5147850

Pulled By: yiwu-arbug

fbshipit-source-id: d947dc8b9f49639fe22f3c8ab9a82a8d730ddddf
2017-05-30 10:42:01 -07:00
Sagar Vemuri 2d05002b93 RocksDB 5.4.5 release blog post
Summary:
5.4.5 release blog post.
Tag created at: https://github.com/facebook/rocksdb/releases/tag/rocksdb-5.4.5
Closes https://github.com/facebook/rocksdb/pull/2378

Differential Revision: D5141648

Pulled By: sagar0

fbshipit-source-id: 43faadfbd7feb8bb01c3d56127ef3453e23dc28a
2017-05-26 23:11:56 -07:00
Sagar Vemuri 7eca90f187 Update RocksDB blog authors
Summary:
Adding my name to the authors list so that I can publish a post to rocksdb blog (rocksdb.org).
Closes https://github.com/facebook/rocksdb/pull/2379

Differential Revision: D5143582

Pulled By: sagar0

fbshipit-source-id: d85163f8b59aaeb07ac2a1cdd776ae335c7062b9
2017-05-26 20:12:41 -07:00
赵星宇 d03c34497c update comment of GetNextFile
Summary: Closes https://github.com/facebook/rocksdb/pull/2377

Differential Revision: D5141274

Pulled By: lightmark

fbshipit-source-id: c237a285b73ad93488c080ea80c71a29a17f1be0
2017-05-26 15:12:13 -07:00
Aaron Gao f7bb1a0060 support merge and delete in file ingestion
Summary:
Previously sst_file_writer only supports kTypeValue, we need kTypeMerge and kTypeDeletion also as user requested.
Closes https://github.com/facebook/rocksdb/pull/2361

Differential Revision: D5139402

Pulled By: lightmark

fbshipit-source-id: 092a60756d01692539d817a3765ebfd58a8d7f88
2017-05-26 12:11:21 -07:00
Siying Dong c2c62ad4e6 Reorder variables of ReadOptions
Summary:
Reorder variables of ReadOptions so that its size is reduced from 64 to 48 bytes.
Closes https://github.com/facebook/rocksdb/pull/2366

Differential Revision: D5124043

Pulled By: siying

fbshipit-source-id: 70e9c204c34f97fad011f2fe2297ba292d85df7a
2017-05-26 11:41:20 -07:00
Sagar Vemuri 7bb1f5d483 Increase of compaction threads should be logged at info level instead of a warning
Summary:
This log message shouldn't be a warning; some services are seeing high warning count due to this.

The count for the below line is a few hundreds of millions, as per Logview:
```
[rocksdb/src/db/column_family.cc:729] [checkpoints] Increasing compaction threads because we have 2 level-0 files
```
Closes https://github.com/facebook/rocksdb/pull/2364

Differential Revision: D5123565

Pulled By: sagar0

fbshipit-source-id: a07ce499a4f82f0ebde9cda9f4948fb9df6a734c
2017-05-26 09:56:13 -07:00
Sagar Vemuri 6c456ecae7 Clean zstd files
Summary:
zstd files are downloaded and used as part of JNI build, but are left behind even after doing a `make clean`. This PR updates the `clean` target to remove these zstd files as well.
Closes https://github.com/facebook/rocksdb/pull/2365

Differential Revision: D5123537

Pulled By: sagar0

fbshipit-source-id: a8f355da5ba961aa89d5852e35751ffc35de03ea
2017-05-26 09:56:13 -07:00
Andrew Gallagher 347e16f837 codemod: replace headers = AutoHeaders.* with auto_headers
Reviewed By: meyering

Differential Revision: D5094332

fbshipit-source-id: 3df2f693def8ca418bc9febe3e20ccf051f2e19d
2017-05-25 15:12:03 -07:00
Yi Wu 0be636bf70 Fix db_bench build break with blob db
Summary:
Lite build does not recognize FLAGS_use_blob_db. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/2372

Reviewed By: anirbanr-fb

Differential Revision: D5130773

Pulled By: yiwu-arbug

fbshipit-source-id: 43131d9d0be5811f2129af562be72cca26369cb3
2017-05-25 14:11:22 -07:00
Aaron Gao 135ee6a3fc fix tsan crash data race
Summary:
rand_ has data race risk
TEST_TMPDIR=\/dev\/shm\/rocksdb OPT=-g COMPILE_WITH_TSAN=1 CRASH_TEST_KILL_ODD=1887 make J=1 crash_test
Closes https://github.com/facebook/rocksdb/pull/2368

Differential Revision: D5127424

Pulled By: lightmark

fbshipit-source-id: b7f4d1430a5769b57da9f99037106749264b2ced
2017-05-25 10:44:07 -07:00
Andrew Kryczka a99fb9928f fix column_family_test asan
Summary:
stop calling Close() at the end of tests holding a compaction pressure token since it causes the write controller to be deleted while it's still needed. these calls were pointless anyways since Close() is already called in the test's destructor.
Closes https://github.com/facebook/rocksdb/pull/2367

Differential Revision: D5125906

Pulled By: ajkr

fbshipit-source-id: 6cad8673e5546a82ff602ac0ba59cc3f68dbde46
2017-05-24 16:41:51 -07:00
Daniel Black f41bffb3dd travis: clang-3.6 -> clang-4.0
Summary:
just realised when I updated the .travis.yml to trusty the llvm repo was still precise. Update this and clang-4.0.
Closes https://github.com/facebook/rocksdb/pull/2127

Differential Revision: D4869427

Pulled By: sagar0

fbshipit-source-id: b7f906b6fac28e60cacc6a1f1959d6acf8269906
2017-05-24 15:42:24 -07:00
Aaron Gao e7612798b5 update buckifer/TARGETS
Summary:
update targets file for release
Closes https://github.com/facebook/rocksdb/pull/2358

Differential Revision: D5115705

Pulled By: lightmark

fbshipit-source-id: 96a3c7e15b5807b5d0f5a9bb73850b92754b5794
2017-05-24 11:56:57 -07:00
Andrew Kryczka bb01c1880c Introduce max_background_jobs mutable option
Summary:
- `max_background_flushes` and `max_background_compactions` are still supported for backwards compatibility
- `base_background_compactions` is completely deprecated. Now we just throttle to one background compaction when there's no pressure.
- `max_background_jobs` is added to automatically partition the concurrent background jobs into flushes vs compactions. Currently it's very simple as we just allocate one-fourth of the jobs to flushes, and the remaining can be used for compactions.
- The test cases that set `base_background_compactions > 1` needed to be updated. I just grab the pressure token such that the desired number of compactions can be scheduled.
Closes https://github.com/facebook/rocksdb/pull/2205

Differential Revision: D4937461

Pulled By: ajkr

fbshipit-source-id: df52cbbd497e13bbc9a60560a5ac2a2526b3f1f9
2017-05-24 11:29:08 -07:00
Adam Retter 5a25304627 Fix the CMakeLists for RocksJava
Summary: Closes https://github.com/facebook/rocksdb/pull/2356

Differential Revision: D5122240

Pulled By: sagar0

fbshipit-source-id: 3764797dd261d5b2a04d58b3967969e66c541bbb
2017-05-24 11:29:08 -07:00
Siying Dong 41cbb72749 options.delayed_write_rate use the rate of rate_limiter by default.
Summary:
It's hard for RocksDB to come up with a good default of delayed write rate. Use rate given by rate limiter if it is availalbe. This provides the I/O order of magnitude.
Closes https://github.com/facebook/rocksdb/pull/2357

Differential Revision: D5115324

Pulled By: siying

fbshipit-source-id: 341065ad2211c981fc804011c0f0e59a50c7e754
2017-05-24 09:58:24 -07:00
Siying Dong 5068034666 range sync should be enabled
Summary:
We forgot to add the new flag in internal build script. Add it.
Closes https://github.com/facebook/rocksdb/pull/2360

Differential Revision: D5121428

Pulled By: siying

fbshipit-source-id: af72d48cd855b37df1ce3c1fbb00c80377ba6e4f
2017-05-24 09:58:24 -07:00
Sagar Vemuri 02594b5f11 Fix build errors in blob_dump_tool with GCC 4.8
Summary:
Fixing the build errors seen with GCC 4.8.1.
```
Makefile:105: Warning: Compiling in debug mode. Don't use the resulting binary in production
utilities/blob_db/blob_dump_tool.cc: In member function ‘rocksdb::Status rocksdb::blob_db::BlobDumpTool::DumpBlobLogFooter(uint64_t, uint64_t*)’:
utilities/blob_db/blob_dump_tool.cc:149:42: error: expected ‘)’ before ‘PRIu64’
   fprintf(stdout, "  Blob count     : %" PRIu64 "\n", footer.GetBlobCount());
                                          ^
utilities/blob_db/blob_dump_tool.cc:149:76: error: spurious trailing ‘%’ in format [-Werror=format=]
   fprintf(stdout, "  Blob count     : %" PRIu64 "\n", footer.GetBlobCount());
                                                                            ^
utilities/blob_db/blob_dump_tool.cc:149:76: error: too many arguments for format [-Werror=format-extra-args]
utilities/blob_db/blob_dump_tool.cc: In member function ‘rocksdb::Status rocksdb::blob_db::BlobDumpTool::DumpRecord(rocksdb::blob_db::BlobDumpTool::DisplayType, rocksdb::blob_db::BlobDumpTool::DisplayType, uint64_t*)’:
utilities/blob_db/blob_dump_tool.cc:161:49: error: expected ‘)’ before ‘PRIx64’
   fprintf(stdout, "Read record with offset 0x%" PRIx64 " (%" PRIu64 "):\n",
                                                 ^
utilities/blob_db/blob_dump_tool.cc:162:27: error: spurious trailing ‘%’ in format [-Werror=format=]
           *offset, *offset);
                           ^
utilities/blob_db/blob_dump_tool.cc:162:27: error: too many arguments for format [-Werror=format-extra-args]
utilities/blob_db/blob_dump_tool.cc:176:38: error: expected ‘)’ before ‘PRIu64’
   fprintf(stdout, "  blob size  : %" PRIu64 "\n", record.GetBlobSize());
                                      ^
utilities/blob_db/blob_dump_tool.cc:176:71: error: spurious trailing ‘%’ in format [-Werror=format=]
   fprintf(stdout, "  blob size  : %" PRIu64 "\n", record.GetBlobSize());
                                                                       ^
utilities/blob_db/blob_dump_tool.cc:176:71: error: too many arguments for format [-Werror=format-extra-args]
utilities/blob_db/blob_dump_tool.cc:178:38: error: expected ‘)’ before ‘PRIu64’
   fprintf(stdout, "  time       : %" PRIu64 "\n", record.GetTimeVal());
                                      ^
utilities/blob_db/blob_dump_tool.cc:178:70: error: spurious trailing ‘%’ in format [-Werror=format=]
   fprintf(stdout, "  time       : %" PRIu64 "\n", record.GetTimeVal());
                                                                      ^
utilities/blob_db/blob_dump_tool.cc:178:70: error: too many arguments for format [-Werror=format-extra-args]
utilities/blob_db/blob_dump_tool.cc:214:38: error: expected ‘)’ before ‘PRIu64’
   fprintf(stdout, "  sequence   : %" PRIu64 "\n", record.GetSN());
                                      ^
utilities/blob_db/blob_dump_tool.cc:214:65: error: spurious trailing ‘%’ in format [-Werror=format=]
   fprintf(stdout, "  sequence   : %" PRIu64 "\n", record.GetSN());
```
Closes https://github.com/facebook/rocksdb/pull/2359

Differential Revision: D5117684

Pulled By: sagar0

fbshipit-source-id: 7480346bcd96205fcae890927c5e68cf004e87be
2017-05-24 00:11:36 -07:00
Igor Canadi 52d9e5f7b6 Fix column family seconds_up accounting
Summary:
`cf_stats_snapshot_.seconds_up` appears to be never updated, unlike `db_stats_snapshot_.seconds_up`, which is updated here: https://github.com/facebook/rocksdb/blob/master/db/internal_stats.cc#L883

This leads to wrong information in the log, for example:
```
** Compaction Stats [default] **

....

Uptime(secs): 85591.2 total, 85591.2 interval
```

Even though DB's interval is correctly logged as 60 seconds:
```
** DB Stats **
Uptime(secs): 85591.2 total, 637.8 interval
```
Closes https://github.com/facebook/rocksdb/pull/2338

Differential Revision: D5114131

Pulled By: sagar0

fbshipit-source-id: 85243a38213236ccbb601a7f7aaa8865eaa8083c
2017-05-23 17:14:04 -07:00
Sagar Vemuri 7d8207f1f2 Fix errors in clang-analyzer builds
Summary:
Fix build error in db_iter.cc when running clang-analyzer.
```
  CC       db/db_iter.o
db/db_iter.cc:938:21: error: no matching constructor for initialization of 'rocksdb::ParsedInternalKey'
  ParsedInternalKey ikey(Slice(), 0, 0);
                    ^    ~~~~~~~~~~~~~
./db/dbformat.h:84:3: note: candidate constructor not viable: no known conversion from 'int' to 'rocksdb::ValueType' for 3rd argument
  ParsedInternalKey(const Slice& u, const SequenceNumber& seq, ValueType t)
  ^
./db/dbformat.h:78:8: note: candidate constructor (the implicit copy constructor) not viable: requires 1 argument, but 3 were provided
struct ParsedInternalKey {
       ^
./db/dbformat.h:78:8: note: candidate constructor (the implicit move constructor) not viable: requires 1 argument, but 3 were provided
./db/dbformat.h:83:3: note: candidate constructor not viable: requires 0 arguments, but 3 were provided
  ParsedInternalKey() { }  // Intentionally left uninitialized (for speed)
  ^
1 error generated.
```
Closes https://github.com/facebook/rocksdb/pull/2354

Differential Revision: D5115751

Pulled By: sagar0

fbshipit-source-id: b0e386d4e935e4725b07761c3ca5f7a8cbde3692
2017-05-23 15:11:42 -07:00
Sagar Vemuri 85b8569ae8 Fix release build on Linux
Summary:
Release builds are failing on Linux with the error:
```
tools/db_stress.cc: In function ‘int main(int, char**)’:
tools/db_stress.cc:2365:12: error: ‘rocksdb::SyncPoint’ has not been declared
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
            ^
tools/db_stress.cc:2370:12: error: ‘rocksdb::SyncPoint’ has not been declared
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
            ^
tools/db_stress.cc:2375:12: error: ‘rocksdb::SyncPoint’ has not been declared
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
            ^
make[1]: *** [tools/db_stress.o] Error 1
make[1]: Leaving directory `/data/sandcastle/boxes/trunk-git-rocksdb-public'
make: *** [release] Error 2
```
Closes https://github.com/facebook/rocksdb/pull/2355

Differential Revision: D5113552

Pulled By: sagar0

fbshipit-source-id: 351df707277787da5633ba4a40e52edc7c895dc4
2017-05-23 14:57:05 -07:00
Giuseppe Ottaviano 69ec8356b2 Allow SstFileWriter to use the rate limiter
Summary:
The default IO priority of WritableFiles is IO_TOTAL, meaning that
they will bypass the rate limiter if it's passed in the options.

This change allows to pass an io priority in construction, so that by
setting IO_LOW or IO_HIGH the rate limit will be honored.

It also fixes a minor bug: SstFileWriter's copy and move constructor
are not disabled and incorrect, as any copy/move will result in a
double free. Switching to unique_ptr makes the object correctly
movable and non-copyable as expected.

Also fix minor style inconsistencies.
Closes https://github.com/facebook/rocksdb/pull/2335

Differential Revision: D5113260

Pulled By: sagar0

fbshipit-source-id: e084236e7ff0b50a56cbeceaa9fedd5e210bf9f8
2017-05-23 11:42:09 -07:00
Andrew Kryczka 6cc9aef162 New API for background work in single thread pool
Summary:
Previously users could set `max_background_flushes=0` to force rocksdb to use a single thread pool for both background flushes and compactions. That'll no longer be possible since I'm going to deprecate `max_background_flushes` and `max_background_compactions` in favor of a single option. This diff introduces a new way to force a single thread pool: when high-pri pool has zero threads, all background jobs will be submitted to low-pri pool.

Note the majority of the code change is adding `Env::GetBackgroundThreads()`, which is necessary to check whether the user has provided a zero-sized thread pool.
Closes https://github.com/facebook/rocksdb/pull/2204

Differential Revision: D4936256

Pulled By: ajkr

fbshipit-source-id: 929a07a0c0705f7766f5339cd013ff74e90d6e01
2017-05-23 11:12:27 -07:00
Yi Wu 9d0a07ed52 Fix rocksdb.estimate-num-keys DB property underflow
Summary:
rocksdb.estimate-num-keys is compute from `estimate_num_keys - 2 * estimate_num_deletes`. If  `2 * estimate_num_deletes > estimate_num_keys` it will underflow. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/2348

Differential Revision: D5109272

Pulled By: yiwu-arbug

fbshipit-source-id: e1bfb91346a59b7282a282b615002507e9d7c246
2017-05-23 10:42:59 -07:00
Yi Wu 578fb0b1dc Simple blob file dumper
Summary:
A simple blob file dumper.
Closes https://github.com/facebook/rocksdb/pull/2242

Differential Revision: D5097553

Pulled By: yiwu-arbug

fbshipit-source-id: c6e00d949fcd3658f9f68da9352f06339fac418d
2017-05-23 10:42:59 -07:00
Andrew Kryczka ac39d6bec5 Core-local statistics
Summary:
This diff changes `StatisticsImpl` from a thread-local approach to a core-local one. The goal is to perform faster aggregations, particularly for applications that have many threads. There should be no behavior change.
Closes https://github.com/facebook/rocksdb/pull/2258

Differential Revision: D5016258

Pulled By: ajkr

fbshipit-source-id: 7d4d165b4a91d8110f0409d113d1be91f22d31a9
2017-05-23 10:42:59 -07:00
1043 changed files with 51723 additions and 23453 deletions
-17
View File
@@ -1,17 +0,0 @@
{
"project_id" : "rocksdb",
"conduit_uri" : "https://phabricator.fb.com/api/",
"copyright_holder" : "Facebook",
"load" : [
"arcanist_util"
],
"lint.engine" : "FacebookFbcodeLintEngine",
"lint.engine.single.linter" : "FbcodeCppLinter",
"unit.engine" : "FacebookFbcodeUnitTestEngine",
"arcanist_configuration" : "FacebookArcanistConfiguration",
"base" : "git:HEAD^, hg:.^",
"git.default-relative-commit" : "HEAD^",
"git:arc.feature.start.default" : "origin/master",
"arc.feature.start.default" : "master",
"history.immutable" : false
}
+1 -1
View File
@@ -31,6 +31,7 @@ build/
ldb
manifest_dump
sst_dump
blob_dump
column_aware_encoding_exp
util/build_version.cc
build_tools/VALGRIND_LOGS/
@@ -38,7 +39,6 @@ coverage/COVERAGE_REPORT
.gdbhistory
.gdb_history
package/
.phutil_module_cache
unity.a
tags
etags
+39 -31
View File
@@ -7,6 +7,7 @@ os:
compiler:
- clang
- gcc
osx_image: xcode8.3
jdk:
- oraclejdk7
cache:
@@ -15,56 +16,63 @@ cache:
addons:
apt:
sources: ['ubuntu-toolchain-r-test', 'llvm-toolchain-precise-3.6']
packages: ['clang-3.6' , 'g++-6', 'zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev', 'mingw-w64']
packages: ['zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev', 'mingw-w64']
env:
- TEST_GROUP=platform_dependent1
- TEST_GROUP=platform_dependent2
- TEST_GROUP=platform_dependent3
- TEST_GROUP=1
- TEST_GROUP=2
- TEST_GROUP=platform_dependent # 16-18 minutes
- TEST_GROUP=1 # 33-35 minutes
- TEST_GROUP=2 # 30-32 minutes
- TEST_GROUP=3 # ? minutes - under development
# Run java tests
- JOB_NAME=java_test
- JOB_NAME=java_test # 4-11 minutes
# Build ROCKSDB_LITE
- JOB_NAME=lite_build
- JOB_NAME=lite_build # 3-4 minutes
# Build examples
- JOB_NAME=examples
- JOB_NAME=cmake
- JOB_NAME=cmake-mingw
- JOB_NAME=examples # 5-7 minutes
- JOB_NAME=cmake # 3-5 minutes
- JOB_NAME=cmake-mingw # 3 minutes
matrix:
exclude:
- os: osx
compiler: gcc
- os: osx
env: TEST_GROUP=1
- os: osx
env: TEST_GROUP=2
- os: osx
env: TEST_GROUP=3
- os : osx
env: JOB_NAME=cmake-mingw
- os: linux
env: JOB_NAME=cmake-mingw
- os : linux
compiler: clang
- os : osx
compiler: gcc
# https://docs.travis-ci.com/user/caching/#ccache-cache
install:
- if [ "${TRAVIS_OS_NAME}" == osx ]; then
brew install ccache;
PATH=$PATH:/usr/local/opt/ccache/libexec;
fi
- if [[ "${JOB_NAME}" == cmake* ]] && [ "${TRAVIS_OS_NAME}" == linux ]; then
mkdir cmake-dist && curl -sfSL https://cmake.org/files/v3.8/cmake-3.8.1-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
fi
before_script:
- if [[ "${TRAVIS_OS_NAME}" == 'linux' && "${CXX}" == 'clang++' ]]; then CXX=clang++-3.6; fi
# test one linux g++ build with g++-6
- if [[ "${TRAVIS_OS_NAME}" == 'linux' && "${CXX}" == 'g++' && "${JOB_NAME}" == 'unittests' ]]; then CXX=g++-6; fi
# Limit the maximum number of open file descriptors to 8192
- ulimit -n 8192 || true
# Increase the maximum number of open file descriptors, since some tests use
# more FDs than the default limit.
- ulimit -n 8192
script:
- ${CXX} --version
- if [[ "${TEST_GROUP}" == 'platform_dependent1' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=external_sst_file_basic_test make -j4 check_some; fi
- if [[ "${TEST_GROUP}" == 'platform_dependent2' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=external_sst_file_basic_test ROCKSDBTESTS_END=checkpoint_test make -j4 check_some; fi
- if [[ "${TEST_GROUP}" == 'platform_dependent3' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=checkpoint_test ROCKSDBTESTS_END=db_block_cache_test make -j4 check_some; fi
- if [[ "${TEST_GROUP}" == '1' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=comparator_db_test make -j4 check_some; fi
- if [[ "${TEST_GROUP}" == '2' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=comparator_db_test make -j4 check_some; fi
- if [[ "${JOB_NAME}" == 'java_test' ]]; then OPT=-DTRAVIS V=1 make clean jclean && make rocksdbjava jtest; fi
- if [[ "${JOB_NAME}" == 'lite_build' ]]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib; fi
- if [[ "${JOB_NAME}" == 'examples' ]]; then OPT=-DTRAVIS V=1 make -j4 static_lib; cd examples; make -j4; fi
- if [[ "${JOB_NAME}" == 'cmake' ]]; then mkdir build && cd build && cmake .. && make -j4 rocksdb; fi
- if [[ "${JOB_NAME}" == 'cmake-mingw' ]]; then mkdir build && cd build && cmake .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb; fi
- if [ `command -v ccache` ]; then ccache -C; fi
- if [ "${TEST_GROUP}" == 'platform_dependent' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=db_block_cache_test make -j4 all_but_some_tests check_some; fi
- if [ "${TEST_GROUP}" == '1' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=comparator_db_test make -j4 check_some; fi
- if [ "${TEST_GROUP}" == '2' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=comparator_db_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some; fi
- if [ "${TEST_GROUP}" == '3' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_prepared_transaction_test make -j4 check_some; fi
- if [ "${JOB_NAME}" == 'java_test' ]; then OPT=-DTRAVIS V=1 make clean jclean && make rocksdbjava jtest; fi
- if [ "${JOB_NAME}" == 'lite_build' ]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib tools; fi
- if [ "${JOB_NAME}" == 'examples' ]; then OPT=-DTRAVIS V=1 make -j4 static_lib; cd examples; make -j4; fi
- if [ "${JOB_NAME}" == 'cmake' ]; then mkdir build && cd build && cmake -DJNI=1 .. && make -j4 rocksdb rocksdbjni; fi
- if [ "${JOB_NAME}" == 'cmake-mingw' ]; then mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni; fi
notifications:
email:
- leveldb@fb.com
+1
View File
@@ -9,3 +9,4 @@ Sanjay Ghemawat <sanjay@google.com>
# Partial list of contributors:
Kevin Regan <kevin.d.regan@gmail.com>
Johan Bilien <jobi@litl.com>
Matthew Von-Maszewski <https://github.com/matthewvon> (Basho Technologies)
+358 -156
View File
@@ -14,7 +14,7 @@
# cd build
# 3. Run cmake to generate project files for Windows, add more options to enable required third-party libraries.
# See thirdparty.inc for more information.
# sample command: cmake -G "Visual Studio 14 Win64" -DGFLAGS=1 -DSNAPPY=1 -DJEMALLOC=1 -DJNI=1 ..
# sample command: cmake -G "Visual Studio 15 Win64" -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
# 4. Then build the project in debug mode (you may want to add /m[:<N>] flag to run msbuild in <N> parallel threads
# or simply /m ot use all avail cores)
# msbuild rocksdb.sln
@@ -32,19 +32,29 @@
# 3. cmake ..
# 4. make -j
cmake_minimum_required(VERSION 2.6)
cmake_minimum_required(VERSION 2.8.12)
project(rocksdb)
enable_language(CXX)
enable_language(C)
enable_language(ASM)
if(POLICY CMP0042)
cmake_policy(SET CMP0042 NEW)
endif()
list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake/modules/")
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
option(WITH_JEMALLOC "build with JeMalloc" OFF)
option(WITH_SNAPPY "build with SNAPPY" OFF)
option(WITH_LZ4 "build with lz4" OFF)
option(WITH_ZLIB "build with zlib" OFF)
if(MSVC)
# Defaults currently different for GFLAGS.
# We will address find_package work a little later
option(WITH_GFLAGS "build with GFlags" OFF)
option(WITH_XPRESS "build with windows built in compression" OFF)
include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
else()
option(WITH_JEMALLOC "build with JeMalloc" OFF)
if(CMAKE_SYSTEM_NAME MATCHES "FreeBSD")
# FreeBSD has jemaloc as default malloc
# but it does not have all the jemalloc files in include/...
@@ -56,26 +66,57 @@ else()
include_directories(${JEMALLOC_INCLUDE_DIR})
endif()
endif()
option(WITH_SNAPPY "build with SNAPPY" OFF)
# No config file for this
option(WITH_GFLAGS "build with GFlags" ON)
if(WITH_GFLAGS)
find_package(gflags)
if(gflags_FOUND)
add_definitions(-DGFLAGS=1)
include_directories(${gflags_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${gflags_LIBRARIES})
endif()
endif()
if(WITH_SNAPPY)
find_package(snappy REQUIRED)
add_definitions(-DSNAPPY)
include_directories(${SNAPPY_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${SNAPPY_LIBRARIES})
endif()
if(WITH_ZLIB)
find_package(zlib REQUIRED)
add_definitions(-DZLIB)
include_directories(${ZLIB_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${ZLIB_LIBRARIES})
endif()
option(WITH_BZ2 "build with bzip2" OFF)
if(WITH_BZ2)
find_package(bzip2 REQUIRED)
add_definitions(-DBZIP2)
include_directories(${BZIP2_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${BZIP2_LIBRARIES})
endif()
if(WITH_LZ4)
find_package(lz4 REQUIRED)
add_definitions(-DLZ4)
include_directories(${LZ4_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${LZ4_LIBRARIES})
endif()
option(WITH_ZSTD "build with zstd" OFF)
if(WITH_ZSTD)
find_package(zstd REQUIRED)
add_definitions(-DZSTD)
include_directories(${ZSTD_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${ZSTD_LIBRARIES})
endif()
endif()
if(WIN32)
execute_process(COMMAND powershell -noprofile -Command "Get-Date -format MM_dd_yyyy" OUTPUT_VARIABLE DATE)
execute_process(COMMAND powershell -noprofile -Command "Get-Date -format HH:mm:ss" OUTPUT_VARIABLE TIME)
string(REGEX REPLACE "(..)_(..)_..(..).*" "\\1/\\2/\\3" DATE "${DATE}")
string(REGEX REPLACE "(..):(.....).*" " \\1:\\2" TIME "${TIME}")
set(GIT_DATE_TIME "${DATE} ${TIME}")
else()
execute_process(COMMAND date "+%Y/%m/%d %H:%M:%S" OUTPUT_VARIABLE DATETIME)
string(REGEX REPLACE "\n" "" DATETIME ${DATETIME})
set(GIT_DATE_TIME "${DATETIME}")
endif()
string(TIMESTAMP GIT_DATE_TIME "%Y/%m/%d %H:%M:%S" UTC)
find_package(Git)
@@ -91,20 +132,19 @@ endif()
string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA "${GIT_SHA}")
if(NOT WIN32)
execute_process(COMMAND
"./build_tools/version.sh" "full"
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
OUTPUT_VARIABLE ROCKSDB_VERSION
)
string(STRIP "${ROCKSDB_VERSION}" ROCKSDB_VERSION)
execute_process(COMMAND
"./build_tools/version.sh" "major"
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
OUTPUT_VARIABLE ROCKSDB_VERSION_MAJOR
)
string(STRIP "${ROCKSDB_VERSION_MAJOR}" ROCKSDB_VERSION_MAJOR)
endif()
set(SH_CMD "sh")
execute_process(COMMAND
${SH_CMD} -c "build_tools/version.sh full"
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
OUTPUT_VARIABLE ROCKSDB_VERSION
)
string(STRIP "${ROCKSDB_VERSION}" ROCKSDB_VERSION)
execute_process(COMMAND
${SH_CMD} -c "build_tools/version.sh major"
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
OUTPUT_VARIABLE ROCKSDB_VERSION_MAJOR
)
string(STRIP "${ROCKSDB_VERSION_MAJOR}" ROCKSDB_VERSION_MAJOR)
option(WITH_MD_LIBRARY "build with MD" ON)
if(WIN32 AND MSVC)
@@ -115,31 +155,78 @@ if(WIN32 AND MSVC)
endif()
endif()
set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
add_library(build_version OBJECT ${BUILD_VERSION_CC})
target_include_directories(build_version PRIVATE
${CMAKE_CURRENT_SOURCE_DIR}/util)
if(MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4800 /wd4996 /wd4351 /wd4100 /wd4204 /wd4324")
else()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
if(MINGW)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O2 -fno-omit-frame-pointer")
include(CheckCXXCompilerFlag)
CHECK_CXX_COMPILER_FLAG("-momit-leaf-frame-pointer" HAVE_OMIT_LEAF_FRAME_POINTER)
if(HAVE_OMIT_LEAF_FRAME_POINTER)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -momit-leaf-frame-pointer")
endif()
endif()
endif()
include(CheckCCompilerFlag)
if(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
CHECK_C_COMPILER_FLAG("-maltivec" HAS_ALTIVEC)
if(HAS_ALTIVEC)
message(STATUS " HAS_ALTIVEC yes")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maltivec")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maltivec")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power8")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power8")
endif(HAS_ALTIVEC)
endif(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
option(PORTABLE "build a portable binary" OFF)
option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
if(PORTABLE)
# MSVC does not need a separate compiler flag to enable SSE4.2; if nmmintrin.h
# is available, it is available by default.
if(FORCE_SSE42 AND NOT MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.2")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.2 -mpclmul")
endif()
else()
if(MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
else()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
if(NOT HAVE_POWER8)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
endif()
endif()
endif()
set(CMAKE_REQUIRED_FLAGS ${CMAKE_CXX_FLAGS})
include(CheckCXXSourceCompiles)
if(NOT MSVC)
set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
endif()
CHECK_CXX_SOURCE_COMPILES("
#include <cstdint>
#include <nmmintrin.h>
#include <wmmintrin.h>
int main() {
volatile uint32_t x = _mm_crc32_u32(0, 0);
const auto a = _mm_set_epi64x(0, 0);
const auto b = _mm_set_epi64x(0, 0);
const auto c = _mm_clmulepi64_si128(a, b, 0x00);
auto d = _mm_cvtsi128_si64(c);
}
" HAVE_SSE42)
unset(CMAKE_REQUIRED_FLAGS)
if(HAVE_SSE42)
add_definitions(-DHAVE_SSE42)
elseif(FORCE_SSE42)
@@ -158,32 +245,6 @@ if(HAVE_THREAD_LOCAL)
add_definitions(-DROCKSDB_SUPPORT_THREAD_LOCAL)
endif()
set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
add_library(build_version OBJECT ${BUILD_VERSION_CC})
target_include_directories(build_version PRIVATE
${CMAKE_CURRENT_SOURCE_DIR}/util)
if(MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W3 /wd4127 /wd4800 /wd4996 /wd4351")
else()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers")
if(MINGW)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
add_definitions(-DNDEBUG)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O2 -fno-omit-frame-pointer")
include(CheckCXXCompilerFlag)
CHECK_CXX_COMPILER_FLAG("-momit-leaf-frame-pointer" HAVE_OMIT_LEAF_FRAME_POINTER)
if(HAVE_OMIT_LEAF_FRAME_POINTER)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -momit-leaf-frame-pointer")
endif()
endif()
endif()
option(FAIL_ON_WARNINGS "Treat compile warnings as errors" ON)
if(FAIL_ON_WARNINGS)
if(MSVC)
@@ -195,7 +256,6 @@ endif()
option(WITH_ASAN "build with ASAN" OFF)
if(WITH_ASAN)
add_definitions(-DROCKSDB_TSAN_RUN)
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=address")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=address")
@@ -207,7 +267,6 @@ endif()
option(WITH_TSAN "build with TSAN" OFF)
if(WITH_TSAN)
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread -pie")
add_definitions(-DROCKSDB_TSAN_RUN)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=thread -fPIC")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=thread -fPIC")
if(WITH_JEMALLOC)
@@ -217,6 +276,7 @@ endif()
option(WITH_UBSAN "build with UBSAN" OFF)
if(WITH_UBSAN)
add_definitions(-DROCKSDB_UBSAN_RUN)
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=undefined")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=undefined")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=undefined")
@@ -225,6 +285,20 @@ if(WITH_UBSAN)
endif()
endif()
find_package(NUMA)
if(NUMA_FOUND)
add_definitions(-DNUMA)
include_directories(${NUMA_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${NUMA_LIBRARIES})
endif()
find_package(TBB)
if(TBB_FOUND)
add_definitions(-DTBB)
include_directories(${TBB_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${TBB_LIBRARIES})
endif()
# Used to run CI build and tests so we can run faster
set(OPTIMIZE_DEBUG_DEFAULT 0) # Debug build is unoptimized by default use -DOPTDBG=1 to optimize
@@ -292,10 +366,8 @@ if(NOT WIN32)
endif()
option(WITH_FALLOCATE "build with fallocate" ON)
if(WITH_FALLOCATE)
include(CheckCSourceCompiles)
CHECK_C_SOURCE_COMPILES("
CHECK_CXX_SOURCE_COMPILES("
#include <fcntl.h>
#include <linux/falloc.h>
int main() {
@@ -308,12 +380,38 @@ int main() {
endif()
endif()
include(CheckFunctionExists)
CHECK_FUNCTION_EXISTS(malloc_usable_size HAVE_MALLOC_USABLE_SIZE)
CHECK_CXX_SOURCE_COMPILES("
#include <fcntl.h>
int main() {
int fd = open(\"/dev/null\", 0);
sync_file_range(fd, 0, 1024, SYNC_FILE_RANGE_WRITE);
}
" HAVE_SYNC_FILE_RANGE_WRITE)
if(HAVE_SYNC_FILE_RANGE_WRITE)
add_definitions(-DROCKSDB_RANGESYNC_PRESENT)
endif()
CHECK_CXX_SOURCE_COMPILES("
#include <pthread.h>
int main() {
(void) PTHREAD_MUTEX_ADAPTIVE_NP;
}
" HAVE_PTHREAD_MUTEX_ADAPTIVE_NP)
if(HAVE_PTHREAD_MUTEX_ADAPTIVE_NP)
add_definitions(-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX)
endif()
include(CheckCXXSymbolExists)
check_cxx_symbol_exists(malloc_usable_size malloc.h HAVE_MALLOC_USABLE_SIZE)
if(HAVE_MALLOC_USABLE_SIZE)
add_definitions(-DROCKSDB_MALLOC_USABLE_SIZE)
endif()
check_cxx_symbol_exists(sched_getcpu sched.h HAVE_SCHED_GETCPU)
if(HAVE_SCHED_GETCPU)
add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
endif()
include_directories(${PROJECT_SOURCE_DIR})
include_directories(${PROJECT_SOURCE_DIR}/include)
include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
@@ -359,6 +457,7 @@ set(SOURCES
db/internal_stats.cc
db/log_reader.cc
db/log_writer.cc
db/malloc_stats.cc
db/managed_iterator.cc
db/memtable.cc
db/memtable_list.cc
@@ -380,14 +479,16 @@ set(SOURCES
db/write_thread.cc
env/env.cc
env/env_chroot.cc
env/env_encryption.cc
env/env_hdfs.cc
env/memenv.cc
env/mock_env.cc
memtable/alloc_tracker.cc
memtable/hash_cuckoo_rep.cc
memtable/hash_linklist_rep.cc
memtable/hash_skiplist_rep.cc
memtable/memtable_allocator.cc
memtable/skiplistrep.cc
memtable/vectorrep.cc
memtable/write_buffer_manager.cc
monitoring/histogram.cc
monitoring/histogram_windowing.cc
monitoring/instrumented_mutex.cc
@@ -413,6 +514,7 @@ set(SOURCES
table/block_based_table_factory.cc
table/block_based_table_reader.cc
table/block_builder.cc
table/block_fetcher.cc
table/block_prefix_index.cc
table/bloom_block.cc
table/cuckoo_table_builder.cc
@@ -475,11 +577,15 @@ set(SOURCES
utilities/backupable/backupable_db.cc
utilities/blob_db/blob_db.cc
utilities/blob_db/blob_db_impl.cc
utilities/blob_db/blob_db_options_impl.cc
utilities/blob_db/blob_dump_tool.cc
utilities/blob_db/blob_file.cc
utilities/blob_db/blob_log_reader.cc
utilities/blob_db/blob_log_writer.cc
utilities/blob_db/blob_log_format.cc
utilities/blob_db/ttl_extractor.cc
utilities/cassandra/cassandra_compaction_filter.cc
utilities/cassandra/format.cc
utilities/cassandra/merge_operator.cc
utilities/checkpoint/checkpoint_impl.cc
utilities/col_buf_decoder.cc
utilities/col_buf_encoder.cc
@@ -513,18 +619,35 @@ set(SOURCES
utilities/spatialdb/spatial_db.cc
utilities/table_properties_collectors/compact_on_deletion_collector.cc
utilities/transactions/optimistic_transaction_db_impl.cc
utilities/transactions/optimistic_transaction_impl.cc
utilities/transactions/optimistic_transaction.cc
utilities/transactions/pessimistic_transaction.cc
utilities/transactions/pessimistic_transaction_db.cc
utilities/transactions/snapshot_checker.cc
utilities/transactions/transaction_base.cc
utilities/transactions/transaction_db_impl.cc
utilities/transactions/transaction_db_mutex_impl.cc
utilities/transactions/transaction_impl.cc
utilities/transactions/transaction_lock_mgr.cc
utilities/transactions/transaction_util.cc
utilities/transactions/write_prepared_txn.cc
utilities/transactions/write_prepared_txn_db.cc
utilities/ttl/db_ttl_impl.cc
utilities/write_batch_with_index/write_batch_with_index.cc
utilities/write_batch_with_index/write_batch_with_index_internal.cc
$<TARGET_OBJECTS:build_version>)
if(HAVE_SSE42 AND NOT FORCE_SSE42)
if(NOT MSVC)
set_source_files_properties(
util/crc32c.cc
PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
endif()
endif()
if(HAVE_POWER8)
list(APPEND SOURCES
util/crc32c_ppc.c
util/crc32c_ppc_asm.S)
endif(HAVE_POWER8)
if(WIN32)
list(APPEND SOURCES
port/win/io_win.cc
@@ -534,6 +657,12 @@ if(WIN32)
port/win/win_logger.cc
port/win/win_thread.cc
port/win/xpress_win.cc)
if(WITH_JEMALLOC)
list(APPEND SOURCES
port/win/win_jemalloc.cc)
endif()
else()
list(APPEND SOURCES
port/port_posix.cc
@@ -595,7 +724,72 @@ else()
message(STATUS "JNI library is disabled")
endif()
set(TESTS
# Installation and packaging
if(WIN32)
option(ROCKSDB_INSTALL_ON_WINDOWS "Enable install target on Windows" OFF)
endif()
if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
if(CMAKE_INSTALL_PREFIX_INITIALIZED_TO_DEFAULT)
if(${CMAKE_SYSTEM_NAME} STREQUAL "Linux")
# Change default installation prefix on Linux to /usr
set(CMAKE_INSTALL_PREFIX /usr CACHE PATH "Install path prefix, prepended onto install directories." FORCE)
endif()
endif()
include(GNUInstallDirs)
include(CMakePackageConfigHelpers)
set(package_config_destination ${CMAKE_INSTALL_LIBDIR}/cmake/rocksdb)
configure_package_config_file(
${CMAKE_CURRENT_LIST_DIR}/cmake/RocksDBConfig.cmake.in RocksDBConfig.cmake
INSTALL_DESTINATION ${package_config_destination}
)
write_basic_package_version_file(
RocksDBConfigVersion.cmake
VERSION ${ROCKSDB_VERSION}
COMPATIBILITY SameMajorVersion
)
install(DIRECTORY include/rocksdb COMPONENT devel DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}")
install(
TARGETS ${ROCKSDB_STATIC_LIB}
EXPORT RocksDBTargets
COMPONENT devel
ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
)
install(
TARGETS ${ROCKSDB_SHARED_LIB}
EXPORT RocksDBTargets
COMPONENT runtime
RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
)
install(
EXPORT RocksDBTargets
COMPONENT devel
DESTINATION ${package_config_destination}
NAMESPACE RocksDB::
)
install(
FILES
${CMAKE_CURRENT_BINARY_DIR}/RocksDBConfig.cmake
${CMAKE_CURRENT_BINARY_DIR}/RocksDBConfigVersion.cmake
COMPONENT devel
DESTINATION ${package_config_destination}
)
endif()
option(WITH_TESTS "build with tests" ON)
if(WITH_TESTS)
set(TESTS
cache/cache_test.cc
cache/lru_cache_test.cc
db/column_family_test.cc
@@ -608,6 +802,7 @@ set(TESTS
db/corruption_test.cc
db/cuckoo_table_db_test.cc
db/db_basic_test.cc
db/db_blob_index_test.cc
db/db_block_cache_test.cc
db/db_bloom_filter_test.cc
db/db_compaction_filter_test.cc
@@ -632,6 +827,7 @@ set(TESTS
db/db_test2.cc
db/db_universal_compaction_test.cc
db/db_wal_test.cc
db/db_write_test.cc
db/dbformat_test.cc
db/deletefile_test.cc
db/external_sst_file_basic_test.cc
@@ -664,6 +860,7 @@ set(TESTS
env/mock_env_test.cc
memtable/inlineskiplist_test.cc
memtable/skiplist_test.cc
memtable/write_buffer_manager_test.cc
monitoring/histogram_test.cc
monitoring/iostats_context_test.cc
monitoring/statistics_test.cc
@@ -671,6 +868,7 @@ set(TESTS
options/options_test.cc
table/block_based_filter_block_test.cc
table/block_test.cc
table/cleanable_test.cc
table/cuckoo_table_builder_test.cc
table/cuckoo_table_reader_test.cc
table/full_filter_block_test.cc
@@ -690,6 +888,7 @@ set(TESTS
util/event_logger_test.cc
util/file_reader_writer_test.cc
util/filelock_test.cc
util/hash_test.cc
util/heap_test.cc
util/rate_limiter_test.cc
util/slice_transform_test.cc
@@ -697,6 +896,11 @@ set(TESTS
util/thread_list_test.cc
util/thread_local_test.cc
utilities/backupable/backupable_db_test.cc
utilities/blob_db/blob_db_test.cc
utilities/cassandra/cassandra_functional_test.cc
utilities/cassandra/cassandra_format_test.cc
utilities/cassandra/cassandra_row_merge_test.cc
utilities/cassandra/cassandra_serialize_test.cc
utilities/checkpoint/checkpoint_test.cc
utilities/column_aware_encoding_test.cc
utilities/date_tiered/date_tiered_test.cc
@@ -713,98 +917,96 @@ set(TESTS
utilities/persistent_cache/persistent_cache_test.cc
utilities/redis/redis_lists_test.cc
utilities/spatialdb/spatial_db_test.cc
utilities/simulator_cache/sim_cache_test.cc
utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
utilities/transactions/optimistic_transaction_test.cc
utilities/transactions/transaction_test.cc
utilities/transactions/write_prepared_transaction_test.cc
utilities/ttl/ttl_test.cc
utilities/write_batch_with_index/write_batch_with_index_test.cc
)
if(WITH_LIBRADOS)
list(APPEND TESTS utilities/env_librados_test.cc)
endif()
)
if(WITH_LIBRADOS)
list(APPEND TESTS utilities/env_librados_test.cc)
endif()
set(BENCHMARKS
cache/cache_bench.cc
memtable/memtablerep_bench.cc
tools/db_bench.cc
table/table_reader_bench.cc
utilities/column_aware_encoding_exp.cc
utilities/persistent_cache/hash_table_bench.cc)
add_library(testharness OBJECT util/testharness.cc)
foreach(sourcefile ${BENCHMARKS})
get_filename_component(exename ${sourcefile} NAME_WE)
add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
$<TARGET_OBJECTS:testharness>)
target_link_libraries(${exename}${ARTIFACT_SUFFIX} gtest ${LIBS})
endforeach(sourcefile ${BENCHMARKS})
# For test util library that is build only in DEBUG mode
# and linked to tests. Add test only code that is not #ifdefed for Release here.
set(TESTUTIL_SOURCE
db/db_test_util.cc
env/mock_env.cc
monitoring/thread_status_updater_debug.cc
table/mock_table.cc
util/fault_injection_test_env.cc
)
# test utilities are only build in debug
enable_testing()
add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND})
set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
if(MSVC)
set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
endif()
set_target_properties(${TESTUTILLIB}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
)
# Tests are excluded from Release builds
set(TEST_EXES ${TESTS})
foreach(sourcefile ${TEST_EXES})
set(BENCHMARKS
cache/cache_bench.cc
memtable/memtablerep_bench.cc
tools/db_bench.cc
table/table_reader_bench.cc
utilities/column_aware_encoding_exp.cc
utilities/persistent_cache/hash_table_bench.cc)
add_library(testharness OBJECT util/testharness.cc)
foreach(sourcefile ${BENCHMARKS})
get_filename_component(exename ${sourcefile} NAME_WE)
add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
$<TARGET_OBJECTS:testharness>)
set_target_properties(${exename}${ARTIFACT_SUFFIX}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
)
target_link_libraries(${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} gtest ${LIBS})
if(NOT "${exename}" MATCHES "db_sanity_test")
target_link_libraries(${exename}${ARTIFACT_SUFFIX} gtest ${LIBS})
endforeach(sourcefile ${BENCHMARKS})
# For test util library that is build only in DEBUG mode
# and linked to tests. Add test only code that is not #ifdefed for Release here.
set(TESTUTIL_SOURCE
db/db_test_util.cc
monitoring/thread_status_updater_debug.cc
table/mock_table.cc
util/fault_injection_test_env.cc
utilities/cassandra/test_utils.cc
)
# test utilities are only build in debug
enable_testing()
add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND})
set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
if(MSVC)
set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
endif()
set_target_properties(${TESTUTILLIB}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
)
# Tests are excluded from Release builds
set(TEST_EXES ${TESTS})
foreach(sourcefile ${TEST_EXES})
get_filename_component(exename ${sourcefile} NAME_WE)
add_executable(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} ${sourcefile}
$<TARGET_OBJECTS:testharness>)
set_target_properties(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
OUTPUT_NAME ${exename}${ARTIFACT_SUFFIX}
)
target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} gtest ${LIBS})
if(NOT "${exename}" MATCHES "db_sanity_test")
add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
add_dependencies(check ${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX})
endif()
endforeach(sourcefile ${TEST_EXES})
# C executables must link to a shared object
set(C_TESTS db/c_test.c)
set(C_TEST_EXES ${C_TESTS})
foreach(sourcefile ${C_TEST_EXES})
string(REPLACE ".c" "" exename ${sourcefile})
string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
set_target_properties(${exename}${ARTIFACT_SUFFIX}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
)
target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${ROCKSDB_IMPORT_LIB} testutillib${ARTIFACT_SUFFIX})
add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
endif()
endforeach(sourcefile ${TEST_EXES})
# C executables must link to a shared object
set(C_TESTS db/c_test.c)
set(C_TEST_EXES ${C_TESTS})
foreach(sourcefile ${C_TEST_EXES})
string(REPLACE ".c" "" exename ${sourcefile})
string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
set_target_properties(${exename}${ARTIFACT_SUFFIX}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
)
target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${ROCKSDB_IMPORT_LIB} testutillib${ARTIFACT_SUFFIX})
add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
endforeach(sourcefile ${C_TEST_EXES})
add_subdirectory(tools)
# Installation and packaging for Linux
if(NOT WIN32)
install(TARGETS ${ROCKSDB_STATIC_LIB} COMPONENT devel ARCHIVE DESTINATION lib64)
install(TARGETS ${ROCKSDB_SHARED_LIB} COMPONENT runtime DESTINATION lib64)
install(DIRECTORY "${PROJECT_SOURCE_DIR}/include/rocksdb/"
COMPONENT devel
DESTINATION include/rocksdb)
set(CMAKE_INSTALL_PREFIX /usr)
endforeach(sourcefile ${C_TEST_EXES})
endif()
option(WITH_TOOLS "build with tools" ON)
if(WITH_TOOLS)
add_subdirectory(tools)
endif()
+3
View File
@@ -0,0 +1,3 @@
# Code of Conduct
Facebook has adopted a Code of Conduct that we expect project participants to adhere to. Please [read the full text](https://code.facebook.com/codeofconduct) so that you can understand what actions will and will not be tolerated.
+3 -5
View File
@@ -1,5 +1,8 @@
# Contributing to RocksDB
## Code of Conduct
The code of conduct is described in [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md)
## Contributor License Agreement ("CLA")
In order to accept your pull request, we need you to submit a CLA. You
@@ -12,8 +15,3 @@ Complete your CLA here: <https://code.facebook.com/cla>
If you prefer to sign a paper copy, we can send you a PDF. Send us an
e-mail or create a new github issue to request the CLA in PDF format.
## License
By contributing to RocksDB, you agree that your contributions will be
licensed under the [BSD License](LICENSE).
+3
View File
@@ -1,5 +1,8 @@
# RocksDB default options change log
## Unreleased
* delayed_write_rate takes the rate given by rate_limiter if not specified.
## 5.2
* Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files.
## 5.0 (11/17/2016)
+138 -1
View File
@@ -1,5 +1,139 @@
# Rocksdb Change Log
## Unreleased
### Public API Change
* RocksDBOptionsParser::Parse()'s `ignore_unknown_options` argument will only be effective if the option file shows it is generated using a higher version of RocksDB than the current version.
## 5.12.0 (2/14/2018)
### Public API Change
* Iterator::SeekForPrev is now a pure virtual method. This is to prevent user who implement the Iterator interface fail to implement SeekForPrev by mistake.
* Add `include_end` option to make the range end exclusive when `include_end == false` in `DeleteFilesInRange()`.
* Add `CompactRangeOptions::allow_write_stall`, which makes `CompactRange` start working immediately, even if it causes user writes to stall. The default value is false, meaning we add delay to `CompactRange` calls until stalling can be avoided when possible. Note this delay is not present in previous RocksDB versions.
* Creating checkpoint with empty directory now returns `Status::InvalidArgument`; previously, it returned `Status::IOError`.
* Adds a BlockBasedTableOption to turn off index block compression.
* Close() method now returns a status when closing a db.
### New Features
* Improve the performance of iterators doing long range scans by using readahead.
* Add new function `DeleteFilesInRanges()` to delete files in multiple ranges at once for better performance.
* FreeBSD build support for RocksDB and RocksJava.
* Improved performance of long range scans with readahead.
* Updated to and now continuously tested in Visual Studio 2017.
### Bug Fixes
* Fix `DisableFileDeletions()` followed by `GetSortedWalFiles()` to not return obsolete WAL files that `PurgeObsoleteFiles()` is going to delete.
* Fix Handle error return from WriteBuffer() during WAL file close and DB close.
* Fix advance reservation of arena block addresses.
* Fix handling of empty string as checkpoint directory.
## 5.11.0 (01/08/2018)
### Public API Change
* Add `autoTune` and `getBytesPerSecond()` to RocksJava RateLimiter
### New Features
* Add a new histogram stat called rocksdb.db.flush.micros for memtable flush.
* Add "--use_txn" option to use transactional API in db_stress.
* Disable onboard cache for compaction output in Windows platform.
* Improve the performance of iterators doing long range scans by using readahead.
### Bug Fixes
* Fix a stack-use-after-scope bug in ForwardIterator.
* Fix builds on platforms including Linux, Windows, and PowerPC.
* Fix buffer overrun in backup engine for DBs with huge number of files.
* Fix a mislabel bug for bottom-pri compaction threads.
* Fix DB::Flush() keep waiting after flush finish under certain condition.
## 5.10.0 (12/11/2017)
### Public API Change
* When running `make` with environment variable `USE_SSE` set and `PORTABLE` unset, will use all machine features available locally. Previously this combination only compiled SSE-related features.
### New Features
* Provide lifetime hints when writing files on Linux. This reduces hardware write-amp on storage devices supporting multiple streams.
* Add a DB stat, `NUMBER_ITER_SKIP`, which returns how many internal keys were skipped during iterations (e.g., due to being tombstones or duplicate versions of a key).
* Add PerfContext counters, `key_lock_wait_count` and `key_lock_wait_time`, which measure the number of times transactions wait on key locks and total amount of time waiting.
### Bug Fixes
* Fix IOError on WAL write doesn't propagate to write group follower
* Make iterator invalid on merge error.
* Fix performance issue in `IngestExternalFile()` affecting databases with large number of SST files.
* Fix possible corruption to LSM structure when `DeleteFilesInRange()` deletes a subset of files spanned by a `DeleteRange()` marker.
## 5.9.0 (11/1/2017)
### Public API Change
* `BackupableDBOptions::max_valid_backups_to_open == 0` now means no backups will be opened during BackupEngine initialization. Previously this condition disabled limiting backups opened.
* `DBOptions::preserve_deletes` is a new option that allows one to specify that DB should not drop tombstones for regular deletes if they have sequence number larger than what was set by the new API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)`. Disabled by default.
* API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)` was added, users who wish to preserve deletes are expected to periodically call this function to advance the cutoff seqnum (all deletes made before this seqnum can be dropped by DB). It's user responsibility to figure out how to advance the seqnum in the way so the tombstones are kept for the desired period of time, yet are eventually processed in time and don't eat up too much space.
* `ReadOptions::iter_start_seqnum` was added; if set to something > 0 user will see 2 changes in iterators behavior 1) only keys written with sequence larger than this parameter would be returned and 2) the `Slice` returned by iter->key() now points to the the memory that keep User-oriented representation of the internal key, rather than user key. New struct `FullKey` was added to represent internal keys, along with a new helper function `ParseFullKey(const Slice& internal_key, FullKey* result);`.
* Deprecate trash_dir param in NewSstFileManager, right now we will rename deleted files to <name>.trash instead of moving them to trash directory
* Allow setting a custom trash/DB size ratio limit in the SstFileManager, after which files that are to be scheduled for deletion are deleted immediately, regardless of any delete ratelimit.
* Return an error on write if write_options.sync = true and write_options.disableWAL = true to warn user of inconsistent options. Previously we will not write to WAL and not respecting the sync options in this case.
### New Features
* CRC32C is now using the 3-way pipelined SSE algorithm `crc32c_3way` on supported platforms to improve performance. The system will choose to use this algorithm on supported platforms automatically whenever possible. If PCLMULQDQ is not supported it will fall back to the old Fast_CRC32 algorithm.
* `DBOptions::writable_file_max_buffer_size` can now be changed dynamically.
* `DBOptions::bytes_per_sync`, `DBOptions::compaction_readahead_size`, and `DBOptions::wal_bytes_per_sync` can now be changed dynamically, `DBOptions::wal_bytes_per_sync` will flush all memtables and switch to a new WAL file.
* Support dynamic adjustment of rate limit according to demand for background I/O. It can be enabled by passing `true` to the `auto_tuned` parameter in `NewGenericRateLimiter()`. The value passed as `rate_bytes_per_sec` will still be respected as an upper-bound.
* Support dynamically changing `ColumnFamilyOptions::compaction_options_fifo`.
* Introduce `EventListener::OnStallConditionsChanged()` callback. Users can implement it to be notified when user writes are stalled, stopped, or resumed.
* Add a new db property "rocksdb.estimate-oldest-key-time" to return oldest data timestamp. The property is available only for FIFO compaction with compaction_options_fifo.allow_compaction = false.
* Upon snapshot release, recompact bottommost files containing deleted/overwritten keys that previously could not be dropped due to the snapshot. This alleviates space-amp caused by long-held snapshots.
* Support lower bound on iterators specified via `ReadOptions::iterate_lower_bound`.
* Support for differential snapshots (via iterator emitting the sequence of key-values representing the difference between DB state at two different sequence numbers). Supports preserving and emitting puts and regular deletes, doesn't support SingleDeletes, MergeOperator, Blobs and Range Deletes.
### Bug Fixes
* Fix a potential data inconsistency issue during point-in-time recovery. `DB:Open()` will abort if column family inconsistency is found during PIT recovery.
* Fix possible metadata corruption in databases using `DeleteRange()`.
## 5.8.0 (08/30/2017)
### Public API Change
* Users of `Statistics::getHistogramString()` will see fewer histogram buckets and different bucket endpoints.
* `Slice::compare` and BytewiseComparator `Compare` no longer accept `Slice`s containing nullptr.
* `Transaction::Get` and `Transaction::GetForUpdate` variants with `PinnableSlice` added.
### New Features
* Add Iterator::Refresh(), which allows users to update the iterator state so that they can avoid some initialization costs of recreating iterators.
* Replace dynamic_cast<> (except unit test) so people can choose to build with RTTI off. With make, release mode is by default built with -fno-rtti and debug mode is built without it. Users can override it by setting USE_RTTI=0 or 1.
* Universal compactions including the bottom level can be executed in a dedicated thread pool. This alleviates head-of-line blocking in the compaction queue, which cause write stalling, particularly in multi-instance use cases. Users can enable this feature via `Env::SetBackgroundThreads(N, Env::Priority::BOTTOM)`, where `N > 0`.
* Allow merge operator to be called even with a single merge operand during compactions, by appropriately overriding `MergeOperator::AllowSingleOperand`.
* Add `DB::VerifyChecksum()`, which verifies the checksums in all SST files in a running DB.
* Block-based table support for disabling checksums by setting `BlockBasedTableOptions::checksum = kNoChecksum`.
### Bug Fixes
* Fix wrong latencies in `rocksdb.db.get.micros`, `rocksdb.db.write.micros`, and `rocksdb.sst.read.micros`.
* Fix incorrect dropping of deletions during intra-L0 compaction.
* Fix transient reappearance of keys covered by range deletions when memtable prefix bloom filter is enabled.
* Fix potentially wrong file smallest key when range deletions separated by snapshot are written together.
## 5.7.0 (07/13/2017)
### Public API Change
* DB property "rocksdb.sstables" now prints keys in hex form.
### New Features
* Measure estimated number of reads per file. The information can be accessed through DB::GetColumnFamilyMetaData or "rocksdb.sstables" DB property.
* RateLimiter support for throttling background reads, or throttling the sum of background reads and writes. This can give more predictable I/O usage when compaction reads more data than it writes, e.g., due to lots of deletions.
* [Experimental] FIFO compaction with TTL support. It can be enabled by setting CompactionOptionsFIFO.ttl > 0.
* Introduce `EventListener::OnBackgroundError()` callback. Users can implement it to be notified of errors causing the DB to enter read-only mode, and optionally override them.
* Partitioned Index/Filters exiting the experimental mode. To enable partitioned indexes set index_type to kTwoLevelIndexSearch and to further enable partitioned filters set partition_filters to true. To configure the partition size set metadata_block_size.
### Bug Fixes
* Fix discarding empty compaction output files when `DeleteRange()` is used together with subcompactions.
## 5.6.0 (06/06/2017)
### Public API Change
* Scheduling flushes and compactions in the same thread pool is no longer supported by setting `max_background_flushes=0`. Instead, users can achieve this by configuring their high-pri thread pool to have zero threads.
* Replace `Options::max_background_flushes`, `Options::max_background_compactions`, and `Options::base_background_compactions` all with `Options::max_background_jobs`, which automatically decides how many threads to allocate towards flush/compaction.
* options.delayed_write_rate by default take the value of options.rate_limiter rate.
* Replace global variable `IOStatsContext iostats_context` with `IOStatsContext* get_iostats_context()`; replace global variable `PerfContext perf_context` with `PerfContext* get_perf_context()`.
### New Features
* Change ticker/histogram statistics implementations to use core-local storage. This improves aggregation speed compared to our previous thread-local approach, particularly for applications with many threads.
* Users can pass a cache object to write buffer manager, so that they can cap memory usage for memtable and block cache using one single limit.
* Flush will be triggered when 7/8 of the limit introduced by write_buffer_manager or db_write_buffer_size is triggered, so that the hard threshold is hard to hit.
* Introduce WriteOptions.low_pri. If it is true, low priority writes will be throttled if the compaction is behind.
* `DB::IngestExternalFile()` now supports ingesting files into a database containing range deletions.
### Bug Fixes
* Shouldn't ignore return value of fsync() in flush.
## 5.5.0 (05/17/2017)
### New Features
@@ -13,7 +147,10 @@
* Add debugging function `GetAllKeyVersions` to see internal versions of a range of keys.
* Support file ingestion with universal compaction style
* Support file ingestion behind with option `allow_ingest_behind`
* New option enable_pipelined_write which may improve write throughput in case writing from multiple threads and WAL enabled .
* New option enable_pipelined_write which may improve write throughput in case writing from multiple threads and WAL enabled.
### Bug Fixes
* Fix the bug that Direct I/O uses direct reads for non-SST file
## 5.4.0 (04/11/2017)
### Public API Change
+43
View File
@@ -32,6 +32,7 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
* You can link RocksDB with following compression libraries:
- [zlib](http://www.zlib.net/) - a library for data compression.
- [bzip2](http://www.bzip.org/) - a library for data compression.
- [lz4](https://github.com/lz4/lz4) - a library for extremely fast data compression.
- [snappy](http://google.github.io/snappy/) - a library for fast
data compression.
- [zstandard](http://www.zstd.net) - Fast real-time compression
@@ -53,6 +54,7 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
`sudo apt-get install libsnappy-dev`.
* Install zlib. Try: `sudo apt-get install zlib1g-dev`.
* Install bzip2: `sudo apt-get install libbz2-dev`.
* Install lz4: `sudo apt-get install liblz4-dev`.
* Install zstandard: `sudo apt-get install libzstd-dev`.
* **Linux - CentOS / RHEL**
@@ -81,6 +83,10 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
sudo yum install bzip2 bzip2-devel
* Install lz4:
sudo yum install lz4-devel
* Install ASAN (optional for debugging):
sudo yum install libasan
@@ -101,12 +107,49 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
* run `brew tap homebrew/versions; brew install gcc48 --use-llvm` to install gcc 4.8 (or higher).
* run `brew install rocksdb`
* **FreeBSD** (11.01):
* You can either install RocksDB from the Ports system using `cd /usr/ports/databases/rocksdb && make install`, or you can follow the details below to install dependencies and compile from source code:
* Install the dependencies for RocksDB:
export BATCH=YES
cd /usr/ports/devel/gmake && make install
cd /usr/ports/devel/gflags && make install
cd /usr/ports/archivers/snappy && make install
cd /usr/ports/archivers/bzip2 && make install
cd /usr/ports/archivers/liblz4 && make install
cd /usr/ports/archivesrs/zstd && make install
cd /usr/ports/devel/git && make install
* Install the dependencies for RocksJava (optional):
export BATCH=yes
cd /usr/ports/java/openjdk7 && make install
* Build RocksDB from source:
cd ~
git clone https://github.com/facebook/rocksdb.git
cd rocksdb
gmake static_lib
* Build RocksJava from source (optional):
cd rocksdb
export JAVA_HOME=/usr/local/openjdk7
gmake rocksdbjava
* **iOS**:
* Run: `TARGET_OS=IOS make static_lib`. When building the project which uses rocksdb iOS library, make sure to define two important pre-processing macros: `ROCKSDB_LITE` and `IOS_CROSS_COMPILE`.
* **Windows**:
* For building with MS Visual Studio 13 you will need Update 4 installed.
* Read and follow the instructions at CMakeLists.txt
* Or install via [vcpkg](https://github.com/microsoft/vcpkg)
* run `vcpkg install rocksdb:x64-windows`
* **AIX 6.1**
* Install AIX Toolbox rpms with gcc
+6 -1
View File
@@ -9,5 +9,10 @@ This is the list of all known third-party language bindings for RocksDB. If some
* Haskell - https://hackage.haskell.org/package/rocksdb-haskell
* PHP - https://github.com/Photonios/rocksdb-php
* C# - https://github.com/warrenfalk/rocksdb-sharp
* Rust - https://github.com/spacejam/rust-rocksdb
* Rust
* https://github.com/spacejam/rust-rocksdb
* https://github.com/bh1xuw/rust-rocks
* D programming language - https://github.com/b1naryth1ef/rocksdb
* Erlang - https://gitlab.com/barrel-db/erlang-rocksdb
* Elixir - https://github.com/urbint/rox
* Nim - https://github.com/status-im/nim-rocksdb
+202
View File
@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
+1 -7
View File
@@ -1,10 +1,4 @@
BSD License
For rocksdb software
Copyright (c) 2011-present, Facebook, Inc.
All rights reserved.
---------------------------------------------------------------------
This contains code that is from LevelDB, and that code is under the following license:
Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+236 -42
View File
@@ -96,12 +96,34 @@ OPT += -momit-leaf-frame-pointer
endif
endif
# if we're compiling for release, compile without debug code (-DNDEBUG) and
# don't treat warnings as errors
ifeq (,$(shell $(CXX) -fsyntax-only -maltivec -xc /dev/null 2>&1))
CXXFLAGS += -DHAS_ALTIVEC
CFLAGS += -DHAS_ALTIVEC
HAS_ALTIVEC=1
endif
ifeq (,$(shell $(CXX) -fsyntax-only -mcpu=power8 -xc /dev/null 2>&1))
CXXFLAGS += -DHAVE_POWER8
CFLAGS += -DHAVE_POWER8
HAVE_POWER8=1
endif
# if we're compiling for release, compile without debug code (-DNDEBUG)
ifeq ($(DEBUG_LEVEL),0)
OPT += -DNDEBUG
DISABLE_WARNING_AS_ERROR=1
ifneq ($(USE_RTTI), 1)
CXXFLAGS += -fno-rtti
else
CXXFLAGS += -DROCKSDB_USE_RTTI
endif
else
ifneq ($(USE_RTTI), 0)
CXXFLAGS += -DROCKSDB_USE_RTTI
else
CXXFLAGS += -fno-rtti
endif
$(warning Warning: Compiling in debug mode. Don't use the resulting binary in production)
endif
@@ -193,8 +215,8 @@ endif
ifdef COMPILE_WITH_TSAN
DISABLE_JEMALLOC=1
EXEC_LDFLAGS += -fsanitize=thread
PLATFORM_CCFLAGS += -fsanitize=thread -fPIC -DROCKSDB_TSAN_RUN
PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC -DROCKSDB_TSAN_RUN
PLATFORM_CCFLAGS += -fsanitize=thread -fPIC
PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC
# Turn off -pg when enabling TSAN testing, because that induces
# a link failure. TODO: find the root cause
PROFILING_FLAGS =
@@ -210,9 +232,18 @@ endif
# USAN doesn't work well with jemalloc. If we're compiling with USAN, we should use regular malloc.
ifdef COMPILE_WITH_UBSAN
DISABLE_JEMALLOC=1
EXEC_LDFLAGS += -fsanitize=undefined
PLATFORM_CCFLAGS += -fsanitize=undefined
PLATFORM_CXXFLAGS += -fsanitize=undefined
# Suppress alignment warning because murmurhash relies on casting unaligned
# memory to integer. Fixing it may cause performance regression. 3-way crc32
# relies on it too, although it can be rewritten to eliminate with minimal
# performance regression.
EXEC_LDFLAGS += -fsanitize=undefined -fno-sanitize-recover=all
PLATFORM_CCFLAGS += -fsanitize=undefined -fno-sanitize-recover=all -DROCKSDB_UBSAN_RUN
PLATFORM_CXXFLAGS += -fsanitize=undefined -fno-sanitize-recover=all -DROCKSDB_UBSAN_RUN
endif
ifdef ROCKSDB_VALGRIND_RUN
PLATFORM_CCFLAGS += -DROCKSDB_VALGRIND_RUN
PLATFORM_CXXFLAGS += -DROCKSDB_VALGRIND_RUN
endif
ifndef DISABLE_JEMALLOC
@@ -220,6 +251,10 @@ ifndef DISABLE_JEMALLOC
PLATFORM_CXXFLAGS += -DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE
PLATFORM_CCFLAGS += -DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE
endif
ifdef WITH_JEMALLOC_FLAG
PLATFORM_LDFLAGS += -ljemalloc
JAVA_LDFLAGS += -ljemalloc
endif
EXEC_LDFLAGS := $(JEMALLOC_LIB) $(EXEC_LDFLAGS)
PLATFORM_CXXFLAGS += $(JEMALLOC_INCLUDE)
PLATFORM_CCFLAGS += $(JEMALLOC_INCLUDE)
@@ -274,6 +309,9 @@ LDFLAGS += $(LUA_LIB)
endif
ifeq ($(NO_THREEWAY_CRC32C), 1)
CXXFLAGS += -DNO_THREEWAY_CRC32C
endif
CFLAGS += $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CCFLAGS) $(OPT)
CXXFLAGS += $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CXXFLAGS) $(OPT) -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers
@@ -306,6 +344,14 @@ util/build_version.cc: FORCE
endif
LIBOBJECTS = $(LIB_SOURCES:.cc=.o)
ifeq ($(HAVE_POWER8),1)
LIB_CC_OBJECTS = $(LIB_SOURCES:.cc=.o)
LIBOBJECTS += $(LIB_SOURCES_C:.c=.o)
LIBOBJECTS += $(LIB_SOURCES_ASM:.S=.o)
else
LIB_CC_OBJECTS = $(LIB_SOURCES:.cc=.o)
endif
LIBOBJECTS += $(TOOL_LIB_SOURCES:.cc=.o)
MOCKOBJECTS = $(MOCK_LIB_SOURCES:.cc=.o)
@@ -323,6 +369,7 @@ EXPOBJECTS = $(EXP_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)
TESTS = \
db_basic_test \
db_encryption_test \
db_test2 \
external_sst_file_basic_test \
auto_roll_logger_test \
@@ -335,6 +382,7 @@ TESTS = \
inlineskiplist_test \
env_basic_test \
env_test \
hash_test \
thread_local_test \
rate_limiter_test \
perf_context_test \
@@ -342,6 +390,7 @@ TESTS = \
db_wal_test \
db_block_cache_test \
db_test \
db_blob_index_test \
db_bloom_filter_test \
db_iter_test \
db_log_iter_test \
@@ -362,7 +411,9 @@ TESTS = \
db_properties_test \
db_table_properties_test \
db_statistics_test \
db_write_test \
autovector_test \
blob_db_test \
cleanable_test \
column_family_test \
table_properties_collector_test \
@@ -398,7 +449,12 @@ TESTS = \
external_sst_file_test \
prefix_test \
skiplist_test \
write_buffer_manager_test \
stringappend_test \
cassandra_format_test \
cassandra_functional_test \
cassandra_row_merge_test \
cassandra_serialize_test \
ttl_test \
date_tiered_test \
backupable_db_test \
@@ -451,11 +507,13 @@ TESTS = \
object_registry_test \
repair_test \
env_timed_test \
write_prepared_transaction_test \
PARALLEL_TEST = \
backupable_db_test \
db_compaction_filter_test \
db_compaction_test \
db_merge_operator_test \
db_sst_test \
db_test \
db_universal_compaction_test \
@@ -466,8 +524,13 @@ PARALLEL_TEST = \
manual_compaction_test \
persistent_cache_test \
table_test \
transaction_test
transaction_test \
write_prepared_transaction_test \
# options_settable_test doesn't pass with UBSAN as we use hack in the test
ifdef COMPILE_WITH_UBSAN
TESTS := $(shell echo $(TESTS) | sed 's/\boptions_settable_test\b//g')
endif
SUBSET := $(TESTS)
ifdef ROCKSDBTESTS_START
SUBSET := $(shell echo $(SUBSET) | sed 's/^.*$(ROCKSDBTESTS_START)/$(ROCKSDBTESTS_START)/')
@@ -485,7 +548,8 @@ TOOLS = \
ldb \
db_repl_stress \
rocksdb_dump \
rocksdb_undump
rocksdb_undump \
blob_dump \
TEST_LIBS = \
librocksdb_env_basic_test.a
@@ -545,14 +609,35 @@ $(SHARED2): $(SHARED4)
$(SHARED3): $(SHARED4)
ln -fs $(SHARED4) $(SHARED3)
endif
ifeq ($(HAVE_POWER8),1)
SHARED_C_OBJECTS = $(LIB_SOURCES_C:.c=.o)
SHARED_ASM_OBJECTS = $(LIB_SOURCES_ASM:.S=.o)
SHARED_C_LIBOBJECTS = $(patsubst %.o,shared-objects/%.o,$(SHARED_C_OBJECTS))
SHARED_ASM_LIBOBJECTS = $(patsubst %.o,shared-objects/%.o,$(SHARED_ASM_OBJECTS))
shared_libobjects = $(patsubst %,shared-objects/%,$(LIB_CC_OBJECTS))
else
shared_libobjects = $(patsubst %,shared-objects/%,$(LIBOBJECTS))
CLEAN_FILES += shared-objects
endif
CLEAN_FILES += shared-objects
shared_all_libobjects = $(shared_libobjects)
ifeq ($(HAVE_POWER8),1)
shared-ppc-objects = $(SHARED_C_LIBOBJECTS) $(SHARED_ASM_LIBOBJECTS)
shared-objects/util/crc32c_ppc.o: util/crc32c_ppc.c
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
shared-objects/util/crc32c_ppc_asm.o: util/crc32c_ppc_asm.S
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
endif
$(shared_libobjects): shared-objects/%.o: %.cc
$(AM_V_CC)mkdir -p $(@D) && $(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) -c $< -o $@
$(SHARED4): $(shared_libobjects)
ifeq ($(HAVE_POWER8),1)
shared_all_libobjects = $(shared_libobjects) $(shared-ppc-objects)
endif
$(SHARED4): $(shared_all_libobjects)
$(CXX) $(PLATFORM_SHARED_LDFLAGS)$(SHARED3) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(shared_libobjects) $(LDFLAGS) -o $@
endif # PLATFORM_SHARED_EXT
@@ -565,6 +650,8 @@ endif # PLATFORM_SHARED_EXT
all: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(TESTS)
all_but_some_tests: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(SUBSET)
static_lib: $(LIBRARY)
shared_lib: $(SHARED)
@@ -672,7 +759,7 @@ gen_parallel_tests:
# 107.816 PASS t/DBTest.EncodeDecompressedBlockSizeTest
#
slow_test_regexp = \
^t/run-table_test-HarnessTest.Randomized$$|^t/run-db_test-.*(?:FileCreationRandomFailure|EncodeDecompressedBlockSizeTest)$$|^.*RecoverFromCorruptedWALWithoutFlush$$
^.*SnapshotConcurrentAccessTest.*$$|^t/run-table_test-HarnessTest.Randomized$$|^t/run-db_test-.*(?:FileCreationRandomFailure|EncodeDecompressedBlockSizeTest)$$|^.*RecoverFromCorruptedWALWithoutFlush$$
prioritize_long_running_tests = \
perl -pe 's,($(slow_test_regexp)),100 $$1,' \
| sort -k1,1gr \
@@ -768,8 +855,8 @@ ldb_tests: ldb
crash_test: whitebox_crash_test blackbox_crash_test
blackbox_crash_test: db_stress
python -u tools/db_crashtest.py --simple blackbox
python -u tools/db_crashtest.py blackbox
python -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
python -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)
ifeq ($(CRASH_TEST_KILL_ODD),)
CRASH_TEST_KILL_ODD=888887
@@ -777,9 +864,9 @@ endif
whitebox_crash_test: db_stress
python -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
$(CRASH_TEST_KILL_ODD)
$(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
python -u tools/db_crashtest.py whitebox --random_kill_odd \
$(CRASH_TEST_KILL_ODD)
$(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
asan_check:
$(MAKE) clean
@@ -802,7 +889,7 @@ ubsan_crash_test:
$(MAKE) clean
valgrind_test:
DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
valgrind_check: $(TESTS)
$(MAKE) DRIVER="$(VALGRIND_VER) $(VALGRIND_OPTS)" gen_parallel_tests
@@ -901,7 +988,7 @@ clean:
rm -rf $(CLEAN_FILES) ios-x86 ios-arm scan_build_report
find . -name "*.[oda]" -exec rm -f {} \;
find . -type f -regex ".*\.\(\(gcda\)\|\(gcno\)\)" -exec rm {} \;
rm -rf bzip2* snappy* zlib* lz4*
rm -rf bzip2* snappy* zlib* lz4* zstd*
cd java; $(MAKE) clean
tags:
@@ -981,12 +1068,27 @@ cache_test: cache/cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
coding_test: util/coding_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
hash_test: util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
option_change_migration_test: utilities/option_change_migration/option_change_migration_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
stringappend_test: utilities/merge_operators/string_append/stringappend_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
cassandra_format_test: utilities/cassandra/cassandra_format_test.o utilities/cassandra/test_utils.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
cassandra_functional_test: utilities/cassandra/cassandra_functional_test.o utilities/cassandra/test_utils.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
cassandra_row_merge_test: utilities/cassandra/cassandra_row_merge_test.o utilities/cassandra/test_utils.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
cassandra_serialize_test: utilities/cassandra/cassandra_serialize_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
redis_test: utilities/redis/redis_lists_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
@@ -1011,12 +1113,18 @@ slice_transform_test: util/slice_transform_test.o $(LIBOBJECTS) $(TESTHARNESS)
db_basic_test: db/db_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
db_encryption_test: db/db_encryption_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
db_test: db/db_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
db_test2: db/db_test2.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
db_blob_index_test: db/db_blob_index_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
db_block_cache_test: db/db_block_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
@@ -1062,6 +1170,9 @@ db_sst_test: db/db_sst_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
db_statistics_test: db/db_statistics_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
db_write_test: db/db_write_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
external_sst_file_basic_test: db/external_sst_file_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
@@ -1178,7 +1289,7 @@ env_test: env/env_test.o $(LIBOBJECTS) $(TESTHARNESS)
fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
rate_limiter_test: util/rate_limiter_test.o $(LIBOBJECTS) $(TESTHARNESS)
rate_limiter_test: util/rate_limiter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
delete_scheduler_test: util/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1217,6 +1328,9 @@ inlineskiplist_test: memtable/inlineskiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
skiplist_test: memtable/skiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
write_buffer_manager_test: memtable/write_buffer_manager_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
version_edit_test: db/version_edit_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
@@ -1340,9 +1454,15 @@ heap_test: util/heap_test.o $(GTEST)
transaction_test: utilities/transactions/transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
write_prepared_transaction_test: utilities/transactions/write_prepared_transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
sst_dump: tools/sst_dump.o $(LIBOBJECTS)
$(AM_LINK)
blob_dump: tools/blob_dump.o $(LIBOBJECTS)
$(AM_LINK)
column_aware_encoding_exp: utilities/column_aware_encoding_exp.o $(EXPOBJECTS)
$(AM_LINK)
@@ -1373,6 +1493,9 @@ lua_test: utilities/lua/rocks_lua_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTH
range_del_aggregator_test: db/range_del_aggregator_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
blob_db_test: utilities/blob_db/blob_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
$(AM_LINK)
#-------------------------------------------------
# make install related stuff
INSTALL_PATH ?= /usr/local
@@ -1441,11 +1564,11 @@ BZIP2_DOWNLOAD_BASE ?= http://www.bzip.org
SNAPPY_VER ?= 1.1.4
SNAPPY_SHA256 ?= 134bfe122fd25599bb807bb8130e7ba6d9bdb851e0b16efcb83ac4f5d0b70057
SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/releases/download
LZ4_VER ?= 1.7.5
LZ4_SHA256 ?= 0190cacd63022ccb86f44fa5041dc6c3804407ad61550ca21c382827319e7e7e
LZ4_VER ?= 1.8.0
LZ4_SHA256 ?= 2ca482ea7a9bb103603108b5a7510b7592b90158c151ff50a28f1ca8389fccf6
LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
ZSTD_VER ?= 1.2.0
ZSTD_SHA256 ?= 4a7e4593a3638276ca7f2a09dc4f38e674d8317bbea51626393ca73fc047cbfb
ZSTD_VER ?= 1.3.3
ZSTD_SHA256 ?= a77c47153ee7de02626c5b2a097005786b71688be61e9fb81806a011f90b297b
ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
ifeq ($(PLATFORM), OS_MACOSX)
@@ -1459,7 +1582,7 @@ else
endif
endif
ifeq ($(PLATFORM), OS_FREEBSD)
JAVA_INCLUDE += -I$(JAVA_HOME)/include/freebsd
JAVA_INCLUDE = -I$(JAVA_HOME)/include -I$(JAVA_HOME)/include/freebsd
ROCKSDBJNILIB = librocksdbjni-freebsd$(ARCH).so
ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-freebsd$(ARCH).jar
endif
@@ -1485,7 +1608,7 @@ libz.a:
exit 1; \
fi
tar xvzf zlib-$(ZLIB_VER).tar.gz
cd zlib-$(ZLIB_VER) && CFLAGS='-fPIC ${EXTRA_CFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' ./configure --static && make
cd zlib-$(ZLIB_VER) && CFLAGS='-fPIC ${EXTRA_CFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' ./configure --static && $(MAKE)
cp zlib-$(ZLIB_VER)/libz.a .
libbz2.a:
@@ -1497,7 +1620,7 @@ libbz2.a:
exit 1; \
fi
tar xvzf bzip2-$(BZIP2_VER).tar.gz
cd bzip2-$(BZIP2_VER) && make CFLAGS='-fPIC -O2 -g -D_FILE_OFFSET_BITS=64 ${EXTRA_CFLAGS}' AR='ar ${EXTRA_ARFLAGS}'
cd bzip2-$(BZIP2_VER) && $(MAKE) CFLAGS='-fPIC -O2 -g -D_FILE_OFFSET_BITS=64 ${EXTRA_CFLAGS}' AR='ar ${EXTRA_ARFLAGS}'
cp bzip2-$(BZIP2_VER)/libbz2.a .
libsnappy.a:
@@ -1510,7 +1633,7 @@ libsnappy.a:
fi
tar xvzf snappy-$(SNAPPY_VER).tar.gz
cd snappy-$(SNAPPY_VER) && CFLAGS='${EXTRA_CFLAGS}' CXXFLAGS='${EXTRA_CXXFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' ./configure --with-pic --enable-static --disable-shared
cd snappy-$(SNAPPY_VER) && make ${SNAPPY_MAKE_TARGET}
cd snappy-$(SNAPPY_VER) && $(MAKE) ${SNAPPY_MAKE_TARGET}
cp snappy-$(SNAPPY_VER)/.libs/libsnappy.a .
liblz4.a:
@@ -1523,7 +1646,7 @@ liblz4.a:
exit 1; \
fi
tar xvzf lz4-$(LZ4_VER).tar.gz
cd lz4-$(LZ4_VER)/lib && make CFLAGS='-fPIC -O2 ${EXTRA_CFLAGS}' all
cd lz4-$(LZ4_VER)/lib && $(MAKE) CFLAGS='-fPIC -O2 ${EXTRA_CFLAGS}' all
cp lz4-$(LZ4_VER)/lib/liblz4.a .
libzstd.a:
@@ -1536,29 +1659,45 @@ libzstd.a:
exit 1; \
fi
tar xvzf zstd-$(ZSTD_VER).tar.gz
cd zstd-$(ZSTD_VER)/lib && make CFLAGS='-fPIC -O2 ${EXTRA_CFLAGS}' all
cd zstd-$(ZSTD_VER)/lib && DESTDIR=. PREFIX= $(MAKE) CFLAGS='-fPIC -O2 ${EXTRA_CFLAGS}' install
cp zstd-$(ZSTD_VER)/lib/libzstd.a .
# A version of each $(LIBOBJECTS) compiled with -fPIC and a fixed set of static compression libraries
java_static_libobjects = $(patsubst %,jls/%,$(LIBOBJECTS))
java_static_libobjects = $(patsubst %,jls/%,$(LIB_CC_OBJECTS))
CLEAN_FILES += jls
java_static_all_libobjects = $(java_static_libobjects)
ifneq ($(ROCKSDB_JAVA_NO_COMPRESSION), 1)
JAVA_COMPRESSIONS = libz.a libbz2.a libsnappy.a liblz4.a libzstd.a
endif
JAVA_STATIC_FLAGS = -DZLIB -DBZIP2 -DSNAPPY -DLZ4 -DZSTD
JAVA_STATIC_INCLUDES = -I./zlib-$(ZLIB_VER) -I./bzip2-$(BZIP2_VER) -I./snappy-$(SNAPPY_VER) -I./lz4-$(LZ4_VER)/lib -I./zstd-$(ZSTD_VER)/lib
JAVA_STATIC_INCLUDES = -I./zlib-$(ZLIB_VER) -I./bzip2-$(BZIP2_VER) -I./snappy-$(SNAPPY_VER) -I./lz4-$(LZ4_VER)/lib -I./zstd-$(ZSTD_VER)/lib/include
ifeq ($(HAVE_POWER8),1)
JAVA_STATIC_C_LIBOBJECTS = $(patsubst %.c.o,jls/%.c.o,$(LIB_SOURCES_C:.c=.o))
JAVA_STATIC_ASM_LIBOBJECTS = $(patsubst %.S.o,jls/%.S.o,$(LIB_SOURCES_ASM:.S=.o))
java_static_ppc_libobjects = $(JAVA_STATIC_C_LIBOBJECTS) $(JAVA_STATIC_ASM_LIBOBJECTS)
jls/util/crc32c_ppc.o: util/crc32c_ppc.c
$(AM_V_CC)$(CC) $(CFLAGS) $(JAVA_STATIC_FLAGS) $(JAVA_STATIC_INCLUDES) -c $< -o $@
jls/util/crc32c_ppc_asm.o: util/crc32c_ppc_asm.S
$(AM_V_CC)$(CC) $(CFLAGS) $(JAVA_STATIC_FLAGS) $(JAVA_STATIC_INCLUDES) -c $< -o $@
java_static_all_libobjects += $(java_static_ppc_libobjects)
endif
$(java_static_libobjects): jls/%.o: %.cc $(JAVA_COMPRESSIONS)
$(AM_V_CC)mkdir -p $(@D) && $(CXX) $(CXXFLAGS) $(JAVA_STATIC_FLAGS) $(JAVA_STATIC_INCLUDES) -fPIC -c $< -o $@ $(COVERAGEFLAGS)
rocksdbjavastatic: $(java_static_libobjects)
rocksdbjavastatic: $(java_static_all_libobjects)
cd java;$(MAKE) javalib;
rm -f ./java/target/$(ROCKSDBJNILIB)
$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC \
-o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) \
$(java_static_libobjects) $(COVERAGEFLAGS) \
$(java_static_all_libobjects) $(COVERAGEFLAGS) \
$(JAVA_COMPRESSIONS) $(JAVA_STATIC_LDFLAGS)
cd java/target;strip $(STRIPFLAGS) $(ROCKSDBJNILIB)
cd java;jar -cf target/$(ROCKSDB_JAR) HISTORY*.md
@@ -1576,18 +1715,26 @@ rocksdbjavastaticrelease: rocksdbjavastatic
rocksdbjavastaticreleasedocker: rocksdbjavastatic
DOCKER_LINUX_X64_CONTAINER=`docker ps -aqf name=rocksdb_linux_x64-be`; \
if [ -z "$$DOCKER_LINUX_X64_CONTAINER" ]; then \
docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos5_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
fi
docker start -a rocksdb_linux_x64-be
DOCKER_LINUX_X86_CONTAINER=`docker ps -aqf name=rocksdb_linux_x86-be`; \
if [ -z "$$DOCKER_LINUX_X86_CONTAINER" ]; then \
docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x86-be evolvedbinary/rocksjava:centos5_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x86-be evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
fi
docker start -a rocksdb_linux_x86-be
cd java;jar -cf target/$(ROCKSDB_JAR_ALL) HISTORY*.md
cd java/target;jar -uf $(ROCKSDB_JAR_ALL) librocksdbjni-*.so librocksdbjni-*.jnilib
cd java/target/classes;jar -uf ../$(ROCKSDB_JAR_ALL) org/rocksdb/*.class org/rocksdb/util/*.class
rocksdbjavastaticdockerppc64le:
mkdir -p java/target
DOCKER_LINUX_PPC64LE_CONTAINER=`docker ps -aqf name=rocksdb_linux_ppc64le-be`; \
if [ -z "$$DOCKER_LINUX_PPC64LE_CONTAINER" ]; then \
docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_ppc64le-be evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
fi
docker start -a rocksdb_linux_ppc64le-be
rocksdbjavastaticpublish: rocksdbjavastaticrelease rocksdbjavastaticpublishcentral
rocksdbjavastaticpublishdocker: rocksdbjavastaticreleasedocker rocksdbjavastaticpublishcentral
@@ -1602,13 +1749,36 @@ rocksdbjavastaticpublishcentral:
mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH).jar
# A version of each $(LIBOBJECTS) compiled with -fPIC
java_libobjects = $(patsubst %,jl/%,$(LIBOBJECTS))
ifeq ($(HAVE_POWER8),1)
JAVA_CC_OBJECTS = $(SHARED_CC_OBJECTS)
JAVA_C_OBJECTS = $(SHARED_C_OBJECTS)
JAVA_ASM_OBJECTS = $(SHARED_ASM_OBJECTS)
JAVA_C_LIBOBJECTS = $(patsubst %.c.o,jl/%.c.o,$(JAVA_C_OBJECTS))
JAVA_ASM_LIBOBJECTS = $(patsubst %.S.o,jl/%.S.o,$(JAVA_ASM_OBJECTS))
endif
java_libobjects = $(patsubst %,jl/%,$(LIB_CC_OBJECTS))
CLEAN_FILES += jl
java_all_libobjects = $(java_libobjects)
ifeq ($(HAVE_POWER8),1)
java_ppc_libobjects = $(JAVA_C_LIBOBJECTS) $(JAVA_ASM_LIBOBJECTS)
jl/crc32c_ppc.o: util/crc32c_ppc.c
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
jl/crc32c_ppc_asm.o: util/crc32c_ppc_asm.S
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
java_all_libobjects += $(java_ppc_libobjects)
endif
$(java_libobjects): jl/%.o: %.cc
$(AM_V_CC)mkdir -p $(@D) && $(CXX) $(CXXFLAGS) -fPIC -c $< -o $@ $(COVERAGEFLAGS)
rocksdbjava: $(java_libobjects)
rocksdbjava: $(java_all_libobjects)
$(AM_V_GEN)cd java;$(MAKE) javalib;
$(AM_V_at)rm -f ./java/target/$(ROCKSDBJNILIB)
$(AM_V_at)$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) $(java_libobjects) $(JAVA_LDFLAGS) $(COVERAGEFLAGS)
@@ -1663,30 +1833,54 @@ IOSVERSION=$(shell defaults read $(PLATFORMSROOT)/iPhoneOS.platform/version CFBu
lipo ios-x86/$@ ios-arm/$@ -create -output $@
else
ifeq ($(HAVE_POWER8),1)
util/crc32c_ppc.o: util/crc32c_ppc.c
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
util/crc32c_ppc_asm.o: util/crc32c_ppc_asm.S
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
endif
.cc.o:
$(AM_V_CC)$(CXX) $(CXXFLAGS) -c $< -o $@ $(COVERAGEFLAGS)
.c.o:
$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
endif
# ---------------------------------------------------------------------------
# Source files dependencies detection
# ---------------------------------------------------------------------------
all_sources = $(LIB_SOURCES) $(MAIN_SOURCES) $(MOCK_LIB_SOURCES) $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(TEST_LIB_SOURCES) $(EXP_LIB_SOURCES)
DEPFILES = $(all_sources:.cc=.d)
DEPFILES = $(all_sources:.cc=.cc.d)
# Add proper dependency support so changing a .h file forces a .cc file to
# rebuild.
# The .d file indicates .cc file's dependencies on .h files. We generate such
# dependency by g++'s -MM option, whose output is a make dependency rule.
$(DEPFILES): %.d: %.cc
%.cc.d: %.cc
@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
-MM -MT'$@' -MT'$(<:.cc=.o)' "$<" -o '$@'
ifeq ($(HAVE_POWER8),1)
DEPFILES_C = $(LIB_SOURCES_C:.c=.c.d)
DEPFILES_ASM = $(LIB_SOURCES_ASM:.S=.S.d)
%.c.d: %.c
@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
-MM -MT'$@' -MT'$(<:.c=.o)' "$<" -o '$@'
%.S.d: %.S
@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
-MM -MT'$@' -MT'$(<:.S=.o)' "$<" -o '$@'
$(DEPFILES_C): %.c.d
$(DEPFILES_ASM): %.S.d
depend: $(DEPFILES) $(DEPFILES_C) $(DEPFILES_ASM)
else
depend: $(DEPFILES)
endif
# if the make goal is either "clean" or "format", we shouldn't
# try to import the *.d files.
-33
View File
@@ -1,33 +0,0 @@
Additional Grant of Patent Rights Version 2
"Software" means the RocksDB software distributed by Facebook, Inc.
Facebook, Inc. ("Facebook") hereby grants to each recipient of the Software
("you") a perpetual, worldwide, royalty-free, non-exclusive, irrevocable
(subject to the termination provision below) license under any Necessary
Claims, to make, have made, use, sell, offer to sell, import, and otherwise
transfer the Software. For avoidance of doubt, no license is granted under
Facebooks rights in any patent claims that are infringed by (i) modifications
to the Software made by you or any third party or (ii) the Software in
combination with any software or other technology.
The license granted hereunder will terminate, automatically and without notice,
if you (or any of your subsidiaries, corporate affiliates or agents) initiate
directly or indirectly, or take a direct financial interest in, any Patent
Assertion: (i) against Facebook or any of its subsidiaries or corporate
affiliates, (ii) against any party if such Patent Assertion arises in whole or
in part from any software, technology, product or service of Facebook or any of
its subsidiaries or corporate affiliates, or (iii) against any party relating
to the Software. Notwithstanding the foregoing, if Facebook or any of its
subsidiaries or corporate affiliates files a lawsuit alleging patent
infringement against you in the first instance, and you respond by filing a
patent infringement counterclaim in that lawsuit against that party that is
unrelated to the Software, the license granted hereunder will not terminate
under section (i) of this paragraph due to such counterclaim.
A "Necessary Claim" is a claim of a patent owned by Facebook that is
necessarily infringed by the Software standing alone.
A "Patent Assertion" is any lawsuit or other action alleging direct, indirect,
or contributory infringement or inducement to infringe any patent, including a
cross-claim or counterclaim.
+3 -2
View File
@@ -1,7 +1,8 @@
## RocksDB: A Persistent Key-Value Store for Flash and RAM Storage
[![Build Status](https://travis-ci.org/facebook/rocksdb.svg?branch=master)](https://travis-ci.org/facebook/rocksdb)
[![Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
[![Linux/Mac Build Status](https://travis-ci.org/facebook/rocksdb.svg?branch=master)](https://travis-ci.org/facebook/rocksdb)
[![Windows Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
[![PPC64le Build Status](http://140.211.168.68:8080/buildStatus/icon?job=Rocksdb)](http://140.211.168.68:8080/job/Rocksdb)
RocksDB is developed and maintained by Facebook Database Engineering Team.
+1014 -434
View File
File diff suppressed because it is too large Load Diff
+13 -5
View File
@@ -5,12 +5,14 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
1. MyRocks -- https://github.com/MySQLOnRocksDB/mysql-5.6
2. MongoRocks -- https://github.com/mongodb-partners/mongo-rocks
3. ZippyDB -- Facebook's distributed key-value store with Paxos-style replication, built on top of RocksDB.[*] https://www.youtube.com/watch?v=DfiN7pG0D0khtt
4. Laser -- Laser is a high query throughput, low (millisecond) latency, key-value storage service built on top of RocksDB.[*]
3. ZippyDB -- Facebook's distributed key-value store with Paxos-style replication, built on top of RocksDB.[1] https://www.youtube.com/watch?v=DfiN7pG0D0khtt
4. Laser -- Laser is a high query throughput, low (millisecond) latency, key-value storage service built on top of RocksDB.[1]
4. Dragon -- a distributed graph query engine. https://code.facebook.com/posts/1737605303120405/dragon-a-distributed-graph-query-engine/
5. Stylus -- a low-level stream processing framework writtenin C++.[*]
5. Stylus -- a low-level stream processing framework writtenin C++.[1]
6. LogDevice -- a distributed data store for logs [2]
[*] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
[1] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
[2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/
## LinkedIn
Two different use cases at Linkedin are using RocksDB as a storage engine:
@@ -76,7 +78,13 @@ quasardb uses a heavily tuned RocksDB as its persistence layer.
[Dgraph](https://github.com/dgraph-io/dgraph) is an open-source, scalable, distributed, low latency, high throughput Graph database .They use RocksDB to store state locally on a machine.
## Uber
[Uber](http://eng.uber.com/cherami/) uses RocksDB as a durable and and scalable task queue.
[Uber](http://eng.uber.com/cherami/) uses RocksDB as a durable and scalable task queue.
## 360 Pika
[360](http://www.360.cn/) [Pika](https://github.com/Qihoo360/pika) is a nosql compatible with redis. With the huge amount of data stored, redis may suffer for a capacity bottleneck, and pika was born for solving it. It has widely been widely used in many company
## LzLabs
LzLabs is using RocksDB as a storage engine in their multi-database distributed framework to store application configuration and user data.
## ProfaneDB
[ProfaneDB](https://profanedb.gitlab.io/) is a database for Protocol Buffers, and uses RocksDB for storage. It is accessible via gRPC, and the schema is defined using directly `.proto` files.
+3 -3
View File
@@ -1,14 +1,14 @@
version: 1.0.{build}
image: Visual Studio 2015
image: Visual Studio 2017
before_build:
- md %APPVEYOR_BUILD_FOLDER%\build
- cd %APPVEYOR_BUILD_FOLDER%\build
- cmake -G "Visual Studio 14 2015 Win64" -DOPTDBG=1 -DXPRESS=1 ..
- cmake -G "Visual Studio 15 Win64" -DOPTDBG=1 -DWITH_XPRESS=1 -DPORTABLE=1 ..
- cd ..
build:
project: build\rocksdb.sln
parallel: true
verbosity: minimal
verbosity: normal
test:
test_script:
- ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test -Concurrency 8
@@ -1,3 +0,0 @@
<?php
phutil_register_library('arcanist_util', __FILE__);
-71
View File
@@ -1,71 +0,0 @@
<?php
/**
* This file is automatically generated. Use 'arc liberate' to rebuild it.
* @generated
* @phutil-library-version 2
*/
if (class_exists('ArcanistWorkflow')) {
phutil_register_library_map(array(
'__library_version__' => 2,
'class' =>
array(
'ArcanistCpplintLinter' => 'cpp_linter/ArcanistCpplintLinter.php',
'BaseDirectoryScopedFormatLinter' => 'cpp_linter/BaseDirectoryScopedFormatLinter.php',
'FacebookArcanistConfiguration' => 'config/FacebookArcanistConfiguration.php',
'FacebookFbcodeLintEngine' => 'lint_engine/FacebookFbcodeLintEngine.php',
'FacebookFbcodeUnitTestEngine' => 'unit_engine/FacebookFbcodeUnitTestEngine.php',
'FacebookHowtoevenLintEngine' => 'lint_engine/FacebookHowtoevenLintEngine.php',
'FacebookHowtoevenLinter' => 'cpp_linter/FacebookHowtoevenLinter.php',
'FbcodeClangFormatLinter' => 'cpp_linter/FbcodeClangFormatLinter.php',
'FbcodeCppLinter' => 'cpp_linter/FbcodeCppLinter.php',
),
'function' =>
array(
),
'xmap' =>
array(
'ArcanistCpplintLinter' => 'ArcanistLinter',
'BaseDirectoryScopedFormatLinter' => 'ArcanistLinter',
'FacebookArcanistConfiguration' => 'ArcanistConfiguration',
'FacebookFbcodeLintEngine' => 'ArcanistLintEngine',
'FacebookFbcodeUnitTestEngine' => 'ArcanistBaseUnitTestEngine',
'FacebookHowtoevenLintEngine' => 'ArcanistLintEngine',
'FacebookHowtoevenLinter' => 'ArcanistLinter',
'FbcodeClangFormatLinter' => 'BaseDirectoryScopedFormatLinter',
'FbcodeCppLinter' => 'ArcanistLinter',
),
));
} else {
phutil_register_library_map(array(
'__library_version__' => 2,
'class' =>
array(
'ArcanistCpplintLinter' => 'cpp_linter/ArcanistCpplintLinter.php',
'BaseDirectoryScopedFormatLinter' => 'cpp_linter/BaseDirectoryScopedFormatLinter.php',
'FacebookArcanistConfiguration' => 'config/FacebookOldArcanistConfiguration.php',
'FacebookFbcodeLintEngine' => 'lint_engine/FacebookFbcodeLintEngine.php',
'FacebookFbcodeUnitTestEngine' => 'unit_engine/FacebookOldFbcodeUnitTestEngine.php',
'FacebookHowtoevenLintEngine' => 'lint_engine/FacebookHowtoevenLintEngine.php',
'FacebookHowtoevenLinter' => 'cpp_linter/FacebookHowtoevenLinter.php',
'FbcodeClangFormatLinter' => 'cpp_linter/FbcodeClangFormatLinter.php',
'FbcodeCppLinter' => 'cpp_linter/FbcodeCppLinter.php',
),
'function' =>
array(
),
'xmap' =>
array(
'ArcanistCpplintLinter' => 'ArcanistLinter',
'BaseDirectoryScopedFormatLinter' => 'ArcanistLinter',
'FacebookArcanistConfiguration' => 'ArcanistConfiguration',
'FacebookFbcodeLintEngine' => 'ArcanistLintEngine',
'FacebookFbcodeUnitTestEngine' => 'ArcanistBaseUnitTestEngine',
'FacebookHowtoevenLintEngine' => 'ArcanistLintEngine',
'FacebookHowtoevenLinter' => 'ArcanistLinter',
'FbcodeClangFormatLinter' => 'BaseDirectoryScopedFormatLinter',
'FbcodeCppLinter' => 'ArcanistLinter',
),
));
}
@@ -1,43 +0,0 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
require('RocksDBCommonHelper.php');
define("DIFF_COMMAND", "diff");
class FacebookArcanistConfiguration extends ArcanistConfiguration {
public function getCustomArgumentsForCommand($command) {
if ($command == "land") {
return array(
'async' => array('help' => 'Just to make tools happy'));
}
return array();
}
public function didRunWorkflow($command,
ArcanistWorkflow $workflow,
$error_code) {
// Default options don't terminate on failure, but that's what we want. In
// the current case we use assertions intentionally as "terminate on failure
// invariants".
assert_options(ASSERT_BAIL, true);
assert($workflow);
assert(strlen($command) > 0);
if ($command == DIFF_COMMAND && !$workflow->isRawDiffSource()) {
$diffID = $workflow->getDiffId();
// When submitting a diff this code path gets executed multiple times in
// a row. We only care about the case when ID for the diff is provided
// because that's what we need to apply the diff and trigger the tests.
if (strlen($diffID) > 0) {
assert(is_numeric($diffID));
startTestsInSandcastle(true /* $applyDiff */, $workflow, $diffID);
}
}
}
}
@@ -1,43 +0,0 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
require('RocksDBCommonHelper.php');
define("DIFF_COMMAND", "diff");
class FacebookArcanistConfiguration extends ArcanistConfiguration {
public function getCustomArgumentsForCommand($command) {
if ($command == "land") {
return array(
'async' => array('help' => 'Just to make tools happy'));
}
return array();
}
public function didRunWorkflow($command,
ArcanistBaseWorkflow $workflow,
$error_code) {
// Default options don't terminate on failure, but that's what we want. In
// the current case we use assertions intentionally as "terminate on failure
// invariants".
assert_options(ASSERT_BAIL, true);
assert($workflow);
assert(strlen($command) > 0);
if ($command == DIFF_COMMAND && !$workflow->isRawDiffSource()) {
$diffID = $workflow->getDiffId();
// When submitting a diff this code path gets executed multiple times in
// a row. We only care about the case when ID for the diff is provided
// because that's what we need to apply the diff and trigger the tests.
if (strlen($diffID) > 0) {
assert(is_numeric($diffID));
startTestsInSandcastle(true /* $applyDiff */, $workflow, $diffID);
}
}
}
}
@@ -1,88 +0,0 @@
<?php
/**
* Uses google's cpplint.py to check code. RocksDB team forked this file from
* phabricator's /src/lint/linter/ArcanistCpplintLinter.php, and customized it
* for its own use.
*
* You can get it here:
* http://google-styleguide.googlecode.com/svn/trunk/cpplint/cpplint.py
* @group linter
*/
final class ArcanistCpplintLinter extends ArcanistLinter {
public function willLintPaths(array $paths) {
return;
}
public function getLinterName() {
return 'cpplint.py';
}
public function getLintPath() {
$bin = 'cpplint.py';
// Search under current dir
list($err) = exec_manual('which %s/%s', $this->linterDir(), $bin);
if (!$err) {
return $this->linterDir().'/'.$bin;
}
// Look for globally installed cpplint.py
list($err) = exec_manual('which %s', $bin);
if ($err) {
throw new ArcanistUsageException(
"cpplint.py does not appear to be installed on this system. Install ".
"it (e.g., with 'wget \"http://google-styleguide.googlecode.com/".
"svn/trunk/cpplint/cpplint.py\"') ".
"in your .arcconfig to point to the directory where it resides. ".
"Also don't forget to chmod a+x cpplint.py!");
}
return $bin;
}
public function lintPath($path) {
$bin = $this->getLintPath();
$path = $this->rocksdbDir().'/'.$path;
$f = new ExecFuture("%C $path", $bin);
list($err, $stdout, $stderr) = $f->resolve();
if ($err === 2) {
throw new Exception("cpplint failed to run correctly:\n".$stderr);
}
$lines = explode("\n", $stderr);
$messages = array();
foreach ($lines as $line) {
$line = trim($line);
$matches = null;
$regex = '/^[^:]+:(\d+):\s*(.*)\s*\[(.*)\] \[(\d+)\]$/';
if (!preg_match($regex, $line, $matches)) {
continue;
}
foreach ($matches as $key => $match) {
$matches[$key] = trim($match);
}
$message = new ArcanistLintMessage();
$message->setPath($path);
$message->setLine($matches[1]);
$message->setCode($matches[3]);
$message->setName($matches[3]);
$message->setDescription($matches[2]);
$message->setSeverity(ArcanistLintSeverity::SEVERITY_WARNING);
$this->addLintMessage($message);
}
}
// The path of this linter
private function linterDir() {
return dirname(__FILE__);
}
// TODO(kaili) a quick and dirty way to figure out rocksdb's root dir.
private function rocksdbDir() {
return $this->linterDir()."/../..";
}
}
@@ -1,74 +0,0 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
abstract class BaseDirectoryScopedFormatLinter extends ArcanistLinter {
const LINT_FORMATTING = 1;
private $changedLines = array();
private $rawLintOutput = array();
abstract protected function getPathsToLint();
protected function shouldLintPath($path) {
foreach ($this->getPathsToLint() as $p) {
// check if $path starts with $p
if (strncmp($path, $p, strlen($p)) === 0) {
return true;
}
}
return false;
}
// API to tell this linter which lines were changed
final public function setPathChangedLines($path, $changed) {
$this->changedLines[$path] = $changed;
}
final public function willLintPaths(array $paths) {
$futures = array();
foreach ($paths as $path) {
if (!$this->shouldLintPath($path)) {
continue;
}
$changed = $this->changedLines[$path];
if (!isset($changed)) {
// do not run linter if there are no changes
continue;
}
$futures[$path] = $this->getFormatFuture($path, $changed);
}
foreach (id(new FutureIterator($futures))->limit(8) as $p => $f) {
$this->rawLintOutput[$p] = $f->resolvex();
}
}
abstract protected function getFormatFuture($path, array $changed);
abstract protected function getLintMessage($diff);
final public function lintPath($path) {
if (!isset($this->rawLintOutput[$path])) {
return;
}
list($new_content) = $this->rawLintOutput[$path];
$old_content = $this->getData($path);
if ($new_content != $old_content) {
$diff = ArcanistDiffUtils::renderDifferences($old_content, $new_content);
$this->raiseLintAtOffset(
0,
self::LINT_FORMATTING,
$this->getLintMessage($diff),
$old_content,
$new_content);
}
}
}
@@ -1,223 +0,0 @@
<?php
// Copyright 2015-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
final class FacebookHowtoevenLinter extends ArcanistLinter {
const VERSION = 'fd9192f324c36d28136d14380f0b552a1385b59b';
private $parsedTargets = array();
public function getLinterName() {
return 'Howtoeven';
}
protected function getSeverity($code) {
$severities = array(
ArcanistLintSeverity::SEVERITY_DISABLED,
ArcanistLintSeverity::SEVERITY_ADVICE,
ArcanistLintSeverity::SEVERITY_WARNING,
ArcanistLintSeverity::SEVERITY_ERROR,
);
return idx($severities, $code, ArcanistLintSeverity::SEVERITY_WARNING);
}
public function willLintPaths(array $paths) {
// Cleanup previous runs.
$this->localExecx("rm -rf _build/_lint");
// Build compilation database.
$lintable_paths = $this->getLintablePaths($paths);
$interesting_paths = $this->getInterestingPaths($lintable_paths);
if (!$lintable_paths) {
return;
}
// Run lint.
try {
$this->localExecx(
"%C %C -p _build/dev/ %Ls",
$this->getBinaryPath(),
$this->getFilteredIssues(),
$lintable_paths);
} catch (CommandException $exception) {
PhutilConsole::getConsole()->writeErr($exception->getMessage());
}
// Load results.
$result = id(
new SQLite3(
$this->getProjectRoot().'/_build/_lint/lint.db',
SQLITE3_OPEN_READONLY))
->query("SELECT * FROM raised_issues");
while ($issue = $result->fetchArray(SQLITE3_ASSOC)) {
// Skip issues not part of the linted file.
if (in_array($issue['file'], $interesting_paths)) {
$this->addLintMessage(id(new ArcanistLintMessage())
->setPath($issue['file'])
->setLine($issue['line'])
->setChar($issue['column'])
->setCode('Howtoeven')
->setSeverity($this->getSeverity($issue['severity']))
->setName('Hte-'.$issue['name'])
->setDescription(
sprintf(
"%s\n\n%s",
($issue['message']) ? $issue['message'] : $issue['description'],
$issue['explanation']))
->setOriginalText(idx($issue, 'original', ''))
->setReplacementText(idx($issue, 'replacement', '')));
}
}
}
public function lintPath($path) {
}
/**
* Get the paths that we know how to lint.
*
* The strategy is to first look whether there's an existing compilation
* database and use that if it's exhaustive. We generate our own only if
* necessary.
*/
private function getLintablePaths($paths) {
// Replace headers with existing sources.
for ($i = 0; $i < count($paths); $i++) {
if (preg_match("/\.h$/", $paths[$i])) {
$header = preg_replace("/\.h$/", ".cpp", $paths[$i]);
if (file_exists($header)) {
$paths[$i] = $header;
}
}
}
// Check if database exists and is exhaustive.
$available_paths = $this->getAvailablePaths();
$lintable_paths = array_intersect($paths, $available_paths);
if ($paths === $lintable_paths) {
return $lintable_paths;
}
// Generate our own database.
$targets = $this->getTargetsFor($paths);
if (!$targets) {
PhutilConsole::getConsole()->writeErr(
"No build targets found for %s\n",
implode(', ', $paths));
return array();
}
$this->localExecx("./tools/build/bin/fbconfig.par -r %Ls", $targets);
$this->localExecx("./tools/build/bin/fbmake.par gen_cdb");
$available_paths = $this->getAvailablePaths();
$lintable_paths = array_intersect($paths, $available_paths);
if ($paths != $lintable_paths) {
PhutilConsole::getConsole()->writeErr(
"Can't lint %s\n",
implode(', ', array_diff($paths, $available_paths)));
}
// Return what we know how to lint.
return $lintable_paths;
}
/**
* Get the available paths in the current compilation database.
*/
private function getAvailablePaths() {
$database_path = $this->getProjectRoot()
.'/_build/dev/compile_commands.json';
if (!file_exists($database_path)) {
return array();
}
$entries = json_decode(file_get_contents($database_path), true);
$paths = array();
foreach ($entries as $entry) {
$paths[] = $entry['file'];
}
return $paths;
}
/**
* Search for the targets directories for the given files.
*/
private static function getTargetsFor($paths) {
$targets = array();
foreach ($paths as $path) {
while (($path = dirname($path)) !== '.') {
if (in_array('TARGETS', scandir($path))) {
$contents = file_get_contents($path.'/TARGETS');
if (strpos($contents, 'cpp_binary') !== false) {
$targets[] = $path;
break;
}
}
}
}
return array_unique($targets);
}
/**
* The paths that we actually want to report on.
*/
private function getInterestingPaths($paths) {
$headers = array();
foreach ($paths as $path) {
$headers[] = preg_replace("/\.cpp$/", ".h", $path);
}
return array_merge($paths, $headers);
}
/**
* The path where the binary is located. Will return the current dewey binary
* unless the `HOWTOEVEN_BUILD` environment variable is set.
*/
private function getBinaryPath() {
$path = sprintf(
"/mnt/dewey/fbcode/.commits/%s/builds/howtoeven/client",
self::VERSION);
$build = getenv('HOWTOEVEN_BUILD');
if ($build) {
$path = sprintf(
"./_build/%s/tools/howtoeven/client",
$build);
if (!file_exists($path)) {
PhutilConsole::getConsole()->writeErr(">> %s does not exist\n", $path);
exit(1);
}
}
return $path;
}
/**
* Execute the command in the root directory.
*/
private function localExecx($command /* , ... */) {
$arguments = func_get_args();
return newv('ExecFuture', $arguments)
->setCWD($this->getProjectRoot())
->resolvex();
}
/**
* The root of the project.
*/
private function getProjectRoot() {
return $this->getEngine()->getWorkingCopy()->getProjectRoot();
}
private function getFilteredIssues() {
$issues = getenv('HOWTOEVEN_ISSUES');
return ($issues) ? csprintf('-issues %s', $issues) : '';
}
}
@@ -1,58 +0,0 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
final class FbcodeClangFormatLinter extends BaseDirectoryScopedFormatLinter {
const LINT_FORMATTING = 1;
const CLANG_FORMAT_BINARY = '/mnt/vol/engshare/admin/scripts/clang-format';
protected function getPathsToLint() {
return array('');
}
public function getLinterName() {
return 'CLANG_FORMAT';
}
public function getLintSeverityMap() {
return array(
self::LINT_FORMATTING => ArcanistLintSeverity::SEVERITY_ADVICE,
);
}
public function getLintNameMap() {
return array(
self::LINT_FORMATTING => pht('Changes are not clang-formatted'),
);
}
protected function getFormatFuture($path, array $changed) {
$args = "";
foreach ($changed as $key => $value) {
$args .= " --lines=$key:$key";
}
$binary = self::CLANG_FORMAT_BINARY;
if (!file_exists($binary)) {
// trust the $PATH
$binary = "clang-format";
}
return new ExecFuture(
"%s %s $args",
$binary,
$this->getEngine()->getFilePathOnDisk($path));
}
protected function getLintMessage($diff) {
$link_to_clang_format =
"[[ http://fburl.com/clang-format | clang-format ]]";
return <<<LINT_MSG
Changes in this file were not formatted using $link_to_clang_format.
Please run build_tools/format-diff.sh or `make format`
LINT_MSG;
}
}
@@ -1,126 +0,0 @@
<?php
// Copyright 2004-present Facebook. All rights reserved.
class FbcodeCppLinter extends ArcanistLinter {
const FLINT = "/home/engshare/tools/flint";
const LINT_ERROR = 1;
const LINT_WARNING = 2;
const LINT_ADVICE = 3;
const C_FLAG = "--c_mode=true";
private $rawLintOutput = array();
public function willLintPaths(array $paths) {
if (!file_exists(self::FLINT)) {
return;
}
$futures = array();
foreach ($paths as $p) {
$lpath = $this->getEngine()->getFilePathOnDisk($p);
$lpath_file = file($lpath);
if (preg_match('/\.(c)$/', $lpath) ||
preg_match('/-\*-.*Mode: C[; ].*-\*-/', $lpath_file[0]) ||
preg_match('/vim(:.*)*:\s*(set\s+)?filetype=c\s*:/', $lpath_file[0])
) {
$futures[$p] = new ExecFuture("%s %s %s 2>&1",
self::FLINT, self::C_FLAG,
$this->getEngine()->getFilePathOnDisk($p));
} else {
$futures[$p] = new ExecFuture("%s %s 2>&1",
self::FLINT, $this->getEngine()->getFilePathOnDisk($p));
}
}
foreach (Futures($futures)->limit(8) as $p => $f) {
$this->rawLintOutput[$p] = $f->resolvex();
}
return;
}
public function getLinterName() {
return "FBCPP";
}
public function lintPath($path) {
$this->runCppLint($path);
}
private function runCppLint($path) {
$msgs = $this->getCppLintOutput($path);
foreach ($msgs as $m) {
$this->raiseLintAtLine($m['line'], 0, $m['severity'], $m['msg']);
}
}
private function adviseOnEachPattern(
$path,
$regex,
$message,
$lint_type = self::LINT_ADVICE,
$match_idx = 0) {
$file_data = $this->getData($path);
$matches = array();
if (!preg_match_all($regex, $file_data, $matches, PREG_OFFSET_CAPTURE)) {
return;
}
foreach ($matches[$match_idx] as $match) {
list($match_str, $offset) = $match;
$this->raiseLintAtOffset($offset, $lint_type, $message, $match_str);
}
}
public function getLintSeverityMap() {
return array(
self::LINT_WARNING => ArcanistLintSeverity::SEVERITY_WARNING,
self::LINT_ADVICE => ArcanistLintSeverity::SEVERITY_ADVICE,
self::LINT_ERROR => ArcanistLintSeverity::SEVERITY_ERROR
);
}
public function getLintNameMap() {
return array(
self::LINT_ADVICE => "CppLint Advice",
self::LINT_WARNING => "CppLint Warning",
self::LINT_ERROR => "CppLint Error"
);
}
private function getCppLintOutput($path) {
if (!array_key_exists($path, $this->rawLintOutput)) {
return array();
}
list($output) = $this->rawLintOutput[$path];
$msgs = array();
$current = null;
$matches = array();
foreach (explode("\n", $output) as $line) {
if (preg_match('/.*?:(\d+):(.*)/', $line, $matches)) {
if ($current) {
$msgs[] = $current;
}
$line = $matches[1];
$text = $matches[2];
if (preg_match('/.*Warning.*/', $text)) {
$sev = self::LINT_WARNING;
} else if (preg_match('/.*Advice.*/', $text)) {
$sev = self::LINT_ADVICE;
} else {
$sev = self::LINT_ERROR;
}
$current = array('line' => $line,
'msg' => $text,
'severity' => $sev);
} else if ($current) {
$current['msg'] .= ' ' . $line;
}
}
if ($current) {
$msgs[] = $current;
}
return $msgs;
}
}
File diff suppressed because it is too large Load Diff
@@ -1,138 +0,0 @@
<?php
// Copyright 2004-present Facebook. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
class FacebookFbcodeLintEngine extends ArcanistLintEngine {
public function buildLinters() {
$linters = array();
$paths = $this->getPaths();
// Remove all deleted files, which are not checked by the
// following linters.
foreach ($paths as $key => $path) {
if (!Filesystem::pathExists($this->getFilePathOnDisk($path))) {
unset($paths[$key]);
}
}
$generated_linter = new ArcanistGeneratedLinter();
$linters[] = $generated_linter;
$nolint_linter = new ArcanistNoLintLinter();
$linters[] = $nolint_linter;
$text_linter = new ArcanistTextLinter();
$text_linter->setCustomSeverityMap(array(
ArcanistTextLinter::LINT_LINE_WRAP
=> ArcanistLintSeverity::SEVERITY_ADVICE,
));
$linters[] = $text_linter;
$java_text_linter = new ArcanistTextLinter();
$java_text_linter->setMaxLineLength(100);
$java_text_linter->setCustomSeverityMap(array(
ArcanistTextLinter::LINT_LINE_WRAP
=> ArcanistLintSeverity::SEVERITY_ADVICE,
));
$linters[] = $java_text_linter;
$python_linter = new ArcanistPEP8Linter();
$linters[] = $python_linter;
$cpp_linters = array();
$cpp_linters[] = $linters[] = new ArcanistCpplintLinter();
$cpp_linters[] = $linters[] = new FbcodeCppLinter();
$clang_format_linter = new FbcodeClangFormatLinter();
$linters[] = $clang_format_linter;
$spelling_linter = new ArcanistSpellingLinter();
$linters[] = $spelling_linter;
foreach ($paths as $path) {
$is_text = false;
$text_extensions = (
'/\.('.
'cpp|cxx|c|cc|h|hpp|hxx|tcc|'.
'py|rb|hs|pl|pm|tw|'.
'php|phpt|css|js|'.
'java|'.
'thrift|'.
'lua|'.
'siv|'.
'txt'.
')$/'
);
if (preg_match($text_extensions, $path)) {
$is_text = true;
}
if ($is_text) {
$nolint_linter->addPath($path);
$generated_linter->addPath($path);
$generated_linter->addData($path, $this->loadData($path));
if (preg_match('/\.java$/', $path)) {
$java_text_linter->addPath($path);
$java_text_linter->addData($path, $this->loadData($path));
} else {
$text_linter->addPath($path);
$text_linter->addData($path, $this->loadData($path));
}
$spelling_linter->addPath($path);
$spelling_linter->addData($path, $this->loadData($path));
}
if (preg_match('/\.(cpp|c|cc|cxx|h|hh|hpp|hxx|tcc)$/', $path)
&& !preg_match('/third-party/', $path)) {
foreach ($cpp_linters as &$linter) {
$linter->addPath($path);
$linter->addData($path, $this->loadData($path));
}
$clang_format_linter->addPath($path);
$clang_format_linter->addData($path, $this->loadData($path));
$clang_format_linter->setPathChangedLines(
$path, $this->getPathChangedLines($path));
}
// Match *.py and contbuild config files
if (preg_match('/(\.(py|tw|smcprops)|^contbuild\/configs\/[^\/]*)$/',
$path)) {
$space_count = 4;
$real_path = $this->getFilePathOnDisk($path);
$dir = dirname($real_path);
do {
if (file_exists($dir.'/.python2space')) {
$space_count = 2;
break;
}
$dir = dirname($dir);
} while ($dir != '/' && $dir != '.');
$cur_path_linter = $python_linter;
$cur_path_linter->addPath($path);
$cur_path_linter->addData($path, $this->loadData($path));
if (preg_match('/\.tw$/', $path)) {
$cur_path_linter->setCustomSeverityMap(array(
'E251' => ArcanistLintSeverity::SEVERITY_DISABLED,
));
}
}
}
$name_linter = new ArcanistFilenameLinter();
$linters[] = $name_linter;
foreach ($paths as $path) {
$name_linter->addPath($path);
}
return $linters;
}
}
@@ -1,27 +0,0 @@
<?php
// Copyright 2015-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
final class FacebookHowtoevenLintEngine extends ArcanistLintEngine {
public function buildLinters() {
$paths = array();
foreach ($this->getPaths() as $path) {
// Don't try to lint deleted files or changed directories.
if (!Filesystem::pathExists($path) || is_dir($path)) {
continue;
}
if (preg_match('/\.(cpp|c|cc|cxx|h|hh|hpp|hxx|tcc)$/', $path)) {
$paths[] = $path;
}
}
$howtoeven = new FacebookHowtoevenLinter();
$howtoeven->setPaths($paths);
return array($howtoeven);
}
}
@@ -1,17 +0,0 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
class FacebookFbcodeUnitTestEngine extends ArcanistUnitTestEngine {
public function run() {
// For a call to `arc call-conduit differential.updateunitresults` to
// succeed we need at least one entry here.
$result = new ArcanistUnitTestResult();
$result->setName("dummy_placeholder_entry");
$result->setResult(ArcanistUnitTestResult::RESULT_PASS);
return array($result);
}
}
@@ -1,17 +0,0 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
class FacebookFbcodeUnitTestEngine extends ArcanistBaseUnitTestEngine {
public function run() {
// For a call to `arc call-conduit differential.updateunitresults` to
// succeed we need at least one entry here.
$result = new ArcanistUnitTestResult();
$result->setName("dummy_placeholder_entry");
$result->setResult(ArcanistUnitTestResult::RESULT_PASS);
return array($result);
}
}
+3 -3
View File
@@ -36,7 +36,7 @@ def parse_src_mk(repo_path):
# get all .cc / .c files
def get_cc_files(repo_path):
cc_files = []
for root, dirnames, filenames in os.walk(repo_path):
for root, dirnames, filenames in os.walk(repo_path): # noqa: B007 T25377293 Grandfathered in
root = root[(len(repo_path) + 1):]
if "java" in root:
# Skip java
@@ -84,7 +84,7 @@ def get_tests(repo_path):
else:
# we consumed all the parallel tests
break
return tests
@@ -122,7 +122,7 @@ def generate_targets(repo_path):
[":rocksdb_lib"])
# test for every test we found in the Makefile
for test in tests:
for test in sorted(tests):
match_src = [src for src in cc_files if ("/%s.c" % test) in src]
if len(match_src) == 0:
print(ColorString.warning("Cannot find .cc file for %s" % test))
+2 -1
View File
@@ -1,4 +1,5 @@
#!/bin/bash
#!/usr/bin/env bash
# Create a tmp directory for the test to use
TEST_DIR=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
# shellcheck disable=SC2068
TEST_TMPDIR="$TEST_DIR" $@ && rm -rf "$TEST_DIR"
+12 -14
View File
@@ -3,19 +3,17 @@ from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
import targets_cfg
import pprint
# TODO(tec): replace this with PrettyPrinter
def pretty_list(lst, indent=6):
def pretty_list(lst, indent=8):
if lst is None or len(lst) == 0:
return ""
if len(lst) == 1:
return "\"%s\"" % lst[0]
separator = "\",\n%s\"" % (" " * indent)
res = separator.join(lst)
res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 2))
res = separator.join(sorted(lst))
res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 4))
return res
@@ -27,7 +25,7 @@ class TARGETSBuilder:
self.total_lib = 0
self.total_bin = 0
self.total_test = 0
self.tests_cfg = []
self.tests_cfg = ""
def __del__(self):
self.targets_file.close()
@@ -37,8 +35,8 @@ class TARGETSBuilder:
headers = "AutoHeaders.RECURSIVE_GLOB"
self.targets_file.write(targets_cfg.library_template % (
name,
headers,
pretty_list(srcs),
headers,
pretty_list(deps)))
self.total_lib = self.total_lib + 1
@@ -53,13 +51,13 @@ class TARGETSBuilder:
exec_mode = "serial"
if is_parallel:
exec_mode = "parallel"
self.tests_cfg.append([test_name, str(src), str(exec_mode)])
self.tests_cfg += targets_cfg.test_cfg_template % (
test_name,
str(src),
str(exec_mode))
self.total_test = self.total_test + 1
def flush_tests(self):
self.targets_file.write(targets_cfg.unittests_template % (
pprint.PrettyPrinter().pformat(self.tests_cfg)
))
self.tests_cfg = []
self.targets_file.write(targets_cfg.unittests_template % self.tests_cfg)
self.tests_cfg = ""
+94 -64
View File
@@ -2,111 +2,141 @@ from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
rocksdb_target_header = """REPO_PATH = "internal_repo_rocksdb/repo/"
rocksdb_target_header = """REPO_PATH = package_name() + "/"
BUCK_BINS = "buck-out/gen/" + REPO_PATH
TEST_RUNNER = REPO_PATH + "buckifier/rocks_test_runner.sh"
rocksdb_compiler_flags = [
"-msse",
"-msse4.2",
"-fno-builtin-memcmp",
"-DROCKSDB_PLATFORM_POSIX",
"-DROCKSDB_LIB_IO_POSIX",
"-DROCKSDB_FALLOCATE_PRESENT",
"-DROCKSDB_MALLOC_USABLE_SIZE",
"-DOS_LINUX",
# Flags to enable libs we include
"-DSNAPPY",
"-DZLIB",
"-DBZIP2",
"-DLZ4",
"-DZSTD",
"-DGFLAGS=gflags",
"-DNUMA",
"-DTBB",
# Needed to compile in fbcode
"-Wno-expansion-to-defined",
"-fno-builtin-memcmp",
"-DROCKSDB_PLATFORM_POSIX",
"-DROCKSDB_LIB_IO_POSIX",
"-DROCKSDB_FALLOCATE_PRESENT",
"-DROCKSDB_MALLOC_USABLE_SIZE",
"-DROCKSDB_RANGESYNC_PRESENT",
"-DROCKSDB_SCHED_GETCPU_PRESENT",
"-DROCKSDB_SUPPORT_THREAD_LOCAL",
"-DOS_LINUX",
# Flags to enable libs we include
"-DSNAPPY",
"-DZLIB",
"-DBZIP2",
"-DLZ4",
"-DZSTD",
"-DGFLAGS=gflags",
"-DNUMA",
"-DTBB",
# Needed to compile in fbcode
"-Wno-expansion-to-defined",
]
rocksdb_external_deps = [
('bzip2', None, 'bz2'),
('snappy', None, "snappy"),
('zlib', None, 'z'),
('gflags', None, 'gflags'),
('lz4', None, 'lz4'),
('zstd', None),
('tbb', None),
("numa", "2.0.8", "numa"),
("googletest", None, "gtest"),
("bzip2", None, "bz2"),
("snappy", None, "snappy"),
("zlib", None, "z"),
("gflags", None, "gflags"),
("lz4", None, "lz4"),
("zstd", None),
("tbb", None),
("numa", None, "numa"),
("googletest", None, "gtest"),
]
rocksdb_preprocessor_flags = [
# Directories with files for #include
"-I" + REPO_PATH + "include/",
"-I" + REPO_PATH,
# Directories with files for #include
"-I" + REPO_PATH + "include/",
"-I" + REPO_PATH,
]
rocksdb_arch_preprocessor_flags = {
"x86_64": ["-DHAVE_SSE42"],
}
build_mode = read_config("fbcode", "build_mode")
is_opt_mode = build_mode.startswith("opt")
# -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
# doesn't harm and avoid forgetting to add it.
if is_opt_mode:
rocksdb_compiler_flags.append("-DNDEBUG")
"""
library_template = """
cpp_library(
name = "%s",
headers = %s,
srcs = [%s],
deps = [%s],
preprocessor_flags = rocksdb_preprocessor_flags,
headers = %s,
arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
compiler_flags = rocksdb_compiler_flags,
preprocessor_flags = rocksdb_preprocessor_flags,
deps = [%s],
external_deps = rocksdb_external_deps,
)
"""
binary_template = """
cpp_binary(
name = "%s",
srcs = [%s],
deps = [%s],
preprocessor_flags = rocksdb_preprocessor_flags,
compiler_flags = rocksdb_compiler_flags,
external_deps = rocksdb_external_deps,
name = "%s",
srcs = [%s],
arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
compiler_flags = rocksdb_compiler_flags,
preprocessor_flags = rocksdb_preprocessor_flags,
deps = [%s],
external_deps = rocksdb_external_deps,
)
"""
test_cfg_template = """ [
"%s",
"%s",
"%s",
],
"""
unittests_template = """
# [test_name, test_src, test_type]
ROCKS_TESTS = %s
ROCKS_TESTS = [
%s]
# Generate a test rule for each entry in ROCKS_TESTS
for test_cfg in ROCKS_TESTS:
test_name = test_cfg[0]
test_cc = test_cfg[1]
ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
test_bin = test_name + "_bin"
# Do not build the tests in opt mode, since SyncPoint and other test code
# will not be included.
if not is_opt_mode:
for test_cfg in ROCKS_TESTS:
test_name = test_cfg[0]
test_cc = test_cfg[1]
ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
test_bin = test_name + "_bin"
cpp_binary (
name = test_bin,
srcs = [test_cc],
deps = [":rocksdb_test_lib"],
preprocessor_flags = rocksdb_preprocessor_flags,
compiler_flags = rocksdb_compiler_flags,
external_deps = rocksdb_external_deps,
)
cpp_binary (
name = test_bin,
srcs = [test_cc],
deps = [":rocksdb_test_lib"],
preprocessor_flags = rocksdb_preprocessor_flags,
arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
compiler_flags = rocksdb_compiler_flags,
external_deps = rocksdb_external_deps,
)
custom_unittest(
name = test_name,
type = ttype,
deps = [":" + test_bin],
command = [TEST_RUNNER, BUCK_BINS + test_bin]
)
custom_unittest(
name = test_name,
type = ttype,
deps = [":" + test_bin],
command = [TEST_RUNNER, BUCK_BINS + test_bin]
)
custom_unittest(
name = "make_rocksdbjavastatic",
type = "simple",
command = ["internal_repo_rocksdb/make_rocksdbjavastatic.sh"],
type = "simple",
)
custom_unittest(
name = "make_rocksdb_lite_release",
type = "simple",
command = ["internal_repo_rocksdb/make_rocksdb_lite_release.sh"],
type = "simple",
)
"""
@@ -1,8 +1,8 @@
<?php
// Copyright 2004-present Facebook. All Rights Reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
// Name of the environment variables which need to be set by the entity which
// triggers continuous runs so that code at the end of the file gets executed
@@ -21,11 +21,17 @@ function postURL($diffID, $url) {
assert(is_numeric($diffID));
assert(strlen($url) > 0);
$cmd = 'echo \'{"diff_id": ' . $diffID . ', '
. '"name":"click here for sandcastle tests for D' . $diffID . '", '
. '"link":"' . $url . '"}\' | '
. 'arc call-conduit '
. 'differential.updateunitresults';
$cmd_args = array(
'diff_id' => (int)$diffID,
'name' => sprintf(
'click here for sandcastle tests for D%d',
(int)$diffID
),
'link' => $url
);
$cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
. ' | arc call-conduit differential.updateunitresults';
shell_exec($cmd);
}
@@ -35,11 +41,15 @@ function buildUpdateTestStatusCmd($diffID, $test, $status) {
assert(strlen($test) > 0);
assert(strlen($status) > 0);
$cmd = 'echo \'{"diff_id": ' . $diffID . ', '
. '"name":"' . $test . '", '
. '"result":"' . $status . '"}\' | '
. 'arc call-conduit '
. 'differential.updateunitresults';
$cmd_args = array(
'diff_id' => (int)$diffID,
'name' => $test,
'result' => $status
);
$cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
. ' | arc call-conduit differential.updateunitresults';
return $cmd;
}
@@ -68,7 +78,7 @@ function getSteps($applyDiff, $diffID, $username, $test) {
// and authenticate using that in Sandcastle.
$setup = array(
"name" => "Setup arcrc",
"shell" => "echo " . $arcrc_content . " | base64 --decode"
"shell" => "echo " . escapeshellarg($arcrc_content) . " | base64 --decode"
. " | gzip -d > ~/.arcrc",
"user" => "root"
);
@@ -94,7 +104,17 @@ function getSteps($applyDiff, $diffID, $username, $test) {
"user" => "root"
);
// This fixes "FATAL: ThreadSanitizer can not mmap the shadow memory"
// Source:
// https://github.com/google/sanitizers/wiki/ThreadSanitizerCppManual#FAQ
$fix_kernel_issue = array(
"name" => "Fix kernel issue with tsan",
"shell" => "echo 2 >/proc/sys/kernel/randomize_va_space",
"user" => "root"
);
$steps[] = $fix_git_ignore;
$steps[] = $fix_kernel_issue;
// This will be the command used to execute particular type of tests.
$cmd = "";
@@ -104,7 +124,7 @@ function getSteps($applyDiff, $diffID, $username, $test) {
$patch = array(
"name" => "Patch " . $diffID,
"shell" => "arc --arcrc-file ~/.arcrc "
. "patch --nocommit --diff " . $diffID,
. "patch --nocommit --diff " . escapeshellarg($diffID),
"user" => "root"
);
@@ -115,8 +135,8 @@ function getSteps($applyDiff, $diffID, $username, $test) {
}
// Run the actual command.
$cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " . $test
. "; exit_code=$?; ";
$cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " .
escapeshellarg($test) . "; exit_code=$?; ";
if ($applyDiff) {
$cmd = $cmd . "([[ \$exit_code -eq 0 ]] &&"
@@ -149,7 +169,7 @@ function getSteps($applyDiff, $diffID, $username, $test) {
"name" => "Run " . $test,
"shell" => $cmd,
"user" => "root",
"parser" => "python build_tools/error_filter.py " . $test,
"parser" => "python build_tools/error_filter.py " . escapeshellarg($test),
);
$steps[] = $run_test;
@@ -197,7 +217,7 @@ function getSandcastleConfig() {
if (file_exists(PRIMARY_TOKEN_FILE)) {
$cmd = 'cat ' . PRIMARY_TOKEN_FILE;
} else {
$cmd = 'cat ' . $cwd_token_file;
$cmd = 'cat ' . escapeshellarg($cwd_token_file);
}
assert(strlen($cmd) > 0);
@@ -241,7 +261,7 @@ function getSandcastleConfig() {
// List of tests we want to run in Sandcastle.
$tests = array("unit", "unit_non_shm", "unit_481", "clang_unit", "tsan",
"asan", "lite_test", "valgrind", "release", "release_481",
"clang_release", "punit", "clang_analyze", "code_cov",
"clang_release", "clang_analyze", "code_cov",
"java_build", "no_compression", "unity", "ubsan");
$send_email_template = array(
@@ -321,9 +341,11 @@ function getSandcastleConfig() {
$app = $sandcastle_config[0];
$token = $sandcastle_config[1];
$cmd = 'curl -s -k -F app=' . $app . ' '
. '-F token=' . $token . ' -F job=\'' . json_encode($job)
.'\' "' . $url . '"';
$cmd = 'curl -s -k '
. ' -F app=' . escapeshellarg($app)
. ' -F token=' . escapeshellarg($token)
. ' -F job=' . escapeshellarg(json_encode($job))
.' ' . escapeshellarg($url);
$output = shell_exec($cmd);
assert(strlen($output) > 0);
+212 -149
View File
@@ -141,6 +141,7 @@ case "$TARGET_OS" in
;;
FreeBSD)
PLATFORM=OS_FREEBSD
CXX=clang++
COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_FREEBSD"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread"
# PORT_FILES=port/freebsd/freebsd_specific.cc
@@ -210,117 +211,137 @@ EOF
fi
fi
# Test whether Snappy library is installed
# http://code.google.com/p/snappy/
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <snappy.h>
int main() {}
if ! test $ROCKSDB_DISABLE_SNAPPY; then
# Test whether Snappy library is installed
# http://code.google.com/p/snappy/
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <snappy.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DSNAPPY"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lsnappy"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lsnappy"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DSNAPPY"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lsnappy"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lsnappy"
fi
fi
# Test whether gflags library is installed
# http://gflags.github.io/gflags/
# check if the namespace is gflags
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
#include <gflags/gflags.h>
using namespace gflags;
int main() {}
if ! test $ROCKSDB_DISABLE_GFLAGS; then
# Test whether gflags library is installed
# http://gflags.github.io/gflags/
# check if the namespace is gflags
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
#include <gflags/gflags.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=gflags"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
else
# check if namespace is google
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
#include <gflags/gflags.h>
using namespace google;
int main() {}
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
else
# check if namespace is google
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
#include <gflags/gflags.h>
using namespace google;
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
fi
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
fi
fi
fi
# Test whether zlib library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <zlib.h>
int main() {}
if ! test $ROCKSDB_DISABLE_ZLIB; then
# Test whether zlib library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <zlib.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DZLIB"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lz"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lz"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DZLIB"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lz"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lz"
fi
fi
# Test whether bzip library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <bzlib.h>
int main() {}
if ! test $ROCKSDB_DISABLE_BZIP; then
# Test whether bzip library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <bzlib.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DBZIP2"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbz2"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lbz2"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DBZIP2"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbz2"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lbz2"
fi
fi
# Test whether lz4 library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <lz4.h>
#include <lz4hc.h>
int main() {}
if ! test $ROCKSDB_DISABLE_LZ4; then
# Test whether lz4 library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <lz4.h>
#include <lz4hc.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DLZ4"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -llz4"
JAVA_LDFLAGS="$JAVA_LDFLAGS -llz4"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DLZ4"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -llz4"
JAVA_LDFLAGS="$JAVA_LDFLAGS -llz4"
fi
fi
# Test whether zstd library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <zstd.h>
int main() {}
if ! test $ROCKSDB_DISABLE_ZSTD; then
# Test whether zstd library is installed
$CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <zstd.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DZSTD"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lzstd"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lzstd"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DZSTD"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lzstd"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lzstd"
fi
fi
# Test whether numa is available
$CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null <<EOF
#include <numa.h>
#include <numaif.h>
int main() {}
if ! test $ROCKSDB_DISABLE_NUMA; then
# Test whether numa is available
$CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null <<EOF
#include <numa.h>
#include <numaif.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DNUMA"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lnuma"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DNUMA"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lnuma"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
fi
fi
# Test whether tbb is available
$CXX $CFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null <<EOF
#include <tbb/tbb.h>
int main() {}
if ! test $ROCKSDB_DISABLE_TBB; then
# Test whether tbb is available
$CXX $CFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null <<EOF
#include <tbb/tbb.h>
int main() {}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DTBB"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltbb"
JAVA_LDFLAGS="$JAVA_LDFLAGS -ltbb"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DTBB"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltbb"
JAVA_LDFLAGS="$JAVA_LDFLAGS -ltbb"
fi
fi
# Test whether jemalloc is available
if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
2>/dev/null; then
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ljemalloc"
JAVA_LDFLAGS="$JAVA_LDFLAGS -ljemalloc"
JEMALLOC=1
else
if ! test $ROCKSDB_DISABLE_JEMALLOC; then
# Test whether jemalloc is available
if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
2>/dev/null; then
# This will enable some preprocessor identifiers in the Makefile
JEMALLOC=1
# JEMALLOC can be enabled either using the flag (like here) or by
# providing direct link to the jemalloc library
WITH_JEMALLOC_FLAG=1
fi
fi
if ! test $JEMALLOC && ! test $ROCKSDB_DISABLE_TCMALLOC; then
# jemalloc is not available. Let's try tcmalloc
if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null \
-ltcmalloc 2>/dev/null; then
@@ -329,88 +350,100 @@ EOF
fi
fi
# Test whether malloc_usable_size is available
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <malloc.h>
int main() {
size_t res = malloc_usable_size(0);
return 0;
}
if ! test $ROCKSDB_DISABLE_MALLOC_USABLE_SIZE; then
# Test whether malloc_usable_size is available
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <malloc.h>
int main() {
size_t res = malloc_usable_size(0);
return 0;
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
fi
fi
# Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <pthread.h>
int main() {
int x = PTHREAD_MUTEX_ADAPTIVE_NP;
return 0;
}
if ! test $ROCKSDB_DISABLE_PTHREAD_MUTEX_ADAPTIVE_NP; then
# Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <pthread.h>
int main() {
int x = PTHREAD_MUTEX_ADAPTIVE_NP;
return 0;
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
fi
fi
# Test whether backtrace is available
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <execinfo.h>>
int main() {
void* frames[1];
backtrace_symbols(frames, backtrace(frames, 1));
return 0;
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
else
# Test whether execinfo library is installed
$CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <execinfo.h>
if ! test $ROCKSDB_DISABLE_BACKTRACE; then
# Test whether backtrace is available
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <execinfo.h>>
int main() {
void* frames[1];
backtrace_symbols(frames, backtrace(frames, 1));
return 0;
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
else
# Test whether execinfo library is installed
$CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <execinfo.h>
int main() {
void* frames[1];
backtrace_symbols(frames, backtrace(frames, 1));
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
fi
fi
fi
# Test if -pg is supported
$CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null <<EOF
int main() {
return 0;
}
if ! test $ROCKSDB_DISABLE_PG; then
# Test if -pg is supported
$CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null <<EOF
int main() {
return 0;
}
EOF
if [ "$?" = 0 ]; then
PROFILING_FLAGS=-pg
if [ "$?" = 0 ]; then
PROFILING_FLAGS=-pg
fi
fi
# Test whether sync_file_range is supported for compatibility with an old glibc
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <fcntl.h>
int main() {
int fd = open("/dev/null", 0);
sync_file_range(fd, 0, 1024, SYNC_FILE_RANGE_WRITE);
}
if ! test $ROCKSDB_DISABLE_SYNC_FILE_RANGE; then
# Test whether sync_file_range is supported for compatibility with an old glibc
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <fcntl.h>
int main() {
int fd = open("/dev/null", 0);
sync_file_range(fd, 0, 1024, SYNC_FILE_RANGE_WRITE);
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_RANGESYNC_PRESENT"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_RANGESYNC_PRESENT"
fi
fi
# Test whether sched_getcpu is supported
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <sched.h>
int main() {
int cpuid = sched_getcpu();
}
if ! test $ROCKSDB_DISABLE_SCHED_GETCPU; then
# Test whether sched_getcpu is supported
$CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <sched.h>
int main() {
int cpuid = sched_getcpu();
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SCHED_GETCPU_PRESENT"
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SCHED_GETCPU_PRESENT"
fi
fi
fi
@@ -442,21 +475,26 @@ if test "$USE_HDFS"; then
JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
fi
if test "$USE_SSE"; then
COMMON_FLAGS="$COMMON_FLAGS -msse4.2"
elif test -z "$PORTABLE"; then
if test -z "$PORTABLE"; then
if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
# Tune for this POWER processor, treating '+' models as base models
POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
elif test -n "`echo $TARGET_ARCHITECTURE | grep ^arm`"; then
# TODO: Handle this with approprite options.
COMMON_FLAGS="$COMMON_FLAGS"
elif [ "$TARGET_OS" != AIX ] && [ "$TARGET_OS" != SunOS ]; then
COMMON_FLAGS="$COMMON_FLAGS -march=native "
elif test "$USE_SSE"; then
COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
fi
elif test "$USE_SSE"; then
COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
fi
$CXX $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <cstdint>
#include <nmmintrin.h>
int main() {
@@ -467,6 +505,24 @@ if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DHAVE_SSE42"
elif test "$USE_SSE"; then
echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling"
exit 1
fi
$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <cstdint>
#include <wmmintrin.h>
int main() {
const auto a = _mm_set_epi64x(0, 0);
const auto b = _mm_set_epi64x(0, 0);
const auto c = _mm_clmulepi64_si128(a, b, 0x00);
auto d = _mm_cvtsi128_si64(c);
}
EOF
if [ "$?" = 0 ]; then
COMMON_FLAGS="$COMMON_FLAGS -DHAVE_PCLMUL"
elif test "$USE_SSE"; then
echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling"
exit 1
fi
# iOS doesn't support thread-local storage, but this check would erroneously
@@ -517,7 +573,14 @@ echo "ROCKSDB_PATCH=$ROCKSDB_PATCH" >> "$OUTPUT"
echo "CLANG_SCAN_BUILD=$CLANG_SCAN_BUILD" >> "$OUTPUT"
echo "CLANG_ANALYZER=$CLANG_ANALYZER" >> "$OUTPUT"
echo "PROFILING_FLAGS=$PROFILING_FLAGS" >> "$OUTPUT"
# This will enable some related identifiers for the preprocessor
if test -n "$JEMALLOC"; then
echo "JEMALLOC=1" >> "$OUTPUT"
fi
# Indicates that jemalloc should be enabled using -ljemalloc flag
# The alternative is to porvide a direct link to the library via JEMALLOC_LIB
# and JEMALLOC_INCLUDE
if test -n "$WITH_JEMALLOC_FLAG"; then
echo "WITH_JEMALLOC_FLAG=$WITH_JEMALLOC_FLAG" >> "$OUTPUT"
fi
echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
+4 -2
View File
@@ -1,4 +1,4 @@
#!/bin/bash
#!/usr/bin/env bash
#
# Copyright (c) 2016, Facebook. All rights reserved.
#
@@ -13,10 +13,12 @@ error=0
function log {
DATE=`date +%Y-%m-%d:%H:%M:%S`
# shellcheck disable=SC2068
echo $DATE $@
}
function log_err {
# shellcheck disable=SC2145
log "ERROR: $@ Error code: $error."
}
@@ -67,7 +69,7 @@ function update_repo_status {
#
# Path to the determinator from the root of the RocksDB repo.
CONTRUN_DETERMINATOR=./arcanist_util/config/RocksDBCommonHelper.php
CONTRUN_DETERMINATOR=./build_tools/RocksDBCommonHelper.php
# Value of the previous commit.
PREV_COMMIT=
+19 -18
View File
@@ -1,18 +1,19 @@
GCC_BASE=/mnt/gvfs/third-party2/gcc/2928bb3ed95bf64f5b388ee88c30dc74710c3b35/5.x/centos6-native/f4950a1
CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/a5fea028cb7ba43498976e1f8054b0b2e790c295/stable/centos6-native/6aaf4de
LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/7a9099f6587ee4378c0b1fa32bb8934019d30ca4/5.x/gcc-5-glibc-2.23/339d858
GLIBC_BASE=/mnt/gvfs/third-party2/glibc/3b7c6469854dfc7832a1c3cc5b86919a84e5f865/2.23/gcc-5-glibc-2.23/ca1d1c0
SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/8c38a4c1e52b4c2cc8a9cdc31b9c947ed7dbfcb4/1.1.3/gcc-5-glibc-2.23/9bc6787
ZLIB_BASE=/mnt/gvfs/third-party2/zlib/d7861abe6f0e27ab98c9303b95a662f0e4cdedb5/1.2.8/gcc-5-glibc-2.23/9bc6787
BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/740325875f6729f42d28deaa2147b0854f3a347e/1.0.6/gcc-5-glibc-2.23/9bc6787
LZ4_BASE=/mnt/gvfs/third-party2/lz4/0815d59804160c96caac5f27ca004f51af893dc6/r131/gcc-5-glibc-2.23/9bc6787
ZSTD_BASE=/mnt/gvfs/third-party2/zstd/c15a4f5f619a2930478d01e2e34dc1e0652b0873/1.1.4/gcc-5-glibc-2.23/03859b5
GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/f905a5e1032fb30c05db3d3752319857388c0c49/2.2.0/gcc-5-glibc-2.23/9bc6787
JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/8d60633d822a2a55849c73db24e74a25e52b71db/master/gcc-5-glibc-2.23/1c32b4b
NUMA_BASE=/mnt/gvfs/third-party2/numa/17c514c4d102a25ca15f4558be564eeed76f4b6a/2.0.8/gcc-5-glibc-2.23/9bc6787
LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/8db74270cd6d0212ac92d69e7fc7beefe617d772/trunk/gcc-5-glibc-2.23/b1847cb
TBB_BASE=/mnt/gvfs/third-party2/tbb/9d9a554877d0c5bef330fe818ab7178806dd316a/4.0_update2/gcc-5-glibc-2.23/9bc6787
KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/90c9734afc5579c9d1db529fa788d09f97763b85/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/9e829389ef61b92c62de8748c80169aaf25ce1f0/2.26.1/centos6-native/da39a3e
VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d7f4d4d86674a57668e3a96f76f0e17dd0eb8765/3.11.0/gcc-5-glibc-2.23/9bc6787
LUA_BASE=/mnt/gvfs/third-party2/lua/61e4abf5813bbc39bc4f548757ccfcadde175a48/5.2.3/gcc-5-glibc-2.23/65372bd
# shellcheck disable=SC2148
GCC_BASE=/mnt/gvfs/third-party2/gcc/8219ec1bcedf8ad9da05e121e193364de2cc4f61/5.x/centos6-native/c447969
CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/64d8d58e3d84f8bde7a029763d4f5baf39d0d5b9/stable/centos6-native/6aaf4de
LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/ba9be983c81de7299b59fe71950c664a84dcb5f8/5.x/gcc-5-glibc-2.23/339d858
GLIBC_BASE=/mnt/gvfs/third-party2/glibc/f20197cf3d4bd50339c9777aaa0b2ccadad9e2cb/2.23/gcc-5-glibc-2.23/ca1d1c0
SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/6427ce8c7496e4ab06c2da81543b94c0de8be3d0/1.1.3/gcc-5-glibc-2.23/9bc6787
ZLIB_BASE=/mnt/gvfs/third-party2/zlib/8f1e8b867d26efef93eac2fabbdb2e1d512665d7/1.2.8/gcc-5-glibc-2.23/9bc6787
BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/70471c0571559fe0af7db6d7e8860b93a7eadfe1/1.0.6/gcc-5-glibc-2.23/9bc6787
LZ4_BASE=/mnt/gvfs/third-party2/lz4/453c89d6f0e68cdf1c151c769197fabedad9cac8/r131/gcc-5-glibc-2.23/9bc6787
ZSTD_BASE=/mnt/gvfs/third-party2/zstd/00a40fa5f8bd2cd0622f2e868552793aef37ccf4/1.3.0/gcc-5-glibc-2.23/03859b5
GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/47eef08f9acb77de982fbda6047c26d330739538/2.2.0/gcc-5-glibc-2.23/9bc6787
JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/4414ddc78df8008b35cc4adac23590ad29148584/master/gcc-5-glibc-2.23/d506c82
NUMA_BASE=/mnt/gvfs/third-party2/numa/9d7ae2693d05d62f9a579cb21e6b717cf257a75d/2.0.11/gcc-5-glibc-2.23/9bc6787
LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/2b2dd58e3a52ccf2c1d827def59e5f740de0ad15/1.2/gcc-5-glibc-2.23/b443de1
TBB_BASE=/mnt/gvfs/third-party2/tbb/379addf7ab2468a2b4293b47456cfcd1c9cb318d/4.3/gcc-5-glibc-2.23/9bc6787
KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/3f68f5fe65a85b7c2d3e66852268fbd1efdb3151/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/b9fab0aec99d9c36408e810b2677e91c12807afd/2.28/centos6-native/da39a3e
VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/423431d61786b20bcc3bde8972901130cb29e6b3/3.11.0/gcc-5-glibc-2.23/9bc6787
LUA_BASE=/mnt/gvfs/third-party2/lua/3b0bb3bd9a0f690a069c479fcc0f7424fc7456d2/5.2.3/gcc-5-glibc-2.23/65372bd
+1
View File
@@ -1,3 +1,4 @@
# shellcheck disable=SC2148
GCC_BASE=/mnt/gvfs/third-party2/gcc/cf7d14c625ce30bae1a4661c2319c5a283e4dd22/4.8.1/centos6-native/cc6c9dc
CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/8598c375b0e94e1448182eb3df034704144a838d/stable/centos6-native/3f16ddd
LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d6e0a7da6faba45f5e5b1638f9edd7afc2f34e7d/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
+1 -1
View File
@@ -1,2 +1,2 @@
#!/bin/bash
#!/usr/bin/env bash
docker run -v $PWD:/rocks -w /rocks buildpack-deps make
+4 -4
View File
@@ -1,7 +1,7 @@
# Copyright (c) 2016-present, Facebook, Inc. All rights reserved.
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree. An additional grant
# of patent rights can be found in the PATENTS file in the same directory.
# Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
# This source code is licensed under both the GPLv2 (found in the
# COPYING file in the root directory) and Apache 2.0 License
# (found in the LICENSE.Apache file in the root directory).
'''Filter for error messages in test output:
- Receives merged stdout/stderr from test on stdin
+2 -1
View File
@@ -83,6 +83,7 @@ CFLAGS+=" -DTBB"
# use Intel SSE support for checksum calculations
export USE_SSE=1
export PORTABLE=1
BINUTILS="$BINUTILS_BASE/bin"
AR="$BINUTILS/ar"
@@ -128,7 +129,7 @@ else
fi
CFLAGS+=" $DEPS_INCLUDE"
CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_SCHED_GETCPU_PRESENT"
CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
CXXFLAGS+=" $CFLAGS"
EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
+2 -1
View File
@@ -54,6 +54,7 @@ TBB_LIBS="$TBB_BASE/lib/libtbb.a"
# use Intel SSE support for checksum calculations
export USE_SSE=1
export PORTABLE=1
BINUTILS="$BINUTILS_BASE/bin"
AR="$BINUTILS/ar"
@@ -93,7 +94,7 @@ else
fi
CFLAGS+=" $DEPS_INCLUDE"
CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_SCHED_GETCPU_PRESENT"
CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA -DTBB"
CXXFLAGS+=" $CFLAGS"
+1 -1
View File
@@ -1,4 +1,4 @@
#!/bin/bash
#!/usr/bin/env bash
# If clang_format_diff.py command is not specfied, we assume we are able to
# access directly without any path.
if [ -z $CLANG_FORMAT_DIFF ]
-53
View File
@@ -1,53 +0,0 @@
#!/bin/bash
# Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree. An additional grant
# of patent rights can be found in the PATENTS file in the same directory.
set -e
if [ -z "$GIT" ]
then
GIT="git"
fi
# Print out the colored progress info so that it can be brainlessly
# distinguished by users.
function title() {
echo -e "\033[1;32m$*\033[0m"
}
usage="Create new RocksDB version and prepare it for the release process\n"
usage+="USAGE: ./make_new_version.sh <version> [<remote>]\n"
usage+=" version: specify a version without '.fb' suffix (e.g. 5.4).\n"
usage+=" remote: name of the remote to push the branch to (default: origin)."
# -- Pre-check
if [[ $# < 1 ]]; then
echo -e $usage
exit 1
fi
ROCKSDB_VERSION=$1
REMOTE="origin"
if [[ $# > 1 ]]; then
REMOTE=$2
fi
GIT_BRANCH=`git rev-parse --abbrev-ref HEAD`
echo $GIT_BRANCH
if [ $GIT_BRANCH != "master" ]; then
echo "Error: Current branch is '$GIT_BRANCH', Please switch to master branch."
exit 1
fi
title "Adding new tag for this release ..."
BRANCH="$ROCKSDB_VERSION.fb"
$GIT checkout -b $BRANCH
# Setting up the proxy for remote repo access
title "Pushing new branch to remote repo ..."
git push $REMOTE --set-upstream $BRANCH
title "Branch $BRANCH is pushed to github;"
+5
View File
@@ -1,3 +1,4 @@
# shellcheck disable=SC1113
#/usr/bin/env bash
set -e
@@ -28,12 +29,14 @@ function package() {
if dpkg --get-selections | grep --quiet $1; then
log "$1 is already installed. skipping."
else
# shellcheck disable=SC2068
apt-get install $@ -y
fi
elif [[ $OS = "centos" ]]; then
if rpm -qa | grep --quiet $1; then
log "$1 is already installed. skipping."
else
# shellcheck disable=SC2068
yum install $@ -y
fi
fi
@@ -52,6 +55,7 @@ function gem_install() {
if gem list | grep --quiet $1; then
log "$1 is already installed. skipping."
else
# shellcheck disable=SC2068
gem install $@
fi
}
@@ -125,4 +129,5 @@ function main() {
include $LIB_DIR
}
# shellcheck disable=SC2068
main $@
+1 -1
View File
@@ -1,4 +1,4 @@
#!/bin/bash
#!/usr/bin/env bash
set -e
+11 -79
View File
@@ -1,4 +1,4 @@
#!/bin/bash
#!/usr/bin/env bash
# This script is executed by Sandcastle
# to determine next steps to run
@@ -130,35 +130,6 @@ DISABLE_COMMANDS="[
}
]"
#
# RocksDB unit test in parallel
# Currently we always have noise in our parallel runs. This job is to help
# manage the noise
#
PARALLEL_UNIT_TEST_COMMANDS="[
{
'name':'Rocksdb Parallel Unit Test',
'oncall':'$ONCALL',
'steps': [
$CLEANUP_ENV,
{
'name':'Build and test RocksDB debug version',
'shell':'$DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || $CONTRUN_NAME=punit_check $TASK_CREATION_TOOL || cat t/log-*',
'user':'root',
$PARSER
},
$CLEANUP_ENV,
{
'name':'Build and test RocksDB debug version under gcc-4.8.1',
'shell':'$GCC_481 $DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || $CONTRUN_NAME=punit_check_gcc481 $TASK_CREATION_TOOL || cat t/log-*',
'user':'root',
$PARSER
},
],
$REPORT
}
]"
#
# RocksDB unit test
#
@@ -372,7 +343,7 @@ LITE_BUILD_COMMANDS="[
$CLEANUP_ENV,
{
'name':'Build RocksDB debug version',
'shell':'$LITE make J=1 static_lib || $CONTRUN_NAME=lite_static_lib $TASK_CREATION_TOOL',
'shell':'$LITE make J=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
'user':'root',
$PARSER
},
@@ -382,23 +353,19 @@ LITE_BUILD_COMMANDS="[
]"
#
# RocksDB lite tests
#
LITE_UNIT_TEST_COMMANDS="[
# Report RocksDB lite binary size to scuba
REPORT_LITE_BINARY_SIZE_COMMANDS="[
{
'name':'Rocksdb Lite Unit Test',
'name':'Rocksdb Lite Binary Size',
'oncall':'$ONCALL',
'steps': [
$CLEANUP_ENV,
{
'name':'Build RocksDB debug version',
'shell':'$SHM $LITE make J=1 check || $CONTRUN_NAME=lite_check $TASK_CREATION_TOOL',
'name':'Report RocksDB Lite binary size to scuba',
'shell':'tools/report_lite_binary_size.sh',
'user':'root',
$PARSER
},
],
$REPORT
}
]"
#
@@ -593,7 +560,7 @@ TSAN_CRASH_TEST_COMMANDS="[
{
'name':'Compile and run',
'timeout': 86400,
'shell':'set -o pipefail && $SHM $DEBUG $TSAN CRASH_TEST_KILL_ODD=1887 make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
'shell':'set -o pipefail && $SHM $DEBUG $TSAN CRASH_TEST_KILL_ODD=1887 CRASH_TEST_EXT_ARGS=--log2_keys_per_lock=22 make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
'user':'root',
$PARSER
},
@@ -612,39 +579,7 @@ run_format_compatible()
rm -rf /dev/shm/rocksdb
mkdir /dev/shm/rocksdb
echo '
if [ -e "build_tools/build_detect_platform" ]
then
sed "s/tcmalloc/nothingnothingnothing/g" build_tools/build_detect_platform > $TEST_TMPDIR/temp_build_file
rm -rf build_tools/build_detect_platform
cp $TEST_TMPDIR/temp_build_file build_tools/build_detect_platform
chmod +x build_tools/build_detect_platform
fi
if [ -e "build_detect_platform" ]
then
sed "s/tcmalloc/nothingnothingnothing/g" build_detect_platform > $TEST_TMPDIR/temp_build_file
rm -rf build_detect_platform
cp $TEST_TMPDIR/temp_build_file build_detect_platform
chmod +x build_detect_platform
fi
make ldb -j32
if [ -e "build_detect_platform" ]
then
git checkout -- build_detect_platform
fi
if [ -e "build_tools/build_detect_platform" ]
then
git checkout -- build_tools/build_detect_platform
fi
' > temp_build_ldb.sh
sed "s/make ldb -j32/source temp_build_ldb.sh/g" tools/check_format_compatible.sh > tools/temp_check_format_compatible.sh
chmod +x tools/temp_check_format_compatible.sh
tools/temp_check_format_compatible.sh
tools/check_format_compatible.sh
}
FORMAT_COMPATIBLE_COMMANDS="[
@@ -776,9 +711,6 @@ JAVA_BUILD_TEST_COMMANDS="[
case $1 in
punit)
echo $PARALLEL_UNIT_TEST_COMMANDS
;;
unit)
echo $UNIT_TEST_COMMANDS
;;
@@ -812,8 +744,8 @@ case $1 in
lite)
echo $LITE_BUILD_COMMANDS
;;
lite_test)
echo $LITE_UNIT_TEST_COMMANDS
report_lite_binary_size)
echo $REPORT_LITE_BINARY_SIZE_COMMANDS
;;
stress_crash)
echo $STRESS_CRASH_TEST_COMMANDS
+46 -16
View File
@@ -1,13 +1,16 @@
# This script enables you running RocksDB tests by running
# All the tests concurrently and utilizing all the cores
Param(
[switch]$EnableJE = $false, # Look for and use _je executable, append _je to listed exclusions
[switch]$EnableJE = $false, # Look for and use test executable, append _je to listed exclusions
[switch]$RunAll = $false, # Will attempt discover all *_test[_je].exe binaries and run all
# of them as Google suites. I.e. It will run test cases concurrently
# except those mentioned as $Run, those will run as individual test cases
# And any execlued with $ExcludeExes or $ExcludeCases
# It will also not run any individual test cases
# excluded but $ExcludeCasese
[switch]$RunAllExe = $false, # Look for and use test exdcutables, append _je to exclusions automatically
# It will attempt to run them in parallel w/o breaking them up on individual
# test cases. Those listed with $ExcludeExes will be excluded
[string]$SuiteRun = "", # Split test suites in test cases and run in parallel, not compatible with $RunAll
[string]$Run = "", # Run specified executables in parallel but do not split to test cases
[string]$ExcludeCases = "", # Exclude test cases, expects a comma separated list, no spaces
@@ -39,13 +42,18 @@ $RunOnly.Add("compact_on_deletion_collector_test") | Out-Null
$RunOnly.Add("merge_test") | Out-Null
$RunOnly.Add("stringappend_test") | Out-Null # Apparently incorrectly written
$RunOnly.Add("backupable_db_test") | Out-Null # Disabled
$RunOnly.Add("timer_queue_test") | Out-Null # Not a gtest
if($RunAll -and $SuiteRun -ne "") {
Write-Error "$RunAll and $SuiteRun are not compatible"
exit 1
}
if($RunAllExe -and $Run -ne "") {
Write-Error "$RunAllExe and $Run are not compatible"
exit 1
}
# If running under Appveyor assume that root
[string]$Appveyor = $Env:APPVEYOR_BUILD_FOLDER
if($Appveyor -ne "") {
@@ -131,12 +139,8 @@ function ExtractTestCases([string]$GTestExe, $HashTable) {
# Leading whitespace is fine
$l = $l -replace '^\s+',''
# but no whitespace any other place
if($l -match "\s+") {
continue
}
# Trailing dot is a test group but no whitespace
elseif ( $l -match "\.$" ) {
if ($l -match "\.$" -and $l -notmatch "\s+") {
$Group = $l
} else {
# Otherwise it is a test name, remove leading space
@@ -223,13 +227,11 @@ $TestExes = [ordered]@{}
if($Run -ne "") {
$test_list = $Run -split ' '
ForEach($t in $test_list) {
if($EnableJE) {
$t += "_je"
}
MakeAndAdd -token $t -HashTable $TestExes
}
@@ -237,6 +239,38 @@ if($Run -ne "") {
Write-Error "Failed to extract tests from $Run"
exit 1
}
} elseif($RunAllExe) {
# Discover all the test binaries
if($EnableJE) {
$pattern = "*_test_je.exe"
} else {
$pattern = "*_test.exe"
}
$search_path = -join ($BinariesFolder, $pattern)
Write-Host "Binaries Search Path: $search_path"
$DiscoveredExe = @()
dir -Path $search_path | ForEach-Object {
$DiscoveredExe += ($_.Name)
}
# Remove exclusions
ForEach($e in $DiscoveredExe) {
$e = $e -replace '.exe$', ''
$bare_name = $e -replace '_je$', ''
if($ExcludeExesSet.Contains($bare_name)) {
Write-Warning "Test $e is excluded"
continue
}
MakeAndAdd -token $e -HashTable $TestExes
}
if($TestExes.Count -lt 1) {
Write-Error "Failed to discover test executables"
exit 1
}
}
# Ordered by exe @{ Exe = @{ TestCase = LogName }}
@@ -245,9 +279,7 @@ $CasesToRun = [ordered]@{}
if($SuiteRun -ne "") {
$suite_list = $SuiteRun -split ' '
ProcessSuites -ListOfSuites $suite_list -HashOfHashes $CasesToRun
}
if($RunAll) {
} elseif ($RunAll) {
# Discover all the test binaries
if($EnableJE) {
$pattern = "*_test_je.exe"
@@ -255,7 +287,6 @@ if($RunAll) {
$pattern = "*_test.exe"
}
$search_path = -join ($BinariesFolder, $pattern)
Write-Host "Binaries Search Path: $search_path"
@@ -287,8 +318,6 @@ if($RunAll) {
}
Write-Host "Attempting to start: $NumTestsToStart tests"
# Invoke a test with a filter and redirect all output
$InvokeTestCase = {
param($exe, $test, $log);
@@ -333,7 +362,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
$Cases = @{}
if($Suites.Count -gt 0) {
# Will teh first one
# Will the first one
ForEach($e in $Suites.Keys) {
$exe_name = $e
$Cases = $Suites[$e]
@@ -365,6 +394,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
break
}
Write-Host "Starting $exe_name"
[string]$Exe = -Join ($BinariesFolder, $exe_name)
$job = Start-Job -Name $exe_name -ScriptBlock $InvokeTestAsync -ArgumentList @($Exe,$log_path)
$JobToLog.Add($job, $log_path)
+15 -14
View File
@@ -38,6 +38,7 @@ function get_lib_base()
# platform is not provided, use latest gcc
result=`ls -dr1v $result/gcc-*[^fb]/ | head -n1`
else
echo $lib_platform
result="$result/$lib_platform/"
fi
@@ -71,22 +72,22 @@ log_variable GCC_BASE
log_variable CLANG_BASE
# Libraries locations
get_lib_base libgcc 5.x
get_lib_base glibc 2.23
get_lib_base snappy LATEST gcc-5-glibc-2.23
get_lib_base zlib LATEST
get_lib_base bzip2 LATEST
get_lib_base lz4 LATEST
get_lib_base zstd LATEST
get_lib_base gflags LATEST
get_lib_base jemalloc LATEST
get_lib_base numa LATEST
get_lib_base libunwind LATEST
get_lib_base tbb 4.0_update2 gcc-5-glibc-2.23
get_lib_base libgcc 5.x gcc-5-glibc-2.23
get_lib_base glibc 2.23 gcc-5-glibc-2.23
get_lib_base snappy LATEST gcc-5-glibc-2.23
get_lib_base zlib LATEST gcc-5-glibc-2.23
get_lib_base bzip2 LATEST gcc-5-glibc-2.23
get_lib_base lz4 LATEST gcc-5-glibc-2.23
get_lib_base zstd LATEST gcc-5-glibc-2.23
get_lib_base gflags LATEST gcc-5-glibc-2.23
get_lib_base jemalloc LATEST gcc-5-glibc-2.23
get_lib_base numa LATEST gcc-5-glibc-2.23
get_lib_base libunwind LATEST gcc-5-glibc-2.23
get_lib_base tbb LATEST gcc-5-glibc-2.23
get_lib_base kernel-headers LATEST
get_lib_base kernel-headers 4.0.9-36_fbk5_2933_gd092e3f gcc-5-glibc-2.23
get_lib_base binutils LATEST centos6-native
get_lib_base valgrind 3.10.0 gcc-5-glibc-2.23
get_lib_base valgrind LATEST gcc-5-glibc-2.23
get_lib_base lua 5.2.3 gcc-5-glibc-2.23
git diff $OUTPUT
+8 -10
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#ifndef __STDC_FORMAT_MACROS
#define __STDC_FORMAT_MACROS
@@ -19,16 +17,16 @@ int main() {
#include <inttypes.h>
#include <sys/types.h>
#include <stdio.h>
#include <gflags/gflags.h>
#include "rocksdb/db.h"
#include "rocksdb/cache.h"
#include "rocksdb/env.h"
#include "port/port.h"
#include "rocksdb/cache.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "util/gflags_compat.h"
#include "util/mutexlock.h"
#include "util/random.h"
using GFLAGS::ParseCommandLineFlags;
using GFLAGS_NAMESPACE::ParseCommandLineFlags;
static const uint32_t KB = 1024;
+3 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
+8 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -29,6 +27,11 @@ std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
#include <atomic>
#include <deque>
// "tbb/concurrent_hash_map.h" requires RTTI if exception is enabled.
// Disable it so users can chooose to disable RTTI.
#ifndef ROCKSDB_USE_RTTI
#define TBB_USE_EXCEPTIONS 0
#endif
#include "tbb/concurrent_hash_map.h"
#include "cache/sharded_cache.h"
+3 -3
View File
@@ -1,7 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
+70 -11
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -24,7 +22,7 @@
namespace rocksdb {
LRUHandleTable::LRUHandleTable() : length_(0), elems_(0), list_(nullptr) {
LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {
Resize();
}
@@ -102,7 +100,9 @@ void LRUHandleTable::Resize() {
}
LRUCacheShard::LRUCacheShard()
: usage_(0), lru_usage_(0), high_pri_pool_usage_(0) {
: capacity_(0), high_pri_pool_usage_(0), strict_capacity_limit_(false),
high_pri_pool_ratio_(0), high_pri_pool_capacity_(0), usage_(0),
lru_usage_(0) {
// Make empty circular linked list
lru_.next = &lru_;
lru_.prev = &lru_;
@@ -159,6 +159,21 @@ void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
*lru_low_pri = lru_low_pri_;
}
size_t LRUCacheShard::TEST_GetLRUSize() {
LRUHandle* lru_handle = lru_.next;
size_t lru_size = 0;
while (lru_handle != &lru_) {
lru_size++;
lru_handle = lru_handle->next;
}
return lru_size;
}
double LRUCacheShard::GetHighPriPoolRatio() {
MutexLock l(&mutex_);
return high_pri_pool_ratio_;
}
void LRUCacheShard::LRU_Remove(LRUHandle* e) {
assert(e->next != nullptr);
assert(e->prev != nullptr);
@@ -225,6 +240,22 @@ void LRUCacheShard::EvictFromLRU(size_t charge,
}
}
void* LRUCacheShard::operator new(size_t size) {
return port::cacheline_aligned_alloc(size);
}
void* LRUCacheShard::operator new[](size_t size) {
return port::cacheline_aligned_alloc(size);
}
void LRUCacheShard::operator delete(void *memblock) {
port::cacheline_aligned_free(memblock);
}
void LRUCacheShard::operator delete[](void* memblock) {
port::cacheline_aligned_free(memblock);
}
void LRUCacheShard::SetCapacity(size_t capacity) {
autovector<LRUHandle*> last_reference_list;
{
@@ -329,6 +360,7 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
e->deleter = deleter;
e->charge = charge;
e->key_length = key.size();
e->flags = 0;
e->hash = hash;
e->refs = (handle == nullptr
? 1
@@ -440,11 +472,11 @@ std::string LRUCacheShard::GetPrintableOptions() const {
LRUCache::LRUCache(size_t capacity, int num_shard_bits,
bool strict_capacity_limit, double high_pri_pool_ratio)
: ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
int num_shards = 1 << num_shard_bits;
shards_ = new LRUCacheShard[num_shards];
num_shards_ = 1 << num_shard_bits;
shards_ = new LRUCacheShard[num_shards_];
SetCapacity(capacity);
SetStrictCapacityLimit(strict_capacity_limit);
for (int i = 0; i < num_shards; i++) {
for (int i = 0; i < num_shards_; i++) {
shards_[i].SetHighPriorityPoolRatio(high_pri_pool_ratio);
}
}
@@ -471,7 +503,34 @@ uint32_t LRUCache::GetHash(Handle* handle) const {
return reinterpret_cast<const LRUHandle*>(handle)->hash;
}
void LRUCache::DisownData() { shards_ = nullptr; }
void LRUCache::DisownData() {
// Do not drop data if compile with ASAN to suppress leak warning.
#ifndef __SANITIZE_ADDRESS__
shards_ = nullptr;
#endif // !__SANITIZE_ADDRESS__
}
size_t LRUCache::TEST_GetLRUSize() {
size_t lru_size_of_all_shards = 0;
for (int i = 0; i < num_shards_; i++) {
lru_size_of_all_shards += shards_[i].TEST_GetLRUSize();
}
return lru_size_of_all_shards;
}
double LRUCache::GetHighPriPoolRatio() {
double result = 0.0;
if (num_shards_ > 0) {
result = shards_[0].GetHighPriPoolRatio();
}
return result;
}
std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
cache_opts.strict_capacity_limit,
cache_opts.high_pri_pool_ratio);
}
std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
bool strict_capacity_limit,
+50 -19
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -59,7 +57,7 @@ struct LRUHandle {
// Include the following flags:
// in_cache: whether this entry is referenced by the hash table.
// is_high_pri: whether this entry is high priority entry.
// in_high_pro_pool: whether this entry is in high-pri pool.
// in_high_pri_pool: whether this entry is in high-pri pool.
char flags;
uint32_t hash; // Hash of key(); used for fast sharding and comparisons
@@ -150,13 +148,13 @@ class LRUHandleTable {
// The table consists of an array of buckets where each bucket is
// a linked list of cache entries that hash into the bucket.
LRUHandle** list_;
uint32_t length_;
uint32_t elems_;
LRUHandle** list_;
};
// A single shard of sharded cache.
class LRUCacheShard : public CacheShard {
class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
public:
LRUCacheShard();
virtual ~LRUCacheShard();
@@ -200,6 +198,22 @@ class LRUCacheShard : public CacheShard {
void TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri);
// Retrieves number of elements in LRU, for unit test purpose only
// not threadsafe
size_t TEST_GetLRUSize();
// Retrives high pri pool ratio
double GetHighPriPoolRatio();
// Overloading to aligned it to cache line size
void* operator new(size_t);
void* operator new[](size_t);
void operator delete(void *);
void operator delete[](void*);
private:
void LRU_Remove(LRUHandle* e);
void LRU_Insert(LRUHandle* e);
@@ -221,12 +235,6 @@ class LRUCacheShard : public CacheShard {
// Initialized before use.
size_t capacity_;
// Memory size for entries residing in the cache
size_t usage_;
// Memory size for entries residing only in the LRU list
size_t lru_usage_;
// Memory size for entries in high-pri pool.
size_t high_pri_pool_usage_;
@@ -240,11 +248,6 @@ class LRUCacheShard : public CacheShard {
// Remember the value to avoid recomputing each time.
double high_pri_pool_capacity_;
// mutex_ protects the following state.
// We don't count mutex_ as the cache's internal state so semantically we
// don't mind mutex_ invoking the non-const actions.
mutable port::Mutex mutex_;
// Dummy head of LRU list.
// lru.prev is newest entry, lru.next is oldest entry.
// LRU contains items which can be evicted, ie reference only by cache
@@ -253,7 +256,29 @@ class LRUCacheShard : public CacheShard {
// Pointer to head of low-pri pool in LRU list.
LRUHandle* lru_low_pri_;
// ------------^^^^^^^^^^^^^-----------
// Not frequently modified data members
// ------------------------------------
//
// We separate data members that are updated frequently from the ones that
// are not frequently updated so that they don't share the same cache line
// which will lead into false cache sharing
//
// ------------------------------------
// Frequently modified data members
// ------------vvvvvvvvvvvvv-----------
LRUHandleTable table_;
// Memory size for entries residing in the cache
size_t usage_;
// Memory size for entries residing only in the LRU list
size_t lru_usage_;
// mutex_ protects the following state.
// We don't count mutex_ as the cache's internal state so semantically we
// don't mind mutex_ invoking the non-const actions.
mutable port::Mutex mutex_;
};
class LRUCache : public ShardedCache {
@@ -269,8 +294,14 @@ class LRUCache : public ShardedCache {
virtual uint32_t GetHash(Handle* handle) const override;
virtual void DisownData() override;
// Retrieves number of elements in LRU, for unit test purpose only
size_t TEST_GetLRUSize();
// Retrives high pri pool ratio
double GetHighPriPoolRatio();
private:
LRUCacheShard* shards_;
int num_shards_ = 0;
};
} // namespace rocksdb
+13 -6
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include "cache/lru_cache.h"
@@ -19,7 +17,16 @@ class LRUCacheTest : public testing::Test {
~LRUCacheTest() {}
void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0) {
cache_.reset(new LRUCacheShard());
cache_.reset(
#if defined(_MSC_VER)
#pragma warning(push)
#pragma warning(disable: 4316) // We've validated the alignment with the new operators
#endif
new LRUCacheShard()
#if defined(_MSC_VER)
#pragma warning(pop)
#endif
);
cache_->SetCapacity(capacity);
cache_->SetStrictCapacityLimit(false);
cache_->SetHighPriorityPoolRatio(high_pri_pool_ratio);
+3 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
+3 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
+3
View File
@@ -0,0 +1,3 @@
@PACKAGE_INIT@
include("${CMAKE_CURRENT_LIST_DIR}/RocksDBTargets.cmake")
check_required_components(RocksDB)
+21
View File
@@ -0,0 +1,21 @@
# - Find NUMA
# Find the NUMA library and includes
#
# NUMA_INCLUDE_DIR - where to find numa.h, etc.
# NUMA_LIBRARIES - List of libraries when using NUMA.
# NUMA_FOUND - True if NUMA found.
find_path(NUMA_INCLUDE_DIR
NAMES numa.h numaif.h
HINTS ${NUMA_ROOT_DIR}/include)
find_library(NUMA_LIBRARIES
NAMES numa
HINTS ${NUMA_ROOT_DIR}/lib)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIR)
mark_as_advanced(
NUMA_LIBRARIES
NUMA_INCLUDE_DIR)
+21
View File
@@ -0,0 +1,21 @@
# - Find TBB
# Find the Thread Building Blocks library and includes
#
# TBB_INCLUDE_DIR - where to find tbb.h, etc.
# TBB_LIBRARIES - List of libraries when using TBB.
# TBB_FOUND - True if TBB found.
find_path(TBB_INCLUDE_DIR
NAMES tbb/tbb.h
HINTS ${TBB_ROOT_DIR}/include)
find_library(TBB_LIBRARIES
NAMES tbb
HINTS ${TBB_ROOT_DIR}/lib)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIR)
mark_as_advanced(
TBB_LIBRARIES
TBB_INCLUDE_DIR)
+21
View File
@@ -0,0 +1,21 @@
# - Find Bzip2
# Find the bzip2 compression library and includes
#
# BZIP2_INCLUDE_DIR - where to find bzlib.h, etc.
# BZIP2_LIBRARIES - List of libraries when using bzip2.
# BZIP2_FOUND - True if bzip2 found.
find_path(BZIP2_INCLUDE_DIR
NAMES bzlib.h
HINTS ${BZIP2_ROOT_DIR}/include)
find_library(BZIP2_LIBRARIES
NAMES bz2
HINTS ${BZIP2_ROOT_DIR}/lib)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(bzip2 DEFAULT_MSG BZIP2_LIBRARIES BZIP2_INCLUDE_DIR)
mark_as_advanced(
BZIP2_LIBRARIES
BZIP2_INCLUDE_DIR)
+21
View File
@@ -0,0 +1,21 @@
# - Find Lz4
# Find the lz4 compression library and includes
#
# LZ4_INCLUDE_DIR - where to find lz4.h, etc.
# LZ4_LIBRARIES - List of libraries when using lz4.
# LZ4_FOUND - True if lz4 found.
find_path(LZ4_INCLUDE_DIR
NAMES lz4.h
HINTS ${LZ4_ROOT_DIR}/include)
find_library(LZ4_LIBRARIES
NAMES lz4
HINTS ${LZ4_ROOT_DIR}/lib)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(lz4 DEFAULT_MSG LZ4_LIBRARIES LZ4_INCLUDE_DIR)
mark_as_advanced(
LZ4_LIBRARIES
LZ4_INCLUDE_DIR)
+21
View File
@@ -0,0 +1,21 @@
# - Find zlib
# Find the zlib compression library and includes
#
# ZLIB_INCLUDE_DIR - where to find zlib.h, etc.
# ZLIB_LIBRARIES - List of libraries when using zlib.
# ZLIB_FOUND - True if zlib found.
find_path(ZLIB_INCLUDE_DIR
NAMES zlib.h
HINTS ${ZLIB_ROOT_DIR}/include)
find_library(ZLIB_LIBRARIES
NAMES z
HINTS ${ZLIB_ROOT_DIR}/lib)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(zlib DEFAULT_MSG ZLIB_LIBRARIES ZLIB_INCLUDE_DIR)
mark_as_advanced(
ZLIB_LIBRARIES
ZLIB_INCLUDE_DIR)
+21
View File
@@ -0,0 +1,21 @@
# - Find zstd
# Find the zstd compression library and includes
#
# ZSTD_INCLUDE_DIR - where to find zstd.h, etc.
# ZSTD_LIBRARIES - List of libraries when using zstd.
# ZSTD_FOUND - True if zstd found.
find_path(ZSTD_INCLUDE_DIR
NAMES zstd.h
HINTS ${ZSTD_ROOT_DIR}/include)
find_library(ZSTD_LIBRARIES
NAMES zstd
HINTS ${ZSTD_ROOT_DIR}/lib)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(zstd DEFAULT_MSG ZSTD_LIBRARIES ZSTD_INCLUDE_DIR)
mark_as_advanced(
ZSTD_LIBRARIES
ZSTD_INCLUDE_DIR)
+1 -1
View File
@@ -1,4 +1,4 @@
#!/bin/bash
#!/usr/bin/env bash
# Exit on error.
set -e
+1 -1
View File
@@ -72,7 +72,7 @@ def display_file_coverage(per_file_coverage, total_coverage):
header_template = \
"%" + str(max_file_name_length) + "s\t%s\t%s"
separator = "-" * (max_file_name_length + 10 + 20)
print header_template % ("Filename", "Coverage", "Lines")
print header_template % ("Filename", "Coverage", "Lines") # noqa: E999 T25377293 Grandfathered in
print separator
# -- Print body
+20 -19
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -47,17 +45,17 @@ TableBuilder* NewTableBuilder(
int_tbl_prop_collector_factories,
uint32_t column_family_id, const std::string& column_family_name,
WritableFileWriter* file, const CompressionType compression_type,
const CompressionOptions& compression_opts,
int level,
const std::string* compression_dict, const bool skip_filters) {
const CompressionOptions& compression_opts, int level,
const std::string* compression_dict, const bool skip_filters,
const uint64_t creation_time, const uint64_t oldest_key_time) {
assert((column_family_id ==
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
column_family_name.empty());
return ioptions.table_factory->NewTableBuilder(
TableBuilderOptions(ioptions, internal_comparator,
int_tbl_prop_collector_factories, compression_type,
compression_opts, compression_dict, skip_filters,
column_family_name, level),
TableBuilderOptions(
ioptions, internal_comparator, int_tbl_prop_collector_factories,
compression_type, compression_opts, compression_dict, skip_filters,
column_family_name, level, creation_time, oldest_key_time),
column_family_id, file);
}
@@ -72,11 +70,12 @@ Status BuildTable(
uint32_t column_family_id, const std::string& column_family_name,
std::vector<SequenceNumber> snapshots,
SequenceNumber earliest_write_conflict_snapshot,
const CompressionType compression,
SnapshotChecker* snapshot_checker, const CompressionType compression,
const CompressionOptions& compression_opts, bool paranoid_file_checks,
InternalStats* internal_stats, TableFileCreationReason reason,
EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
TableProperties* table_properties, int level) {
TableProperties* table_properties, int level, const uint64_t creation_time,
const uint64_t oldest_key_time, Env::WriteLifeTimeHint write_hint) {
assert((column_family_id ==
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
column_family_name.empty());
@@ -118,24 +117,26 @@ Status BuildTable(
return s;
}
file->SetIOPriority(io_priority);
file->SetWriteLifeTimeHint(write_hint);
file_writer.reset(new WritableFileWriter(std::move(file), env_options,
ioptions.statistics));
builder = NewTableBuilder(
ioptions, internal_comparator, int_tbl_prop_collector_factories,
column_family_id, column_family_name, file_writer.get(), compression,
compression_opts, level);
compression_opts, level, nullptr /* compression_dict */,
false /* skip_filters */, creation_time, oldest_key_time);
}
MergeHelper merge(env, internal_comparator.user_comparator(),
ioptions.merge_operator, nullptr, ioptions.info_log,
true /* internal key corruption is not ok */,
snapshots.empty() ? 0 : snapshots.back());
snapshots.empty() ? 0 : snapshots.back(),
snapshot_checker);
CompactionIterator c_iter(
iter, internal_comparator.user_comparator(), &merge, kMaxSequenceNumber,
&snapshots, earliest_write_conflict_snapshot, env,
&snapshots, earliest_write_conflict_snapshot, snapshot_checker, env,
true /* internal key corruption is not ok */, range_del_agg.get());
c_iter.SeekToFirst();
for (; c_iter.Valid(); c_iter.Next()) {
@@ -179,7 +180,7 @@ Status BuildTable(
// Finish and check for file errors
if (s.ok() && !empty) {
StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
file_writer->Sync(ioptions.use_fsync);
s = file_writer->Sync(ioptions.use_fsync);
}
if (s.ok() && !empty) {
s = file_writer->Close();
+11 -10
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
@@ -31,6 +29,7 @@ struct FileMetaData;
class Env;
struct EnvOptions;
class Iterator;
class SnapshotChecker;
class TableCache;
class VersionEdit;
class TableBuilder;
@@ -50,10 +49,10 @@ TableBuilder* NewTableBuilder(
int_tbl_prop_collector_factories,
uint32_t column_family_id, const std::string& column_family_name,
WritableFileWriter* file, const CompressionType compression_type,
const CompressionOptions& compression_opts,
int level,
const CompressionOptions& compression_opts, int level,
const std::string* compression_dict = nullptr,
const bool skip_filters = false);
const bool skip_filters = false, const uint64_t creation_time = 0,
const uint64_t oldest_key_time = 0);
// Build a Table file from the contents of *iter. The generated file
// will be named according to number specified in meta. On success, the rest of
@@ -74,11 +73,13 @@ extern Status BuildTable(
uint32_t column_family_id, const std::string& column_family_name,
std::vector<SequenceNumber> snapshots,
SequenceNumber earliest_write_conflict_snapshot,
const CompressionType compression,
SnapshotChecker* snapshot_checker, const CompressionType compression,
const CompressionOptions& compression_opts, bool paranoid_file_checks,
InternalStats* internal_stats, TableFileCreationReason reason,
EventLogger* event_logger = nullptr, int job_id = 0,
const Env::IOPriority io_priority = Env::IO_HIGH,
TableProperties* table_properties = nullptr, int level = -1);
TableProperties* table_properties = nullptr, int level = -1,
const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET);
} // namespace rocksdb
+443 -20
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -23,22 +21,23 @@
#include "rocksdb/env.h"
#include "rocksdb/filter_policy.h"
#include "rocksdb/iterator.h"
#include "rocksdb/memtablerep.h"
#include "rocksdb/merge_operator.h"
#include "rocksdb/options.h"
#include "rocksdb/status.h"
#include "rocksdb/write_batch.h"
#include "rocksdb/memtablerep.h"
#include "rocksdb/universal_compaction.h"
#include "rocksdb/statistics.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/table.h"
#include "rocksdb/rate_limiter.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/statistics.h"
#include "rocksdb/status.h"
#include "rocksdb/table.h"
#include "rocksdb/universal_compaction.h"
#include "rocksdb/utilities/backupable_db.h"
#include "rocksdb/utilities/write_batch_with_index.h"
#include "utilities/merge_operators.h"
#include "rocksdb/utilities/checkpoint.h"
#include "rocksdb/utilities/optimistic_transaction_db.h"
#include "rocksdb/utilities/transaction.h"
#include "rocksdb/utilities/transaction_db.h"
#include "rocksdb/utilities/checkpoint.h"
#include "rocksdb/utilities/write_batch_with_index.h"
#include "rocksdb/write_batch.h"
#include "utilities/merge_operators.h"
using rocksdb::BytewiseComparator;
using rocksdb::Cache;
@@ -54,6 +53,7 @@ using rocksdb::CompressionType;
using rocksdb::WALRecoveryMode;
using rocksdb::DB;
using rocksdb::DBOptions;
using rocksdb::DbPath;
using rocksdb::Env;
using rocksdb::EnvOptions;
using rocksdb::InfoLogLevel;
@@ -96,6 +96,8 @@ using rocksdb::PinnableSlice;
using rocksdb::TransactionDBOptions;
using rocksdb::TransactionDB;
using rocksdb::TransactionOptions;
using rocksdb::OptimisticTransactionDB;
using rocksdb::OptimisticTransactionOptions;
using rocksdb::Transaction;
using rocksdb::Checkpoint;
@@ -115,7 +117,9 @@ struct rocksdb_flushoptions_t { FlushOptions rep; };
struct rocksdb_fifo_compaction_options_t { CompactionOptionsFIFO rep; };
struct rocksdb_readoptions_t {
ReadOptions rep;
Slice upper_bound; // stack variable to set pointer to in ReadOptions
// stack variables to set pointers to in ReadOptions
Slice upper_bound;
Slice lower_bound;
};
struct rocksdb_writeoptions_t { WriteOptions rep; };
struct rocksdb_options_t { Options rep; };
@@ -154,6 +158,12 @@ struct rocksdb_transaction_t {
struct rocksdb_checkpoint_t {
Checkpoint* rep;
};
struct rocksdb_optimistictransactiondb_t {
OptimisticTransactionDB* rep;
};
struct rocksdb_optimistictransaction_options_t {
OptimisticTransactionOptions rep;
};
struct rocksdb_compactionfiltercontext_t {
CompactionFilter::Context rep;
@@ -384,6 +394,10 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
}
};
struct rocksdb_dbpath_t {
DbPath rep;
};
struct rocksdb_env_t {
Env* rep;
bool is_default;
@@ -1812,6 +1826,26 @@ void rocksdb_block_based_options_set_block_restart_interval(
options->rep.block_restart_interval = block_restart_interval;
}
void rocksdb_block_based_options_set_index_block_restart_interval(
rocksdb_block_based_table_options_t* options, int index_block_restart_interval) {
options->rep.index_block_restart_interval = index_block_restart_interval;
}
void rocksdb_block_based_options_set_metadata_block_size(
rocksdb_block_based_table_options_t* options, uint64_t metadata_block_size) {
options->rep.metadata_block_size = metadata_block_size;
}
void rocksdb_block_based_options_set_partition_filters(
rocksdb_block_based_table_options_t* options, unsigned char partition_filters) {
options->rep.partition_filters = partition_filters;
}
void rocksdb_block_based_options_set_use_delta_encoding(
rocksdb_block_based_table_options_t* options, unsigned char use_delta_encoding) {
options->rep.use_delta_encoding = use_delta_encoding;
}
void rocksdb_block_based_options_set_filter_policy(
rocksdb_block_based_table_options_t* options,
rocksdb_filterpolicy_t* filter_policy) {
@@ -1865,6 +1899,11 @@ void rocksdb_block_based_options_set_cache_index_and_filter_blocks(
options->rep.cache_index_and_filter_blocks = v;
}
void rocksdb_block_based_options_set_cache_index_and_filter_blocks_with_high_priority(
rocksdb_block_based_table_options_t* options, unsigned char v) {
options->rep.cache_index_and_filter_blocks_with_high_priority = v;
}
void rocksdb_block_based_options_set_pin_l0_filter_and_index_blocks_in_cache(
rocksdb_block_based_table_options_t* options, unsigned char v) {
options->rep.pin_l0_filter_and_index_blocks_in_cache = v;
@@ -1879,7 +1918,6 @@ void rocksdb_options_set_block_based_table_factory(
}
}
rocksdb_cuckoo_table_options_t*
rocksdb_cuckoo_options_create() {
return new rocksdb_cuckoo_table_options_t;
@@ -1961,6 +1999,11 @@ void rocksdb_options_optimize_universal_style_compaction(
opt->rep.OptimizeUniversalStyleCompaction(memtable_memory_budget);
}
void rocksdb_options_set_allow_ingest_behind(
rocksdb_options_t* opt, unsigned char v) {
opt->rep.allow_ingest_behind = v;
}
void rocksdb_options_set_compaction_filter(
rocksdb_options_t* opt,
rocksdb_compactionfilter_t* filter) {
@@ -2011,6 +2054,16 @@ void rocksdb_options_set_paranoid_checks(
opt->rep.paranoid_checks = v;
}
void rocksdb_options_set_db_paths(rocksdb_options_t* opt,
const rocksdb_dbpath_t** dbpath_values,
size_t num_paths) {
std::vector<DbPath> db_paths(num_paths);
for (size_t i = 0; i < num_paths; ++i) {
db_paths[i] = dbpath_values[i]->rep;
}
opt->rep.db_paths = db_paths;
}
void rocksdb_options_set_env(rocksdb_options_t* opt, rocksdb_env_t* env) {
opt->rep.env = (env ? env->rep : nullptr);
}
@@ -2089,6 +2142,11 @@ void rocksdb_options_enable_statistics(rocksdb_options_t* opt) {
opt->rep.statistics = rocksdb::CreateDBStatistics();
}
void rocksdb_options_set_skip_stats_update_on_db_open(rocksdb_options_t* opt,
unsigned char val) {
opt->rep.skip_stats_update_on_db_open = val;
}
void rocksdb_options_set_num_levels(rocksdb_options_t* opt, int n) {
opt->rep.num_levels = n;
}
@@ -2239,11 +2297,21 @@ void rocksdb_options_set_use_adaptive_mutex(
opt->rep.use_adaptive_mutex = v;
}
void rocksdb_options_set_wal_bytes_per_sync(
rocksdb_options_t* opt, uint64_t v) {
opt->rep.wal_bytes_per_sync = v;
}
void rocksdb_options_set_bytes_per_sync(
rocksdb_options_t* opt, uint64_t v) {
opt->rep.bytes_per_sync = v;
}
void rocksdb_options_set_writable_file_max_buffer_size(rocksdb_options_t* opt,
uint64_t v) {
opt->rep.writable_file_max_buffer_size = v;
}
void rocksdb_options_set_allow_concurrent_memtable_write(rocksdb_options_t* opt,
unsigned char v) {
opt->rep.allow_concurrent_memtable_write = v;
@@ -2691,6 +2759,18 @@ void rocksdb_readoptions_set_iterate_upper_bound(
}
}
void rocksdb_readoptions_set_iterate_lower_bound(
rocksdb_readoptions_t *opt,
const char* key, size_t keylen) {
if (key == nullptr) {
opt->lower_bound = Slice();
opt->rep.iterate_lower_bound = nullptr;
} else {
opt->lower_bound = Slice(key, keylen);
opt->rep.iterate_lower_bound = &opt->lower_bound;
}
}
void rocksdb_readoptions_set_read_tier(
rocksdb_readoptions_t* opt, int v) {
opt->rep.read_tier = static_cast<rocksdb::ReadTier>(v);
@@ -2701,11 +2781,21 @@ void rocksdb_readoptions_set_tailing(
opt->rep.tailing = v;
}
void rocksdb_readoptions_set_managed(
rocksdb_readoptions_t* opt, unsigned char v) {
opt->rep.managed = v;
}
void rocksdb_readoptions_set_readahead_size(
rocksdb_readoptions_t* opt, size_t v) {
opt->rep.readahead_size = v;
}
void rocksdb_readoptions_set_prefix_same_as_start(
rocksdb_readoptions_t* opt, unsigned char v) {
opt->rep.prefix_same_as_start = v;
}
void rocksdb_readoptions_set_pin_data(rocksdb_readoptions_t* opt,
unsigned char v) {
opt->rep.pin_data = v;
@@ -2716,6 +2806,22 @@ void rocksdb_readoptions_set_total_order_seek(rocksdb_readoptions_t* opt,
opt->rep.total_order_seek = v;
}
void rocksdb_readoptions_set_max_skippable_internal_keys(
rocksdb_readoptions_t* opt,
uint64_t v) {
opt->rep.max_skippable_internal_keys = v;
}
void rocksdb_readoptions_set_background_purge_on_iterator_cleanup(
rocksdb_readoptions_t* opt, unsigned char v) {
opt->rep.background_purge_on_iterator_cleanup = v;
}
void rocksdb_readoptions_set_ignore_range_deletions(
rocksdb_readoptions_t* opt, unsigned char v) {
opt->rep.ignore_range_deletions = v;
}
rocksdb_writeoptions_t* rocksdb_writeoptions_create() {
return new rocksdb_writeoptions_t;
}
@@ -2733,6 +2839,24 @@ void rocksdb_writeoptions_disable_WAL(rocksdb_writeoptions_t* opt, int disable)
opt->rep.disableWAL = disable;
}
void rocksdb_writeoptions_set_ignore_missing_column_families(
rocksdb_writeoptions_t* opt,
unsigned char v) {
opt->rep.ignore_missing_column_families = v;
}
void rocksdb_writeoptions_set_no_slowdown(
rocksdb_writeoptions_t* opt,
unsigned char v) {
opt->rep.no_slowdown = v;
}
void rocksdb_writeoptions_set_low_pri(
rocksdb_writeoptions_t* opt,
unsigned char v) {
opt->rep.low_pri = v;
}
rocksdb_compactoptions_t* rocksdb_compactoptions_create() {
return new rocksdb_compactoptions_t;
}
@@ -2791,6 +2915,17 @@ size_t rocksdb_cache_get_pinned_usage(rocksdb_cache_t* cache) {
return cache->rep->GetPinnedUsage();
}
rocksdb_dbpath_t* rocksdb_dbpath_create(const char* path, uint64_t target_size) {
rocksdb_dbpath_t* result = new rocksdb_dbpath_t;
result->rep.path = std::string(path);
result->rep.target_size = target_size;
return result;
}
void rocksdb_dbpath_destroy(rocksdb_dbpath_t* dbpath) {
delete dbpath;
}
rocksdb_env_t* rocksdb_create_default_env() {
rocksdb_env_t* result = new rocksdb_env_t;
result->rep = Env::Default();
@@ -2852,7 +2987,26 @@ void rocksdb_sstfilewriter_open(rocksdb_sstfilewriter_t* writer,
void rocksdb_sstfilewriter_add(rocksdb_sstfilewriter_t* writer, const char* key,
size_t keylen, const char* val, size_t vallen,
char** errptr) {
SaveError(errptr, writer->rep->Add(Slice(key, keylen), Slice(val, vallen)));
SaveError(errptr, writer->rep->Put(Slice(key, keylen), Slice(val, vallen)));
}
void rocksdb_sstfilewriter_put(rocksdb_sstfilewriter_t* writer, const char* key,
size_t keylen, const char* val, size_t vallen,
char** errptr) {
SaveError(errptr, writer->rep->Put(Slice(key, keylen), Slice(val, vallen)));
}
void rocksdb_sstfilewriter_merge(rocksdb_sstfilewriter_t* writer,
const char* key, size_t keylen,
const char* val, size_t vallen,
char** errptr) {
SaveError(errptr, writer->rep->Merge(Slice(key, keylen), Slice(val, vallen)));
}
void rocksdb_sstfilewriter_delete(rocksdb_sstfilewriter_t* writer,
const char* key, size_t keylen,
char** errptr) {
SaveError(errptr, writer->rep->Delete(Slice(key, keylen)));
}
void rocksdb_sstfilewriter_finish(rocksdb_sstfilewriter_t* writer,
@@ -2895,6 +3049,12 @@ void rocksdb_ingestexternalfileoptions_set_allow_blocking_flush(
opt->rep.allow_blocking_flush = allow_blocking_flush;
}
void rocksdb_ingestexternalfileoptions_set_ingest_behind(
rocksdb_ingestexternalfileoptions_t* opt,
unsigned char ingest_behind) {
opt->rep.ingest_behind = ingest_behind;
}
void rocksdb_ingestexternalfileoptions_destroy(
rocksdb_ingestexternalfileoptions_t* opt) {
delete opt;
@@ -3206,6 +3366,32 @@ void rocksdb_transaction_options_set_max_write_batch_size(
opt->rep.max_write_batch_size = size;
}
rocksdb_optimistictransaction_options_t*
rocksdb_optimistictransaction_options_create() {
return new rocksdb_optimistictransaction_options_t;
}
void rocksdb_optimistictransaction_options_destroy(
rocksdb_optimistictransaction_options_t* opt) {
delete opt;
}
void rocksdb_optimistictransaction_options_set_set_snapshot(
rocksdb_optimistictransaction_options_t* opt, unsigned char v) {
opt->rep.set_snapshot = v;
}
rocksdb_column_family_handle_t* rocksdb_transactiondb_create_column_family(
rocksdb_transactiondb_t* txn_db,
const rocksdb_options_t* column_family_options,
const char* column_family_name, char** errptr) {
rocksdb_column_family_handle_t* handle = new rocksdb_column_family_handle_t;
SaveError(errptr, txn_db->rep->CreateColumnFamily(
ColumnFamilyOptions(column_family_options->rep),
std::string(column_family_name), &(handle->rep)));
return handle;
}
rocksdb_transactiondb_t* rocksdb_transactiondb_open(
const rocksdb_options_t* options,
const rocksdb_transactiondb_options_t* txn_db_options, const char* name,
@@ -3257,12 +3443,27 @@ void rocksdb_transaction_rollback(rocksdb_transaction_t* txn, char** errptr) {
SaveError(errptr, txn->rep->Rollback());
}
void rocksdb_transaction_set_savepoint(rocksdb_transaction_t* txn) {
txn->rep->SetSavePoint();
}
void rocksdb_transaction_rollback_to_savepoint(rocksdb_transaction_t* txn, char** errptr) {
SaveError(errptr, txn->rep->RollbackToSavePoint());
}
void rocksdb_transaction_destroy(rocksdb_transaction_t* txn) {
delete txn->rep;
delete txn;
}
//Read a key inside a transaction
const rocksdb_snapshot_t* rocksdb_transaction_get_snapshot(
rocksdb_transaction_t* txn) {
rocksdb_snapshot_t* result = new rocksdb_snapshot_t;
result->rep = txn->rep->GetSnapshot();
return result;
}
// Read a key inside a transaction
char* rocksdb_transaction_get(rocksdb_transaction_t* txn,
const rocksdb_readoptions_t* options,
const char* key, size_t klen, size_t* vlen,
@@ -3282,6 +3483,49 @@ char* rocksdb_transaction_get(rocksdb_transaction_t* txn,
return result;
}
char* rocksdb_transaction_get_cf(rocksdb_transaction_t* txn,
const rocksdb_readoptions_t* options,
rocksdb_column_family_handle_t* column_family,
const char* key, size_t klen, size_t* vlen,
char** errptr) {
char* result = nullptr;
std::string tmp;
Status s =
txn->rep->Get(options->rep, column_family->rep, Slice(key, klen), &tmp);
if (s.ok()) {
*vlen = tmp.size();
result = CopyString(tmp);
} else {
*vlen = 0;
if (!s.IsNotFound()) {
SaveError(errptr, s);
}
}
return result;
}
// Read a key inside a transaction
char* rocksdb_transaction_get_for_update(rocksdb_transaction_t* txn,
const rocksdb_readoptions_t* options,
const char* key, size_t klen,
size_t* vlen, unsigned char exclusive,
char** errptr) {
char* result = nullptr;
std::string tmp;
Status s =
txn->rep->GetForUpdate(options->rep, Slice(key, klen), &tmp, exclusive);
if (s.ok()) {
*vlen = tmp.size();
result = CopyString(tmp);
} else {
*vlen = 0;
if (!s.IsNotFound()) {
SaveError(errptr, s);
}
}
return result;
}
// Read a key outside a transaction
char* rocksdb_transactiondb_get(
rocksdb_transactiondb_t* txn_db,
@@ -3304,6 +3548,26 @@ char* rocksdb_transactiondb_get(
return result;
}
char* rocksdb_transactiondb_get_cf(
rocksdb_transactiondb_t* txn_db, const rocksdb_readoptions_t* options,
rocksdb_column_family_handle_t* column_family, const char* key,
size_t keylen, size_t* vallen, char** errptr) {
char* result = nullptr;
std::string tmp;
Status s = txn_db->rep->Get(options->rep, column_family->rep,
Slice(key, keylen), &tmp);
if (s.ok()) {
*vallen = tmp.size();
result = CopyString(tmp);
} else {
*vallen = 0;
if (!s.IsNotFound()) {
SaveError(errptr, s);
}
}
return result;
}
// Put a key inside a transaction
void rocksdb_transaction_put(rocksdb_transaction_t* txn, const char* key,
size_t klen, const char* val, size_t vlen,
@@ -3311,7 +3575,15 @@ void rocksdb_transaction_put(rocksdb_transaction_t* txn, const char* key,
SaveError(errptr, txn->rep->Put(Slice(key, klen), Slice(val, vlen)));
}
//Put a key outside a transaction
void rocksdb_transaction_put_cf(rocksdb_transaction_t* txn,
rocksdb_column_family_handle_t* column_family,
const char* key, size_t klen, const char* val,
size_t vlen, char** errptr) {
SaveError(errptr, txn->rep->Put(column_family->rep, Slice(key, klen),
Slice(val, vlen)));
}
// Put a key outside a transaction
void rocksdb_transactiondb_put(rocksdb_transactiondb_t* txn_db,
const rocksdb_writeoptions_t* options,
const char* key, size_t klen, const char* val,
@@ -3320,12 +3592,53 @@ void rocksdb_transactiondb_put(rocksdb_transactiondb_t* txn_db,
txn_db->rep->Put(options->rep, Slice(key, klen), Slice(val, vlen)));
}
void rocksdb_transactiondb_put_cf(rocksdb_transactiondb_t* txn_db,
const rocksdb_writeoptions_t* options,
rocksdb_column_family_handle_t* column_family,
const char* key, size_t keylen,
const char* val, size_t vallen,
char** errptr) {
SaveError(errptr, txn_db->rep->Put(options->rep, column_family->rep,
Slice(key, keylen), Slice(val, vallen)));
}
// Write batch into transaction db
void rocksdb_transactiondb_write(
rocksdb_transactiondb_t* db,
const rocksdb_writeoptions_t* options,
rocksdb_writebatch_t* batch,
char** errptr) {
SaveError(errptr, db->rep->Write(options->rep, &batch->rep));
}
// Merge a key inside a transaction
void rocksdb_transaction_merge(rocksdb_transaction_t* txn, const char* key,
size_t klen, const char* val, size_t vlen,
char** errptr) {
SaveError(errptr, txn->rep->Merge(Slice(key, klen), Slice(val, vlen)));
}
// Merge a key outside a transaction
void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
const rocksdb_writeoptions_t* options,
const char* key, size_t klen, const char* val,
size_t vlen, char** errptr) {
SaveError(errptr, txn_db->rep->Merge(options->rep, Slice(key, klen),
Slice(val, vlen)));
}
// Delete a key inside a transaction
void rocksdb_transaction_delete(rocksdb_transaction_t* txn, const char* key,
size_t klen, char** errptr) {
SaveError(errptr, txn->rep->Delete(Slice(key, klen)));
}
void rocksdb_transaction_delete_cf(
rocksdb_transaction_t* txn, rocksdb_column_family_handle_t* column_family,
const char* key, size_t klen, char** errptr) {
SaveError(errptr, txn->rep->Delete(column_family->rep, Slice(key, klen)));
}
// Delete a key outside a transaction
void rocksdb_transactiondb_delete(rocksdb_transactiondb_t* txn_db,
const rocksdb_writeoptions_t* options,
@@ -3333,6 +3646,14 @@ void rocksdb_transactiondb_delete(rocksdb_transactiondb_t* txn_db,
SaveError(errptr, txn_db->rep->Delete(options->rep, Slice(key, klen)));
}
void rocksdb_transactiondb_delete_cf(
rocksdb_transactiondb_t* txn_db, const rocksdb_writeoptions_t* options,
rocksdb_column_family_handle_t* column_family, const char* key,
size_t keylen, char** errptr) {
SaveError(errptr, txn_db->rep->Delete(options->rep, column_family->rep,
Slice(key, keylen)));
}
// Create an iterator inside a transaction
rocksdb_iterator_t* rocksdb_transaction_create_iterator(
rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options) {
@@ -3341,6 +3662,23 @@ rocksdb_iterator_t* rocksdb_transaction_create_iterator(
return result;
}
// Create an iterator inside a transaction with column family
rocksdb_iterator_t* rocksdb_transaction_create_iterator_cf(
rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
rocksdb_column_family_handle_t* column_family) {
rocksdb_iterator_t* result = new rocksdb_iterator_t;
result->rep = txn->rep->GetIterator(options->rep, column_family->rep);
return result;
}
// Create an iterator outside a transaction
rocksdb_iterator_t* rocksdb_transactiondb_create_iterator(
rocksdb_transactiondb_t* txn_db, const rocksdb_readoptions_t* options) {
rocksdb_iterator_t* result = new rocksdb_iterator_t;
result->rep = txn_db->rep->NewIterator(options->rep);
return result;
}
void rocksdb_transactiondb_close(rocksdb_transactiondb_t* txn_db) {
delete txn_db->rep;
delete txn_db;
@@ -3357,6 +3695,91 @@ rocksdb_checkpoint_t* rocksdb_transactiondb_checkpoint_object_create(
return result;
}
rocksdb_optimistictransactiondb_t* rocksdb_optimistictransactiondb_open(
const rocksdb_options_t* options, const char* name, char** errptr) {
OptimisticTransactionDB* otxn_db;
if (SaveError(errptr, OptimisticTransactionDB::Open(
options->rep, std::string(name), &otxn_db))) {
return nullptr;
}
rocksdb_optimistictransactiondb_t* result =
new rocksdb_optimistictransactiondb_t;
result->rep = otxn_db;
return result;
}
rocksdb_optimistictransactiondb_t*
rocksdb_optimistictransactiondb_open_column_families(
const rocksdb_options_t* db_options, const char* name,
int num_column_families, const char** column_family_names,
const rocksdb_options_t** column_family_options,
rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
std::vector<ColumnFamilyDescriptor> column_families;
for (int i = 0; i < num_column_families; i++) {
column_families.push_back(ColumnFamilyDescriptor(
std::string(column_family_names[i]),
ColumnFamilyOptions(column_family_options[i]->rep)));
}
OptimisticTransactionDB* otxn_db;
std::vector<ColumnFamilyHandle*> handles;
if (SaveError(errptr, OptimisticTransactionDB::Open(
DBOptions(db_options->rep), std::string(name),
column_families, &handles, &otxn_db))) {
return nullptr;
}
for (size_t i = 0; i < handles.size(); i++) {
rocksdb_column_family_handle_t* c_handle =
new rocksdb_column_family_handle_t;
c_handle->rep = handles[i];
column_family_handles[i] = c_handle;
}
rocksdb_optimistictransactiondb_t* result =
new rocksdb_optimistictransactiondb_t;
result->rep = otxn_db;
return result;
}
rocksdb_t* rocksdb_optimistictransactiondb_get_base_db(
rocksdb_optimistictransactiondb_t* otxn_db) {
DB* base_db = otxn_db->rep->GetBaseDB();
if (base_db != nullptr) {
rocksdb_t* result = new rocksdb_t;
result->rep = base_db;
return result;
}
return nullptr;
}
void rocksdb_optimistictransactiondb_close_base_db(rocksdb_t* base_db) {
delete base_db;
}
rocksdb_transaction_t* rocksdb_optimistictransaction_begin(
rocksdb_optimistictransactiondb_t* otxn_db,
const rocksdb_writeoptions_t* write_options,
const rocksdb_optimistictransaction_options_t* otxn_options,
rocksdb_transaction_t* old_txn) {
if (old_txn == nullptr) {
rocksdb_transaction_t* result = new rocksdb_transaction_t;
result->rep = otxn_db->rep->BeginTransaction(write_options->rep,
otxn_options->rep, nullptr);
return result;
}
old_txn->rep = otxn_db->rep->BeginTransaction(
write_options->rep, otxn_options->rep, old_txn->rep);
return old_txn;
}
void rocksdb_optimistictransactiondb_close(
rocksdb_optimistictransactiondb_t* otxn_db) {
delete otxn_db->rep;
delete otxn_db;
}
void rocksdb_free(void* ptr) { free(ptr); }
rocksdb_pinnableslice_t* rocksdb_get_pinned(
+204 -6
View File
@@ -41,6 +41,7 @@ static char dbname[200];
static char sstfilename[200];
static char dbbackupname[200];
static char dbcheckpointname[200];
static char dbpathname[200];
static void StartPhase(const char* name) {
fprintf(stderr, "=== Test %s\n", name);
@@ -333,6 +334,20 @@ static void CheckTxnGet(
Free(&val);
}
static void CheckTxnGetCF(rocksdb_transaction_t* txn,
const rocksdb_readoptions_t* options,
rocksdb_column_family_handle_t* column_family,
const char* key, const char* expected) {
char* err = NULL;
size_t val_len;
char* val;
val = rocksdb_transaction_get_cf(txn, options, column_family, key,
strlen(key), &val_len, &err);
CheckNoError(err);
CheckEqual(expected, val, val_len);
Free(&val);
}
static void CheckTxnDBGet(
rocksdb_transactiondb_t* txn_db,
const rocksdb_readoptions_t* options,
@@ -347,10 +362,25 @@ static void CheckTxnDBGet(
Free(&val);
}
static void CheckTxnDBGetCF(rocksdb_transactiondb_t* txn_db,
const rocksdb_readoptions_t* options,
rocksdb_column_family_handle_t* column_family,
const char* key, const char* expected) {
char* err = NULL;
size_t val_len;
char* val;
val = rocksdb_transactiondb_get_cf(txn_db, options, column_family, key,
strlen(key), &val_len, &err);
CheckNoError(err);
CheckEqual(expected, val, val_len);
Free(&val);
}
int main(int argc, char** argv) {
rocksdb_t* db;
rocksdb_comparator_t* cmp;
rocksdb_cache_t* cache;
rocksdb_dbpath_t *dbpath;
rocksdb_env_t* env;
rocksdb_options_t* options;
rocksdb_compactoptions_t* coptions;
@@ -362,6 +392,8 @@ int main(int argc, char** argv) {
rocksdb_transactiondb_options_t* txn_db_options;
rocksdb_transaction_t* txn;
rocksdb_transaction_options_t* txn_options;
rocksdb_optimistictransactiondb_t* otxn_db;
rocksdb_optimistictransaction_options_t* otxn_options;
char* err = NULL;
int run = -1;
@@ -385,8 +417,14 @@ int main(int argc, char** argv) {
GetTempDir(),
((int)geteuid()));
snprintf(dbpathname, sizeof(dbpathname),
"%s/rocksdb_c_test-%d-dbpath",
GetTempDir(),
((int) geteuid()));
StartPhase("create_objects");
cmp = rocksdb_comparator_create(NULL, CmpDestroy, CmpCompare, CmpName);
dbpath = rocksdb_dbpath_create(dbpathname, 1024 * 1024);
env = rocksdb_create_default_env();
cache = rocksdb_cache_create_lru(100000);
@@ -569,11 +607,11 @@ int main(int argc, char** argv) {
unlink(sstfilename);
rocksdb_sstfilewriter_open(writer, sstfilename, &err);
CheckNoError(err);
rocksdb_sstfilewriter_add(writer, "sstk1", 5, "v1", 2, &err);
rocksdb_sstfilewriter_put(writer, "sstk1", 5, "v1", 2, &err);
CheckNoError(err);
rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v2", 2, &err);
rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v2", 2, &err);
CheckNoError(err);
rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v3", 2, &err);
rocksdb_sstfilewriter_put(writer, "sstk3", 5, "v3", 2, &err);
CheckNoError(err);
rocksdb_sstfilewriter_finish(writer, &err);
CheckNoError(err);
@@ -590,11 +628,11 @@ int main(int argc, char** argv) {
unlink(sstfilename);
rocksdb_sstfilewriter_open(writer, sstfilename, &err);
CheckNoError(err);
rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v4", 2, &err);
rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v4", 2, &err);
CheckNoError(err);
rocksdb_sstfilewriter_add(writer, "sstk22", 6, "v5", 2, &err);
rocksdb_sstfilewriter_put(writer, "sstk22", 6, "v5", 2, &err);
CheckNoError(err);
rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v6", 2, &err);
rocksdb_sstfilewriter_put(writer, "sstk3", 5, "v6", 2, &err);
CheckNoError(err);
rocksdb_sstfilewriter_finish(writer, &err);
CheckNoError(err);
@@ -1357,6 +1395,18 @@ int main(int argc, char** argv) {
CheckNoError(err);
CheckTxnDBGet(txn_db, roptions, "foo", NULL);
// write batch into TransactionDB
rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
rocksdb_writebatch_put(wb, "foo", 3, "a", 1);
rocksdb_writebatch_clear(wb);
rocksdb_writebatch_put(wb, "bar", 3, "b", 1);
rocksdb_writebatch_put(wb, "box", 3, "c", 1);
rocksdb_writebatch_delete(wb, "bar", 3);
rocksdb_transactiondb_write(txn_db, woptions, wb, &err);
rocksdb_writebatch_destroy(wb);
CheckTxnDBGet(txn_db, roptions, "box", "c");
CheckNoError(err);
// begin a transaction
txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
// put
@@ -1413,6 +1463,42 @@ int main(int argc, char** argv) {
CheckNoError(err);
CheckTxnDBGet(txn_db, roptions, "bar", NULL);
// save point
rocksdb_transaction_put(txn, "foo1", 4, "hi1", 3, &err);
rocksdb_transaction_set_savepoint(txn);
CheckTxnGet(txn, roptions, "foo1", "hi1");
rocksdb_transaction_put(txn, "foo2", 4, "hi2", 3, &err);
CheckTxnGet(txn, roptions, "foo2", "hi2");
// rollback to savepoint
rocksdb_transaction_rollback_to_savepoint(txn, &err);
CheckNoError(err);
CheckTxnGet(txn, roptions, "foo2", NULL);
CheckTxnGet(txn, roptions, "foo1", "hi1");
CheckTxnDBGet(txn_db, roptions, "foo1", NULL);
CheckTxnDBGet(txn_db, roptions, "foo2", NULL);
rocksdb_transaction_commit(txn, &err);
CheckNoError(err);
CheckTxnDBGet(txn_db, roptions, "foo1", "hi1");
CheckTxnDBGet(txn_db, roptions, "foo2", NULL);
// Column families.
rocksdb_column_family_handle_t* cfh;
cfh = rocksdb_transactiondb_create_column_family(txn_db, options,
"txn_db_cf", &err);
CheckNoError(err);
rocksdb_transactiondb_put_cf(txn_db, woptions, cfh, "cf_foo", 6, "cf_hello",
8, &err);
CheckNoError(err);
CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", "cf_hello");
rocksdb_transactiondb_delete_cf(txn_db, woptions, cfh, "cf_foo", 6, &err);
CheckNoError(err);
CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
rocksdb_column_family_handle_destroy(cfh);
// close and destroy
rocksdb_transaction_destroy(txn);
rocksdb_transactiondb_close(txn_db);
@@ -1422,6 +1508,105 @@ int main(int argc, char** argv) {
rocksdb_transactiondb_options_destroy(txn_db_options);
}
StartPhase("optimistic_transactions");
{
rocksdb_options_t* db_options = rocksdb_options_create();
rocksdb_options_set_create_if_missing(db_options, 1);
rocksdb_options_set_allow_concurrent_memtable_write(db_options, 1);
otxn_db = rocksdb_optimistictransactiondb_open(db_options, dbname, &err);
otxn_options = rocksdb_optimistictransaction_options_create();
rocksdb_transaction_t* txn1 = rocksdb_optimistictransaction_begin(
otxn_db, woptions, otxn_options, NULL);
rocksdb_transaction_t* txn2 = rocksdb_optimistictransaction_begin(
otxn_db, woptions, otxn_options, NULL);
rocksdb_transaction_put(txn1, "key", 3, "value", 5, &err);
CheckNoError(err);
rocksdb_transaction_put(txn2, "key1", 4, "value1", 6, &err);
CheckNoError(err);
CheckTxnGet(txn1, roptions, "key", "value");
rocksdb_transaction_commit(txn1, &err);
CheckNoError(err);
rocksdb_transaction_commit(txn2, &err);
CheckNoError(err);
rocksdb_transaction_destroy(txn1);
rocksdb_transaction_destroy(txn2);
// Check column family
db = rocksdb_optimistictransactiondb_get_base_db(otxn_db);
rocksdb_put(db, woptions, "key", 3, "value", 5, &err);
CheckNoError(err);
rocksdb_column_family_handle_t *cfh1, *cfh2;
cfh1 = rocksdb_create_column_family(db, db_options, "txn_db_cf1", &err);
cfh2 = rocksdb_create_column_family(db, db_options, "txn_db_cf2", &err);
txn = rocksdb_optimistictransaction_begin(otxn_db, woptions, otxn_options,
NULL);
rocksdb_transaction_put_cf(txn, cfh1, "key_cf1", 7, "val_cf1", 7, &err);
CheckNoError(err);
rocksdb_transaction_put_cf(txn, cfh2, "key_cf2", 7, "val_cf2", 7, &err);
CheckNoError(err);
rocksdb_transaction_commit(txn, &err);
CheckNoError(err);
txn = rocksdb_optimistictransaction_begin(otxn_db, woptions, otxn_options,
txn);
CheckGetCF(db, roptions, cfh1, "key_cf1", "val_cf1");
CheckTxnGetCF(txn, roptions, cfh1, "key_cf1", "val_cf1");
// Check iterator with column family
rocksdb_transaction_put_cf(txn, cfh1, "key1_cf", 7, "val1_cf", 7, &err);
CheckNoError(err);
rocksdb_iterator_t* iter =
rocksdb_transaction_create_iterator_cf(txn, roptions, cfh1);
CheckCondition(!rocksdb_iter_valid(iter));
rocksdb_iter_seek_to_first(iter);
CheckCondition(rocksdb_iter_valid(iter));
CheckIter(iter, "key1_cf", "val1_cf");
rocksdb_iter_get_error(iter, &err);
CheckNoError(err);
rocksdb_iter_destroy(iter);
rocksdb_transaction_destroy(txn);
rocksdb_column_family_handle_destroy(cfh1);
rocksdb_column_family_handle_destroy(cfh2);
rocksdb_optimistictransactiondb_close_base_db(db);
rocksdb_optimistictransactiondb_close(otxn_db);
// Check open optimistic transaction db with column families
size_t cf_len;
char** column_fams =
rocksdb_list_column_families(db_options, dbname, &cf_len, &err);
CheckNoError(err);
CheckEqual("default", column_fams[0], 7);
CheckEqual("txn_db_cf1", column_fams[1], 10);
CheckEqual("txn_db_cf2", column_fams[2], 10);
CheckCondition(cf_len == 3);
rocksdb_list_column_families_destroy(column_fams, cf_len);
const char* cf_names[3] = {"default", "txn_db_cf1", "txn_db_cf2"};
rocksdb_options_t* cf_options = rocksdb_options_create();
const rocksdb_options_t* cf_opts[3] = {cf_options, cf_options, cf_options};
rocksdb_options_set_error_if_exists(cf_options, 0);
rocksdb_column_family_handle_t* cf_handles[3];
otxn_db = rocksdb_optimistictransactiondb_open_column_families(
db_options, dbname, 3, cf_names, cf_opts, cf_handles, &err);
CheckNoError(err);
rocksdb_transaction_t* txn_cf = rocksdb_optimistictransaction_begin(
otxn_db, woptions, otxn_options, NULL);
CheckTxnGetCF(txn_cf, roptions, cf_handles[0], "key", "value");
CheckTxnGetCF(txn_cf, roptions, cf_handles[1], "key_cf1", "val_cf1");
CheckTxnGetCF(txn_cf, roptions, cf_handles[2], "key_cf2", "val_cf2");
rocksdb_transaction_destroy(txn_cf);
rocksdb_options_destroy(cf_options);
rocksdb_column_family_handle_destroy(cf_handles[0]);
rocksdb_column_family_handle_destroy(cf_handles[1]);
rocksdb_column_family_handle_destroy(cf_handles[2]);
rocksdb_optimistictransactiondb_close(otxn_db);
rocksdb_destroy_db(db_options, dbname, &err);
rocksdb_options_destroy(db_options);
rocksdb_optimistictransaction_options_destroy(otxn_options);
CheckNoError(err);
}
// Simple sanity check that setting memtable rep works.
StartPhase("memtable_reps");
{
@@ -1440,6 +1625,18 @@ int main(int argc, char** argv) {
CheckNoError(err);
}
// Simple sanity check that options setting db_paths work.
StartPhase("open_db_paths");
{
rocksdb_close(db);
rocksdb_destroy_db(options, dbname, &err);
const rocksdb_dbpath_t* paths[1] = {dbpath};
rocksdb_options_set_db_paths(options, paths, 1);
db = rocksdb_open(options, dbname, &err);
CheckNoError(err);
}
StartPhase("cleanup");
rocksdb_close(db);
rocksdb_options_destroy(options);
@@ -1449,6 +1646,7 @@ int main(int argc, char** argv) {
rocksdb_compactoptions_destroy(coptions);
rocksdb_cache_destroy(cache);
rocksdb_comparator_destroy(cmp);
rocksdb_dbpath_destroy(dbpath);
rocksdb_env_destroy(env);
fprintf(stderr, "PASS\n");
+175 -70
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -125,6 +123,22 @@ Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
" is not linked with the binary.");
}
}
if (cf_options.compression_opts.zstd_max_train_bytes > 0) {
if (!CompressionTypeSupported(CompressionType::kZSTD)) {
// Dictionary trainer is available since v0.6.1, but ZSTD was marked
// stable only since v0.8.0. For now we enable the feature in stable
// versions only.
return Status::InvalidArgument(
"zstd dictionary trainer cannot be used because " +
CompressionTypeToString(CompressionType::kZSTD) +
" is not linked with the binary.");
}
if (cf_options.compression_opts.max_dict_bytes == 0) {
return Status::InvalidArgument(
"The dictionary size limit (`CompressionOptions::max_dict_bytes`) "
"should be nonzero if we're using zstd's dictionary generator.");
}
}
return Status::OK();
}
@@ -330,12 +344,13 @@ void SuperVersionUnrefHandle(void* ptr) {
// When latter happens, we are in ~ColumnFamilyData(), no get should happen as
// well.
SuperVersion* sv = static_cast<SuperVersion*>(ptr);
if (sv->Unref()) {
sv->db_mutex->Lock();
sv->Cleanup();
sv->db_mutex->Unlock();
delete sv;
}
bool was_last_ref __attribute__((__unused__));
was_last_ref = sv->Unref();
// Thread-local SuperVersions can't outlive ColumnFamilyData::super_version_.
// This is important because we can't do SuperVersion cleanup here.
// That would require locking DB mutex, which would deadlock because
// SuperVersionUnrefHandle is called with locked ThreadLocalPtr mutex.
assert(!was_last_ref);
}
} // anonymous namespace
@@ -349,13 +364,14 @@ ColumnFamilyData::ColumnFamilyData(
dummy_versions_(_dummy_versions),
current_(nullptr),
refs_(0),
initialized_(false),
dropped_(false),
internal_comparator_(cf_options.comparator),
initial_cf_options_(SanitizeOptions(db_options, cf_options)),
ioptions_(db_options, initial_cf_options_),
mutable_cf_options_(initial_cf_options_),
is_delete_range_supported_(strcmp(cf_options.table_factory->Name(),
BlockBasedTableFactory().Name()) == 0),
is_delete_range_supported_(
cf_options.table_factory->IsDeleteRangeSupported()),
write_buffer_manager_(write_buffer_manager),
mem_(nullptr),
imm_(ioptions_.min_write_buffer_number_to_merge,
@@ -366,11 +382,13 @@ ColumnFamilyData::ColumnFamilyData(
next_(nullptr),
prev_(nullptr),
log_number_(0),
flush_reason_(FlushReason::kUnknown),
column_family_set_(column_family_set),
pending_flush_(false),
pending_compaction_(false),
prev_compaction_needed_bytes_(0),
allow_2pc_(db_options.allow_2pc) {
allow_2pc_(db_options.allow_2pc),
last_memtable_id_(0) {
Ref();
// Convert user defined table properties collector factories to internal ones.
@@ -453,7 +471,7 @@ ColumnFamilyData::~ColumnFamilyData() {
local_sv_.reset();
super_version_->db_mutex->Lock();
bool is_last_reference __attribute__((unused));
bool is_last_reference __attribute__((__unused__));
is_last_reference = super_version_->Unref();
assert(is_last_reference);
super_version_->Cleanup();
@@ -464,7 +482,8 @@ ColumnFamilyData::~ColumnFamilyData() {
if (dummy_versions_ != nullptr) {
// List must be empty
assert(dummy_versions_->TEST_Next() == dummy_versions_);
bool deleted __attribute__((unused)) = dummy_versions_->Unref();
bool deleted __attribute__((__unused__));
deleted = dummy_versions_->Unref();
assert(deleted);
}
@@ -551,7 +570,7 @@ std::unique_ptr<WriteControllerToken> SetupDelay(
// If DB just falled into the stop condition, we need to further reduce
// the write rate to avoid the stop condition.
if (penalize_stop) {
// Penalize the near stop or stop condition by more agressive slowdown.
// Penalize the near stop or stop condition by more aggressive slowdown.
// This is to provide the long term slowdown increase signal.
// The penalty is more than the reward of recovering to the normal
// condition.
@@ -614,58 +633,97 @@ int GetL0ThresholdSpeedupCompaction(int level0_file_num_compaction_trigger,
}
} // namespace
void ColumnFamilyData::RecalculateWriteStallConditions(
std::pair<WriteStallCondition, ColumnFamilyData::WriteStallCause>
ColumnFamilyData::GetWriteStallConditionAndCause(
int num_unflushed_memtables, int num_l0_files,
uint64_t num_compaction_needed_bytes,
const MutableCFOptions& mutable_cf_options) {
if (num_unflushed_memtables >= mutable_cf_options.max_write_buffer_number) {
return {WriteStallCondition::kStopped, WriteStallCause::kMemtableLimit};
} else if (!mutable_cf_options.disable_auto_compactions &&
num_l0_files >= mutable_cf_options.level0_stop_writes_trigger) {
return {WriteStallCondition::kStopped, WriteStallCause::kL0FileCountLimit};
} else if (!mutable_cf_options.disable_auto_compactions &&
mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
num_compaction_needed_bytes >=
mutable_cf_options.hard_pending_compaction_bytes_limit) {
return {WriteStallCondition::kStopped,
WriteStallCause::kPendingCompactionBytes};
} else if (mutable_cf_options.max_write_buffer_number > 3 &&
num_unflushed_memtables >=
mutable_cf_options.max_write_buffer_number - 1) {
return {WriteStallCondition::kDelayed, WriteStallCause::kMemtableLimit};
} else if (!mutable_cf_options.disable_auto_compactions &&
mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
num_l0_files >=
mutable_cf_options.level0_slowdown_writes_trigger) {
return {WriteStallCondition::kDelayed, WriteStallCause::kL0FileCountLimit};
} else if (!mutable_cf_options.disable_auto_compactions &&
mutable_cf_options.soft_pending_compaction_bytes_limit > 0 &&
num_compaction_needed_bytes >=
mutable_cf_options.soft_pending_compaction_bytes_limit) {
return {WriteStallCondition::kDelayed,
WriteStallCause::kPendingCompactionBytes};
}
return {WriteStallCondition::kNormal, WriteStallCause::kNone};
}
WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
const MutableCFOptions& mutable_cf_options) {
auto write_stall_condition = WriteStallCondition::kNormal;
if (current_ != nullptr) {
auto* vstorage = current_->storage_info();
auto write_controller = column_family_set_->write_controller_;
uint64_t compaction_needed_bytes =
vstorage->estimated_compaction_needed_bytes();
auto write_stall_condition_and_cause = GetWriteStallConditionAndCause(
imm()->NumNotFlushed(), vstorage->l0_delay_trigger_count(),
vstorage->estimated_compaction_needed_bytes(), mutable_cf_options);
write_stall_condition = write_stall_condition_and_cause.first;
auto write_stall_cause = write_stall_condition_and_cause.second;
bool was_stopped = write_controller->IsStopped();
bool needed_delay = write_controller->NeedsDelay();
if (imm()->NumNotFlushed() >= mutable_cf_options.max_write_buffer_number) {
if (write_stall_condition == WriteStallCondition::kStopped &&
write_stall_cause == WriteStallCause::kMemtableLimit) {
write_controller_token_ = write_controller->GetStopToken();
internal_stats_->AddCFStats(InternalStats::MEMTABLE_COMPACTION, 1);
internal_stats_->AddCFStats(InternalStats::MEMTABLE_LIMIT_STOPS, 1);
ROCKS_LOG_WARN(
ioptions_.info_log,
"[%s] Stopping writes because we have %d immutable memtables "
"(waiting for flush), max_write_buffer_number is set to %d",
name_.c_str(), imm()->NumNotFlushed(),
mutable_cf_options.max_write_buffer_number);
} else if (!mutable_cf_options.disable_auto_compactions &&
vstorage->l0_delay_trigger_count() >=
mutable_cf_options.level0_stop_writes_trigger) {
} else if (write_stall_condition == WriteStallCondition::kStopped &&
write_stall_cause == WriteStallCause::kL0FileCountLimit) {
write_controller_token_ = write_controller->GetStopToken();
internal_stats_->AddCFStats(InternalStats::LEVEL0_NUM_FILES_TOTAL, 1);
internal_stats_->AddCFStats(InternalStats::L0_FILE_COUNT_LIMIT_STOPS, 1);
if (compaction_picker_->IsLevel0CompactionInProgress()) {
internal_stats_->AddCFStats(
InternalStats::LEVEL0_NUM_FILES_WITH_COMPACTION, 1);
InternalStats::LOCKED_L0_FILE_COUNT_LIMIT_STOPS, 1);
}
ROCKS_LOG_WARN(ioptions_.info_log,
"[%s] Stopping writes because we have %d level-0 files",
name_.c_str(), vstorage->l0_delay_trigger_count());
} else if (!mutable_cf_options.disable_auto_compactions &&
mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
compaction_needed_bytes >=
mutable_cf_options.hard_pending_compaction_bytes_limit) {
} else if (write_stall_condition == WriteStallCondition::kStopped &&
write_stall_cause == WriteStallCause::kPendingCompactionBytes) {
write_controller_token_ = write_controller->GetStopToken();
internal_stats_->AddCFStats(
InternalStats::HARD_PENDING_COMPACTION_BYTES_LIMIT, 1);
InternalStats::PENDING_COMPACTION_BYTES_LIMIT_STOPS, 1);
ROCKS_LOG_WARN(
ioptions_.info_log,
"[%s] Stopping writes because of estimated pending compaction "
"bytes %" PRIu64,
name_.c_str(), compaction_needed_bytes);
} else if (mutable_cf_options.max_write_buffer_number > 3 &&
imm()->NumNotFlushed() >=
mutable_cf_options.max_write_buffer_number - 1) {
} else if (write_stall_condition == WriteStallCondition::kDelayed &&
write_stall_cause == WriteStallCause::kMemtableLimit) {
write_controller_token_ =
SetupDelay(write_controller, compaction_needed_bytes,
prev_compaction_needed_bytes_, was_stopped,
mutable_cf_options.disable_auto_compactions);
internal_stats_->AddCFStats(InternalStats::MEMTABLE_SLOWDOWN, 1);
internal_stats_->AddCFStats(InternalStats::MEMTABLE_LIMIT_SLOWDOWNS, 1);
ROCKS_LOG_WARN(
ioptions_.info_log,
"[%s] Stalling writes because we have %d immutable memtables "
@@ -674,10 +732,8 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
name_.c_str(), imm()->NumNotFlushed(),
mutable_cf_options.max_write_buffer_number,
write_controller->delayed_write_rate());
} else if (!mutable_cf_options.disable_auto_compactions &&
mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
vstorage->l0_delay_trigger_count() >=
mutable_cf_options.level0_slowdown_writes_trigger) {
} else if (write_stall_condition == WriteStallCondition::kDelayed &&
write_stall_cause == WriteStallCause::kL0FileCountLimit) {
// L0 is the last two files from stopping.
bool near_stop = vstorage->l0_delay_trigger_count() >=
mutable_cf_options.level0_stop_writes_trigger - 2;
@@ -685,20 +741,19 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
SetupDelay(write_controller, compaction_needed_bytes,
prev_compaction_needed_bytes_, was_stopped || near_stop,
mutable_cf_options.disable_auto_compactions);
internal_stats_->AddCFStats(InternalStats::LEVEL0_SLOWDOWN_TOTAL, 1);
internal_stats_->AddCFStats(InternalStats::L0_FILE_COUNT_LIMIT_SLOWDOWNS,
1);
if (compaction_picker_->IsLevel0CompactionInProgress()) {
internal_stats_->AddCFStats(
InternalStats::LEVEL0_SLOWDOWN_WITH_COMPACTION, 1);
InternalStats::LOCKED_L0_FILE_COUNT_LIMIT_SLOWDOWNS, 1);
}
ROCKS_LOG_WARN(ioptions_.info_log,
"[%s] Stalling writes because we have %d level-0 files "
"rate %" PRIu64,
name_.c_str(), vstorage->l0_delay_trigger_count(),
write_controller->delayed_write_rate());
} else if (!mutable_cf_options.disable_auto_compactions &&
mutable_cf_options.soft_pending_compaction_bytes_limit > 0 &&
vstorage->estimated_compaction_needed_bytes() >=
mutable_cf_options.soft_pending_compaction_bytes_limit) {
} else if (write_stall_condition == WriteStallCondition::kDelayed &&
write_stall_cause == WriteStallCause::kPendingCompactionBytes) {
// If the distance to hard limit is less than 1/4 of the gap between soft
// and
// hard bytes limit, we think it is near stop and speed up the slowdown.
@@ -715,7 +770,7 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
prev_compaction_needed_bytes_, was_stopped || near_stop,
mutable_cf_options.disable_auto_compactions);
internal_stats_->AddCFStats(
InternalStats::SOFT_PENDING_COMPACTION_BYTES_LIMIT, 1);
InternalStats::PENDING_COMPACTION_BYTES_LIMIT_SLOWDOWNS, 1);
ROCKS_LOG_WARN(
ioptions_.info_log,
"[%s] Stalling writes because of estimated pending compaction "
@@ -723,13 +778,14 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
name_.c_str(), vstorage->estimated_compaction_needed_bytes(),
write_controller->delayed_write_rate());
} else {
assert(write_stall_condition == WriteStallCondition::kNormal);
if (vstorage->l0_delay_trigger_count() >=
GetL0ThresholdSpeedupCompaction(
mutable_cf_options.level0_file_num_compaction_trigger,
mutable_cf_options.level0_slowdown_writes_trigger)) {
write_controller_token_ =
write_controller->GetCompactionPressureToken();
ROCKS_LOG_WARN(
ROCKS_LOG_INFO(
ioptions_.info_log,
"[%s] Increasing compaction threads because we have %d level-0 "
"files ",
@@ -743,7 +799,7 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
write_controller_token_ =
write_controller->GetCompactionPressureToken();
if (mutable_cf_options.soft_pending_compaction_bytes_limit > 0) {
ROCKS_LOG_WARN(
ROCKS_LOG_INFO(
ioptions_.info_log,
"[%s] Increasing compaction threads because of estimated pending "
"compaction "
@@ -760,10 +816,17 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
uint64_t write_rate = write_controller->delayed_write_rate();
write_controller->set_delayed_write_rate(static_cast<uint64_t>(
static_cast<double>(write_rate) * kDelayRecoverSlowdownRatio));
// Set the low pri limit to be 1/4 the delayed write rate.
// Note we don't reset this value even after delay condition is relased.
// Low-pri rate will continue to apply if there is a compaction
// pressure.
write_controller->low_pri_rate_limiter()->SetBytesPerSecond(write_rate /
4);
}
}
prev_compaction_needed_bytes_ = compaction_needed_bytes;
}
return write_stall_condition;
}
const EnvOptions* ColumnFamilyData::soptions() const {
@@ -785,7 +848,7 @@ uint64_t ColumnFamilyData::GetTotalSstFilesSize() const {
MemTable* ColumnFamilyData::ConstructNewMemtable(
const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
return new MemTable(internal_comparator_, ioptions_, mutable_cf_options,
write_buffer_manager_, earliest_seq);
write_buffer_manager_, earliest_seq, id_);
}
void ColumnFamilyData::CreateNewMemtable(
@@ -836,10 +899,13 @@ Compaction* ColumnFamilyData::CompactRange(
SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
InstrumentedMutex* db_mutex) {
SuperVersion* sv = nullptr;
sv = GetThreadLocalSuperVersion(db_mutex);
SuperVersion* sv = GetThreadLocalSuperVersion(db_mutex);
sv->Ref();
if (!ReturnThreadLocalSuperVersion(sv)) {
// This Unref() corresponds to the Ref() in GetThreadLocalSuperVersion()
// when the thread-local pointer was populated. So, the Ref() earlier in
// this function still prevents the returned SuperVersion* from being
// deleted out from under the caller.
sv->Unref();
}
return sv;
@@ -847,7 +913,6 @@ SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
InstrumentedMutex* db_mutex) {
SuperVersion* sv = nullptr;
// The SuperVersion is cached in thread local storage to avoid acquiring
// mutex when SuperVersion does not change since the last use. When a new
// SuperVersion is installed, the compaction or flush thread cleans up
@@ -866,7 +931,7 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
// should only keep kSVInUse before ReturnThreadLocalSuperVersion call
// (if no Scrape happens).
assert(ptr != SuperVersion::kSVInUse);
sv = static_cast<SuperVersion*>(ptr);
SuperVersion* sv = static_cast<SuperVersion*>(ptr);
if (sv == SuperVersion::kSVObsolete ||
sv->version_number != super_version_number_.load()) {
RecordTick(ioptions_.statistics, NUMBER_SUPERVERSION_ACQUIRES);
@@ -909,15 +974,16 @@ bool ColumnFamilyData::ReturnThreadLocalSuperVersion(SuperVersion* sv) {
return false;
}
SuperVersion* ColumnFamilyData::InstallSuperVersion(
SuperVersion* new_superversion, InstrumentedMutex* db_mutex) {
void ColumnFamilyData::InstallSuperVersion(
SuperVersionContext* sv_context, InstrumentedMutex* db_mutex) {
db_mutex->AssertHeld();
return InstallSuperVersion(new_superversion, db_mutex, mutable_cf_options_);
return InstallSuperVersion(sv_context, db_mutex, mutable_cf_options_);
}
SuperVersion* ColumnFamilyData::InstallSuperVersion(
SuperVersion* new_superversion, InstrumentedMutex* db_mutex,
void ColumnFamilyData::InstallSuperVersion(
SuperVersionContext* sv_context, InstrumentedMutex* db_mutex,
const MutableCFOptions& mutable_cf_options) {
SuperVersion* new_superversion = sv_context->new_superversion.release();
new_superversion->db_mutex = db_mutex;
new_superversion->mutable_cf_options = mutable_cf_options;
new_superversion->Init(mem_, imm_.current(), current_);
@@ -925,16 +991,31 @@ SuperVersion* ColumnFamilyData::InstallSuperVersion(
super_version_ = new_superversion;
++super_version_number_;
super_version_->version_number = super_version_number_;
// Reset SuperVersions cached in thread local storage
ResetThreadLocalSuperVersions();
super_version_->write_stall_condition =
RecalculateWriteStallConditions(mutable_cf_options);
RecalculateWriteStallConditions(mutable_cf_options);
if (old_superversion != nullptr) {
// Reset SuperVersions cached in thread local storage.
// This should be done before old_superversion->Unref(). That's to ensure
// that local_sv_ never holds the last reference to SuperVersion, since
// it has no means to safely do SuperVersion cleanup.
ResetThreadLocalSuperVersions();
if (old_superversion != nullptr && old_superversion->Unref()) {
old_superversion->Cleanup();
return old_superversion; // will let caller delete outside of mutex
if (old_superversion->mutable_cf_options.write_buffer_size !=
mutable_cf_options.write_buffer_size) {
mem_->UpdateWriteBufferSize(mutable_cf_options.write_buffer_size);
}
if (old_superversion->write_stall_condition !=
new_superversion->write_stall_condition) {
sv_context->PushWriteStallNotification(
old_superversion->write_stall_condition,
new_superversion->write_stall_condition, GetName(), ioptions());
}
if (old_superversion->Unref()) {
old_superversion->Cleanup();
sv_context->superversions_to_free.push_back(old_superversion);
}
}
return nullptr;
}
void ColumnFamilyData::ResetThreadLocalSuperVersions() {
@@ -946,10 +1027,12 @@ void ColumnFamilyData::ResetThreadLocalSuperVersions() {
continue;
}
auto sv = static_cast<SuperVersion*>(ptr);
if (sv->Unref()) {
sv->Cleanup();
delete sv;
}
bool was_last_ref __attribute__((__unused__));
was_last_ref = sv->Unref();
// sv couldn't have been the last reference because
// ResetThreadLocalSuperVersions() is called before
// unref'ing super_version_.
assert(!was_last_ref);
}
}
@@ -967,6 +1050,24 @@ Status ColumnFamilyData::SetOptions(
}
#endif // ROCKSDB_LITE
// REQUIRES: DB mutex held
Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
if (initial_cf_options_.compaction_style != kCompactionStyleLevel) {
return Env::WLTH_NOT_SET;
}
if (level == 0) {
return Env::WLTH_MEDIUM;
}
int base_level = current_->storage_info()->base_level();
// L1: medium, L2: long, ...
if (level - base_level >= 2) {
return Env::WLTH_EXTREME;
}
return static_cast<Env::WriteLifeTimeHint>(level - base_level +
static_cast<int>(Env::WLTH_MEDIUM));
}
ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
const ImmutableDBOptions* db_options,
const EnvOptions& env_options,
@@ -993,10 +1094,14 @@ ColumnFamilySet::~ColumnFamilySet() {
while (column_family_data_.size() > 0) {
// cfd destructor will delete itself from column_family_data_
auto cfd = column_family_data_.begin()->second;
cfd->Unref();
bool last_ref __attribute__((__unused__));
last_ref = cfd->Unref();
assert(last_ref);
delete cfd;
}
dummy_cfd_->Unref();
bool dummy_last_ref __attribute__((__unused__));
dummy_last_ref = dummy_cfd_->Unref();
assert(dummy_last_ref);
delete dummy_cfd_;
}
+48 -16
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -32,6 +30,7 @@ namespace rocksdb {
class Version;
class VersionSet;
class VersionStorageInfo;
class MemTable;
class MemTableListVersion;
class CompactionPicker;
@@ -43,6 +42,7 @@ class DBImpl;
class LogBuffer;
class InstrumentedMutex;
class InstrumentedMutexLock;
struct SuperVersionContext;
extern const double kIncSlowdownRatio;
@@ -78,7 +78,7 @@ class ColumnFamilyHandleImpl : public ColumnFamilyHandle {
class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
public:
ColumnFamilyHandleInternal()
: ColumnFamilyHandleImpl(nullptr, nullptr, nullptr) {}
: ColumnFamilyHandleImpl(nullptr, nullptr, nullptr), internal_cfd_(nullptr) {}
void SetCFD(ColumnFamilyData* _cfd) { internal_cfd_ = _cfd; }
virtual ColumnFamilyData* cfd() const override { return internal_cfd_; }
@@ -97,6 +97,7 @@ struct SuperVersion {
MutableCFOptions mutable_cf_options;
// Version number of the current SuperVersion
uint64_t version_number;
WriteStallCondition write_stall_condition;
InstrumentedMutex* db_mutex;
@@ -194,7 +195,7 @@ class ColumnFamilyData {
// *) delete all memory associated with that column family
// *) delete all the files associated with that column family
void SetDropped();
bool IsDropped() const { return dropped_; }
bool IsDropped() const { return dropped_.load(std::memory_order_relaxed); }
// thread-safe
int NumberLevels() const { return ioptions_.num_levels; }
@@ -202,6 +203,10 @@ class ColumnFamilyData {
void SetLogNumber(uint64_t log_number) { log_number_ = log_number; }
uint64_t GetLogNumber() const { return log_number_; }
void SetFlushReason(FlushReason flush_reason) {
flush_reason_ = flush_reason;
}
FlushReason GetFlushReason() const { return flush_reason_; }
// thread-safe
const EnvOptions* soptions() const;
const ImmutableCFOptions* ioptions() const { return &ioptions_; }
@@ -239,7 +244,11 @@ class ColumnFamilyData {
void SetCurrent(Version* _current);
uint64_t GetNumLiveVersions() const; // REQUIRE: DB mutex held
uint64_t GetTotalSstFilesSize() const; // REQUIRE: DB mutex held
void SetMemtable(MemTable* new_mem) { mem_ = new_mem; }
void SetMemtable(MemTable* new_mem) {
uint64_t memtable_id = last_memtable_id_.fetch_add(1) + 1;
new_mem->SetID(memtable_id);
mem_ = new_mem;
}
// calculate the oldest log needed for the durability of this column family
uint64_t OldestLogToKeep();
@@ -266,7 +275,7 @@ class ColumnFamilyData {
int level) const;
// A flag to tell a manual compaction is to compact all levels together
// instad of for specific level.
// instead of a specific level.
static const int kCompactAllLevels;
// A flag to tell a manual compaction's output is base level.
static const int kCompactToBaseLevel;
@@ -313,11 +322,11 @@ class ColumnFamilyData {
// As argument takes a pointer to allocated SuperVersion to enable
// the clients to allocate SuperVersion outside of mutex.
// IMPORTANT: Only call this from DBImpl::InstallSuperVersion()
SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
InstrumentedMutex* db_mutex,
const MutableCFOptions& mutable_cf_options);
SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
InstrumentedMutex* db_mutex);
void InstallSuperVersion(SuperVersionContext* sv_context,
InstrumentedMutex* db_mutex,
const MutableCFOptions& mutable_cf_options);
void InstallSuperVersion(SuperVersionContext* sv_context,
InstrumentedMutex* db_mutex);
void ResetThreadLocalSuperVersions();
@@ -327,14 +336,31 @@ class ColumnFamilyData {
bool pending_flush() { return pending_flush_; }
bool pending_compaction() { return pending_compaction_; }
enum class WriteStallCause {
kNone,
kMemtableLimit,
kL0FileCountLimit,
kPendingCompactionBytes,
};
static std::pair<WriteStallCondition, WriteStallCause>
GetWriteStallConditionAndCause(int num_unflushed_memtables, int num_l0_files,
uint64_t num_compaction_needed_bytes,
const MutableCFOptions& mutable_cf_options);
// Recalculate some small conditions, which are changed only during
// compaction, adding new memtable and/or
// recalculation of compaction score. These values are used in
// DBImpl::MakeRoomForWrite function to decide, if it need to make
// a write stall
void RecalculateWriteStallConditions(
WriteStallCondition RecalculateWriteStallConditions(
const MutableCFOptions& mutable_cf_options);
void set_initialized() { initialized_.store(true); }
bool initialized() const { return initialized_.load(); }
Env::WriteLifeTimeHint CalculateSSTWriteHint(int level);
private:
friend class ColumnFamilySet;
ColumnFamilyData(uint32_t id, const std::string& name,
@@ -351,7 +377,8 @@ class ColumnFamilyData {
Version* current_; // == dummy_versions->prev_
std::atomic<int> refs_; // outstanding references to ColumnFamilyData
bool dropped_; // true if client dropped it
std::atomic<bool> initialized_;
std::atomic<bool> dropped_; // true if client dropped it
const InternalKeyComparator internal_comparator_;
std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
@@ -393,6 +420,8 @@ class ColumnFamilyData {
// recovered from
uint64_t log_number_;
std::atomic<FlushReason> flush_reason_;
// An object that keeps all the compaction stats
// and picks the next compaction
std::unique_ptr<CompactionPicker> compaction_picker_;
@@ -412,6 +441,9 @@ class ColumnFamilyData {
// if the database was opened with 2pc enabled
bool allow_2pc_;
// Memtable id to track flush.
std::atomic<uint64_t> last_memtable_id_;
};
// ColumnFamilySet has interesting thread-safety requirements
+74 -166
View File
@@ -1,8 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in
// the LICENSE file in the root directory of this source tree. An
// additional grant of patent rights can be found in the PATENTS file
// in the same directory.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -303,6 +302,7 @@ class ColumnFamilyTest : public testing::Test {
ASSERT_OK(Put(cf, key, RandomString(&rnd_, key_value_size - 10)));
}
}
db_->FlushWAL(false);
}
#ifndef ROCKSDB_LITE // TEST functions in DB are not supported in lite
@@ -521,6 +521,30 @@ TEST_F(ColumnFamilyTest, DontReuseColumnFamilyID) {
}
}
#ifndef ROCKSDB_LITE
TEST_F(ColumnFamilyTest, CreateCFRaceWithGetAggProperty) {
Open();
rocksdb::SyncPoint::GetInstance()->LoadDependency(
{{"DBImpl::WriteOptionsFile:1",
"ColumnFamilyTest.CreateCFRaceWithGetAggProperty:1"},
{"ColumnFamilyTest.CreateCFRaceWithGetAggProperty:2",
"DBImpl::WriteOptionsFile:2"}});
rocksdb::SyncPoint::GetInstance()->EnableProcessing();
rocksdb::port::Thread thread([&] { CreateColumnFamilies({"one"}); });
TEST_SYNC_POINT("ColumnFamilyTest.CreateCFRaceWithGetAggProperty:1");
uint64_t pv;
db_->GetAggregatedIntProperty(DB::Properties::kEstimateTableReadersMem, &pv);
TEST_SYNC_POINT("ColumnFamilyTest.CreateCFRaceWithGetAggProperty:2");
thread.join();
rocksdb::SyncPoint::GetInstance()->DisableProcessing();
}
#endif // !ROCKSDB_LITE
class FlushEmptyCFTestWithParam : public ColumnFamilyTest,
public testing::WithParamInterface<bool> {
public:
@@ -558,6 +582,7 @@ TEST_P(FlushEmptyCFTestWithParam, FlushEmptyCFTest) {
Flush(0);
ASSERT_OK(Put(1, "bar", "v3")); // seqID 4
ASSERT_OK(Put(1, "foo", "v4")); // seqID 5
db_->FlushWAL(false);
// Preserve file system state up to here to simulate a crash condition.
fault_env->SetFilesystemActive(false);
@@ -620,6 +645,7 @@ TEST_P(FlushEmptyCFTestWithParam, FlushEmptyCFTest2) {
// Write to log file D
ASSERT_OK(Put(1, "bar", "v4")); // seqID 7
ASSERT_OK(Put(1, "bar", "v5")); // seqID 8
db_->FlushWAL(false);
// Preserve file system state up to here to simulate a crash condition.
fault_env->SetFilesystemActive(false);
std::vector<std::string> names;
@@ -907,62 +933,62 @@ TEST_F(ColumnFamilyTest, FlushTest) {
TEST_F(ColumnFamilyTest, LogDeletionTest) {
db_options_.max_total_wal_size = std::numeric_limits<uint64_t>::max();
column_family_options_.arena_block_size = 4 * 1024;
column_family_options_.write_buffer_size = 100000; // 100KB
column_family_options_.write_buffer_size = 128000; // 128KB
Open();
CreateColumnFamilies({"one", "two", "three", "four"});
// Each bracket is one log file. if number is in (), it means
// we don't need it anymore (it's been flushed)
// []
AssertCountLiveLogFiles(0);
PutRandomData(0, 1, 100);
PutRandomData(0, 1, 128);
// [0]
PutRandomData(1, 1, 100);
PutRandomData(1, 1, 128);
// [0, 1]
PutRandomData(1, 1000, 100);
PutRandomData(1, 1000, 128);
WaitForFlush(1);
// [0, (1)] [1]
AssertCountLiveLogFiles(2);
PutRandomData(0, 1, 100);
PutRandomData(0, 1, 128);
// [0, (1)] [0, 1]
AssertCountLiveLogFiles(2);
PutRandomData(2, 1, 100);
PutRandomData(2, 1, 128);
// [0, (1)] [0, 1, 2]
PutRandomData(2, 1000, 100);
PutRandomData(2, 1000, 128);
WaitForFlush(2);
// [0, (1)] [0, 1, (2)] [2]
AssertCountLiveLogFiles(3);
PutRandomData(2, 1000, 100);
PutRandomData(2, 1000, 128);
WaitForFlush(2);
// [0, (1)] [0, 1, (2)] [(2)] [2]
AssertCountLiveLogFiles(4);
PutRandomData(3, 1, 100);
PutRandomData(3, 1, 128);
// [0, (1)] [0, 1, (2)] [(2)] [2, 3]
PutRandomData(1, 1, 100);
PutRandomData(1, 1, 128);
// [0, (1)] [0, 1, (2)] [(2)] [1, 2, 3]
AssertCountLiveLogFiles(4);
PutRandomData(1, 1000, 100);
PutRandomData(1, 1000, 128);
WaitForFlush(1);
// [0, (1)] [0, (1), (2)] [(2)] [(1), 2, 3] [1]
AssertCountLiveLogFiles(5);
PutRandomData(0, 1000, 100);
PutRandomData(0, 1000, 128);
WaitForFlush(0);
// [(0), (1)] [(0), (1), (2)] [(2)] [(1), 2, 3] [1, (0)] [0]
// delete obsolete logs -->
// [(1), 2, 3] [1, (0)] [0]
AssertCountLiveLogFiles(3);
PutRandomData(0, 1000, 100);
PutRandomData(0, 1000, 128);
WaitForFlush(0);
// [(1), 2, 3] [1, (0)], [(0)] [0]
AssertCountLiveLogFiles(4);
PutRandomData(1, 1000, 100);
PutRandomData(1, 1000, 128);
WaitForFlush(1);
// [(1), 2, 3] [(1), (0)] [(0)] [0, (1)] [1]
AssertCountLiveLogFiles(5);
PutRandomData(2, 1000, 100);
PutRandomData(2, 1000, 128);
WaitForFlush(2);
// [(1), (2), 3] [(1), (0)] [(0)] [0, (1)] [1, (2)], [2]
AssertCountLiveLogFiles(6);
PutRandomData(3, 1000, 100);
PutRandomData(3, 1000, 128);
WaitForFlush(3);
// [(1), (2), (3)] [(1), (0)] [(0)] [0, (1)] [1, (2)], [2, (3)] [3]
// delete obsolete logs -->
@@ -1380,7 +1406,6 @@ TEST_F(ColumnFamilyTest, AutomaticAndManualCompactions) {
ColumnFamilyOptions default_cf, one, two;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
@@ -1404,6 +1429,9 @@ TEST_F(ColumnFamilyTest, AutomaticAndManualCompactions) {
two.write_buffer_size = 100000;
Reopen({default_cf, one, two});
// make sure all background compaction jobs can be scheduled
auto stop_token =
dbfull()->TEST_write_controler().GetCompactionPressureToken();
bool cf_1_1 = true;
rocksdb::SyncPoint::GetInstance()->LoadDependency(
@@ -1463,7 +1491,6 @@ TEST_F(ColumnFamilyTest, AutomaticAndManualCompactions) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
@@ -1472,7 +1499,6 @@ TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
ColumnFamilyOptions default_cf, one, two;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
@@ -1496,6 +1522,9 @@ TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
two.write_buffer_size = 100000;
Reopen({default_cf, one, two});
// make sure all background compaction jobs can be scheduled
auto stop_token =
dbfull()->TEST_write_controler().GetCompactionPressureToken();
// SETUP column family "one" -- universal style
for (int i = 0; i < one.level0_file_num_compaction_trigger - 2; ++i) {
@@ -1558,7 +1587,6 @@ TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
@@ -1567,7 +1595,6 @@ TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
ColumnFamilyOptions default_cf, one;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
@@ -1586,6 +1613,9 @@ TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
one.write_buffer_size = 120000;
Reopen({default_cf, one});
// make sure all background compaction jobs can be scheduled
auto stop_token =
dbfull()->TEST_write_controler().GetCompactionPressureToken();
// SETUP column family "one" -- universal style
for (int i = 0; i < one.level0_file_num_compaction_trigger - 2; ++i) {
@@ -1656,7 +1686,6 @@ TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
@@ -1665,7 +1694,6 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
ColumnFamilyOptions default_cf, one;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
@@ -1684,6 +1712,9 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
one.write_buffer_size = 120000;
Reopen({default_cf, one});
// make sure all background compaction jobs can be scheduled
auto stop_token =
dbfull()->TEST_write_controler().GetCompactionPressureToken();
// SETUP column family "one" -- universal style
for (int i = 0; i < one.level0_file_num_compaction_trigger - 2; ++i) {
@@ -1745,7 +1776,6 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
@@ -1754,7 +1784,6 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
ColumnFamilyOptions default_cf, one;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
@@ -1773,6 +1802,9 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
one.write_buffer_size = 120000;
Reopen({default_cf, one});
// make sure all background compaction jobs can be scheduled
auto stop_token =
dbfull()->TEST_write_controler().GetCompactionPressureToken();
// SETUP column family "one" -- level style
for (int i = 0; i < one.level0_file_num_compaction_trigger - 2; ++i) {
@@ -1834,127 +1866,6 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
// This test checks for automatic getting a conflict if there is a
// manual which has not yet been scheduled.
// The manual compaction waits in NotScheduled
// We generate more files and then trigger an automatic compaction
// This will wait because there is an unscheduled manual compaction.
// Once the conflict is hit, the manual compaction starts and ends
// Then another automatic will start and end.
TEST_F(ColumnFamilyTest, SameCFManualAutomaticConflict) {
Open();
CreateColumnFamilies({"one"});
ColumnFamilyOptions default_cf, one;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
default_cf.write_buffer_size = 64 << 10; // 64KB
default_cf.target_file_size_base = 30 << 10;
default_cf.max_compaction_bytes = default_cf.target_file_size_base * 1100;
BlockBasedTableOptions table_options;
table_options.no_block_cache = true;
default_cf.table_factory.reset(NewBlockBasedTableFactory(table_options));
one.compaction_style = kCompactionStyleUniversal;
one.num_levels = 1;
// trigger compaction if there are >= 4 files
one.level0_file_num_compaction_trigger = 4;
one.write_buffer_size = 120000;
Reopen({default_cf, one});
// SETUP column family "one" -- universal style
for (int i = 0; i < one.level0_file_num_compaction_trigger - 2; ++i) {
PutRandomData(1, 10, 12000, true);
PutRandomData(1, 1, 10, true);
WaitForFlush(1);
AssertFilesPerLevel(ToString(i + 1), 1);
}
bool cf_1_1 = true;
bool cf_1_2 = true;
rocksdb::SyncPoint::GetInstance()->LoadDependency(
{{"DBImpl::BackgroundCompaction()::Conflict",
"ColumnFamilyTest::ManualAutoCon:7"},
{"ColumnFamilyTest::ManualAutoCon:9",
"ColumnFamilyTest::ManualAutoCon:8"},
{"ColumnFamilyTest::ManualAutoCon:2",
"ColumnFamilyTest::ManualAutoCon:6"},
{"ColumnFamilyTest::ManualAutoCon:4",
"ColumnFamilyTest::ManualAutoCon:5"},
{"ColumnFamilyTest::ManualAutoCon:1",
"ColumnFamilyTest::ManualAutoCon:2"},
{"ColumnFamilyTest::ManualAutoCon:1",
"ColumnFamilyTest::ManualAutoCon:3"}});
rocksdb::SyncPoint::GetInstance()->SetCallBack(
"DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* arg) {
if (cf_1_1) {
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:4");
cf_1_1 = false;
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:3");
} else if (cf_1_2) {
cf_1_2 = false;
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:2");
}
});
rocksdb::SyncPoint::GetInstance()->SetCallBack(
"DBImpl::RunManualCompaction:NotScheduled", [&](void* arg) {
InstrumentedMutex* mutex = static_cast<InstrumentedMutex*>(arg);
mutex->Unlock();
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:9");
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:7");
mutex->Lock();
});
rocksdb::SyncPoint::GetInstance()->EnableProcessing();
rocksdb::port::Thread threads([&] {
CompactRangeOptions compact_options;
compact_options.exclusive_manual_compaction = false;
ASSERT_OK(
db_->CompactRange(compact_options, handles_[1], nullptr, nullptr));
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:6");
});
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:8");
WaitForFlush(1);
// Add more L0 files and force automatic compaction
for (int i = 0; i < one.level0_file_num_compaction_trigger; ++i) {
PutRandomData(1, 10, 12000, true);
PutRandomData(1, 1, 10, true);
WaitForFlush(1);
AssertFilesPerLevel(ToString(one.level0_file_num_compaction_trigger + i),
1);
}
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:5");
// Add more L0 files and force automatic compaction
for (int i = 0; i < one.level0_file_num_compaction_trigger; ++i) {
PutRandomData(1, 10, 12000, true);
PutRandomData(1, 1, 10, true);
WaitForFlush(1);
}
TEST_SYNC_POINT("ColumnFamilyTest::ManualAutoCon:1");
threads.join();
WaitForCompaction();
// VERIFY compaction "one"
ASSERT_LE(NumTableFilesAtLevel(0, 1), 3);
// Compare against saved keys
std::set<std::string>::iterator key_iter = keys_.begin();
while (key_iter != keys_.end()) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
// In this test, we generate enough files to trigger automatic compactions.
@@ -1969,7 +1880,6 @@ TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
ColumnFamilyOptions default_cf, one;
db_options_.max_open_files = 20; // only 10 files in file cache
db_options_.max_background_compactions = 3;
db_options_.base_background_compactions = 3;
default_cf.compaction_style = kCompactionStyleLevel;
default_cf.num_levels = 3;
@@ -1988,6 +1898,9 @@ TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
one.write_buffer_size = 120000;
Reopen({default_cf, one});
// make sure all background compaction jobs can be scheduled
auto stop_token =
dbfull()->TEST_write_controler().GetCompactionPressureToken();
bool cf_1_1 = true;
bool cf_1_2 = true;
@@ -2042,8 +1955,6 @@ TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
key_iter++;
}
Close();
}
#endif // !ROCKSDB_LITE
@@ -2496,7 +2407,6 @@ TEST_F(ColumnFamilyTest, CreateAndDropRace) {
TEST_F(ColumnFamilyTest, WriteStallSingleColumnFamily) {
const uint64_t kBaseRate = 800000u;
db_options_.delayed_write_rate = kBaseRate;
db_options_.base_background_compactions = 2;
db_options_.max_background_compactions = 6;
Open({"default"});
@@ -2677,7 +2587,6 @@ TEST_F(ColumnFamilyTest, WriteStallSingleColumnFamily) {
}
TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
db_options_.base_background_compactions = 2;
db_options_.max_background_compactions = 6;
Open({"default"});
ColumnFamilyData* cfd =
@@ -2697,7 +2606,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
vstorage->TEST_set_estimated_compaction_needed_bytes(40);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
vstorage->TEST_set_estimated_compaction_needed_bytes(50);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2709,11 +2618,11 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
vstorage->TEST_set_estimated_compaction_needed_bytes(45);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
vstorage->set_l0_delay_trigger_count(7);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
vstorage->set_l0_delay_trigger_count(9);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2721,7 +2630,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
vstorage->set_l0_delay_trigger_count(6);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
// Speed up threshold = min(4 * 2, 4 + (12 - 4)/4) = 6
mutable_cf_options.level0_file_num_compaction_trigger = 4;
@@ -2730,7 +2639,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
vstorage->set_l0_delay_trigger_count(5);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
vstorage->set_l0_delay_trigger_count(7);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2738,7 +2647,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
vstorage->set_l0_delay_trigger_count(3);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
}
TEST_F(ColumnFamilyTest, WriteStallTwoColumnFamilies) {
@@ -2817,7 +2726,6 @@ TEST_F(ColumnFamilyTest, WriteStallTwoColumnFamilies) {
}
TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
db_options_.base_background_compactions = 2;
db_options_.max_background_compactions = 6;
column_family_options_.soft_pending_compaction_bytes_limit = 200;
column_family_options_.hard_pending_compaction_bytes_limit = 2000;
@@ -2845,11 +2753,11 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
vstorage->TEST_set_estimated_compaction_needed_bytes(40);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
vstorage->TEST_set_estimated_compaction_needed_bytes(60);
cfd1->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
@@ -2867,7 +2775,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
vstorage1->TEST_set_estimated_compaction_needed_bytes(3);
cfd1->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
vstorage->set_l0_delay_trigger_count(9);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2879,7 +2787,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
vstorage->set_l0_delay_trigger_count(0);
cfd->RecalculateWriteStallConditions(mutable_cf_options);
ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
}
#ifndef ROCKSDB_LITE
+3 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#ifndef ROCKSDB_LITE
+8 -7
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#ifndef ROCKSDB_LITE
#include "db/compacted_db_impl.h"
@@ -19,7 +17,8 @@ extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
CompactedDBImpl::CompactedDBImpl(
const DBOptions& options, const std::string& dbname)
: DBImpl(options, dbname) {
: DBImpl(options, dbname), cfd_(nullptr), version_(nullptr),
user_comparator_(nullptr) {
}
CompactedDBImpl::~CompactedDBImpl() {
@@ -95,6 +94,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
}
Status CompactedDBImpl::Init(const Options& options) {
SuperVersionContext sv_context(/* create_superversion */ true);
mutex_.Lock();
ColumnFamilyDescriptor cf(kDefaultColumnFamilyName,
ColumnFamilyOptions(options));
@@ -102,9 +102,10 @@ Status CompactedDBImpl::Init(const Options& options) {
if (s.ok()) {
cfd_ = reinterpret_cast<ColumnFamilyHandleImpl*>(
DefaultColumnFamily())->cfd();
delete cfd_->InstallSuperVersion(new SuperVersion(), &mutex_);
cfd_->InstallSuperVersion(&sv_context, &mutex_);
}
mutex_.Unlock();
sv_context.Clean();
if (!s.ok()) {
return s;
}
+3 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#pragma once
#ifndef ROCKSDB_LITE
+66 -60
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -88,35 +86,23 @@ void Compaction::GetBoundaryKeys(
bool Compaction::IsBottommostLevel(
int output_level, VersionStorageInfo* vstorage,
const std::vector<CompactionInputFiles>& inputs) {
if (inputs[0].level == 0 &&
inputs[0].files.back() != vstorage->LevelFiles(0).back()) {
return false;
int output_l0_idx;
if (output_level == 0) {
output_l0_idx = 0;
for (const auto* file : vstorage->LevelFiles(0)) {
if (inputs[0].files.back() == file) {
break;
}
++output_l0_idx;
}
assert(static_cast<size_t>(output_l0_idx) < vstorage->LevelFiles(0).size());
} else {
output_l0_idx = -1;
}
Slice smallest_key, largest_key;
GetBoundaryKeys(vstorage, inputs, &smallest_key, &largest_key);
// Checks whether there are files living beyond the output_level.
// If lower levels have files, it checks for overlap between files
// if the compaction process and those files.
// Bottomlevel optimizations can be made if there are no files in
// lower levels or if there is no overlap with the files in
// the lower levels.
for (int i = output_level + 1; i < vstorage->num_levels(); i++) {
// It is not the bottommost level if there are files in higher
// levels when the output level is 0 or if there are files in
// higher levels which overlap with files to be compacted.
// output_level == 0 means that we want it to be considered
// s the bottommost level only if the last file on the level
// is a part of the files to be compacted - this is verified by
// the first if condition in this function
if (vstorage->NumLevelFiles(i) > 0 &&
(output_level == 0 ||
vstorage->OverlapInLevel(i, &smallest_key, &largest_key))) {
return false;
}
}
return true;
return !vstorage->RangeMightExistAfterSortedRun(smallest_key, largest_key,
output_level, output_l0_idx);
}
// test function to validate the functionality of IsBottommostLevel()
@@ -171,6 +157,7 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
is_full_compaction_(IsFullCompaction(vstorage, inputs_)),
is_manual_compaction_(_manual_compaction),
is_trivial_move_(false),
compaction_reason_(_compaction_reason) {
MarkFilesBeingCompacted(true);
if (is_manual_compaction_) {
@@ -242,7 +229,7 @@ bool Compaction::IsTrivialMove() const {
// Used in universal compaction, where trivial move can be done if the
// input files are non overlapping
if ((immutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
(output_level_ != 0)) {
return is_trivial_move_;
}
@@ -285,28 +272,31 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
assert(input_version_ != nullptr);
assert(level_ptrs != nullptr);
assert(level_ptrs->size() == static_cast<size_t>(number_levels_));
assert(cfd_->ioptions()->compaction_style != kCompactionStyleFIFO);
if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
return bottommost_level_;
}
// Maybe use binary search to find right entry instead of linear search?
const Comparator* user_cmp = cfd_->user_comparator();
for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
const std::vector<FileMetaData*>& files = input_vstorage_->LevelFiles(lvl);
for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
auto* f = files[level_ptrs->at(lvl)];
if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
// We've advanced far enough
if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
// Key falls in this file's range, so definitely
// exists beyond output level
return false;
if (bottommost_level_) {
return true;
} else if (output_level_ != 0 &&
cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
// Maybe use binary search to find right entry instead of linear search?
const Comparator* user_cmp = cfd_->user_comparator();
for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
const std::vector<FileMetaData*>& files =
input_vstorage_->LevelFiles(lvl);
for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
auto* f = files[level_ptrs->at(lvl)];
if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
// We've advanced far enough
if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
// Key falls in this file's range, so definitely
// exists beyond output level
return false;
}
break;
}
break;
}
}
return true;
}
return true;
return false;
}
// Mark (or clear) each file that is being compacted
@@ -415,20 +405,23 @@ void Compaction::Summary(char* output, int len) {
uint64_t Compaction::OutputFilePreallocationSize() const {
uint64_t preallocation_size = 0;
if (max_output_file_size_ != port::kMaxUint64 &&
(cfd_->ioptions()->compaction_style == kCompactionStyleLevel ||
output_level() > 0)) {
preallocation_size = max_output_file_size_;
} else {
for (const auto& level_files : inputs_) {
for (const auto& file : level_files.files) {
preallocation_size += file->fd.GetFileSize();
}
for (const auto& level_files : inputs_) {
for (const auto& file : level_files.files) {
preallocation_size += file->fd.GetFileSize();
}
}
if (max_output_file_size_ != port::kMaxUint64 &&
(immutable_cf_options_.compaction_style == kCompactionStyleLevel ||
output_level() > 0)) {
preallocation_size = std::min(max_output_file_size_, preallocation_size);
}
// Over-estimate slightly so we don't end up just barely crossing
// the threshold
return preallocation_size + (preallocation_size / 10);
// No point to prellocate more than 1GB.
return std::min(uint64_t{1073741824},
preallocation_size + (preallocation_size / 10));
}
std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
@@ -461,4 +454,17 @@ bool Compaction::ShouldFormSubcompactions() const {
}
}
uint64_t Compaction::MaxInputFileCreationTime() const {
uint64_t max_creation_time = 0;
for (const auto& file : inputs_[0].files) {
if (file->fd.table_reader != nullptr &&
file->fd.table_reader->GetTableProperties() != nullptr) {
uint64_t creation_time =
file->fd.table_reader->GetTableProperties()->creation_time;
max_creation_time = std::max(max_creation_time, creation_time);
}
}
return max_creation_time;
}
} // namespace rocksdb
+7 -6
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -101,7 +99,8 @@ class Compaction {
// input level.
// REQUIREMENT: "compaction_input_level" must be >= 0 and
// < "input_levels()"
const std::vector<FileMetaData*>* inputs(size_t compaction_input_level) {
const std::vector<FileMetaData*>* inputs(
size_t compaction_input_level) const {
assert(compaction_input_level < inputs_.size());
return &inputs_[compaction_input_level].files;
}
@@ -242,6 +241,8 @@ class Compaction {
uint64_t max_compaction_bytes() const { return max_compaction_bytes_; }
uint64_t MaxInputFileCreationTime() const;
private:
// mark (or clear) all files that are being compacted
void MarkFilesBeingCompacted(bool mark_as_compacted);
+5 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2016-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#pragma once
@@ -18,6 +16,8 @@ struct CompactionIterationStats {
int64_t num_record_drop_obsolete = 0;
int64_t num_record_drop_range_del = 0;
int64_t num_range_del_drop_obsolete = 0;
// Deletions obsoleted before bottom level due to file gap optimization.
int64_t num_optimized_del_drop_obsolete = 0;
uint64_t total_filter_time = 0;
// Input statistics
+166 -74
View File
@@ -1,13 +1,12 @@
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include "db/compaction_iterator.h"
#include "db/snapshot_checker.h"
#include "port/likely.h"
#include "rocksdb/listener.h"
#include "table/internal_iterator.h"
@@ -29,6 +28,8 @@ CompactionEventListener::CompactionListenerValueType fromInternalValueType(
kSingleDelete;
case kTypeRangeDeletion:
return CompactionEventListener::CompactionListenerValueType::kRangeDelete;
case kTypeBlobIndex:
return CompactionEventListener::CompactionListenerValueType::kBlobIndex;
default:
assert(false);
return CompactionEventListener::CompactionListenerValueType::kInvalid;
@@ -39,42 +40,55 @@ CompactionEventListener::CompactionListenerValueType fromInternalValueType(
CompactionIterator::CompactionIterator(
InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
SequenceNumber earliest_write_conflict_snapshot, Env* env,
SequenceNumber earliest_write_conflict_snapshot,
const SnapshotChecker* snapshot_checker, Env* env,
bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
const Compaction* compaction, const CompactionFilter* compaction_filter,
CompactionEventListener* compaction_listener,
const std::atomic<bool>* shutting_down)
const std::atomic<bool>* shutting_down,
const SequenceNumber preserve_deletes_seqnum)
: CompactionIterator(
input, cmp, merge_helper, last_sequence, snapshots,
earliest_write_conflict_snapshot, env, expect_valid_internal_key,
range_del_agg,
earliest_write_conflict_snapshot, snapshot_checker, env,
expect_valid_internal_key, range_del_agg,
std::unique_ptr<CompactionProxy>(
compaction ? new CompactionProxy(compaction) : nullptr),
compaction_filter, compaction_listener, shutting_down) {}
compaction_filter, compaction_listener, shutting_down,
preserve_deletes_seqnum) {}
CompactionIterator::CompactionIterator(
InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
SequenceNumber earliest_write_conflict_snapshot, Env* env,
SequenceNumber earliest_write_conflict_snapshot,
const SnapshotChecker* snapshot_checker, Env* env,
bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
std::unique_ptr<CompactionProxy> compaction,
const CompactionFilter* compaction_filter,
CompactionEventListener* compaction_listener,
const std::atomic<bool>* shutting_down)
const std::atomic<bool>* shutting_down,
const SequenceNumber preserve_deletes_seqnum
)
: input_(input),
cmp_(cmp),
merge_helper_(merge_helper),
snapshots_(snapshots),
earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
snapshot_checker_(snapshot_checker),
env_(env),
expect_valid_internal_key_(expect_valid_internal_key),
range_del_agg_(range_del_agg),
compaction_(std::move(compaction)),
compaction_filter_(compaction_filter),
#ifndef ROCKSDB_LITE
compaction_listener_(compaction_listener),
#endif // ROCKSDB_LITE
shutting_down_(shutting_down),
preserve_deletes_seqnum_(preserve_deletes_seqnum),
ignore_snapshots_(false),
merge_out_iter_(merge_helper_) {
current_user_key_sequence_(0),
current_user_key_snapshot_(0),
merge_out_iter_(merge_helper_),
current_key_committed_(false) {
assert(compaction_filter_ == nullptr || compaction_ != nullptr);
bottommost_level_ =
compaction_ == nullptr ? false : compaction_->bottommost_level();
@@ -113,6 +127,7 @@ void CompactionIterator::ResetRecordCounts() {
iter_stats_.num_record_drop_obsolete = 0;
iter_stats_.num_record_drop_range_del = 0;
iter_stats_.num_range_del_drop_obsolete = 0;
iter_stats_.num_optimized_del_drop_obsolete = 0;
}
void CompactionIterator::SeekToFirst() {
@@ -130,8 +145,8 @@ void CompactionIterator::Next() {
if (merge_out_iter_.Valid()) {
key_ = merge_out_iter_.key();
value_ = merge_out_iter_.value();
bool valid_key __attribute__((__unused__)) =
ParseInternalKey(key_, &ikey_);
bool valid_key __attribute__((__unused__));
valid_key = ParseInternalKey(key_, &ikey_);
// MergeUntil stops when it encounters a corrupt key and does not
// include them in the result, so we expect the keys here to be valid.
assert(valid_key);
@@ -165,6 +180,61 @@ void CompactionIterator::Next() {
PrepareOutput();
}
void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
Slice* skip_until) {
if (compaction_filter_ != nullptr &&
(ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex) &&
(visible_at_tip_ || ignore_snapshots_ ||
ikey_.sequence > latest_snapshot_ ||
(snapshot_checker_ != nullptr &&
UNLIKELY(!snapshot_checker_->IsInSnapshot(ikey_.sequence,
latest_snapshot_))))) {
// If the user has specified a compaction filter and the sequence
// number is greater than any external snapshot, then invoke the
// filter. If the return value of the compaction filter is true,
// replace the entry with a deletion marker.
CompactionFilter::Decision filter;
compaction_filter_value_.clear();
compaction_filter_skip_until_.Clear();
CompactionFilter::ValueType value_type =
ikey_.type == kTypeValue ? CompactionFilter::ValueType::kValue
: CompactionFilter::ValueType::kBlobIndex;
{
StopWatchNano timer(env_, true);
filter = compaction_filter_->FilterV2(
compaction_->level(), ikey_.user_key, value_type, value_,
&compaction_filter_value_, compaction_filter_skip_until_.rep());
iter_stats_.total_filter_time +=
env_ != nullptr ? timer.ElapsedNanos() : 0;
}
if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
cmp_->Compare(*compaction_filter_skip_until_.rep(), ikey_.user_key) <=
0) {
// Can't skip to a key smaller than the current one.
// Keep the key as per FilterV2 documentation.
filter = CompactionFilter::Decision::kKeep;
}
if (filter == CompactionFilter::Decision::kRemove) {
// convert the current key to a delete; key_ is pointing into
// current_key_ at this point, so updating current_key_ updates key()
ikey_.type = kTypeDeletion;
current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
// no value associated with delete
value_.clear();
iter_stats_.num_record_drop_user++;
} else if (filter == CompactionFilter::Decision::kChangeValue) {
value_ = compaction_filter_value_;
} else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
*need_skip = true;
compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
kValueTypeForSeek);
*skip_until = compaction_filter_skip_until_.Encode();
}
}
}
void CompactionIterator::NextFromInput() {
at_next_ = false;
valid_ = false;
@@ -219,6 +289,9 @@ void CompactionIterator::NextFromInput() {
has_outputted_key_ = false;
current_user_key_sequence_ = kMaxSequenceNumber;
current_user_key_snapshot_ = 0;
current_key_committed_ =
(snapshot_checker_ == nullptr ||
snapshot_checker_->IsInSnapshot(ikey_.sequence, kMaxSequenceNumber));
#ifndef ROCKSDB_LITE
if (compaction_listener_) {
@@ -226,53 +299,12 @@ void CompactionIterator::NextFromInput() {
fromInternalValueType(ikey_.type),
value_, ikey_.sequence, true);
}
#endif // ROCKSDB_LITE
#endif // !ROCKSDB_LITE
// apply the compaction filter to the first occurrence of the user key
if (compaction_filter_ != nullptr && ikey_.type == kTypeValue &&
(visible_at_tip_ || ikey_.sequence > latest_snapshot_ ||
ignore_snapshots_)) {
// If the user has specified a compaction filter and the sequence
// number is greater than any external snapshot, then invoke the
// filter. If the return value of the compaction filter is true,
// replace the entry with a deletion marker.
CompactionFilter::Decision filter;
compaction_filter_value_.clear();
compaction_filter_skip_until_.Clear();
{
StopWatchNano timer(env_, true);
filter = compaction_filter_->FilterV2(
compaction_->level(), ikey_.user_key,
CompactionFilter::ValueType::kValue, value_,
&compaction_filter_value_, compaction_filter_skip_until_.rep());
iter_stats_.total_filter_time +=
env_ != nullptr ? timer.ElapsedNanos() : 0;
}
if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
cmp_->Compare(*compaction_filter_skip_until_.rep(),
ikey_.user_key) <= 0) {
// Can't skip to a key smaller than the current one.
// Keep the key as per FilterV2 documentation.
filter = CompactionFilter::Decision::kKeep;
}
if (filter == CompactionFilter::Decision::kRemove) {
// convert the current key to a delete; key_ is pointing into
// current_key_ at this point, so updating current_key_ updates key()
ikey_.type = kTypeDeletion;
current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
// no value associated with delete
value_.clear();
iter_stats_.num_record_drop_user++;
} else if (filter == CompactionFilter::Decision::kChangeValue) {
value_ = compaction_filter_value_;
} else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
need_skip = true;
compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
kValueTypeForSeek);
skip_until = compaction_filter_skip_until_.Encode();
}
// Apply the compaction filter to the first committed version of the user
// key.
if (current_key_committed_) {
InvokeFilterIfNeeded(&need_skip, &skip_until);
}
} else {
#ifndef ROCKSDB_LITE
@@ -291,13 +323,33 @@ void CompactionIterator::NextFromInput() {
current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
key_ = current_key_.GetInternalKey();
ikey_.user_key = current_key_.GetUserKey();
// Note that newer version of a key is ordered before older versions. If a
// newer version of a key is committed, so as the older version. No need
// to query snapshot_checker_ in that case.
if (UNLIKELY(!current_key_committed_)) {
assert(snapshot_checker_ != nullptr);
current_key_committed_ =
snapshot_checker_->IsInSnapshot(ikey_.sequence, kMaxSequenceNumber);
// Apply the compaction filter to the first committed version of the
// user key.
if (current_key_committed_) {
InvokeFilterIfNeeded(&need_skip, &skip_until);
}
}
}
if (UNLIKELY(!current_key_committed_)) {
assert(snapshot_checker_ != nullptr);
valid_ = true;
break;
}
// If there are no snapshots, then this kv affect visibility at tip.
// Otherwise, search though all existing snapshots to find the earliest
// snapshot that is affected by this kv.
SequenceNumber last_sequence __attribute__((__unused__)) =
current_user_key_sequence_;
SequenceNumber last_sequence __attribute__((__unused__));
last_sequence = current_user_key_sequence_;
current_user_key_sequence_ = ikey_.sequence;
SequenceNumber last_snapshot = current_user_key_snapshot_;
SequenceNumber prev_snapshot = 0; // 0 means no previous snapshot
@@ -362,7 +414,10 @@ void CompactionIterator::NextFromInput() {
cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
// Check whether the next key belongs to the same snapshot as the
// SingleDelete.
if (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot) {
if (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot ||
(snapshot_checker_ != nullptr &&
UNLIKELY(!snapshot_checker_->IsInSnapshot(next_ikey.sequence,
prev_snapshot)))) {
if (next_ikey.type == kTypeSingleDeletion) {
// We encountered two SingleDeletes in a row. This could be due to
// unexpected user input.
@@ -373,8 +428,12 @@ void CompactionIterator::NextFromInput() {
// input_->Next().
++iter_stats_.num_record_drop_obsolete;
++iter_stats_.num_single_del_mismatch;
} else if ((ikey_.sequence <= earliest_write_conflict_snapshot_) ||
has_outputted_key_) {
} else if (has_outputted_key_ ||
(ikey_.sequence <= earliest_write_conflict_snapshot_ &&
(snapshot_checker_ == nullptr ||
LIKELY(snapshot_checker_->IsInSnapshot(
ikey_.sequence,
earliest_write_conflict_snapshot_))))) {
// Found a matching value, we can drop the single delete and the
// value. It is safe to drop both records since we've already
// outputted a key in this snapshot, or there is no earlier
@@ -422,12 +481,18 @@ void CompactionIterator::NextFromInput() {
// comparison, so the value of has_current_user_key does not matter.
has_current_user_key_ = false;
if (compaction_ != nullptr && ikey_.sequence <= earliest_snapshot_ &&
(snapshot_checker_ == nullptr ||
LIKELY(snapshot_checker_->IsInSnapshot(ikey_.sequence,
earliest_snapshot_))) &&
compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
&level_ptrs_)) {
// Key doesn't exist outside of this range.
// Can compact out this SingleDelete.
++iter_stats_.num_record_drop_obsolete;
++iter_stats_.num_single_del_fallthru;
if (!bottommost_level_) {
++iter_stats_.num_optimized_del_drop_obsolete;
}
} else {
// Output SingleDelete
valid_ = true;
@@ -452,6 +517,10 @@ void CompactionIterator::NextFromInput() {
input_->Next();
} else if (compaction_ != nullptr && ikey_.type == kTypeDeletion &&
ikey_.sequence <= earliest_snapshot_ &&
(snapshot_checker_ == nullptr ||
LIKELY(snapshot_checker_->IsInSnapshot(ikey_.sequence,
earliest_snapshot_))) &&
ikeyNotNeededForIncrementalSnapshot() &&
compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
&level_ptrs_)) {
// TODO(noetzli): This is the only place where we use compaction_
@@ -468,7 +537,15 @@ void CompactionIterator::NextFromInput() {
//
// Note: Dropping this Delete will not affect TransactionDB
// write-conflict checking since it is earlier than any snapshot.
//
// It seems that we can also drop deletion later than earliest snapshot
// given that:
// (1) The deletion is earlier than earliest_write_conflict_snapshot, and
// (2) No value exist earlier than the deletion.
++iter_stats_.num_record_drop_obsolete;
if (!bottommost_level_) {
++iter_stats_.num_optimized_del_drop_obsolete;
}
input_->Next();
} else if (ikey_.type == kTypeMerge) {
if (!merge_helper_->HasOperator()) {
@@ -494,8 +571,8 @@ void CompactionIterator::NextFromInput() {
// These will be correctly set below.
key_ = merge_out_iter_.key();
value_ = merge_out_iter_.value();
bool valid_key __attribute__((__unused__)) =
ParseInternalKey(key_, &ikey_);
bool valid_key __attribute__((__unused__));
valid_key = ParseInternalKey(key_, &ikey_);
// MergeUntil stops when it encounters a corrupt key and does not
// include them in the result, so we expect the keys here to valid.
assert(valid_key);
@@ -545,11 +622,18 @@ void CompactionIterator::PrepareOutput() {
// and the earliest snapshot is larger than this seqno
// and the userkey differs from the last userkey in compaction
// then we can squash the seqno to zero.
//
// This is safe for TransactionDB write-conflict checking since transactions
// only care about sequence number larger than any active snapshots.
if ((compaction_ != nullptr && !compaction_->allow_ingest_behind()) &&
//
// Can we do the same for levels above bottom level as long as
// KeyNotExistsBeyondOutputLevel() return true?
if ((compaction_ != nullptr &&
!compaction_->allow_ingest_behind()) &&
ikeyNotNeededForIncrementalSnapshot() &&
bottommost_level_ && valid_ && ikey_.sequence <= earliest_snapshot_ &&
(snapshot_checker_ == nullptr || LIKELY(snapshot_checker_->IsInSnapshot(
ikey_.sequence, earliest_snapshot_))) &&
ikey_.type != kTypeMerge &&
!cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
@@ -561,10 +645,11 @@ void CompactionIterator::PrepareOutput() {
inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
SequenceNumber in, SequenceNumber* prev_snapshot) {
assert(snapshots_->size());
SequenceNumber prev __attribute__((__unused__)) = kMaxSequenceNumber;
SequenceNumber prev = kMaxSequenceNumber;
for (const auto cur : *snapshots_) {
assert(prev == kMaxSequenceNumber || prev <= cur);
if (cur >= in) {
if (cur >= in && (snapshot_checker_ == nullptr ||
snapshot_checker_->IsInSnapshot(in, cur))) {
*prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
return cur;
}
@@ -575,4 +660,11 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
return kMaxSequenceNumber;
}
// used in 2 places - prevents deletion markers to be dropped if they may be
// needed and disables seqnum zero-out in PrepareOutput for recent keys.
inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
return (!compaction_->preserve_deletes()) ||
(ikey_.sequence < preserve_deletes_seqnum_);
}
} // namespace rocksdb
+31 -11
View File
@@ -1,11 +1,7 @@
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#pragma once
#include <algorithm>
@@ -18,6 +14,7 @@
#include "db/merge_helper.h"
#include "db/pinned_iterators_manager.h"
#include "db/range_del_aggregator.h"
#include "db/snapshot_checker.h"
#include "options/cf_options.h"
#include "rocksdb/compaction_filter.h"
@@ -52,6 +49,9 @@ class CompactionIterator {
virtual bool allow_ingest_behind() const {
return compaction_->immutable_cf_options()->allow_ingest_behind;
}
virtual bool preserve_deletes() const {
return compaction_->immutable_cf_options()->preserve_deletes;
}
protected:
CompactionProxy() = default;
@@ -63,25 +63,29 @@ class CompactionIterator {
CompactionIterator(InternalIterator* input, const Comparator* cmp,
MergeHelper* merge_helper, SequenceNumber last_sequence,
std::vector<SequenceNumber>* snapshots,
SequenceNumber earliest_write_conflict_snapshot, Env* env,
SequenceNumber earliest_write_conflict_snapshot,
const SnapshotChecker* snapshot_checker, Env* env,
bool expect_valid_internal_key,
RangeDelAggregator* range_del_agg,
const Compaction* compaction = nullptr,
const CompactionFilter* compaction_filter = nullptr,
CompactionEventListener* compaction_listener = nullptr,
const std::atomic<bool>* shutting_down = nullptr);
const std::atomic<bool>* shutting_down = nullptr,
const SequenceNumber preserve_deletes_seqnum = 0);
// Constructor with custom CompactionProxy, used for tests.
CompactionIterator(InternalIterator* input, const Comparator* cmp,
MergeHelper* merge_helper, SequenceNumber last_sequence,
std::vector<SequenceNumber>* snapshots,
SequenceNumber earliest_write_conflict_snapshot, Env* env,
SequenceNumber earliest_write_conflict_snapshot,
const SnapshotChecker* snapshot_checker, Env* env,
bool expect_valid_internal_key,
RangeDelAggregator* range_del_agg,
std::unique_ptr<CompactionProxy> compaction,
const CompactionFilter* compaction_filter = nullptr,
CompactionEventListener* compaction_listener = nullptr,
const std::atomic<bool>* shutting_down = nullptr);
const std::atomic<bool>* shutting_down = nullptr,
const SequenceNumber preserve_deletes_seqnum = 0);
~CompactionIterator();
@@ -115,6 +119,9 @@ class CompactionIterator {
// compression.
void PrepareOutput();
// Invoke compaction filter if needed.
void InvokeFilterIfNeeded(bool* need_skip, Slice* skip_until);
// Given a sequence number, return the sequence number of the
// earliest snapshot that this sequence number is visible in.
// The snapshots themselves are arranged in ascending order of
@@ -124,18 +131,27 @@ class CompactionIterator {
inline SequenceNumber findEarliestVisibleSnapshot(
SequenceNumber in, SequenceNumber* prev_snapshot);
// Checks whether the currently seen ikey_ is needed for
// incremental (differential) snapshot and hence can't be dropped
// or seqnum be zero-ed out even if all other conditions for it are met.
inline bool ikeyNotNeededForIncrementalSnapshot();
InternalIterator* input_;
const Comparator* cmp_;
MergeHelper* merge_helper_;
const std::vector<SequenceNumber>* snapshots_;
const SequenceNumber earliest_write_conflict_snapshot_;
const SnapshotChecker* const snapshot_checker_;
Env* env_;
bool expect_valid_internal_key_;
RangeDelAggregator* range_del_agg_;
std::unique_ptr<CompactionProxy> compaction_;
const CompactionFilter* compaction_filter_;
#ifndef ROCKSDB_LITE
CompactionEventListener* compaction_listener_;
#endif // !ROCKSDB_LITE
const std::atomic<bool>* shutting_down_;
const SequenceNumber preserve_deletes_seqnum_;
bool bottommost_level_;
bool valid_ = false;
bool visible_at_tip_;
@@ -191,6 +207,10 @@ class CompactionIterator {
std::vector<size_t> level_ptrs_;
CompactionIterationStats iter_stats_;
// Used to avoid purging uncommitted values. The application can specify
// uncommitted values by providing a SnapshotChecker object.
bool current_key_committed_;
bool IsShuttingDown() {
// This is a best-effort facility, so memory_order_relaxed is sufficient.
return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
+526 -40
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include "db/compaction_iterator.h"
@@ -11,8 +9,10 @@
#include <vector>
#include "port/port.h"
#include "util/string_util.h"
#include "util/testharness.h"
#include "util/testutil.h"
#include "utilities/merge_operators.h"
namespace rocksdb {
@@ -41,9 +41,9 @@ class NoMergingMergeOp : public MergeOperator {
// Always returns Decition::kRemove.
class StallingFilter : public CompactionFilter {
public:
virtual Decision FilterV2(int level, const Slice& key, ValueType t,
const Slice& existing_value, std::string* new_value,
std::string* skip_until) const override {
Decision FilterV2(int /*level*/, const Slice& key, ValueType /*type*/,
const Slice& /*existing_value*/, std::string* /*new_value*/,
std::string* /*skip_until*/) const override {
int k = std::atoi(key.ToString().c_str());
last_seen.store(k);
while (k >= stall_at.load()) {
@@ -74,6 +74,18 @@ class StallingFilter : public CompactionFilter {
mutable std::atomic<int> last_seen{0};
};
// Compaction filter that filter out all keys.
class FilterAllKeysCompactionFilter : public CompactionFilter {
public:
Decision FilterV2(int /*level*/, const Slice& /*key*/, ValueType /*type*/,
const Slice& /*existing_value*/, std::string* /*new_value*/,
std::string* /*skip_until*/) const override {
return Decision::kRemove;
}
const char* Name() const override { return "AllKeysCompactionFilter"; }
};
class LoggingForwardVectorIterator : public InternalIterator {
public:
struct Action {
@@ -146,71 +158,146 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
public:
FakeCompaction() = default;
virtual int level(size_t compaction_input_level) const { return 0; }
virtual int level(size_t compaction_input_level) const override { return 0; }
virtual bool KeyNotExistsBeyondOutputLevel(
const Slice& user_key, std::vector<size_t>* level_ptrs) const {
return key_not_exists_beyond_output_level;
const Slice& user_key, std::vector<size_t>* level_ptrs) const override {
return is_bottommost_level || key_not_exists_beyond_output_level;
}
virtual bool bottommost_level() const { return false; }
virtual int number_levels() const { return 1; }
virtual Slice GetLargestUserKey() const {
virtual bool bottommost_level() const override { return is_bottommost_level; }
virtual int number_levels() const override { return 1; }
virtual Slice GetLargestUserKey() const override {
return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
}
virtual bool allow_ingest_behind() const { return false; }
virtual bool allow_ingest_behind() const override { return false; }
virtual bool preserve_deletes() const override { return false; }
bool key_not_exists_beyond_output_level = false;
bool is_bottommost_level = false;
};
class CompactionIteratorTest : public testing::Test {
// A simplifed snapshot checker which assumes each snapshot has a global
// last visible sequence.
class TestSnapshotChecker : public SnapshotChecker {
public:
explicit TestSnapshotChecker(
SequenceNumber last_committed_sequence,
const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {})
: last_committed_sequence_(last_committed_sequence),
snapshots_(snapshots) {}
bool IsInSnapshot(SequenceNumber seq,
SequenceNumber snapshot_seq) const override {
if (snapshot_seq == kMaxSequenceNumber) {
return seq <= last_committed_sequence_;
}
assert(snapshots_.count(snapshot_seq) > 0);
return seq <= snapshots_.at(snapshot_seq);
}
private:
SequenceNumber last_committed_sequence_;
// A map of valid snapshot to last visible sequence to the snapshot.
std::unordered_map<SequenceNumber, SequenceNumber> snapshots_;
};
// Test param:
// bool: whether to pass snapshot_checker to compaction iterator.
class CompactionIteratorTest : public testing::TestWithParam<bool> {
public:
CompactionIteratorTest()
: cmp_(BytewiseComparator()), icmp_(cmp_), snapshots_({}) {}
void InitIterators(const std::vector<std::string>& ks,
const std::vector<std::string>& vs,
const std::vector<std::string>& range_del_ks,
const std::vector<std::string>& range_del_vs,
SequenceNumber last_sequence,
MergeOperator* merge_op = nullptr,
CompactionFilter* filter = nullptr) {
void InitIterators(
const std::vector<std::string>& ks, const std::vector<std::string>& vs,
const std::vector<std::string>& range_del_ks,
const std::vector<std::string>& range_del_vs,
SequenceNumber last_sequence,
SequenceNumber last_committed_sequence = kMaxSequenceNumber,
MergeOperator* merge_op = nullptr, CompactionFilter* filter = nullptr,
bool bottommost_level = false,
SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
std::unique_ptr<InternalIterator> range_del_iter(
new test::VectorIterator(range_del_ks, range_del_vs));
range_del_agg_.reset(new RangeDelAggregator(icmp_, snapshots_));
ASSERT_OK(range_del_agg_->AddTombstones(std::move(range_del_iter)));
std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
if (filter) {
if (filter || bottommost_level) {
compaction_proxy_ = new FakeCompaction();
compaction_proxy_->is_bottommost_level = bottommost_level;
compaction.reset(compaction_proxy_);
}
bool use_snapshot_checker = UseSnapshotChecker() || GetParam();
if (use_snapshot_checker || last_committed_sequence < kMaxSequenceNumber) {
snapshot_checker_.reset(
new TestSnapshotChecker(last_committed_sequence, snapshot_map_));
}
merge_helper_.reset(
new MergeHelper(Env::Default(), cmp_, merge_op, filter, nullptr, false,
0 /*latest_snapshot*/, snapshot_checker_.get(),
0 /*level*/, nullptr /*statistics*/, &shutting_down_));
merge_helper_.reset(new MergeHelper(Env::Default(), cmp_, merge_op, filter,
nullptr, false, 0, 0, nullptr,
&shutting_down_));
iter_.reset(new LoggingForwardVectorIterator(ks, vs));
iter_->SeekToFirst();
c_iter_.reset(new CompactionIterator(
iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
kMaxSequenceNumber, Env::Default(), false, range_del_agg_.get(),
std::move(compaction), filter, nullptr, &shutting_down_));
earliest_write_conflict_snapshot, snapshot_checker_.get(),
Env::Default(), false, range_del_agg_.get(), std::move(compaction),
filter, nullptr, &shutting_down_));
}
void AddSnapshot(SequenceNumber snapshot) { snapshots_.push_back(snapshot); }
void AddSnapshot(SequenceNumber snapshot,
SequenceNumber last_visible_seq = kMaxSequenceNumber) {
snapshots_.push_back(snapshot);
snapshot_map_[snapshot] = last_visible_seq;
}
virtual bool UseSnapshotChecker() const { return false; }
void RunTest(
const std::vector<std::string>& input_keys,
const std::vector<std::string>& input_values,
const std::vector<std::string>& expected_keys,
const std::vector<std::string>& expected_values,
SequenceNumber last_committed_seq = kMaxSequenceNumber,
MergeOperator* merge_operator = nullptr,
CompactionFilter* compaction_filter = nullptr,
bool bottommost_level = false,
SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
InitIterators(input_keys, input_values, {}, {}, kMaxSequenceNumber,
last_committed_seq, merge_operator, compaction_filter,
bottommost_level, earliest_write_conflict_snapshot);
c_iter_->SeekToFirst();
for (size_t i = 0; i < expected_keys.size(); i++) {
std::string info = "i = " + ToString(i);
ASSERT_TRUE(c_iter_->Valid()) << info;
ASSERT_OK(c_iter_->status()) << info;
ASSERT_EQ(expected_keys[i], c_iter_->key().ToString()) << info;
ASSERT_EQ(expected_values[i], c_iter_->value().ToString()) << info;
c_iter_->Next();
}
ASSERT_FALSE(c_iter_->Valid());
}
const Comparator* cmp_;
const InternalKeyComparator icmp_;
std::vector<SequenceNumber> snapshots_;
// A map of valid snapshot to last visible sequence to the snapshot.
std::unordered_map<SequenceNumber, SequenceNumber> snapshot_map_;
std::unique_ptr<MergeHelper> merge_helper_;
std::unique_ptr<LoggingForwardVectorIterator> iter_;
std::unique_ptr<CompactionIterator> c_iter_;
std::unique_ptr<RangeDelAggregator> range_del_agg_;
std::unique_ptr<SnapshotChecker> snapshot_checker_;
std::atomic<bool> shutting_down_{false};
FakeCompaction* compaction_proxy_;
};
// It is possible that the output of the compaction iterator is empty even if
// the input is not.
TEST_F(CompactionIteratorTest, EmptyResult) {
TEST_P(CompactionIteratorTest, EmptyResult) {
InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
test::KeyStr("a", 3, kTypeValue)},
{"", "val"}, {}, {}, 5);
@@ -220,7 +307,7 @@ TEST_F(CompactionIteratorTest, EmptyResult) {
// If there is a corruption after a single deletion, the corrupted key should
// be preserved.
TEST_F(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
TEST_P(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
test::KeyStr("a", 3, kTypeValue, true),
test::KeyStr("b", 10, kTypeValue)},
@@ -239,7 +326,7 @@ TEST_F(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
ASSERT_FALSE(c_iter_->Valid());
}
TEST_F(CompactionIteratorTest, SimpleRangeDeletion) {
TEST_P(CompactionIteratorTest, SimpleRangeDeletion) {
InitIterators({test::KeyStr("morning", 5, kTypeValue),
test::KeyStr("morning", 2, kTypeValue),
test::KeyStr("night", 3, kTypeValue)},
@@ -255,7 +342,7 @@ TEST_F(CompactionIteratorTest, SimpleRangeDeletion) {
ASSERT_FALSE(c_iter_->Valid());
}
TEST_F(CompactionIteratorTest, RangeDeletionWithSnapshots) {
TEST_P(CompactionIteratorTest, RangeDeletionWithSnapshots) {
AddSnapshot(10);
std::vector<std::string> ks1;
ks1.push_back(test::KeyStr("ma", 28, kTypeRangeDeletion));
@@ -276,7 +363,7 @@ TEST_F(CompactionIteratorTest, RangeDeletionWithSnapshots) {
ASSERT_FALSE(c_iter_->Valid());
}
TEST_F(CompactionIteratorTest, CompactionFilterSkipUntil) {
TEST_P(CompactionIteratorTest, CompactionFilterSkipUntil) {
class Filter : public CompactionFilter {
virtual Decision FilterV2(int level, const Slice& key, ValueType t,
const Slice& existing_value,
@@ -351,7 +438,7 @@ TEST_F(CompactionIteratorTest, CompactionFilterSkipUntil) {
test::KeyStr("j", 99, kTypeValue)},
{"av50", "am45", "bv60", "bv40", "cv35", "dm70", "em71", "fm65", "fm30",
"fv25", "gv90", "hv91", "im95", "jv99"},
{}, {}, kMaxSequenceNumber, &merge_op, &filter);
{}, {}, kMaxSequenceNumber, kMaxSequenceNumber, &merge_op, &filter);
// Compaction should output just "a", "e" and "h" keys.
c_iter_->SeekToFirst();
@@ -386,13 +473,14 @@ TEST_F(CompactionIteratorTest, CompactionFilterSkipUntil) {
ASSERT_EQ(expected_actions, iter_->log);
}
TEST_F(CompactionIteratorTest, ShuttingDownInFilter) {
TEST_P(CompactionIteratorTest, ShuttingDownInFilter) {
NoMergingMergeOp merge_op;
StallingFilter filter;
InitIterators(
{test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeValue),
test::KeyStr("3", 3, kTypeValue), test::KeyStr("4", 4, kTypeValue)},
{"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, &merge_op, &filter);
{"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, kMaxSequenceNumber,
&merge_op, &filter);
// Don't leave tombstones (kTypeDeletion) for filtered keys.
compaction_proxy_->key_not_exists_beyond_output_level = true;
@@ -423,13 +511,14 @@ TEST_F(CompactionIteratorTest, ShuttingDownInFilter) {
// Same as ShuttingDownInFilter, but shutdown happens during filter call for
// a merge operand, not for a value.
TEST_F(CompactionIteratorTest, ShuttingDownInMerge) {
TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
NoMergingMergeOp merge_op;
StallingFilter filter;
InitIterators(
{test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeMerge),
test::KeyStr("3", 3, kTypeMerge), test::KeyStr("4", 4, kTypeValue)},
{"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, &merge_op, &filter);
{"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, kMaxSequenceNumber,
&merge_op, &filter);
compaction_proxy_->key_not_exists_beyond_output_level = true;
std::atomic<bool> seek_done{false};
@@ -457,6 +546,403 @@ TEST_F(CompactionIteratorTest, ShuttingDownInMerge) {
EXPECT_EQ(2, filter.last_seen.load());
}
TEST_P(CompactionIteratorTest, SingleMergeOperand) {
class Filter : public CompactionFilter {
virtual Decision FilterV2(int level, const Slice& key, ValueType t,
const Slice& existing_value,
std::string* new_value,
std::string* skip_until) const override {
std::string k = key.ToString();
std::string v = existing_value.ToString();
// See InitIterators() call below for the sequence of keys and their
// filtering decisions. Here we closely assert that compaction filter is
// called with the expected keys and only them, and with the right values.
if (k == "a") {
EXPECT_EQ(ValueType::kMergeOperand, t);
EXPECT_EQ("av1", v);
return Decision::kKeep;
} else if (k == "b") {
EXPECT_EQ(ValueType::kMergeOperand, t);
return Decision::kKeep;
} else if (k == "c") {
return Decision::kKeep;
}
ADD_FAILURE();
return Decision::kKeep;
}
const char* Name() const override {
return "CompactionIteratorTest.SingleMergeOperand::Filter";
}
};
class SingleMergeOp : public MergeOperator {
public:
bool FullMergeV2(const MergeOperationInput& merge_in,
MergeOperationOutput* merge_out) const override {
// See InitIterators() call below for why "c" is the only key for which
// FullMergeV2 should be called.
EXPECT_EQ("c", merge_in.key.ToString());
std::string temp_value;
if (merge_in.existing_value != nullptr) {
temp_value = merge_in.existing_value->ToString();
}
for (auto& operand : merge_in.operand_list) {
temp_value.append(operand.ToString());
}
merge_out->new_value = temp_value;
return true;
}
bool PartialMergeMulti(const Slice& key,
const std::deque<Slice>& operand_list,
std::string* new_value,
Logger* logger) const override {
std::string string_key = key.ToString();
EXPECT_TRUE(string_key == "a" || string_key == "b");
if (string_key == "a") {
EXPECT_EQ(1, operand_list.size());
} else if (string_key == "b") {
EXPECT_EQ(2, operand_list.size());
}
std::string temp_value;
for (auto& operand : operand_list) {
temp_value.append(operand.ToString());
}
swap(temp_value, *new_value);
return true;
}
const char* Name() const override {
return "CompactionIteratorTest SingleMergeOp";
}
bool AllowSingleOperand() const override { return true; }
};
SingleMergeOp merge_op;
Filter filter;
InitIterators(
// a should invoke PartialMergeMulti with a single merge operand.
{test::KeyStr("a", 50, kTypeMerge),
// b should invoke PartialMergeMulti with two operands.
test::KeyStr("b", 70, kTypeMerge), test::KeyStr("b", 60, kTypeMerge),
// c should invoke FullMerge due to kTypeValue at the beginning.
test::KeyStr("c", 90, kTypeMerge), test::KeyStr("c", 80, kTypeValue)},
{"av1", "bv2", "bv1", "cv2", "cv1"}, {}, {}, kMaxSequenceNumber,
kMaxSequenceNumber, &merge_op, &filter);
c_iter_->SeekToFirst();
ASSERT_TRUE(c_iter_->Valid());
ASSERT_EQ(test::KeyStr("a", 50, kTypeMerge), c_iter_->key().ToString());
ASSERT_EQ("av1", c_iter_->value().ToString());
c_iter_->Next();
ASSERT_TRUE(c_iter_->Valid());
ASSERT_EQ("bv1bv2", c_iter_->value().ToString());
c_iter_->Next();
ASSERT_EQ("cv1cv2", c_iter_->value().ToString());
}
// In bottommost level, values earlier than earliest snapshot can be output
// with sequence = 0.
TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
AddSnapshot(1);
RunTest({test::KeyStr("a", 1, kTypeValue), test::KeyStr("b", 2, kTypeValue)},
{"v1", "v2"},
{test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 2, kTypeValue)},
{"v1", "v2"}, kMaxSequenceNumber /*last_commited_seq*/,
nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
true /*bottommost_level*/);
}
// In bottommost level, deletions earlier than earliest snapshot can be removed
// permanently.
TEST_P(CompactionIteratorTest, RemoveDeletionAtBottomLevel) {
AddSnapshot(1);
RunTest({test::KeyStr("a", 1, kTypeDeletion),
test::KeyStr("b", 2, kTypeDeletion)},
{"", ""}, {test::KeyStr("b", 2, kTypeDeletion)}, {""},
kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
nullptr /*compaction_filter*/, true /*bottommost_level*/);
}
// In bottommost level, single deletions earlier than earliest snapshot can be
// removed permanently.
TEST_P(CompactionIteratorTest, RemoveSingleDeletionAtBottomLevel) {
AddSnapshot(1);
RunTest({test::KeyStr("a", 1, kTypeSingleDeletion),
test::KeyStr("b", 2, kTypeSingleDeletion)},
{"", ""}, {test::KeyStr("b", 2, kTypeSingleDeletion)}, {""},
kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
nullptr /*compaction_filter*/, true /*bottommost_level*/);
}
INSTANTIATE_TEST_CASE_P(CompactionIteratorTestInstance, CompactionIteratorTest,
testing::Values(true, false));
// Tests how CompactionIterator work together with SnapshotChecker.
class CompactionIteratorWithSnapshotCheckerTest
: public CompactionIteratorTest {
public:
bool UseSnapshotChecker() const override { return true; }
};
// Uncommitted keys (keys with seq > last_committed_seq) should be output as-is
// while committed version of these keys should get compacted as usual.
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
PreserveUncommittedKeys_Value) {
RunTest(
{test::KeyStr("foo", 3, kTypeValue), test::KeyStr("foo", 2, kTypeValue),
test::KeyStr("foo", 1, kTypeValue)},
{"v3", "v2", "v1"},
{test::KeyStr("foo", 3, kTypeValue), test::KeyStr("foo", 2, kTypeValue)},
{"v3", "v2"}, 2 /*last_committed_seq*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
PreserveUncommittedKeys_Deletion) {
RunTest({test::KeyStr("foo", 2, kTypeDeletion),
test::KeyStr("foo", 1, kTypeValue)},
{"", "v1"},
{test::KeyStr("foo", 2, kTypeDeletion),
test::KeyStr("foo", 1, kTypeValue)},
{"", "v1"}, 1 /*last_committed_seq*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
PreserveUncommittedKeys_Merge) {
auto merge_op = MergeOperators::CreateStringAppendOperator();
RunTest(
{test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 2, kTypeMerge),
test::KeyStr("foo", 1, kTypeValue)},
{"v3", "v2", "v1"},
{test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 2, kTypeValue)},
{"v3", "v1,v2"}, 2 /*last_committed_seq*/, merge_op.get());
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
PreserveUncommittedKeys_SingleDelete) {
RunTest({test::KeyStr("foo", 2, kTypeSingleDeletion),
test::KeyStr("foo", 1, kTypeValue)},
{"", "v1"},
{test::KeyStr("foo", 2, kTypeSingleDeletion),
test::KeyStr("foo", 1, kTypeValue)},
{"", "v1"}, 1 /*last_committed_seq*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
PreserveUncommittedKeys_BlobIndex) {
RunTest({test::KeyStr("foo", 3, kTypeBlobIndex),
test::KeyStr("foo", 2, kTypeBlobIndex),
test::KeyStr("foo", 1, kTypeBlobIndex)},
{"v3", "v2", "v1"},
{test::KeyStr("foo", 3, kTypeBlobIndex),
test::KeyStr("foo", 2, kTypeBlobIndex)},
{"v3", "v2"}, 2 /*last_committed_seq*/);
}
// Test compaction iterator dedup keys visible to the same snapshot.
TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Value) {
AddSnapshot(2, 1);
RunTest(
{test::KeyStr("foo", 4, kTypeValue), test::KeyStr("foo", 3, kTypeValue),
test::KeyStr("foo", 2, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
{"v4", "v3", "v2", "v1"},
{test::KeyStr("foo", 4, kTypeValue), test::KeyStr("foo", 3, kTypeValue),
test::KeyStr("foo", 1, kTypeValue)},
{"v4", "v3", "v1"}, 3 /*last_committed_seq*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Deletion) {
AddSnapshot(2, 1);
RunTest(
{test::KeyStr("foo", 4, kTypeValue),
test::KeyStr("foo", 3, kTypeDeletion),
test::KeyStr("foo", 2, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
{"v4", "", "v2", "v1"},
{test::KeyStr("foo", 4, kTypeValue),
test::KeyStr("foo", 3, kTypeDeletion),
test::KeyStr("foo", 1, kTypeValue)},
{"v4", "", "v1"}, 3 /*last_committed_seq*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Merge) {
AddSnapshot(2, 1);
AddSnapshot(4, 3);
auto merge_op = MergeOperators::CreateStringAppendOperator();
RunTest(
{test::KeyStr("foo", 5, kTypeMerge), test::KeyStr("foo", 4, kTypeMerge),
test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 2, kTypeMerge),
test::KeyStr("foo", 1, kTypeValue)},
{"v5", "v4", "v3", "v2", "v1"},
{test::KeyStr("foo", 5, kTypeMerge), test::KeyStr("foo", 4, kTypeMerge),
test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 1, kTypeValue)},
{"v5", "v4", "v2,v3", "v1"}, 4 /*last_committed_seq*/, merge_op.get());
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
DedupSameSnapshot_SingleDeletion) {
AddSnapshot(2, 1);
RunTest(
{test::KeyStr("foo", 4, kTypeValue),
test::KeyStr("foo", 3, kTypeSingleDeletion),
test::KeyStr("foo", 2, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
{"v4", "", "v2", "v1"},
{test::KeyStr("foo", 4, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
{"v4", "v1"}, 3 /*last_committed_seq*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_BlobIndex) {
AddSnapshot(2, 1);
RunTest({test::KeyStr("foo", 4, kTypeBlobIndex),
test::KeyStr("foo", 3, kTypeBlobIndex),
test::KeyStr("foo", 2, kTypeBlobIndex),
test::KeyStr("foo", 1, kTypeBlobIndex)},
{"v4", "v3", "v2", "v1"},
{test::KeyStr("foo", 4, kTypeBlobIndex),
test::KeyStr("foo", 3, kTypeBlobIndex),
test::KeyStr("foo", 1, kTypeBlobIndex)},
{"v4", "v3", "v1"}, 3 /*last_committed_seq*/);
}
// At bottom level, sequence numbers can be zero out, and deletions can be
// removed, but only when they are visible to earliest snapshot.
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
NotZeroOutSequenceIfNotVisibleToEarliestSnapshot) {
AddSnapshot(2, 1);
RunTest({test::KeyStr("a", 1, kTypeValue), test::KeyStr("b", 2, kTypeValue),
test::KeyStr("c", 3, kTypeValue)},
{"v1", "v2", "v3"},
{test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 2, kTypeValue),
test::KeyStr("c", 3, kTypeValue)},
{"v1", "v2", "v3"}, kMaxSequenceNumber /*last_commited_seq*/,
nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
true /*bottommost_level*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
NotRemoveDeletionIfNotVisibleToEarliestSnapshot) {
AddSnapshot(2, 1);
RunTest(
{test::KeyStr("a", 1, kTypeDeletion), test::KeyStr("b", 2, kTypeDeletion),
test::KeyStr("c", 3, kTypeDeletion)},
{"", "", ""},
{test::KeyStr("b", 2, kTypeDeletion),
test::KeyStr("c", 3, kTypeDeletion)},
{"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
true /*bottommost_level*/);
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
NotRemoveSingleDeletionIfNotVisibleToEarliestSnapshot) {
AddSnapshot(2, 1);
RunTest({test::KeyStr("a", 1, kTypeSingleDeletion),
test::KeyStr("b", 2, kTypeSingleDeletion),
test::KeyStr("c", 3, kTypeSingleDeletion)},
{"", "", ""},
{test::KeyStr("b", 2, kTypeSingleDeletion),
test::KeyStr("c", 3, kTypeSingleDeletion)},
{"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
true /*bottommost_level*/);
}
// Single delete should not cancel out values that not visible to the
// same set of snapshots
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
SingleDeleteAcrossSnapshotBoundary) {
AddSnapshot(2, 1);
RunTest({test::KeyStr("a", 2, kTypeSingleDeletion),
test::KeyStr("a", 1, kTypeValue)},
{"", "v1"},
{test::KeyStr("a", 2, kTypeSingleDeletion),
test::KeyStr("a", 1, kTypeValue)},
{"", "v1"}, 2 /*last_committed_seq*/);
}
// Single delete should be kept in case it is not visible to the
// earliest write conflict snapshot. If a single delete is kept for this reason,
// corresponding value can be trimmed to save space.
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
KeepSingleDeletionForWriteConflictChecking) {
AddSnapshot(2, 0);
RunTest({test::KeyStr("a", 2, kTypeSingleDeletion),
test::KeyStr("a", 1, kTypeValue)},
{"", "v1"},
{test::KeyStr("a", 2, kTypeSingleDeletion),
test::KeyStr("a", 1, kTypeValue)},
{"", ""}, 2 /*last_committed_seq*/, nullptr /*merge_operator*/,
nullptr /*compaction_filter*/, false /*bottommost_level*/,
2 /*earliest_write_conflict_snapshot*/);
}
// Compaction filter should keep uncommitted key as-is, and
// * Convert the latest velue to deletion, and/or
// * if latest value is a merge, apply filter to all suequent merges.
TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Value) {
std::unique_ptr<CompactionFilter> compaction_filter(
new FilterAllKeysCompactionFilter());
RunTest(
{test::KeyStr("a", 2, kTypeValue), test::KeyStr("a", 1, kTypeValue),
test::KeyStr("b", 3, kTypeValue), test::KeyStr("c", 1, kTypeValue)},
{"v2", "v1", "v3", "v4"},
{test::KeyStr("a", 2, kTypeValue), test::KeyStr("a", 1, kTypeDeletion),
test::KeyStr("b", 3, kTypeValue), test::KeyStr("c", 1, kTypeDeletion)},
{"v2", "", "v3", ""}, 1 /*last_committed_seq*/,
nullptr /*merge_operator*/, compaction_filter.get());
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Deletion) {
std::unique_ptr<CompactionFilter> compaction_filter(
new FilterAllKeysCompactionFilter());
RunTest(
{test::KeyStr("a", 2, kTypeDeletion), test::KeyStr("a", 1, kTypeValue)},
{"", "v1"},
{test::KeyStr("a", 2, kTypeDeletion),
test::KeyStr("a", 1, kTypeDeletion)},
{"", ""}, 1 /*last_committed_seq*/, nullptr /*merge_operator*/,
compaction_filter.get());
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest,
CompactionFilter_PartialMerge) {
std::shared_ptr<MergeOperator> merge_op =
MergeOperators::CreateStringAppendOperator();
std::unique_ptr<CompactionFilter> compaction_filter(
new FilterAllKeysCompactionFilter());
RunTest({test::KeyStr("a", 3, kTypeMerge), test::KeyStr("a", 2, kTypeMerge),
test::KeyStr("a", 1, kTypeMerge)},
{"v3", "v2", "v1"}, {test::KeyStr("a", 3, kTypeMerge)}, {"v3"},
2 /*last_committed_seq*/, merge_op.get(), compaction_filter.get());
}
TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_FullMerge) {
std::shared_ptr<MergeOperator> merge_op =
MergeOperators::CreateStringAppendOperator();
std::unique_ptr<CompactionFilter> compaction_filter(
new FilterAllKeysCompactionFilter());
RunTest(
{test::KeyStr("a", 3, kTypeMerge), test::KeyStr("a", 2, kTypeMerge),
test::KeyStr("a", 1, kTypeValue)},
{"v3", "v2", "v1"},
{test::KeyStr("a", 3, kTypeMerge), test::KeyStr("a", 1, kTypeDeletion)},
{"v3", ""}, 2 /*last_committed_seq*/, merge_op.get(),
compaction_filter.get());
}
} // namespace rocksdb
int main(int argc, char** argv) {
+153 -65
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -40,7 +38,6 @@
#include "monitoring/iostats_context_imp.h"
#include "monitoring/perf_context_imp.h"
#include "monitoring/thread_status_util.h"
#include "port/likely.h"
#include "port/port.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
@@ -266,15 +263,16 @@ void CompactionJob::AggregateStatistics() {
CompactionJob::CompactionJob(
int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
const EnvOptions& env_options, VersionSet* versions,
const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
const EnvOptions env_options, VersionSet* versions,
const std::atomic<bool>* shutting_down,
const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
Directory* db_directory, Directory* output_directory, Statistics* stats,
InstrumentedMutex* db_mutex, Status* db_bg_error,
std::vector<SequenceNumber> existing_snapshots,
SequenceNumber earliest_write_conflict_snapshot,
std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
bool paranoid_file_checks, bool measure_io_stats, const std::string& dbname,
CompactionJobStats* compaction_job_stats)
const SnapshotChecker* snapshot_checker, std::shared_ptr<Cache> table_cache,
EventLogger* event_logger, bool paranoid_file_checks, bool measure_io_stats,
const std::string& dbname, CompactionJobStats* compaction_job_stats)
: job_id_(job_id),
compact_(new CompactionState(compaction)),
compaction_job_stats_(compaction_job_stats),
@@ -283,8 +281,11 @@ CompactionJob::CompactionJob(
db_options_(db_options),
env_options_(env_options),
env_(db_options.env),
env_optiosn_for_read_(
env_->OptimizeForCompactionTableRead(env_options, db_options_)),
versions_(versions),
shutting_down_(shutting_down),
preserve_deletes_seqnum_(preserve_deletes_seqnum),
log_buffer_(log_buffer),
db_directory_(db_directory),
output_directory_(output_directory),
@@ -293,10 +294,13 @@ CompactionJob::CompactionJob(
db_bg_error_(db_bg_error),
existing_snapshots_(std::move(existing_snapshots)),
earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
snapshot_checker_(snapshot_checker),
table_cache_(std::move(table_cache)),
event_logger_(event_logger),
bottommost_level_(false),
paranoid_file_checks_(paranoid_file_checks),
measure_io_stats_(measure_io_stats) {
measure_io_stats_(measure_io_stats),
write_hint_(Env::WLTH_NOT_SET) {
assert(log_buffer_ != nullptr);
const auto* cfd = compact_->compaction->column_family_data();
ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
@@ -367,6 +371,8 @@ void CompactionJob::Prepare() {
assert(c->column_family_data()->current()->storage_info()
->NumLevelFiles(compact_->compaction->level()) > 0);
write_hint_ = c->column_family_data()->CalculateSSTWriteHint(
c->output_level());
// Is this compaction producing files at the bottommost level?
bottommost_level_ = c->bottommost_level();
@@ -596,6 +602,9 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
double read_write_amp = 0.0;
double write_amp = 0.0;
double bytes_read_per_sec = 0;
double bytes_written_per_sec = 0;
if (stats.bytes_read_non_output_levels > 0) {
read_write_amp = (stats.bytes_written + stats.bytes_read_output_level +
stats.bytes_read_non_output_levels) /
@@ -603,37 +612,46 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
write_amp = stats.bytes_written /
static_cast<double>(stats.bytes_read_non_output_levels);
}
if (stats.micros > 0) {
bytes_read_per_sec =
(stats.bytes_read_non_output_levels + stats.bytes_read_output_level) /
static_cast<double>(stats.micros);
bytes_written_per_sec =
stats.bytes_written / static_cast<double>(stats.micros);
}
ROCKS_LOG_BUFFER(
log_buffer_,
"[%s] compacted to: %s, MB/sec: %.1f rd, %.1f wr, level %d, "
"files in(%d, %d) out(%d) "
"MB in(%.1f, %.1f) out(%.1f), read-write-amplify(%.1f) "
"write-amplify(%.1f) %s, records in: %d, records dropped: %d\n",
cfd->GetName().c_str(), vstorage->LevelSummary(&tmp),
(stats.bytes_read_non_output_levels + stats.bytes_read_output_level) /
static_cast<double>(stats.micros),
stats.bytes_written / static_cast<double>(stats.micros),
compact_->compaction->output_level(),
"write-amplify(%.1f) %s, records in: %" PRIu64
", records dropped: %" PRIu64 " output_compression: %s\n",
cfd->GetName().c_str(), vstorage->LevelSummary(&tmp), bytes_read_per_sec,
bytes_written_per_sec, compact_->compaction->output_level(),
stats.num_input_files_in_non_output_levels,
stats.num_input_files_in_output_level, stats.num_output_files,
stats.bytes_read_non_output_levels / 1048576.0,
stats.bytes_read_output_level / 1048576.0,
stats.bytes_written / 1048576.0, read_write_amp, write_amp,
status.ToString().c_str(), stats.num_input_records,
stats.num_dropped_records);
stats.num_dropped_records,
CompressionTypeToString(compact_->compaction->output_compression())
.c_str());
UpdateCompactionJobStats(stats);
auto stream = event_logger_->LogToBuffer(log_buffer_);
stream << "job" << job_id_
<< "event" << "compaction_finished"
stream << "job" << job_id_ << "event"
<< "compaction_finished"
<< "compaction_time_micros" << compaction_stats_.micros
<< "output_level" << compact_->compaction->output_level()
<< "num_output_files" << compact_->NumOutputFiles()
<< "total_output_size" << compact_->total_bytes
<< "num_input_records" << compact_->num_input_records
<< "num_output_records" << compact_->num_output_records
<< "num_subcompactions" << compact_->sub_compact_states.size();
<< "total_output_size" << compact_->total_bytes << "num_input_records"
<< compact_->num_input_records << "num_output_records"
<< compact_->num_output_records << "num_subcompactions"
<< compact_->sub_compact_states.size() << "output_compression"
<< CompressionTypeToString(compact_->compaction->output_compression());
if (compaction_job_stats_ != nullptr) {
stream << "num_single_delete_mismatches"
@@ -668,7 +686,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
std::unique_ptr<RangeDelAggregator> range_del_agg(
new RangeDelAggregator(cfd->internal_comparator(), existing_snapshots_));
std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
sub_compact->compaction, range_del_agg.get()));
sub_compact->compaction, range_del_agg.get(), env_optiosn_for_read_));
AutoThreadOperationStageUpdater stage_updater(
ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -693,15 +711,18 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
sub_compact->compaction->mutable_cf_options();
// To build compression dictionary, we sample the first output file, assuming
// it'll reach the maximum length, and then use the dictionary for compressing
// subsequent output files. The dictionary may be less than max_dict_bytes if
// the first output file's length is less than the maximum.
// it'll reach the maximum length. We optionally pass these samples through
// zstd's dictionary trainer, or just use them directly. Then, the dictionary
// is used for compressing subsequent output files in the same subcompaction.
const bool kUseZstdTrainer =
cfd->ioptions()->compression_opts.zstd_max_train_bytes > 0;
const size_t kSampleBytes =
kUseZstdTrainer ? cfd->ioptions()->compression_opts.zstd_max_train_bytes
: cfd->ioptions()->compression_opts.max_dict_bytes;
const int kSampleLenShift = 6; // 2^6 = 64-byte samples
std::set<size_t> sample_begin_offsets;
if (bottommost_level_ &&
cfd->ioptions()->compression_opts.max_dict_bytes > 0) {
const size_t kMaxSamples =
cfd->ioptions()->compression_opts.max_dict_bytes >> kSampleLenShift;
if (bottommost_level_ && kSampleBytes > 0) {
const size_t kMaxSamples = kSampleBytes >> kSampleLenShift;
const size_t kOutFileLen = mutable_cf_options->MaxFileSizeForLevel(
compact_->compaction->output_level());
if (kOutFileLen != port::kMaxSizet) {
@@ -726,8 +747,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
compaction_filter, db_options_.info_log.get(),
false /* internal key corruption is expected */,
existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
compact_->compaction->level(), db_options_.statistics.get(),
shutting_down_);
snapshot_checker_, compact_->compaction->level(),
db_options_.statistics.get(), shutting_down_);
TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
@@ -755,9 +776,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
Status status;
sub_compact->c_iter.reset(new CompactionIterator(
input.get(), cfd->user_comparator(), &merge, versions_->LastSequence(),
&existing_snapshots_, earliest_write_conflict_snapshot_, env_, false,
range_del_agg.get(), sub_compact->compaction, compaction_filter,
comp_event_listener, shutting_down_));
&existing_snapshots_, earliest_write_conflict_snapshot_,
snapshot_checker_, env_, false, range_del_agg.get(),
sub_compact->compaction, compaction_filter, comp_event_listener,
shutting_down_, preserve_deletes_seqnum_));
auto c_iter = sub_compact->c_iter.get();
c_iter->SeekToFirst();
if (c_iter->Valid() &&
@@ -770,11 +792,11 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
}
const auto& c_iter_stats = c_iter->iter_stats();
auto sample_begin_offset_iter = sample_begin_offsets.cbegin();
// data_begin_offset and compression_dict are only valid while generating
// data_begin_offset and dict_sample_data are only valid while generating
// dictionary from the first output file.
size_t data_begin_offset = 0;
std::string compression_dict;
compression_dict.reserve(cfd->ioptions()->compression_opts.max_dict_bytes);
std::string dict_sample_data;
dict_sample_data.reserve(kSampleBytes);
while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
// Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
@@ -846,7 +868,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
data_elmt_copy_len =
data_end_offset - (data_begin_offset + data_elmt_copy_offset);
}
compression_dict.append(&data_elmt.data()[data_elmt_copy_offset],
dict_sample_data.append(&data_elmt.data()[data_elmt_copy_offset],
data_elmt_copy_len);
if (sample_end_offset > data_end_offset) {
// Didn't finish sample. Try to finish it with the next data_elmt.
@@ -901,9 +923,15 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
RecordDroppedKeys(range_del_out_stats,
&sub_compact->compaction_job_stats);
if (sub_compact->outputs.size() == 1) {
// Use dictionary from first output file for compression of subsequent
// files.
sub_compact->compression_dict = std::move(compression_dict);
// Use samples from first output file to create dictionary for
// compression of subsequent files.
if (kUseZstdTrainer) {
sub_compact->compression_dict = ZSTD_TrainDictionary(
dict_sample_data, kSampleLenShift,
cfd->ioptions()->compression_opts.max_dict_bytes);
} else {
sub_compact->compression_dict = std::move(dict_sample_data);
}
}
}
}
@@ -1008,6 +1036,10 @@ void CompactionJob::RecordDroppedKeys(
RecordTick(stats_, COMPACTION_RANGE_DEL_DROP_OBSOLETE,
c_iter_stats.num_range_del_drop_obsolete);
}
if (c_iter_stats.num_optimized_del_drop_obsolete > 0) {
RecordTick(stats_, COMPACTION_OPTIMIZED_DEL_DROP_OBSOLETE,
c_iter_stats.num_optimized_del_drop_obsolete);
}
}
Status CompactionJob::FinishCompactionOutputFile(
@@ -1025,12 +1057,12 @@ Status CompactionJob::FinishCompactionOutputFile(
uint64_t output_number = sub_compact->current_output()->meta.fd.GetNumber();
assert(output_number != 0);
TableProperties table_properties;
// Check for iterator errors
Status s = input_status;
auto meta = &sub_compact->current_output()->meta;
if (s.ok()) {
Slice lower_bound_guard, upper_bound_guard;
std::string smallest_user_key;
const Slice *lower_bound, *upper_bound;
if (sub_compact->outputs.size() == 1) {
// For the first output table, include range tombstones before the min key
@@ -1040,7 +1072,8 @@ Status CompactionJob::FinishCompactionOutputFile(
// For subsequent output tables, only include range tombstones from min
// key onwards since the previous file was extended to contain range
// tombstones falling before min key.
lower_bound_guard = meta->smallest.user_key();
smallest_user_key = meta->smallest.user_key().ToString(false /*hex*/);
lower_bound_guard = Slice(smallest_user_key);
lower_bound = &lower_bound_guard;
} else {
lower_bound = nullptr;
@@ -1058,16 +1091,18 @@ Status CompactionJob::FinishCompactionOutputFile(
range_del_agg->AddToBuilder(sub_compact->builder.get(), lower_bound,
upper_bound, meta, range_del_out_stats,
bottommost_level_);
meta->marked_for_compaction = sub_compact->builder->NeedCompact();
}
const uint64_t current_entries = sub_compact->builder->NumEntries();
meta->marked_for_compaction = sub_compact->builder->NeedCompact();
if (s.ok()) {
s = sub_compact->builder->Finish();
} else {
sub_compact->builder->Abandon();
}
const uint64_t current_bytes = sub_compact->builder->FileSize();
meta->fd.file_size = current_bytes;
if (s.ok()) {
meta->fd.file_size = current_bytes;
}
sub_compact->current_output()->finished = true;
sub_compact->total_bytes += current_bytes;
@@ -1081,6 +1116,23 @@ Status CompactionJob::FinishCompactionOutputFile(
}
sub_compact->outfile.reset();
if (s.ok() && current_entries == 0) {
// If there is nothing to output, no necessary to generate a sst file.
// This happens when the output level is bottom level, at the same time
// the sub_compact output nothing.
std::string fname = TableFileName(
db_options_.db_paths, meta->fd.GetNumber(), meta->fd.GetPathId());
env_->DeleteFile(fname);
// Also need to remove the file from outputs, or it will be added to the
// VersionEdit.
assert(!sub_compact->outputs.empty());
sub_compact->outputs.pop_back();
sub_compact->builder.reset();
sub_compact->current_output_file_size = 0;
return s;
}
ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
TableProperties tp;
if (s.ok() && current_entries > 0) {
@@ -1095,7 +1147,8 @@ Status CompactionJob::FinishCompactionOutputFile(
nullptr /* range_del_agg */, nullptr,
cfd->internal_stats()->GetFileReadHist(
compact_->compaction->output_level()),
false);
false, nullptr /* arena */, false /* skip_filters */,
compact_->compaction->output_level());
s = iter->status();
if (s.ok() && paranoid_file_checks_) {
@@ -1118,27 +1171,44 @@ Status CompactionJob::FinishCompactionOutputFile(
meta->marked_for_compaction ? " (need compaction)" : "");
}
}
std::string fname = TableFileName(db_options_.db_paths, meta->fd.GetNumber(),
meta->fd.GetPathId());
std::string fname;
FileDescriptor output_fd;
if (meta != nullptr) {
fname = TableFileName(db_options_.db_paths, meta->fd.GetNumber(),
meta->fd.GetPathId());
output_fd = meta->fd;
} else {
fname = "(nil)";
}
EventHelpers::LogAndNotifyTableFileCreationFinished(
event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname,
job_id_, meta->fd, tp, TableFileCreationReason::kCompaction, s);
job_id_, output_fd, tp, TableFileCreationReason::kCompaction, s);
#ifndef ROCKSDB_LITE
// Report new file to SstFileManagerImpl
auto sfm =
static_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
if (sfm && meta->fd.GetPathId() == 0) {
if (sfm && meta != nullptr && meta->fd.GetPathId() == 0) {
auto fn = TableFileName(cfd->ioptions()->db_paths, meta->fd.GetNumber(),
meta->fd.GetPathId());
sfm->OnAddFile(fn);
if (sfm->IsMaxAllowedSpaceReached()) {
// TODO(ajkr): should we return OK() if max space was reached by the final
// compaction output file (similarly to how flush works when full)?
s = Status::IOError("Max allowed space was reached");
TEST_SYNC_POINT(
"CompactionJob::FinishCompactionOutputFile:"
"MaxAllowedSpaceReached");
InstrumentedMutexLock l(db_mutex_);
if (db_bg_error_->ok()) {
s = Status::IOError("Max allowed space was reached");
*db_bg_error_ = s;
TEST_SYNC_POINT(
"CompactionJob::FinishCompactionOutputFile:MaxAllowedSpaceReached");
Status new_bg_error = s;
// may temporarily unlock and lock the mutex.
EventHelpers::NotifyOnBackgroundError(
cfd->ioptions()->listeners, BackgroundErrorReason::kCompaction,
&new_bg_error, db_mutex_);
if (!new_bg_error.ok()) {
*db_bg_error_ = new_bg_error;
}
}
}
}
@@ -1216,11 +1286,12 @@ Status CompactionJob::OpenCompactionOutputFile(
#endif // !ROCKSDB_LITE
// Make the output file
unique_ptr<WritableFile> writable_file;
EnvOptions opt_env_opts =
env_->OptimizeForCompactionTableWrite(env_options_, db_options_);
#ifndef NDEBUG
bool syncpoint_arg = env_options_.use_direct_writes;
TEST_SYNC_POINT_CALLBACK("CompactionJob::OpenCompactionOutputFile",
&opt_env_opts.use_direct_writes);
Status s = NewWritableFile(env_, fname, &writable_file, opt_env_opts);
&syncpoint_arg);
#endif
Status s = NewWritableFile(env_, fname, &writable_file, env_options_);
if (!s.ok()) {
ROCKS_LOG_ERROR(
db_options_.info_log,
@@ -1243,6 +1314,7 @@ Status CompactionJob::OpenCompactionOutputFile(
sub_compact->outputs.push_back(out);
writable_file->SetIOPriority(Env::IO_LOW);
writable_file->SetWriteLifeTimeHint(write_hint_);
writable_file->SetPreallocationBlockSize(static_cast<size_t>(
sub_compact->compaction->OutputFilePreallocationSize()));
sub_compact->outfile.reset(new WritableFileWriter(
@@ -1253,14 +1325,30 @@ Status CompactionJob::OpenCompactionOutputFile(
// data is going to be found
bool skip_filters =
cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;
uint64_t output_file_creation_time =
sub_compact->compaction->MaxInputFileCreationTime();
if (output_file_creation_time == 0) {
int64_t _current_time = 0;
auto status = db_options_.env->GetCurrentTime(&_current_time);
// Safe to proceed even if GetCurrentTime fails. So, log and proceed.
if (!status.ok()) {
ROCKS_LOG_WARN(
db_options_.info_log,
"Failed to get current time to populate creation_time property. "
"Status: %s",
status.ToString().c_str());
}
output_file_creation_time = static_cast<uint64_t>(_current_time);
}
sub_compact->builder.reset(NewTableBuilder(
*cfd->ioptions(), cfd->internal_comparator(),
cfd->int_tbl_prop_collector_factories(), cfd->GetID(), cfd->GetName(),
sub_compact->outfile.get(), sub_compact->compaction->output_compression(),
cfd->ioptions()->compression_opts,
sub_compact->compaction->output_level(),
&sub_compact->compression_dict,
skip_filters));
sub_compact->compaction->output_level(), &sub_compact->compression_dict,
skip_filters, output_file_creation_time));
LogFlush(db_options_.info_log);
return s;
}
+17 -9
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -47,24 +45,28 @@
namespace rocksdb {
class Arena;
class MemTable;
class SnapshotChecker;
class TableCache;
class Version;
class VersionEdit;
class VersionSet;
class Arena;
class CompactionJob {
public:
CompactionJob(int job_id, Compaction* compaction,
const ImmutableDBOptions& db_options,
const EnvOptions& env_options, VersionSet* versions,
const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
const EnvOptions env_options, VersionSet* versions,
const std::atomic<bool>* shutting_down,
const SequenceNumber preserve_deletes_seqnum,
LogBuffer* log_buffer,
Directory* db_directory, Directory* output_directory,
Statistics* stats, InstrumentedMutex* db_mutex,
Status* db_bg_error,
std::vector<SequenceNumber> existing_snapshots,
SequenceNumber earliest_write_conflict_snapshot,
const SnapshotChecker* snapshot_checker,
std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
bool paranoid_file_checks, bool measure_io_stats,
const std::string& dbname,
@@ -129,11 +131,14 @@ class CompactionJob {
// DBImpl state
const std::string& dbname_;
const ImmutableDBOptions& db_options_;
const EnvOptions& env_options_;
const EnvOptions env_options_;
Env* env_;
// env_option optimized for compaction table reads
EnvOptions env_optiosn_for_read_;
VersionSet* versions_;
const std::atomic<bool>* shutting_down_;
const SequenceNumber preserve_deletes_seqnum_;
LogBuffer* log_buffer_;
Directory* db_directory_;
Directory* output_directory_;
@@ -151,6 +156,8 @@ class CompactionJob {
// should make sure not to remove evidence that a write occurred.
SequenceNumber earliest_write_conflict_snapshot_;
const SnapshotChecker* const snapshot_checker_;
std::shared_ptr<Cache> table_cache_;
EventLogger* event_logger_;
@@ -162,6 +169,7 @@ class CompactionJob {
std::vector<Slice> boundaries_;
// Stores the approx size of keys covered in the range of each subcompaction
std::vector<uint64_t> sizes_;
Env::WriteLifeTimeHint write_hint_;
};
} // namespace rocksdb
+3 -7
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -656,7 +654,6 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
Options options;
options.listeners.emplace_back(stats_checker);
options.create_if_missing = true;
options.max_background_flushes = 0;
// just enough setting to hold off auto-compaction.
options.level0_file_num_compaction_trigger = kTestScale + 1;
options.num_levels = 3;
@@ -878,7 +875,6 @@ TEST_P(CompactionJobStatsTest, DeletionStatsTest) {
Options options;
options.listeners.emplace_back(stats_checker);
options.create_if_missing = true;
options.max_background_flushes = 0;
options.level0_file_num_compaction_trigger = kTestScale+1;
options.num_levels = 3;
options.compression = kNoCompression;
+34 -11
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#ifndef ROCKSDB_LITE
@@ -78,6 +76,7 @@ class CompactionJobTest : public testing::Test {
table_cache_.get(), &write_buffer_manager_,
&write_controller_)),
shutting_down_(false),
preserve_deletes_seqnum_(0),
mock_table_factory_(new mock::MockTableFactory()) {
EXPECT_OK(env_->CreateDirIfMissing(dbname_));
db_options_.db_paths.emplace_back(dbname_,
@@ -144,6 +143,8 @@ class CompactionJobTest : public testing::Test {
}
void SetLastSequence(const SequenceNumber sequence_number) {
versions_->SetLastAllocatedSequence(sequence_number + 1);
versions_->SetLastPublishedSequence(sequence_number + 1);
versions_->SetLastSequence(sequence_number + 1);
}
@@ -251,12 +252,15 @@ class CompactionJobTest : public testing::Test {
LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
mutex_.Lock();
EventLogger event_logger(db_options_.info_log.get());
CompactionJob compaction_job(
0, &compaction, db_options_, env_options_, versions_.get(),
&shutting_down_, &log_buffer, nullptr, nullptr, nullptr, &mutex_,
&bg_error_, snapshots, earliest_write_conflict_snapshot, table_cache_,
&event_logger, false, false, dbname_, &compaction_job_stats_);
// TODO(yiwu) add a mock snapshot checker and add test for it.
SnapshotChecker* snapshot_checker = nullptr;
CompactionJob compaction_job(0, &compaction, db_options_, env_options_,
versions_.get(), &shutting_down_,
preserve_deletes_seqnum_, &log_buffer,
nullptr, nullptr, nullptr, &mutex_, &bg_error_,
snapshots, earliest_write_conflict_snapshot,
snapshot_checker, table_cache_, &event_logger,
false, false, dbname_, &compaction_job_stats_);
VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
compaction_job.Prepare();
@@ -292,6 +296,7 @@ class CompactionJobTest : public testing::Test {
std::unique_ptr<VersionSet> versions_;
InstrumentedMutex mutex_;
std::atomic<bool> shutting_down_;
SequenceNumber preserve_deletes_seqnum_;
std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
CompactionJobStats compaction_job_stats_;
ColumnFamilyData* cfd_;
@@ -339,6 +344,24 @@ TEST_F(CompactionJobTest, SimpleDeletion) {
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, OutputNothing) {
NewDB();
auto file1 = mock::MakeMockFile({{KeyStr("a", 1U, kTypeValue), "val"}});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({{KeyStr("a", 2U, kTypeDeletion), ""}});
AddMockFile(file2);
auto expected_results = mock::MakeMockFile();
SetLastSequence(4U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, SimpleOverwrite) {
NewDB();
+201 -74
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -91,7 +89,7 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
// If bottommost_compression is set and we are compacting to the
// bottommost level then we should use it.
if (ioptions.bottommost_compression != kDisableCompressionOption &&
level > base_level && level >= (vstorage->num_non_empty_levels() - 1)) {
level >= (vstorage->num_non_empty_levels() - 1)) {
return ioptions.bottommost_compression;
}
// If the user has specified a different compression level for each level,
@@ -236,11 +234,6 @@ bool CompactionPicker::ExpandInputsToCleanCut(const std::string& cf_name,
// If, after the expansion, there are files that are already under
// compaction, then we must drop/cancel this compaction.
if (AreFilesInCompaction(inputs->files)) {
ROCKS_LOG_WARN(
ioptions_.info_log,
"[%s] ExpandWhileOverlapping() failure because some of the necessary"
" compaction input files are currently being compacted.",
cf_name.c_str());
return false;
}
return true;
@@ -299,25 +292,16 @@ Compaction* CompactionPicker::CompactFiles(
VersionStorageInfo* vstorage, const MutableCFOptions& mutable_cf_options,
uint32_t output_path_id) {
assert(input_files.size());
// This compaction output should not overlap with a running compaction as
// `SanitizeCompactionInputFiles` should've checked earlier and db mutex
// shouldn't have been released since.
assert(!FilesRangeOverlapWithCompaction(input_files, output_level));
// TODO(rven ): we might be able to run concurrent level 0 compaction
// if the key ranges of the two compactions do not overlap, but for now
// we do not allow it.
if ((input_files[0].level == 0) && !level0_compactions_in_progress_.empty()) {
return nullptr;
}
// This compaction output could overlap with a running compaction
if (FilesRangeOverlapWithCompaction(input_files, output_level)) {
return nullptr;
}
auto c =
new Compaction(vstorage, ioptions_, mutable_cf_options, input_files,
output_level, compact_options.output_file_size_limit,
mutable_cf_options.max_compaction_bytes, output_path_id,
compact_options.compression, /* grandparents */ {}, true);
// If it's level 0 compaction, make sure we don't execute any other level 0
// compactions in parallel
RegisterCompaction(c);
return c;
}
@@ -403,7 +387,10 @@ bool CompactionPicker::SetupOtherInputs(
assert(output_level_inputs->empty());
const int input_level = inputs->level;
const int output_level = output_level_inputs->level;
assert(input_level != output_level);
if (input_level == output_level) {
// no possibility of conflict
return true;
}
// For now, we only support merging two levels, start level and output level.
// We need to assert other levels are empty.
@@ -737,10 +724,6 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
auto& levels = cf_meta.levels;
auto comparator = icmp_->user_comparator();
// TODO(yhchiang): If there is any input files of L1 or up and there
// is at least one L0 files. All L0 files older than the L0 file needs
// to be included. Otherwise, it is a false conditoin
// TODO(yhchiang): add is_adjustable to CompactionOptions
// the smallest and largest key of the current compaction input
@@ -801,6 +784,8 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
}
last_included++;
}
} else if (output_level > 0) {
last_included = static_cast<int>(current_files.size() - 1);
}
// include all files between the first and the last compaction input files.
@@ -956,6 +941,9 @@ void CompactionPicker::UnregisterCompaction(Compaction* c) {
bool LevelCompactionPicker::NeedsCompaction(
const VersionStorageInfo* vstorage) const {
if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
return true;
}
if (!vstorage->FilesMarkedForCompaction().empty()) {
return true;
}
@@ -1108,11 +1096,7 @@ void LevelCompactionBuilder::SetupInitialFiles() {
}
output_level_ =
(start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
if (PickFileToCompact() &&
compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
&start_level_inputs_) &&
!compaction_picker_->FilesRangeOverlapWithCompaction(
{start_level_inputs_}, output_level_)) {
if (PickFileToCompact()) {
// found the compaction!
if (start_level_ == 0) {
// L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
@@ -1150,7 +1134,28 @@ void LevelCompactionBuilder::SetupInitialFiles() {
is_manual_ = true;
parent_index_ = base_index_ = -1;
PickFilesMarkedForCompaction();
if (!start_level_inputs_.empty()) {
if (start_level_inputs_.empty()) {
size_t i;
for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
++i) {
auto& level_and_file =
vstorage_->BottommostFilesMarkedForCompaction()[i];
assert(!level_and_file.second->being_compacted);
start_level_inputs_.level = output_level_ = start_level_ =
level_and_file.first;
start_level_inputs_.files = {level_and_file.second};
if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
&start_level_inputs_)) {
break;
}
}
if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
start_level_inputs_.clear();
} else {
assert(!start_level_inputs_.empty());
compaction_reason_ = CompactionReason::kBottommostFiles;
}
} else {
compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
}
}
@@ -1290,6 +1295,8 @@ uint32_t LevelCompactionBuilder::GetPathId(
uint64_t level_size;
int cur_level = 0;
// max_bytes_for_level_base denotes L1 size.
// We estimate L0 size to be the same as L1.
level_size = mutable_cf_options.max_bytes_for_level_base;
// Last path is the fallback
@@ -1300,8 +1307,21 @@ uint32_t LevelCompactionBuilder::GetPathId(
return p;
} else {
current_path_size -= level_size;
level_size = static_cast<uint64_t>(
level_size * mutable_cf_options.max_bytes_for_level_multiplier);
if (cur_level > 0) {
if (ioptions.level_compaction_dynamic_level_bytes) {
// Currently, level_compaction_dynamic_level_bytes is ignored when
// multiple db paths are specified. https://github.com/facebook/
// rocksdb/blob/master/db/column_family.cc.
// Still, adding this check to avoid accidentally using
// max_bytes_for_level_multiplier_additional
level_size = static_cast<uint64_t>(
level_size * mutable_cf_options.max_bytes_for_level_multiplier);
} else {
level_size = static_cast<uint64_t>(
level_size * mutable_cf_options.max_bytes_for_level_multiplier *
mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
}
}
cur_level++;
continue;
}
@@ -1334,12 +1354,10 @@ bool LevelCompactionBuilder::PickFileToCompact() {
const std::vector<FileMetaData*>& level_files =
vstorage_->LevelFiles(start_level_);
// record the first file that is not yet compacted
int nextIndex = -1;
for (unsigned int i = vstorage_->NextCompactionIndex(start_level_);
i < file_size.size(); i++) {
int index = file_size[i];
unsigned int cmp_idx;
for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
cmp_idx < file_size.size(); cmp_idx++) {
int index = file_size[cmp_idx];
auto* f = level_files[index];
// do not pick a file to compact if it is being compacted
@@ -1348,27 +1366,42 @@ bool LevelCompactionBuilder::PickFileToCompact() {
continue;
}
// remember the startIndex for the next call to PickCompaction
if (nextIndex == -1) {
nextIndex = i;
}
// Do not pick this file if its parents at level+1 are being compacted.
// Maybe we can avoid redoing this work in SetupOtherInputs
parent_index_ = -1;
if (compaction_picker_->IsRangeInCompaction(vstorage_, &f->smallest,
&f->largest, output_level_,
&parent_index_)) {
continue;
}
start_level_inputs_.files.push_back(f);
start_level_inputs_.level = start_level_;
if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
&start_level_inputs_) ||
compaction_picker_->FilesRangeOverlapWithCompaction(
{start_level_inputs_}, output_level_)) {
// A locked (pending compaction) input-level file was pulled in due to
// user-key overlap.
start_level_inputs_.clear();
continue;
}
// Now that input level is fully expanded, we check whether any output files
// are locked due to pending compaction.
//
// Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
// level files are locked, not just the extra ones pulled in for user-key
// overlap.
InternalKey smallest, largest;
compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
CompactionInputFiles output_level_inputs;
output_level_inputs.level = output_level_;
vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
&output_level_inputs.files);
if (!output_level_inputs.empty() &&
!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
&output_level_inputs)) {
start_level_inputs_.clear();
continue;
}
base_index_ = index;
break;
}
// store where to start the iteration in the next call to PickCompaction
vstorage_->SetNextCompactionIndex(start_level_, nextIndex);
vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
return start_level_inputs_.size() > 0;
}
@@ -1405,21 +1438,97 @@ bool FIFOCompactionPicker::NeedsCompaction(
return vstorage->CompactionScore(kLevel0) >= 1;
}
Compaction* FIFOCompactionPicker::PickCompaction(
namespace {
uint64_t GetTotalFilesSize(
const std::vector<FileMetaData*>& files) {
uint64_t total_size = 0;
for (const auto& f : files) {
total_size += f->fd.file_size;
}
return total_size;
}
} // anonymous namespace
Compaction* FIFOCompactionPicker::PickTTLCompaction(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
assert(vstorage->num_levels() == 1);
assert(mutable_cf_options.compaction_options_fifo.ttl > 0);
const int kLevel0 = 0;
const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
uint64_t total_size = 0;
for (const auto& file : level_files) {
total_size += file->fd.file_size;
uint64_t total_size = GetTotalFilesSize(level_files);
int64_t _current_time;
auto status = ioptions_.env->GetCurrentTime(&_current_time);
if (!status.ok()) {
ROCKS_LOG_BUFFER(log_buffer,
"[%s] FIFO compaction: Couldn't get current time: %s. "
"Not doing compactions based on TTL. ",
cf_name.c_str(), status.ToString().c_str());
return nullptr;
}
const uint64_t current_time = static_cast<uint64_t>(_current_time);
std::vector<CompactionInputFiles> inputs;
inputs.emplace_back();
inputs[0].level = 0;
// avoid underflow
if (current_time > mutable_cf_options.compaction_options_fifo.ttl) {
for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
auto f = *ritr;
if (f->fd.table_reader != nullptr &&
f->fd.table_reader->GetTableProperties() != nullptr) {
auto creation_time =
f->fd.table_reader->GetTableProperties()->creation_time;
if (creation_time == 0 ||
creation_time >= (current_time -
mutable_cf_options.compaction_options_fifo.ttl)) {
break;
}
total_size -= f->compensated_file_size;
inputs[0].files.push_back(f);
}
}
}
if (total_size <= ioptions_.compaction_options_fifo.max_table_files_size ||
// Return a nullptr and proceed to size-based FIFO compaction if:
// 1. there are no files older than ttl OR
// 2. there are a few files older than ttl, but deleting them will not bring
// the total size to be less than max_table_files_size threshold.
if (inputs[0].files.empty() ||
total_size >
mutable_cf_options.compaction_options_fifo.max_table_files_size) {
return nullptr;
}
for (const auto& f : inputs[0].files) {
ROCKS_LOG_BUFFER(log_buffer,
"[%s] FIFO compaction: picking file %" PRIu64
" with creation time %" PRIu64 " for deletion",
cf_name.c_str(), f->fd.GetNumber(),
f->fd.table_reader->GetTableProperties()->creation_time);
}
Compaction* c = new Compaction(
vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
kNoCompression, {}, /* is manual */ false, vstorage->CompactionScore(0),
/* is deletion compaction */ true, CompactionReason::kFIFOTtl);
return c;
}
Compaction* FIFOCompactionPicker::PickSizeCompaction(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
const int kLevel0 = 0;
const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
uint64_t total_size = GetTotalFilesSize(level_files);
if (total_size <=
mutable_cf_options.compaction_options_fifo.max_table_files_size ||
level_files.size() == 0) {
// total size not exceeded
if (ioptions_.compaction_options_fifo.allow_compaction &&
if (mutable_cf_options.compaction_options_fifo.allow_compaction &&
level_files.size() > 0) {
CompactionInputFiles comp_inputs;
if (FindIntraL0Compaction(
@@ -1435,16 +1544,16 @@ Compaction* FIFOCompactionPicker::PickCompaction(
/* is manual */ false, vstorage->CompactionScore(0),
/* is deletion compaction */ false,
CompactionReason::kFIFOReduceNumFiles);
RegisterCompaction(c);
return c;
}
}
ROCKS_LOG_BUFFER(log_buffer,
"[%s] FIFO compaction: nothing to do. Total size %" PRIu64
", max size %" PRIu64 "\n",
cf_name.c_str(), total_size,
ioptions_.compaction_options_fifo.max_table_files_size);
ROCKS_LOG_BUFFER(
log_buffer,
"[%s] FIFO compaction: nothing to do. Total size %" PRIu64
", max size %" PRIu64 "\n",
cf_name.c_str(), total_size,
mutable_cf_options.compaction_options_fifo.max_table_files_size);
return nullptr;
}
@@ -1460,24 +1569,42 @@ Compaction* FIFOCompactionPicker::PickCompaction(
std::vector<CompactionInputFiles> inputs;
inputs.emplace_back();
inputs[0].level = 0;
// delete old files (FIFO)
for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
auto f = *ritr;
total_size -= f->compensated_file_size;
inputs[0].files.push_back(f);
char tmp_fsize[16];
AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
ROCKS_LOG_BUFFER(log_buffer, "[%s] FIFO compaction: picking file %" PRIu64
" with size %s for deletion",
ROCKS_LOG_BUFFER(log_buffer,
"[%s] FIFO compaction: picking file %" PRIu64
" with size %s for deletion",
cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
if (total_size <= ioptions_.compaction_options_fifo.max_table_files_size) {
if (total_size <=
mutable_cf_options.compaction_options_fifo.max_table_files_size) {
break;
}
}
Compaction* c = new Compaction(
vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
kNoCompression, {}, /* is manual */ false, vstorage->CompactionScore(0),
/* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
return c;
}
Compaction* FIFOCompactionPicker::PickCompaction(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
assert(vstorage->num_levels() == 1);
Compaction* c = nullptr;
if (mutable_cf_options.compaction_options_fifo.ttl > 0) {
c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
}
if (c == nullptr) {
c = PickSizeCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
}
RegisterCompaction(c);
return c;
}
+18 -5
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -90,6 +88,10 @@ class CompactionPicker {
// Takes a list of CompactionInputFiles and returns a (manual) Compaction
// object.
//
// Caller must provide a set of input files that has been passed through
// `SanitizeCompactionInputFiles` earlier. The lock should not be released
// between that call and this one.
Compaction* CompactFiles(const CompactionOptions& compact_options,
const std::vector<CompactionInputFiles>& input_files,
int output_level, VersionStorageInfo* vstorage,
@@ -244,6 +246,17 @@ class FIFOCompactionPicker : public CompactionPicker {
virtual bool NeedsCompaction(
const VersionStorageInfo* vstorage) const override;
private:
Compaction* PickTTLCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* version,
LogBuffer* log_buffer);
Compaction* PickSizeCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* version,
LogBuffer* log_buffer);
};
class NullCompactionPicker : public CompactionPicker {
+136 -12
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include "db/compaction_picker.h"
#include <limits>
@@ -177,6 +175,8 @@ TEST_F(CompactionPickerTest, Level1Trigger) {
}
TEST_F(CompactionPickerTest, Level1Trigger2) {
mutable_cf_options_.target_file_size_base = 10000000000;
mutable_cf_options_.RefreshDerivedOptions(ioptions_);
NewVersionStorage(6, kCompactionStyleLevel);
Add(1, 66U, "150", "200", 1000000001U);
Add(1, 88U, "201", "300", 1000000000U);
@@ -193,13 +193,14 @@ TEST_F(CompactionPickerTest, Level1Trigger2) {
ASSERT_EQ(66U, compaction->input(0, 0)->fd.GetNumber());
ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
ASSERT_EQ(7U, compaction->input(1, 1)->fd.GetNumber());
ASSERT_EQ(uint64_t{1073741824}, compaction->OutputFilePreallocationSize());
}
TEST_F(CompactionPickerTest, LevelMaxScore) {
NewVersionStorage(6, kCompactionStyleLevel);
mutable_cf_options_.target_file_size_base = 10000000;
mutable_cf_options_.target_file_size_multiplier = 10;
mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
mutable_cf_options_.RefreshDerivedOptions(ioptions_);
Add(0, 1U, "150", "200", 1000000U);
// Level 1 score 1.2
Add(1, 66U, "150", "200", 6000000U);
@@ -220,6 +221,9 @@ TEST_F(CompactionPickerTest, LevelMaxScore) {
ASSERT_TRUE(compaction.get() != nullptr);
ASSERT_EQ(1U, compaction->num_input_files(0));
ASSERT_EQ(7U, compaction->input(0, 0)->fd.GetNumber());
ASSERT_EQ(mutable_cf_options_.target_file_size_base +
mutable_cf_options_.target_file_size_base / 10,
compaction->OutputFilePreallocationSize());
}
TEST_F(CompactionPickerTest, NeedsCompactionLevel) {
@@ -439,7 +443,7 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
const uint64_t kFileSize = 100000;
ioptions_.compaction_options_universal.allow_trivial_move = true;
mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
NewVersionStorage(1, kCompactionStyleUniversal);
UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
// must return false when there's no files.
@@ -470,7 +474,7 @@ TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
const uint64_t kFileSize = 100000;
ioptions_.compaction_options_universal.allow_trivial_move = true;
mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
NewVersionStorage(3, kCompactionStyleUniversal);
@@ -498,7 +502,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
const uint64_t kMaxSize = kFileSize * kFileCount / 2;
fifo_options_.max_table_files_size = kMaxSize;
ioptions_.compaction_options_fifo = fifo_options_;
mutable_cf_options_.compaction_options_fifo = fifo_options_;
FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
UpdateVersionStorageInfo();
// must return false when there's no files.
@@ -514,7 +518,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
kFileSize, 0, i * 100, i * 100 + 99);
current_size += kFileSize;
UpdateVersionStorageInfo();
ASSERT_EQ(level_compaction_picker.NeedsCompaction(vstorage_.get()),
ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()),
vstorage_->CompactionScore(0) >= 1);
}
}
@@ -523,9 +527,10 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
NewVersionStorage(6, kCompactionStyleLevel);
ioptions_.compaction_pri = kMinOverlappingRatio;
mutable_cf_options_.target_file_size_base = 10000000;
mutable_cf_options_.target_file_size_base = 100000000000;
mutable_cf_options_.target_file_size_multiplier = 10;
mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
mutable_cf_options_.RefreshDerivedOptions(ioptions_);
Add(2, 6U, "150", "179", 50000000U);
Add(2, 7U, "180", "220", 50000000U);
@@ -545,6 +550,8 @@ TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
ASSERT_EQ(1U, compaction->num_input_files(0));
// Pick file 8 because it overlaps with 0 files on level 3.
ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
// Compaction input size * 1.1
ASSERT_GE(uint64_t{55000000}, compaction->OutputFilePreallocationSize());
}
TEST_F(CompactionPickerTest, CompactionPriMinOverlapping2) {
@@ -854,6 +861,80 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys9) {
ASSERT_EQ(8U, compaction->input(1, 1)->fd.GetNumber());
}
TEST_F(CompactionPickerTest, OverlappingUserKeys10) {
// Locked file encountered when pulling in extra input-level files with same
// user keys. Verify we pick the next-best file from the same input level.
NewVersionStorage(6, kCompactionStyleLevel);
mutable_cf_options_.max_compaction_bytes = 100000000000u;
// file_number 2U is largest and thus first choice. But it overlaps with
// file_number 1U which is being compacted. So instead we pick the next-
// biggest file, 3U, which is eligible for compaction.
Add(1 /* level */, 1U /* file_number */, "100" /* smallest */,
"150" /* largest */, 1U /* file_size */);
file_map_[1U].first->being_compacted = true;
Add(1 /* level */, 2U /* file_number */, "150" /* smallest */,
"200" /* largest */, 1000000000U /* file_size */, 0 /* smallest_seq */,
0 /* largest_seq */);
Add(1 /* level */, 3U /* file_number */, "201" /* smallest */,
"250" /* largest */, 900000000U /* file_size */);
Add(2 /* level */, 4U /* file_number */, "100" /* smallest */,
"150" /* largest */, 1U /* file_size */);
Add(2 /* level */, 5U /* file_number */, "151" /* smallest */,
"200" /* largest */, 1U /* file_size */);
Add(2 /* level */, 6U /* file_number */, "201" /* smallest */,
"250" /* largest */, 1U /* file_size */);
UpdateVersionStorageInfo();
std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
ASSERT_TRUE(compaction.get() != nullptr);
ASSERT_EQ(2U, compaction->num_input_levels());
ASSERT_EQ(1U, compaction->num_input_files(0));
ASSERT_EQ(1U, compaction->num_input_files(1));
ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
}
TEST_F(CompactionPickerTest, OverlappingUserKeys11) {
// Locked file encountered when pulling in extra output-level files with same
// user keys. Expected to skip that compaction and pick the next-best choice.
NewVersionStorage(6, kCompactionStyleLevel);
mutable_cf_options_.max_compaction_bytes = 100000000000u;
// score(L1) = 3.7
// score(L2) = 1.85
// There is no eligible file in L1 to compact since both candidates pull in
// file_number 5U, which overlaps with a file pending compaction (6U). The
// first eligible compaction is from L2->L3.
Add(1 /* level */, 2U /* file_number */, "151" /* smallest */,
"200" /* largest */, 1000000000U /* file_size */);
Add(1 /* level */, 3U /* file_number */, "201" /* smallest */,
"250" /* largest */, 1U /* file_size */);
Add(2 /* level */, 4U /* file_number */, "100" /* smallest */,
"149" /* largest */, 5000000000U /* file_size */);
Add(2 /* level */, 5U /* file_number */, "150" /* smallest */,
"201" /* largest */, 1U /* file_size */);
Add(2 /* level */, 6U /* file_number */, "201" /* smallest */,
"249" /* largest */, 1U /* file_size */, 0 /* smallest_seq */,
0 /* largest_seq */);
file_map_[6U].first->being_compacted = true;
Add(3 /* level */, 7U /* file_number */, "100" /* smallest */,
"149" /* largest */, 1U /* file_size */);
UpdateVersionStorageInfo();
std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
ASSERT_TRUE(compaction.get() != nullptr);
ASSERT_EQ(2U, compaction->num_input_levels());
ASSERT_EQ(1U, compaction->num_input_files(0));
ASSERT_EQ(1U, compaction->num_input_files(1));
ASSERT_EQ(4U, compaction->input(0, 0)->fd.GetNumber());
ASSERT_EQ(7U, compaction->input(1, 0)->fd.GetNumber());
}
TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri1) {
NewVersionStorage(6, kCompactionStyleLevel);
mutable_cf_options_.level0_file_num_compaction_trigger = 2;
@@ -952,7 +1033,7 @@ TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri3) {
TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded1) {
int num_levels = ioptions_.num_levels;
ioptions_.level_compaction_dynamic_level_bytes = false;
mutable_cf_options_.level0_file_num_compaction_trigger = 3;
mutable_cf_options_.level0_file_num_compaction_trigger = 4;
mutable_cf_options_.max_bytes_for_level_base = 1000;
mutable_cf_options_.max_bytes_for_level_multiplier = 10;
NewVersionStorage(num_levels, kCompactionStyleLevel);
@@ -1318,6 +1399,49 @@ TEST_F(CompactionPickerTest, IsTrivialMoveOff) {
ASSERT_FALSE(compaction->IsTrivialMove());
}
TEST_F(CompactionPickerTest, CacheNextCompactionIndex) {
NewVersionStorage(6, kCompactionStyleLevel);
mutable_cf_options_.max_compaction_bytes = 100000000000u;
Add(1 /* level */, 1U /* file_number */, "100" /* smallest */,
"149" /* largest */, 1000000000U /* file_size */);
file_map_[1U].first->being_compacted = true;
Add(1 /* level */, 2U /* file_number */, "150" /* smallest */,
"199" /* largest */, 900000000U /* file_size */);
Add(1 /* level */, 3U /* file_number */, "200" /* smallest */,
"249" /* largest */, 800000000U /* file_size */);
Add(1 /* level */, 4U /* file_number */, "250" /* smallest */,
"299" /* largest */, 700000000U /* file_size */);
Add(2 /* level */, 5U /* file_number */, "150" /* smallest */,
"199" /* largest */, 1U /* file_size */);
file_map_[5U].first->being_compacted = true;
UpdateVersionStorageInfo();
std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
ASSERT_TRUE(compaction.get() != nullptr);
ASSERT_EQ(1U, compaction->num_input_levels());
ASSERT_EQ(1U, compaction->num_input_files(0));
ASSERT_EQ(0U, compaction->num_input_files(1));
ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
ASSERT_EQ(2, vstorage_->NextCompactionIndex(1 /* level */));
compaction.reset(level_compaction_picker.PickCompaction(
cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
ASSERT_TRUE(compaction.get() != nullptr);
ASSERT_EQ(1U, compaction->num_input_levels());
ASSERT_EQ(1U, compaction->num_input_files(0));
ASSERT_EQ(0U, compaction->num_input_files(1));
ASSERT_EQ(4U, compaction->input(0, 0)->fd.GetNumber());
ASSERT_EQ(3, vstorage_->NextCompactionIndex(1 /* level */));
compaction.reset(level_compaction_picker.PickCompaction(
cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
ASSERT_TRUE(compaction.get() == nullptr);
ASSERT_EQ(4, vstorage_->NextCompactionIndex(1 /* level */));
}
} // namespace rocksdb
int main(int argc, char** argv) {
+33 -27
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -37,7 +35,7 @@ namespace {
// and the index of the file in that level
struct InputFileInfo {
InputFileInfo() : f(nullptr) {}
InputFileInfo() : f(nullptr), level(0), index(0) {}
FileMetaData* f;
size_t level;
@@ -206,7 +204,8 @@ void UniversalCompactionPicker::SortedRun::DumpSizeInfo(
std::vector<UniversalCompactionPicker::SortedRun>
UniversalCompactionPicker::CalculateSortedRuns(
const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions) {
const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
const MutableCFOptions& mutable_cf_options) {
std::vector<UniversalCompactionPicker::SortedRun> ret;
for (FileMetaData* f : vstorage.LevelFiles(0)) {
ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
@@ -220,7 +219,8 @@ UniversalCompactionPicker::CalculateSortedRuns(
for (FileMetaData* f : vstorage.LevelFiles(level)) {
total_compensated_size += f->compensated_file_size;
total_size += f->fd.GetFileSize();
if (ioptions.compaction_options_universal.allow_trivial_move == true) {
if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
true) {
if (f->being_compacted) {
being_compacted = f->being_compacted;
}
@@ -229,7 +229,8 @@ UniversalCompactionPicker::CalculateSortedRuns(
// non-zero level, all the files should share the same being_compacted
// value.
// This assumption is only valid when
// ioptions.compaction_options_universal.allow_trivial_move is false
// mutable_cf_options.compaction_options_universal.allow_trivial_move is
// false
assert(is_first || f->being_compacted == being_compacted);
}
if (is_first) {
@@ -247,14 +248,13 @@ UniversalCompactionPicker::CalculateSortedRuns(
// Universal style of compaction. Pick files that are contiguous in
// time-range to compact.
//
Compaction* UniversalCompactionPicker::PickCompaction(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
const int kLevel0 = 0;
double score = vstorage->CompactionScore(kLevel0);
std::vector<SortedRun> sorted_runs =
CalculateSortedRuns(*vstorage, ioptions_);
CalculateSortedRuns(*vstorage, ioptions_, mutable_cf_options);
if (sorted_runs.size() == 0 ||
sorted_runs.size() <
@@ -281,7 +281,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
} else {
// Size amplification is within limits. Try reducing read
// amplification while maintaining file size ratios.
unsigned int ratio = ioptions_.compaction_options_universal.size_ratio;
unsigned int ratio =
mutable_cf_options.compaction_options_universal.size_ratio;
if ((c = PickCompactionToReduceSortedRuns(
cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
@@ -329,7 +330,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
return nullptr;
}
if (ioptions_.compaction_options_universal.allow_trivial_move == true) {
if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
true) {
c->set_is_trivial_move(IsInputFilesNonOverlapping(c));
}
@@ -375,6 +377,7 @@ Compaction* UniversalCompactionPicker::PickCompaction(
c->inputs(0)->size());
RegisterCompaction(c);
vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
c);
@@ -382,7 +385,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
}
uint32_t UniversalCompactionPicker::GetPathId(
const ImmutableCFOptions& ioptions, uint64_t file_size) {
const ImmutableCFOptions& ioptions,
const MutableCFOptions& mutable_cf_options, uint64_t file_size) {
// Two conditions need to be satisfied:
// (1) the target path needs to be able to hold the file's size
// (2) Total size left in this and previous paths need to be not
@@ -399,8 +403,8 @@ uint32_t UniversalCompactionPicker::GetPathId(
// that case. We need to improve it.
uint64_t accumulated_size = 0;
uint64_t future_size =
file_size * (100 - ioptions.compaction_options_universal.size_ratio) /
100;
file_size *
(100 - mutable_cf_options.compaction_options_universal.size_ratio) / 100;
uint32_t p = 0;
assert(!ioptions.db_paths.empty());
for (; p < ioptions.db_paths.size() - 1; p++) {
@@ -424,9 +428,9 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
unsigned int max_number_of_files_to_compact,
const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
unsigned int min_merge_width =
ioptions_.compaction_options_universal.min_merge_width;
mutable_cf_options.compaction_options_universal.min_merge_width;
unsigned int max_merge_width =
ioptions_.compaction_options_universal.max_merge_width;
mutable_cf_options.compaction_options_universal.max_merge_width;
const SortedRun* sr = nullptr;
bool done = false;
@@ -493,7 +497,7 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
if (sz < static_cast<double>(succeeding_sr->size)) {
break;
}
if (ioptions_.compaction_options_universal.stop_style ==
if (mutable_cf_options.compaction_options_universal.stop_style ==
kCompactionStopStyleSimilarSize) {
// Similar-size stopping rule: also check the last picked file isn't
// far larger than the next candidate file.
@@ -536,7 +540,7 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
// size ratio of compression.
bool enable_compression = true;
int ratio_to_compress =
ioptions_.compaction_options_universal.compression_size_percent;
mutable_cf_options.compaction_options_universal.compression_size_percent;
if (ratio_to_compress >= 0) {
uint64_t total_size = 0;
for (auto& sorted_run : sorted_runs) {
@@ -557,7 +561,8 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
for (unsigned int i = 0; i < first_index_after; i++) {
estimated_total_size += sorted_runs[i].size;
}
uint32_t path_id = GetPathId(ioptions_, estimated_total_size);
uint32_t path_id =
GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
int start_level = sorted_runs[start_index].level;
int output_level;
if (first_index_after == sorted_runs.size()) {
@@ -598,9 +603,9 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
CompactionReason compaction_reason;
if (max_number_of_files_to_compact == UINT_MAX) {
compaction_reason = CompactionReason::kUniversalSortedRunNum;
} else {
compaction_reason = CompactionReason::kUniversalSizeRatio;
} else {
compaction_reason = CompactionReason::kUniversalSortedRunNum;
}
return new Compaction(
vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
@@ -621,9 +626,9 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, double score,
const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
// percentage flexibilty while reducing size amplification
uint64_t ratio =
ioptions_.compaction_options_universal.max_size_amplification_percent;
// percentage flexibility while reducing size amplification
uint64_t ratio = mutable_cf_options.compaction_options_universal
.max_size_amplification_percent;
unsigned int candidate_count = 0;
uint64_t candidate_size = 0;
@@ -701,7 +706,8 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
estimated_total_size += sorted_runs[loop].size;
}
uint32_t path_id = GetPathId(ioptions_, estimated_total_size);
uint32_t path_id =
GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
int start_level = sorted_runs[start_index].level;
std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
+6 -6
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -82,11 +80,13 @@ class UniversalCompactionPicker : public CompactionPicker {
bool IsInputFilesNonOverlapping(Compaction* c);
static std::vector<SortedRun> CalculateSortedRuns(
const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions);
const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
const MutableCFOptions& mutable_cf_options);
// Pick a path ID to place a newly generated file, with its estimated file
// size.
static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
const MutableCFOptions& mutable_cf_options,
uint64_t file_size);
};
} // namespace rocksdb
+3 -7
View File
@@ -1,11 +1,7 @@
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include <map>
#include <string>
+46 -12
View File
@@ -1,30 +1,64 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2012 Facebook.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#ifndef ROCKSDB_LITE
#include "rocksdb/convenience.h"
#include "db/db_impl.h"
#include "util/cast_util.h"
namespace rocksdb {
void CancelAllBackgroundWork(DB* db, bool wait) {
(dynamic_cast<DBImpl*>(db->GetRootDB()))->CancelAllBackgroundWork(wait);
(static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
->CancelAllBackgroundWork(wait);
}
Status DeleteFilesInRange(DB* db, ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end) {
return (dynamic_cast<DBImpl*>(db->GetRootDB()))
->DeleteFilesInRange(column_family, begin, end);
const Slice* begin, const Slice* end,
bool include_end) {
RangePtr range(begin, end);
return DeleteFilesInRanges(db, column_family, &range, 1, include_end);
}
Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
const RangePtr* ranges, size_t n,
bool include_end) {
return (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
->DeleteFilesInRanges(column_family, ranges, n, include_end);
}
Status VerifySstFileChecksum(const Options& options,
const EnvOptions& env_options,
const std::string& file_path) {
unique_ptr<RandomAccessFile> file;
uint64_t file_size;
InternalKeyComparator internal_comparator(options.comparator);
ImmutableCFOptions ioptions(options);
Status s = ioptions.env->NewRandomAccessFile(file_path, &file, env_options);
if (s.ok()) {
s = ioptions.env->GetFileSize(file_path, &file_size);
} else {
return s;
}
unique_ptr<TableReader> table_reader;
std::unique_ptr<RandomAccessFileReader> file_reader(
new RandomAccessFileReader(std::move(file), file_path));
s = ioptions.table_factory->NewTableReader(
TableReaderOptions(ioptions, env_options, internal_comparator,
false /* skip_filters */, -1 /* level */),
std::move(file_reader), file_size, &table_reader,
false /* prefetch_index_and_filter_in_cache */);
if (!s.ok()) {
return s;
}
s = table_reader->VerifyChecksum();
return s;
}
} // namespace rocksdb
+16 -7
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
@@ -22,6 +20,7 @@
#include "db/log_format.h"
#include "db/version_set.h"
#include "rocksdb/cache.h"
#include "rocksdb/convenience.h"
#include "rocksdb/env.h"
#include "rocksdb/table.h"
#include "rocksdb/write_batch.h"
@@ -154,7 +153,7 @@ class CorruptionTest : public testing::Test {
struct stat sbuf;
if (stat(fname.c_str(), &sbuf) != 0) {
const char* msg = strerror(errno);
ASSERT_TRUE(false) << fname << ": " << msg;
FAIL() << fname << ": " << msg;
}
if (offset < 0) {
@@ -181,6 +180,9 @@ class CorruptionTest : public testing::Test {
}
s = WriteStringToFile(Env::Default(), contents, fname);
ASSERT_TRUE(s.ok()) << s.ToString();
Options options;
EnvOptions env_options;
ASSERT_NOK(VerifySstFileChecksum(options, env_options, fname));
}
void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
@@ -215,7 +217,7 @@ class CorruptionTest : public testing::Test {
return;
}
}
ASSERT_TRUE(false) << "no file found at level";
FAIL() << "no file found at level";
}
@@ -314,6 +316,7 @@ TEST_F(CorruptionTest, TableFile) {
Corrupt(kTableFile, 100, 1);
Check(99, 99);
ASSERT_NOK(dbi->VerifyChecksum());
}
TEST_F(CorruptionTest, TableFileIndexData) {
@@ -329,9 +332,11 @@ TEST_F(CorruptionTest, TableFileIndexData) {
// corrupt an index block of an entire file
Corrupt(kTableFile, -2000, 500);
Reopen();
dbi = reinterpret_cast<DBImpl*>(db_);
// one full file should be readable, since only one was corrupted
// the other file should be fully non-readable, since index was corrupted
Check(5000, 5000);
ASSERT_NOK(dbi->VerifyChecksum());
}
TEST_F(CorruptionTest, MissingDescriptor) {
@@ -391,10 +396,12 @@ TEST_F(CorruptionTest, CompactionInputError) {
Corrupt(kTableFile, 100, 1);
Check(9, 9);
ASSERT_NOK(dbi->VerifyChecksum());
// Force compactions by writing lots of values
Build(10000);
Check(10000, 10000);
ASSERT_NOK(dbi->VerifyChecksum());
}
TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
@@ -426,6 +433,7 @@ TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
CorruptTableFileAtLevel(0, 100, 1);
Check(9, 9);
ASSERT_NOK(dbi->VerifyChecksum());
// Write must eventually fail because of corrupted table
Status s;
@@ -447,6 +455,7 @@ TEST_F(CorruptionTest, UnrelatedKeys) {
DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
dbi->TEST_FlushMemTable();
Corrupt(kTableFile, 100, 1);
ASSERT_NOK(dbi->VerifyChecksum());
std::string tmp1, tmp2;
ASSERT_OK(db_->Put(WriteOptions(), Key(1000, &tmp1), Value(1000, &tmp2)));
+7 -9
View File
@@ -1,9 +1,7 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#ifndef ROCKSDB_LITE
@@ -243,7 +241,7 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
// Write 28 values, each 10016 B ~ 10KB
for (int idx = 0; idx < 28; ++idx) {
ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + char(idx))));
}
dbfull()->TEST_WaitForFlushMemTable();
ASSERT_EQ("1", FilesPerLevel());
@@ -252,7 +250,7 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
true /* disallow trivial move */);
ASSERT_EQ("0,2", FilesPerLevel());
for (int idx = 0; idx < 28; ++idx) {
ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
ASSERT_EQ(std::string(10000, 'a' + char(idx)), Get(Key(idx)));
}
}
@@ -273,14 +271,14 @@ TEST_F(CuckooTableDBTest, SameKeyInsertedInTwoDifferentFilesAndCompacted) {
// Generate one more file in level-0, and should trigger level-0 compaction
for (int idx = 0; idx < 11; ++idx) {
ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + char(idx))));
}
dbfull()->TEST_WaitForFlushMemTable();
dbfull()->TEST_CompactRange(0, nullptr, nullptr);
ASSERT_EQ("0,1", FilesPerLevel());
for (int idx = 0; idx < 11; ++idx) {
ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
ASSERT_EQ(std::string(10000, 'a' + char(idx)), Get(Key(idx)));
}
}

Some files were not shown because too many files have changed in this diff Show More