add <sys/sysmacros.h> to avoid warning with glibc 2.25

Summary:
https://github.com/facebook/rocksdb/issues/2152
Closes https://github.com/facebook/rocksdb/pull/2208

Differential Revision: D4945577

Pulled By: lightmark

fbshipit-source-id: 4e679150f2c9443d3be0b6008b26b65fabbda75a

.arcconfig

@@ -0,0 +1,17 @@
+{
+  "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
+}

.gitignore

@@ -1,3 +1,4 @@
+TARGETS
 make_config.mk
 
 *.a
@@ -31,7 +32,6 @@ build/
 ldb
 manifest_dump
 sst_dump
-blob_dump
 column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
@@ -39,9 +39,9 @@ coverage/COVERAGE_REPORT
 .gdbhistory
 .gdb_history
 package/
+.phutil_module_cache
 unity.a
 tags
-etags
 rocksdb_dump
 rocksdb_undump
 db_test2
@@ -60,7 +60,7 @@ rocksdb.h
 unity.cc
 java/crossbuild/.vagrant
 .vagrant/
-java/**/*.asc
+java/**.asc
 java/javadoc
 
 scan_build_report/
@@ -71,4 +71,3 @@ db_logs/
 tp2/
 fbcode/
 fbcode
-buckifier/*.pyc

.travis.yml

@@ -7,7 +7,6 @@ os:
 compiler:
   - clang
   - gcc
-osx_image: xcode8.3
 jdk:
   - oraclejdk7
 cache:
@@ -16,63 +15,44 @@ cache:
 
 addons:
    apt:
-      packages: ['zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev', 'mingw-w64']
+      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']
 env:
-  - 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
+  - TEST_GROUP=platform_dependent1
+  - TEST_GROUP=platform_dependent2
+  - TEST_GROUP=platform_dependent3
+  - TEST_GROUP=1
+  - TEST_GROUP=2
   # Run java tests
-  - JOB_NAME=java_test # 4-11 minutes
+  - JOB_NAME=java_test
   # Build ROCKSDB_LITE
-  - JOB_NAME=lite_build # 3-4 minutes
-  # Build examples
-  - JOB_NAME=examples # 5-7 minutes
-  - JOB_NAME=cmake # 3-5 minutes
-  - JOB_NAME=cmake-mingw # 3 minutes
+  - JOB_NAME=lite_build
 
 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
-    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:
-  # Increase the maximum number of open file descriptors, since some tests use
-  # more FDs than the default limit.
-  - ulimit -n 8192
+  - 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
 
 script:
   - ${CXX} --version
-  - if [ `command -v ccache` ]; then ccache -C; fi
-  - if [ "${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
+  - 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 rocksdbjava jtest; fi
+  - if [[ "${JOB_NAME}" == 'lite_build' ]]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib; fi
 notifications:
     email:
       - leveldb@fb.com

AUTHORS

@@ -9,4 +9,3 @@ 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)

CODE_OF_CONDUCT.md

@@ -1,3 +0,0 @@
-# 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.

CONTRIBUTING.md

@@ -1,8 +1,5 @@
 # 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

DEFAULT_OPTIONS_HISTORY.md

@@ -1,8 +1,5 @@
 # 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)

HISTORY.md

@@ -1,137 +1,6 @@
 # Rocksdb Change Log
-## Unreleased
-### 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.
-### Bug Fixes
-* Fix `DisableFileDeletions()` followed by `GetSortedWalFiles()` to not return obsolete WAL files that `PurgeObsoleteFiles()` is going to delete.
-* 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
-* FIFO compaction to support Intra L0 compaction too with CompactionOptionsFIFO.allow_compaction=true.
-* DB::ResetStats() to reset internal stats.
-* Statistics::Reset() to reset user stats.
-* ldb add option --try_load_options, which will open DB with its own option file.
-* Introduce WriteBatch::PopSavePoint to pop the most recent save point explicitly.
-* Support dynamically change `max_open_files` option via SetDBOptions()
-* Added DB::CreateColumnFamilie() and DB::DropColumnFamilies() to bulk create/drop column families.
-* 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.
-
-### 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
-* random_access_max_buffer_size no longer has any effect
-* Removed Env::EnableReadAhead(), Env::ShouldForwardRawRequest()
-* Support dynamically change `stats_dump_period_sec` option via SetDBOptions().
-* Added ReadOptions::max_skippable_internal_keys to set a threshold to fail a request as incomplete when too many keys are being skipped when using iterators.
-* DB::Get in place of std::string accepts PinnableSlice, which avoids the extra memcpy of value to std::string in most of cases.
-    * PinnableSlice releases the pinned resources that contain the value when it is destructed or when ::Reset() is called on it.
-    * The old API that accepts std::string, although discouraged, is still supported.
-* Replace Options::use_direct_writes with Options::use_direct_io_for_flush_and_compaction. Read Direct IO wiki for details.
-* Added CompactionEventListener and EventListener::OnFlushBegin interfaces.
-
-### New Features
-* Memtable flush can be avoided during checkpoint creation if total log file size is smaller than a threshold specified by the user.
-* Introduce level-based L0->L0 compactions to reduce file count, so write delays are incurred less often.
-* (Experimental) Partitioning filters which creates an index on the partitions. The feature can be enabled by setting partition_filters when using kFullFilter. Currently the feature also requires two-level indexing to be enabled. Number of partitions is the same as the number of partitions for indexes, which is controlled by metadata_block_size.
+## 5.3.7
+* Change license to Apache + GPLv2
 
 ## 5.3.0 (03/08/2017)
 ### Public API Change
@@ -140,6 +9,9 @@
 * Remove option min_partial_merge_operands. Partial merge operands will always be merged in flush or compaction if there are more than one.
 * Remove option verify_checksums_in_compaction. Compaction will always verify checksum.
 
+### New Features
+* Memtable flush can be avoided during checkpoint creation if total log file size is smaller than a threshold specified by the user.
+
 ### Bug Fixes
 * Fix the bug that iterator may skip keys
 
@@ -358,7 +230,7 @@
 * Added a new way to report QPS from db_bench (check out --report_file and --report_interval_seconds)
 * Added a cache for individual rows. See DBOptions::row_cache for more info.
 * Several new features on EventListener (see include/rocksdb/listener.h):
- - OnCompationCompleted() now returns per-compaction job statistics, defined in include/rocksdb/compaction_job_stats.h.
+ - OnCompationCompleted() now returns per-compaciton job statistics, defined in include/rocksdb/compaction_job_stats.h.
  - Added OnTableFileCreated() and OnTableFileDeleted().
 * Add compaction_options_universal.enable_trivial_move to true, to allow trivial move while performing universal compaction. Trivial move will happen only when all the input files are non overlapping.
 

INSTALL.md

@@ -1,6 +1,6 @@
 ## Compilation
 
-**Important**: If you plan to run RocksDB in production, don't compile using default
+**Important**: If you plan to run RocksDB in production, don't compile using default 
 `make` or `make all`. That will compile RocksDB in debug mode, which is much slower
 than release mode.
 
@@ -21,18 +21,14 @@ depend on gflags. You will need to have gflags installed to run `make all`. This
 use binaries compiled by `make all` in production.
 
 * By default the binary we produce is optimized for the platform you're compiling on
-(`-march=native` or the equivalent). SSE4.2 will thus be enabled automatically if your
-CPU supports it. To print a warning if your CPU does not support SSE4.2, build with
-`USE_SSE=1 make static_lib` or, if using CMake, `cmake -DFORCE_SSE42=ON`. If you want
-to build a portable binary, add `PORTABLE=1` before your make commands, like this:
-`PORTABLE=1 make static_lib`.
+(-march=native or the equivalent). If you want to build a portable binary, add 'PORTABLE=1' before
+your make commands, like this: `PORTABLE=1 make static_lib`
 
 ## Dependencies
 
 * 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
@@ -54,7 +50,6 @@ 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**
@@ -63,38 +58,31 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
     * Install gflags:
 
               git clone https://github.com/gflags/gflags.git
-              cd gflags
               git checkout v2.0
+              cd gflags
               ./configure && make && sudo make install
 
-      **Notice**: Once installed, please add the include path for gflags to your `CPATH` environment variable and the
-      lib path to `LIBRARY_PATH`. If installed with default settings, the include path will be `/usr/local/include`
-      and the lib path will be `/usr/local/lib`.
-
     * Install snappy:
 
-              sudo yum install snappy snappy-devel
+              wget https://github.com/google/snappy/releases/download/1.1.4/snappy-1.1.4.tar.gz
+              tar -xzvf snappy-1.1.4.tar.gz
+              cd snappy-1.1.4
+              ./configure && make && sudo make install
 
     * Install zlib:
 
-              sudo yum install zlib zlib-devel
+              sudo yum install zlib
+              sudo yum install zlib-devel
 
     * Install bzip2:
 
-              sudo yum install bzip2 bzip2-devel
-
-    * Install lz4:
-
-              sudo yum install lz4-devel
-
-    * Install ASAN (optional for debugging):
-
-              sudo yum install libasan
+              sudo yum install bzip2
+              sudo yum install bzip2-devel
 
     * Install zstandard:
 
              wget https://github.com/facebook/zstd/archive/v1.1.3.tar.gz
-             mv v1.1.3.tar.gz zstd-1.1.3.tar.gz
+             mv v1.1.3.tar.gz zstandard-1.1.3.tar.gz
              tar zxvf zstd-1.1.3.tar.gz
              cd zstd-1.1.3
              make && sudo make install
@@ -107,73 +95,9 @@ 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
-    * Use these environment variables:
-  
-             export PORTABLE=1
-             export CC=gcc
-             export AR="ar -X64"
-             export EXTRA_ARFLAGS=-X64
-             export EXTRA_CFLAGS=-maix64
-             export EXTRA_CXXFLAGS=-maix64
-             export PLATFORM_LDFLAGS="-static-libstdc++ -static-libgcc"
-             export LIBPATH=/opt/freeware/lib
-             export JAVA_HOME=/usr/java8_64
-             export PATH=/opt/freeware/bin:$PATH
-  
-* **Solaris Sparc**
-    * Install GCC 4.8.2 and higher.
-    * Use these environment variables:
-
-             export CC=gcc
-             export EXTRA_CFLAGS=-m64
-             export EXTRA_CXXFLAGS=-m64
-             export EXTRA_LDFLAGS=-m64
-             export PORTABLE=1
-             export PLATFORM_LDFLAGS="-static-libstdc++ -static-libgcc"
-

LANGUAGE-BINDINGS.md

@@ -9,9 +9,5 @@ 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
-    * https://github.com/bh1xuw/rust-rocks
+* Rust - https://github.com/spacejam/rust-rocksdb
 * D programming language - https://github.com/b1naryth1ef/rocksdb
-* Erlang - https://gitlab.com/barrel-db/erlang-rocksdb
-* Elixir - https://github.com/urbint/rox

Makefile

@@ -14,8 +14,7 @@ CFLAGS += ${EXTRA_CFLAGS}
 CXXFLAGS += ${EXTRA_CXXFLAGS}
 LDFLAGS += $(EXTRA_LDFLAGS)
 MACHINE ?= $(shell uname -m)
-ARFLAGS = ${EXTRA_ARFLAGS} rs
-STRIPFLAGS = -S -x
+ARFLAGS = rs
 
 # Transform parallel LOG output into something more readable.
 perl_command = perl -n \
@@ -96,34 +95,12 @@ OPT += -momit-leaf-frame-pointer
 endif
 endif
 
-ifeq (,$(shell $(CXX) -fsyntax-only -maltivec -xc /dev/null 2>&1))
-CXXFLAGS += -DHAS_ALTIVEC
-CFLAGS += -DHAS_ALTIVEC
-HAS_ALTIVEC=1
-endif
-
-ifeq (,$(shell $(CXX) -fsyntax-only -mcpu=power8 -xc /dev/null 2>&1))
-CXXFLAGS += -DHAVE_POWER8
-CFLAGS +=  -DHAVE_POWER8
-HAVE_POWER8=1
-endif
-
-# if we're compiling for release, compile without debug code (-DNDEBUG)
+# if we're compiling for release, compile without debug code (-DNDEBUG) and
+# don't treat warnings as errors
 ifeq ($(DEBUG_LEVEL),0)
 OPT += -DNDEBUG
-
-ifneq ($(USE_RTTI), 1)
-	CXXFLAGS += -fno-rtti
+DISABLE_WARNING_AS_ERROR=1
 else
-	CXXFLAGS += -DROCKSDB_USE_RTTI
-endif
-else
-ifneq ($(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
 
@@ -177,9 +154,7 @@ missing_make_config_paths := $(shell				\
 $(foreach path, $(missing_make_config_paths), \
 	$(warning Warning: $(path) dont exist))
 
-ifeq ($(PLATFORM), OS_AIX)
-# no debug info
-else ifneq ($(PLATFORM), IOS)
+ifneq ($(PLATFORM), IOS)
 CFLAGS += -g
 CXXFLAGS += -g
 else
@@ -187,11 +162,6 @@ else
 OPT += -DNDEBUG
 endif
 
-ifeq ($(PLATFORM), OS_AIX)
-ARFLAGS = -X64 rs
-STRIPFLAGS = -X64 -x
-endif
-
 ifeq ($(PLATFORM), OS_SOLARIS)
 	PLATFORM_CXXFLAGS += -D _GLIBCXX_USE_C99
 endif
@@ -214,9 +184,9 @@ endif
 # TSAN doesn't work well with jemalloc. If we're compiling with TSAN, we should use regular malloc.
 ifdef COMPILE_WITH_TSAN
 	DISABLE_JEMALLOC=1
-	EXEC_LDFLAGS += -fsanitize=thread
-	PLATFORM_CCFLAGS += -fsanitize=thread -fPIC
-	PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC
+	EXEC_LDFLAGS += -fsanitize=thread -pie
+	PLATFORM_CCFLAGS += -fsanitize=thread -fPIC -DROCKSDB_TSAN_RUN
+	PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC -DROCKSDB_TSAN_RUN
         # Turn off -pg when enabling TSAN testing, because that induces
         # a link failure.  TODO: find the root cause
 	PROFILING_FLAGS =
@@ -224,49 +194,28 @@ ifdef COMPILE_WITH_TSAN
 	LUA_PATH =
 endif
 
-# AIX doesn't work with -pg
-ifeq ($(PLATFORM), OS_AIX)
-	PROFILING_FLAGS =
-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 -DROCKSDB_UBSAN_RUN
-	PLATFORM_CXXFLAGS += -fsanitize=undefined -DROCKSDB_UBSAN_RUN
-endif
-
-ifdef ROCKSDB_VALGRIND_RUN
-	PLATFORM_CCFLAGS += -DROCKSDB_VALGRIND_RUN
-	PLATFORM_CXXFLAGS += -DROCKSDB_VALGRIND_RUN
+	PLATFORM_CCFLAGS += -fsanitize=undefined
+	PLATFORM_CXXFLAGS += -fsanitize=undefined
 endif
 
 ifndef DISABLE_JEMALLOC
 	ifdef 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
+		PLATFORM_CXXFLAGS += "-DROCKSDB_JEMALLOC"
+		PLATFORM_CCFLAGS +=  "-DROCKSDB_JEMALLOC"
 	endif
 	EXEC_LDFLAGS := $(JEMALLOC_LIB) $(EXEC_LDFLAGS)
 	PLATFORM_CXXFLAGS += $(JEMALLOC_INCLUDE)
 	PLATFORM_CCFLAGS += $(JEMALLOC_INCLUDE)
 endif
 
-export GTEST_THROW_ON_FAILURE=1
-export GTEST_HAS_EXCEPTIONS=1
+export GTEST_THROW_ON_FAILURE=1 GTEST_HAS_EXCEPTIONS=1
 GTEST_DIR = ./third-party/gtest-1.7.0/fused-src
-# AIX: pre-defined system headers are surrounded by an extern "C" block
-ifeq ($(PLATFORM), OS_AIX)
-	PLATFORM_CCFLAGS += -I$(GTEST_DIR)
-	PLATFORM_CXXFLAGS += -I$(GTEST_DIR)
-else
-	PLATFORM_CCFLAGS += -isystem $(GTEST_DIR)
-	PLATFORM_CXXFLAGS += -isystem $(GTEST_DIR)
-endif
+PLATFORM_CCFLAGS += -isystem $(GTEST_DIR)
+PLATFORM_CXXFLAGS += -isystem $(GTEST_DIR)
 
 # This (the first rule) must depend on "all".
 default: all
@@ -274,11 +223,6 @@ default: all
 WARNING_FLAGS = -W -Wextra -Wall -Wsign-compare -Wshadow \
   -Wno-unused-parameter
 
-ifndef DISABLE_WARNING_AS_ERROR
-	WARNING_FLAGS += -Werror
-endif
-
-
 ifdef LUA_PATH
 
 ifndef LUA_INCLUDE
@@ -305,18 +249,12 @@ 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
 
 LDFLAGS += $(PLATFORM_LDFLAGS)
 
-# If NO_UPDATE_BUILD_VERSION is set we don't update util/build_version.cc, but
-# the file needs to already exist or else the build will fail
-ifndef NO_UPDATE_BUILD_VERSION
 date := $(shell date +%F)
 ifdef FORCE_GIT_SHA
 	git_sha := $(FORCE_GIT_SHA)
@@ -330,6 +268,7 @@ gen_build_version = sed -e s/@@GIT_SHA@@/$(git_sha)/ -e s/@@GIT_DATE_TIME@@/$(da
 # as a regular source file as part of the compilation process.
 # One can run "strings executable_filename | grep _build_" to find
 # the version of the source that we used to build the executable file.
+CLEAN_FILES += util/build_version.cc:
 FORCE:
 util/build_version.cc: FORCE
 	$(AM_V_GEN)rm -f $@-t
@@ -337,17 +276,8 @@ util/build_version.cc: FORCE
 	$(AM_V_at)if test -f $@; then					\
 	  cmp -s $@-t $@ && rm -f $@-t || mv -f $@-t $@;		\
 	else mv -f $@-t $@; fi
-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)
 
@@ -365,7 +295,6 @@ 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 \
@@ -378,7 +307,6 @@ TESTS = \
 	inlineskiplist_test \
 	env_basic_test \
 	env_test \
-	hash_test \
 	thread_local_test \
 	rate_limiter_test \
 	perf_context_test \
@@ -386,7 +314,6 @@ 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 \
@@ -406,10 +333,7 @@ TESTS = \
 	db_io_failure_test \
 	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 \
@@ -425,7 +349,6 @@ TESTS = \
 	file_reader_writer_test \
 	block_based_filter_block_test \
 	full_filter_block_test \
-	partitioned_filter_block_test \
 	hash_table_test \
 	histogram_test \
 	log_test \
@@ -445,15 +368,11 @@ 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 \
+	blob_db_test \
 	document_db_test \
 	json_document_test \
 	sim_cache_test \
@@ -474,7 +393,6 @@ TESTS = \
 	options_settable_test \
 	options_util_test \
 	event_logger_test \
-	timer_queue_test \
 	cuckoo_table_builder_test \
 	cuckoo_table_reader_test \
 	cuckoo_table_db_test \
@@ -502,14 +420,11 @@ TESTS = \
 	lru_cache_test \
 	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 \
@@ -520,8 +435,7 @@ PARALLEL_TEST = \
 	manual_compaction_test \
 	persistent_cache_test \
 	table_test \
-	transaction_test \
-	write_prepared_transaction_test \
+	transaction_test
 
 SUBSET := $(TESTS)
 ifdef ROCKSDBTESTS_START
@@ -540,8 +454,7 @@ TOOLS = \
 	ldb \
 	db_repl_stress \
 	rocksdb_dump \
-	rocksdb_undump \
-	blob_dump \
+	rocksdb_undump
 
 TEST_LIBS = \
 	librocksdb_env_basic_test.a
@@ -601,36 +514,10 @@ $(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))
-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 $@
-
-ifeq ($(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 $@
+$(SHARED4):
+	$(CXX) $(PLATFORM_SHARED_LDFLAGS)$(SHARED3) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(LIB_SOURCES) $(TOOL_LIB_SOURCES) \
+		$(LDFLAGS) -o $@
 
 endif  # PLATFORM_SHARED_EXT
 
@@ -642,8 +529,6 @@ 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: $(SHARED)
@@ -673,8 +558,7 @@ ifneq (,$(filter check parallel_check,$(MAKECMDGOALS)),)
 # and create a randomly-named rocksdb.XXXX directory therein.
 # We'll use that directory in the "make check" rules.
 ifeq ($(TMPD),)
-TMPDIR := $(shell echo $${TMPDIR:-/tmp})
-TMPD := $(shell f=/dev/shm; test -k $$f || f=$(TMPDIR);     \
+TMPD := $(shell f=/dev/shm; test -k $$f || f=/tmp;			\
   perl -le 'use File::Temp "tempdir";'					\
     -e 'print tempdir("'$$f'/rocksdb.XXXX", CLEANUP => 0)')
 endif
@@ -751,7 +635,7 @@ gen_parallel_tests:
 # 107.816 PASS t/DBTest.EncodeDecompressedBlockSizeTest
 #
 slow_test_regexp = \
-	^.*SnapshotConcurrentAccessTest.*$$|^t/run-table_test-HarnessTest.Randomized$$|^t/run-db_test-.*(?:FileCreationRandomFailure|EncodeDecompressedBlockSizeTest)$$|^.*RecoverFromCorruptedWALWithoutFlush$$
+	^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							\
@@ -829,12 +713,10 @@ check: all
 	      echo "===== Running $$t"; ./$$t || exit 1; done;          \
 	fi
 	rm -rf $(TMPD)
-ifneq ($(PLATFORM), OS_AIX)
 ifeq ($(filter -DROCKSDB_LITE,$(OPT)),)
 	python tools/ldb_test.py
 	sh tools/rocksdb_dump_test.sh
 endif
-endif
 
 # TODO add ldb_tests
 check_some: $(SUBSET)
@@ -847,8 +729,8 @@ ldb_tests: ldb
 crash_test: whitebox_crash_test blackbox_crash_test
 
 blackbox_crash_test: db_stress
-	python -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
-	python -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --simple blackbox
+	python -u tools/db_crashtest.py blackbox
 
 ifeq ($(CRASH_TEST_KILL_ODD),)
   CRASH_TEST_KILL_ODD=888887
@@ -856,9 +738,9 @@ endif
 
 whitebox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+      $(CRASH_TEST_KILL_ODD)
 	python -u tools/db_crashtest.py whitebox  --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+      $(CRASH_TEST_KILL_ODD)
 
 asan_check:
 	$(MAKE) clean
@@ -881,7 +763,7 @@ ubsan_crash_test:
 	$(MAKE) clean
 
 valgrind_test:
-	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
+	DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
 valgrind_check: $(TESTS)
 	$(MAKE) DRIVER="$(VALGRIND_VER) $(VALGRIND_OPTS)" gen_parallel_tests
@@ -980,13 +862,12 @@ 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* zstd*
+	rm -rf bzip2* snappy* zlib* lz4*
 	cd java; $(MAKE) clean
 
 tags:
 	ctags * -R
 	cscope -b `find . -name '*.cc'` `find . -name '*.h'` `find . -name '*.c'`
-	ctags -e -R -o etags *
 
 format:
 	build_tools/format-diff.sh
@@ -1005,20 +886,20 @@ $(TOOLS_LIBRARY): $(BENCH_LIB_SOURCES:.cc=.o) $(TOOL_LIB_SOURCES:.cc=.o) $(LIB_S
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
 
-librocksdb_env_basic_test.a: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
+librocksdb_env_basic_test.a: util/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
 
 db_bench: tools/db_bench.o $(BENCHTOOLOBJECTS)
 	$(AM_LINK)
 
-cache_bench: cache/cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
+cache_bench: util/cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
 persistent_cache_bench: utilities/persistent_cache/persistent_cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
-memtablerep_bench: memtable/memtablerep_bench.o $(LIBOBJECTS) $(TESTUTIL)
+memtablerep_bench: db/memtablerep_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
 db_stress: tools/db_stress.o $(LIBOBJECTS) $(TESTUTIL)
@@ -1054,40 +935,25 @@ dynamic_bloom_test: util/dynamic_bloom_test.o $(LIBOBJECTS) $(TESTHARNESS)
 c_test: db/c_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-cache_test: cache/cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
+cache_test: util/cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 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)
 
 hash_table_test: utilities/persistent_cache/hash_table_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-histogram_test: monitoring/histogram_test.o $(LIBOBJECTS) $(TESTHARNESS)
+histogram_test: util/histogram_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 thread_local_test: util/thread_local_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1105,18 +971,12 @@ 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)
 
@@ -1159,12 +1019,6 @@ db_range_del_test: db/db_range_del_test.o db/db_test_util.o $(LIBOBJECTS) $(TEST
 db_sst_test: db/db_sst_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-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)
 
@@ -1213,6 +1067,9 @@ prefix_test: db/prefix_test.o $(LIBOBJECTS) $(TESTHARNESS)
 backupable_db_test: utilities/backupable/backupable_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+blob_db_test: utilities/blob_db/blob_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 checkpoint_test: utilities/checkpoint/checkpoint_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1231,9 +1088,6 @@ spatial_db_test: utilities/spatialdb/spatial_db_test.o $(LIBOBJECTS) $(TESTHARNE
 env_mirror_test: utilities/env_mirror_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-env_timed_test: utilities/env_timed_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 ifdef ROCKSDB_USE_LIBRADOS
 env_librados_test: utilities/env_librados_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_V_CCLD)$(CXX) $^ $(EXEC_LDFLAGS) -o $@ $(LDFLAGS) $(COVERAGEFLAGS)
@@ -1272,16 +1126,16 @@ wal_manager_test: db/wal_manager_test.o $(LIBOBJECTS) $(TESTHARNESS)
 dbformat_test: db/dbformat_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-env_basic_test: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
+env_basic_test: util/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-env_test: env/env_test.o $(LIBOBJECTS) $(TESTHARNESS)
+env_test: util/env_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-rate_limiter_test: util/rate_limiter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+rate_limiter_test: util/rate_limiter_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 delete_scheduler_test: util/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1299,9 +1153,6 @@ block_based_filter_block_test: table/block_based_filter_block_test.o $(LIBOBJECT
 full_filter_block_test: table/full_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-partitioned_filter_block_test: table/partitioned_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 log_test: db/log_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1314,13 +1165,10 @@ table_test: table/table_test.o $(LIBOBJECTS) $(TESTHARNESS)
 block_test: table/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-inlineskiplist_test: memtable/inlineskiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
+inlineskiplist_test: db/inlineskiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-skiplist_test: memtable/skiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-write_buffer_manager_test: memtable/write_buffer_manager_test.o $(LIBOBJECTS) $(TESTHARNESS)
+skiplist_test: db/skiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 version_edit_test: db/version_edit_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1395,10 +1243,10 @@ thread_list_test: util/thread_list_test.o $(LIBOBJECTS) $(TESTHARNESS)
 compact_files_test: db/compact_files_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-options_test: options/options_test.o $(LIBOBJECTS) $(TESTHARNESS)
+options_test: util/options_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-options_settable_test: options/options_settable_test.o $(LIBOBJECTS) $(TESTHARNESS)
+options_settable_test: util/options_settable_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 options_util_test: utilities/options/options_util_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1410,9 +1258,6 @@ db_bench_tool_test: tools/db_bench_tool_test.o $(BENCHTOOLOBJECTS) $(TESTHARNESS
 event_logger_test: util/event_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-timer_queue_test: util/timer_queue_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 sst_dump_test: tools/sst_dump_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1422,7 +1267,7 @@ column_aware_encoding_test: utilities/column_aware_encoding_test.o $(TESTHARNESS
 optimistic_transaction_test: utilities/transactions/optimistic_transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-mock_env_test : env/mock_env_test.o $(LIBOBJECTS) $(TESTHARNESS)
+mock_env_test : util/mock_env_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 manual_compaction_test: db/manual_compaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1431,7 +1276,7 @@ manual_compaction_test: db/manual_compaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 filelock_test: util/filelock_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-auto_roll_logger_test: util/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
+auto_roll_logger_test: db/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 memtable_list_test: db/memtable_list_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1446,15 +1291,9 @@ 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)
 
@@ -1467,16 +1306,16 @@ ldb_cmd_test: tools/ldb_cmd_test.o $(LIBOBJECTS) $(TESTHARNESS)
 ldb: tools/ldb.o $(LIBOBJECTS)
 	$(AM_LINK)
 
-iostats_context_test: monitoring/iostats_context_test.o $(LIBOBJECTS) $(TESTHARNESS)
+iostats_context_test: util/iostats_context_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_V_CCLD)$(CXX) $^ $(EXEC_LDFLAGS) -o $@ $(LDFLAGS)
 
 persistent_cache_test: utilities/persistent_cache/persistent_cache_test.o  db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-statistics_test: monitoring/statistics_test.o $(LIBOBJECTS) $(TESTHARNESS)
+statistics_test: util/statistics_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-lru_cache_test: cache/lru_cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
+lru_cache_test: util/lru_cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 lua_test: utilities/lua/rocks_lua_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1485,9 +1324,6 @@ 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)
-	$(AM_LINK)
-
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1535,32 +1371,23 @@ ifeq ($(PLATFORM), OS_SOLARIS)
 else
 	ARCH := $(shell getconf LONG_BIT)
 endif
-
-ifeq (,$(findstring ppc,$(MACHINE)))
-        ROCKSDBJNILIB = librocksdbjni-linux$(ARCH).so
-else
-        ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE).so
-endif
+ROCKSDBJNILIB = librocksdbjni-linux$(ARCH).so
 ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux$(ARCH).jar
 ROCKSDB_JAR_ALL = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH).jar
 ROCKSDB_JAVADOCS_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-javadoc.jar
 ROCKSDB_SOURCES_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-sources.jar
 SHA256_CMD = sha256sum
 
-ZLIB_VER ?= 1.2.11
-ZLIB_SHA256 ?= c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1
-ZLIB_DOWNLOAD_BASE ?= http://zlib.net
-BZIP2_VER ?= 1.0.6
-BZIP2_SHA256 ?= a2848f34fcd5d6cf47def00461fcb528a0484d8edef8208d6d2e2909dc61d9cd
-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 ?= 1.8.0
-LZ4_SHA256 ?= 2ca482ea7a9bb103603108b5a7510b7592b90158c151ff50a28f1ca8389fccf6
-LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
-ZSTD_VER ?= 1.3.3
-ZSTD_SHA256 ?= a77c47153ee7de02626c5b2a097005786b71688be61e9fb81806a011f90b297b
+ZLIB_VER = 1.2.11
+ZLIB_SHA256 = c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1
+BZIP2_VER = 1.0.6
+BZIP2_SHA256 = a2848f34fcd5d6cf47def00461fcb528a0484d8edef8208d6d2e2909dc61d9cd
+SNAPPY_VER = 1.1.4
+SNAPPY_SHA256 = 134bfe122fd25599bb807bb8130e7ba6d9bdb851e0b16efcb83ac4f5d0b70057
+LZ4_VER = 1.7.5
+LZ4_SHA256 = 0190cacd63022ccb86f44fa5041dc6c3804407ad61550ca21c382827319e7e7e
+ZSTD_VER ?= 1.2.0
+ZSTD_SHA256 ?= 4a7e4593a3638276ca7f2a09dc4f38e674d8317bbea51626393ca73fc047cbfb
 ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
 
 ifeq ($(PLATFORM), OS_MACOSX)
@@ -1574,7 +1401,7 @@ else
 endif
 endif
 ifeq ($(PLATFORM), OS_FREEBSD)
-	JAVA_INCLUDE = -I$(JAVA_HOME)/include -I$(JAVA_HOME)/include/freebsd
+	JAVA_INCLUDE += -I$(JAVA_HOME)/include/freebsd
 	ROCKSDBJNILIB = librocksdbjni-freebsd$(ARCH).so
 	ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-freebsd$(ARCH).jar
 endif
@@ -1584,53 +1411,47 @@ ifeq ($(PLATFORM), OS_SOLARIS)
 	JAVA_INCLUDE = -I$(JAVA_HOME)/include/ -I$(JAVA_HOME)/include/solaris
 	SHA256_CMD = digest -a sha256
 endif
-ifeq ($(PLATFORM), OS_AIX)
-	JAVA_INCLUDE = -I$(JAVA_HOME)/include/ -I$(JAVA_HOME)/include/aix
-	ROCKSDBJNILIB = librocksdbjni-aix.so
-	EXTRACT_SOURCES = gunzip < TAR_GZ | tar xvf -
-	SNAPPY_MAKE_TARGET = libsnappy.la
-endif
 
 libz.a:
 	-rm -rf zlib-$(ZLIB_VER)
-	curl -O -L ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
+	curl -O -L http://zlib.net/zlib-$(ZLIB_VER).tar.gz
 	ZLIB_SHA256_ACTUAL=`$(SHA256_CMD) zlib-$(ZLIB_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZLIB_SHA256)" != "$$ZLIB_SHA256_ACTUAL" ]; then \
 		echo zlib-$(ZLIB_VER).tar.gz checksum mismatch, expected=\"$(ZLIB_SHA256)\" actual=\"$$ZLIB_SHA256_ACTUAL\"; \
 		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' ./configure --static && make
 	cp zlib-$(ZLIB_VER)/libz.a .
 
 libbz2.a:
 	-rm -rf bzip2-$(BZIP2_VER)
-	curl -O -L ${BZIP2_DOWNLOAD_BASE}/$(BZIP2_VER)/bzip2-$(BZIP2_VER).tar.gz
+	curl -O -L http://www.bzip.org/$(BZIP2_VER)/bzip2-$(BZIP2_VER).tar.gz
 	BZIP2_SHA256_ACTUAL=`$(SHA256_CMD) bzip2-$(BZIP2_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(BZIP2_SHA256)" != "$$BZIP2_SHA256_ACTUAL" ]; then \
 		echo bzip2-$(BZIP2_VER).tar.gz checksum mismatch, expected=\"$(BZIP2_SHA256)\" actual=\"$$BZIP2_SHA256_ACTUAL\"; \
 		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'
 	cp bzip2-$(BZIP2_VER)/libbz2.a .
 
 libsnappy.a:
 	-rm -rf snappy-$(SNAPPY_VER)
-	curl -O -L ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER)/snappy-$(SNAPPY_VER).tar.gz
+	curl -O -L https://github.com/google/snappy/releases/download/$(SNAPPY_VER)/snappy-$(SNAPPY_VER).tar.gz
 	SNAPPY_SHA256_ACTUAL=`$(SHA256_CMD) snappy-$(SNAPPY_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(SNAPPY_SHA256)" != "$$SNAPPY_SHA256_ACTUAL" ]; then \
 		echo snappy-$(SNAPPY_VER).tar.gz checksum mismatch, expected=\"$(SNAPPY_SHA256)\" actual=\"$$SNAPPY_SHA256_ACTUAL\"; \
 		exit 1; \
 	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) && ./configure --with-pic --enable-static
+	cd snappy-$(SNAPPY_VER) && make
 	cp snappy-$(SNAPPY_VER)/.libs/libsnappy.a .
 
 liblz4.a:
 	-rm -rf lz4-$(LZ4_VER)
-	curl -O -L ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
+	curl -O -L https://github.com/lz4/lz4/archive/v$(LZ4_VER).tar.gz
 	mv v$(LZ4_VER).tar.gz lz4-$(LZ4_VER).tar.gz
 	LZ4_SHA256_ACTUAL=`$(SHA256_CMD) lz4-$(LZ4_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(LZ4_SHA256)" != "$$LZ4_SHA256_ACTUAL" ]; then \
@@ -1638,7 +1459,7 @@ 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' all
 	cp lz4-$(LZ4_VER)/lib/liblz4.a .
 
 libzstd.a:
@@ -1651,47 +1472,31 @@ libzstd.a:
 		exit 1; \
 	fi
 	tar xvzf zstd-$(ZSTD_VER).tar.gz
-	cd zstd-$(ZSTD_VER)/lib && DESTDIR=. PREFIX= $(MAKE) CFLAGS='-fPIC -O2 ${EXTRA_CFLAGS}' install
+	cd zstd-$(ZSTD_VER)/lib && make CFLAGS='-fPIC -O2 ${EXTRA_CFLAGS}' all
 	cp zstd-$(ZSTD_VER)/lib/libzstd.a .
 
 # A version of each $(LIBOBJECTS) compiled with -fPIC and a fixed set of static compression libraries
-java_static_libobjects = $(patsubst %,jls/%,$(LIB_CC_OBJECTS))
+java_static_libobjects = $(patsubst %,jls/%,$(LIBOBJECTS))
 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-$(ZSTD_VER)/lib/include
-
-ifeq ($(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 += $(java_static_ppc_libobjects)
-endif
+JAVA_STATIC_INCLUDES = -I./zlib-$(ZLIB_VER) -I./bzip2-$(BZIP2_VER) -I./snappy-$(SNAPPY_VER) -I./lz4-$(LZ4_VER)/lib -I./zstd-$(ZSTD_VER)/lib
 
 $(java_static_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_all_libobjects)
+rocksdbjavastatic: $(java_static_libobjects)
 	cd java;$(MAKE) javalib;
 	rm -f ./java/target/$(ROCKSDBJNILIB)
 	$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC \
 	  -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) \
-	  $(java_static_all_libobjects) $(COVERAGEFLAGS) \
+	  $(java_static_libobjects) $(COVERAGEFLAGS) \
 	  $(JAVA_COMPRESSIONS) $(JAVA_STATIC_LDFLAGS)
-	cd java/target;strip $(STRIPFLAGS) $(ROCKSDBJNILIB)
+	cd java/target;strip -S -x $(ROCKSDBJNILIB)
 	cd java;jar -cf target/$(ROCKSDB_JAR) HISTORY*.md
 	cd java/target;jar -uf $(ROCKSDB_JAR) $(ROCKSDBJNILIB)
 	cd java/target/classes;jar -uf ../$(ROCKSDB_JAR) org/rocksdb/*.class org/rocksdb/util/*.class
@@ -1707,26 +1512,18 @@ rocksdbjavastaticrelease: rocksdbjavastatic
 rocksdbjavastaticreleasedocker: rocksdbjavastatic
 	DOCKER_LINUX_X64_CONTAINER=`docker ps -aqf name=rocksdb_linux_x64-be`; \
 	if [ -z "$$DOCKER_LINUX_X64_CONTAINER" ]; then \
-		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos5_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
 	fi
 	docker start -a rocksdb_linux_x64-be
 	DOCKER_LINUX_X86_CONTAINER=`docker ps -aqf name=rocksdb_linux_x86-be`; \
 	if [ -z "$$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:centos6_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:centos5_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
@@ -1741,36 +1538,13 @@ 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 $(LIBOBJECTS) compiled with -fPIC
-ifeq ($(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))
+java_libobjects = $(patsubst %,jl/%,$(LIBOBJECTS))
 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_all_libobjects)
+rocksdbjava: $(java_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) $(COVERAGEFLAGS)
@@ -1825,54 +1599,30 @@ IOSVERSION=$(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=.cc.d)
+DEPFILES = $(all_sources:.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.
-%.cc.d: %.cc
+$(DEPFILES): %.d: %.cc
 	@$(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.

README.md

@@ -1,8 +1,7 @@
 ## RocksDB: A Persistent Key-Value Store for Flash and RAM Storage
 
-[![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)
+[![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)
 
 
 RocksDB is developed and maintained by Facebook Database Engineering Team.

USERS.md

@@ -5,14 +5,12 @@ 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.[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]
+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.[*]
 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++.[1]
-6. LogDevice -- a distributed data store for logs [2]
+5. Stylus -- a low-level stream processing framework writtenin C++.[*]
 
-[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/
+[*] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
 
 ## LinkedIn
 Two different use cases at Linkedin are using RocksDB as a storage engine:
@@ -78,13 +76,7 @@ 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 scalable task queue.
+[Uber](http://eng.uber.com/cherami/) uses RocksDB as a durable and 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.

appveyor.yml

@@ -3,13 +3,16 @@ image: Visual Studio 2015
 before_build:
 - md %APPVEYOR_BUILD_FOLDER%\build
 - cd %APPVEYOR_BUILD_FOLDER%\build
-- cmake -G "Visual Studio 14 Win64" -DOPTDBG=1 -DWITH_XPRESS=1 -DPORTABLE=1 ..
+- cmake -G "Visual Studio 14 2015 Win64" -DOPTDBG=1 -DXPRESS=1 ..
 - cd ..
 build:
   project: build\rocksdb.sln
   parallel: true
-  verbosity: normal
+  verbosity: minimal
 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
+- ps: build_tools\run_ci_db_test.ps1 -Run db_basic_test -Concurrency 8
+- ps: build_tools\run_ci_db_test.ps1 -Run db_test2 -Concurrency 8
+- ps: build_tools\run_ci_db_test.ps1 -Run db_test -Concurrency 8
+- ps: build_tools\run_ci_db_test.ps1 -Run env_test,env_basic_test -Concurrency 2
 

buckifier/buckify_rocksdb.py

@@ -1,172 +0,0 @@
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-from targets_builder import TARGETSBuilder
-from optparse import OptionParser
-import os
-import fnmatch
-import sys
-import tempfile
-
-from util import ColorString
-import util
-
-# tests to export as libraries for inclusion in other projects
-_EXPORTED_TEST_LIBS = ["env_basic_test"]
-
-# Parse src.mk files as a Dictionary of
-# VAR_NAME => list of files
-def parse_src_mk(repo_path):
-    src_mk = repo_path + "/src.mk"
-    src_files = {}
-    for line in open(src_mk):
-        line = line.strip()
-        if len(line) == 0 or line[0] == '#':
-            continue
-        if '=' in line:
-            current_src = line.split('=')[0].strip()
-            src_files[current_src] = []
-        elif '.cc' in line:
-            src_path = line.split('.cc')[0].strip() + '.cc'
-            src_files[current_src].append(src_path)
-    return src_files
-
-
-# get all .cc / .c files
-def get_cc_files(repo_path):
-    cc_files = []
-    for root, dirnames, filenames in os.walk(repo_path):
-        root = root[(len(repo_path) + 1):]
-        if "java" in root:
-            # Skip java
-            continue
-        for filename in fnmatch.filter(filenames, '*.cc'):
-            cc_files.append(os.path.join(root, filename))
-        for filename in fnmatch.filter(filenames, '*.c'):
-            cc_files.append(os.path.join(root, filename))
-    return cc_files
-
-
-# Get tests from Makefile
-def get_tests(repo_path):
-    Makefile = repo_path + "/Makefile"
-
-    # Dictionary TEST_NAME => IS_PARALLEL
-    tests = {}
-
-    found_tests = False
-    for line in open(Makefile):
-        line = line.strip()
-        if line.startswith("TESTS ="):
-            found_tests = True
-        elif found_tests:
-            if line.endswith("\\"):
-                # remove the trailing \
-                line = line[:-1]
-                line = line.strip()
-                tests[line] = False
-            else:
-                # we consumed all the tests
-                break
-
-    found_parallel_tests = False
-    for line in open(Makefile):
-        line = line.strip()
-        if line.startswith("PARALLEL_TEST ="):
-            found_parallel_tests = True
-        elif found_parallel_tests:
-            if line.endswith("\\"):
-                # remove the trailing \
-                line = line[:-1]
-                line = line.strip()
-                tests[line] = True
-            else:
-                # we consumed all the parallel tests
-                break
-    
-    return tests
-
-
-# Prepare TARGETS file for buck
-def generate_targets(repo_path):
-    print(ColorString.info("Generating TARGETS"))
-    # parsed src.mk file
-    src_mk = parse_src_mk(repo_path)
-    # get all .cc files
-    cc_files = get_cc_files(repo_path)
-    # get tests from Makefile
-    tests = get_tests(repo_path)
-
-    if src_mk is None or cc_files is None or tests is None:
-        return False
-
-    TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path)
-    # rocksdb_lib
-    TARGETS.add_library(
-        "rocksdb_lib",
-        src_mk["LIB_SOURCES"] +
-        src_mk["TOOL_LIB_SOURCES"])
-    # rocksdb_test_lib
-    TARGETS.add_library(
-        "rocksdb_test_lib",
-        src_mk.get("MOCK_LIB_SOURCES", []) +
-        src_mk.get("TEST_LIB_SOURCES", []) +
-        src_mk.get("EXP_LIB_SOURCES", []),
-        [":rocksdb_lib"])
-    # rocksdb_tools_lib
-    TARGETS.add_library(
-        "rocksdb_tools_lib",
-        src_mk.get("BENCH_LIB_SOURCES", []) +
-        ["util/testutil.cc"],
-        [":rocksdb_lib"])
-
-    # test for every test we found in the Makefile
-    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))
-            continue
-        elif len(match_src) > 1:
-            print(ColorString.warning("Found more than one .cc for %s" % test))
-            print(match_src)
-            continue
-
-        assert(len(match_src) == 1)
-        is_parallel = tests[test]
-        TARGETS.register_test(test, match_src[0], is_parallel)
-
-        if test in _EXPORTED_TEST_LIBS:
-            test_library = "%s_lib" % test
-            TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
-    TARGETS.flush_tests()
-
-    print(ColorString.info("Generated TARGETS Summary:"))
-    print(ColorString.info("- %d libs" % TARGETS.total_lib))
-    print(ColorString.info("- %d binarys" % TARGETS.total_bin))
-    print(ColorString.info("- %d tests" % TARGETS.total_test))
-    return True
-
-
-def get_rocksdb_path():
-    # rocksdb = {script_dir}/..
-    script_dir = os.path.dirname(sys.argv[0])
-    script_dir = os.path.abspath(script_dir)
-    rocksdb_path = os.path.abspath(
-        os.path.join(script_dir, "../"))
-
-    return rocksdb_path
-
-def exit_with_error(msg):
-    print(ColorString.error(msg))
-    sys.exit(1)
-
-
-def main():
-    # Generate TARGETS file for buck
-    ok = generate_targets(get_rocksdb_path())
-    if not ok:
-        exit_with_error("Failed to generate TARGETS files")
-
-if __name__ == "__main__":
-    main()

buckifier/rocks_test_runner.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-# Create a tmp directory for the test to use
-TEST_DIR=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
-TEST_TMPDIR="$TEST_DIR" $@ && rm -rf "$TEST_DIR"

buckifier/targets_builder.py

@@ -1,63 +0,0 @@
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-import targets_cfg
-
-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(sorted(lst))
-    res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 4))
-    return res
-
-
-class TARGETSBuilder:
-    def __init__(self, path):
-        self.path = path
-        self.targets_file = open(path, 'w')
-        self.targets_file.write(targets_cfg.rocksdb_target_header)
-        self.total_lib = 0
-        self.total_bin = 0
-        self.total_test = 0
-        self.tests_cfg = ""
-
-    def __del__(self):
-        self.targets_file.close()
-
-    def add_library(self, name, srcs, deps=None, headers=None):
-        if headers is None:
-            headers = "AutoHeaders.RECURSIVE_GLOB"
-        self.targets_file.write(targets_cfg.library_template % (
-            name,
-            pretty_list(srcs),
-            headers,
-            pretty_list(deps)))
-        self.total_lib = self.total_lib + 1
-
-    def add_binary(self, name, srcs, deps=None):
-        self.targets_file.write(targets_cfg.binary_template % (
-            name,
-            pretty_list(srcs),
-            pretty_list(deps)))
-        self.total_bin = self.total_bin + 1
-
-    def register_test(self, test_name, src, is_parallel):
-        exec_mode = "serial"
-        if is_parallel:
-            exec_mode = "parallel"
-        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 % self.tests_cfg)
-        self.tests_cfg = ""

buckifier/targets_cfg.py

@@ -1,142 +0,0 @@
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-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 = [
-    "-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", None, "numa"),
-    ("googletest", None, "gtest"),
-]
-
-rocksdb_preprocessor_flags = [
-    # 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",
-    srcs = [%s],
-    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],
-    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]
-
-# Generate a test rule for each entry in ROCKS_TESTS
-# 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,
-          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 = "make_rocksdbjavastatic",
-    command = ["internal_repo_rocksdb/make_rocksdbjavastatic.sh"],
-    type = "simple",
-)
-
-custom_unittest(
-    name = "make_rocksdb_lite_release",
-    command = ["internal_repo_rocksdb/make_rocksdb_lite_release.sh"],
-    type = "simple",
-)
-"""

buckifier/util.py

@@ -1,107 +0,0 @@
-"""
-This module keeps commonly used components.
-"""
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-import subprocess
-import os
-import time
-
-class ColorString:
-    """ Generate colorful strings on terminal """
-    HEADER = '\033[95m'
-    BLUE = '\033[94m'
-    GREEN = '\033[92m'
-    WARNING = '\033[93m'
-    FAIL = '\033[91m'
-    ENDC = '\033[0m'
-
-    @staticmethod
-    def _make_color_str(text, color):
-        return "".join([color, text.encode('utf-8'), ColorString.ENDC])
-
-    @staticmethod
-    def ok(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.GREEN)
-
-    @staticmethod
-    def info(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.BLUE)
-
-    @staticmethod
-    def header(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.HEADER)
-
-    @staticmethod
-    def error(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.FAIL)
-
-    @staticmethod
-    def warning(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.WARNING)
-
-    is_disabled = False
-
-
-def run_shell_command(shell_cmd, cmd_dir=None):
-    """ Run a single shell command.
-        @returns a tuple of shell command return code, stdout, stderr """
-
-    if cmd_dir is not None and not os.path.exists(cmd_dir):
-        run_shell_command("mkdir -p %s" % cmd_dir)
-
-    start = time.time()
-    print("\t>>> Running: " + shell_cmd)
-    p = subprocess.Popen(shell_cmd,
-                         shell=True,
-                         stdout=subprocess.PIPE,
-                         stderr=subprocess.PIPE,
-                         cwd=cmd_dir)
-    stdout, stderr = p.communicate()
-    end = time.time()
-
-    # Report time if we spent more than 5 minutes executing a command
-    execution_time = end - start
-    if execution_time > (60 * 5):
-        mins = (execution_time / 60)
-        secs = (execution_time % 60)
-        print("\t>time spent: %d minutes %d seconds" % (mins, secs))
-
-
-    return p.returncode, stdout, stderr
-
-
-def run_shell_commands(shell_cmds, cmd_dir=None, verbose=False):
-    """ Execute a sequence of shell commands, which is equivalent to
-        running `cmd1 && cmd2 && cmd3`
-        @returns boolean indication if all commands succeeds.
-    """
-
-    if cmd_dir:
-        print("\t=== Set current working directory => %s" % cmd_dir)
-
-    for shell_cmd in shell_cmds:
-        ret_code, stdout, stderr = run_shell_command(shell_cmd, cmd_dir)
-        if stdout:
-            if verbose or ret_code != 0:
-                print(ColorString.info("stdout: \n"), stdout)
-        if stderr:
-            # contents in stderr is not necessarily to be error messages.
-            if verbose or ret_code != 0:
-                print(ColorString.error("stderr: \n"), stderr)
-        if ret_code != 0:
-            return False
-
-    return True

build_tools/RocksDBCommonHelper.php

@@ -1,377 +0,0 @@
-<?php
-// Copyright 2004-present Facebook. 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).
-
-// 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
-// and Sandcastle run starts.
-define("ENV_POST_RECEIVE_HOOK", "POST_RECEIVE_HOOK");
-define("ENV_HTTPS_APP_VALUE", "HTTPS_APP_VALUE");
-define("ENV_HTTPS_TOKEN_VALUE", "HTTPS_TOKEN_VALUE");
-
-define("PRIMARY_TOKEN_FILE", '/home/krad/.sandcastle');
-define("CONT_RUN_ALIAS", "leveldb");
-
-//////////////////////////////////////////////////////////////////////
-/*  Run tests in sandcastle */
-function postURL($diffID, $url) {
-  assert(strlen($diffID) > 0);
-  assert(is_numeric($diffID));
-  assert(strlen($url) > 0);
-
-  $cmd_args = array(
-    'diff_id' => (int)$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($cmd);
-}
-
-function buildUpdateTestStatusCmd($diffID, $test, $status) {
-  assert(strlen($diffID) > 0);
-  assert(is_numeric($diffID));
-  assert(strlen($test) > 0);
-  assert(strlen($status) > 0);
-
-  $cmd_args = array(
-    'diff_id' => (int)$diffID,
-    'name' => $test,
-    'result' => $status
-  );
-
-  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
-         . ' | arc call-conduit differential.updateunitresults';
-
-  return $cmd;
-}
-
-function updateTestStatus($diffID, $test) {
-  assert(strlen($diffID) > 0);
-  assert(is_numeric($diffID));
-  assert(strlen($test) > 0);
-
-  shell_exec(buildUpdateTestStatusCmd($diffID, $test, "waiting"));
-}
-
-function getSteps($applyDiff, $diffID, $username, $test) {
-  assert(strlen($username) > 0);
-  assert(strlen($test) > 0);
-
-  if ($applyDiff) {
-    assert(strlen($diffID) > 0);
-    assert(is_numeric($diffID));
-
-    $arcrc_content = (PHP_OS == "Darwin" ?
-        exec("cat ~/.arcrc | gzip -f | base64") :
-            exec("cat ~/.arcrc | gzip -f | base64 -w0"));
-    assert(strlen($arcrc_content) > 0);
-
-    // Sandcastle machines don't have arc setup. We copy the user certificate
-    // and authenticate using that in Sandcastle.
-    $setup = array(
-      "name" => "Setup arcrc",
-      "shell" => "echo " . escapeshellarg($arcrc_content) . " | base64 --decode"
-                 . " | gzip -d > ~/.arcrc",
-      "user" => "root"
-    );
-
-    // arc demands certain permission on its config.
-    // also fix the sticky bit issue in sandcastle
-    $fix_permission = array(
-      "name" => "Fix environment",
-      "shell" => "chmod 600 ~/.arcrc && chmod +t /dev/shm",
-      "user" => "root"
-    );
-
-    // Construct the steps in the order of execution.
-    $steps[] = $setup;
-    $steps[] = $fix_permission;
-  }
-
-  // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
-  // Git thinks it is an uncommited change.
-  $fix_git_ignore = array(
-    "name" => "Fix git ignore",
-    "shell" => "echo fbcode >> .git/info/exclude",
-    "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.
-  $cmd = "";
-
-  if ($applyDiff) {
-    // Patch the code (keep your fingures crossed).
-    $patch = array(
-      "name" => "Patch " . $diffID,
-      "shell" => "arc --arcrc-file ~/.arcrc "
-                  . "patch --nocommit --diff " . escapeshellarg($diffID),
-      "user" => "root"
-    );
-
-    $steps[] = $patch;
-
-    updateTestStatus($diffID, $test);
-    $cmd = buildUpdateTestStatusCmd($diffID, $test, "running") . "; ";
-  }
-
-  // Run the actual command.
-  $cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " .
-           escapeshellarg($test) . "; exit_code=$?; ";
-
-  if ($applyDiff) {
-    $cmd = $cmd . "([[ \$exit_code -eq 0 ]] &&"
-                . buildUpdateTestStatusCmd($diffID, $test, "pass") . ")"
-                . "||" . buildUpdateTestStatusCmd($diffID, $test, "fail")
-                . "; ";
-  }
-
-  // shell command to sort the tests based on exit code and print
-  // the output of the log files.
-  $cat_sorted_logs = "
-    while read code log_file;
-      do echo \"################ cat \$log_file [exit_code : \$code] ################\";
-      cat \$log_file;
-    done < <(tail -n +2 LOG | sort -k7,7n -k4,4gr | awk '{print \$7,\$NF}')";
-
-  // Shell command to cat all log files
-  $cat_all_logs = "for f in `ls t/!(run-*)`; do echo \$f;cat \$f; done";
-
-  // If LOG file exist use it to cat log files sorted by exit code, otherwise
-  // cat everything
-  $logs_cmd = "if [ -f LOG ]; then {$cat_sorted_logs}; else {$cat_all_logs}; fi";
-
-  $cmd = $cmd . " cat /tmp/precommit-check.log"
-              . "; shopt -s extglob; {$logs_cmd}"
-              . "; shopt -u extglob; [[ \$exit_code -eq 0 ]]";
-  assert(strlen($cmd) > 0);
-
-  $run_test = array(
-    "name" => "Run " . $test,
-    "shell" => $cmd,
-    "user" => "root",
-    "parser" => "python build_tools/error_filter.py " . escapeshellarg($test),
-  );
-
-  $steps[] = $run_test;
-
-  if ($applyDiff) {
-    // Clean up the user arc config we are using.
-    $cleanup = array(
-      "name" => "Arc cleanup",
-      "shell" => "rm -f ~/.arcrc",
-      "user" => "root"
-    );
-
-    $steps[] = $cleanup;
-  }
-
-  assert(count($steps) > 0);
-  return $steps;
-}
-
-function getSandcastleConfig() {
-  $sandcastle_config = array();
-
-  $cwd = getcwd();
-  $cwd_token_file = "{$cwd}/.sandcastle";
-  // This is a case when we're executed from a continuous run. Fetch the values
-  // from the environment.
-  if (getenv(ENV_POST_RECEIVE_HOOK)) {
-    $sandcastle_config[0] = getenv(ENV_HTTPS_APP_VALUE);
-    $sandcastle_config[1] = getenv(ENV_HTTPS_TOKEN_VALUE);
-  } else {
-    // This is a typical `[p]arc diff` case. Fetch the values from the specific
-    // configuration files.
-    for ($i = 0; $i < 50; $i++) {
-      if (file_exists(PRIMARY_TOKEN_FILE) ||
-          file_exists($cwd_token_file)) {
-        break;
-      }
-      // If we failed to fetch the tokens, sleep for 0.2 second and try again
-      usleep(200000);
-    }
-    assert(file_exists(PRIMARY_TOKEN_FILE) ||
-           file_exists($cwd_token_file));
-
-    // Try the primary location first, followed by a secondary.
-    if (file_exists(PRIMARY_TOKEN_FILE)) {
-      $cmd = 'cat ' . PRIMARY_TOKEN_FILE;
-    } else {
-      $cmd = 'cat ' . escapeshellarg($cwd_token_file);
-    }
-
-    assert(strlen($cmd) > 0);
-    $sandcastle_config = explode(':', rtrim(shell_exec($cmd)));
-  }
-
-  // In this case be very explicit about the implications.
-  if (count($sandcastle_config) != 2) {
-    echo "Sandcastle configuration files don't contain valid information " .
-         "or the necessary environment variables aren't defined. Unable " .
-         "to validate the code changes.";
-    exit(1);
-  }
-
-  assert(strlen($sandcastle_config[0]) > 0);
-  assert(strlen($sandcastle_config[1]) > 0);
-  assert(count($sandcastle_config) > 0);
-
-  return $sandcastle_config;
-}
-
-// This function can be called either from `[p]arc diff` command or during
-// the Git post-receive hook.
- function startTestsInSandcastle($applyDiff, $workflow, $diffID) {
-  // 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);
-
-  // In case of a diff we'll send notificatios to the author. Else it'll go to
-  // the entire team because failures indicate that build quality has regressed.
-  $username = $applyDiff ? exec("whoami") : CONT_RUN_ALIAS;
-  assert(strlen($username) > 0);
-
-  if ($applyDiff) {
-    assert($workflow);
-    assert(strlen($diffID) > 0);
-    assert(is_numeric($diffID));
-  }
-
-  // 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", "clang_analyze", "code_cov",
-                 "java_build", "no_compression", "unity", "ubsan");
-
-  $send_email_template = array(
-    'type' => 'email',
-    'triggers' => array('fail'),
-    'emails' => array($username . '@fb.com'),
-  );
-
-  // Construct a job definition for each test and add it to the master plan.
-  foreach ($tests as $test) {
-    $stepName = "RocksDB diff " . $diffID . " test " . $test;
-
-    if (!$applyDiff) {
-      $stepName = "RocksDB continuous integration test " . $test;
-    }
-
-    $arg[] = array(
-      "name" => $stepName,
-      "report" => array($send_email_template),
-      "steps" => getSteps($applyDiff, $diffID, $username, $test)
-    );
-  }
-
-  // We cannot submit the parallel execution master plan to Sandcastle and
-  // need supply the job plan as a determinator. So we construct a small job
-  // that will spit out the master job plan which Sandcastle will parse and
-  // execute. Why compress the job definitions? Otherwise we run over the max
-  // string size.
-  $cmd = "echo " . base64_encode(json_encode($arg))
-         . (PHP_OS == "Darwin" ?
-             " | gzip -f | base64" :
-                 " | gzip -f | base64 -w0");
-  assert(strlen($cmd) > 0);
-
-  $arg_encoded = shell_exec($cmd);
-  assert(strlen($arg_encoded) > 0);
-
-  $runName = "Run diff " . $diffID . "for user " . $username;
-
-  if (!$applyDiff) {
-    $runName = "RocksDB continuous integration build and test run";
-  }
-
-  $command = array(
-    "name" => $runName,
-    "steps" => array()
-  );
-
-  $command["steps"][] = array(
-    "name" => "Generate determinator",
-    "shell" => "echo " . $arg_encoded . " | base64 --decode | gzip -d"
-               . " | base64 --decode",
-    "determinator" => true,
-    "user" => "root"
-  );
-
-  // Submit to Sandcastle.
-  $url = 'https://interngraph.intern.facebook.com/sandcastle/create';
-
-  $job = array(
-    'command' => 'SandcastleUniversalCommand',
-    'args' => $command,
-    'capabilities' => array(
-      'vcs' => 'rocksdb-int-git',
-      'type' => 'lego',
-    ),
-    'hash' => 'origin/master',
-    'user' => $username,
-    'alias' => 'rocksdb-precommit',
-    'tags' => array('rocksdb'),
-    'description' => 'Rocksdb precommit job',
-  );
-
-  // Fetch the configuration necessary to submit a successful HTTPS request.
-  $sandcastle_config = getSandcastleConfig();
-
-  $app = $sandcastle_config[0];
-  $token = $sandcastle_config[1];
-
-  $cmd = 'curl -s -k '
-          . ' -F app=' . escapeshellarg($app)
-          . ' -F token=' . escapeshellarg($token)
-          . ' -F job=' . escapeshellarg(json_encode($job))
-          .' ' . escapeshellarg($url);
-
-  $output = shell_exec($cmd);
-  assert(strlen($output) > 0);
-
-  // Extract Sandcastle URL from the response.
-  preg_match('/url": "(.+)"/', $output, $sandcastle_url);
-
-  assert(count($sandcastle_url) > 0, "Unable to submit Sandcastle request.");
-  assert(strlen($sandcastle_url[1]) > 0, "Unable to extract Sandcastle URL.");
-
-  if ($applyDiff) {
-    echo "\nSandcastle URL: " . $sandcastle_url[1] . "\n";
-    // Ask Phabricator to display it on the diff UI.
-    postURL($diffID, $sandcastle_url[1]);
-  } else {
-    echo "Continuous integration started Sandcastle tests. You can look at ";
-    echo "the progress at:\n" . $sandcastle_url[1] . "\n";
-  }
-}
-
-// Continuous run cript will set the environment variable and based on that
-// we'll trigger the execution of tests in Sandcastle. In that case we don't
-// need to apply any diffs and there's no associated workflow either.
-if (getenv(ENV_POST_RECEIVE_HOOK)) {
-  startTestsInSandcastle(
-    false /* $applyDiff */,
-    NULL /* $workflow */,
-    NULL /* $diffID */);
-}

build_tools/build_detect_platform

@@ -51,12 +51,7 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
     FBCODE_BUILD="true"
     # If we're compiling with TSAN we need pic build
     PIC_BUILD=$COMPILE_WITH_TSAN
-    if [ -z "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
-      source "$PWD/build_tools/fbcode_config.sh"
-    else
-      # we need this to build with MySQL. Don't use for other purposes.
-      source "$PWD/build_tools/fbcode_config4.8.1.sh"
-    fi
+    source "$PWD/build_tools/fbcode_config.sh"
 fi
 
 # Delete existing output, if it exists
@@ -128,20 +123,12 @@ case "$TARGET_OS" in
         ;;
     SunOS)
         PLATFORM=OS_SOLARIS
-        COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_SOLARIS -m64"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt -static-libstdc++ -static-libgcc -m64"
+        COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_SOLARIS"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
         # PORT_FILES=port/sunos/sunos_specific.cc
         ;;
-    AIX)
-        PLATFORM=OS_AIX
-        CC=gcc
-        COMMON_FLAGS="$COMMON_FLAGS -maix64 -pthread -fno-builtin-memcmp -D_REENTRANT -DOS_AIX -D__STDC_FORMAT_MACROS"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -pthread -lpthread -lrt -maix64 -static-libstdc++ -static-libgcc"
-        # PORT_FILES=port/aix/aix_specific.cc
-        ;;
     FreeBSD)
         PLATFORM=OS_FREEBSD
-        CXX=clang++
         COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_FREEBSD"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread"
         # PORT_FILES=port/freebsd/freebsd_specific.cc
@@ -211,137 +198,117 @@ EOF
         fi
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -lsnappy"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DSNAPPY"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lsnappy"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lsnappy"
     fi
 
-    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() {}
+    # Test whether gflags library is installed
+    # http://gflags.github.io/gflags/
+    # check if the namespace is gflags
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+      #include <gflags/gflags.h>
+      using namespace gflags;
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
-        else
-          # check if namespace is google
-          $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
-            #include <gflags/gflags.h>
-            using namespace google;
-            int main() {}
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=gflags"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
+    else
+      # check if namespace is google
+      $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+        #include <gflags/gflags.h>
+        using namespace google;
+        int main() {}
 EOF
-          if [ "$?" = 0 ]; then
-              COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
-              PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
-          fi
-        fi
+      if [ "$?" = 0 ]; then
+          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
+          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
+      fi
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -lz"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DZLIB"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lz"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lz"
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -lbz2"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DBZIP2"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbz2"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lbz2"
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -llz4"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DLZ4"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -llz4"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -llz4"
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -lzstd"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DZSTD"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lzstd"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lzstd"
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -lnuma"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DNUMA"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lnuma"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
     fi
 
-    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() {}
+    # 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="$JAVA_LDFLAGS -ltbb"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DTBB"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltbb"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -ltbb"
     fi
 
-    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
+    # 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
         # jemalloc is not available. Let's try tcmalloc
         if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null \
           -ltcmalloc 2>/dev/null; then
@@ -350,100 +317,65 @@ EOF
         fi
     fi
 
-    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;
-          }
+    # 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="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
     fi
 
-    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;
-          }
+    # 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="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
     fi
 
-    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>>
+    # 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 $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
+          #include <execinfo.h>
           int main() {
             void* frames[1];
             backtrace_symbols(frames, backtrace(frames, 1));
-            return 0;
           }
 EOF
         if [ "$?" = 0 ]; then
             COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-        else
-            # Test whether execinfo library is installed
-            $CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
-              #include <execinfo.h>
-              int main() {
-                void* frames[1];
-                backtrace_symbols(frames, backtrace(frames, 1));
-              }
-EOF
-            if [ "$?" = 0 ]; then
-                COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-                PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
-                JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
-            fi
+            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
+            JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
         fi
     fi
 
-    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;
-          }
+    # 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
-        fi
-    fi
-
-    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"
-        fi
-    fi
-
-    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="$COMMON_FLAGS -DROCKSDB_SCHED_GETCPU_PRESENT"
-        fi
+    if [ "$?" = 0 ]; then
+        PROFILING_FLAGS=-pg
     fi
 fi
 
@@ -475,70 +407,23 @@ if test "$USE_HDFS"; then
   JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi
 
-if test -z "$PORTABLE"; then
+if [ "$TARGET_OS" = FreeBSD -a "$TARGET_ARCHITECTURE" = i386 ]; then
+  # Intel SSE instructions breaks compilation on FreeBSD i386
+  unset USE_SSE
+fi
+
+if test "$USE_SSE"; then
+  # if Intel SSE instruction set is supported, set USE_SSE=1
+  COMMON_FLAGS="$COMMON_FLAGS -msse -msse4.2 "
+elif test -z "$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
+  else
     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 $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <nmmintrin.h>
-  int main() {
-    volatile uint32_t x = _mm_crc32_u32(0, 0);
-  }
-EOF
-if [ "$?" = 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
-# succeed because the cross-compiler flags are added by the Makefile, not this
-# script.
-if [ "$PLATFORM" != IOS ]; then
-  $CXX $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #if defined(_MSC_VER) && !defined(__thread)
-  #define __thread __declspec(thread)
-  #endif
-  int main() {
-    static __thread int tls;
-  }
-EOF
-  if [ "$?" = 0 ]; then
-    COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SUPPORT_THREAD_LOCAL"
   fi
 fi
 
@@ -573,14 +458,7 @@ 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"

build_tools/cont_integration.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 #
 # Copyright (c) 2016, Facebook. All rights reserved.
 #
@@ -67,7 +67,7 @@ function update_repo_status {
 #
 
 # Path to the determinator from the root of the RocksDB repo.
-CONTRUN_DETERMINATOR=./build_tools/RocksDBCommonHelper.php
+CONTRUN_DETERMINATOR=./arcanist_util/config/RocksDBCommonHelper.php
 
 # Value of the previous commit.
 PREV_COMMIT=

build_tools/dependencies.sh

@@ -1,18 +1,19 @@
-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
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/963d9aeda70cc4779885b1277484fe7544a04e3e/9.0.0/platform007/9e92d53/
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
+NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/ab9f09bba370e7066cafd4eb59752db93f2e8312/2.29.1/platform007/15a3614
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832

build_tools/dockerbuild.sh

@@ -1,2 +1,2 @@
-#!/usr/bin/env bash
+#!/bin/bash
 docker run -v $PWD:/rocks -w /rocks buildpack-deps make

build_tools/fbcode_config.sh

@@ -13,7 +13,7 @@ source "$BASEDIR/dependencies.sh"
 CFLAGS=""
 
 # libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include"
+LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/7.3.0"
 LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
 
 # glibc
@@ -43,12 +43,16 @@ if test -z $PIC_BUILD; then
   LZ4_INCLUDE=" -I $LZ4_BASE/include/"
   LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
   CFLAGS+=" -DLZ4"
-
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-  CFLAGS+=" -DZSTD"
 fi
 
+ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
+if test -z $PIC_BUILD; then
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
+else
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
+fi
+CFLAGS+=" -DZSTD"
+
 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
 if test -z $PIC_BUILD; then
@@ -83,7 +87,6 @@ CFLAGS+=" -DTBB"
 
 # use Intel SSE support for checksum calculations
 export USE_SSE=1
-export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -105,8 +108,8 @@ if [ -z "$USE_CLANG" ]; then
   CXX="$GCC_BASE/bin/g++"
 
   CFLAGS+=" -B$BINUTILS/gold"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
   CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
   JEMALLOC=1
 else
   # clang
@@ -117,8 +120,8 @@ else
   KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
 
   CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/5.x "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/5.x/x86_64-facebook-linux "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x/x86_64-facebook-linux "
   CFLAGS+=" -isystem $GLIBC_INCLUDE"
   CFLAGS+=" -isystem $LIBGCC_INCLUDE"
   CFLAGS+=" -isystem $CLANG_INCLUDE"
@@ -134,9 +137,9 @@ CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
 EXEC_LDFLAGS+=" -B$BINUTILS/gold"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-5-glibc-2.23/lib/ld.so"
+EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-5-glibc-2.23/lib"
+EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform007/lib"
 # required by libtbb
 EXEC_LDFLAGS+=" -ldl"
 
@@ -146,12 +149,4 @@ EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GF
 
 VALGRIND_VER="$VALGRIND_BASE/bin/"
 
-LUA_PATH="$LUA_BASE"
-
-if test -z $PIC_BUILD; then
-  LUA_LIB=" $LUA_PATH/lib/liblua.a"
-else
-  LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
-fi
-
-export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD 

build_tools/fbcode_config4.8.1.sh

@@ -54,7 +54,6 @@ 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"
@@ -94,7 +93,7 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-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+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
 CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA -DTBB"
 CXXFLAGS+=" $CFLAGS"
 

build_tools/format-diff.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/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 ]
@@ -9,12 +9,10 @@ fi
 # Check clang-format-diff.py
 if ! which $CLANG_FORMAT_DIFF &> /dev/null
 then
-  echo "You didn't have clang-format-diff.py and/or clang-format available in your computer!"
-  echo "You can download clang-format-diff.py by running: "
+  echo "You didn't have clang-format-diff.py available in your computer!"
+  echo "You can download it by running: "
   echo "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
-  echo "You can download clang-format by running: "
-  echo "    brew install clang-format"
-  echo "Then, move both files (i.e. ${CLANG_FORMAT_DIFF} and clang-format) to some directory within PATH=${PATH}"
+  echo "and move ${CLANG_FORMAT_DIFF} to some directory within PATH=${PATH}"
   exit 128
 fi
 

build_tools/make_package.sh

@@ -99,18 +99,6 @@ function main() {
 
   make static_lib
   make install INSTALL_PATH=package
-
-  cd package
-
-  LIB_DIR=lib
-  if [[ -z "$ARCH" ]]; then
-      ARCH=$(getconf LONG_BIT)
-  fi
-  if [[ ("$FPM_OUTPUT" = "rpm") && ($ARCH -eq 64) ]]; then
-      mv lib lib64
-      LIB_DIR=lib64
-  fi
-
   fpm \
     -s dir \
     -t $FPM_OUTPUT \
@@ -122,7 +110,7 @@ function main() {
     --license BSD \
     --vendor Facebook \
     --description "RocksDB is an embeddable persistent key-value store for fast storage." \
-    include $LIB_DIR
+    package
 }
 
 main $@

build_tools/regression_build_test.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 
 set -e
 

build_tools/rocksdb-lego-determinator

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 # This script is executed by Sandcastle
 # to determine next steps to run
 
@@ -81,7 +81,6 @@ PARALLELISM="$PARALLEL_J $PARALLEL_j"
 
 DEBUG="OPT=-g"
 SHM="TEST_TMPDIR=/dev/shm/rocksdb"
-NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
@@ -130,6 +129,35 @@ 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
+            },
+        ],
+        $REPORT
+    }
+]"
+
 #
 # RocksDB unit test
 #
@@ -163,7 +191,7 @@ UNIT_TEST_NON_SHM_COMMANDS="[
             {
                 'name':'Build and test RocksDB debug version',
                 'timeout': 86400,
-                'shell':'$NON_SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
+                'shell':'$DEBUG make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -343,7 +371,27 @@ LITE_BUILD_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build RocksDB debug version',
-                'shell':'$LITE make J=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
+                'shell':'$LITE make J=1 static_lib || $CONTRUN_NAME=lite_static_lib $TASK_CREATION_TOOL',
+                'user':'root',
+                $PARSER
+            },
+        ],
+        $REPORT
+    }
+]"
+
+#
+# RocksDB lite tests
+#
+LITE_UNIT_TEST_COMMANDS="[
+    {
+        'name':'Rocksdb Lite Unit Test',
+        'oncall':'$ONCALL',
+        'steps': [
+            $CLEANUP_ENV,
+            {
+                'name':'Build RocksDB debug version',
+                'shell':'$SHM $LITE make J=1 check || $CONTRUN_NAME=lite_check $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -544,7 +592,7 @@ TSAN_CRASH_TEST_COMMANDS="[
             {
                 'name':'Compile and run',
                 'timeout': 86400,
-                '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',
+                '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',
                 'user':'root',
                 $PARSER
             },
@@ -563,7 +611,39 @@ run_format_compatible()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
 
-  tools/check_format_compatible.sh
+  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
 }
 
 FORMAT_COMPATIBLE_COMMANDS="[
@@ -695,6 +775,9 @@ JAVA_BUILD_TEST_COMMANDS="[
 
 
 case $1 in
+  punit)
+    echo $PARALLEL_UNIT_TEST_COMMANDS
+    ;;
   unit)
     echo $UNIT_TEST_COMMANDS
     ;;
@@ -728,6 +811,9 @@ case $1 in
   lite)
     echo $LITE_BUILD_COMMANDS
     ;;
+  lite_test)
+    echo $LITE_UNIT_TEST_COMMANDS
+    ;;
   stress_crash)
     echo $STRESS_CRASH_TEST_COMMANDS
     ;;

build_tools/run_ci_db_test.ps1

@@ -1,58 +1,24 @@
 # This script enables you running RocksDB tests by running
-# All the tests concurrently and utilizing all the cores
+# All the tests in parallel and utilizing all the cores
+# For db_test the script first lists and parses the tests
+# and then fires them up in parallel using async PS Job functionality
+# Run the script from the enlistment
 Param(
-  [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
-                               # Takes effect when $RunAll or $SuiteRun is specified. Must have full
-                               # Test cases name including a group and a parameter if any
-  [string]$ExcludeExes = "",   # Exclude exes from consideration, expects a comma separated list,
-                               # no spaces. Takes effect only when $RunAll is specified
-  [string]$WorkFolder = "",    # Direct tests to use that folder. SSD or Ram drive are better options.
+  [switch]$EnableJE = $false,  # Use je executable
+  [switch]$EnableRerun = $false, # Rerun failed tests sequentially at the end
+  [string]$WorkFolder = "",  # Direct tests to use that folder
+  [int]$Limit = -1, # -1 means run all otherwise limit for testing purposes
+  [string]$Exclude = "", # Expect a comma separated list, no spaces
+  [string]$Run = "db_test",  # Run db_test|db_test2|tests|testname1,testname2...
    # Number of async tasks that would run concurrently. Recommend a number below 64.
    # However, CPU utlization really depends on the storage media. Recommend ram based disk.
    # a value of 1 will run everything serially
-  [int]$Concurrency = 8,
-  [int]$Limit = -1 # -1 means do not limit for test purposes
+  [int]$Concurrency = 16
 )
 
 # Folders and commands must be fullpath to run assuming
 # the current folder is at the root of the git enlistment
-$StartDate = (Get-Date)
-$StartDate
-
-
-$DebugPreference = "Continue"
-
-# These tests are not google test suites and we should guard
-# Against running them as suites
-$RunOnly = New-Object System.Collections.Generic.HashSet[string]
-$RunOnly.Add("c_test") | Out-Null
-$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
-}
+Get-Date
 
 # If running under Appveyor assume that root
 [string]$Appveyor = $Env:APPVEYOR_BUILD_FOLDER
@@ -81,32 +47,40 @@ if($WorkFolder -eq "") {
 }
 
 Write-Output "Root: $RootFolder, WorkFolder: $WorkFolder"
-Write-Output "BinariesFolder: $BinariesFolder, LogFolder: $LogFolder"
+
+# Use JEMALLOC executables
+if($Run -ceq "db_test" -or
+   $Run -ceq "db_test2" -or
+   $Run -ceq "db_basic_test") {
+
+   $file_name = $Run
+
+   if($EnableJE) {
+     $file_name += "_je"
+   }
+
+   $file_name += ".exe"
+
+   $db_test = -Join ($BinariesFolder, $file_name)
+
+   Write-Output "Binaries: $BinariesFolder db_test: $db_test"
+}
+
+
+#Exclusions that we do not want to run
+$ExcludeTests = New-Object System.Collections.Generic.HashSet[string]
+
+
+if($Exclude -ne "") {
+    Write-Host "Exclude: $Exclude"
+    $l = $Exclude -split ' '
+    ForEach($t in $l) { $ExcludeTests.Add($t) | Out-Null }
+}
 
 # Create test directories in the current folder
 md -Path $WorkFolder -ErrorAction Ignore | Out-Null
 md -Path $LogFolder -ErrorAction Ignore | Out-Null
 
-
-$ExcludeCasesSet = New-Object System.Collections.Generic.HashSet[string]
-if($ExcludeCases -ne "") {
-    Write-Host "ExcludeCases: $ExcludeCases"
-    $l = $ExcludeCases -split ' '
-    ForEach($t in $l) { 
-      $ExcludeCasesSet.Add($t) | Out-Null
-    }
-}
-
-$ExcludeExesSet = New-Object System.Collections.Generic.HashSet[string]
-if($ExcludeExes -ne "") {
-    Write-Host "ExcludeExe: $ExcludeExes"
-    $l = $ExcludeExes -split ' '
-    ForEach($t in $l) { 
-      $ExcludeExesSet.Add($t) | Out-Null
-    }
-}
-
-
 # Extract the names of its tests by running db_test with --gtest_list_tests.
 # This filter removes the "#"-introduced comments, and expands to
 # fully-qualified names by changing input like this:
@@ -124,33 +98,28 @@ if($ExcludeExes -ne "") {
 #   DBTest.WriteEmptyBatch
 #   MultiThreaded/MultiThreadedDBTest.MultiThreaded/0
 #   MultiThreaded/MultiThreadedDBTest.MultiThreaded/1
-#
 # Output into the parameter in a form TestName -> Log File Name
-function ExtractTestCases([string]$GTestExe, $HashTable) {
+function Normalize-DbTests($HashTable) {
 
     $Tests = @()
 # Run db_test to get a list of tests and store it into $a array
-    &$GTestExe --gtest_list_tests | tee -Variable Tests | Out-Null
+    &$db_test --gtest_list_tests | tee -Variable Tests | Out-Null
 
     # Current group
     $Group=""
 
     ForEach( $l in $Tests) {
-
-      # Leading whitespace is fine
-      $l = $l -replace '^\s+',''
-      # Trailing dot is a test group but no whitespace
-      if ($l -match "\.$" -and $l -notmatch "\s+") {
+      # Trailing dot is a test group
+      if( $l -match "\.$") {
         $Group = $l
       }  else {
         # Otherwise it is a test name, remove leading space
-        $test = $l
+        $test = $l -replace '^\s+',''
         # remove trailing comment if any and create a log name
         $test = $test -replace '\s+\#.*',''
         $test = "$Group$test"
 
-        if($ExcludeCasesSet.Contains($test)) {
-            Write-Warning "$test case is excluded"
+        if($ExcludeTests.Contains($test)) {
             continue
         }
 
@@ -166,157 +135,61 @@ function ExtractTestCases([string]$GTestExe, $HashTable) {
 
 # The function removes trailing .exe siffix if any,
 # creates a name for the log file
-# Then adds the test name if it was not excluded into
-# a HashTable in a form of test_name -> log_path
 function MakeAndAdd([string]$token, $HashTable) {
-
     $test_name = $token -replace '.exe$', ''
     $log_name =  -join ($test_name, ".log")
     $log_path = -join ($LogFolder, $log_name)
-    $HashTable.Add($test_name, $log_path)
-}
-
-# This function takes a list of Suites to run
-# Lists all the test cases in each of the suite
-# and populates HashOfHashes
-# Ordered by suite(exe) @{ Exe = @{ TestCase = LogName }}
-function ProcessSuites($ListOfSuites, $HashOfHashes) {
-
-  $suite_list = $ListOfSuites
-  # Problem: if you run --gtest_list_tests on
-  # a non Google Test executable then it will start executing
-  # and we will get nowhere
-  ForEach($suite in $suite_list) {
-
-    if($RunOnly.Contains($suite)) {
-      Write-Warning "$suite is excluded from running as Google test suite"
-      continue
-    }
-
-    if($EnableJE) {
-      $suite += "_je"
-    }
-
-    $Cases = [ordered]@{}
-    $Cases.Clear()
-    $suite_exe = -Join ($BinariesFolder, $suite)
-    ExtractTestCases -GTestExe $suite_exe -HashTable $Cases
-    if($Cases.Count -gt 0) {
-      $HashOfHashes.Add($suite, $Cases);
-    }
-  }
-
-  # Make logs and run
-  if($CasesToRun.Count -lt 1) {
-     Write-Error "Failed to extract tests from $SuiteRun"
-     exit 1
-  }
-
-}
-
-# This will contain all test executables to run
-
-# Hash table that contains all non suite
-# Test executable to run
-$TestExes = [ordered]@{}
-
-# Check for test exe that are not
-# Google Test Suites
-# Since this is explicitely mentioned it is not subject
-# for exclusions
-if($Run -ne "") {
-
-  $test_list = $Run -split ' '
-  ForEach($t in $test_list) {
-
-    if($EnableJE) {
-      $t += "_je"
-    }
-    MakeAndAdd -token $t -HashTable $TestExes
-  }
-
-  if($TestExes.Count -lt 1) {
-     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 }}
-$CasesToRun = [ordered]@{}
-
-if($SuiteRun -ne "") {
-  $suite_list = $SuiteRun -split ' '
-  ProcessSuites -ListOfSuites $suite_list -HashOfHashes $CasesToRun
-} elseif ($RunAll) {
-# 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"
-
-  $ListOfExe = @()
-  dir -Path $search_path | ForEach-Object {
-     $ListOfExe += ($_.Name)     
-  }
-
-  # Exclude those in RunOnly from running as suites
-  $ListOfSuites = @()
-  ForEach($e in $ListOfExe) {
-
-    $e = $e -replace '.exe$', ''
-    $bare_name = $e -replace '_je$', ''
-
-    if($ExcludeExesSet.Contains($bare_name)) {
-      Write-Warning "Test $e is excluded"
-      continue
-    }
-
-    if($RunOnly.Contains($bare_name)) {
-      MakeAndAdd -token $e -HashTable $TestExes
+    if(!$ExcludeTests.Contains($test_name)) {
+        $HashTable.Add($test_name, $log_path)
     } else {
-      $ListOfSuites += $bare_name
+        Write-Warning "Test $test_name is excluded"
     }
-  }
-
-  ProcessSuites -ListOfSuites $ListOfSuites -HashOfHashes $CasesToRun
 }
 
+# The function scans build\Debug folder to discover
+# Test executables. It then populates a table with
+# Test executable name -> Log file
+function Discover-TestBinaries([string]$Pattern, $HashTable) {
+
+    $Exclusions = @("db_test*", "db_sanity_test*", "db_basic_test*")
+
+    $p = -join ($BinariesFolder, $pattern)
+
+    Write-Host "Path: $p"
+
+    dir -Path $p -Exclude $Exclusions | ForEach-Object {
+       MakeAndAdd -token ($_.Name) -HashTable $HashTable
+    }
+}
+
+$TestsToRun = [ordered]@{}
+
+if($Run -ceq "db_test" -or
+   $Run -ceq "db_test2" -or
+   $Run -ceq "db_basic_test") {
+    Normalize-DbTests -HashTable $TestsToRun
+} elseif($Run -ceq "tests") {
+    if($EnableJE) {
+        $pattern = "*_test_je.exe"
+    } else {
+        $pattern = "*_test.exe"
+    }
+    Discover-TestBinaries -Pattern $pattern -HashTable $TestsToRun
+} else {
+
+    $test_list = $Run -split ' '
+
+    ForEach($t in $test_list) {
+       MakeAndAdd -token $t -HashTable $TestsToRun
+    }
+}
+
+$NumTestsToStart = $TestsToRun.Count
+if($Limit -ge 0 -and $NumTestsToStart -gt $Limit) {
+    $NumTestsToStart = $Limit
+}
+
+Write-Host "Attempting to start: $NumTestsToStart tests"
 
 # Invoke a test with a filter and redirect all output
 $InvokeTestCase = {
@@ -332,13 +205,13 @@ $InvokeTestAsync = {
 
 # Hash that contains tests to rerun if any failed
 # Those tests will be rerun sequentially
-# $Rerun = [ordered]@{}
+$Rerun = [ordered]@{}
 # Test limiting factor here
-[int]$count = 0
+$count = 0
 # Overall status
 [bool]$success = $true;
 
-function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
+function RunJobs($TestToLog, [int]$ConcurrencyVal, [bool]$AddForRerun)
 {
     # Array to wait for any of the running jobs
     $jobs = @()
@@ -347,67 +220,38 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
 
     # Wait for all to finish and get the results
     while(($JobToLog.Count -gt 0) -or
-          ($TestCmds.Count -gt 0) -or 
-           ($Suites.Count -gt 0)) {
+          ($TestToLog.Count -gt 0)) {
 
         # Make sure we have maximum concurrent jobs running if anything
         # and the $Limit either not set or allows to proceed
         while(($JobToLog.Count -lt $ConcurrencyVal) -and
-              ((($TestCmds.Count -gt 0) -or ($Suites.Count -gt 0)) -and
+              (($TestToLog.Count -gt 0) -and
               (($Limit -lt 0) -or ($count -lt $Limit)))) {
 
-            # We always favore suites to run if available
-            [string]$exe_name = ""
-            [string]$log_path = ""
-            $Cases = @{}
 
-            if($Suites.Count -gt 0) {
-              # Will the first one
-              ForEach($e in $Suites.Keys) {
-                $exe_name = $e
-                $Cases = $Suites[$e]
+            # We only need the first key
+            foreach($key in $TestToLog.keys) {
+                $k = $key
                 break
-              }
-              [string]$test_case = ""
-              [string]$log_path = ""
-              ForEach($c in $Cases.Keys) {
-                 $test_case = $c
-                 $log_path = $Cases[$c]
-                 break
-              }
-
-              Write-Host "Starting $exe_name::$test_case"
-              [string]$Exe =  -Join ($BinariesFolder, $exe_name)
-              $job = Start-Job -Name "$exe_name::$test_case" -ArgumentList @($Exe,$test_case,$log_path) -ScriptBlock $InvokeTestCase
-              $JobToLog.Add($job, $log_path)
-
-              $Cases.Remove($test_case)
-              if($Cases.Count -lt 1) {
-                $Suites.Remove($exe_name)
-              }
-
-            } elseif ($TestCmds.Count -gt 0) {
-
-               ForEach($e in $TestCmds.Keys) {
-                 $exe_name = $e
-                 $log_path = $TestCmds[$e]
-                 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)
-
-              $TestCmds.Remove($exe_name)
-
-            } else {
-                Write-Error "In the job loop but nothing to run"
-                exit 1
             }
 
+            Write-Host "Starting $k"
+            $log_path = ($TestToLog.$k)
+
+            if($Run -ceq "db_test" -or
+               $Run -ceq "db_test2" -or
+               $Run -ceq "db_basic_test") {
+              $job = Start-Job -Name $k -ScriptBlock $InvokeTestCase -ArgumentList @($db_test,$k,$log_path)
+            } else {
+              [string]$Exe =  -Join ($BinariesFolder, $k)
+               $job = Start-Job -Name $k -ScriptBlock $InvokeTestAsync -ArgumentList @($exe,$log_path)
+            }
+
+            $JobToLog.Add($job, $log_path)
+            $TestToLog.Remove($k)
+
             ++$count
-        } # End of Job starting loop
+        }
 
         if($JobToLog.Count -lt 1) {
           break
@@ -452,6 +296,9 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
                 $success = $false;
                 Write-Warning $message
                 $log_content | Write-Warning
+                if($AddForRerun) {
+                    $Rerun.Add($completed.Name, $log)
+                }
             } else {
                 Write-Host $message
             }
@@ -463,14 +310,16 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
     }
 }
 
-RunJobs -Suites $CasesToRun -TestCmds $TestExes -ConcurrencyVal $Concurrency
+RunJobs -TestToLog $TestsToRun -ConcurrencyVal $Concurrency -AddForRerun $EnableRerun
 
-$EndDate = (Get-Date)
+if($Rerun.Count -gt 0) {
+    Write-Host "Rerunning " ($Rerun.Count) " tests sequentially"
+    $success = $true
+    $count = 0
+    RunJobs -TestToLog $Rerun -ConcurrencyVal 1 -AddForRerun $false
+}
 
-New-TimeSpan -Start $StartDate -End $EndDate | 
-  ForEach-Object { 
-    "Elapsed time: {0:g}" -f $_
-  }
+Get-Date
 
 
 if(!$success) {
@@ -478,9 +327,7 @@ if(!$success) {
 # So we simply exit
 #    Remove-Job -Job $jobs -Force
 # indicate failure using this exit code
-    exit 1
+    exit 12345
  }
 
- exit 0
-
  

build_tools/update_dependencies.sh

@@ -38,7 +38,6 @@ 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
   
@@ -54,7 +53,7 @@ function get_lib_base()
 }
 
 ###########################################################
-#                   5.x dependencies                      #
+#                   4.9.x dependencies                    #
 ###########################################################
 
 OUTPUT="$BASEDIR/dependencies.sh"
@@ -65,30 +64,30 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"
 
 # Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos6-native/*/`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.9.x/centos6-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
 
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
 # Libraries locations
-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 libgcc     4.9.x
+get_lib_base glibc      2.20
+get_lib_base snappy     LATEST gcc-4.9-glibc-2.20
+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-4.9-glibc-2.20
 
-get_lib_base kernel-headers 4.0.9-36_fbk5_2933_gd092e3f gcc-5-glibc-2.23
+get_lib_base kernel-headers LATEST 
 get_lib_base binutils   LATEST centos6-native 
-get_lib_base valgrind   LATEST gcc-5-glibc-2.23
-get_lib_base lua        5.2.3 gcc-5-glibc-2.23
+get_lib_base valgrind   3.10.0 gcc-4.9-glibc-2.20
+get_lib_base lua        5.2.3 gcc-4.9-glibc-2.20
 
 git diff $OUTPUT
 

cmake/RocksDBConfig.cmake.in

@@ -1,3 +0,0 @@
-@PACKAGE_INIT@
-include("${CMAKE_CURRENT_LIST_DIR}/RocksDBTargets.cmake")
-check_required_components(RocksDB)

cmake/modules/FindJeMalloc.cmake

@@ -1,21 +1,22 @@
 # - Find JeMalloc library
 # Find the native JeMalloc includes and library
+# This module defines
+#  JEMALLOC_INCLUDE_DIRS, where to find jemalloc.h, Set when
+#                        JEMALLOC_INCLUDE_DIR is found.
+#  JEMALLOC_LIBRARIES, libraries to link against to use JeMalloc.
+#  JEMALLOC_FOUND, If false, do not try to use JeMalloc.
 #
-# JEMALLOC_INCLUDE_DIR - where to find jemalloc.h, etc.
-# JEMALLOC_LIBRARIES - List of libraries when using jemalloc.
-# JEMALLOC_FOUND - True if jemalloc found.
-
 find_path(JEMALLOC_INCLUDE_DIR
-  NAMES jemalloc/jemalloc.h
-  HINTS ${JEMALLOC_ROOT_DIR}/include)
+  jemalloc/jemalloc.h)
 
 find_library(JEMALLOC_LIBRARIES
-  NAMES jemalloc
-  HINTS ${JEMALLOC_ROOT_DIR}/lib)
+  jemalloc)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(jemalloc DEFAULT_MSG JEMALLOC_LIBRARIES JEMALLOC_INCLUDE_DIR)
+find_package_handle_standard_args(JeMalloc DEFAULT_MSG
+    JEMALLOC_LIBRARIES JEMALLOC_INCLUDE_DIR)
 
-mark_as_advanced(
+MARK_AS_ADVANCED(
+  JEMALLOC_INCLUDE_DIR
   JEMALLOC_LIBRARIES
-  JEMALLOC_INCLUDE_DIR)
+)

cmake/modules/FindNUMA.cmake

@@ -1,21 +0,0 @@
-# - 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)

cmake/modules/FindTBB.cmake

@@ -1,21 +0,0 @@
-# - 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)

cmake/modules/Findbzip2.cmake

@@ -1,21 +0,0 @@
-# - 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)

cmake/modules/Findlz4.cmake

@@ -1,21 +0,0 @@
-# - 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)

cmake/modules/Findsnappy.cmake

@@ -13,6 +13,8 @@ find_library(SNAPPY_LIBRARIES
   NAMES snappy
   HINTS ${SNAPPY_ROOT_DIR}/lib)
 
+# handle the QUIETLY and REQUIRED arguments and set UUID_FOUND to TRUE if
+# all listed variables are TRUE
 include(FindPackageHandleStandardArgs)
 find_package_handle_standard_args(snappy DEFAULT_MSG SNAPPY_LIBRARIES SNAPPY_INCLUDE_DIR)
 

cmake/modules/Findzlib.cmake

@@ -1,21 +0,0 @@
-# - 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)

cmake/modules/Findzstd.cmake

@@ -1,21 +0,0 @@
-# - 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)

coverage/coverage_test.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 
 # Exit on error.
 set -e

db/auto_roll_logger.cc

@@ -3,7 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 //
-#include "util/auto_roll_logger.h"
+#include "db/auto_roll_logger.h"
 #include "util/mutexlock.h"
 
 namespace rocksdb {

db/auto_roll_logger.h

@@ -10,11 +10,11 @@
 #include <list>
 #include <string>
 
+#include "db/filename.h"
 #include "port/port.h"
 #include "port/util_logger.h"
-#include "util/filename.h"
-#include "util/mutexlock.h"
 #include "util/sync_point.h"
+#include "util/mutexlock.h"
 
 namespace rocksdb {
 
@@ -91,8 +91,6 @@ class AutoRollLogger : public Logger {
     return log_fname_;
   }
 
-  uint64_t TEST_ctime() const { return ctime_; }
-
  private:
   bool LogExpired();
   Status ResetLogger();
@@ -103,14 +101,6 @@ class AutoRollLogger : public Logger {
   std::string ValistToString(const char* format, va_list args) const;
   // Write the logs marked as headers to the new log file
   void WriteHeaderInfo();
-  // Implementation of Close()
-  virtual Status CloseImpl() override {
-    if (logger_) {
-      return logger_->Close();
-    } else {
-      return Status::OK();
-    }
-  }
 
   std::string log_fname_; // Current active info log's file name.
   std::string dbname_;

db/auto_roll_logger_test.cc

@@ -6,40 +6,23 @@
 
 #ifndef ROCKSDB_LITE
 
-#include "util/auto_roll_logger.h"
-#include <errno.h>
-#include <sys/stat.h>
-#include <algorithm>
-#include <cmath>
-#include <fstream>
-#include <iostream>
-#include <iterator>
 #include <string>
 #include <thread>
 #include <vector>
+#include <cmath>
+#include <iostream>
+#include <fstream>
+#include <iterator>
+#include <algorithm>
+#include "db/auto_roll_logger.h"
 #include "port/port.h"
-#include "rocksdb/db.h"
-#include "util/logging.h"
 #include "util/sync_point.h"
 #include "util/testharness.h"
+#include "rocksdb/db.h"
+#include <sys/stat.h>
+#include <errno.h>
 
 namespace rocksdb {
-namespace {
-class NoSleepEnv : public EnvWrapper {
- public:
-  NoSleepEnv(Env* base) : EnvWrapper(base) {}
-  virtual void SleepForMicroseconds(int micros) override {
-    fake_time_ += static_cast<uint64_t>(micros);
-  }
-
-  virtual uint64_t NowNanos() override { return fake_time_ * 1000; }
-
-  virtual uint64_t NowMicros() override { return fake_time_; }
-
- private:
-  uint64_t fake_time_ = 6666666666;
-};
-}  // namespace
 
 class AutoRollLoggerTest : public testing::Test {
  public:
@@ -60,13 +43,13 @@ class AutoRollLoggerTest : public testing::Test {
 
   void RollLogFileBySizeTest(AutoRollLogger* logger, size_t log_max_size,
                              const std::string& log_message);
-  void RollLogFileByTimeTest(Env*, AutoRollLogger* logger, size_t time,
-                             const std::string& log_message);
+  uint64_t RollLogFileByTimeTest(AutoRollLogger* logger, size_t time,
+                                 const std::string& log_message);
 
   static const std::string kSampleMessage;
   static const std::string kTestDir;
   static const std::string kLogFile;
-  static Env* default_env;
+  static Env* env;
 };
 
 const std::string AutoRollLoggerTest::kSampleMessage(
@@ -74,15 +57,15 @@ const std::string AutoRollLoggerTest::kSampleMessage(
 const std::string AutoRollLoggerTest::kTestDir(test::TmpDir() + "/db_log_test");
 const std::string AutoRollLoggerTest::kLogFile(test::TmpDir() +
                                                "/db_log_test/LOG");
-Env* AutoRollLoggerTest::default_env = Env::Default();
+Env* AutoRollLoggerTest::env = Env::Default();
 
 // In this test we only want to Log some simple log message with
 // no format. LogMessage() provides such a simple interface and
 // avoids the [format-security] warning which occurs when you
-// call ROCKS_LOG_INFO(logger, log_message) directly.
+// call Log(logger, log_message) directly.
 namespace {
 void LogMessage(Logger* logger, const char* message) {
-  ROCKS_LOG_INFO(logger, "%s", message);
+  Log(logger, "%s", message);
 }
 
 void LogMessage(const InfoLogLevel log_level, Logger* logger,
@@ -91,6 +74,16 @@ void LogMessage(const InfoLogLevel log_level, Logger* logger,
 }
 }  // namespace
 
+namespace {
+void GetFileCreateTime(const std::string& fname, uint64_t* file_ctime) {
+  struct stat s;
+  if (stat(fname.c_str(), &s) != 0) {
+    *file_ctime = (uint64_t)0;
+  }
+  *file_ctime = static_cast<uint64_t>(s.st_ctime);
+}
+}  // namespace
+
 void AutoRollLoggerTest::RollLogFileBySizeTest(AutoRollLogger* logger,
                                                size_t log_max_size,
                                                const std::string& log_message) {
@@ -117,42 +110,45 @@ void AutoRollLoggerTest::RollLogFileBySizeTest(AutoRollLogger* logger,
   ASSERT_TRUE(message_size == logger->GetLogFileSize());
 }
 
-void AutoRollLoggerTest::RollLogFileByTimeTest(Env* env, AutoRollLogger* logger,
-                                               size_t time,
-                                               const std::string& log_message) {
-  uint64_t expected_ctime;
-  uint64_t actual_ctime;
-
+uint64_t AutoRollLoggerTest::RollLogFileByTimeTest(
+    AutoRollLogger* logger, size_t time, const std::string& log_message) {
+  uint64_t expected_create_time;
+  uint64_t actual_create_time;
   uint64_t total_log_size;
   EXPECT_OK(env->GetFileSize(kLogFile, &total_log_size));
-  expected_ctime = logger->TEST_ctime();
+  GetFileCreateTime(kLogFile, &expected_create_time);
   logger->SetCallNowMicrosEveryNRecords(0);
 
   // -- Write to the log for several times, which is supposed
   // to be finished before time.
   for (int i = 0; i < 10; ++i) {
-    env->SleepForMicroseconds(50000);
-    LogMessage(logger, log_message.c_str());
-    EXPECT_OK(logger->GetStatus());
-    // Make sure we always write to the same log file (by
-    // checking the create time);
+     LogMessage(logger, log_message.c_str());
+     EXPECT_OK(logger->GetStatus());
+     // Make sure we always write to the same log file (by
+     // checking the create time);
+     GetFileCreateTime(kLogFile, &actual_create_time);
 
-    actual_ctime = logger->TEST_ctime();
-
-    // Also make sure the log size is increasing.
-    EXPECT_EQ(expected_ctime, actual_ctime);
-    EXPECT_GT(logger->GetLogFileSize(), total_log_size);
-    total_log_size = logger->GetLogFileSize();
+     // Also make sure the log size is increasing.
+     EXPECT_EQ(expected_create_time, actual_create_time);
+     EXPECT_GT(logger->GetLogFileSize(), total_log_size);
+     total_log_size = logger->GetLogFileSize();
   }
 
   // -- Make the log file expire
-  env->SleepForMicroseconds(static_cast<int>(time * 1000000));
+#ifdef OS_WIN
+  Sleep(static_cast<unsigned int>(time) * 1000);
+#else
+  sleep(static_cast<unsigned int>(time));
+#endif
   LogMessage(logger, log_message.c_str());
 
   // At this time, the new log file should be created.
-  actual_ctime = logger->TEST_ctime();
-  EXPECT_LT(expected_ctime, actual_ctime);
+  GetFileCreateTime(kLogFile, &actual_create_time);
+  EXPECT_GT(actual_create_time, expected_create_time);
   EXPECT_LT(logger->GetLogFileSize(), total_log_size);
+  expected_create_time = actual_create_time;
+
+  return expected_create_time;
 }
 
 TEST_F(AutoRollLoggerTest, RollLogFileBySize) {
@@ -166,19 +162,16 @@ TEST_F(AutoRollLoggerTest, RollLogFileBySize) {
 }
 
 TEST_F(AutoRollLoggerTest, RollLogFileByTime) {
-  NoSleepEnv nse(Env::Default());
+    size_t time = 2;
+    size_t log_size = 1024 * 5;
 
-  size_t time = 2;
-  size_t log_size = 1024 * 5;
+    InitTestDb();
+    // -- Test the existence of file during the server restart.
+    ASSERT_EQ(Status::NotFound(), env->FileExists(kLogFile));
+    AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, time);
+    ASSERT_OK(env->FileExists(kLogFile));
 
-  InitTestDb();
-  // -- Test the existence of file during the server restart.
-  ASSERT_EQ(Status::NotFound(), default_env->FileExists(kLogFile));
-  AutoRollLogger logger(&nse, kTestDir, "", log_size, time);
-  ASSERT_OK(default_env->FileExists(kLogFile));
-
-  RollLogFileByTimeTest(&nse, &logger, time,
-                        kSampleMessage + ":RollLogFileByTime");
+    RollLogFileByTimeTest(&logger, time, kSampleMessage + ":RollLogFileByTime");
 }
 
 TEST_F(AutoRollLoggerTest, OpenLogFilesMultipleTimesWithOptionLog_max_size) {
@@ -211,16 +204,16 @@ TEST_F(AutoRollLoggerTest, CompositeRollByTimeAndSizeLogger) {
 
   InitTestDb();
 
-  NoSleepEnv nse(Env::Default());
-  AutoRollLogger logger(&nse, kTestDir, "", log_max_size, time);
+  AutoRollLogger logger(Env::Default(), kTestDir, "", log_max_size, time);
 
   // Test the ability to roll by size
-  RollLogFileBySizeTest(&logger, log_max_size,
-                        kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
+  RollLogFileBySizeTest(
+      &logger, log_max_size,
+      kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
 
   // Test the ability to roll by Time
-  RollLogFileByTimeTest(&nse, &logger, time,
-                        kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
+  RollLogFileByTimeTest( &logger, time,
+      kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
 }
 
 #ifndef OS_WIN
@@ -228,7 +221,6 @@ TEST_F(AutoRollLoggerTest, CompositeRollByTimeAndSizeLogger) {
 // port
 TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
   DBOptions options;
-  NoSleepEnv nse(Env::Default());
   shared_ptr<Logger> logger;
 
   // Normal logger
@@ -247,15 +239,15 @@ TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
       kSampleMessage + ":CreateLoggerFromOptions - size");
 
   // Only roll by Time
-  options.env = &nse;
   InitTestDb();
   options.max_log_file_size = 0;
   options.log_file_time_to_roll = 2;
   ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
   auto_roll_logger =
     dynamic_cast<AutoRollLogger*>(logger.get());
-  RollLogFileByTimeTest(&nse, auto_roll_logger, options.log_file_time_to_roll,
-                        kSampleMessage + ":CreateLoggerFromOptions - time");
+  RollLogFileByTimeTest(
+      auto_roll_logger, options.log_file_time_to_roll,
+      kSampleMessage + ":CreateLoggerFromOptions - time");
 
   // roll by both Time and size
   InitTestDb();
@@ -264,10 +256,12 @@ TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
   ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
   auto_roll_logger =
     dynamic_cast<AutoRollLogger*>(logger.get());
-  RollLogFileBySizeTest(auto_roll_logger, options.max_log_file_size,
-                        kSampleMessage + ":CreateLoggerFromOptions - both");
-  RollLogFileByTimeTest(&nse, auto_roll_logger, options.log_file_time_to_roll,
-                        kSampleMessage + ":CreateLoggerFromOptions - both");
+  RollLogFileBySizeTest(
+      auto_roll_logger, options.max_log_file_size,
+      kSampleMessage + ":CreateLoggerFromOptions - both");
+  RollLogFileByTimeTest(
+      auto_roll_logger, options.log_file_time_to_roll,
+      kSampleMessage + ":CreateLoggerFromOptions - both");
 }
 
 TEST_F(AutoRollLoggerTest, LogFlushWhileRolling) {
@@ -338,12 +332,12 @@ TEST_F(AutoRollLoggerTest, InfoLogLevel) {
       logger.SetInfoLogLevel((InfoLogLevel)log_level);
 
       // again, messages with level smaller than log_level will not be logged.
-      ROCKS_LOG_HEADER(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_DEBUG(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_INFO(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_WARN(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_ERROR(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_FATAL(&logger, "%s", kSampleMessage.c_str());
+      Log(InfoLogLevel::HEADER_LEVEL, &logger, "%s", kSampleMessage.c_str());
+      Debug(&logger, "%s", kSampleMessage.c_str());
+      Info(&logger, "%s", kSampleMessage.c_str());
+      Warn(&logger, "%s", kSampleMessage.c_str());
+      Error(&logger, "%s", kSampleMessage.c_str());
+      Fatal(&logger, "%s", kSampleMessage.c_str());
       log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
     }
   }
@@ -354,45 +348,6 @@ TEST_F(AutoRollLoggerTest, InfoLogLevel) {
   inFile.close();
 }
 
-TEST_F(AutoRollLoggerTest, Close) {
-  InitTestDb();
-
-  size_t log_size = 8192;
-  size_t log_lines = 0;
-  AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, 0);
-  for (int log_level = InfoLogLevel::HEADER_LEVEL;
-       log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
-    logger.SetInfoLogLevel((InfoLogLevel)log_level);
-    for (int log_type = InfoLogLevel::DEBUG_LEVEL;
-         log_type <= InfoLogLevel::HEADER_LEVEL; log_type++) {
-      // log messages with log level smaller than log_level will not be
-      // logged.
-      LogMessage((InfoLogLevel)log_type, &logger, kSampleMessage.c_str());
-    }
-    log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
-  }
-  for (int log_level = InfoLogLevel::HEADER_LEVEL;
-       log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
-    logger.SetInfoLogLevel((InfoLogLevel)log_level);
-
-    // again, messages with level smaller than log_level will not be logged.
-    ROCKS_LOG_HEADER(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_DEBUG(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_INFO(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_WARN(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_ERROR(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_FATAL(&logger, "%s", kSampleMessage.c_str());
-    log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
-  }
-  ASSERT_EQ(logger.Close(), Status::OK());
-
-  std::ifstream inFile(AutoRollLoggerTest::kLogFile.c_str());
-  size_t lines = std::count(std::istreambuf_iterator<char>(inFile),
-                         std::istreambuf_iterator<char>(), '\n');
-  ASSERT_EQ(log_lines, lines);
-  inFile.close();
-}
-
 // Test the logger Header function for roll over logs
 // We expect the new logs creates as roll over to carry the headers specified
 static std::vector<std::string> GetOldFileNames(const std::string& path) {
@@ -456,7 +411,8 @@ TEST_F(AutoRollLoggerTest, LogHeaderTest) {
     } else if (test_num == 1) {
       // HEADER_LEVEL should make this behave like calling Header()
       for (size_t i = 0; i < MAX_HEADERS; i++) {
-        ROCKS_LOG_HEADER(&logger, "%s %d", HEADER_STR.c_str(), i);
+        Log(InfoLogLevel::HEADER_LEVEL, &logger, "%s %d",
+            HEADER_STR.c_str(), i);
       }
     }
 
@@ -506,7 +462,7 @@ TEST_F(AutoRollLoggerTest, LogFileExistence) {
   options.max_log_file_size = 100 * 1024 * 1024;
   options.create_if_missing = true;
   ASSERT_OK(rocksdb::DB::Open(options, kTestDir, &db));
-  ASSERT_OK(default_env->FileExists(kLogFile));
+  ASSERT_OK(env->FileExists(kLogFile));
   delete db;
 }
 

db/builder.cc

@@ -16,12 +16,11 @@
 #include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/event_helpers.h"
+#include "db/filename.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
-#include "monitoring/iostats_context_imp.h"
-#include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
@@ -30,9 +29,9 @@
 #include "table/block_based_table_builder.h"
 #include "table/internal_iterator.h"
 #include "util/file_reader_writer.h"
-#include "util/filename.h"
+#include "util/iostats_context_imp.h"
 #include "util/stop_watch.h"
-#include "util/sync_point.h"
+#include "util/thread_status_util.h"
 
 namespace rocksdb {
 
@@ -45,17 +44,17 @@ 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 uint64_t creation_time, const uint64_t oldest_key_time) {
+    const CompressionOptions& compression_opts,
+    int level,
+    const std::string* compression_dict, const bool skip_filters) {
   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, creation_time, oldest_key_time),
+      TableBuilderOptions(ioptions, internal_comparator,
+                          int_tbl_prop_collector_factories, compression_type,
+                          compression_opts, compression_dict, skip_filters,
+                          column_family_name, level),
       column_family_id, file);
 }
 
@@ -70,12 +69,11 @@ Status BuildTable(
     uint32_t column_family_id, const std::string& column_family_name,
     std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
-    SnapshotChecker* snapshot_checker, const CompressionType compression,
+    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, const uint64_t creation_time,
-    const uint64_t oldest_key_time, Env::WriteLifeTimeHint write_hint) {
+    TableProperties* table_properties, int level) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
@@ -105,10 +103,6 @@ Status BuildTable(
     unique_ptr<WritableFileWriter> file_writer;
     {
       unique_ptr<WritableFile> file;
-#ifndef NDEBUG
-      bool use_direct_writes = env_options.use_direct_writes;
-      TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
-#endif  // !NDEBUG
       s = NewWritableFile(env, fname, &file, env_options);
       if (!s.ok()) {
         EventHelpers::LogAndNotifyTableFileCreationFinished(
@@ -117,15 +111,14 @@ 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, nullptr /* compression_dict */,
-          false /* skip_filters */, creation_time, oldest_key_time);
+          compression_opts, level);
     }
 
     MergeHelper merge(env, internal_comparator.user_comparator(),
@@ -135,7 +128,7 @@ Status BuildTable(
 
     CompactionIterator c_iter(
         iter, internal_comparator.user_comparator(), &merge, kMaxSequenceNumber,
-        &snapshots, earliest_write_conflict_snapshot, snapshot_checker, env,
+        &snapshots, earliest_write_conflict_snapshot, env,
         true /* internal key corruption is not ok */, range_del_agg.get());
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
@@ -179,7 +172,7 @@ Status BuildTable(
     // Finish and check for file errors
     if (s.ok() && !empty) {
       StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
-      s = file_writer->Sync(ioptions.use_fsync);
+      file_writer->Sync(ioptions.use_fsync);
     }
     if (s.ok() && !empty) {
       s = file_writer->Close();
@@ -187,11 +180,6 @@ Status BuildTable(
 
     if (s.ok() && !empty) {
       // Verify that the table is usable
-      // We set for_compaction to false and don't OptimizeForCompactionTableRead
-      // here because this is a special case after we finish the table building
-      // No matter whether use_direct_io_for_flush_and_compaction is true,
-      // we will regrad this verification as user reads since the goal is
-      // to cache it here for further user reads
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
           ReadOptions(), env_options, internal_comparator, meta->fd,
           nullptr /* range_del_agg */, nullptr,

db/builder.h

@@ -10,7 +10,6 @@
 #include <utility>
 #include <vector>
 #include "db/table_properties_collector.h"
-#include "options/cf_options.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/env.h"
 #include "rocksdb/listener.h"
@@ -19,6 +18,7 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/cf_options.h"
 #include "util/event_logger.h"
 
 namespace rocksdb {
@@ -29,7 +29,6 @@ struct FileMetaData;
 class Env;
 struct EnvOptions;
 class Iterator;
-class SnapshotChecker;
 class TableCache;
 class VersionEdit;
 class TableBuilder;
@@ -49,10 +48,10 @@ 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 uint64_t creation_time = 0,
-    const uint64_t oldest_key_time = 0);
+    const bool skip_filters = false);
 
 // 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
@@ -73,13 +72,11 @@ extern Status BuildTable(
     uint32_t column_family_id, const std::string& column_family_name,
     std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
-    SnapshotChecker* snapshot_checker, const CompressionType compression,
+    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,
-    const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
-    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET);
+    TableProperties* table_properties = nullptr, int level = -1);
 
 }  // namespace rocksdb

db/c_test.c

@@ -20,7 +20,7 @@
 // Can not use port/port.h macros as this is a c file
 #ifdef OS_WIN
 
-#include <windows.h>
+#include <Windows.h>
 
 #define snprintf _snprintf
 
@@ -40,8 +40,6 @@ const char* phase = "";
 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);
@@ -89,16 +87,6 @@ static void Free(char** ptr) {
   }
 }
 
-static void CheckValue(
-    char* err,
-    const char* expected,
-    char** actual,
-    size_t actual_length) {
-  CheckNoError(err);
-  CheckEqual(expected, *actual, actual_length);
-  Free(actual);
-}
-
 static void CheckGet(
     rocksdb_t* db,
     const rocksdb_readoptions_t* options,
@@ -128,32 +116,6 @@ static void CheckGetCF(
   Free(&val);
 }
 
-static void CheckPinGet(rocksdb_t* db, const rocksdb_readoptions_t* options,
-                        const char* key, const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  const char* val;
-  rocksdb_pinnableslice_t* p;
-  p = rocksdb_get_pinned(db, options, key, strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
-
-static void CheckPinGetCF(rocksdb_t* db, const rocksdb_readoptions_t* options,
-                          rocksdb_column_family_handle_t* handle,
-                          const char* key, const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  const char* val;
-  rocksdb_pinnableslice_t* p;
-  p = rocksdb_get_pinned_cf(db, options, handle, key, strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
 
 static void CheckIter(rocksdb_iterator_t* iter,
                       const char* key, const char* val) {
@@ -320,67 +282,10 @@ static char* MergeOperatorPartialMerge(
   return result;
 }
 
-static void CheckTxnGet(
-        rocksdb_transaction_t* txn,
-        const rocksdb_readoptions_t* options,
-        const char* key,
-        const char* expected) {
-        char* err = NULL;
-        size_t val_len;
-        char* val;
-        val = rocksdb_transaction_get(txn, options, key, strlen(key), &val_len, &err);
-        CheckNoError(err);
-        CheckEqual(expected, val, val_len);
-        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,
-        const char* key,
-        const char* expected) {
-        char* err = NULL;
-        size_t val_len;
-        char* val;
-        val = rocksdb_transactiondb_get(txn_db, options, key, strlen(key), &val_len, &err);
-        CheckNoError(err);
-        CheckEqual(expected, val, val_len);
-        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;
@@ -388,12 +293,6 @@ int main(int argc, char** argv) {
   rocksdb_readoptions_t* roptions;
   rocksdb_writeoptions_t* woptions;
   rocksdb_ratelimiter_t* rate_limiter;
-  rocksdb_transactiondb_t* txn_db;
-  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;
 
@@ -407,24 +306,13 @@ int main(int argc, char** argv) {
            GetTempDir(),
            ((int) geteuid()));
 
-  snprintf(dbcheckpointname, sizeof(dbcheckpointname),
-           "%s/rocksdb_c_test-%d-checkpoint",
-           GetTempDir(),
-           ((int) geteuid()));
-
   snprintf(sstfilename, sizeof(sstfilename),
            "%s/rocksdb_c_test-%d-sst",
            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);
 
@@ -533,36 +421,6 @@ int main(int argc, char** argv) {
     rocksdb_backup_engine_close(be);
   }
 
-  StartPhase("checkpoint");
-  {
-    rocksdb_destroy_db(options, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_t* checkpoint = rocksdb_checkpoint_object_create(db, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_create(checkpoint, dbcheckpointname, 0, &err);
-    CheckNoError(err);
-
-    // start a new database from the checkpoint
-    rocksdb_close(db);
-    rocksdb_options_set_error_if_exists(options, 0);
-    db = rocksdb_open(options, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    CheckGet(db, roptions, "foo", "hello");
-
-    rocksdb_checkpoint_object_destroy(checkpoint);
-
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_options_set_error_if_exists(options, 1);
-  }
-
   StartPhase("compactall");
   rocksdb_compact_range(db, NULL, 0, NULL, 0);
   CheckGet(db, roptions, "foo", "hello");
@@ -607,11 +465,11 @@ int main(int argc, char** argv) {
     unlink(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk1", 5, "v1", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk1", 5, "v1", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v2", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v2", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk3", 5, "v3", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v3", 2, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_finish(writer, &err);
     CheckNoError(err);
@@ -628,11 +486,11 @@ int main(int argc, char** argv) {
     unlink(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v4", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v4", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk22", 6, "v5", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk22", 6, "v5", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk3", 5, "v6", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v6", 2, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_finish(writer, &err);
     CheckNoError(err);
@@ -719,13 +577,10 @@ int main(int argc, char** argv) {
   {
     rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
     rocksdb_writebatch_set_save_point(wb);
-    rocksdb_writebatch_set_save_point(wb);
     const char* k_list[2] = {"z", "ap"};
     const size_t k_sizes[2] = {1, 2};
     const char* v_list[3] = {"x", "y", "z"};
     const size_t v_sizes[3] = {1, 1, 1};
-    rocksdb_writebatch_pop_save_point(wb, &err);
-    CheckNoError(err);
     rocksdb_writebatch_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
     rocksdb_writebatch_rollback_to_save_point(wb, &err);
     CheckNoError(err);
@@ -753,90 +608,6 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_destroy(wb2);
   }
 
-  StartPhase("writebatch_wi");
-  {
-    rocksdb_writebatch_wi_t* wbi = rocksdb_writebatch_wi_create(0, 1);
-    rocksdb_writebatch_wi_put(wbi, "foo", 3, "a", 1);
-    rocksdb_writebatch_wi_clear(wbi);
-    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
-    rocksdb_writebatch_wi_put(wbi, "box", 3, "c", 1);
-    rocksdb_writebatch_wi_delete(wbi, "bar", 3);
-    int count = rocksdb_writebatch_wi_count(wbi);
-    CheckCondition(count == 3);
-    size_t size;
-    char* value;
-    value = rocksdb_writebatch_wi_get_from_batch(wbi, options, "box", 3, &size, &err);
-    CheckValue(err, "c", &value, size);
-    value = rocksdb_writebatch_wi_get_from_batch(wbi, options, "bar", 3, &size, &err);
-    CheckValue(err, NULL, &value, size);
-    value = rocksdb_writebatch_wi_get_from_batch_and_db(wbi, db, roptions, "foo", 3, &size, &err);
-    CheckValue(err, "hello", &value, size);
-    value = rocksdb_writebatch_wi_get_from_batch_and_db(wbi, db, roptions, "box", 3, &size, &err);
-    CheckValue(err, "c", &value, size);
-    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "foo", "hello");
-    CheckGet(db, roptions, "bar", NULL);
-    CheckGet(db, roptions, "box", "c");
-    int pos = 0;
-    rocksdb_writebatch_wi_iterate(wbi, &pos, CheckPut, CheckDel);
-    CheckCondition(pos == 3);
-    rocksdb_writebatch_wi_clear(wbi);
-    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
-    rocksdb_writebatch_wi_put(wbi, "bay", 3, "d", 1);
-    rocksdb_writebatch_wi_delete_range(wbi, "bar", 3, "bay", 3);
-    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "bar", NULL);
-    CheckGet(db, roptions, "bay", "d");
-    rocksdb_writebatch_wi_clear(wbi);
-    const char* start_list[1] = {"bay"};
-    const size_t start_sizes[1] = {3};
-    const char* end_list[1] = {"baz"};
-    const size_t end_sizes[1] = {3};
-    rocksdb_writebatch_wi_delete_rangev(wbi, 1, start_list, start_sizes, end_list,
-                                     end_sizes);
-    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "bay", NULL);
-    rocksdb_writebatch_wi_destroy(wbi);
-  }
-
-  StartPhase("writebatch_wi_vectors");
-  {
-    rocksdb_writebatch_wi_t* wb = rocksdb_writebatch_wi_create(0, 1);
-    const char* k_list[2] = { "z", "ap" };
-    const size_t k_sizes[2] = { 1, 2 };
-    const char* v_list[3] = { "x", "y", "z" };
-    const size_t v_sizes[3] = { 1, 1, 1 };
-    rocksdb_writebatch_wi_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
-    rocksdb_write_writebatch_wi(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "zap", "xyz");
-    rocksdb_writebatch_wi_delete(wb, "zap", 3);
-    rocksdb_write_writebatch_wi(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "zap", NULL);
-    rocksdb_writebatch_wi_destroy(wb);
-  }
-
-  StartPhase("writebatch_wi_savepoint");
-  {
-    rocksdb_writebatch_wi_t* wb = rocksdb_writebatch_wi_create(0, 1);
-    rocksdb_writebatch_wi_set_save_point(wb);
-    const char* k_list[2] = {"z", "ap"};
-    const size_t k_sizes[2] = {1, 2};
-    const char* v_list[3] = {"x", "y", "z"};
-    const size_t v_sizes[3] = {1, 1, 1};
-    rocksdb_writebatch_wi_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
-    rocksdb_writebatch_wi_rollback_to_save_point(wb, &err);
-    CheckNoError(err);
-    rocksdb_write_writebatch_wi(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "zap", NULL);
-    rocksdb_writebatch_wi_destroy(wb);
-  }
-
   StartPhase("iter");
   {
     rocksdb_iterator_t* iter = rocksdb_create_iterator(db, roptions);
@@ -863,37 +634,6 @@ int main(int argc, char** argv) {
     rocksdb_iter_destroy(iter);
   }
 
-  StartPhase("wbwi_iter");
-  {
-    rocksdb_iterator_t* base_iter = rocksdb_create_iterator(db, roptions);
-    rocksdb_writebatch_wi_t* wbi = rocksdb_writebatch_wi_create(0, 1);
-    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
-    rocksdb_writebatch_wi_delete(wbi, "foo", 3);
-    rocksdb_iterator_t* iter = rocksdb_writebatch_wi_create_iterator_with_base(wbi, base_iter);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-    CheckIter(iter, "bar", "b");
-    rocksdb_iter_next(iter);
-    CheckIter(iter, "box", "c");
-    rocksdb_iter_prev(iter);
-    CheckIter(iter, "bar", "b");
-    rocksdb_iter_prev(iter);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_last(iter);
-    CheckIter(iter, "box", "c");
-    rocksdb_iter_seek(iter, "b", 1);
-    CheckIter(iter, "bar", "b");
-    rocksdb_iter_seek_for_prev(iter, "c", 1);
-    CheckIter(iter, "box", "c");
-    rocksdb_iter_seek_for_prev(iter, "box", 3);
-    CheckIter(iter, "box", "c");
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-    rocksdb_writebatch_wi_destroy(wbi);
-  }
-
   StartPhase("multiget");
   {
     const char* keys[3] = { "box", "foo", "notfound" };
@@ -921,13 +661,6 @@ int main(int argc, char** argv) {
     }
   }
 
-  StartPhase("pin_get");
-  {
-    CheckPinGet(db, roptions, "box", "c");
-    CheckPinGet(db, roptions, "foo", "hello");
-    CheckPinGet(db, roptions, "notfound", NULL);
-  }
-
   StartPhase("approximate_sizes");
   {
     int i;
@@ -1139,13 +872,11 @@ int main(int argc, char** argv) {
     CheckNoError(err);
 
     CheckGetCF(db, roptions, handles[1], "foo", "hello");
-    CheckPinGetCF(db, roptions, handles[1], "foo", "hello");
 
     rocksdb_delete_cf(db, woptions, handles[1], "foo", 3, &err);
     CheckNoError(err);
 
     CheckGetCF(db, roptions, handles[1], "foo", NULL);
-    CheckPinGetCF(db, roptions, handles[1], "foo", NULL);
 
     rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
     rocksdb_writebatch_put_cf(wb, handles[1], "baz", 3, "a", 1);
@@ -1158,9 +889,6 @@ int main(int argc, char** argv) {
     CheckGetCF(db, roptions, handles[1], "baz", NULL);
     CheckGetCF(db, roptions, handles[1], "bar", NULL);
     CheckGetCF(db, roptions, handles[1], "box", "c");
-    CheckPinGetCF(db, roptions, handles[1], "baz", NULL);
-    CheckPinGetCF(db, roptions, handles[1], "bar", NULL);
-    CheckPinGetCF(db, roptions, handles[1], "box", "c");
     rocksdb_writebatch_destroy(wb);
 
     const char* keys[3] = { "box", "box", "barfooxx" };
@@ -1372,245 +1100,14 @@ int main(int argc, char** argv) {
     }
   }
 
-  StartPhase("transactions");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    // open a TransactionDB
-    txn_db_options = rocksdb_transactiondb_options_create();
-    txn_options = rocksdb_transaction_options_create();
-    rocksdb_options_set_create_if_missing(options, 1);
-    txn_db = rocksdb_transactiondb_open(options, txn_db_options, dbname, &err);
-    CheckNoError(err);
-
-    // put outside a transaction
-    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-
-    // delete from outside transaction
-    rocksdb_transactiondb_delete(txn_db, woptions, "foo", 3, &err);
-    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
-    rocksdb_transaction_put(txn, "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-    CheckTxnGet(txn, roptions, "foo", "hello");
-    // delete
-    rocksdb_transaction_delete(txn, "foo", 3, &err);
-    CheckNoError(err);
-    CheckTxnGet(txn, roptions, "foo", NULL);
-
-    rocksdb_transaction_put(txn, "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-
-    // read from outside transaction, before commit
-    CheckTxnDBGet(txn_db, roptions, "foo", NULL);
-
-    // commit
-    rocksdb_transaction_commit(txn, &err);
-    CheckNoError(err);
-
-    // read from outside transaction, after commit
-    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-
-    // reuse old transaction
-    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, txn);
-
-    // snapshot
-    const rocksdb_snapshot_t* snapshot;
-    snapshot = rocksdb_transactiondb_create_snapshot(txn_db);
-    rocksdb_readoptions_set_snapshot(roptions, snapshot);
-  
-    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hey", 3,  &err);
-    CheckNoError(err);
-
-    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-    rocksdb_readoptions_set_snapshot(roptions, NULL);
-    rocksdb_transactiondb_release_snapshot(txn_db, snapshot);
-    CheckTxnDBGet(txn_db, roptions, "foo", "hey");
-
-    // iterate
-    rocksdb_transaction_put(txn, "bar", 3, "hi", 2, &err);
-    rocksdb_iterator_t* iter = rocksdb_transaction_create_iterator(txn, roptions);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-    CheckIter(iter, "bar", "hi");
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-
-    // rollback
-    rocksdb_transaction_rollback(txn, &err);
-    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);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_transaction_options_destroy(txn_options);
-    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");
   {
     // Create database with vector memtable.
+    rocksdb_close(db);
+    rocksdb_destroy_db(options, dbname, &err);
+    CheckNoError(err);
+
     rocksdb_options_set_memtable_vector_rep(options);
     db = rocksdb_open(options, dbname, &err);
     CheckNoError(err);
@@ -1625,18 +1122,6 @@ 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);
@@ -1646,7 +1131,6 @@ 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");

db/column_family.cc

@@ -20,7 +20,6 @@
 #include <limits>
 
 #include "db/compaction_picker.h"
-#include "db/compaction_picker_universal.h"
 #include "db/db_impl.h"
 #include "db/internal_stats.h"
 #include "db/job_context.h"
@@ -28,11 +27,11 @@
 #include "db/version_set.h"
 #include "db/write_controller.h"
 #include "memtable/hash_skiplist_rep.h"
-#include "monitoring/thread_status_util.h"
-#include "options/options_helper.h"
 #include "table/block_based_table_factory.h"
 #include "util/autovector.h"
 #include "util/compression.h"
+#include "util/options_helper.h"
+#include "util/thread_status_util.h"
 
 namespace rocksdb {
 
@@ -123,22 +122,6 @@ 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();
 }
 
@@ -186,12 +169,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
       result.num_levels < 2) {
     result.num_levels = 2;
   }
-
-  if (result.compaction_style == kCompactionStyleUniversal &&
-      db_options.allow_ingest_behind && result.num_levels < 3) {
-    result.num_levels = 3;
-  }
-
   if (result.max_write_buffer_number < 2) {
     result.max_write_buffer_number = 2;
   }
@@ -218,6 +195,7 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     result.num_levels = 1;
     // since we delete level0 files in FIFO compaction when there are too many
     // of them, these options don't really mean anything
+    result.level0_file_num_compaction_trigger = std::numeric_limits<int>::max();
     result.level0_slowdown_writes_trigger = std::numeric_limits<int>::max();
     result.level0_stop_writes_trigger = std::numeric_limits<int>::max();
   }
@@ -227,8 +205,8 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
   }
 
   if (result.level0_file_num_compaction_trigger == 0) {
-    ROCKS_LOG_WARN(db_options.info_log.get(),
-                   "level0_file_num_compaction_trigger cannot be 0");
+    Warn(db_options.info_log.get(),
+         "level0_file_num_compaction_trigger cannot be 0");
     result.level0_file_num_compaction_trigger = 1;
   }
 
@@ -236,14 +214,14 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
           result.level0_slowdown_writes_trigger ||
       result.level0_slowdown_writes_trigger <
           result.level0_file_num_compaction_trigger) {
-    ROCKS_LOG_WARN(db_options.info_log.get(),
-                   "This condition must be satisfied: "
-                   "level0_stop_writes_trigger(%d) >= "
-                   "level0_slowdown_writes_trigger(%d) >= "
-                   "level0_file_num_compaction_trigger(%d)",
-                   result.level0_stop_writes_trigger,
-                   result.level0_slowdown_writes_trigger,
-                   result.level0_file_num_compaction_trigger);
+    Warn(db_options.info_log.get(),
+         "This condition must be satisfied: "
+         "level0_stop_writes_trigger(%d) >= "
+         "level0_slowdown_writes_trigger(%d) >= "
+         "level0_file_num_compaction_trigger(%d)",
+         result.level0_stop_writes_trigger,
+         result.level0_slowdown_writes_trigger,
+         result.level0_file_num_compaction_trigger);
     if (result.level0_slowdown_writes_trigger <
         result.level0_file_num_compaction_trigger) {
       result.level0_slowdown_writes_trigger =
@@ -253,14 +231,14 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
         result.level0_slowdown_writes_trigger) {
       result.level0_stop_writes_trigger = result.level0_slowdown_writes_trigger;
     }
-    ROCKS_LOG_WARN(db_options.info_log.get(),
-                   "Adjust the value to "
-                   "level0_stop_writes_trigger(%d)"
-                   "level0_slowdown_writes_trigger(%d)"
-                   "level0_file_num_compaction_trigger(%d)",
-                   result.level0_stop_writes_trigger,
-                   result.level0_slowdown_writes_trigger,
-                   result.level0_file_num_compaction_trigger);
+    Warn(db_options.info_log.get(),
+         "Adjust the value to "
+         "level0_stop_writes_trigger(%d)"
+         "level0_slowdown_writes_trigger(%d)"
+         "level0_file_num_compaction_trigger(%d)",
+         result.level0_stop_writes_trigger,
+         result.level0_slowdown_writes_trigger,
+         result.level0_file_num_compaction_trigger);
   }
 
   if (result.soft_pending_compaction_bytes_limit == 0) {
@@ -363,14 +341,13 @@ 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_(
-          cf_options.table_factory->IsDeleteRangeSupported()),
+      is_delete_range_supported_(strcmp(cf_options.table_factory->Name(),
+                                        BlockBasedTableFactory().Name()) == 0),
       write_buffer_manager_(write_buffer_manager),
       mem_(nullptr),
       imm_(ioptions_.min_write_buffer_number_to_merge,
@@ -385,8 +362,7 @@ ColumnFamilyData::ColumnFamilyData(
       pending_flush_(false),
       pending_compaction_(false),
       prev_compaction_needed_bytes_(0),
-      allow_2pc_(db_options.allow_2pc),
-      last_memtable_id_(0) {
+      allow_2pc_(db_options.allow_2pc) {
   Ref();
 
   // Convert user defined table properties collector factories to internal ones.
@@ -410,27 +386,27 @@ ColumnFamilyData::ColumnFamilyData(
     } else if (ioptions_.compaction_style == kCompactionStyleNone) {
       compaction_picker_.reset(new NullCompactionPicker(
           ioptions_, &internal_comparator_));
-      ROCKS_LOG_WARN(ioptions_.info_log,
-                     "Column family %s does not use any background compaction. "
-                     "Compactions can only be done via CompactFiles\n",
-                     GetName().c_str());
+      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
+          "Column family %s does not use any background compaction. "
+          "Compactions can only be done via CompactFiles\n",
+          GetName().c_str());
 #endif  // !ROCKSDB_LITE
     } else {
-      ROCKS_LOG_ERROR(ioptions_.info_log,
-                      "Unable to recognize the specified compaction style %d. "
-                      "Column family %s will use kCompactionStyleLevel.\n",
-                      ioptions_.compaction_style, GetName().c_str());
+      Log(InfoLogLevel::ERROR_LEVEL, ioptions_.info_log,
+          "Unable to recognize the specified compaction style %d. "
+          "Column family %s will use kCompactionStyleLevel.\n",
+          ioptions_.compaction_style, GetName().c_str());
       compaction_picker_.reset(
           new LevelCompactionPicker(ioptions_, &internal_comparator_));
     }
 
     if (column_family_set_->NumberOfColumnFamilies() < 10) {
-      ROCKS_LOG_INFO(ioptions_.info_log,
-                     "--------------- Options for column family [%s]:\n",
-                     name.c_str());
+      Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
+          "--------------- Options for column family [%s]:\n", name.c_str());
       initial_cf_options_.Dump(ioptions_.info_log);
     } else {
-      ROCKS_LOG_INFO(ioptions_.info_log, "\t(skipping printing options)\n");
+      Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
+          "\t(skipping printing options)\n");
     }
   }
 
@@ -480,8 +456,7 @@ ColumnFamilyData::~ColumnFamilyData() {
   if (dummy_versions_ != nullptr) {
     // List must be empty
     assert(dummy_versions_->TEST_Next() == dummy_versions_);
-    bool deleted __attribute__((unused));
-    deleted = dummy_versions_->Unref();
+    bool deleted __attribute__((unused)) = dummy_versions_->Unref();
     assert(deleted);
   }
 
@@ -568,7 +543,7 @@ 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 aggressive slowdown.
+      // Penalize the near stop or stop condition by more agressive slowdown.
       // This is to provide the long term slowdown increase signal.
       // The penalty is more than the reward of recovering to the normal
       // condition.
@@ -631,9 +606,8 @@ int GetL0ThresholdSpeedupCompaction(int level0_file_num_compaction_trigger,
 }
 }  // namespace
 
-WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
+void 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_;
@@ -645,10 +619,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
 
     if (imm()->NumNotFlushed() >= mutable_cf_options.max_write_buffer_number) {
       write_controller_token_ = write_controller->GetStopToken();
-      internal_stats_->AddCFStats(InternalStats::MEMTABLE_LIMIT_STOPS, 1);
-      write_stall_condition = WriteStallCondition::kStopped;
-      ROCKS_LOG_WARN(
-          ioptions_.info_log,
+      internal_stats_->AddCFStats(InternalStats::MEMTABLE_COMPACTION, 1);
+      Log(InfoLogLevel::WARN_LEVEL, 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(),
@@ -657,25 +629,22 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
                vstorage->l0_delay_trigger_count() >=
                    mutable_cf_options.level0_stop_writes_trigger) {
       write_controller_token_ = write_controller->GetStopToken();
-      internal_stats_->AddCFStats(InternalStats::L0_FILE_COUNT_LIMIT_STOPS, 1);
-      write_stall_condition = WriteStallCondition::kStopped;
+      internal_stats_->AddCFStats(InternalStats::LEVEL0_NUM_FILES_TOTAL, 1);
       if (compaction_picker_->IsLevel0CompactionInProgress()) {
         internal_stats_->AddCFStats(
-            InternalStats::LOCKED_L0_FILE_COUNT_LIMIT_STOPS, 1);
+            InternalStats::LEVEL0_NUM_FILES_WITH_COMPACTION, 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());
+      Log(InfoLogLevel::WARN_LEVEL, 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) {
       write_controller_token_ = write_controller->GetStopToken();
       internal_stats_->AddCFStats(
-          InternalStats::PENDING_COMPACTION_BYTES_LIMIT_STOPS, 1);
-      write_stall_condition = WriteStallCondition::kStopped;
-      ROCKS_LOG_WARN(
-          ioptions_.info_log,
+          InternalStats::HARD_PENDING_COMPACTION_BYTES_LIMIT, 1);
+      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
           "[%s] Stopping writes because of estimated pending compaction "
           "bytes %" PRIu64,
           name_.c_str(), compaction_needed_bytes);
@@ -686,10 +655,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
           SetupDelay(write_controller, compaction_needed_bytes,
                      prev_compaction_needed_bytes_, was_stopped,
                      mutable_cf_options.disable_auto_compactions);
-      internal_stats_->AddCFStats(InternalStats::MEMTABLE_LIMIT_SLOWDOWNS, 1);
-      write_stall_condition = WriteStallCondition::kDelayed;
-      ROCKS_LOG_WARN(
-          ioptions_.info_log,
+      internal_stats_->AddCFStats(InternalStats::MEMTABLE_SLOWDOWN, 1);
+      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
           "[%s] Stalling writes because we have %d immutable memtables "
           "(waiting for flush), max_write_buffer_number is set to %d "
           "rate %" PRIu64,
@@ -707,18 +674,16 @@ WriteStallCondition 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::L0_FILE_COUNT_LIMIT_SLOWDOWNS,
-                                  1);
-      write_stall_condition = WriteStallCondition::kDelayed;
+      internal_stats_->AddCFStats(InternalStats::LEVEL0_SLOWDOWN_TOTAL, 1);
       if (compaction_picker_->IsLevel0CompactionInProgress()) {
         internal_stats_->AddCFStats(
-            InternalStats::LOCKED_L0_FILE_COUNT_LIMIT_SLOWDOWNS, 1);
+            InternalStats::LEVEL0_SLOWDOWN_WITH_COMPACTION, 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());
+      Log(InfoLogLevel::WARN_LEVEL, 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() >=
@@ -739,10 +704,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
                      prev_compaction_needed_bytes_, was_stopped || near_stop,
                      mutable_cf_options.disable_auto_compactions);
       internal_stats_->AddCFStats(
-          InternalStats::PENDING_COMPACTION_BYTES_LIMIT_SLOWDOWNS, 1);
-      write_stall_condition = WriteStallCondition::kDelayed;
-      ROCKS_LOG_WARN(
-          ioptions_.info_log,
+          InternalStats::SOFT_PENDING_COMPACTION_BYTES_LIMIT, 1);
+      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
           "[%s] Stalling writes because of estimated pending compaction "
           "bytes %" PRIu64 " rate %" PRIu64,
           name_.c_str(), vstorage->estimated_compaction_needed_bytes(),
@@ -754,8 +717,7 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
               mutable_cf_options.level0_slowdown_writes_trigger)) {
         write_controller_token_ =
             write_controller->GetCompactionPressureToken();
-        ROCKS_LOG_INFO(
-            ioptions_.info_log,
+        Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
             "[%s] Increasing compaction threads because we have %d level-0 "
             "files ",
             name_.c_str(), vstorage->l0_delay_trigger_count());
@@ -768,8 +730,7 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
         write_controller_token_ =
             write_controller->GetCompactionPressureToken();
         if (mutable_cf_options.soft_pending_compaction_bytes_limit > 0) {
-          ROCKS_LOG_INFO(
-              ioptions_.info_log,
+          Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
               "[%s] Increasing compaction threads because of estimated pending "
               "compaction "
               "bytes %" PRIu64,
@@ -785,17 +746,10 @@ WriteStallCondition 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 {
@@ -816,8 +770,9 @@ uint64_t ColumnFamilyData::GetTotalSstFilesSize() const {
 
 MemTable* ColumnFamilyData::ConstructNewMemtable(
     const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
+  assert(current_ != nullptr);
   return new MemTable(internal_comparator_, ioptions_, mutable_cf_options,
-                      write_buffer_manager_, earliest_seq, id_);
+                      write_buffer_manager_, earliest_seq);
 }
 
 void ColumnFamilyData::CreateNewMemtable(
@@ -872,10 +827,6 @@ SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
   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;
@@ -945,16 +896,15 @@ bool ColumnFamilyData::ReturnThreadLocalSuperVersion(SuperVersion* sv) {
   return false;
 }
 
-void ColumnFamilyData::InstallSuperVersion(
-    SuperVersionContext* sv_context, InstrumentedMutex* db_mutex) {
+SuperVersion* ColumnFamilyData::InstallSuperVersion(
+    SuperVersion* new_superversion, InstrumentedMutex* db_mutex) {
   db_mutex->AssertHeld();
-  return InstallSuperVersion(sv_context, db_mutex, mutable_cf_options_);
+  return InstallSuperVersion(new_superversion, db_mutex, mutable_cf_options_);
 }
 
-void ColumnFamilyData::InstallSuperVersion(
-    SuperVersionContext* sv_context, InstrumentedMutex* db_mutex,
+SuperVersion* ColumnFamilyData::InstallSuperVersion(
+    SuperVersion* new_superversion, 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_);
@@ -962,28 +912,16 @@ void ColumnFamilyData::InstallSuperVersion(
   super_version_ = new_superversion;
   ++super_version_number_;
   super_version_->version_number = super_version_number_;
-  super_version_->write_stall_condition =
-      RecalculateWriteStallConditions(mutable_cf_options);
-
-  if (old_superversion != nullptr) {
-    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);
-    }
-  }
-
   // Reset SuperVersions cached in thread local storage
   ResetThreadLocalSuperVersions();
+
+  RecalculateWriteStallConditions(mutable_cf_options);
+
+  if (old_superversion != nullptr && old_superversion->Unref()) {
+    old_superversion->Cleanup();
+    return old_superversion;  // will let caller delete outside of mutex
+  }
+  return nullptr;
 }
 
 void ColumnFamilyData::ResetThreadLocalSuperVersions() {
@@ -1016,24 +954,6 @@ 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,
@@ -1060,12 +980,10 @@ ColumnFamilySet::~ColumnFamilySet() {
   while (column_family_data_.size() > 0) {
     // cfd destructor will delete itself from column_family_data_
     auto cfd = column_family_data_.begin()->second;
-    bool last_ref __attribute__((__unused__)) = cfd->Unref();
-    assert(last_ref);
+    cfd->Unref();
     delete cfd;
   }
-  bool dummy_last_ref __attribute__((__unused__)) = dummy_cfd_->Unref();
-  assert(dummy_last_ref);
+  dummy_cfd_->Unref();
   delete dummy_cfd_;
 }
 

db/column_family.h

@@ -19,11 +19,11 @@
 #include "db/table_properties_collector.h"
 #include "db/write_batch_internal.h"
 #include "db/write_controller.h"
-#include "options/cf_options.h"
 #include "rocksdb/compaction_job_stats.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
+#include "util/cf_options.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
@@ -41,7 +41,6 @@ class DBImpl;
 class LogBuffer;
 class InstrumentedMutex;
 class InstrumentedMutexLock;
-struct SuperVersionContext;
 
 extern const double kIncSlowdownRatio;
 
@@ -77,7 +76,7 @@ class ColumnFamilyHandleImpl : public ColumnFamilyHandle {
 class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
  public:
   ColumnFamilyHandleInternal()
-      : ColumnFamilyHandleImpl(nullptr, nullptr, nullptr), internal_cfd_(nullptr) {}
+      : ColumnFamilyHandleImpl(nullptr, nullptr, nullptr) {}
 
   void SetCFD(ColumnFamilyData* _cfd) { internal_cfd_ = _cfd; }
   virtual ColumnFamilyData* cfd() const override { return internal_cfd_; }
@@ -96,7 +95,6 @@ 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 +192,7 @@ 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_.load(std::memory_order_relaxed); }
+  bool IsDropped() const { return dropped_; }
 
   // thread-safe
   int NumberLevels() const { return ioptions_.num_levels; }
@@ -239,11 +237,7 @@ 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) {
-    uint64_t memtable_id = last_memtable_id_.fetch_add(1) + 1;
-    new_mem->SetID(memtable_id);
-    mem_ = new_mem;
-  }
+  void SetMemtable(MemTable* new_mem) { mem_ = new_mem; }
 
   // calculate the oldest log needed for the durability of this column family
   uint64_t OldestLogToKeep();
@@ -270,7 +264,7 @@ class ColumnFamilyData {
                                   int level) const;
 
   // A flag to tell a manual compaction is to compact all levels together
-  // instead of a specific level.
+  // instad of for specific level.
   static const int kCompactAllLevels;
   // A flag to tell a manual compaction's output is base level.
   static const int kCompactToBaseLevel;
@@ -317,11 +311,11 @@ 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()
-  void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex,
-                           const MutableCFOptions& mutable_cf_options);
-  void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex);
+  SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
+                                    InstrumentedMutex* db_mutex,
+                                    const MutableCFOptions& mutable_cf_options);
+  SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
+                                    InstrumentedMutex* db_mutex);
 
   void ResetThreadLocalSuperVersions();
 
@@ -336,15 +330,9 @@ class ColumnFamilyData {
   // recalculation of compaction score. These values are used in
   // DBImpl::MakeRoomForWrite function to decide, if it need to make
   // a write stall
-  WriteStallCondition RecalculateWriteStallConditions(
+  void 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,
@@ -361,8 +349,7 @@ class ColumnFamilyData {
   Version* current_;         // == dummy_versions->prev_
 
   std::atomic<int> refs_;      // outstanding references to ColumnFamilyData
-  std::atomic<bool> initialized_;
-  std::atomic<bool> dropped_;  // true if client dropped it
+  bool dropped_;               // true if client dropped it
 
   const InternalKeyComparator internal_comparator_;
   std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
@@ -423,9 +410,6 @@ 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

db/column_family_test.cc

@@ -14,13 +14,13 @@
 
 #include "db/db_impl.h"
 #include "db/db_test_util.h"
-#include "options/options_parser.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
 #include "util/coding.h"
 #include "util/fault_injection_test_env.h"
+#include "util/options_parser.h"
 #include "util/string_util.h"
 #include "util/sync_point.h"
 #include "util/testharness.h"
@@ -54,7 +54,7 @@ class EnvCounter : public EnvWrapper {
   }
 
  private:
-  std::atomic<int> num_new_writable_file_;
+  int num_new_writable_file_;
 };
 
 class ColumnFamilyTest : public testing::Test {
@@ -302,7 +302,6 @@ 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
@@ -521,30 +520,6 @@ 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:
@@ -582,7 +557,6 @@ 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);
@@ -645,7 +619,6 @@ 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;
@@ -702,44 +675,6 @@ TEST_F(ColumnFamilyTest, AddDrop) {
               std::vector<std::string>({"default", "four", "three"}));
 }
 
-TEST_F(ColumnFamilyTest, BulkAddDrop) {
-  constexpr int kNumCF = 1000;
-  ColumnFamilyOptions cf_options;
-  WriteOptions write_options;
-  Open();
-  std::vector<std::string> cf_names;
-  std::vector<ColumnFamilyHandle*> cf_handles;
-  for (int i = 1; i <= kNumCF; i++) {
-    cf_names.push_back("cf1-" + ToString(i));
-  }
-  ASSERT_OK(db_->CreateColumnFamilies(cf_options, cf_names, &cf_handles));
-  for (int i = 1; i <= kNumCF; i++) {
-    ASSERT_OK(db_->Put(write_options, cf_handles[i - 1], "foo", "bar"));
-  }
-  ASSERT_OK(db_->DropColumnFamilies(cf_handles));
-  std::vector<ColumnFamilyDescriptor> cf_descriptors;
-  for (auto* handle : cf_handles) {
-    delete handle;
-  }
-  cf_handles.clear();
-  for (int i = 1; i <= kNumCF; i++) {
-    cf_descriptors.emplace_back("cf2-" + ToString(i), ColumnFamilyOptions());
-  }
-  ASSERT_OK(db_->CreateColumnFamilies(cf_descriptors, &cf_handles));
-  for (int i = 1; i <= kNumCF; i++) {
-    ASSERT_OK(db_->Put(write_options, cf_handles[i - 1], "foo", "bar"));
-  }
-  ASSERT_OK(db_->DropColumnFamilies(cf_handles));
-  for (auto* handle : cf_handles) {
-    delete handle;
-  }
-  Close();
-  std::vector<std::string> families;
-  ASSERT_OK(DB::ListColumnFamilies(db_options_, dbname_, &families));
-  std::sort(families.begin(), families.end());
-  ASSERT_TRUE(families == std::vector<std::string>({"default"}));
-}
-
 TEST_F(ColumnFamilyTest, DropTest) {
   // first iteration - dont reopen DB before dropping
   // second iteration - reopen DB before dropping
@@ -933,62 +868,62 @@ 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 = 128000;  // 128KB
+  column_family_options_.write_buffer_size = 100000;  // 100KB
   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, 128);
+  PutRandomData(0, 1, 100);
   // [0]
-  PutRandomData(1, 1, 128);
+  PutRandomData(1, 1, 100);
   // [0, 1]
-  PutRandomData(1, 1000, 128);
+  PutRandomData(1, 1000, 100);
   WaitForFlush(1);
   // [0, (1)] [1]
   AssertCountLiveLogFiles(2);
-  PutRandomData(0, 1, 128);
+  PutRandomData(0, 1, 100);
   // [0, (1)] [0, 1]
   AssertCountLiveLogFiles(2);
-  PutRandomData(2, 1, 128);
+  PutRandomData(2, 1, 100);
   // [0, (1)] [0, 1, 2]
-  PutRandomData(2, 1000, 128);
+  PutRandomData(2, 1000, 100);
   WaitForFlush(2);
   // [0, (1)] [0, 1, (2)] [2]
   AssertCountLiveLogFiles(3);
-  PutRandomData(2, 1000, 128);
+  PutRandomData(2, 1000, 100);
   WaitForFlush(2);
   // [0, (1)] [0, 1, (2)] [(2)] [2]
   AssertCountLiveLogFiles(4);
-  PutRandomData(3, 1, 128);
+  PutRandomData(3, 1, 100);
   // [0, (1)] [0, 1, (2)] [(2)] [2, 3]
-  PutRandomData(1, 1, 128);
+  PutRandomData(1, 1, 100);
   // [0, (1)] [0, 1, (2)] [(2)] [1, 2, 3]
   AssertCountLiveLogFiles(4);
-  PutRandomData(1, 1000, 128);
+  PutRandomData(1, 1000, 100);
   WaitForFlush(1);
   // [0, (1)] [0, (1), (2)] [(2)] [(1), 2, 3] [1]
   AssertCountLiveLogFiles(5);
-  PutRandomData(0, 1000, 128);
+  PutRandomData(0, 1000, 100);
   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, 128);
+  PutRandomData(0, 1000, 100);
   WaitForFlush(0);
   // [(1), 2, 3] [1, (0)], [(0)] [0]
   AssertCountLiveLogFiles(4);
-  PutRandomData(1, 1000, 128);
+  PutRandomData(1, 1000, 100);
   WaitForFlush(1);
   // [(1), 2, 3] [(1), (0)] [(0)] [0, (1)] [1]
   AssertCountLiveLogFiles(5);
-  PutRandomData(2, 1000, 128);
+  PutRandomData(2, 1000, 100);
   WaitForFlush(2);
   // [(1), (2), 3] [(1), (0)] [(0)] [0, (1)] [1, (2)], [2]
   AssertCountLiveLogFiles(6);
-  PutRandomData(3, 1000, 128);
+  PutRandomData(3, 1000, 100);
   WaitForFlush(3);
   // [(1), (2), (3)] [(1), (0)] [(0)] [0, (1)] [1, (2)], [2, (3)] [3]
   // delete obsolete logs -->
@@ -1406,6 +1341,7 @@ 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;
@@ -1429,9 +1365,6 @@ 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(
@@ -1491,6 +1424,7 @@ TEST_F(ColumnFamilyTest, AutomaticAndManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
+  Close();
 }
 
 TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
@@ -1499,6 +1433,7 @@ 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;
@@ -1522,9 +1457,6 @@ 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) {
@@ -1587,6 +1519,7 @@ TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
+  Close();
 }
 
 TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
@@ -1595,6 +1528,7 @@ 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;
@@ -1613,9 +1547,6 @@ 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) {
@@ -1686,6 +1617,7 @@ TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
+  Close();
 }
 
 TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
@@ -1694,6 +1626,7 @@ 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;
@@ -1712,9 +1645,6 @@ 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) {
@@ -1776,6 +1706,7 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
+  Close();
 }
 
 TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
@@ -1784,6 +1715,7 @@ 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;
@@ -1798,13 +1730,10 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
 
   one.num_levels = 1;
   // trigger compaction if there are >= 4 files
-  one.level0_file_num_compaction_trigger = 3;
+  one.level0_file_num_compaction_trigger = 4;
   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) {
@@ -1866,20 +1795,142 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
+  Close();
 }
 
-// In this test, we generate enough files to trigger automatic compactions.
-// The automatic compaction waits in NonTrivial:AfterRun
+// 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 the automatic compaction has files it needs.
-// Once the conflict is hit, the automatic compaction starts and ends
-// Then the manual will run and end.
-TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
+// 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.
+// The automatic compaction waits in NonTrivial:AfterRun
+// We generate more files and then trigger an automatic compaction
+// This will wait because the automatic compaction has files it needs.
+// Once the conflict is hit, the automatic compaction starts and ends
+// Then the manual will run and end.
+TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
+  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;
@@ -1898,9 +1949,6 @@ 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;
@@ -1955,6 +2003,8 @@ TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
+
+  Close();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -2407,6 +2457,7 @@ 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"});
@@ -2587,6 +2638,7 @@ TEST_F(ColumnFamilyTest, WriteStallSingleColumnFamily) {
 }
 
 TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
+  db_options_.base_background_compactions = 2;
   db_options_.max_background_compactions = 6;
   Open({"default"});
   ColumnFamilyData* cfd =
@@ -2606,7 +2658,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(40);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(50);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2618,11 +2670,11 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(45);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(7);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(9);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2630,7 +2682,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
 
   vstorage->set_l0_delay_trigger_count(6);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   // Speed up threshold = min(4 * 2, 4 + (12 - 4)/4) = 6
   mutable_cf_options.level0_file_num_compaction_trigger = 4;
@@ -2639,7 +2691,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
 
   vstorage->set_l0_delay_trigger_count(5);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(7);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2647,7 +2699,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
 
   vstorage->set_l0_delay_trigger_count(3);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 }
 
 TEST_F(ColumnFamilyTest, WriteStallTwoColumnFamilies) {
@@ -2726,6 +2778,7 @@ 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;
@@ -2753,11 +2806,11 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(40);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(60);
   cfd1->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
@@ -2775,7 +2828,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(3);
   cfd1->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(9);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
@@ -2787,7 +2840,7 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
 
   vstorage->set_l0_delay_trigger_count(0);
   cfd->RecalculateWriteStallConditions(mutable_cf_options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
+  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
 }
 
 #ifndef ROCKSDB_LITE

db/compacted_db_impl.cc

@@ -17,8 +17,7 @@ extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
 
 CompactedDBImpl::CompactedDBImpl(
   const DBOptions& options, const std::string& dbname)
-  : DBImpl(options, dbname), cfd_(nullptr), version_(nullptr),
-    user_comparator_(nullptr) {
+  : DBImpl(options, dbname) {
 }
 
 CompactedDBImpl::~CompactedDBImpl() {
@@ -43,8 +42,8 @@ size_t CompactedDBImpl::FindFile(const Slice& key) {
   return right;
 }
 
-Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
-                            const Slice& key, PinnableSlice* value) {
+Status CompactedDBImpl::Get(const ReadOptions& options,
+     ColumnFamilyHandle*, const Slice& key, std::string* value) {
   GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                          GetContext::kNotFound, key, value, nullptr, nullptr,
                          nullptr, nullptr);
@@ -76,14 +75,11 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
   int idx = 0;
   for (auto* r : reader_list) {
     if (r != nullptr) {
-      PinnableSlice pinnable_val;
-      std::string& value = (*values)[idx];
       GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
-                             GetContext::kNotFound, keys[idx], &pinnable_val,
+                             GetContext::kNotFound, keys[idx], &(*values)[idx],
                              nullptr, nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
       r->Get(options, lkey.internal_key(), &get_context);
-      value.assign(pinnable_val.data(), pinnable_val.size());
       if (get_context.State() == GetContext::kFound) {
         statuses[idx] = Status::OK();
       }
@@ -94,7 +90,6 @@ 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));
@@ -102,10 +97,9 @@ Status CompactedDBImpl::Init(const Options& options) {
   if (s.ok()) {
     cfd_ = reinterpret_cast<ColumnFamilyHandleImpl*>(
               DefaultColumnFamily())->cfd();
-    cfd_->InstallSuperVersion(&sv_context, &mutex_);
+    delete cfd_->InstallSuperVersion(new SuperVersion(), &mutex_);
   }
   mutex_.Unlock();
-  sv_context.Clean();
   if (!s.ok()) {
     return s;
   }
@@ -157,8 +151,8 @@ Status CompactedDBImpl::Open(const Options& options,
   std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
   Status s = db->Init(options);
   if (s.ok()) {
-    ROCKS_LOG_INFO(db->immutable_db_options_.info_log,
-                   "Opened the db as fully compacted mode");
+    Log(INFO_LEVEL, db->immutable_db_options_.info_log,
+        "Opened the db as fully compacted mode");
     LogFlush(db->immutable_db_options_.info_log);
     *dbptr = db.release();
   }

db/compacted_db_impl.h

@@ -23,7 +23,7 @@ class CompactedDBImpl : public DBImpl {
   using DB::Get;
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
-                     PinnableSlice* value) override;
+                     std::string* value) override;
   using DB::MultiGet;
   virtual std::vector<Status> MultiGet(
       const ReadOptions& options,

db/compaction.cc

@@ -18,7 +18,7 @@
 
 #include "db/column_family.h"
 #include "rocksdb/compaction_filter.h"
-#include "util/string_util.h"
+#include "util/logging.h"
 #include "util/sync_point.h"
 
 namespace rocksdb {
@@ -86,23 +86,35 @@ void Compaction::GetBoundaryKeys(
 bool Compaction::IsBottommostLevel(
     int output_level, VersionStorageInfo* vstorage,
     const std::vector<CompactionInputFiles>& inputs) {
-  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;
+  if (inputs[0].level == 0 &&
+      inputs[0].files.back() != vstorage->LevelFiles(0).back()) {
+    return false;
   }
+
   Slice smallest_key, largest_key;
   GetBoundaryKeys(vstorage, inputs, &smallest_key, &largest_key);
-  return !vstorage->RangeMightExistAfterSortedRun(smallest_key, largest_key,
-                                                  output_level, output_l0_idx);
+
+  // 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;
 }
 
 // test function to validate the functionality of IsBottommostLevel()
@@ -157,7 +169,6 @@ 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_) {
@@ -229,7 +240,7 @@ bool Compaction::IsTrivialMove() const {
 
   // Used in universal compaction, where trivial move can be done if the
   // input files are non overlapping
-  if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
+  if ((immutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
       (output_level_ != 0)) {
     return is_trivial_move_;
   }
@@ -272,31 +283,28 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   assert(input_version_ != nullptr);
   assert(level_ptrs != nullptr);
   assert(level_ptrs->size() == static_cast<size_t>(number_levels_));
-  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;
+  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;
         }
+        break;
       }
     }
-    return true;
   }
-  return false;
+  return true;
 }
 
 // Mark (or clear) each file that is being compacted
@@ -405,23 +413,19 @@ void Compaction::Summary(char* output, int len) {
 uint64_t Compaction::OutputFilePreallocationSize() const {
   uint64_t preallocation_size = 0;
 
-  for (const auto& level_files : inputs_) {
-    for (const auto& file : level_files.files) {
-      preallocation_size += file->fd.GetFileSize();
+  if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel ||
+      output_level() > 0) {
+    preallocation_size = max_output_file_size_;
+  } else {
+    // output_level() == 0
+    assert(num_input_levels() > 0);
+    for (const auto& f : inputs_[0].files) {
+      preallocation_size += f->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
-  // No point to prellocate more than 1GB.
-  return std::min(uint64_t{1073741824},
-                  preallocation_size + (preallocation_size / 10));
+  return preallocation_size + (preallocation_size / 10);
 }
 
 std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
@@ -446,7 +450,7 @@ bool Compaction::ShouldFormSubcompactions() const {
     return false;
   }
   if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
-    return start_level_ == 0 && output_level_ > 0 && !IsOutputLevelEmpty();
+    return start_level_ == 0 && !IsOutputLevelEmpty();
   } else if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
     return number_levels_ > 1 && output_level_ > 0;
   } else {
@@ -454,17 +458,4 @@ 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

db/compaction.h

@@ -9,9 +9,9 @@
 
 #pragma once
 #include "db/version_set.h"
-#include "options/cf_options.h"
 #include "util/arena.h"
 #include "util/autovector.h"
+#include "util/cf_options.h"
 
 namespace rocksdb {
 
@@ -99,8 +99,7 @@ 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 {
+  const std::vector<FileMetaData*>* inputs(size_t compaction_input_level) {
     assert(compaction_input_level < inputs_.size());
     return &inputs_[compaction_input_level].files;
   }
@@ -241,8 +240,6 @@ 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);

db/compaction_iteration_stats.h

@@ -16,8 +16,6 @@ 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

db/compaction_iterator.cc

@@ -4,91 +4,45 @@
 //  (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"
 
 namespace rocksdb {
 
-#ifndef ROCKSDB_LITE
-CompactionEventListener::CompactionListenerValueType fromInternalValueType(
-    ValueType vt) {
-  switch (vt) {
-    case kTypeDeletion:
-      return CompactionEventListener::CompactionListenerValueType::kDelete;
-    case kTypeValue:
-      return CompactionEventListener::CompactionListenerValueType::kValue;
-    case kTypeMerge:
-      return CompactionEventListener::CompactionListenerValueType::
-          kMergeOperand;
-    case kTypeSingleDeletion:
-      return CompactionEventListener::CompactionListenerValueType::
-          kSingleDelete;
-    case kTypeRangeDeletion:
-      return CompactionEventListener::CompactionListenerValueType::kRangeDelete;
-    case kTypeBlobIndex:
-      return CompactionEventListener::CompactionListenerValueType::kBlobIndex;
-    default:
-      assert(false);
-      return CompactionEventListener::CompactionListenerValueType::kInvalid;
-  }
-}
-#endif  // ROCKSDB_LITE
-
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_write_conflict_snapshot,
-    const SnapshotChecker* snapshot_checker, Env* env,
+    SequenceNumber earliest_write_conflict_snapshot, 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 SequenceNumber preserve_deletes_seqnum)
+    const std::atomic<bool>* shutting_down)
     : CompactionIterator(
           input, cmp, merge_helper, last_sequence, snapshots,
-          earliest_write_conflict_snapshot, snapshot_checker, env,
-          expect_valid_internal_key, range_del_agg,
+          earliest_write_conflict_snapshot, env, expect_valid_internal_key,
+          range_del_agg,
           std::unique_ptr<CompactionProxy>(
               compaction ? new CompactionProxy(compaction) : nullptr),
-          compaction_filter, compaction_listener, shutting_down,
-          preserve_deletes_seqnum) {}
+          compaction_filter, shutting_down) {}
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_write_conflict_snapshot,
-    const SnapshotChecker* snapshot_checker, Env* env,
+    SequenceNumber earliest_write_conflict_snapshot, 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 SequenceNumber preserve_deletes_seqnum
-  )
+    const std::atomic<bool>* shutting_down)
     : 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),
-      current_user_key_sequence_(0),
-      current_user_key_snapshot_(0),
-      merge_out_iter_(merge_helper_),
-      current_key_committed_(false) {
+      merge_out_iter_(merge_helper_) {
   assert(compaction_filter_ == nullptr || compaction_ != nullptr);
   bottommost_level_ =
       compaction_ == nullptr ? false : compaction_->bottommost_level();
@@ -99,17 +53,15 @@ CompactionIterator::CompactionIterator(
   if (snapshots_->size() == 0) {
     // optimize for fast path if there are no snapshots
     visible_at_tip_ = true;
-    earliest_snapshot_ = kMaxSequenceNumber;
+    earliest_snapshot_ = last_sequence;
     latest_snapshot_ = 0;
   } else {
     visible_at_tip_ = false;
     earliest_snapshot_ = snapshots_->at(0);
     latest_snapshot_ = snapshots_->back();
   }
-  if (compaction_filter_ != nullptr) {
-    if (compaction_filter_->IgnoreSnapshots()) {
-      ignore_snapshots_ = true;
-    }
+  if (compaction_filter_ != nullptr && compaction_filter_->IgnoreSnapshots()) {
+    ignore_snapshots_ = true;
   } else {
     ignore_snapshots_ = false;
   }
@@ -127,7 +79,6 @@ 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() {
@@ -145,14 +96,14 @@ void CompactionIterator::Next() {
     if (merge_out_iter_.Valid()) {
       key_ = merge_out_iter_.key();
       value_ = merge_out_iter_.value();
-      bool valid_key __attribute__((__unused__));
-      valid_key =  ParseInternalKey(key_, &ikey_);
+      bool valid_key __attribute__((__unused__)) =
+          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);
       // Keep current_key_ in sync.
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      key_ = current_key_.GetInternalKey();
+      key_ = current_key_.GetKey();
       ikey_.user_key = current_key_.GetUserKey();
       valid_ = true;
     } else {
@@ -180,61 +131,6 @@ 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;
@@ -253,7 +149,7 @@ void CompactionIterator::NextFromInput() {
         status_ = Status::Corruption("Corrupted internal key not expected.");
         break;
       }
-      key_ = current_key_.SetInternalKey(key_);
+      key_ = current_key_.SetKey(key_);
       has_current_user_key_ = false;
       current_user_key_sequence_ = kMaxSequenceNumber;
       current_user_key_snapshot_ = 0;
@@ -283,73 +179,75 @@ void CompactionIterator::NextFromInput() {
         !cmp_->Equal(ikey_.user_key, current_user_key_)) {
       // First occurrence of this user key
       // Copy key for output
-      key_ = current_key_.SetInternalKey(key_, &ikey_);
+      key_ = current_key_.SetKey(key_, &ikey_);
       current_user_key_ = ikey_.user_key;
       has_current_user_key_ = true;
       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_) {
-        compaction_listener_->OnCompaction(compaction_->level(), ikey_.user_key,
-                                           fromInternalValueType(ikey_.type),
-                                           value_, ikey_.sequence, true);
-      }
-#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;
+        }
 
-      // Apply the compaction filter to the first committed version of the user
-      // key.
-      if (current_key_committed_) {
-        InvokeFilterIfNeeded(&need_skip, &skip_until);
+        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();
+        }
       }
     } else {
-#ifndef ROCKSDB_LITE
-      if (compaction_listener_) {
-        compaction_listener_->OnCompaction(compaction_->level(), ikey_.user_key,
-                                           fromInternalValueType(ikey_.type),
-                                           value_, ikey_.sequence, false);
-      }
-#endif  // ROCKSDB_LITE
-
       // Update the current key to reflect the new sequence number/type without
       // copying the user key.
       // TODO(rven): Compaction filter does not process keys in this path
       // Need to have the compaction filter process multiple versions
       // if we have versions on both sides of a snapshot
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      key_ = current_key_.GetInternalKey();
+      key_ = current_key_.GetKey();
       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__));
-    last_sequence = current_user_key_sequence_;
+    SequenceNumber last_sequence __attribute__((__unused__)) =
+        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
@@ -414,10 +312,7 @@ 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 ||
-            (snapshot_checker_ != nullptr &&
-             UNLIKELY(!snapshot_checker_->IsInSnapshot(next_ikey.sequence,
-                                                       prev_snapshot)))) {
+        if (prev_snapshot == 0 || 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.
@@ -428,12 +323,8 @@ void CompactionIterator::NextFromInput() {
             // input_->Next().
             ++iter_stats_.num_record_drop_obsolete;
             ++iter_stats_.num_single_del_mismatch;
-          } else if (has_outputted_key_ ||
-                     (ikey_.sequence <= earliest_write_conflict_snapshot_ &&
-                      (snapshot_checker_ == nullptr ||
-                       LIKELY(snapshot_checker_->IsInSnapshot(
-                           ikey_.sequence,
-                           earliest_write_conflict_snapshot_))))) {
+          } else if ((ikey_.sequence <= earliest_write_conflict_snapshot_) ||
+                     has_outputted_key_) {
             // 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
@@ -481,18 +372,12 @@ 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;
@@ -507,7 +392,7 @@ void CompactionIterator::NextFromInput() {
       // is the same as the visibility of a previous instance of the
       // same key, then this kv is not visible in any snapshot.
       // Hidden by an newer entry for same user key
-      // TODO(noetzli): why not > ?
+      // TODO: why not > ?
       //
       // Note: Dropping this key will not affect TransactionDB write-conflict
       // checking since there has already been a record returned for this key
@@ -517,10 +402,6 @@ 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_
@@ -538,9 +419,6 @@ void CompactionIterator::NextFromInput() {
       // Note:  Dropping this Delete will not affect TransactionDB
       // write-conflict checking since it is earlier than any snapshot.
       ++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()) {
@@ -554,10 +432,6 @@ void CompactionIterator::NextFromInput() {
       // have hit (A)
       // We encapsulate the merge related state machine in a different
       // object to minimize change to the existing flow.
-      // In case snapshot_checker is present, we can probably merge further
-      // beyond prev_snapshot, since there could be more keys with sequence
-      // smaller than prev_snapshot, but reported by snapshot_checker as not
-      // visible by prev_snapshot. But it will make the logic more complicated.
       Status s = merge_helper_->MergeUntil(input_, range_del_agg_,
                                            prev_snapshot, bottommost_level_);
       merge_out_iter_.SeekToFirst();
@@ -570,14 +444,14 @@ void CompactionIterator::NextFromInput() {
         //       These will be correctly set below.
         key_ = merge_out_iter_.key();
         value_ = merge_out_iter_.value();
-        bool valid_key __attribute__((__unused__));
-        valid_key = ParseInternalKey(key_, &ikey_);
+        bool valid_key __attribute__((__unused__)) =
+            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);
         // Keep current_key_ in sync.
         current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-        key_ = current_key_.GetInternalKey();
+        key_ = current_key_.GetKey();
         ikey_.user_key = current_key_.GetUserKey();
         valid_ = true;
       } else {
@@ -624,12 +498,7 @@ void CompactionIterator::PrepareOutput() {
 
   // 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()) &&
-      ikeyNotNeededForIncrementalSnapshot() &&
-      bottommost_level_ && valid_ && ikey_.sequence <= earliest_snapshot_ &&
-      (snapshot_checker_ == nullptr || LIKELY(snapshot_checker_->IsInSnapshot(
-        ikey_.sequence, earliest_snapshot_))) &&
+  if (bottommost_level_ && valid_ && ikey_.sequence < earliest_snapshot_ &&
       ikey_.type != kTypeMerge &&
       !cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
     assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
@@ -641,11 +510,10 @@ void CompactionIterator::PrepareOutput() {
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  SequenceNumber prev = kMaxSequenceNumber;
+  SequenceNumber prev __attribute__((__unused__)) = kMaxSequenceNumber;
   for (const auto cur : *snapshots_) {
     assert(prev == kMaxSequenceNumber || prev <= cur);
-    if (cur >= in && (snapshot_checker_ == nullptr ||
-                      snapshot_checker_->IsInSnapshot(in, cur))) {
+    if (cur >= in) {
       *prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
       return cur;
     }
@@ -656,11 +524,4 @@ 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

db/compaction_iterator.h

@@ -14,14 +14,10 @@
 #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"
 
 namespace rocksdb {
 
-class CompactionEventListener;
-
 class CompactionIterator {
  public:
   // A wrapper around Compaction. Has a much smaller interface, only what
@@ -46,12 +42,6 @@ class CompactionIterator {
     virtual Slice GetLargestUserKey() const {
       return compaction_->GetLargestUserKey();
     }
-    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;
@@ -63,29 +53,23 @@ class CompactionIterator {
   CompactionIterator(InternalIterator* input, const Comparator* cmp,
                      MergeHelper* merge_helper, SequenceNumber last_sequence,
                      std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
+                     SequenceNumber earliest_write_conflict_snapshot, 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 SequenceNumber preserve_deletes_seqnum = 0);
+                     const std::atomic<bool>* shutting_down = nullptr);
 
   // 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,
-                     const SnapshotChecker* snapshot_checker, Env* env,
+                     SequenceNumber earliest_write_conflict_snapshot, 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 SequenceNumber preserve_deletes_seqnum = 0);
+                     const std::atomic<bool>* shutting_down = nullptr);
 
   ~CompactionIterator();
 
@@ -119,9 +103,6 @@ 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
@@ -131,27 +112,17 @@ 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_;
@@ -207,10 +178,6 @@ 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);

db/compaction_iterator_test.cc

@@ -154,9 +154,6 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
   virtual Slice GetLargestUserKey() const {
     return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
   }
-  virtual bool allow_ingest_behind() const { return false; }
-
-  virtual bool preserve_deletes() const {return false; }
 
   bool key_not_exists_beyond_output_level = false;
 };
@@ -183,8 +180,6 @@ class CompactionIteratorTest : public testing::Test {
       compaction_proxy_ = new FakeCompaction();
       compaction.reset(compaction_proxy_);
     }
-    // TODO(yiwu) add a mock snapshot checker and add test for it.
-    SnapshotChecker* snapshot_checker = nullptr;
 
     merge_helper_.reset(new MergeHelper(Env::Default(), cmp_, merge_op, filter,
                                         nullptr, false, 0, 0, nullptr,
@@ -193,9 +188,8 @@ class CompactionIteratorTest : public testing::Test {
     iter_->SeekToFirst();
     c_iter_.reset(new CompactionIterator(
         iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
-        kMaxSequenceNumber, snapshot_checker, Env::Default(), false,
-        range_del_agg_.get(), std::move(compaction), filter, nullptr,
-        &shutting_down_));
+        kMaxSequenceNumber, Env::Default(), false, range_del_agg_.get(),
+        std::move(compaction), filter, &shutting_down_));
   }
 
   void AddSnapshot(SequenceNumber snapshot) { snapshots_.push_back(snapshot); }
@@ -460,111 +454,6 @@ TEST_F(CompactionIteratorTest, ShuttingDownInMerge) {
   EXPECT_EQ(2, filter.last_seen.load());
 }
 
-TEST_F(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,
-      &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());
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/compaction_job.cc

@@ -28,6 +28,7 @@
 #include "db/db_iter.h"
 #include "db/dbformat.h"
 #include "db/event_helpers.h"
+#include "db/filename.h"
 #include "db/log_reader.h"
 #include "db/log_writer.h"
 #include "db/memtable.h"
@@ -35,9 +36,7 @@
 #include "db/merge_context.h"
 #include "db/merge_helper.h"
 #include "db/version_set.h"
-#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"
@@ -50,15 +49,16 @@
 #include "table/table_builder.h"
 #include "util/coding.h"
 #include "util/file_reader_writer.h"
-#include "util/filename.h"
+#include "util/iostats_context_imp.h"
 #include "util/log_buffer.h"
 #include "util/logging.h"
-#include "util/mutexlock.h"
-#include "util/random.h"
 #include "util/sst_file_manager_impl.h"
+#include "util/mutexlock.h"
+#include "util/perf_context_imp.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 #include "util/sync_point.h"
+#include "util/thread_status_util.h"
 
 namespace rocksdb {
 
@@ -263,16 +263,15 @@ 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,
-    const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
+    const EnvOptions& env_options, VersionSet* versions,
+    const std::atomic<bool>* shutting_down, 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, CompactionJobStats* compaction_job_stats)
+    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),
@@ -281,11 +280,8 @@ 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),
@@ -294,13 +290,10 @@ 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),
-      write_hint_(Env::WLTH_NOT_SET) {
+      measure_io_stats_(measure_io_stats) {
   assert(log_buffer_ != nullptr);
   const auto* cfd = compact_->compaction->column_family_data();
   ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
@@ -371,8 +364,6 @@ 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();
 
@@ -602,9 +593,6 @@ 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) /
@@ -612,46 +600,37 @@ 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(
+  LogToBuffer(
       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: %" 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(),
+      "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(),
       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,
-      CompressionTypeToString(compact_->compaction->output_compression())
-          .c_str());
+      stats.num_dropped_records);
 
   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() << "output_compression"
-         << CompressionTypeToString(compact_->compaction->output_compression());
+         << "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();
 
   if (compaction_job_stats_ != nullptr) {
     stream << "num_single_delete_mismatches"
@@ -686,7 +665,7 @@ 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(), env_optiosn_for_read_));
+      sub_compact->compaction, range_del_agg.get()));
 
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -711,18 +690,15 @@ 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. 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;
+  // 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.
   const int kSampleLenShift = 6;  // 2^6 = 64-byte samples
   std::set<size_t> sample_begin_offsets;
-  if (bottommost_level_ && kSampleBytes > 0) {
-    const size_t kMaxSamples = kSampleBytes >> kSampleLenShift;
+  if (bottommost_level_ &&
+      cfd->ioptions()->compression_opts.max_dict_bytes > 0) {
+    const size_t kMaxSamples =
+        cfd->ioptions()->compression_opts.max_dict_bytes >> kSampleLenShift;
     const size_t kOutFileLen = mutable_cf_options->MaxFileSizeForLevel(
         compact_->compaction->output_level());
     if (kOutFileLen != port::kMaxSizet) {
@@ -757,29 +733,17 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   if (start != nullptr) {
     IterKey start_iter;
     start_iter.SetInternalKey(*start, kMaxSequenceNumber, kValueTypeForSeek);
-    input->Seek(start_iter.GetInternalKey());
+    input->Seek(start_iter.GetKey());
   } else {
     input->SeekToFirst();
   }
 
-  // we allow only 1 compaction event listener. Used by blob storage
-  CompactionEventListener* comp_event_listener = nullptr;
-#ifndef ROCKSDB_LITE
-  for (auto& celitr : cfd->ioptions()->listeners) {
-    comp_event_listener = celitr->GetCompactionEventListener();
-    if (comp_event_listener != nullptr) {
-      break;
-    }
-  }
-#endif  // ROCKSDB_LITE
-
   Status status;
   sub_compact->c_iter.reset(new CompactionIterator(
       input.get(), cfd->user_comparator(), &merge, versions_->LastSequence(),
-      &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_));
+      &existing_snapshots_, earliest_write_conflict_snapshot_, env_, false,
+      range_del_agg.get(), sub_compact->compaction, compaction_filter,
+      shutting_down_));
   auto c_iter = sub_compact->c_iter.get();
   c_iter->SeekToFirst();
   if (c_iter->Valid() &&
@@ -792,11 +756,11 @@ 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 dict_sample_data are only valid while generating
+  // data_begin_offset and compression_dict are only valid while generating
   // dictionary from the first output file.
   size_t data_begin_offset = 0;
-  std::string dict_sample_data;
-  dict_sample_data.reserve(kSampleBytes);
+  std::string compression_dict;
+  compression_dict.reserve(cfd->ioptions()->compression_opts.max_dict_bytes);
 
   while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
     // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
@@ -868,7 +832,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
             data_elmt_copy_len =
                 data_end_offset - (data_begin_offset + data_elmt_copy_offset);
           }
-          dict_sample_data.append(&data_elmt.data()[data_elmt_copy_offset],
+          compression_dict.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.
@@ -923,15 +887,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       RecordDroppedKeys(range_del_out_stats,
                         &sub_compact->compaction_job_stats);
       if (sub_compact->outputs.size() == 1) {
-        // 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);
-        }
+        // Use dictionary from first output file for compression of subsequent
+        // files.
+        sub_compact->compression_dict = std::move(compression_dict);
       }
     }
   }
@@ -1036,10 +994,6 @@ 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(
@@ -1057,12 +1011,12 @@ 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
@@ -1072,8 +1026,7 @@ 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.
-      smallest_user_key = meta->smallest.user_key().ToString(false /*hex*/);
-      lower_bound_guard = Slice(smallest_user_key);
+      lower_bound_guard = meta->smallest.user_key();
       lower_bound = &lower_bound_guard;
     } else {
       lower_bound = nullptr;
@@ -1091,18 +1044,16 @@ 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();
-  if (s.ok()) {
-    meta->fd.file_size = current_bytes;
-  }
+  meta->fd.file_size = current_bytes;
   sub_compact->current_output()->finished = true;
   sub_compact->total_bytes += current_bytes;
 
@@ -1116,39 +1067,16 @@ 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) {
     // Verify that the table is usable
-    // We set for_compaction to false and don't OptimizeForCompactionTableRead
-    // here because this is a special case after we finish the table building
-    // No matter whether use_direct_io_for_flush_and_compaction is true,
-    // we will regrad this verification as user reads since the goal is
-    // to cache it here for further user reads
     InternalIterator* iter = cfd->table_cache()->NewIterator(
         ReadOptions(), env_options_, cfd->internal_comparator(), meta->fd,
         nullptr /* range_del_agg */, nullptr,
         cfd->internal_stats()->GetFileReadHist(
             compact_->compaction->output_level()),
-        false, nullptr /* arena */, false /* skip_filters */,
-        compact_->compaction->output_level());
+        false);
     s = iter->status();
 
     if (s.ok() && paranoid_file_checks_) {
@@ -1163,52 +1091,35 @@ Status CompactionJob::FinishCompactionOutputFile(
       tp = sub_compact->builder->GetTableProperties();
       sub_compact->current_output()->table_properties =
           std::make_shared<TableProperties>(tp);
-      ROCKS_LOG_INFO(db_options_.info_log,
-                     "[%s] [JOB %d] Generated table #%" PRIu64 ": %" PRIu64
-                     " keys, %" PRIu64 " bytes%s",
-                     cfd->GetName().c_str(), job_id_, output_number,
-                     current_entries, current_bytes,
-                     meta->marked_for_compaction ? " (need compaction)" : "");
+      Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
+          "[%s] [JOB %d] Generated table #%" PRIu64 ": %" PRIu64
+          " keys, %" PRIu64 " bytes%s",
+          cfd->GetName().c_str(), job_id_, output_number, current_entries,
+          current_bytes,
+          meta->marked_for_compaction ? " (need compaction)" : "");
     }
   }
-  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)";
-  }
+  std::string fname = TableFileName(db_options_.db_paths, meta->fd.GetNumber(),
+                                    meta->fd.GetPathId());
   EventHelpers::LogAndNotifyTableFileCreationFinished(
       event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname,
-      job_id_, output_fd, tp, TableFileCreationReason::kCompaction, s);
+      job_id_, meta->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 != nullptr && meta->fd.GetPathId() == 0) {
+  if (sfm && 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()) {
-        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;
-        }
+        s = Status::IOError("Max allowed space was reached");
+        *db_bg_error_ = s;
+        TEST_SYNC_POINT(
+            "CompactionJob::FinishCompactionOutputFile:MaxAllowedSpaceReached");
       }
     }
   }
@@ -1231,16 +1142,17 @@ Status CompactionJob::InstallCompactionResults(
   if (!versions_->VerifyCompactionFileConsistency(compaction)) {
     Compaction::InputLevelSummaryBuffer inputs_summary;
 
-    ROCKS_LOG_ERROR(db_options_.info_log, "[%s] [JOB %d] Compaction %s aborted",
-                    compaction->column_family_data()->GetName().c_str(),
-                    job_id_, compaction->InputLevelSummary(&inputs_summary));
+    Log(InfoLogLevel::ERROR_LEVEL, db_options_.info_log,
+        "[%s] [JOB %d] Compaction %s aborted",
+        compaction->column_family_data()->GetName().c_str(), job_id_,
+        compaction->InputLevelSummary(&inputs_summary));
     return Status::Corruption("Compaction input files inconsistent");
   }
 
   {
     Compaction::InputLevelSummaryBuffer inputs_summary;
-    ROCKS_LOG_INFO(
-        db_options_.info_log, "[%s] [JOB %d] Compacted %s => %" PRIu64 " bytes",
+    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
+        "[%s] [JOB %d] Compacted %s => %" PRIu64 " bytes",
         compaction->column_family_data()->GetName().c_str(), job_id_,
         compaction->InputLevelSummary(&inputs_summary), compact_->total_bytes);
   }
@@ -1286,15 +1198,9 @@ Status CompactionJob::OpenCompactionOutputFile(
 #endif  // !ROCKSDB_LITE
   // Make the output file
   unique_ptr<WritableFile> writable_file;
-#ifndef NDEBUG
-  bool syncpoint_arg = env_options_.use_direct_writes;
-  TEST_SYNC_POINT_CALLBACK("CompactionJob::OpenCompactionOutputFile",
-                           &syncpoint_arg);
-#endif
   Status s = NewWritableFile(env_, fname, &writable_file, env_options_);
   if (!s.ok()) {
-    ROCKS_LOG_ERROR(
-        db_options_.info_log,
+    Log(InfoLogLevel::ERROR_LEVEL, db_options_.info_log,
         "[%s] [JOB %d] OpenCompactionOutputFiles for table #%" PRIu64
         " fails at NewWritableFile with status %s",
         sub_compact->compaction->column_family_data()->GetName().c_str(),
@@ -1314,7 +1220,6 @@ 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(
@@ -1325,30 +1230,14 @@ 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, output_file_creation_time));
+      sub_compact->compaction->output_level(),
+      &sub_compact->compression_dict,
+      skip_filters));
   LogFlush(db_options_.info_log);
   return s;
 }
@@ -1487,14 +1376,14 @@ void CompactionJob::LogCompaction() {
   // we're not logging
   if (db_options_.info_log_level <= InfoLogLevel::INFO_LEVEL) {
     Compaction::InputLevelSummaryBuffer inputs_summary;
-    ROCKS_LOG_INFO(
-        db_options_.info_log, "[%s] [JOB %d] Compacting %s, score %.2f",
-        cfd->GetName().c_str(), job_id_,
-        compaction->InputLevelSummary(&inputs_summary), compaction->score());
+    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
+        "[%s] [JOB %d] Compacting %s, score %.2f", cfd->GetName().c_str(),
+        job_id_, compaction->InputLevelSummary(&inputs_summary),
+        compaction->score());
     char scratch[2345];
     compaction->Summary(scratch, sizeof(scratch));
-    ROCKS_LOG_INFO(db_options_.info_log, "[%s] Compaction start summary: %s\n",
-                   cfd->GetName().c_str(), scratch);
+    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
+        "[%s] Compaction start summary: %s\n", cfd->GetName().c_str(), scratch);
     // build event logger report
     auto stream = event_logger_->Log();
     stream << "job" << job_id_ << "event"

db/compaction_job.h

@@ -29,7 +29,6 @@
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
-#include "options/db_options.h"
 #include "port/port.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/compaction_job_stats.h"
@@ -39,34 +38,31 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/db_options.h"
 #include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
 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,
-                const SequenceNumber preserve_deletes_seqnum,
-                LogBuffer* log_buffer,
+                const EnvOptions& env_options, VersionSet* versions,
+                const std::atomic<bool>* shutting_down, 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,
@@ -131,14 +127,11 @@ 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_;
@@ -156,8 +149,6 @@ 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_;
@@ -169,7 +160,6 @@ 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

db/compaction_job_stats_test.cc

@@ -23,13 +23,11 @@
 
 #include "db/db_impl.h"
 #include "db/dbformat.h"
+#include "db/filename.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "db/write_batch_internal.h"
-#include "env/mock_env.h"
 #include "memtable/hash_linklist_rep.h"
-#include "monitoring/statistics.h"
-#include "monitoring/thread_status_util.h"
 #include "port/stack_trace.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/compaction_filter.h"
@@ -52,15 +50,17 @@
 #include "table/plain_table_factory.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/compression.h"
-#include "util/filename.h"
 #include "util/hash.h"
 #include "util/logging.h"
+#include "util/mock_env.h"
 #include "util/mutexlock.h"
 #include "util/rate_limiter.h"
+#include "util/statistics.h"
 #include "util/string_util.h"
 #include "util/sync_point.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
+#include "util/thread_status_util.h"
 #include "utilities/merge_operators.h"
 
 #if !defined(IOS_CROSS_COMPILE)
@@ -654,6 +654,7 @@ 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;
@@ -875,6 +876,7 @@ 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;

db/compaction_job_test.cc

@@ -76,7 +76,6 @@ 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_,
@@ -143,8 +142,6 @@ 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);
   }
 
@@ -252,15 +249,12 @@ 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());
-    // 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_);
+    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_);
+
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 
     compaction_job.Prepare();
@@ -296,7 +290,6 @@ 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_;
@@ -344,24 +337,6 @@ 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();
 

db/compaction_picker.h

@@ -17,10 +17,10 @@
 
 #include "db/compaction.h"
 #include "db/version_set.h"
-#include "options/cf_options.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "rocksdb/status.h"
+#include "util/cf_options.h"
 
 namespace rocksdb {
 
@@ -84,19 +84,15 @@ class CompactionPicker {
   void ReleaseCompactionFiles(Compaction* c, Status status);
 
   // Returns true if any one of the specified files are being compacted
-  bool AreFilesInCompaction(const std::vector<FileMetaData*>& files);
+  bool FilesInCompaction(const std::vector<FileMetaData*>& files);
 
   // 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,
-                           const MutableCFOptions& mutable_cf_options,
-                           uint32_t output_path_id);
+  Compaction* FormCompaction(
+      const CompactionOptions& compact_options,
+      const std::vector<CompactionInputFiles>& input_files, int output_level,
+      VersionStorageInfo* vstorage, const MutableCFOptions& mutable_cf_options,
+      uint32_t output_path_id);
 
   // Converts a set of compaction input file numbers into
   // a list of CompactionInputFiles.
@@ -106,6 +102,12 @@ class CompactionPicker {
       const VersionStorageInfo* vstorage,
       const CompactionOptions& compact_options) const;
 
+  // Used in universal compaction when the enabled_trivial_move
+  // option is set. Checks whether there are any overlapping files
+  // in the input. Returns true if the input files are non
+  // overlapping.
+  bool IsInputNonOverlapping(Compaction* c);
+
   // Is there currently a compaction involving level 0 taking place
   bool IsLevel0CompactionInProgress() const {
     return !level0_compactions_in_progress_.empty();
@@ -136,6 +138,7 @@ class CompactionPicker {
   void GetRange(const std::vector<CompactionInputFiles>& inputs,
                 InternalKey* smallest, InternalKey* largest) const;
 
+ protected:
   int NumberLevels() const { return ioptions_.num_levels; }
 
   // Add more files to the inputs on "level" to make sure that
@@ -148,14 +151,14 @@ class CompactionPicker {
   // populated.
   //
   // Will return false if it is impossible to apply this compaction.
-  bool ExpandInputsToCleanCut(const std::string& cf_name,
+  bool ExpandWhileOverlapping(const std::string& cf_name,
                               VersionStorageInfo* vstorage,
                               CompactionInputFiles* inputs);
 
   // Returns true if any one of the parent files are being compacted
-  bool IsRangeInCompaction(VersionStorageInfo* vstorage,
-                           const InternalKey* smallest,
-                           const InternalKey* largest, int level, int* index);
+  bool RangeInCompaction(VersionStorageInfo* vstorage,
+                         const InternalKey* smallest,
+                         const InternalKey* largest, int level, int* index);
 
   // Returns true if the key range that `inputs` files cover overlap with the
   // key range of a currently running compaction.
@@ -174,20 +177,6 @@ class CompactionPicker {
                        const CompactionInputFiles& output_level_inputs,
                        std::vector<FileMetaData*>* grandparents);
 
-  // Register this compaction in the set of running compactions
-  void RegisterCompaction(Compaction* c);
-
-  // Remove this compaction from the set of running compactions
-  void UnregisterCompaction(Compaction* c);
-
-  std::set<Compaction*>* level0_compactions_in_progress() {
-    return &level0_compactions_in_progress_;
-  }
-  std::unordered_set<Compaction*>* compactions_in_progress() {
-    return &compactions_in_progress_;
-  }
-
- protected:
   const ImmutableCFOptions& ioptions_;
 
 // A helper function to SanitizeCompactionInputFiles() that
@@ -198,6 +187,12 @@ class CompactionPicker {
       const ColumnFamilyMetaData& cf_meta, const int output_level) const;
 #endif  // ROCKSDB_LITE
 
+  // Register this compaction in the set of running compactions
+  void RegisterCompaction(Compaction* c);
+
+  // Remove this compaction from the set of running compactions
+  void UnregisterCompaction(Compaction* c);
+
   // Keeps track of all compactions that are running on Level0.
   // Protected by DB mutex
   std::set<Compaction*> level0_compactions_in_progress_;
@@ -221,9 +216,101 @@ class LevelCompactionPicker : public CompactionPicker {
 
   virtual bool NeedsCompaction(
       const VersionStorageInfo* vstorage) const override;
+
+  // Pick a path ID to place a newly generated file, with its level
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            int level);
+
+ private:
+  // For the specfied level, pick a file that we want to compact.
+  // Returns false if there is no file to compact.
+  // If it returns true, inputs->files.size() will be exactly one.
+  // If level is 0 and there is already a compaction on that level, this
+  // function will return false.
+  bool PickCompactionBySize(VersionStorageInfo* vstorage, int level,
+                            int output_level, CompactionInputFiles* inputs,
+                            int* parent_index, int* base_index);
+
+  // If there is any file marked for compaction, put put it into inputs.
+  // This is still experimental. It will return meaningful results only if
+  // clients call experimental feature SuggestCompactRange()
+  void PickFilesMarkedForCompactionExperimental(const std::string& cf_name,
+                                                VersionStorageInfo* vstorage,
+                                                CompactionInputFiles* inputs,
+                                                int* level, int* output_level);
 };
 
 #ifndef ROCKSDB_LITE
+class UniversalCompactionPicker : public CompactionPicker {
+ public:
+  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
+                            const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+
+ private:
+  struct SortedRun {
+    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
+              uint64_t _compensated_file_size, bool _being_compacted)
+        : level(_level),
+          file(_file),
+          size(_size),
+          compensated_file_size(_compensated_file_size),
+          being_compacted(_being_compacted) {
+      assert(compensated_file_size > 0);
+      assert(level != 0 || file != nullptr);
+    }
+
+    void Dump(char* out_buf, size_t out_buf_size,
+              bool print_path = false) const;
+
+    // sorted_run_count is added into the string to print
+    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
+                      size_t sorted_run_count) const;
+
+    int level;
+    // `file` Will be null for level > 0. For level = 0, the sorted run is
+    // for this file.
+    FileMetaData* file;
+    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
+    // files in the level. `being_compacted` should be the same for all files
+    // in a non-zero level. Use the value here.
+    uint64_t size;
+    uint64_t compensated_file_size;
+    bool being_compacted;
+  };
+
+  // Pick Universal compaction to limit read amplification
+  Compaction* PickCompactionUniversalReadAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score, unsigned int ratio,
+      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
+      LogBuffer* log_buffer);
+
+  // Pick Universal compaction to limit space amplification.
+  Compaction* PickCompactionUniversalSizeAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  static std::vector<SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions);
+
+  // Pick a path ID to place a newly generated file, with its estimated file
+  // size.
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            uint64_t file_size);
+};
+
 class FIFOCompactionPicker : public CompactionPicker {
  public:
   FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -246,17 +333,6 @@ 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 {

db/compaction_picker_test.cc

@@ -3,12 +3,11 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#include "db/compaction.h"
 #include "db/compaction_picker.h"
 #include <limits>
 #include <string>
 #include <utility>
-#include "db/compaction.h"
-#include "db/compaction_picker_universal.h"
 
 #include "util/logging.h"
 #include "util/string_util.h"
@@ -175,8 +174,6 @@ 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);
@@ -193,15 +190,14 @@ 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);
+  Add(0, 1U, "150", "200", 1000000000U);
   // Level 1 score 1.2
   Add(1, 66U, "150", "200", 6000000U);
   Add(1, 88U, "201", "300", 6000000U);
@@ -221,9 +217,6 @@ 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) {
@@ -406,35 +399,6 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
               vstorage_->CompactionScore(0) >= 1);
   }
 }
-
-TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
-  const uint64_t kFileSize = 100000;
-  NewVersionStorage(1, kCompactionStyleUniversal);
-  ioptions_.allow_ingest_behind = true;
-  ioptions_.num_levels = 3;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  // must return false when there's no files.
-  ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
-            false);
-
-  NewVersionStorage(3, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 2U, "201", "250", kFileSize, 0, 401, 450);
-  Add(0, 4U, "260", "300", kFileSize, 0, 260, 300);
-  Add(1, 5U, "100", "151", kFileSize, 0, 200, 251);
-  Add(1, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(2, 6U, "120", "200", kFileSize, 0, 20, 100);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  // output level should be the one above the bottom-most
-  ASSERT_EQ(1, compaction->output_level());
-}
 // Tests if the files can be trivially moved in multi level
 // universal compaction when allow_trivial_move option is set
 // In this test as the input files overlaps, they cannot
@@ -443,7 +407,7 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
 TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
   const uint64_t kFileSize = 100000;
 
-  mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
+  ioptions_.compaction_options_universal.allow_trivial_move = true;
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
   // must return false when there's no files.
@@ -474,7 +438,7 @@ TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
 TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
   const uint64_t kFileSize = 100000;
 
-  mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
+  ioptions_.compaction_options_universal.allow_trivial_move = true;
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
 
   NewVersionStorage(3, kCompactionStyleUniversal);
@@ -502,7 +466,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   const uint64_t kMaxSize = kFileSize * kFileCount / 2;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  ioptions_.compaction_options_fifo = fifo_options_;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
   UpdateVersionStorageInfo();
   // must return false when there's no files.
@@ -518,7 +482,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
         kFileSize, 0, i * 100, i * 100 + 99);
     current_size += kFileSize;
     UpdateVersionStorageInfo();
-    ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()),
+    ASSERT_EQ(level_compaction_picker.NeedsCompaction(vstorage_.get()),
               vstorage_->CompactionScore(0) >= 1);
   }
 }
@@ -527,10 +491,9 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
 TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
   NewVersionStorage(6, kCompactionStyleLevel);
   ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.target_file_size_base = 100000000000;
+  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(2, 6U, "150", "179", 50000000U);
   Add(2, 7U, "180", "220", 50000000U);
@@ -550,8 +513,6 @@ 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) {
@@ -861,80 +822,6 @@ 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;
@@ -1033,7 +920,7 @@ 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 = 4;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
   mutable_cf_options_.max_bytes_for_level_base = 1000;
   mutable_cf_options_.max_bytes_for_level_multiplier = 10;
   NewVersionStorage(num_levels, kCompactionStyleLevel);
@@ -1123,8 +1010,7 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
 
   // Set Last level size 50000
   // num_levels - 1 target 5000
-  // num_levels - 2 is base level with target 1000 (rounded up to
-  // max_bytes_for_level_base).
+  // num_levels - 2 is base level with taret 500
   Add(num_levels - 1, 10U, "400", "500", 50000);
 
   Add(0, 1U, "150", "200", 200);
@@ -1133,16 +1019,16 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
   Add(0, 5U, "150", "200", 200);
   Add(0, 6U, "150", "200", 200);
   // num_levels - 3 is over target by 100 + 1000
-  Add(num_levels - 3, 7U, "400", "500", 550);
-  Add(num_levels - 3, 8U, "600", "700", 550);
+  Add(num_levels - 3, 7U, "400", "500", 300);
+  Add(num_levels - 3, 8U, "600", "700", 300);
   // num_levels - 2 is over target by 1100 + 200
   Add(num_levels - 2, 9U, "150", "200", 5200);
 
   UpdateVersionStorageInfo();
 
-  // Merging to the second last level: (5200 / 2100 + 1) * 1100
+  // Merging to the second last level: (5200 / 1600 + 1) * 1100
   // Merging to the last level: (50000 / 6300 + 1) * 1300
-  ASSERT_EQ(2100u + 3823u + 11617u,
+  ASSERT_EQ(1600u + 4675u + 11617u,
             vstorage_->estimated_compaction_needed_bytes());
 }
 
@@ -1399,49 +1285,6 @@ 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) {

db/compaction_picker_universal.cc

@@ -1,755 +0,0 @@
-//  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).
-//
-// 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.
-
-#include "db/compaction_picker_universal.h"
-#ifndef ROCKSDB_LITE
-
-#ifndef __STDC_FORMAT_MACROS
-#define __STDC_FORMAT_MACROS
-#endif
-
-#include <inttypes.h>
-#include <limits>
-#include <queue>
-#include <string>
-#include <utility>
-#include "db/column_family.h"
-#include "monitoring/statistics.h"
-#include "util/filename.h"
-#include "util/log_buffer.h"
-#include "util/random.h"
-#include "util/string_util.h"
-#include "util/sync_point.h"
-
-namespace rocksdb {
-namespace {
-// Used in universal compaction when trivial move is enabled.
-// This structure is used for the construction of min heap
-// that contains the file meta data, the level of the file
-// and the index of the file in that level
-
-struct InputFileInfo {
-  InputFileInfo() : f(nullptr), level(0), index(0) {}
-
-  FileMetaData* f;
-  size_t level;
-  size_t index;
-};
-
-// Used in universal compaction when trivial move is enabled.
-// This comparator is used for the construction of min heap
-// based on the smallest key of the file.
-struct SmallestKeyHeapComparator {
-  explicit SmallestKeyHeapComparator(const Comparator* ucmp) { ucmp_ = ucmp; }
-
-  bool operator()(InputFileInfo i1, InputFileInfo i2) const {
-    return (ucmp_->Compare(i1.f->smallest.user_key(),
-                           i2.f->smallest.user_key()) > 0);
-  }
-
- private:
-  const Comparator* ucmp_;
-};
-
-typedef std::priority_queue<InputFileInfo, std::vector<InputFileInfo>,
-                            SmallestKeyHeapComparator>
-    SmallestKeyHeap;
-
-// This function creates the heap that is used to find if the files are
-// overlapping during universal compaction when the allow_trivial_move
-// is set.
-SmallestKeyHeap create_level_heap(Compaction* c, const Comparator* ucmp) {
-  SmallestKeyHeap smallest_key_priority_q =
-      SmallestKeyHeap(SmallestKeyHeapComparator(ucmp));
-
-  InputFileInfo input_file;
-
-  for (size_t l = 0; l < c->num_input_levels(); l++) {
-    if (c->num_input_files(l) != 0) {
-      if (l == 0 && c->start_level() == 0) {
-        for (size_t i = 0; i < c->num_input_files(0); i++) {
-          input_file.f = c->input(0, i);
-          input_file.level = 0;
-          input_file.index = i;
-          smallest_key_priority_q.push(std::move(input_file));
-        }
-      } else {
-        input_file.f = c->input(l, 0);
-        input_file.level = l;
-        input_file.index = 0;
-        smallest_key_priority_q.push(std::move(input_file));
-      }
-    }
-  }
-  return smallest_key_priority_q;
-}
-
-#ifndef NDEBUG
-// smallest_seqno and largest_seqno are set iff. `files` is not empty.
-void GetSmallestLargestSeqno(const std::vector<FileMetaData*>& files,
-                             SequenceNumber* smallest_seqno,
-                             SequenceNumber* largest_seqno) {
-  bool is_first = true;
-  for (FileMetaData* f : files) {
-    assert(f->smallest_seqno <= f->largest_seqno);
-    if (is_first) {
-      is_first = false;
-      *smallest_seqno = f->smallest_seqno;
-      *largest_seqno = f->largest_seqno;
-    } else {
-      if (f->smallest_seqno < *smallest_seqno) {
-        *smallest_seqno = f->smallest_seqno;
-      }
-      if (f->largest_seqno > *largest_seqno) {
-        *largest_seqno = f->largest_seqno;
-      }
-    }
-  }
-}
-#endif
-}  // namespace
-
-// Algorithm that checks to see if there are any overlapping
-// files in the input
-bool UniversalCompactionPicker::IsInputFilesNonOverlapping(Compaction* c) {
-  auto comparator = icmp_->user_comparator();
-  int first_iter = 1;
-
-  InputFileInfo prev, curr, next;
-
-  SmallestKeyHeap smallest_key_priority_q =
-      create_level_heap(c, icmp_->user_comparator());
-
-  while (!smallest_key_priority_q.empty()) {
-    curr = smallest_key_priority_q.top();
-    smallest_key_priority_q.pop();
-
-    if (first_iter) {
-      prev = curr;
-      first_iter = 0;
-    } else {
-      if (comparator->Compare(prev.f->largest.user_key(),
-                              curr.f->smallest.user_key()) >= 0) {
-        // found overlapping files, return false
-        return false;
-      }
-      assert(comparator->Compare(curr.f->largest.user_key(),
-                                 prev.f->largest.user_key()) > 0);
-      prev = curr;
-    }
-
-    next.f = nullptr;
-
-    if (curr.level != 0 && curr.index < c->num_input_files(curr.level) - 1) {
-      next.f = c->input(curr.level, curr.index + 1);
-      next.level = curr.level;
-      next.index = curr.index + 1;
-    }
-
-    if (next.f) {
-      smallest_key_priority_q.push(std::move(next));
-    }
-  }
-  return true;
-}
-
-bool UniversalCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  const int kLevel0 = 0;
-  return vstorage->CompactionScore(kLevel0) >= 1;
-}
-
-void UniversalCompactionPicker::SortedRun::Dump(char* out_buf,
-                                                size_t out_buf_size,
-                                                bool print_path) const {
-  if (level == 0) {
-    assert(file != nullptr);
-    if (file->fd.GetPathId() == 0 || !print_path) {
-      snprintf(out_buf, out_buf_size, "file %" PRIu64, file->fd.GetNumber());
-    } else {
-      snprintf(out_buf, out_buf_size, "file %" PRIu64
-                                      "(path "
-                                      "%" PRIu32 ")",
-               file->fd.GetNumber(), file->fd.GetPathId());
-    }
-  } else {
-    snprintf(out_buf, out_buf_size, "level %d", level);
-  }
-}
-
-void UniversalCompactionPicker::SortedRun::DumpSizeInfo(
-    char* out_buf, size_t out_buf_size, size_t sorted_run_count) const {
-  if (level == 0) {
-    assert(file != nullptr);
-    snprintf(out_buf, out_buf_size,
-             "file %" PRIu64 "[%" ROCKSDB_PRIszt
-             "] "
-             "with size %" PRIu64 " (compensated size %" PRIu64 ")",
-             file->fd.GetNumber(), sorted_run_count, file->fd.GetFileSize(),
-             file->compensated_file_size);
-  } else {
-    snprintf(out_buf, out_buf_size,
-             "level %d[%" ROCKSDB_PRIszt
-             "] "
-             "with size %" PRIu64 " (compensated size %" PRIu64 ")",
-             level, sorted_run_count, size, compensated_file_size);
-  }
-}
-
-std::vector<UniversalCompactionPicker::SortedRun>
-UniversalCompactionPicker::CalculateSortedRuns(
-    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,
-                     f->being_compacted);
-  }
-  for (int level = 1; level < vstorage.num_levels(); level++) {
-    uint64_t total_compensated_size = 0U;
-    uint64_t total_size = 0U;
-    bool being_compacted = false;
-    bool is_first = true;
-    for (FileMetaData* f : vstorage.LevelFiles(level)) {
-      total_compensated_size += f->compensated_file_size;
-      total_size += f->fd.GetFileSize();
-      if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
-          true) {
-        if (f->being_compacted) {
-          being_compacted = f->being_compacted;
-        }
-      } else {
-        // Compaction always includes all files for a non-zero level, so for a
-        // non-zero level, all the files should share the same being_compacted
-        // value.
-        // This assumption is only valid when
-        // mutable_cf_options.compaction_options_universal.allow_trivial_move is
-        // false
-        assert(is_first || f->being_compacted == being_compacted);
-      }
-      if (is_first) {
-        being_compacted = f->being_compacted;
-        is_first = false;
-      }
-    }
-    if (total_compensated_size > 0) {
-      ret.emplace_back(level, nullptr, total_size, total_compensated_size,
-                       being_compacted);
-    }
-  }
-  return ret;
-}
-
-// 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_, mutable_cf_options);
-
-  if (sorted_runs.size() == 0 ||
-      sorted_runs.size() <
-          (unsigned int)mutable_cf_options.level0_file_num_compaction_trigger) {
-    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: nothing to do\n",
-                     cf_name.c_str());
-    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
-                             nullptr);
-    return nullptr;
-  }
-  VersionStorageInfo::LevelSummaryStorage tmp;
-  ROCKS_LOG_BUFFER_MAX_SZ(
-      log_buffer, 3072,
-      "[%s] Universal: sorted runs files(%" ROCKSDB_PRIszt "): %s\n",
-      cf_name.c_str(), sorted_runs.size(), vstorage->LevelSummary(&tmp));
-
-  // Check for size amplification first.
-  Compaction* c;
-  if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options, vstorage,
-                                         score, sorted_runs, log_buffer)) !=
-      nullptr) {
-    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
-                     cf_name.c_str());
-  } else {
-    // Size amplification is within limits. Try reducing read
-    // amplification while maintaining file size ratios.
-    unsigned int ratio =
-        mutable_cf_options.compaction_options_universal.size_ratio;
-
-    if ((c = PickCompactionToReduceSortedRuns(
-             cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
-             sorted_runs, log_buffer)) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer,
-                       "[%s] Universal: compacting for size ratio\n",
-                       cf_name.c_str());
-    } else {
-      // Size amplification and file size ratios are within configured limits.
-      // If max read amplification is exceeding configured limits, then force
-      // compaction without looking at filesize ratios and try to reduce
-      // the number of files to fewer than level0_file_num_compaction_trigger.
-      // This is guaranteed by NeedsCompaction()
-      assert(sorted_runs.size() >=
-             static_cast<size_t>(
-                 mutable_cf_options.level0_file_num_compaction_trigger));
-      // Get the total number of sorted runs that are not being compacted
-      int num_sr_not_compacted = 0;
-      for (size_t i = 0; i < sorted_runs.size(); i++) {
-        if (sorted_runs[i].being_compacted == false) {
-          num_sr_not_compacted++;
-        }
-      }
-
-      // The number of sorted runs that are not being compacted is greater than
-      // the maximum allowed number of sorted runs
-      if (num_sr_not_compacted >
-          mutable_cf_options.level0_file_num_compaction_trigger) {
-        unsigned int num_files =
-            num_sr_not_compacted -
-            mutable_cf_options.level0_file_num_compaction_trigger + 1;
-        if ((c = PickCompactionToReduceSortedRuns(
-                 cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
-                 num_files, sorted_runs, log_buffer)) != nullptr) {
-          ROCKS_LOG_BUFFER(log_buffer,
-                           "[%s] Universal: compacting for file num -- %u\n",
-                           cf_name.c_str(), num_files);
-        }
-      }
-    }
-  }
-  if (c == nullptr) {
-    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
-                             nullptr);
-    return nullptr;
-  }
-
-  if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
-      true) {
-    c->set_is_trivial_move(IsInputFilesNonOverlapping(c));
-  }
-
-// validate that all the chosen files of L0 are non overlapping in time
-#ifndef NDEBUG
-  SequenceNumber prev_smallest_seqno = 0U;
-  bool is_first = true;
-
-  size_t level_index = 0U;
-  if (c->start_level() == 0) {
-    for (auto f : *c->inputs(0)) {
-      assert(f->smallest_seqno <= f->largest_seqno);
-      if (is_first) {
-        is_first = false;
-      }
-      prev_smallest_seqno = f->smallest_seqno;
-    }
-    level_index = 1U;
-  }
-  for (; level_index < c->num_input_levels(); level_index++) {
-    if (c->num_input_files(level_index) != 0) {
-      SequenceNumber smallest_seqno = 0U;
-      SequenceNumber largest_seqno = 0U;
-      GetSmallestLargestSeqno(*(c->inputs(level_index)), &smallest_seqno,
-                              &largest_seqno);
-      if (is_first) {
-        is_first = false;
-      } else if (prev_smallest_seqno > 0) {
-        // A level is considered as the bottommost level if there are
-        // no files in higher levels or if files in higher levels do
-        // not overlap with the files being compacted. Sequence numbers
-        // of files in bottommost level can be set to 0 to help
-        // compression. As a result, the following assert may not hold
-        // if the prev_smallest_seqno is 0.
-        assert(prev_smallest_seqno > largest_seqno);
-      }
-      prev_smallest_seqno = smallest_seqno;
-    }
-  }
-#endif
-  // update statistics
-  MeasureTime(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
-              c->inputs(0)->size());
-
-  RegisterCompaction(c);
-  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
-
-  TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
-                           c);
-  return c;
-}
-
-uint32_t UniversalCompactionPicker::GetPathId(
-    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
-  //     smaller than expected future file size before this new file is
-  //     compacted, which is estimated based on size_ratio.
-  // For example, if now we are compacting files of size (1, 1, 2, 4, 8),
-  // we will make sure the target file, probably with size of 16, will be
-  // placed in a path so that eventually when new files are generated and
-  // compacted to (1, 1, 2, 4, 8, 16), all those files can be stored in or
-  // before the path we chose.
-  //
-  // TODO(sdong): now the case of multiple column families is not
-  // considered in this algorithm. So the target size can be violated in
-  // that case. We need to improve it.
-  uint64_t accumulated_size = 0;
-  uint64_t future_size =
-      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++) {
-    uint64_t target_size = ioptions.db_paths[p].target_size;
-    if (target_size > file_size &&
-        accumulated_size + (target_size - file_size) > future_size) {
-      return p;
-    }
-    accumulated_size += target_size;
-  }
-  return p;
-}
-
-//
-// Consider compaction files based on their size differences with
-// the next file in time order.
-//
-Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, double score, unsigned int ratio,
-    unsigned int max_number_of_files_to_compact,
-    const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
-  unsigned int min_merge_width =
-      mutable_cf_options.compaction_options_universal.min_merge_width;
-  unsigned int max_merge_width =
-      mutable_cf_options.compaction_options_universal.max_merge_width;
-
-  const SortedRun* sr = nullptr;
-  bool done = false;
-  size_t start_index = 0;
-  unsigned int candidate_count = 0;
-
-  unsigned int max_files_to_compact =
-      std::min(max_merge_width, max_number_of_files_to_compact);
-  min_merge_width = std::max(min_merge_width, 2U);
-
-  // Caller checks the size before executing this function. This invariant is
-  // important because otherwise we may have a possible integer underflow when
-  // dealing with unsigned types.
-  assert(sorted_runs.size() > 0);
-
-  // Considers a candidate file only if it is smaller than the
-  // total size accumulated so far.
-  for (size_t loop = 0; loop < sorted_runs.size(); loop++) {
-    candidate_count = 0;
-
-    // Skip files that are already being compacted
-    for (sr = nullptr; loop < sorted_runs.size(); loop++) {
-      sr = &sorted_runs[loop];
-
-      if (!sr->being_compacted) {
-        candidate_count = 1;
-        break;
-      }
-      char file_num_buf[kFormatFileNumberBufSize];
-      sr->Dump(file_num_buf, sizeof(file_num_buf));
-      ROCKS_LOG_BUFFER(log_buffer,
-                       "[%s] Universal: %s"
-                       "[%d] being compacted, skipping",
-                       cf_name.c_str(), file_num_buf, loop);
-
-      sr = nullptr;
-    }
-
-    // This file is not being compacted. Consider it as the
-    // first candidate to be compacted.
-    uint64_t candidate_size = sr != nullptr ? sr->compensated_file_size : 0;
-    if (sr != nullptr) {
-      char file_num_buf[kFormatFileNumberBufSize];
-      sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Possible candidate %s[%d].",
-                       cf_name.c_str(), file_num_buf, loop);
-    }
-
-    // Check if the succeeding files need compaction.
-    for (size_t i = loop + 1;
-         candidate_count < max_files_to_compact && i < sorted_runs.size();
-         i++) {
-      const SortedRun* succeeding_sr = &sorted_runs[i];
-      if (succeeding_sr->being_compacted) {
-        break;
-      }
-      // Pick files if the total/last candidate file size (increased by the
-      // specified ratio) is still larger than the next candidate file.
-      // candidate_size is the total size of files picked so far with the
-      // default kCompactionStopStyleTotalSize; with
-      // kCompactionStopStyleSimilarSize, it's simply the size of the last
-      // picked file.
-      double sz = candidate_size * (100.0 + ratio) / 100.0;
-      if (sz < static_cast<double>(succeeding_sr->size)) {
-        break;
-      }
-      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.
-        sz = (succeeding_sr->size * (100.0 + ratio)) / 100.0;
-        if (sz < static_cast<double>(candidate_size)) {
-          // If the small file we've encountered begins a run of similar-size
-          // files, we'll pick them up on a future iteration of the outer
-          // loop. If it's some lonely straggler, it'll eventually get picked
-          // by the last-resort read amp strategy which disregards size ratios.
-          break;
-        }
-        candidate_size = succeeding_sr->compensated_file_size;
-      } else {  // default kCompactionStopStyleTotalSize
-        candidate_size += succeeding_sr->compensated_file_size;
-      }
-      candidate_count++;
-    }
-
-    // Found a series of consecutive files that need compaction.
-    if (candidate_count >= (unsigned int)min_merge_width) {
-      start_index = loop;
-      done = true;
-      break;
-    } else {
-      for (size_t i = loop;
-           i < loop + candidate_count && i < sorted_runs.size(); i++) {
-        const SortedRun* skipping_sr = &sorted_runs[i];
-        char file_num_buf[256];
-        skipping_sr->DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
-        ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Skipping %s",
-                         cf_name.c_str(), file_num_buf);
-      }
-    }
-  }
-  if (!done || candidate_count <= 1) {
-    return nullptr;
-  }
-  size_t first_index_after = start_index + candidate_count;
-  // Compression is enabled if files compacted earlier already reached
-  // size ratio of compression.
-  bool enable_compression = true;
-  int ratio_to_compress =
-      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) {
-      total_size += sorted_run.compensated_file_size;
-    }
-
-    uint64_t older_file_size = 0;
-    for (size_t i = sorted_runs.size() - 1; i >= first_index_after; i--) {
-      older_file_size += sorted_runs[i].size;
-      if (older_file_size * 100L >= total_size * (long)ratio_to_compress) {
-        enable_compression = false;
-        break;
-      }
-    }
-  }
-
-  uint64_t estimated_total_size = 0;
-  for (unsigned int i = 0; i < first_index_after; i++) {
-    estimated_total_size += sorted_runs[i].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()) {
-    output_level = vstorage->num_levels() - 1;
-  } else if (sorted_runs[first_index_after].level == 0) {
-    output_level = 0;
-  } else {
-    output_level = sorted_runs[first_index_after].level - 1;
-  }
-
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind &&
-      (output_level == vstorage->num_levels() - 1)) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
-  std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
-  for (size_t i = 0; i < inputs.size(); ++i) {
-    inputs[i].level = start_level + static_cast<int>(i);
-  }
-  for (size_t i = start_index; i < first_index_after; i++) {
-    auto& picking_sr = sorted_runs[i];
-    if (picking_sr.level == 0) {
-      FileMetaData* picking_file = picking_sr.file;
-      inputs[0].files.push_back(picking_file);
-    } else {
-      auto& files = inputs[picking_sr.level - start_level].files;
-      for (auto* f : vstorage->LevelFiles(picking_sr.level)) {
-        files.push_back(f);
-      }
-    }
-    char file_num_buf[256];
-    picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), i);
-    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Picking %s", cf_name.c_str(),
-                     file_num_buf);
-  }
-
-  CompactionReason compaction_reason;
-  if (max_number_of_files_to_compact == UINT_MAX) {
-    compaction_reason = CompactionReason::kUniversalSortedRunNum;
-  } else {
-    compaction_reason = CompactionReason::kUniversalSizeRatio;
-  }
-  return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
-      mutable_cf_options.MaxFileSizeForLevel(output_level), LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, start_level,
-                         1, enable_compression),
-      /* grandparents */ {}, /* is manual */ false, score,
-      false /* deletion_compaction */, compaction_reason);
-}
-
-// Look at overall size amplification. If size amplification
-// exceeeds the configured value, then do a compaction
-// of the candidate files all the way upto the earliest
-// base file (overrides configured values of file-size ratios,
-// min_merge_width and max_merge_width).
-//
-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 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;
-  size_t start_index = 0;
-  const SortedRun* sr = nullptr;
-
-  // Skip files that are already being compacted
-  for (size_t loop = 0; loop < sorted_runs.size() - 1; loop++) {
-    sr = &sorted_runs[loop];
-    if (!sr->being_compacted) {
-      start_index = loop;  // Consider this as the first candidate.
-      break;
-    }
-    char file_num_buf[kFormatFileNumberBufSize];
-    sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: skipping %s[%d] compacted %s",
-                     cf_name.c_str(), file_num_buf, loop,
-                     " cannot be a candidate to reduce size amp.\n");
-    sr = nullptr;
-  }
-
-  if (sr == nullptr) {
-    return nullptr;  // no candidate files
-  }
-  {
-    char file_num_buf[kFormatFileNumberBufSize];
-    sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] Universal: First candidate %s[%" ROCKSDB_PRIszt "] %s",
-        cf_name.c_str(), file_num_buf, start_index, " to reduce size amp.\n");
-  }
-
-  // keep adding up all the remaining files
-  for (size_t loop = start_index; loop < sorted_runs.size() - 1; loop++) {
-    sr = &sorted_runs[loop];
-    if (sr->being_compacted) {
-      char file_num_buf[kFormatFileNumberBufSize];
-      sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-      ROCKS_LOG_BUFFER(
-          log_buffer, "[%s] Universal: Possible candidate %s[%d] %s",
-          cf_name.c_str(), file_num_buf, start_index,
-          " is already being compacted. No size amp reduction possible.\n");
-      return nullptr;
-    }
-    candidate_size += sr->compensated_file_size;
-    candidate_count++;
-  }
-  if (candidate_count == 0) {
-    return nullptr;
-  }
-
-  // size of earliest file
-  uint64_t earliest_file_size = sorted_runs.back().size;
-
-  // size amplification = percentage of additional size
-  if (candidate_size * 100 < ratio * earliest_file_size) {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] Universal: size amp not needed. newer-files-total-size %" PRIu64
-        " earliest-file-size %" PRIu64,
-        cf_name.c_str(), candidate_size, earliest_file_size);
-    return nullptr;
-  } else {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] Universal: size amp needed. newer-files-total-size %" PRIu64
-        " earliest-file-size %" PRIu64,
-        cf_name.c_str(), candidate_size, earliest_file_size);
-  }
-  assert(start_index < sorted_runs.size() - 1);
-
-  // Estimate total file size
-  uint64_t estimated_total_size = 0;
-  for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
-    estimated_total_size += sorted_runs[loop].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());
-  for (size_t i = 0; i < inputs.size(); ++i) {
-    inputs[i].level = start_level + static_cast<int>(i);
-  }
-  // We always compact all the files, so always compress.
-  for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
-    auto& picking_sr = sorted_runs[loop];
-    if (picking_sr.level == 0) {
-      FileMetaData* f = picking_sr.file;
-      inputs[0].files.push_back(f);
-    } else {
-      auto& files = inputs[picking_sr.level - start_level].files;
-      for (auto* f : vstorage->LevelFiles(picking_sr.level)) {
-        files.push_back(f);
-      }
-    }
-    char file_num_buf[256];
-    picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
-    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: size amp picking %s",
-                     cf_name.c_str(), file_num_buf);
-  }
-
-  // output files at the bottom most level, unless it's reserved
-  int output_level = vstorage->num_levels() - 1;
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
-  return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs),
-      output_level, mutable_cf_options.MaxFileSizeForLevel(output_level),
-      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options,
-                         output_level, 1),
-      /* grandparents */ {}, /* is manual */ false, score,
-      false /* deletion_compaction */,
-      CompactionReason::kUniversalSizeAmplification);
-}
-}  // namespace rocksdb
-
-#endif  // !ROCKSDB_LITE

db/compaction_picker_universal.h

@@ -1,93 +0,0 @@
-//  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).
-//
-// 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.
-
-#pragma once
-#ifndef ROCKSDB_LITE
-
-#include "db/compaction_picker.h"
-
-namespace rocksdb {
-class UniversalCompactionPicker : public CompactionPicker {
- public:
-  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
-                            const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* vstorage,
-                                     LogBuffer* log_buffer) override;
-
-  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-
- private:
-  struct SortedRun {
-    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
-              uint64_t _compensated_file_size, bool _being_compacted)
-        : level(_level),
-          file(_file),
-          size(_size),
-          compensated_file_size(_compensated_file_size),
-          being_compacted(_being_compacted) {
-      assert(compensated_file_size > 0);
-      assert(level != 0 || file != nullptr);
-    }
-
-    void Dump(char* out_buf, size_t out_buf_size,
-              bool print_path = false) const;
-
-    // sorted_run_count is added into the string to print
-    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
-                      size_t sorted_run_count) const;
-
-    int level;
-    // `file` Will be null for level > 0. For level = 0, the sorted run is
-    // for this file.
-    FileMetaData* file;
-    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
-    // files in the level. `being_compacted` should be the same for all files
-    // in a non-zero level. Use the value here.
-    uint64_t size;
-    uint64_t compensated_file_size;
-    bool being_compacted;
-  };
-
-  // Pick Universal compaction to limit read amplification
-  Compaction* PickCompactionToReduceSortedRuns(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, double score, unsigned int ratio,
-      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
-      LogBuffer* log_buffer);
-
-  // Pick Universal compaction to limit space amplification.
-  Compaction* PickCompactionToReduceSizeAmp(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, double score,
-      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
-
-  // Used in universal compaction when the enabled_trivial_move
-  // option is set. Checks whether there are any overlapping files
-  // in the input. Returns true if the input files are non
-  // overlapping.
-  bool IsInputFilesNonOverlapping(Compaction* c);
-
-  static std::vector<SortedRun> CalculateSortedRuns(
-      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
-#endif  // !ROCKSDB_LITE

db/convenience.cc

@@ -9,50 +9,19 @@
 #include "rocksdb/convenience.h"
 
 #include "db/db_impl.h"
-#include "util/cast_util.h"
 
 namespace rocksdb {
 
 void CancelAllBackgroundWork(DB* db, bool wait) {
-  (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
-      ->CancelAllBackgroundWork(wait);
+  (dynamic_cast<DBImpl*>(db))->CancelAllBackgroundWork(wait);
 }
 
 Status DeleteFilesInRange(DB* db, ColumnFamilyHandle* column_family,
                           const Slice* begin, const Slice* end) {
-  return (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
+  return (dynamic_cast<DBImpl*>(db))
       ->DeleteFilesInRange(column_family, begin, 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
 
 #endif  // ROCKSDB_LITE

db/corruption_test.cc

@@ -11,21 +11,20 @@
 
 #include "rocksdb/db.h"
 
+#include <inttypes.h>
 #include <errno.h>
 #include <fcntl.h>
-#include <inttypes.h>
 #include <sys/stat.h>
 #include <sys/types.h>
-#include "db/db_impl.h"
-#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"
-#include "util/filename.h"
-#include "util/string_util.h"
+#include "db/db_impl.h"
+#include "db/filename.h"
+#include "db/log_format.h"
+#include "db/version_set.h"
+#include "util/logging.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
 
@@ -153,7 +152,7 @@ class CorruptionTest : public testing::Test {
     struct stat sbuf;
     if (stat(fname.c_str(), &sbuf) != 0) {
       const char* msg = strerror(errno);
-      FAIL() << fname << ": " << msg;
+      ASSERT_TRUE(false) << fname << ": " << msg;
     }
 
     if (offset < 0) {
@@ -180,9 +179,6 @@ 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) {
@@ -217,7 +213,7 @@ class CorruptionTest : public testing::Test {
         return;
       }
     }
-    FAIL() << "no file found at level";
+    ASSERT_TRUE(false) << "no file found at level";
   }
 
 
@@ -316,7 +312,6 @@ TEST_F(CorruptionTest, TableFile) {
 
   Corrupt(kTableFile, 100, 1);
   Check(99, 99);
-  ASSERT_NOK(dbi->VerifyChecksum());
 }
 
 TEST_F(CorruptionTest, TableFileIndexData) {
@@ -332,11 +327,9 @@ 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) {
@@ -396,12 +389,10 @@ 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) {
@@ -433,7 +424,6 @@ 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;
@@ -455,7 +445,6 @@ 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)));

db/cuckoo_table_db_test.cc

@@ -8,10 +8,9 @@
 #include "db/db_impl.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
+#include "table/meta_blocks.h"
 #include "table/cuckoo_table_factory.h"
 #include "table/cuckoo_table_reader.h"
-#include "table/meta_blocks.h"
-#include "util/string_util.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
 
@@ -241,7 +240,7 @@ 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' + char(idx))));
+    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
   }
   dbfull()->TEST_WaitForFlushMemTable();
   ASSERT_EQ("1", FilesPerLevel());
@@ -250,7 +249,7 @@ 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' + char(idx)), Get(Key(idx)));
+    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
   }
 }
 
@@ -271,14 +270,14 @@ 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' + char(idx))));
+    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + 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' + char(idx)), Get(Key(idx)));
+    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
   }
 }
 
@@ -320,14 +319,8 @@ TEST_F(CuckooTableDBTest, AdaptiveTable) {
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  if (rocksdb::port::kLittleEndian) {
-    ::testing::InitGoogleTest(&argc, argv);
-    return RUN_ALL_TESTS();
-  }
-  else {
-    fprintf(stderr, "SKIPPED as Cuckoo table doesn't support Big Endian\n");
-    return 0;
-  }
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
 }
 
 #else

db/db_basic_test.cc

@@ -41,7 +41,7 @@ TEST_F(DBBasicTest, ReadOnlyDB) {
   Close();
 
   auto options = CurrentOptions();
-  assert(options.env == env_);
+  assert(options.env = env_);
   ASSERT_OK(ReadOnlyReopen(options));
   ASSERT_EQ("v3", Get("foo"));
   ASSERT_EQ("v2", Get("bar"));
@@ -175,8 +175,6 @@ TEST_F(DBBasicTest, LevelLimitReopen) {
   int i = 0;
   while (NumTableFilesAtLevel(2, 1) == 0) {
     ASSERT_OK(Put(1, Key(i++), value));
-    dbfull()->TEST_WaitForFlushMemTable();
-    dbfull()->TEST_WaitForCompact();
   }
 
   options.num_levels = 1;
@@ -360,15 +358,15 @@ TEST_F(DBBasicTest, FLUSH) {
     WriteOptions writeOpt = WriteOptions();
     writeOpt.disableWAL = true;
     SetPerfLevel(kEnableTime);
+    ;
     ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v1"));
     // this will now also flush the last 2 writes
     ASSERT_OK(Flush(1));
     ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v1"));
 
-    get_perf_context()->Reset();
+    perf_context.Reset();
     Get(1, "foo");
-    ASSERT_TRUE((int)get_perf_context()->get_from_output_files_time > 0);
-    ASSERT_EQ(2, (int)get_perf_context()->get_read_bytes);
+    ASSERT_TRUE((int)perf_context.get_from_output_files_time > 0);
 
     ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
     ASSERT_EQ("v1", Get(1, "foo"));
@@ -381,9 +379,9 @@ TEST_F(DBBasicTest, FLUSH) {
 
     ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
     ASSERT_EQ("v2", Get(1, "bar"));
-    get_perf_context()->Reset();
+    perf_context.Reset();
     ASSERT_EQ("v2", Get(1, "foo"));
-    ASSERT_TRUE((int)get_perf_context()->get_from_output_files_time > 0);
+    ASSERT_TRUE((int)perf_context.get_from_output_files_time > 0);
 
     writeOpt.disableWAL = false;
     ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v3"));
@@ -570,19 +568,19 @@ TEST_F(DBBasicTest, CompactBetweenSnapshots) {
 
 TEST_F(DBBasicTest, DBOpen_Options) {
   Options options = CurrentOptions();
-  Close();
-  Destroy(options);
+  std::string dbname = test::TmpDir(env_) + "/db_options_test";
+  ASSERT_OK(DestroyDB(dbname, options));
 
   // Does not exist, and create_if_missing == false: error
   DB* db = nullptr;
   options.create_if_missing = false;
-  Status s = DB::Open(options, dbname_, &db);
+  Status s = DB::Open(options, dbname, &db);
   ASSERT_TRUE(strstr(s.ToString().c_str(), "does not exist") != nullptr);
   ASSERT_TRUE(db == nullptr);
 
   // Does not exist, and create_if_missing == true: OK
   options.create_if_missing = true;
-  s = DB::Open(options, dbname_, &db);
+  s = DB::Open(options, dbname, &db);
   ASSERT_OK(s);
   ASSERT_TRUE(db != nullptr);
 
@@ -592,14 +590,14 @@ TEST_F(DBBasicTest, DBOpen_Options) {
   // Does exist, and error_if_exists == true: error
   options.create_if_missing = false;
   options.error_if_exists = true;
-  s = DB::Open(options, dbname_, &db);
+  s = DB::Open(options, dbname, &db);
   ASSERT_TRUE(strstr(s.ToString().c_str(), "exists") != nullptr);
   ASSERT_TRUE(db == nullptr);
 
   // Does exist, and error_if_exists == false: OK
   options.create_if_missing = true;
   options.error_if_exists = false;
-  s = DB::Open(options, dbname_, &db);
+  s = DB::Open(options, dbname, &db);
   ASSERT_OK(s);
   ASSERT_TRUE(db != nullptr);
 
@@ -725,7 +723,6 @@ TEST_F(DBBasicTest, FlushOneColumnFamily) {
 TEST_F(DBBasicTest, MultiGetSimple) {
   do {
     CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    SetPerfLevel(kEnableCount);
     ASSERT_OK(Put(1, "k1", "v1"));
     ASSERT_OK(Put(1, "k2", "v2"));
     ASSERT_OK(Put(1, "k3", "v3"));
@@ -739,15 +736,12 @@ TEST_F(DBBasicTest, MultiGetSimple) {
     std::vector<std::string> values(20, "Temporary data to be overwritten");
     std::vector<ColumnFamilyHandle*> cfs(keys.size(), handles_[1]);
 
-    get_perf_context()->Reset();
     std::vector<Status> s = db_->MultiGet(ReadOptions(), cfs, keys, &values);
     ASSERT_EQ(values.size(), keys.size());
     ASSERT_EQ(values[0], "v1");
     ASSERT_EQ(values[1], "v2");
     ASSERT_EQ(values[2], "v3");
     ASSERT_EQ(values[4], "v5");
-    // four kv pairs * two bytes per value
-    ASSERT_EQ(8, (int)get_perf_context()->multiget_read_bytes);
 
     ASSERT_OK(s[0]);
     ASSERT_OK(s[1]);
@@ -755,7 +749,6 @@ TEST_F(DBBasicTest, MultiGetSimple) {
     ASSERT_TRUE(s[3].IsNotFound());
     ASSERT_OK(s[4]);
     ASSERT_TRUE(s[5].IsNotFound());
-    SetPerfLevel(kDisable);
   } while (ChangeCompactOptions());
 }
 
@@ -792,30 +785,36 @@ TEST_F(DBBasicTest, MultiGetEmpty) {
 TEST_F(DBBasicTest, ChecksumTest) {
   BlockBasedTableOptions table_options;
   Options options = CurrentOptions();
-  // change when new checksum type added
-  int max_checksum = static_cast<int>(kxxHash);
-  const int kNumPerFile = 2;
 
-  // generate one table with each type of checksum
-  for (int i = 0; i <= max_checksum; ++i) {
-    table_options.checksum = static_cast<ChecksumType>(i);
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    Reopen(options);
-    for (int j = 0; j < kNumPerFile; ++j) {
-      ASSERT_OK(Put(Key(i * kNumPerFile + j), Key(i * kNumPerFile + j)));
-    }
-    ASSERT_OK(Flush());
-  }
+  table_options.checksum = kCRC32c;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  Reopen(options);
+  ASSERT_OK(Put("a", "b"));
+  ASSERT_OK(Put("c", "d"));
+  ASSERT_OK(Flush());  // table with crc checksum
 
-  // verify data with each type of checksum
-  for (int i = 0; i <= kxxHash; ++i) {
-    table_options.checksum = static_cast<ChecksumType>(i);
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    Reopen(options);
-    for (int j = 0; j < (max_checksum + 1) * kNumPerFile; ++j) {
-      ASSERT_EQ(Key(j), Get(Key(j)));
-    }
-  }
+  table_options.checksum = kxxHash;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  Reopen(options);
+  ASSERT_OK(Put("e", "f"));
+  ASSERT_OK(Put("g", "h"));
+  ASSERT_OK(Flush());  // table with xxhash checksum
+
+  table_options.checksum = kCRC32c;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  Reopen(options);
+  ASSERT_EQ("b", Get("a"));
+  ASSERT_EQ("d", Get("c"));
+  ASSERT_EQ("f", Get("e"));
+  ASSERT_EQ("h", Get("g"));
+
+  table_options.checksum = kCRC32c;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  Reopen(options);
+  ASSERT_EQ("b", Get("a"));
+  ASSERT_EQ("d", Get("c"));
+  ASSERT_EQ("f", Get("e"));
+  ASSERT_EQ("h", Get("g"));
 }
 
 // On Windows you can have either memory mapped file or a file
@@ -823,9 +822,6 @@ TEST_F(DBBasicTest, ChecksumTest) {
 // sense to run
 #ifndef OS_WIN
 TEST_F(DBBasicTest, MmapAndBufferOptions) {
-  if (!IsMemoryMappedAccessSupported()) {
-    return;
-  }
   Options options = CurrentOptions();
 
   options.use_direct_reads = true;
@@ -847,57 +843,6 @@ TEST_F(DBBasicTest, MmapAndBufferOptions) {
 }
 #endif
 
-class TestEnv : public EnvWrapper {
-  public:
-    explicit TestEnv(Env* base) : EnvWrapper(base) { };
-
-    class TestLogger : public Logger {
-      public:
-        using Logger::Logv;
-        virtual void Logv(const char *format, va_list ap) override { };
-      private:
-        virtual Status CloseImpl() override {
-          return Status::NotSupported();
-        }
-    };
-
-    virtual Status NewLogger(const std::string& fname,
-                             shared_ptr<Logger>* result) {
-      result->reset(new TestLogger());
-      return Status::OK();
-    }
-};
-
-TEST_F(DBBasicTest, DBClose) {
-  Options options = GetDefaultOptions();
-  std::string dbname = test::TmpDir(env_) + "/db_close_test";
-  ASSERT_OK(DestroyDB(dbname, options));
-
-  DB* db = nullptr;
-  options.create_if_missing = true;
-  options.env = new TestEnv(Env::Default());
-  Status s = DB::Open(options, dbname, &db);
-  ASSERT_OK(s);
-  ASSERT_TRUE(db != nullptr);
-
-  s = db->Close();
-  ASSERT_EQ(s, Status::NotSupported());
-
-  delete db;
-
-  // Provide our own logger and ensure DB::Close() does not close it
-  options.info_log.reset(new TestEnv::TestLogger());
-  options.create_if_missing = false;
-  s = DB::Open(options, dbname, &db);
-  ASSERT_OK(s);
-  ASSERT_TRUE(db != nullptr);
-
-  s = db->Close();
-  ASSERT_EQ(s, Status::OK());
-  delete db;
-  delete options.env;
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/db_blob_index_test.cc

@@ -1,410 +0,0 @@
-//  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).
-//
-// 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.
-
-#include <functional>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "db/column_family.h"
-#include "db/db_iter.h"
-#include "db/db_test_util.h"
-#include "db/dbformat.h"
-#include "db/write_batch_internal.h"
-#include "port/port.h"
-#include "port/stack_trace.h"
-#include "util/string_util.h"
-#include "utilities/merge_operators.h"
-
-namespace rocksdb {
-
-// kTypeBlobIndex is a value type used by BlobDB only. The base rocksdb
-// should accept the value type on write, and report not supported value
-// for reads, unless caller request for it explicitly. The base rocksdb
-// doesn't understand format of actual blob index (the value).
-class DBBlobIndexTest : public DBTestBase {
- public:
-  enum Tier {
-    kMemtable = 0,
-    kImmutableMemtables = 1,
-    kL0SstFile = 2,
-    kLnSstFile = 3,
-  };
-  const std::vector<Tier> kAllTiers = {Tier::kMemtable,
-                                       Tier::kImmutableMemtables,
-                                       Tier::kL0SstFile, Tier::kLnSstFile};
-
-  DBBlobIndexTest() : DBTestBase("/db_blob_index_test") {}
-
-  ColumnFamilyHandle* cfh() { return dbfull()->DefaultColumnFamily(); }
-
-  ColumnFamilyData* cfd() {
-    return reinterpret_cast<ColumnFamilyHandleImpl*>(cfh())->cfd();
-  }
-
-  Status PutBlobIndex(WriteBatch* batch, const Slice& key,
-                      const Slice& blob_index) {
-    return WriteBatchInternal::PutBlobIndex(batch, cfd()->GetID(), key,
-                                            blob_index);
-  }
-
-  Status Write(WriteBatch* batch) {
-    return dbfull()->Write(WriteOptions(), batch);
-  }
-
-  std::string GetImpl(const Slice& key, bool* is_blob_index = nullptr,
-                      const Snapshot* snapshot = nullptr) {
-    ReadOptions read_options;
-    read_options.snapshot = snapshot;
-    PinnableSlice value;
-    auto s = dbfull()->GetImpl(read_options, cfh(), key, &value,
-                               nullptr /*value_found*/, nullptr /*callback*/,
-                               is_blob_index);
-    if (s.IsNotFound()) {
-      return "NOT_FOUND";
-    }
-    if (s.IsNotSupported()) {
-      return "NOT_SUPPORTED";
-    }
-    if (!s.ok()) {
-      return s.ToString();
-    }
-    return value.ToString();
-  }
-
-  std::string GetBlobIndex(const Slice& key,
-                           const Snapshot* snapshot = nullptr) {
-    bool is_blob_index = false;
-    std::string value = GetImpl(key, &is_blob_index, snapshot);
-    if (!is_blob_index) {
-      return "NOT_BLOB";
-    }
-    return value;
-  }
-
-  ArenaWrappedDBIter* GetBlobIterator() {
-    return dbfull()->NewIteratorImpl(
-        ReadOptions(), cfd(), dbfull()->GetLatestSequenceNumber(),
-        nullptr /*read_callback*/, true /*allow_blob*/);
-  }
-
-  Options GetTestOptions() {
-    Options options;
-    options.create_if_missing = true;
-    options.num_levels = 2;
-    options.disable_auto_compactions = true;
-    // Disable auto flushes.
-    options.max_write_buffer_number = 10;
-    options.min_write_buffer_number_to_merge = 10;
-    options.merge_operator = MergeOperators::CreateStringAppendOperator();
-    return options;
-  }
-
-  void MoveDataTo(Tier tier) {
-    switch (tier) {
-      case Tier::kMemtable:
-        break;
-      case Tier::kImmutableMemtables:
-        ASSERT_OK(dbfull()->TEST_SwitchMemtable());
-        break;
-      case Tier::kL0SstFile:
-        ASSERT_OK(Flush());
-        break;
-      case Tier::kLnSstFile:
-        ASSERT_OK(Flush());
-        ASSERT_OK(Put("a", "dummy"));
-        ASSERT_OK(Put("z", "dummy"));
-        ASSERT_OK(Flush());
-        ASSERT_OK(
-            dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-#ifndef ROCKSDB_LITE
-        ASSERT_EQ("0,1", FilesPerLevel());
-#endif  // !ROCKSDB_LITE
-        break;
-    }
-  }
-};
-
-// Should be able to write kTypeBlobIndex to memtables and SST files.
-TEST_F(DBBlobIndexTest, Write) {
-  for (auto tier : kAllTiers) {
-    DestroyAndReopen(GetTestOptions());
-    for (int i = 1; i <= 5; i++) {
-      std::string index = ToString(i);
-      WriteBatch batch;
-      ASSERT_OK(PutBlobIndex(&batch, "key" + index, "blob" + index));
-      ASSERT_OK(Write(&batch));
-    }
-    MoveDataTo(tier);
-    for (int i = 1; i <= 5; i++) {
-      std::string index = ToString(i);
-      ASSERT_EQ("blob" + index, GetBlobIndex("key" + index));
-    }
-  }
-}
-
-// Get should be able to return blob index if is_blob_index is provided,
-// otherwise return Status::NotSupported status.
-TEST_F(DBBlobIndexTest, Get) {
-  for (auto tier : kAllTiers) {
-    DestroyAndReopen(GetTestOptions());
-    WriteBatch batch;
-    ASSERT_OK(batch.Put("key", "value"));
-    ASSERT_OK(PutBlobIndex(&batch, "blob_key", "blob_index"));
-    ASSERT_OK(Write(&batch));
-    MoveDataTo(tier);
-    // Verify normal value
-    bool is_blob_index = false;
-    PinnableSlice value;
-    ASSERT_EQ("value", Get("key"));
-    ASSERT_EQ("value", GetImpl("key"));
-    ASSERT_EQ("value", GetImpl("key", &is_blob_index));
-    ASSERT_FALSE(is_blob_index);
-    // Verify blob index
-    ASSERT_TRUE(Get("blob_key", &value).IsNotSupported());
-    ASSERT_EQ("NOT_SUPPORTED", GetImpl("blob_key"));
-    ASSERT_EQ("blob_index", GetImpl("blob_key", &is_blob_index));
-    ASSERT_TRUE(is_blob_index);
-  }
-}
-
-// Get should NOT return Status::NotSupported if blob index is updated with
-// a normal value.
-TEST_F(DBBlobIndexTest, Updated) {
-  for (auto tier : kAllTiers) {
-    DestroyAndReopen(GetTestOptions());
-    WriteBatch batch;
-    for (int i = 0; i < 10; i++) {
-      ASSERT_OK(PutBlobIndex(&batch, "key" + ToString(i), "blob_index"));
-    }
-    ASSERT_OK(Write(&batch));
-    // Avoid blob values from being purged.
-    const Snapshot* snapshot = dbfull()->GetSnapshot();
-    ASSERT_OK(Put("key1", "new_value"));
-    ASSERT_OK(Merge("key2", "a"));
-    ASSERT_OK(Merge("key2", "b"));
-    ASSERT_OK(Merge("key2", "c"));
-    ASSERT_OK(Delete("key3"));
-    ASSERT_OK(SingleDelete("key4"));
-    ASSERT_OK(Delete("key5"));
-    ASSERT_OK(Merge("key5", "a"));
-    ASSERT_OK(Merge("key5", "b"));
-    ASSERT_OK(Merge("key5", "c"));
-    ASSERT_OK(dbfull()->DeleteRange(WriteOptions(), cfh(), "key6", "key9"));
-    MoveDataTo(tier);
-    for (int i = 0; i < 10; i++) {
-      ASSERT_EQ("blob_index", GetBlobIndex("key" + ToString(i), snapshot));
-    }
-    ASSERT_EQ("new_value", Get("key1"));
-    ASSERT_EQ("NOT_SUPPORTED", GetImpl("key2"));
-    ASSERT_EQ("NOT_FOUND", Get("key3"));
-    ASSERT_EQ("NOT_FOUND", Get("key4"));
-    ASSERT_EQ("a,b,c", GetImpl("key5"));
-    for (int i = 6; i < 9; i++) {
-      ASSERT_EQ("NOT_FOUND", Get("key" + ToString(i)));
-    }
-    ASSERT_EQ("blob_index", GetBlobIndex("key9"));
-    dbfull()->ReleaseSnapshot(snapshot);
-  }
-}
-
-// Iterator should get blob value if allow_blob flag is set,
-// otherwise return Status::NotSupported status.
-TEST_F(DBBlobIndexTest, Iterate) {
-  const std::vector<std::vector<ValueType>> data = {
-      /*00*/ {kTypeValue},
-      /*01*/ {kTypeBlobIndex},
-      /*02*/ {kTypeValue},
-      /*03*/ {kTypeBlobIndex, kTypeValue},
-      /*04*/ {kTypeValue},
-      /*05*/ {kTypeValue, kTypeBlobIndex},
-      /*06*/ {kTypeValue},
-      /*07*/ {kTypeDeletion, kTypeBlobIndex},
-      /*08*/ {kTypeValue},
-      /*09*/ {kTypeSingleDeletion, kTypeBlobIndex},
-      /*10*/ {kTypeValue},
-      /*11*/ {kTypeMerge, kTypeMerge, kTypeMerge, kTypeBlobIndex},
-      /*12*/ {kTypeValue},
-      /*13*/
-      {kTypeMerge, kTypeMerge, kTypeMerge, kTypeDeletion, kTypeBlobIndex},
-      /*14*/ {kTypeValue},
-      /*15*/ {kTypeBlobIndex},
-      /*16*/ {kTypeValue},
-  };
-
-  auto get_key = [](int index) {
-    char buf[20];
-    snprintf(buf, sizeof(buf), "%02d", index);
-    return "key" + std::string(buf);
-  };
-
-  auto get_value = [&](int index, int version) {
-    return get_key(index) + "_value" + ToString(version);
-  };
-
-  auto check_iterator = [&](Iterator* iterator, Status::Code expected_status,
-                            const Slice& expected_value) {
-    ASSERT_EQ(expected_status, iterator->status().code());
-    if (expected_status == Status::kOk) {
-      ASSERT_TRUE(iterator->Valid());
-      ASSERT_EQ(expected_value, iterator->value());
-    } else {
-      ASSERT_FALSE(iterator->Valid());
-    }
-  };
-
-  auto create_normal_iterator = [&]() -> Iterator* {
-    return dbfull()->NewIterator(ReadOptions());
-  };
-
-  auto create_blob_iterator = [&]() -> Iterator* { return GetBlobIterator(); };
-
-  auto check_is_blob = [&](bool is_blob) {
-    return [is_blob](Iterator* iterator) {
-      ASSERT_EQ(is_blob,
-                reinterpret_cast<ArenaWrappedDBIter*>(iterator)->IsBlob());
-    };
-  };
-
-  auto verify = [&](int index, Status::Code expected_status,
-                    const Slice& forward_value, const Slice& backward_value,
-                    std::function<Iterator*()> create_iterator,
-                    std::function<void(Iterator*)> extra_check = nullptr) {
-    // Seek
-    auto* iterator = create_iterator();
-    ASSERT_OK(iterator->Refresh());
-    iterator->Seek(get_key(index));
-    check_iterator(iterator, expected_status, forward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-
-    // Next
-    iterator = create_iterator();
-    ASSERT_OK(iterator->Refresh());
-    iterator->Seek(get_key(index - 1));
-    ASSERT_TRUE(iterator->Valid());
-    iterator->Next();
-    check_iterator(iterator, expected_status, forward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-
-    // SeekForPrev
-    iterator = create_iterator();
-    ASSERT_OK(iterator->Refresh());
-    iterator->SeekForPrev(get_key(index));
-    check_iterator(iterator, expected_status, backward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-
-    // Prev
-    iterator = create_iterator();
-    iterator->Seek(get_key(index + 1));
-    ASSERT_TRUE(iterator->Valid());
-    iterator->Prev();
-    check_iterator(iterator, expected_status, backward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-  };
-
-  for (auto tier : {Tier::kMemtable} /*kAllTiers*/) {
-    // Avoid values from being purged.
-    std::vector<const Snapshot*> snapshots;
-    DestroyAndReopen(GetTestOptions());
-
-    // fill data
-    for (int i = 0; i < static_cast<int>(data.size()); i++) {
-      for (int j = static_cast<int>(data[i].size()) - 1; j >= 0; j--) {
-        std::string key = get_key(i);
-        std::string value = get_value(i, j);
-        WriteBatch batch;
-        switch (data[i][j]) {
-          case kTypeValue:
-            ASSERT_OK(Put(key, value));
-            break;
-          case kTypeDeletion:
-            ASSERT_OK(Delete(key));
-            break;
-          case kTypeSingleDeletion:
-            ASSERT_OK(SingleDelete(key));
-            break;
-          case kTypeMerge:
-            ASSERT_OK(Merge(key, value));
-            break;
-          case kTypeBlobIndex:
-            ASSERT_OK(PutBlobIndex(&batch, key, value));
-            ASSERT_OK(Write(&batch));
-            break;
-          default:
-            assert(false);
-        };
-      }
-      snapshots.push_back(dbfull()->GetSnapshot());
-    }
-    ASSERT_OK(
-        dbfull()->DeleteRange(WriteOptions(), cfh(), get_key(15), get_key(16)));
-    snapshots.push_back(dbfull()->GetSnapshot());
-    MoveDataTo(tier);
-
-    // Normal iterator
-    verify(1, Status::kNotSupported, "", "", create_normal_iterator);
-    verify(3, Status::kNotSupported, "", "", create_normal_iterator);
-    verify(5, Status::kOk, get_value(5, 0), get_value(5, 0),
-           create_normal_iterator);
-    verify(7, Status::kOk, get_value(8, 0), get_value(6, 0),
-           create_normal_iterator);
-    verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
-           create_normal_iterator);
-    verify(11, Status::kNotSupported, "", "", create_normal_iterator);
-    verify(13, Status::kOk,
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           create_normal_iterator);
-    verify(15, Status::kOk, get_value(16, 0), get_value(14, 0),
-           create_normal_iterator);
-
-    // Iterator with blob support
-    verify(1, Status::kOk, get_value(1, 0), get_value(1, 0),
-           create_blob_iterator, check_is_blob(true));
-    verify(3, Status::kOk, get_value(3, 0), get_value(3, 0),
-           create_blob_iterator, check_is_blob(true));
-    verify(5, Status::kOk, get_value(5, 0), get_value(5, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(7, Status::kOk, get_value(8, 0), get_value(6, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(11, Status::kNotSupported, "", "", create_blob_iterator);
-    verify(13, Status::kOk,
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(15, Status::kOk, get_value(16, 0), get_value(14, 0),
-           create_blob_iterator, check_is_blob(false));
-
-    for (auto* snapshot : snapshots) {
-      dbfull()->ReleaseSnapshot(snapshot);
-    }
-  }
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_block_cache_test.cc

@@ -7,9 +7,9 @@
 // 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.
 #include <cstdlib>
-#include "cache/lru_cache.h"
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
+#include "util/lru_cache.h"
 
 namespace rocksdb {
 
@@ -497,7 +497,7 @@ TEST_F(DBBlockCacheTest, CompressedCache) {
         options.compression = kNoCompression;
         break;
       default:
-        FAIL();
+        ASSERT_TRUE(false);
     }
     CreateAndReopenWithCF({"pikachu"}, options);
     // default column family doesn't have block cache
@@ -560,7 +560,7 @@ TEST_F(DBBlockCacheTest, CompressedCache) {
         ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT), 0);
         break;
       default:
-        FAIL();
+        ASSERT_TRUE(false);
     }
 
     options.create_if_missing = true;

db/db_bloom_filter_test.cc

@@ -20,23 +20,17 @@ class DBBloomFilterTest : public DBTestBase {
   DBBloomFilterTest() : DBTestBase("/db_bloom_filter_test") {}
 };
 
-class DBBloomFilterTestWithParam
-    : public DBTestBase,
-      public testing::WithParamInterface<std::tuple<bool, bool>> {
-  //                             public testing::WithParamInterface<bool> {
+class DBBloomFilterTestWithParam : public DBTestBase,
+                                   public testing::WithParamInterface<bool> {
  protected:
   bool use_block_based_filter_;
-  bool partition_filters_;
 
  public:
   DBBloomFilterTestWithParam() : DBTestBase("/db_bloom_filter_tests") {}
 
   ~DBBloomFilterTestWithParam() {}
 
-  void SetUp() override {
-    use_block_based_filter_ = std::get<0>(GetParam());
-    partition_filters_ = std::get<1>(GetParam());
-  }
+  void SetUp() override { use_block_based_filter_ = GetParam(); }
 };
 
 // KeyMayExist can lead to a few false positives, but not false negatives.
@@ -49,17 +43,7 @@ TEST_P(DBBloomFilterTestWithParam, KeyMayExist) {
     anon::OptionsOverride options_override;
     options_override.filter_policy.reset(
         NewBloomFilterPolicy(20, use_block_based_filter_));
-    options_override.partition_filters = partition_filters_;
-    options_override.metadata_block_size = 32;
     Options options = CurrentOptions(options_override);
-    if (partition_filters_ &&
-        static_cast<BlockBasedTableOptions*>(
-            options.table_factory->GetOptions())
-                ->index_type != BlockBasedTableOptions::kTwoLevelIndexSearch) {
-      // In the current implementation partitioned filters depend on partitioned
-      // indexes
-      continue;
-    }
     options.statistics = rocksdb::CreateDBStatistics();
     CreateAndReopenWithCF({"pikachu"}, options);
 
@@ -118,204 +102,192 @@ TEST_P(DBBloomFilterTestWithParam, KeyMayExist) {
 }
 
 TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
-  for (bool partition_filters : {true, false}) {
-    Options options = last_options_;
-    options.prefix_extractor.reset(NewFixedPrefixTransform(8));
-    options.statistics = rocksdb::CreateDBStatistics();
-    BlockBasedTableOptions bbto;
-    bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
-    if (partition_filters) {
-      bbto.partition_filters = true;
-      bbto.index_type = BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-    }
-    bbto.whole_key_filtering = false;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    DestroyAndReopen(options);
+  Options options = last_options_;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(8));
+  options.statistics = rocksdb::CreateDBStatistics();
+  BlockBasedTableOptions bbto;
+  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
+  bbto.whole_key_filtering = false;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  DestroyAndReopen(options);
 
-    WriteOptions wo;
-    ReadOptions ro;
-    FlushOptions fo;
-    fo.wait = true;
-    std::string value;
+  WriteOptions wo;
+  ReadOptions ro;
+  FlushOptions fo;
+  fo.wait = true;
+  std::string value;
 
-    ASSERT_OK(dbfull()->Put(wo, "barbarbar", "foo"));
-    ASSERT_OK(dbfull()->Put(wo, "barbarbar2", "foo2"));
-    ASSERT_OK(dbfull()->Put(wo, "foofoofoo", "bar"));
+  ASSERT_OK(dbfull()->Put(wo, "barbarbar", "foo"));
+  ASSERT_OK(dbfull()->Put(wo, "barbarbar2", "foo2"));
+  ASSERT_OK(dbfull()->Put(wo, "foofoofoo", "bar"));
 
-    dbfull()->Flush(fo);
+  dbfull()->Flush(fo);
 
-    ASSERT_EQ("foo", Get("barbarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ("foo2", Get("barbarbar2"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ("NOT_FOUND", Get("barbarbar3"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+  ASSERT_EQ("foo", Get("barbarbar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+  ASSERT_EQ("foo2", Get("barbarbar2"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+  ASSERT_EQ("NOT_FOUND", Get("barbarbar3"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
 
-    ASSERT_EQ("NOT_FOUND", Get("barfoofoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("NOT_FOUND", Get("barfoofoo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
 
-    ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+  ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
 
-    ro.total_order_seek = true;
-    ASSERT_TRUE(db_->Get(ro, "foobarbar", &value).IsNotFound());
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
-  }
+  ro.total_order_seek = true;
+  ASSERT_TRUE(db_->Get(ro, "foobarbar", &value).IsNotFound());
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
 }
 
 TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
-  for (bool partition_filters : {true, false}) {
-    Options options = last_options_;
-    options.prefix_extractor.reset(NewFixedPrefixTransform(3));
-    options.statistics = rocksdb::CreateDBStatistics();
+  Options options = last_options_;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(3));
+  options.statistics = rocksdb::CreateDBStatistics();
 
-    BlockBasedTableOptions bbto;
-    bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
-    bbto.whole_key_filtering = false;
-    if (partition_filters) {
-      bbto.partition_filters = true;
-      bbto.index_type = BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-    }
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    DestroyAndReopen(options);
+  BlockBasedTableOptions bbto;
+  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
+  bbto.whole_key_filtering = false;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  DestroyAndReopen(options);
 
-    WriteOptions wo;
-    ReadOptions ro;
-    FlushOptions fo;
-    fo.wait = true;
-    std::string value;
+  WriteOptions wo;
+  ReadOptions ro;
+  FlushOptions fo;
+  fo.wait = true;
+  std::string value;
 
-    ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
-    // Needs insert some keys to make sure files are not filtered out by key
-    // ranges.
-    ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
-    ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
-    dbfull()->Flush(fo);
+  ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
+  // Needs insert some keys to make sure files are not filtered out by key
+  // ranges.
+  ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
+  ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
+  dbfull()->Flush(fo);
 
-    Reopen(options);
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  Reopen(options);
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
 
-    // Reopen with whole key filtering enabled and prefix extractor
-    // NULL. Bloom filter should be off for both of whole key and
-    // prefix bloom.
-    bbto.whole_key_filtering = true;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    options.prefix_extractor.reset();
-    Reopen(options);
+  // Reopen with whole key filtering enabled and prefix extractor
+  // NULL. Bloom filter should be off for both of whole key and
+  // prefix bloom.
+  bbto.whole_key_filtering = true;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  options.prefix_extractor.reset();
+  Reopen(options);
 
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    // Write DB with only full key filtering.
-    ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
-    // Needs insert some keys to make sure files are not filtered out by key
-    // ranges.
-    ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
-    ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
-    db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  // Write DB with only full key filtering.
+  ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
+  // Needs insert some keys to make sure files are not filtered out by key
+  // ranges.
+  ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
+  ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
+  db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
 
-    // Reopen with both of whole key off and prefix extractor enabled.
-    // Still no bloom filter should be used.
-    options.prefix_extractor.reset(NewFixedPrefixTransform(3));
-    bbto.whole_key_filtering = false;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    Reopen(options);
+  // Reopen with both of whole key off and prefix extractor enabled.
+  // Still no bloom filter should be used.
+  options.prefix_extractor.reset(NewFixedPrefixTransform(3));
+  bbto.whole_key_filtering = false;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  Reopen(options);
 
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
 
-    // Try to create a DB with mixed files:
-    ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
-    // Needs insert some keys to make sure files are not filtered out by key
-    // ranges.
-    ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
-    ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
-    db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  // Try to create a DB with mixed files:
+  ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
+  // Needs insert some keys to make sure files are not filtered out by key
+  // ranges.
+  ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
+  ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
+  db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
 
-    options.prefix_extractor.reset();
-    bbto.whole_key_filtering = true;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    Reopen(options);
+  options.prefix_extractor.reset();
+  bbto.whole_key_filtering = true;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  Reopen(options);
 
-    // Try to create a DB with mixed files.
-    ASSERT_OK(dbfull()->Put(wo, "barfoo", "bar"));
-    // In this case needs insert some keys to make sure files are
-    // not filtered out by key ranges.
-    ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
-    ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
-    Flush();
+  // Try to create a DB with mixed files.
+  ASSERT_OK(dbfull()->Put(wo, "barfoo", "bar"));
+  // In this case needs insert some keys to make sure files are
+  // not filtered out by key ranges.
+  ASSERT_OK(dbfull()->Put(wo, "aaa", ""));
+  ASSERT_OK(dbfull()->Put(wo, "zzz", ""));
+  Flush();
 
-    // Now we have two files:
-    // File 1: An older file with prefix bloom.
-    // File 2: A newer file with whole bloom filter.
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
-    ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
+  // Now we have two files:
+  // File 1: An older file with prefix bloom.
+  // File 2: A newer file with whole bloom filter.
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
+  ASSERT_EQ("bar", Get("barfoo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
 
-    // Reopen with the same setting: only whole key is used
-    Reopen(options);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 5);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 6);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
-    ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
+  // Reopen with the same setting: only whole key is used
+  Reopen(options);
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 5);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 6);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
+  ASSERT_EQ("bar", Get("barfoo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
 
-    // Restart with both filters are allowed
-    options.prefix_extractor.reset(NewFixedPrefixTransform(3));
-    bbto.whole_key_filtering = true;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    Reopen(options);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
-    // File 1 will has it filtered out.
-    // File 2 will not, as prefix `foo` exists in the file.
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 8);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 10);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
-    ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+  // Restart with both filters are allowed
+  options.prefix_extractor.reset(NewFixedPrefixTransform(3));
+  bbto.whole_key_filtering = true;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  Reopen(options);
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
+  // File 1 will has it filtered out.
+  // File 2 will not, as prefix `foo` exists in the file.
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 8);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 10);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+  ASSERT_EQ("bar", Get("barfoo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
 
-    // Restart with only prefix bloom is allowed.
-    options.prefix_extractor.reset(NewFixedPrefixTransform(3));
-    bbto.whole_key_filtering = false;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    Reopen(options);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
-    ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
-    ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
-    ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
-    ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
-  }
+  // Restart with only prefix bloom is allowed.
+  options.prefix_extractor.reset(NewFixedPrefixTransform(3));
+  bbto.whole_key_filtering = false;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  Reopen(options);
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+  ASSERT_EQ("NOT_FOUND", Get("foo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+  ASSERT_EQ("NOT_FOUND", Get("bar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
+  ASSERT_EQ("foo", Get("foobar"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
+  ASSERT_EQ("bar", Get("barfoo"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
 }
 
 TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
@@ -329,12 +301,6 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
     table_options.no_block_cache = true;
     table_options.filter_policy.reset(
         NewBloomFilterPolicy(10, use_block_based_filter_));
-    table_options.partition_filters = partition_filters_;
-    if (partition_filters_) {
-      table_options.index_type =
-          BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-    }
-    table_options.metadata_block_size = 32;
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
     CreateAndReopenWithCF({"pikachu"}, options);
@@ -361,13 +327,7 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
     int reads = env_->random_read_counter_.Read();
     fprintf(stderr, "%d present => %d reads\n", N, reads);
     ASSERT_GE(reads, N);
-    if (partition_filters_) {
-      // Without block cache, we read an extra partition filter per each
-      // level*read and a partition index per each read
-      ASSERT_LE(reads, 4 * N + 2 * N / 100);
-    } else {
-      ASSERT_LE(reads, N + 2 * N / 100);
-    }
+    ASSERT_LE(reads, N + 2 * N / 100);
 
     // Lookup present keys.  Should rarely read from either sstable.
     env_->random_read_counter_.Reset();
@@ -376,13 +336,7 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
     }
     reads = env_->random_read_counter_.Read();
     fprintf(stderr, "%d missing => %d reads\n", N, reads);
-    if (partition_filters_) {
-      // With partitioned filter we read one extra filter per level per each
-      // missed read.
-      ASSERT_LE(reads, 2 * N + 3 * N / 100);
-    } else {
-      ASSERT_LE(reads, 3 * N / 100);
-    }
+    ASSERT_LE(reads, 3 * N / 100);
 
     env_->delay_sstable_sync_.store(false, std::memory_order_release);
     Close();
@@ -390,9 +344,7 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
 }
 
 INSTANTIATE_TEST_CASE_P(DBBloomFilterTestWithParam, DBBloomFilterTestWithParam,
-                        ::testing::Values(std::make_tuple(true, false),
-                                          std::make_tuple(false, true),
-                                          std::make_tuple(false, false)));
+                        ::testing::Bool());
 
 TEST_F(DBBloomFilterTest, BloomFilterRate) {
   while (ChangeFilterOptions()) {
@@ -449,13 +401,28 @@ TEST_F(DBBloomFilterTest, BloomFilterCompatibility) {
     ASSERT_EQ(Key(i), Get(1, Key(i)));
   }
   ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+}
 
-  // Check db with partitioned full filter
-  table_options.partition_filters = true;
-  table_options.index_type =
-      BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
+TEST_F(DBBloomFilterTest, BloomFilterReverseCompatibility) {
+  Options options = CurrentOptions();
+  options.statistics = rocksdb::CreateDBStatistics();
+  BlockBasedTableOptions table_options;
   table_options.filter_policy.reset(NewBloomFilterPolicy(10, false));
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+
+  // Create with full filter
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  const int maxKey = 10000;
+  for (int i = 0; i < maxKey; i++) {
+    ASSERT_OK(Put(1, Key(i), Key(i)));
+  }
+  ASSERT_OK(Put(1, Key(maxKey + 55555), Key(maxKey + 55555)));
+  Flush(1);
+
+  // Check db with block_based filter
+  table_options.filter_policy.reset(NewBloomFilterPolicy(10, true));
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   ReopenWithColumnFamilies({"default", "pikachu"}, options);
 
   // Check if they can be found
@@ -465,43 +432,6 @@ TEST_F(DBBloomFilterTest, BloomFilterCompatibility) {
   ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
 }
 
-TEST_F(DBBloomFilterTest, BloomFilterReverseCompatibility) {
-  for (bool partition_filters : {true, false}) {
-    Options options = CurrentOptions();
-    options.statistics = rocksdb::CreateDBStatistics();
-    BlockBasedTableOptions table_options;
-    if (partition_filters) {
-      table_options.partition_filters = true;
-      table_options.index_type =
-          BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-    }
-    table_options.filter_policy.reset(NewBloomFilterPolicy(10, false));
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    // Create with full filter
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    const int maxKey = 10000;
-    for (int i = 0; i < maxKey; i++) {
-      ASSERT_OK(Put(1, Key(i), Key(i)));
-    }
-    ASSERT_OK(Put(1, Key(maxKey + 55555), Key(maxKey + 55555)));
-    Flush(1);
-
-    // Check db with block_based filter
-    table_options.filter_policy.reset(NewBloomFilterPolicy(10, true));
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    ReopenWithColumnFamilies({"default", "pikachu"}, options);
-
-    // Check if they can be found
-    for (int i = 0; i < maxKey; i++) {
-      ASSERT_EQ(Key(i), Get(1, Key(i)));
-    }
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-  }
-}
-
 namespace {
 // A wrapped bloom over default FilterPolicy
 class WrappedBloom : public FilterPolicy {
@@ -656,12 +586,11 @@ TEST_F(DBBloomFilterTest, PrefixExtractorBlockFilter) {
 #ifndef ROCKSDB_LITE
 class BloomStatsTestWithParam
     : public DBBloomFilterTest,
-      public testing::WithParamInterface<std::tuple<bool, bool, bool>> {
+      public testing::WithParamInterface<std::tuple<bool, bool>> {
  public:
   BloomStatsTestWithParam() {
     use_block_table_ = std::get<0>(GetParam());
     use_block_based_builder_ = std::get<1>(GetParam());
-    partition_filters_ = std::get<2>(GetParam());
 
     options_.create_if_missing = true;
     options_.prefix_extractor.reset(rocksdb::NewFixedPrefixTransform(4));
@@ -670,28 +599,20 @@ class BloomStatsTestWithParam
     if (use_block_table_) {
       BlockBasedTableOptions table_options;
       table_options.hash_index_allow_collision = false;
-      if (partition_filters_) {
-        assert(!use_block_based_builder_);
-        table_options.partition_filters = partition_filters_;
-        table_options.index_type =
-            BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-      }
       table_options.filter_policy.reset(
           NewBloomFilterPolicy(10, use_block_based_builder_));
       options_.table_factory.reset(NewBlockBasedTableFactory(table_options));
     } else {
-      assert(!partition_filters_);  // not supported in plain table
       PlainTableOptions table_options;
       options_.table_factory.reset(NewPlainTableFactory(table_options));
     }
-    options_.env = env_;
 
-    get_perf_context()->Reset();
+    perf_context.Reset();
     DestroyAndReopen(options_);
   }
 
   ~BloomStatsTestWithParam() {
-    get_perf_context()->Reset();
+    perf_context.Reset();
     Destroy(options_);
   }
 
@@ -701,7 +622,6 @@ class BloomStatsTestWithParam
 
   bool use_block_table_;
   bool use_block_based_builder_;
-  bool partition_filters_;
   Options options_;
 };
 
@@ -724,33 +644,33 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTest) {
 
   // check memtable bloom stats
   ASSERT_EQ(value1, Get(key1));
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
+  ASSERT_EQ(1, perf_context.bloom_memtable_hit_count);
   ASSERT_EQ(value3, Get(key3));
-  ASSERT_EQ(2, get_perf_context()->bloom_memtable_hit_count);
-  ASSERT_EQ(0, get_perf_context()->bloom_memtable_miss_count);
+  ASSERT_EQ(2, perf_context.bloom_memtable_hit_count);
+  ASSERT_EQ(0, perf_context.bloom_memtable_miss_count);
 
   ASSERT_EQ("NOT_FOUND", Get(key2));
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_miss_count);
-  ASSERT_EQ(2, get_perf_context()->bloom_memtable_hit_count);
+  ASSERT_EQ(1, perf_context.bloom_memtable_miss_count);
+  ASSERT_EQ(2, perf_context.bloom_memtable_hit_count);
 
   // sanity checks
-  ASSERT_EQ(0, get_perf_context()->bloom_sst_hit_count);
-  ASSERT_EQ(0, get_perf_context()->bloom_sst_miss_count);
+  ASSERT_EQ(0, perf_context.bloom_sst_hit_count);
+  ASSERT_EQ(0, perf_context.bloom_sst_miss_count);
 
   Flush();
 
   // sanity checks
-  ASSERT_EQ(0, get_perf_context()->bloom_sst_hit_count);
-  ASSERT_EQ(0, get_perf_context()->bloom_sst_miss_count);
+  ASSERT_EQ(0, perf_context.bloom_sst_hit_count);
+  ASSERT_EQ(0, perf_context.bloom_sst_miss_count);
 
   // check SST bloom stats
   ASSERT_EQ(value1, Get(key1));
-  ASSERT_EQ(1, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(1, perf_context.bloom_sst_hit_count);
   ASSERT_EQ(value3, Get(key3));
-  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(2, perf_context.bloom_sst_hit_count);
 
   ASSERT_EQ("NOT_FOUND", Get(key2));
-  ASSERT_EQ(1, get_perf_context()->bloom_sst_miss_count);
+  ASSERT_EQ(1, perf_context.bloom_sst_miss_count);
 }
 
 // Same scenario as in BloomStatsTest but using an iterator
@@ -771,21 +691,21 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
   ASSERT_OK(iter->status());
   ASSERT_TRUE(iter->Valid());
   ASSERT_EQ(value1, iter->value().ToString());
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-  ASSERT_EQ(0, get_perf_context()->bloom_memtable_miss_count);
+  ASSERT_EQ(1, perf_context.bloom_memtable_hit_count);
+  ASSERT_EQ(0, perf_context.bloom_memtable_miss_count);
 
   iter->Seek(key3);
   ASSERT_OK(iter->status());
   ASSERT_TRUE(iter->Valid());
   ASSERT_EQ(value3, iter->value().ToString());
-  ASSERT_EQ(2, get_perf_context()->bloom_memtable_hit_count);
-  ASSERT_EQ(0, get_perf_context()->bloom_memtable_miss_count);
+  ASSERT_EQ(2, perf_context.bloom_memtable_hit_count);
+  ASSERT_EQ(0, perf_context.bloom_memtable_miss_count);
 
   iter->Seek(key2);
   ASSERT_OK(iter->status());
   ASSERT_TRUE(!iter->Valid());
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_miss_count);
-  ASSERT_EQ(2, get_perf_context()->bloom_memtable_hit_count);
+  ASSERT_EQ(1, perf_context.bloom_memtable_miss_count);
+  ASSERT_EQ(2, perf_context.bloom_memtable_hit_count);
 
   Flush();
 
@@ -796,27 +716,25 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
   ASSERT_OK(iter->status());
   ASSERT_TRUE(iter->Valid());
   ASSERT_EQ(value1, iter->value().ToString());
-  ASSERT_EQ(1, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(1, perf_context.bloom_sst_hit_count);
 
   iter->Seek(key3);
   ASSERT_OK(iter->status());
   ASSERT_TRUE(iter->Valid());
   ASSERT_EQ(value3, iter->value().ToString());
-  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(2, perf_context.bloom_sst_hit_count);
 
   iter->Seek(key2);
   ASSERT_OK(iter->status());
   ASSERT_TRUE(!iter->Valid());
-  ASSERT_EQ(1, get_perf_context()->bloom_sst_miss_count);
-  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(1, perf_context.bloom_sst_miss_count);
+  ASSERT_EQ(2, perf_context.bloom_sst_hit_count);
 }
 
 INSTANTIATE_TEST_CASE_P(BloomStatsTestWithParam, BloomStatsTestWithParam,
-                        ::testing::Values(std::make_tuple(true, true, false),
-                                          std::make_tuple(true, false, false),
-                                          std::make_tuple(true, false, true),
-                                          std::make_tuple(false, false,
-                                                          false)));
+                        ::testing::Values(std::make_tuple(true, true),
+                                          std::make_tuple(true, false),
+                                          std::make_tuple(false, false)));
 
 namespace {
 void PrefixScanInit(DBBloomFilterTest* dbtest) {

db/db_compaction_filter_test.cc

@@ -24,36 +24,6 @@ class DBTestCompactionFilter : public DBTestBase {
   DBTestCompactionFilter() : DBTestBase("/db_compaction_filter_test") {}
 };
 
-// Param variant of DBTestBase::ChangeCompactOptions
-class DBTestCompactionFilterWithCompactParam
-    : public DBTestCompactionFilter,
-      public ::testing::WithParamInterface<DBTestBase::OptionConfig> {
- public:
-  DBTestCompactionFilterWithCompactParam() : DBTestCompactionFilter() {
-    option_config_ = GetParam();
-    Destroy(last_options_);
-    auto options = CurrentOptions();
-    if (option_config_ == kDefault || option_config_ == kUniversalCompaction ||
-        option_config_ == kUniversalCompactionMultiLevel) {
-      options.create_if_missing = true;
-    }
-    if (option_config_ == kLevelSubcompactions ||
-        option_config_ == kUniversalSubcompactions) {
-      assert(options.max_subcompactions > 1);
-    }
-    TryReopen(options);
-  }
-};
-
-INSTANTIATE_TEST_CASE_P(
-    DBTestCompactionFilterWithCompactOption,
-    DBTestCompactionFilterWithCompactParam,
-    ::testing::Values(DBTestBase::OptionConfig::kDefault,
-                      DBTestBase::OptionConfig::kUniversalCompaction,
-                      DBTestBase::OptionConfig::kUniversalCompactionMultiLevel,
-                      DBTestBase::OptionConfig::kLevelSubcompactions,
-                      DBTestBase::OptionConfig::kUniversalSubcompactions));
-
 class KeepFilter : public CompactionFilter {
  public:
   virtual bool Filter(int level, const Slice& key, const Slice& value,
@@ -338,6 +308,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
       ParsedInternalKey ikey(Slice(), 0, kTypeValue);
+      ikey.sequence = -1;
       ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
       total++;
       if (ikey.sequence != 0) {
@@ -469,63 +440,65 @@ TEST_F(DBTestCompactionFilter, CompactionFilterDeletesAll) {
 }
 #endif  // ROCKSDB_LITE
 
-TEST_P(DBTestCompactionFilterWithCompactParam,
-       CompactionFilterWithValueChange) {
-  Options options = CurrentOptions();
-  options.num_levels = 3;
-  options.compaction_filter_factory = std::make_shared<ChangeFilterFactory>();
-  CreateAndReopenWithCF({"pikachu"}, options);
+TEST_F(DBTestCompactionFilter, CompactionFilterWithValueChange) {
+  do {
+    Options options = CurrentOptions();
+    options.num_levels = 3;
+    options.compaction_filter_factory =
+      std::make_shared<ChangeFilterFactory>();
+    CreateAndReopenWithCF({"pikachu"}, options);
 
-  // Write 100K+1 keys, these are written to a few files
-  // in L0. We do this so that the current snapshot points
-  // to the 100001 key.The compaction filter is  not invoked
-  // on keys that are visible via a snapshot because we
-  // anyways cannot delete it.
-  const std::string value(10, 'x');
-  for (int i = 0; i < 100001; i++) {
-    char key[100];
-    snprintf(key, sizeof(key), "B%010d", i);
-    Put(1, key, value);
-  }
+    // Write 100K+1 keys, these are written to a few files
+    // in L0. We do this so that the current snapshot points
+    // to the 100001 key.The compaction filter is  not invoked
+    // on keys that are visible via a snapshot because we
+    // anyways cannot delete it.
+    const std::string value(10, 'x');
+    for (int i = 0; i < 100001; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%010d", i);
+      Put(1, key, value);
+    }
 
-  // push all files to  lower levels
-  ASSERT_OK(Flush(1));
-  if (option_config_ != kUniversalCompactionMultiLevel &&
-      option_config_ != kUniversalSubcompactions) {
-    dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-    dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-  } else {
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-  }
+    // push all files to  lower levels
+    ASSERT_OK(Flush(1));
+    if (option_config_ != kUniversalCompactionMultiLevel &&
+        option_config_ != kUniversalSubcompactions) {
+      dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+      dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+    } else {
+      dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
+                             nullptr);
+    }
 
-  // re-write all data again
-  for (int i = 0; i < 100001; i++) {
-    char key[100];
-    snprintf(key, sizeof(key), "B%010d", i);
-    Put(1, key, value);
-  }
+    // re-write all data again
+    for (int i = 0; i < 100001; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%010d", i);
+      Put(1, key, value);
+    }
 
-  // push all files to  lower levels. This should
-  // invoke the compaction filter for all 100000 keys.
-  ASSERT_OK(Flush(1));
-  if (option_config_ != kUniversalCompactionMultiLevel &&
-      option_config_ != kUniversalSubcompactions) {
-    dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-    dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-  } else {
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-  }
+    // push all files to  lower levels. This should
+    // invoke the compaction filter for all 100000 keys.
+    ASSERT_OK(Flush(1));
+    if (option_config_ != kUniversalCompactionMultiLevel &&
+        option_config_ != kUniversalSubcompactions) {
+      dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+      dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+    } else {
+      dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
+                             nullptr);
+    }
 
-  // verify that all keys now have the new value that
-  // was set by the compaction process.
-  for (int i = 0; i < 100001; i++) {
-    char key[100];
-    snprintf(key, sizeof(key), "B%010d", i);
-    std::string newvalue = Get(1, key);
-    ASSERT_EQ(newvalue.compare(NEW_VALUE), 0);
-  }
+    // verify that all keys now have the new value that
+    // was set by the compaction process.
+    for (int i = 0; i < 100001; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%010d", i);
+      std::string newvalue = Get(1, key);
+      ASSERT_EQ(newvalue.compare(NEW_VALUE), 0);
+    }
+  } while (ChangeCompactOptions());
 }
 
 TEST_F(DBTestCompactionFilter, CompactionFilterWithMergeOperator) {
@@ -644,6 +617,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
       ParsedInternalKey ikey(Slice(), 0, kTypeValue);
+      ikey.sequence = -1;
       ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
       total++;
       if (ikey.sequence != 0) {
@@ -652,7 +626,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
       iter->Next();
     }
     ASSERT_EQ(total, 700);
-    ASSERT_EQ(count, 1);
+    ASSERT_EQ(count, 2);
   }
 }
 #endif  // ROCKSDB_LITE
@@ -804,7 +778,7 @@ TEST_F(DBTestCompactionFilter, SkipUntil) {
 
   cfilter_skips = 0;
   ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  // Number of skips in tables: 2, 3, 3, 3.
+  // Numberof skips in tables: 2, 3, 3, 3.
   ASSERT_EQ(11, cfilter_skips);
 
   for (int table = 0; table < 4; ++table) {
@@ -825,43 +799,6 @@ TEST_F(DBTestCompactionFilter, SkipUntil) {
   }
 }
 
-TEST_F(DBTestCompactionFilter, SkipUntilWithBloomFilter) {
-  BlockBasedTableOptions table_options;
-  table_options.whole_key_filtering = false;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(100, false));
-
-  Options options = CurrentOptions();
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  options.prefix_extractor.reset(NewCappedPrefixTransform(9));
-  options.compaction_filter_factory = std::make_shared<SkipEvenFilterFactory>();
-  options.disable_auto_compactions = true;
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-
-  Put("0000000010", "v10");
-  Put("0000000020", "v20"); // skipped
-  Put("0000000050", "v50");
-  Flush();
-
-  cfilter_skips = 0;
-  EXPECT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  EXPECT_EQ(1, cfilter_skips);
-
-  Status s;
-  std::string val;
-
-  s = db_->Get(ReadOptions(), "0000000010", &val);
-  ASSERT_OK(s);
-  EXPECT_EQ("v10", val);
-
-  s = db_->Get(ReadOptions(), "0000000020", &val);
-  EXPECT_TRUE(s.IsNotFound());
-
-  s = db_->Get(ReadOptions(), "0000000050", &val);
-  ASSERT_OK(s);
-  EXPECT_EQ("v50", val);
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/db_compaction_test.cc

@@ -40,12 +40,6 @@ class DBCompactionTestWithParam
   bool exclusive_manual_compaction_;
 };
 
-class DBCompactionDirectIOTest : public DBCompactionTest,
-                                 public ::testing::WithParamInterface<bool> {
- public:
-  DBCompactionDirectIOTest() : DBCompactionTest() {}
-};
-
 namespace {
 
 class FlushedFileCollector : public EventListener {
@@ -218,84 +212,6 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
   }
 }
 
-TEST_P(DBCompactionTestWithParam, CompactionsPreserveDeletes) {
-  //  For each options type we test following
-  //  - Enable preserve_deletes
-  //  - write bunch of keys and deletes
-  //  - Set start_seqnum to the beginning; compact; check that keys are present
-  //  - rewind start_seqnum way forward; compact; check that keys are gone
-
-  for (int tid = 0; tid < 3; ++tid) {
-    Options options = DeletionTriggerOptions(CurrentOptions());
-    options.max_subcompactions = max_subcompactions_;
-    options.preserve_deletes=true;
-    options.num_levels = 2;
-
-    if (tid == 1) {
-      options.skip_stats_update_on_db_open = true;
-    } else if (tid == 2) {
-      // third pass with universal compaction
-      options.compaction_style = kCompactionStyleUniversal;
-    }
-
-    DestroyAndReopen(options);
-    Random rnd(301);
-    // highlight the default; all deletes should be preserved
-    SetPreserveDeletesSequenceNumber(0);
-
-    const int kTestSize = kCDTKeysPerBuffer;
-    std::vector<std::string> values;
-    for (int k = 0; k < kTestSize; ++k) {
-      values.push_back(RandomString(&rnd, kCDTValueSize));
-      ASSERT_OK(Put(Key(k), values[k]));
-    }
-
-    for (int k = 0; k < kTestSize; ++k) {
-      ASSERT_OK(Delete(Key(k)));
-    }
-    // to ensure we tackle all tombstones
-    CompactRangeOptions cro;
-    cro.change_level = true;
-    cro.target_level = 2;
-    cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
-
-    dbfull()->TEST_WaitForFlushMemTable();
-    dbfull()->CompactRange(cro, nullptr, nullptr);
-
-    // check that normal user iterator doesn't see anything
-    Iterator* db_iter = dbfull()->NewIterator(ReadOptions());
-    int i = 0;
-    for (db_iter->SeekToFirst(); db_iter->Valid(); db_iter->Next()) {
-      i++;
-    }
-    ASSERT_EQ(i, 0);
-    delete db_iter;
-
-    // check that iterator that sees internal keys sees tombstones
-    ReadOptions ro;
-    ro.iter_start_seqnum=1;
-    db_iter = dbfull()->NewIterator(ro);
-    i = 0;
-    for (db_iter->SeekToFirst(); db_iter->Valid(); db_iter->Next()) {
-      i++;
-    }
-    ASSERT_EQ(i, 4);
-    delete db_iter;
-
-    // now all deletes should be gone
-    SetPreserveDeletesSequenceNumber(100000000);
-    dbfull()->CompactRange(cro, nullptr, nullptr);
-
-    db_iter = dbfull()->NewIterator(ro);
-    i = 0;
-    for (db_iter->SeekToFirst(); db_iter->Valid(); db_iter->Next()) {
-      i++;
-    }
-    ASSERT_EQ(i, 0);
-    delete db_iter;
-  }
-}
-
 TEST_F(DBCompactionTest, SkipStatsUpdateTest) {
   // This test verify UpdateAccumulatedStats is not on
   // if options.skip_stats_update_on_db_open = true
@@ -597,6 +513,7 @@ TEST_F(DBCompactionTest, BGCompactionsAllowed) {
   options.level0_file_num_compaction_trigger = 2;
   options.level0_slowdown_writes_trigger = 20;
   options.soft_pending_compaction_bytes_limit = 1 << 30;  // Infinitely large
+  options.base_background_compactions = 1;
   options.max_background_compactions = 3;
   options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
 
@@ -855,41 +772,6 @@ TEST_F(DBCompactionTest, ZeroSeqIdCompaction) {
   ASSERT_OK(Put("", ""));
 }
 
-TEST_F(DBCompactionTest, ManualCompactionUnknownOutputSize) {
-  // github issue #2249
-  Options options = CurrentOptions();
-  options.compaction_style = kCompactionStyleLevel;
-  options.level0_file_num_compaction_trigger = 3;
-  DestroyAndReopen(options);
-
-  // create two files in l1 that we can compact
-  for (int i = 0; i < 2; ++i) {
-    for (int j = 0; j < options.level0_file_num_compaction_trigger; j++) {
-      // make l0 files' ranges overlap to avoid trivial move
-      Put(std::to_string(2 * i), std::string(1, 'A'));
-      Put(std::to_string(2 * i + 1), std::string(1, 'A'));
-      Flush();
-      dbfull()->TEST_WaitForFlushMemTable();
-    }
-    dbfull()->TEST_WaitForCompact();
-    ASSERT_EQ(NumTableFilesAtLevel(0, 0), 0);
-    ASSERT_EQ(NumTableFilesAtLevel(1, 0), i + 1);
-  }
-
-  ColumnFamilyMetaData cf_meta;
-  dbfull()->GetColumnFamilyMetaData(dbfull()->DefaultColumnFamily(), &cf_meta);
-  ASSERT_EQ(2, cf_meta.levels[1].files.size());
-  std::vector<std::string> input_filenames;
-  for (const auto& sst_file : cf_meta.levels[1].files) {
-    input_filenames.push_back(sst_file.name);
-  }
-
-  // note CompactionOptions::output_file_size_limit is unset.
-  CompactionOptions compact_opt;
-  compact_opt.compression = kNoCompression;
-  dbfull()->CompactFiles(compact_opt, input_filenames, 1);
-}
-
 // Check that writes done during a memtable compaction are recovered
 // if the database is shutdown during the memtable compaction.
 TEST_F(DBCompactionTest, RecoverDuringMemtableCompaction) {
@@ -1270,8 +1152,7 @@ TEST_P(DBCompactionTestWithParam, ManualCompactionPartial) {
   }
 }
 
-// Disable as the test is flaky.
-TEST_F(DBCompactionTest, DISABLED_ManualPartialFill) {
+TEST_F(DBCompactionTest, ManualPartialFill) {
   int32_t trivial_move = 0;
   int32_t non_trivial_move = 0;
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
@@ -1305,9 +1186,6 @@ TEST_F(DBCompactionTest, DISABLED_ManualPartialFill) {
   options.max_background_compactions = 3;
 
   DestroyAndReopen(options);
-  // make sure all background compaction jobs can be scheduled
-  auto stop_token =
-      dbfull()->TEST_write_controler().GetCompactionPressureToken();
   int32_t value_size = 10 * 1024;  // 10 KB
 
   // Add 2 non-overlapping files
@@ -1517,60 +1395,6 @@ TEST_F(DBCompactionTest, DeleteFileRange) {
   ASSERT_GT(old_num_files, new_num_files);
 }
 
-TEST_F(DBCompactionTest, DeleteFileRangeFileEndpointsOverlapBug) {
-  // regression test for #2833: groups of files whose user-keys overlap at the
-  // endpoints could be split by `DeleteFilesInRange`. This caused old data to
-  // reappear, either because a new version of the key was removed, or a range
-  // deletion was partially dropped. It could also cause non-overlapping
-  // invariant to be violated if the files dropped by DeleteFilesInRange were
-  // a subset of files that a range deletion spans.
-  const int kNumL0Files = 2;
-  const int kValSize = 8 << 10;  // 8KB
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = kNumL0Files;
-  options.target_file_size_base = 1 << 10;  // 1KB
-  DestroyAndReopen(options);
-
-  // The snapshot prevents key 1 from having its old version dropped. The low
-  // `target_file_size_base` ensures two keys will be in each output file.
-  const Snapshot* snapshot = nullptr;
-  Random rnd(301);
-  // The value indicates which flush the key belonged to, which is enough
-  // for us to determine the keys' relative ages. After L0 flushes finish,
-  // files look like:
-  //
-  // File 0: 0 -> vals[0], 1 -> vals[0]
-  // File 1:               1 -> vals[1], 2 -> vals[1]
-  //
-  // Then L0->L1 compaction happens, which outputs keys as follows:
-  //
-  // File 0: 0 -> vals[0], 1 -> vals[1]
-  // File 1:               1 -> vals[0], 2 -> vals[1]
-  //
-  // DeleteFilesInRange shouldn't be allowed to drop just file 0, as that
-  // would cause `1 -> vals[0]` (an older key) to reappear.
-  std::string vals[kNumL0Files];
-  for (int i = 0; i < kNumL0Files; ++i) {
-    vals[i] = RandomString(&rnd, kValSize);
-    Put(Key(i), vals[i]);
-    Put(Key(i + 1), vals[i]);
-    Flush();
-    if (i == 0) {
-      snapshot = db_->GetSnapshot();
-    }
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  // Verify `DeleteFilesInRange` can't drop only file 0 which would cause
-  // "1 -> vals[0]" to reappear.
-  std::string begin_str = Key(0), end_str = Key(1);
-  Slice begin = begin_str, end = end_str;
-  ASSERT_OK(DeleteFilesInRange(db_, db_->DefaultColumnFamily(), &begin, &end));
-  ASSERT_EQ(vals[1], Get(Key(1)));
-
-  db_->ReleaseSnapshot(snapshot);
-}
-
 TEST_P(DBCompactionTestWithParam, TrivialMoveToLastLevelWithFiles) {
   int32_t trivial_move = 0;
   int32_t non_trivial_move = 0;
@@ -2019,47 +1843,6 @@ TEST_F(DBCompactionTest, L0_CompactionBug_Issue44_b) {
   } while (ChangeCompactOptions());
 }
 
-TEST_F(DBCompactionTest, ManualAutoRace) {
-  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-  rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::BGWorkCompaction", "DBCompactionTest::ManualAutoRace:1"},
-       {"DBImpl::RunManualCompaction:WaitScheduled",
-        "BackgroundCallCompaction:0"}});
-
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Put(1, "foo", "");
-  Put(1, "bar", "");
-  Flush(1);
-  Put(1, "foo", "");
-  Put(1, "bar", "");
-  // Generate four files in CF 0, which should trigger an auto compaction
-  Put("foo", "");
-  Put("bar", "");
-  Flush();
-  Put("foo", "");
-  Put("bar", "");
-  Flush();
-  Put("foo", "");
-  Put("bar", "");
-  Flush();
-  Put("foo", "");
-  Put("bar", "");
-  Flush();
-
-  // The auto compaction is scheduled but waited until here
-  TEST_SYNC_POINT("DBCompactionTest::ManualAutoRace:1");
-  // The auto compaction will wait until the manual compaction is registerd
-  // before processing so that it will be cancelled.
-  dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr, nullptr);
-  ASSERT_EQ("0,1", FilesPerLevel(1));
-
-  // Eventually the cancelled compaction will be rescheduled and executed.
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ("0,1", FilesPerLevel(0));
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
-
 TEST_P(DBCompactionTestWithParam, ManualCompaction) {
   Options options = CurrentOptions();
   options.max_subcompactions = max_subcompactions_;
@@ -2109,6 +1892,7 @@ TEST_P(DBCompactionTestWithParam, ManualCompaction) {
 
     if (iter == 0) {
       options = CurrentOptions();
+      options.max_background_flushes = 0;
       options.num_levels = 3;
       options.create_if_missing = true;
       options.statistics = rocksdb::CreateDBStatistics();
@@ -2554,12 +2338,15 @@ TEST_F(DBCompactionTest, SanitizeCompactionOptionsTest) {
   options.hard_pending_compaction_bytes_limit = 100;
   options.create_if_missing = true;
   DestroyAndReopen(options);
+  ASSERT_EQ(5, db_->GetOptions().base_background_compactions);
   ASSERT_EQ(100, db_->GetOptions().soft_pending_compaction_bytes_limit);
 
+  options.base_background_compactions = 4;
   options.max_background_compactions = 3;
   options.soft_pending_compaction_bytes_limit = 200;
   options.hard_pending_compaction_bytes_limit = 150;
   DestroyAndReopen(options);
+  ASSERT_EQ(3, db_->GetOptions().base_background_compactions);
   ASSERT_EQ(150, db_->GetOptions().soft_pending_compaction_bytes_limit);
 }
 
@@ -2705,337 +2492,12 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
 
-TEST_P(DBCompactionTestWithParam, IntraL0Compaction) {
-  Options options = CurrentOptions();
-  options.compression = kNoCompression;
-  options.level0_file_num_compaction_trigger = 5;
-  options.max_background_compactions = 2;
-  options.max_subcompactions = max_subcompactions_;
-  DestroyAndReopen(options);
-
-  const size_t kValueSize = 1 << 20;
-  Random rnd(301);
-  std::string value(RandomString(&rnd, kValueSize));
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"LevelCompactionPicker::PickCompactionBySize:0",
-        "CompactionJob::Run():Start"}});
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  // index:   0   1   2   3   4   5   6   7   8   9
-  // size:  1MB 1MB 1MB 1MB 1MB 2MB 1MB 1MB 1MB 1MB
-  // score:                     1.5 1.3 1.5 2.0 inf
-  //
-  // Files 0-4 will be included in an L0->L1 compaction.
-  //
-  // L0->L0 will be triggered since the sync points guarantee compaction to base
-  // level is still blocked when files 5-9 trigger another compaction.
-  //
-  // Files 6-9 are the longest span of available files for which
-  // work-per-deleted-file decreases (see "score" row above).
-  for (int i = 0; i < 10; ++i) {
-    ASSERT_OK(Put(Key(0), ""));  // prevents trivial move
-    if (i == 5) {
-      ASSERT_OK(Put(Key(i + 1), value + value));
-    } else {
-      ASSERT_OK(Put(Key(i + 1), value));
-    }
-    ASSERT_OK(Flush());
-  }
-  dbfull()->TEST_WaitForCompact();
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  std::vector<std::vector<FileMetaData>> level_to_files;
-  dbfull()->TEST_GetFilesMetaData(dbfull()->DefaultColumnFamily(),
-                                  &level_to_files);
-  ASSERT_GE(level_to_files.size(), 2);  // at least L0 and L1
-  // L0 has the 2MB file (not compacted) and 4MB file (output of L0->L0)
-  ASSERT_EQ(2, level_to_files[0].size());
-  ASSERT_GT(level_to_files[1].size(), 0);
-  for (int i = 0; i < 2; ++i) {
-    ASSERT_GE(level_to_files[0][i].fd.file_size, 1 << 21);
-  }
-}
-
-TEST_P(DBCompactionTestWithParam, IntraL0CompactionDoesNotObsoleteDeletions) {
-  // regression test for issue #2722: L0->L0 compaction can resurrect deleted
-  // keys from older L0 files if L1+ files' key-ranges do not include the key.
-  Options options = CurrentOptions();
-  options.compression = kNoCompression;
-  options.level0_file_num_compaction_trigger = 5;
-  options.max_background_compactions = 2;
-  options.max_subcompactions = max_subcompactions_;
-  DestroyAndReopen(options);
-
-  const size_t kValueSize = 1 << 20;
-  Random rnd(301);
-  std::string value(RandomString(&rnd, kValueSize));
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"LevelCompactionPicker::PickCompactionBySize:0",
-        "CompactionJob::Run():Start"}});
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  // index:   0   1   2   3   4    5    6   7   8   9
-  // size:  1MB 1MB 1MB 1MB 1MB  1MB  1MB 1MB 1MB 1MB
-  // score:                     1.25 1.33 1.5 2.0 inf
-  //
-  // Files 0-4 will be included in an L0->L1 compaction.
-  //
-  // L0->L0 will be triggered since the sync points guarantee compaction to base
-  // level is still blocked when files 5-9 trigger another compaction. All files
-  // 5-9 are included in the L0->L0 due to work-per-deleted file decreasing.
-  //
-  // Put a key-value in files 0-4. Delete that key in files 5-9. Verify the
-  // L0->L0 preserves the deletion such that the key remains deleted.
-  for (int i = 0; i < 10; ++i) {
-    // key 0 serves both to prevent trivial move and as the key we want to
-    // verify is not resurrected by L0->L0 compaction.
-    if (i < 5) {
-      ASSERT_OK(Put(Key(0), ""));
-    } else {
-      ASSERT_OK(Delete(Key(0)));
-    }
-    ASSERT_OK(Put(Key(i + 1), value));
-    ASSERT_OK(Flush());
-  }
-  dbfull()->TEST_WaitForCompact();
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  std::vector<std::vector<FileMetaData>> level_to_files;
-  dbfull()->TEST_GetFilesMetaData(dbfull()->DefaultColumnFamily(),
-                                  &level_to_files);
-  ASSERT_GE(level_to_files.size(), 2);  // at least L0 and L1
-  // L0 has a single output file from L0->L0
-  ASSERT_EQ(1, level_to_files[0].size());
-  ASSERT_GT(level_to_files[1].size(), 0);
-  ASSERT_GE(level_to_files[0][0].fd.file_size, 1 << 22);
-
-  ReadOptions roptions;
-  std::string result;
-  ASSERT_TRUE(db_->Get(roptions, Key(0), &result).IsNotFound());
-}
-
-TEST_F(DBCompactionTest, OptimizedDeletionObsoleting) {
-  // Deletions can be dropped when compacted to non-last level if they fall
-  // outside the lower-level files' key-ranges.
-  const int kNumL0Files = 4;
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = kNumL0Files;
-  options.statistics = rocksdb::CreateDBStatistics();
-  DestroyAndReopen(options);
-
-  // put key 1 and 3 in separate L1, L2 files.
-  // So key 0, 2, and 4+ fall outside these levels' key-ranges.
-  for (int level = 2; level >= 1; --level) {
-    for (int i = 0; i < 2; ++i) {
-      Put(Key(2 * i + 1), "val");
-      Flush();
-    }
-    MoveFilesToLevel(level);
-    ASSERT_EQ(2, NumTableFilesAtLevel(level));
-  }
-
-  // Delete keys in range [1, 4]. These L0 files will be compacted with L1:
-  // - Tombstones for keys 2 and 4 can be dropped early.
-  // - Tombstones for keys 1 and 3 must be kept due to L2 files' key-ranges.
-  for (int i = 0; i < kNumL0Files; ++i) {
-    Put(Key(0), "val");  // sentinel to prevent trivial move
-    Delete(Key(i + 1));
-    Flush();
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  for (int i = 0; i < kNumL0Files; ++i) {
-    std::string value;
-    ASSERT_TRUE(db_->Get(ReadOptions(), Key(i + 1), &value).IsNotFound());
-  }
-  ASSERT_EQ(2, options.statistics->getTickerCount(
-                   COMPACTION_OPTIMIZED_DEL_DROP_OBSOLETE));
-  ASSERT_EQ(2,
-            options.statistics->getTickerCount(COMPACTION_KEY_DROP_OBSOLETE));
-}
-
-TEST_F(DBCompactionTest, CompactFilesPendingL0Bug) {
-  // https://www.facebook.com/groups/rocksdb.dev/permalink/1389452781153232/
-  // CompactFiles() had a bug where it failed to pick a compaction when an L0
-  // compaction existed, but marked it as scheduled anyways. It'd never be
-  // unmarked as scheduled, so future compactions or DB close could hang.
-  const int kNumL0Files = 5;
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = kNumL0Files - 1;
-  options.max_background_compactions = 2;
-  DestroyAndReopen(options);
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"LevelCompactionPicker::PickCompaction:Return",
-        "DBCompactionTest::CompactFilesPendingL0Bug:Picked"},
-       {"DBCompactionTest::CompactFilesPendingL0Bug:ManualCompacted",
-        "DBImpl::BackgroundCompaction:NonTrivial:AfterRun"}});
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  auto schedule_multi_compaction_token =
-      dbfull()->TEST_write_controler().GetCompactionPressureToken();
-
-  // Files 0-3 will be included in an L0->L1 compaction.
-  //
-  // File 4 will be included in a call to CompactFiles() while the first
-  // compaction is running.
-  for (int i = 0; i < kNumL0Files - 1; ++i) {
-    ASSERT_OK(Put(Key(0), "val"));  // sentinel to prevent trivial move
-    ASSERT_OK(Put(Key(i + 1), "val"));
-    ASSERT_OK(Flush());
-  }
-  TEST_SYNC_POINT("DBCompactionTest::CompactFilesPendingL0Bug:Picked");
-  // file 4 flushed after 0-3 picked
-  ASSERT_OK(Put(Key(kNumL0Files), "val"));
-  ASSERT_OK(Flush());
-
-  // previously DB close would hang forever as this situation caused scheduled
-  // compactions count to never decrement to zero.
-  ColumnFamilyMetaData cf_meta;
-  dbfull()->GetColumnFamilyMetaData(dbfull()->DefaultColumnFamily(), &cf_meta);
-  ASSERT_EQ(kNumL0Files, cf_meta.levels[0].files.size());
-  std::vector<std::string> input_filenames;
-  input_filenames.push_back(cf_meta.levels[0].files.front().name);
-  ASSERT_OK(dbfull()
-                  ->CompactFiles(CompactionOptions(), input_filenames,
-                                 0 /* output_level */));
-  TEST_SYNC_POINT("DBCompactionTest::CompactFilesPendingL0Bug:ManualCompacted");
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
-
-TEST_F(DBCompactionTest, CompactFilesOverlapInL0Bug) {
-  // Regression test for bug of not pulling in L0 files that overlap the user-
-  // specified input files in time- and key-ranges.
-  Put(Key(0), "old_val");
-  Flush();
-  Put(Key(0), "new_val");
-  Flush();
-
-  ColumnFamilyMetaData cf_meta;
-  dbfull()->GetColumnFamilyMetaData(dbfull()->DefaultColumnFamily(), &cf_meta);
-  ASSERT_GE(cf_meta.levels.size(), 2);
-  ASSERT_EQ(2, cf_meta.levels[0].files.size());
-
-  // Compacting {new L0 file, L1 file} should pull in the old L0 file since it
-  // overlaps in key-range and time-range.
-  std::vector<std::string> input_filenames;
-  input_filenames.push_back(cf_meta.levels[0].files.front().name);
-  ASSERT_OK(dbfull()->CompactFiles(CompactionOptions(), input_filenames,
-                                   1 /* output_level */));
-  ASSERT_EQ("new_val", Get(Key(0)));
-}
-
-TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
-  // bottom-level files may contain deletions due to snapshots protecting the
-  // deleted keys. Once the snapshot is released, we should see files with many
-  // such deletions undergo single-file compactions.
-  const int kNumKeysPerFile = 1024;
-  const int kNumLevelFiles = 4;
-  const int kValueSize = 128;
-  Options options = CurrentOptions();
-  options.compression = kNoCompression;
-  options.level0_file_num_compaction_trigger = kNumLevelFiles;
-  // inflate it a bit to account for key/metadata overhead
-  options.target_file_size_base = 120 * kNumKeysPerFile * kValueSize / 100;
-  Reopen(options);
-
-  Random rnd(301);
-  const Snapshot* snapshot = nullptr;
-  for (int i = 0; i < kNumLevelFiles; ++i) {
-    for (int j = 0; j < kNumKeysPerFile; ++j) {
-      ASSERT_OK(
-          Put(Key(i * kNumKeysPerFile + j), RandomString(&rnd, kValueSize)));
-    }
-    if (i == kNumLevelFiles - 1) {
-      snapshot = db_->GetSnapshot();
-      // delete every other key after grabbing a snapshot, so these deletions
-      // and the keys they cover can't be dropped until after the snapshot is
-      // released.
-      for (int j = 0; j < kNumLevelFiles * kNumKeysPerFile; j += 2) {
-        ASSERT_OK(Delete(Key(j)));
-      }
-    }
-    Flush();
-    if (i < kNumLevelFiles - 1) {
-      ASSERT_EQ(i + 1, NumTableFilesAtLevel(0));
-    }
-  }
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(kNumLevelFiles, NumTableFilesAtLevel(1));
-
-  std::vector<LiveFileMetaData> pre_release_metadata, post_release_metadata;
-  db_->GetLiveFilesMetaData(&pre_release_metadata);
-  // just need to bump seqnum so ReleaseSnapshot knows the newest key in the SST
-  // files does not need to be preserved in case of a future snapshot.
-  ASSERT_OK(Put(Key(0), "val"));
-  // release snapshot and wait for compactions to finish. Single-file
-  // compactions should be triggered, which reduce the size of each bottom-level
-  // file without changing file count.
-  db_->ReleaseSnapshot(snapshot);
-  dbfull()->TEST_WaitForCompact();
-  db_->GetLiveFilesMetaData(&post_release_metadata);
-  ASSERT_EQ(pre_release_metadata.size(), post_release_metadata.size());
-
-  for (size_t i = 0; i < pre_release_metadata.size(); ++i) {
-    const auto& pre_file = pre_release_metadata[i];
-    const auto& post_file = post_release_metadata[i];
-    ASSERT_EQ(1, pre_file.level);
-    ASSERT_EQ(1, post_file.level);
-    // each file is smaller than it was before as it was rewritten without
-    // deletion markers/deleted keys.
-    ASSERT_LT(post_file.size, pre_file.size);
-  }
-}
-
 INSTANTIATE_TEST_CASE_P(DBCompactionTestWithParam, DBCompactionTestWithParam,
                         ::testing::Values(std::make_tuple(1, true),
                                           std::make_tuple(1, false),
                                           std::make_tuple(4, true),
                                           std::make_tuple(4, false)));
 
-TEST_P(DBCompactionDirectIOTest, DirectIO) {
-  Options options = CurrentOptions();
-  Destroy(options);
-  options.create_if_missing = true;
-  options.disable_auto_compactions = true;
-  options.use_direct_io_for_flush_and_compaction = GetParam();
-  options.env = new MockEnv(Env::Default());
-  Reopen(options);
-  bool readahead = false;
-  SyncPoint::GetInstance()->SetCallBack(
-      "TableCache::NewIterator:for_compaction", [&](void* arg) {
-        bool* use_direct_reads = static_cast<bool*>(arg);
-        ASSERT_EQ(*use_direct_reads,
-                  options.use_direct_io_for_flush_and_compaction);
-      });
-  SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::OpenCompactionOutputFile", [&](void* arg) {
-        bool* use_direct_writes = static_cast<bool*>(arg);
-        ASSERT_EQ(*use_direct_writes,
-                  options.use_direct_io_for_flush_and_compaction);
-      });
-  if (options.use_direct_io_for_flush_and_compaction) {
-    SyncPoint::GetInstance()->SetCallBack(
-        "SanitizeOptions:direct_io", [&](void* arg) {
-          readahead = true;
-        });
-  }
-  SyncPoint::GetInstance()->EnableProcessing();
-  CreateAndReopenWithCF({"pikachu"}, options);
-  MakeTables(3, "p", "q", 1);
-  ASSERT_EQ("1,1,1", FilesPerLevel(1));
-  Compact(1, "p1", "p9");
-  ASSERT_FALSE(readahead ^ options.use_direct_io_for_flush_and_compaction);
-  ASSERT_EQ("0,0,1", FilesPerLevel(1));
-  Destroy(options);
-  delete options.env;
-}
-
-INSTANTIATE_TEST_CASE_P(DBCompactionDirectIOTest, DBCompactionDirectIOTest,
-                        testing::Bool());
-
 class CompactionPriTest : public DBTestBase,
                           public testing::WithParamInterface<uint32_t> {
  public:

db/db_dynamic_level_test.cc

@@ -57,6 +57,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
       Options options;
       options.env = env.get();
       options.create_if_missing = true;
+      options.db_write_buffer_size = 2048;
       options.write_buffer_size = 2048;
       options.max_write_buffer_number = 2;
       options.level0_file_num_compaction_trigger = 2;
@@ -74,7 +75,6 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
       options.compression_per_level[0] = kNoCompression;
       options.compression_per_level[1] = kLZ4Compression;
       options.compression_per_level[2] = kSnappyCompression;
-      options.env = env_;
 
       DestroyAndReopen(options);
 
@@ -126,6 +126,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
 
   Options options = CurrentOptions();
   options.create_if_missing = true;
+  options.db_write_buffer_size = 204800;
   options.write_buffer_size = 20480;
   options.max_write_buffer_number = 2;
   options.level0_file_num_compaction_trigger = 2;
@@ -282,6 +283,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesCompactRange) {
 
   Options options = CurrentOptions();
   options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
   options.write_buffer_size = 2048;
   options.max_write_buffer_number = 2;
   options.level0_file_num_compaction_trigger = 2;
@@ -359,6 +361,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesCompactRange) {
 TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
   Options options = CurrentOptions();
   options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
   options.write_buffer_size = 2048;
   options.max_write_buffer_number = 2;
   options.level0_file_num_compaction_trigger = 2;
@@ -371,7 +374,6 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
   options.soft_rate_limit = 1.1;
   options.max_background_compactions = 2;
   options.num_levels = 5;
-  options.max_compaction_bytes = 100000000;
 
   DestroyAndReopen(options);
 
@@ -411,6 +413,7 @@ TEST_F(DBTestDynamicLevel, DISABLED_MigrateToDynamicLevelMaxBytesBase) {
 
   Options options;
   options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
   options.write_buffer_size = 2048;
   options.max_write_buffer_number = 8;
   options.level0_file_num_compaction_trigger = 4;

db/db_encryption_test.cc

@@ -1,94 +0,0 @@
-//  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).
-//
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "rocksdb/perf_context.h"
-#if !defined(ROCKSDB_LITE)
-#include "util/sync_point.h"
-#endif
-#include <iostream>
-#include <string>
-
-namespace rocksdb {
-
-class DBEncryptionTest : public DBTestBase {
- public:
-  DBEncryptionTest() : DBTestBase("/db_encryption_test") {}
-};
-
-#ifndef ROCKSDB_LITE
-
-TEST_F(DBEncryptionTest, CheckEncrypted) {
-  ASSERT_OK(Put("foo567", "v1.fetdq"));
-  ASSERT_OK(Put("bar123", "v2.dfgkjdfghsd"));
-  Close();
-
-  // Open all files and look for the values we've put in there.
-  // They should not be found if encrypted, otherwise
-  // they should be found.
-  std::vector<std::string> fileNames;
-  auto status = env_->GetChildren(dbname_, &fileNames);
-  ASSERT_OK(status);
-
-  auto defaultEnv = Env::Default();
-  int hits = 0;
-  for (auto it = fileNames.begin() ; it != fileNames.end(); ++it) {
-    if ((*it == "..") || (*it == ".")) {
-      continue;
-    }
-    auto filePath = dbname_ + "/" + *it;
-    unique_ptr<SequentialFile> seqFile;
-    auto envOptions = EnvOptions(CurrentOptions());
-    status = defaultEnv->NewSequentialFile(filePath, &seqFile, envOptions);
-    ASSERT_OK(status);
-
-    uint64_t fileSize;
-    status = defaultEnv->GetFileSize(filePath, &fileSize);
-    ASSERT_OK(status);
-
-    std::string scratch;
-    scratch.reserve(fileSize);
-    Slice data;
-    status = seqFile->Read(fileSize, &data, (char*)scratch.data());
-    ASSERT_OK(status);
-
-    if (data.ToString().find("foo567") != std::string::npos) {
-      hits++; 
-      //std::cout << "Hit in " << filePath << "\n";
-    }
-    if (data.ToString().find("v1.fetdq") != std::string::npos) {
-      hits++; 
-      //std::cout << "Hit in " << filePath << "\n";
-    }
-    if (data.ToString().find("bar123") != std::string::npos) {
-      hits++; 
-      //std::cout << "Hit in " << filePath << "\n";
-    }
-    if (data.ToString().find("v2.dfgkjdfghsd") != std::string::npos) {
-      hits++; 
-      //std::cout << "Hit in " << filePath << "\n";
-    }
-    if (data.ToString().find("dfgk") != std::string::npos) {
-      hits++; 
-      //std::cout << "Hit in " << filePath << "\n";
-    }
-  }
-  if (encrypted_env_) {
-    ASSERT_EQ(hits, 0);
-  } else {
-    ASSERT_GE(hits, 4);
-  }
-}
-
-#endif // ROCKSDB_LITE
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_filesnapshot.cc

@@ -15,13 +15,13 @@
 #include <algorithm>
 #include <string>
 #include "db/db_impl.h"
+#include "db/filename.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "util/file_util.h"
-#include "util/filename.h"
 #include "util/mutexlock.h"
 #include "util/sync_point.h"
 
@@ -31,11 +31,12 @@ Status DBImpl::DisableFileDeletions() {
   InstrumentedMutexLock l(&mutex_);
   ++disable_delete_obsolete_files_;
   if (disable_delete_obsolete_files_ == 1) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Disabled");
+    Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+        "File Deletions Disabled");
   } else {
-    ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                   "File Deletions Disabled, but already disabled. Counter: %d",
-                   disable_delete_obsolete_files_);
+    Log(InfoLogLevel::WARN_LEVEL, immutable_db_options_.info_log,
+        "File Deletions Disabled, but already disabled. Counter: %d",
+        disable_delete_obsolete_files_);
   }
   return Status::OK();
 }
@@ -54,13 +55,12 @@ Status DBImpl::EnableFileDeletions(bool force) {
       --disable_delete_obsolete_files_;
     }
     if (disable_delete_obsolete_files_ == 0)  {
-      ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Enabled");
+      Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+          "File Deletions Enabled");
       should_purge_files = true;
       FindObsoleteFiles(&job_context, true);
-      bg_cv_.SignalAll();
     } else {
-      ROCKS_LOG_WARN(
-          immutable_db_options_.info_log,
+      Log(InfoLogLevel::WARN_LEVEL, immutable_db_options_.info_log,
           "File Deletions Enable, but not really enabled. Counter: %d",
           disable_delete_obsolete_files_);
     }
@@ -106,8 +106,8 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
 
     if (!status.ok()) {
       mutex_.Unlock();
-      ROCKS_LOG_ERROR(immutable_db_options_.info_log, "Cannot Flush data %s\n",
-                      status.ToString().c_str());
+      Log(InfoLogLevel::ERROR_LEVEL, immutable_db_options_.info_log,
+          "Cannot Flush data %s\n", status.ToString().c_str());
       return status;
     }
   }
@@ -142,18 +142,6 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
 }
 
 Status DBImpl::GetSortedWalFiles(VectorLogPtr& files) {
-  {
-    // If caller disabled deletions, this function should return files that are
-    // guaranteed not to be deleted until deletions are re-enabled. We need to
-    // wait for pending purges to finish since WalManager doesn't know which
-    // files are going to be purged. Additional purges won't be scheduled as
-    // long as deletions are disabled (so the below loop must terminate).
-    InstrumentedMutexLock l(&mutex_);
-    while (disable_delete_obsolete_files_ > 0 &&
-           pending_purge_obsolete_files_ > 0) {
-      bg_cv_.Wait();
-    }
-  }
   return wal_manager_.GetSortedWalFiles(files);
 }
 

db/db_flush_test.cc

@@ -19,19 +19,12 @@ class DBFlushTest : public DBTestBase {
   DBFlushTest() : DBTestBase("/db_flush_test") {}
 };
 
-class DBFlushDirectIOTest : public DBFlushTest,
-                            public ::testing::WithParamInterface<bool> {
- public:
-  DBFlushDirectIOTest() : DBFlushTest() {}
-};
-
 // We had issue when two background threads trying to flush at the same time,
 // only one of them get committed. The test verifies the issue is fixed.
 TEST_F(DBFlushTest, FlushWhileWritingManifest) {
   Options options;
   options.disable_auto_compactions = true;
   options.max_background_flushes = 2;
-  options.env = env_;
   Reopen(options);
   FlushOptions no_wait;
   no_wait.wait = false;
@@ -57,7 +50,7 @@ TEST_F(DBFlushTest, FlushWhileWritingManifest) {
 
 TEST_F(DBFlushTest, SyncFail) {
   std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
-      new FaultInjectionTestEnv(env_));
+      new FaultInjectionTestEnv(Env::Default()));
   Options options;
   options.disable_auto_compactions = true;
   options.env = fault_injection_env.get();
@@ -89,105 +82,6 @@ TEST_F(DBFlushTest, SyncFail) {
   Destroy(options);
 }
 
-TEST_F(DBFlushTest, FlushInLowPriThreadPool) {
-  // Verify setting an empty high-pri (flush) thread pool causes flushes to be
-  // scheduled in the low-pri (compaction) thread pool.
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = 4;
-  options.memtable_factory.reset(new SpecialSkipListFactory(1));
-  Reopen(options);
-  env_->SetBackgroundThreads(0, Env::HIGH);
-
-  std::thread::id tid;
-  int num_flushes = 0, num_compactions = 0;
-  SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::BGWorkFlush", [&](void* arg) {
-        if (tid == std::thread::id()) {
-          tid = std::this_thread::get_id();
-        } else {
-          ASSERT_EQ(tid, std::this_thread::get_id());
-        }
-        ++num_flushes;
-      });
-  SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::BGWorkCompaction", [&](void* arg) {
-        ASSERT_EQ(tid, std::this_thread::get_id());
-        ++num_compactions;
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("key", "val"));
-  for (int i = 0; i < 4; ++i) {
-    ASSERT_OK(Put("key", "val"));
-    dbfull()->TEST_WaitForFlushMemTable();
-  }
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(4, num_flushes);
-  ASSERT_EQ(1, num_compactions);
-}
-
-TEST_F(DBFlushTest, ManualFlushWithMinWriteBufferNumberToMerge) {
-  Options options = CurrentOptions();
-  options.write_buffer_size = 100;
-  options.max_write_buffer_number = 4;
-  options.min_write_buffer_number_to_merge = 3;
-  Reopen(options);
-
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::BGWorkFlush",
-        "DBFlushTest::ManualFlushWithMinWriteBufferNumberToMerge:1"},
-       {"DBFlushTest::ManualFlushWithMinWriteBufferNumberToMerge:2",
-        "DBImpl::FlushMemTableToOutputFile:BeforeInstallSV"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("key1", "value1"));
-
-  port::Thread t([&]() {
-    // The call wait for flush to finish, i.e. with flush_options.wait = true.
-    ASSERT_OK(Flush());
-  });
-
-  // Wait for flush start.
-  TEST_SYNC_POINT("DBFlushTest::ManualFlushWithMinWriteBufferNumberToMerge:1");
-  // Insert a second memtable before the manual flush finish.
-  // At the end of the manual flush job, it will check if further flush
-  // is needed, but it will not trigger flush of the second memtable because
-  // min_write_buffer_number_to_merge is not reached.
-  ASSERT_OK(Put("key2", "value2"));
-  ASSERT_OK(dbfull()->TEST_SwitchMemtable());
-  TEST_SYNC_POINT("DBFlushTest::ManualFlushWithMinWriteBufferNumberToMerge:2");
-
-  // Manual flush should return, without waiting for flush indefinitely.
-  t.join();
-}
-
-TEST_P(DBFlushDirectIOTest, DirectIO) {
-  Options options;
-  options.create_if_missing = true;
-  options.disable_auto_compactions = true;
-  options.max_background_flushes = 2;
-  options.use_direct_io_for_flush_and_compaction = GetParam();
-  options.env = new MockEnv(Env::Default());
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:create_file", [&](void* arg) {
-        bool* use_direct_writes = static_cast<bool*>(arg);
-        ASSERT_EQ(*use_direct_writes,
-                  options.use_direct_io_for_flush_and_compaction);
-      });
-
-  SyncPoint::GetInstance()->EnableProcessing();
-  Reopen(options);
-  ASSERT_OK(Put("foo", "v"));
-  FlushOptions flush_options;
-  flush_options.wait = true;
-  ASSERT_OK(dbfull()->Flush(flush_options));
-  Destroy(options);
-  delete options.env;
-}
-
-INSTANTIATE_TEST_CASE_P(DBFlushDirectIOTest, DBFlushDirectIOTest,
-                        testing::Bool());
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/db_impl.h

@@ -28,40 +28,35 @@
 #include "db/flush_scheduler.h"
 #include "db/internal_stats.h"
 #include "db/log_writer.h"
-#include "db/pre_release_callback.h"
-#include "db/read_callback.h"
-#include "db/snapshot_checker.h"
 #include "db/snapshot_impl.h"
 #include "db/version_edit.h"
 #include "db/wal_manager.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
 #include "memtable_list.h"
-#include "monitoring/instrumented_mutex.h"
-#include "options/db_options.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/memtablerep.h"
-#include "rocksdb/status.h"
 #include "rocksdb/transaction_log.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/db_options.h"
 #include "util/event_logger.h"
 #include "util/hash.h"
+#include "util/instrumented_mutex.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
 
-class Arena;
-class ArenaWrappedDBIter;
 class MemTable;
 class TableCache;
 class Version;
 class VersionEdit;
 class VersionSet;
+class Arena;
 class WriteCallback;
 struct JobContext;
 struct ExternalSstFileInfo;
@@ -69,8 +64,7 @@ struct MemTableInfo;
 
 class DBImpl : public DB {
  public:
-  DBImpl(const DBOptions& options, const std::string& dbname,
-         const bool seq_per_batch = false);
+  DBImpl(const DBOptions& options, const std::string& dbname);
   virtual ~DBImpl();
 
   // Implementations of the DB interface
@@ -97,15 +91,7 @@ class DBImpl : public DB {
   using DB::Get;
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
-                     PinnableSlice* value) override;
-
-  // Function that Get and KeyMayExist call with no_io true or false
-  // Note: 'value_found' from KeyMayExist propagates here
-  Status GetImpl(const ReadOptions& options, ColumnFamilyHandle* column_family,
-                 const Slice& key, PinnableSlice* value,
-                 bool* value_found = nullptr, ReadCallback* callback = nullptr,
-                 bool* is_blob_index = nullptr);
-
+                     std::string* value) override;
   using DB::MultiGet;
   virtual std::vector<Status> MultiGet(
       const ReadOptions& options,
@@ -113,19 +99,10 @@ class DBImpl : public DB {
       const std::vector<Slice>& keys,
       std::vector<std::string>* values) override;
 
-  virtual Status CreateColumnFamily(const ColumnFamilyOptions& cf_options,
+  virtual Status CreateColumnFamily(const ColumnFamilyOptions& options,
                                     const std::string& column_family,
                                     ColumnFamilyHandle** handle) override;
-  virtual Status CreateColumnFamilies(
-      const ColumnFamilyOptions& cf_options,
-      const std::vector<std::string>& column_family_names,
-      std::vector<ColumnFamilyHandle*>* handles) override;
-  virtual Status CreateColumnFamilies(
-      const std::vector<ColumnFamilyDescriptor>& column_families,
-      std::vector<ColumnFamilyHandle*>* handles) override;
   virtual Status DropColumnFamily(ColumnFamilyHandle* column_family) override;
-  virtual Status DropColumnFamilies(
-      const std::vector<ColumnFamilyHandle*>& column_families) override;
 
   // Returns false if key doesn't exist in the database and true if it may.
   // If value_found is not passed in as null, then return the value if found in
@@ -136,7 +113,6 @@ class DBImpl : public DB {
                            ColumnFamilyHandle* column_family, const Slice& key,
                            std::string* value,
                            bool* value_found = nullptr) override;
-
   using DB::NewIterator;
   virtual Iterator* NewIterator(const ReadOptions& options,
                                 ColumnFamilyHandle* column_family) override;
@@ -144,22 +120,15 @@ class DBImpl : public DB {
       const ReadOptions& options,
       const std::vector<ColumnFamilyHandle*>& column_families,
       std::vector<Iterator*>* iterators) override;
-  ArenaWrappedDBIter* NewIteratorImpl(const ReadOptions& options,
-                                      ColumnFamilyData* cfd,
-                                      SequenceNumber snapshot,
-                                      ReadCallback* read_callback,
-                                      bool allow_blob = false,
-                                      bool allow_refresh = true);
-
   virtual const Snapshot* GetSnapshot() override;
   virtual void ReleaseSnapshot(const Snapshot* snapshot) override;
   using DB::GetProperty;
   virtual bool GetProperty(ColumnFamilyHandle* column_family,
                            const Slice& property, std::string* value) override;
   using DB::GetMapProperty;
-  virtual bool GetMapProperty(
-      ColumnFamilyHandle* column_family, const Slice& property,
-      std::map<std::string, std::string>* value) override;
+  virtual bool GetMapProperty(ColumnFamilyHandle* column_family,
+                              const Slice& property,
+                              std::map<std::string, double>* value) override;
   using DB::GetIntProperty;
   virtual bool GetIntProperty(ColumnFamilyHandle* column_family,
                               const Slice& property, uint64_t* value) override;
@@ -218,21 +187,11 @@ class DBImpl : public DB {
   using DB::Flush;
   virtual Status Flush(const FlushOptions& options,
                        ColumnFamilyHandle* column_family) override;
-  virtual Status FlushWAL(bool sync) override;
   virtual Status SyncWAL() override;
 
   virtual SequenceNumber GetLatestSequenceNumber() const override;
-  virtual void SetLastPublishedSequence(SequenceNumber seq);
-  // Returns LastSequence in last_seq_same_as_publish_seq_
-  // mode and LastAllocatedSequence otherwise. This is useful when visiblility
-  // depends also on data written to the WAL but not to the memtable.
-  SequenceNumber TEST_GetLastVisibleSequence() const;
-
-  virtual bool SetPreserveDeletesSequenceNumber(SequenceNumber seqnum) override;
 
 #ifndef ROCKSDB_LITE
-  using DB::ResetStats;
-  virtual Status ResetStats() override;
   virtual Status DisableFileDeletions() override;
   virtual Status EnableFileDeletions(bool force) override;
   virtual int IsFileDeletionsEnabled() const;
@@ -261,11 +220,11 @@ class DBImpl : public DB {
       ColumnFamilyHandle* column_family,
       ColumnFamilyMetaData* metadata) override;
 
+  // experimental API
   Status SuggestCompactRange(ColumnFamilyHandle* column_family,
-                             const Slice* begin, const Slice* end) override;
+                             const Slice* begin, const Slice* end);
 
-  Status PromoteL0(ColumnFamilyHandle* column_family,
-                   int target_level) override;
+  Status PromoteL0(ColumnFamilyHandle* column_family, int target_level);
 
   // Similar to Write() but will call the callback once on the single write
   // thread to determine whether it is safe to perform the write.
@@ -311,8 +270,7 @@ class DBImpl : public DB {
   // TODO(andrewkr): this API need to be aware of range deletion operations
   Status GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
                                  bool cache_only, SequenceNumber* seq,
-                                 bool* found_record_for_key,
-                                 bool* is_blob_index = nullptr);
+                                 bool* found_record_for_key);
 
   using DB::IngestExternalFile;
   virtual Status IngestExternalFile(
@@ -320,8 +278,6 @@ class DBImpl : public DB {
       const std::vector<std::string>& external_files,
       const IngestExternalFileOptions& ingestion_options) override;
 
-  virtual Status VerifyChecksum() override;
-
 #endif  // ROCKSDB_LITE
 
   // Similar to GetSnapshot(), but also lets the db know that this snapshot
@@ -358,7 +314,7 @@ class DBImpl : public DB {
                            ColumnFamilyHandle* column_family = nullptr,
                            bool disallow_trivial_move = false);
 
-  void TEST_SwitchWAL();
+  void TEST_MaybeFlushColumnFamilies();
 
   bool TEST_UnableToFlushOldestLog() {
     return unable_to_flush_oldest_log_;
@@ -368,8 +324,6 @@ class DBImpl : public DB {
     return alive_log_files_.begin()->getting_flushed;
   }
 
-  Status TEST_SwitchMemtable(ColumnFamilyData* cfd = nullptr);
-
   // Force current memtable contents to be flushed.
   Status TEST_FlushMemTable(bool wait = true,
                             ColumnFamilyHandle* cfh = nullptr);
@@ -388,9 +342,6 @@ class DBImpl : public DB {
   // Return the current manifest file no.
   uint64_t TEST_Current_Manifest_FileNo();
 
-  // Returns the number that'll be assigned to the next file that's created.
-  uint64_t TEST_Current_Next_FileNo();
-
   // get total level0 file size. Only for testing.
   uint64_t TEST_GetLevel0TotalSize();
 
@@ -422,9 +373,9 @@ class DBImpl : public DB {
   Status TEST_GetAllImmutableCFOptions(
       std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map);
 
-  // Return the lastest MutableCFOptions of a column family
+  // Return the lastest MutableCFOptions of of a column family
   Status TEST_GetLatestMutableCFOptions(ColumnFamilyHandle* column_family,
-                                        MutableCFOptions* mutable_cf_options);
+                                        MutableCFOptions* mutable_cf_opitons);
 
   Cache* TEST_table_cache() { return table_cache_.get(); }
 
@@ -434,21 +385,12 @@ class DBImpl : public DB {
   uint64_t TEST_FindMinPrepLogReferencedByMemTable();
 
   int TEST_BGCompactionsAllowed() const;
-  int TEST_BGFlushesAllowed() const;
 
 #endif  // NDEBUG
 
-  struct BGJobLimits {
-    int max_flushes;
-    int max_compactions;
-  };
-  // Returns maximum background flushes and compactions allowed to be scheduled
-  BGJobLimits GetBGJobLimits() const;
-  // Need a static version that can be called during SanitizeOptions().
-  static BGJobLimits GetBGJobLimits(int max_background_flushes,
-                                    int max_background_compactions,
-                                    int max_background_jobs,
-                                    bool parallelize_compactions);
+  // Return maximum background compaction allowed to be scheduled based on
+  // compaction status.
+  int BGCompactionsAllowed() const;
 
   // move logs pending closing from job_context to the DB queue and
   // schedule a purge
@@ -468,8 +410,6 @@ class DBImpl : public DB {
   // belong to live files are posibly removed. Also, removes all the
   // files in sst_delete_files and log_delete_files.
   // It is not necessary to hold the mutex when invoking this method.
-  // If FindObsoleteFiles() was run, we need to also run
-  // PurgeObsoleteFiles(), even if disable_delete_obsolete_files_ is true
   void PurgeObsoleteFiles(const JobContext& background_contet,
                           bool schedule_only = false);
 
@@ -496,9 +436,6 @@ class DBImpl : public DB {
   // mutex is held.
   SuperVersion* GetAndRefSuperVersion(uint32_t column_family_id);
 
-  // Un-reference the super version and clean it up if it is the last reference.
-  void CleanupSuperVersion(SuperVersion* sv);
-
   // Un-reference the super version and return it to thread local cache if
   // needed. If it is the last reference of the super version. Clean it up
   // after un-referencing it.
@@ -514,9 +451,6 @@ class DBImpl : public DB {
   // mutex is released.
   ColumnFamilyHandle* GetColumnFamilyHandle(uint32_t column_family_id);
 
-  // Same as above, should called without mutex held and not on write thread.
-  ColumnFamilyHandle* GetColumnFamilyHandleUnlocked(uint32_t column_family_id);
-
   // Returns the number of currently running flushes.
   // REQUIREMENT: mutex_ must be held when calling this function.
   int num_running_flushes() {
@@ -533,12 +467,6 @@ class DBImpl : public DB {
 
   const WriteController& write_controller() { return write_controller_; }
 
-  InternalIterator* NewInternalIterator(const ReadOptions&,
-                                        ColumnFamilyData* cfd,
-                                        SuperVersion* super_version,
-                                        Arena* arena,
-                                        RangeDelAggregator* range_del_agg);
-
   // hollow transactions shell used for recovery.
   // these will then be passed to TransactionDB so that
   // locks can be reacquired before writing can resume.
@@ -546,11 +474,9 @@ class DBImpl : public DB {
     uint64_t log_number_;
     std::string name_;
     WriteBatch* batch_;
-    // The seq number of the first key in the batch
-    SequenceNumber seq_;
     explicit RecoveredTransaction(const uint64_t log, const std::string& name,
-                                  WriteBatch* batch, SequenceNumber seq)
-        : log_number_(log), name_(name), batch_(batch), seq_(seq) {}
+                                  WriteBatch* batch)
+        : log_number_(log), name_(name), batch_(batch) {}
 
     ~RecoveredTransaction() { delete batch_; }
   };
@@ -572,9 +498,8 @@ class DBImpl : public DB {
   }
 
   void InsertRecoveredTransaction(const uint64_t log, const std::string& name,
-                                  WriteBatch* batch, SequenceNumber seq) {
-    recovered_transactions_[name] =
-        new RecoveredTransaction(log, name, batch, seq);
+                                  WriteBatch* batch) {
+    recovered_transactions_[name] = new RecoveredTransaction(log, name, batch);
     MarkLogAsContainingPrepSection(log);
   }
 
@@ -601,26 +526,12 @@ class DBImpl : public DB {
     logs_to_free_queue_.push_back(log_writer);
   }
 
-  void SetSnapshotChecker(SnapshotChecker* snapshot_checker);
-
-  InstrumentedMutex* mutex() { return &mutex_; }
-
   Status NewDB();
 
-  // This is to be used only by internal rocksdb classes.
-  static Status Open(const DBOptions& db_options, const std::string& name,
-                     const std::vector<ColumnFamilyDescriptor>& column_families,
-                     std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
-                     const bool seq_per_batch);
-
-  virtual Status Close() override;
-
  protected:
   Env* const env_;
   const std::string dbname_;
   unique_ptr<VersionSet> versions_;
-  // Flag to check whether we allocated and own the info log file
-  bool own_info_log_;
   const DBOptions initial_db_options_;
   const ImmutableDBOptions immutable_db_options_;
   MutableDBOptions mutable_db_options_;
@@ -628,11 +539,16 @@ class DBImpl : public DB {
   std::unordered_map<std::string, RecoveredTransaction*>
       recovered_transactions_;
 
+  InternalIterator* NewInternalIterator(const ReadOptions&,
+                                        ColumnFamilyData* cfd,
+                                        SuperVersion* super_version,
+                                        Arena* arena,
+                                        RangeDelAggregator* range_del_agg);
+
   // Except in DB::Open(), WriteOptionsFile can only be called when:
-  // Persist options to options file.
-  // If need_mutex_lock = false, the method will lock DB mutex.
-  // If need_enter_write_thread = false, the method will enter write thread.
-  Status WriteOptionsFile(bool need_mutex_lock, bool need_enter_write_thread);
+  // 1. WriteThread::Writer::EnterUnbatched() is used.
+  // 2. db_mutex is held
+  Status WriteOptionsFile();
 
   // The following two functions can only be called when:
   // 1. WriteThread::Writer::EnterUnbatched() is used.
@@ -640,10 +556,6 @@ class DBImpl : public DB {
   Status RenameTempFileToOptionsFile(const std::string& file_name);
   Status DeleteObsoleteOptionsFiles();
 
-  void NotifyOnFlushBegin(ColumnFamilyData* cfd, FileMetaData* file_meta,
-                          const MutableCFOptions& mutable_cf_options,
-                          int job_id, TableProperties prop);
-
   void NotifyOnFlushCompleted(ColumnFamilyData* cfd, FileMetaData* file_meta,
                               const MutableCFOptions& mutable_cf_options,
                               int job_id, TableProperties prop);
@@ -666,73 +578,30 @@ class DBImpl : public DB {
 
   void EraseThreadStatusDbInfo() const;
 
-  // If disable_memtable is set the application logic must guarantee that the
-  // batch will still be skipped from memtable during the recovery. In
-  // WriteCommitted it is guarnateed since disable_memtable is used for prepare
-  // batch which will be written to memtable later during the commit, and in
-  // WritePrepared it is guaranteed since it will be used only for WAL markers
-  // which will never be written to memtable.
   Status WriteImpl(const WriteOptions& options, WriteBatch* updates,
                    WriteCallback* callback = nullptr,
                    uint64_t* log_used = nullptr, uint64_t log_ref = 0,
-                   bool disable_memtable = false, uint64_t* seq_used = nullptr,
-                   PreReleaseCallback* pre_release_callback = nullptr);
-
-  Status PipelinedWriteImpl(const WriteOptions& options, WriteBatch* updates,
-                            WriteCallback* callback = nullptr,
-                            uint64_t* log_used = nullptr, uint64_t log_ref = 0,
-                            bool disable_memtable = false,
-                            uint64_t* seq_used = nullptr);
-
-  Status WriteImplWALOnly(const WriteOptions& options, WriteBatch* updates,
-                          WriteCallback* callback = nullptr,
-                          uint64_t* log_used = nullptr, uint64_t log_ref = 0,
-                          uint64_t* seq_used = nullptr,
-                          PreReleaseCallback* pre_release_callback = nullptr);
+                   bool disable_memtable = false);
 
   uint64_t FindMinLogContainingOutstandingPrep();
   uint64_t FindMinPrepLogReferencedByMemTable();
-  // write cached_recoverable_state_ to memtable if it is not empty
-  // The writer must be the leader in write_thread_ and holding mutex_
-  Status WriteRecoverableState();
 
  private:
   friend class DB;
   friend class InternalStats;
-  friend class PessimisticTransaction;
-  friend class WriteCommittedTxn;
-  friend class WritePreparedTxn;
-  friend class WritePreparedTxnDB;
-  friend class WriteBatchWithIndex;
+  friend class TransactionImpl;
 #ifndef ROCKSDB_LITE
   friend class ForwardIterator;
 #endif
   friend struct SuperVersion;
   friend class CompactedDBImpl;
 #ifndef NDEBUG
-  friend class DBTest2_ReadCallbackTest_Test;
-  friend class WriteCallbackTest_WriteWithCallbackTest_Test;
   friend class XFTransactionWriteHandler;
-  friend class DBBlobIndexTest;
 #endif
   struct CompactionState;
 
-  struct WriteContext {
-    SuperVersionContext superversion_context;
-    autovector<MemTable*> memtables_to_free_;
+  struct WriteContext;
 
-    explicit WriteContext(bool create_superversion = false)
-        : superversion_context(create_superversion) {}
-
-    ~WriteContext() {
-      superversion_context.Clean();
-      for (auto& m : memtables_to_free_) {
-        delete m;
-      }
-    }
-  };
-
-  struct PrepickedCompaction;
   struct PurgeFileInfo;
 
   // Recover the descriptor from persistent storage.  May do a significant
@@ -746,17 +615,12 @@ class DBImpl : public DB {
 
   const Status CreateArchivalDirectory();
 
-  Status CreateColumnFamilyImpl(const ColumnFamilyOptions& cf_options,
-                                const std::string& cf_name,
-                                ColumnFamilyHandle** handle);
-
-  Status DropColumnFamilyImpl(ColumnFamilyHandle* column_family);
-
   // Delete any unneeded files and stale in-memory entries.
   void DeleteObsoleteFiles();
   // Delete obsolete files and log status and information of file deletion
-  void DeleteObsoleteFileImpl(int job_id, const std::string& fname,
-                              FileType type, uint64_t number, uint32_t path_id);
+  void DeleteObsoleteFileImpl(Status file_deletion_status, int job_id,
+                              const std::string& fname, FileType type,
+                              uint64_t number, uint32_t path_id);
 
   // Background process needs to call
   //     auto x = CaptureCurrentFileNumberInPendingOutputs()
@@ -802,9 +666,6 @@ class DBImpl : public DB {
   //            `num_bytes` going through.
   Status DelayWrite(uint64_t num_bytes, const WriteOptions& write_options);
 
-  Status ThrottleLowPriWritesIfNeeded(const WriteOptions& write_options,
-                                      WriteBatch* my_batch);
-
   Status ScheduleFlushes(WriteContext* context);
 
   Status SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context);
@@ -813,44 +674,8 @@ class DBImpl : public DB {
   Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options,
                        bool writes_stopped = false);
 
-  // Wait for memtable flushed.
-  // If flush_memtable_id is non-null, wait until the memtable with the ID
-  // gets flush. Otherwise, wait until the column family don't have any
-  // memtable pending flush.
-  Status WaitForFlushMemTable(ColumnFamilyData* cfd,
-                              const uint64_t* flush_memtable_id = nullptr);
-
-  // REQUIRES: mutex locked
-  Status SwitchWAL(WriteContext* write_context);
-
-  // REQUIRES: mutex locked
-  Status HandleWriteBufferFull(WriteContext* write_context);
-
-  // REQUIRES: mutex locked
-  Status PreprocessWrite(const WriteOptions& write_options, bool* need_log_sync,
-                         WriteContext* write_context);
-
-  WriteBatch* MergeBatch(const WriteThread::WriteGroup& write_group,
-                         WriteBatch* tmp_batch, size_t* write_with_wal,
-                         WriteBatch** to_be_cached_state);
-
-  Status WriteToWAL(const WriteBatch& merged_batch, log::Writer* log_writer,
-                    uint64_t* log_used, uint64_t* log_size);
-
-  Status WriteToWAL(const WriteThread::WriteGroup& write_group,
-                    log::Writer* log_writer, uint64_t* log_used,
-                    bool need_log_sync, bool need_log_dir_sync,
-                    SequenceNumber sequence);
-
-  Status ConcurrentWriteToWAL(const WriteThread::WriteGroup& write_group,
-                              uint64_t* log_used, SequenceNumber* last_sequence,
-                              size_t seq_inc);
-
-  // Used by WriteImpl to update bg_error_ if paranoid check is enabled.
-  void WriteCallbackStatusCheck(const Status& status);
-
-  // Used by WriteImpl to update bg_error_ in case of memtable insert error.
-  void MemTableInsertStatusCheck(const Status& memtable_insert_status);
+  // Wait for memtable flushed
+  Status WaitForFlushMemTable(ColumnFamilyData* cfd);
 
 #ifndef ROCKSDB_LITE
 
@@ -878,19 +703,14 @@ class DBImpl : public DB {
   void SchedulePendingPurge(std::string fname, FileType type, uint64_t number,
                             uint32_t path_id, int job_id);
   static void BGWorkCompaction(void* arg);
-  // Runs a pre-chosen universal compaction involving bottom level in a
-  // separate, bottom-pri thread pool.
-  static void BGWorkBottomCompaction(void* arg);
   static void BGWorkFlush(void* db);
   static void BGWorkPurge(void* arg);
   static void UnscheduleCallback(void* arg);
-  void BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
-                                Env::Priority bg_thread_pri);
+  void BackgroundCallCompaction(void* arg);
   void BackgroundCallFlush();
   void BackgroundCallPurge();
   Status BackgroundCompaction(bool* madeProgress, JobContext* job_context,
-                              LogBuffer* log_buffer,
-                              PrepickedCompaction* prepicked_compaction);
+                              LogBuffer* log_buffer, void* m = 0);
   Status BackgroundFlush(bool* madeProgress, JobContext* job_context,
                          LogBuffer* log_buffer);
 
@@ -920,10 +740,13 @@ class DBImpl : public DB {
 
   const Snapshot* GetSnapshotImpl(bool is_write_conflict_boundary);
 
-  uint64_t GetMaxTotalWalSize() const;
+  // Persist RocksDB options under the single write thread
+  // REQUIRES: mutex locked
+  Status PersistOptions();
 
-  // Actual implementation of Close()
-  virtual Status CloseImpl();
+  void MaybeFlushColumnFamilies();
+
+  uint64_t GetMaxTotalWalSize() const;
 
   // table_cache_ provides its own synchronization
   std::shared_ptr<Cache> table_cache_;
@@ -931,16 +754,11 @@ class DBImpl : public DB {
   // Lock over the persistent DB state.  Non-nullptr iff successfully acquired.
   FileLock* db_lock_;
 
-  // In addition to mutex_, log_write_mutex_ protected writes to logs_ and
-  // logfile_number_. With two_write_queues it also protects alive_log_files_,
-  // and log_empty_. Refer to the definition of each variable below for more
-  // details.
-  InstrumentedMutex log_write_mutex_;
+  // The mutex for options file related operations.
+  // NOTE: should never acquire options_file_mutex_ and mutex_ at the
+  //       same time.
+  InstrumentedMutex options_files_mutex_;
   // State below is protected by mutex_
-  // With two_write_queues enabled, some of the variables that accessed during
-  // WriteToWAL need different synchronization: log_empty_, alive_log_files_,
-  // logs_, logfile_number_. Refer to the definition of each variable below for
-  // more description.
   mutable InstrumentedMutex mutex_;
 
   std::atomic<bool> shutting_down_;
@@ -953,23 +771,11 @@ class DBImpl : public DB {
   // (i.e. whenever a flush is done, even if it didn't make any progress)
   // * whenever there is an error in background purge, flush or compaction
   // * whenever num_running_ingest_file_ goes to 0.
-  // * whenever pending_purge_obsolete_files_ goes to 0.
-  // * whenever disable_delete_obsolete_files_ goes to 0.
   InstrumentedCondVar bg_cv_;
-  // Writes are protected by locking both mutex_ and log_write_mutex_, and reads
-  // must be under either mutex_ or log_write_mutex_. Since after ::Open,
-  // logfile_number_ is currently updated only in write_thread_, it can be read
-  // from the same write_thread_ without any locks.
   uint64_t logfile_number_;
   std::deque<uint64_t>
-      log_recycle_files_;  // a list of log files that we can recycle
+      log_recycle_files;  // a list of log files that we can recycle
   bool log_dir_synced_;
-  // Without two_write_queues, read and writes to log_empty_ are protected by
-  // mutex_. Since it is currently updated/read only in write_thread_, it can be
-  // accessed from the same write_thread_ without any locks. With
-  // two_write_queues writes, where it can be updated in different threads,
-  // read and writes are protected by log_write_mutex_ instead. This is to avoid
-  // expesnive mutex_ lock during WAL write, which update log_empty_.
   bool log_empty_;
   ColumnFamilyHandleImpl* default_cf_handle_;
   InternalStats* default_cf_internal_stats_;
@@ -1004,39 +810,18 @@ class DBImpl : public DB {
     // true for some prefix of logs_
     bool getting_synced = false;
   };
-  // Without two_write_queues, read and writes to alive_log_files_ are
-  // protected by mutex_. However since back() is never popped, and push_back()
-  // is done only from write_thread_, the same thread can access the item
-  // reffered by back() without mutex_. With two_write_queues_, writes
-  // are protected by locking both mutex_ and log_write_mutex_, and reads must
-  // be under either mutex_ or log_write_mutex_.
   std::deque<LogFileNumberSize> alive_log_files_;
   // Log files that aren't fully synced, and the current log file.
   // Synchronization:
-  //  - push_back() is done from write_thread_ with locked mutex_ and
-  //  log_write_mutex_
-  //  - pop_front() is done from any thread with locked mutex_ and
-  //  log_write_mutex_
-  //  - reads are done with either locked mutex_ or log_write_mutex_
+  //  - push_back() is done from write thread with locked mutex_,
+  //  - pop_front() is done from any thread with locked mutex_,
   //  - back() and items with getting_synced=true are not popped,
-  //  - The same thread that sets getting_synced=true will reset it.
-  //  - it follows that the object referred by back() can be safely read from
-  //  the write_thread_ without using mutex
-  //  - it follows that the items with getting_synced=true can be safely read
-  //  from the same thread that has set getting_synced=true
+  //  - it follows that write thread with unlocked mutex_ can safely access
+  //    back() and items with getting_synced=true.
   std::deque<LogWriterNumber> logs_;
   // Signaled when getting_synced becomes false for some of the logs_.
   InstrumentedCondVar log_sync_cv_;
-  // This is the app-level state that is written to the WAL but will be used
-  // only during recovery. Using this feature enables not writing the state to
-  // memtable on normal writes and hence improving the throughput. Each new
-  // write of the state will replace the previous state entirely even if the
-  // keys in the two consecuitive states do not overlap.
-  // It is protected by log_write_mutex_ when two_write_queues_ is enabled.
-  // Otherwise only the heaad of write_thread_ can access it.
-  WriteBatch cached_recoverable_state_;
-  std::atomic<bool> cached_recoverable_state_empty_ = {true};
-  std::atomic<uint64_t> total_log_size_;
+  uint64_t total_log_size_;
   // only used for dynamically adjusting max_total_wal_size. it is a sum of
   // [write_buffer_size * max_write_buffer_number] over all column families
   uint64_t max_total_in_memory_state_;
@@ -1081,19 +866,13 @@ class DBImpl : public DB {
   WriteBufferManager* write_buffer_manager_;
 
   WriteThread write_thread_;
+
   WriteBatch tmp_batch_;
-  // The write thread when the writers have no memtable write. This will be used
-  // in 2PC to batch the prepares separately from the serial commit.
-  WriteThread nonmem_write_thread_;
 
   WriteController write_controller_;
 
-  unique_ptr<RateLimiter> low_pri_write_rate_limiter_;
-
   // Size of the last batch group. In slowdown mode, next write needs to
   // sleep if it uses up the quota.
-  // Note: This is to protect memtable and compaction. If the batch only writes
-  // to the WAL its size need not to be included in this.
   uint64_t last_batch_group_size_;
 
   FlushScheduler flush_scheduler_;
@@ -1157,10 +936,6 @@ class DBImpl : public DB {
   int unscheduled_flushes_;
   int unscheduled_compactions_;
 
-  // count how many background compactions are running or have been scheduled in
-  // the BOTTOM pool
-  int bg_bottom_compaction_scheduled_;
-
   // count how many background compactions are running or have been scheduled
   int bg_compaction_scheduled_;
 
@@ -1177,7 +952,7 @@ class DBImpl : public DB {
   int bg_purge_scheduled_;
 
   // Information for a manual compaction
-  struct ManualCompactionState {
+  struct ManualCompaction {
     ColumnFamilyData* cfd;
     int input_level;
     int output_level;
@@ -1193,21 +968,13 @@ class DBImpl : public DB {
     InternalKey* manual_end;      // how far we are compacting
     InternalKey tmp_storage;      // Used to keep track of compaction progress
     InternalKey tmp_storage1;     // Used to keep track of compaction progress
-  };
-  struct PrepickedCompaction {
-    // background compaction takes ownership of `compaction`.
     Compaction* compaction;
-    // caller retains ownership of `manual_compaction_state` as it is reused
-    // across background compactions.
-    ManualCompactionState* manual_compaction_state;  // nullptr if non-manual
   };
-  std::deque<ManualCompactionState*> manual_compaction_dequeue_;
+  std::deque<ManualCompaction*> manual_compaction_dequeue_;
 
   struct CompactionArg {
-    // caller retains ownership of `db`.
     DBImpl* db;
-    // background compaction takes ownership of `prepicked_compaction`.
-    PrepickedCompaction* prepicked_compaction;
+    ManualCompaction* m;
   };
 
   // Have we encountered a background error in paranoid mode?
@@ -1221,10 +988,6 @@ class DBImpl : public DB {
   // without any synchronization
   int disable_delete_obsolete_files_;
 
-  // Number of times FindObsoleteFiles has found deletable files and the
-  // corresponding call to PurgeObsoleteFiles has not yet finished.
-  int pending_purge_obsolete_files_;
-
   // last time when DeleteObsoleteFiles with full scan was executed. Originaly
   // initialized with startup time.
   uint64_t delete_obsolete_files_last_run_;
@@ -1258,9 +1021,6 @@ class DBImpl : public DB {
   // The options to access storage files
   const EnvOptions env_options_;
 
-  // Additonal options for compaction and flush
-  EnvOptions env_options_for_compaction_;
-
   // Number of running IngestExternalFile() calls.
   // REQUIRES: mutex held
   int num_running_ingest_file_;
@@ -1284,7 +1044,7 @@ class DBImpl : public DB {
   // Indicate DB was opened successfully
   bool opened_successfully_;
 
-  // minimum log number still containing prepared data.
+  // minmum log number still containing prepared data.
   // this is used by FindObsoleteFiles to determine which
   // flushed logs we must keep around because they still
   // contain prepared data which has not been flushed or rolled back
@@ -1297,7 +1057,7 @@ class DBImpl : public DB {
   // to prepared_section_completed_ which maps LOG -> instance_count
   // since a log could contain multiple prepared sections
   //
-  // when trying to determine the minimum log still active we first
+  // when trying to determine the minmum log still active we first
   // consult min_log_with_prep_. while that root value maps to
   // a value > 0 in prepared_section_completed_ we decrement the
   // instance_count for that log and pop the root value in
@@ -1306,23 +1066,30 @@ class DBImpl : public DB {
   std::unordered_map<uint64_t, uint64_t> prepared_section_completed_;
   std::mutex prep_heap_mutex_;
 
-  // Callback for compaction to check if a key is visible to a snapshot.
-  // REQUIRES: mutex held
-  std::unique_ptr<SnapshotChecker> snapshot_checker_;
-
   // No copying allowed
   DBImpl(const DBImpl&);
   void operator=(const DBImpl&);
 
+  // Return the earliest snapshot where seqno is visible.
+  // Store the snapshot right before that, if any, in prev_snapshot
+  inline SequenceNumber findEarliestVisibleSnapshot(
+    SequenceNumber in,
+    std::vector<SequenceNumber>& snapshots,
+    SequenceNumber* prev_snapshot);
+
   // Background threads call this function, which is just a wrapper around
   // the InstallSuperVersion() function. Background threads carry
-  // sv_context which can have new_superversion already
+  // job_context which can have new_superversion already
   // allocated.
+  void InstallSuperVersionAndScheduleWorkWrapper(
+      ColumnFamilyData* cfd, JobContext* job_context,
+      const MutableCFOptions& mutable_cf_options);
+
   // All ColumnFamily state changes go through this function. Here we analyze
   // the new state and we schedule background work if we detect that the new
   // state needs flush or compaction.
-  void InstallSuperVersionAndScheduleWork(
-      ColumnFamilyData* cfd, SuperVersionContext* sv_context,
+  SuperVersion* InstallSuperVersionAndScheduleWork(
+      ColumnFamilyData* cfd, SuperVersion* new_sv,
       const MutableCFOptions& mutable_cf_options);
 
 #ifndef ROCKSDB_LITE
@@ -1336,51 +1103,25 @@ class DBImpl : public DB {
 
 #endif  // ROCKSDB_LITE
 
+  // Function that Get and KeyMayExist call with no_io true or false
+  // Note: 'value_found' from KeyMayExist propagates here
+  Status GetImpl(const ReadOptions& options, ColumnFamilyHandle* column_family,
+                 const Slice& key, std::string* value,
+                 bool* value_found = nullptr);
+
   bool GetIntPropertyInternal(ColumnFamilyData* cfd,
                               const DBPropertyInfo& property_info,
                               bool is_locked, uint64_t* value);
 
   bool HasPendingManualCompaction();
   bool HasExclusiveManualCompaction();
-  void AddManualCompaction(ManualCompactionState* m);
-  void RemoveManualCompaction(ManualCompactionState* m);
-  bool ShouldntRunManualCompaction(ManualCompactionState* m);
+  void AddManualCompaction(ManualCompaction* m);
+  void RemoveManualCompaction(ManualCompaction* m);
+  bool ShouldntRunManualCompaction(ManualCompaction* m);
   bool HaveManualCompaction(ColumnFamilyData* cfd);
-  bool MCOverlap(ManualCompactionState* m, ManualCompactionState* m1);
+  bool MCOverlap(ManualCompaction* m, ManualCompaction* m1);
 
   size_t GetWalPreallocateBlockSize(uint64_t write_buffer_size) const;
-  Env::WriteLifeTimeHint CalculateWALWriteHint() {
-    return Env::WLTH_SHORT;
-  }
-
-  // When set, we use a seprate queue for writes that dont write to memtable. In
-  // 2PC these are the writes at Prepare phase.
-  const bool two_write_queues_;
-  const bool manual_wal_flush_;
-  // Increase the sequence number after writing each batch, whether memtable is
-  // disabled for that or not. Otherwise the sequence number is increased after
-  // writing each key into memtable. This implies that when disable_memtable is
-  // set, the seq is not increased at all.
-  //
-  // Default: false
-  const bool seq_per_batch_;
-  // LastSequence also indicates last published sequence visibile to the
-  // readers. Otherwise LastPublishedSequence should be used.
-  const bool last_seq_same_as_publish_seq_;
-  // It indicates that a customized gc algorithm must be used for
-  // flush/compaction and if it is not provided vis SnapshotChecker, we should
-  // disable gc to be safe.
-  const bool use_custom_gc_;
-
-  // Clients must periodically call SetPreserveDeletesSequenceNumber()
-  // to advance this seqnum. Default value is 0 which means ALL deletes are
-  // preserved. Note that this has no effect if DBOptions.preserve_deletes
-  // is set to false.
-  std::atomic<SequenceNumber> preserve_deletes_seqnum_;
-  const bool preserve_deletes_;
-
-  // Flag to check whether Close() has been called on this DB
-  bool closed_;
 };
 
 extern Options SanitizeOptions(const std::string& db,
@@ -1388,10 +1129,6 @@ extern Options SanitizeOptions(const std::string& db,
 
 extern DBOptions SanitizeOptions(const std::string& db, const DBOptions& src);
 
-extern CompressionType GetCompressionFlush(
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options);
-
 // Fix user-supplied options to be reasonable
 template <class T, class V>
 static void ClipToRange(T* ptr, V minvalue, V maxvalue) {

db/db_impl_debug.cc

@@ -10,7 +10,7 @@
 #ifndef NDEBUG
 
 #include "db/db_impl.h"
-#include "monitoring/thread_status_updater.h"
+#include "util/thread_status_updater.h"
 
 namespace rocksdb {
 
@@ -19,10 +19,9 @@ uint64_t DBImpl::TEST_GetLevel0TotalSize() {
   return default_cf_handle_->cfd()->current()->storage_info()->NumLevelBytes(0);
 }
 
-void DBImpl::TEST_SwitchWAL() {
-  WriteContext write_context;
+void DBImpl::TEST_MaybeFlushColumnFamilies() {
   InstrumentedMutexLock l(&mutex_);
-  SwitchWAL(&write_context);
+  MaybeFlushColumnFamilies();
 }
 
 int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
@@ -60,10 +59,6 @@ uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
   return versions_->manifest_file_number();
 }
 
-uint64_t DBImpl::TEST_Current_Next_FileNo() {
-  return versions_->current_next_file_number();
-}
-
 Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
                                  const Slice* end,
                                  ColumnFamilyHandle* column_family,
@@ -84,15 +79,6 @@ Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
                              disallow_trivial_move);
 }
 
-Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
-  WriteContext write_context;
-  InstrumentedMutexLock l(&mutex_);
-  if (cfd == nullptr) {
-    cfd = default_cf_handle_->cfd();
-  }
-  return SwitchMemtable(cfd, &write_context);
-}
-
 Status DBImpl::TEST_FlushMemTable(bool wait, ColumnFamilyHandle* cfh) {
   FlushOptions fo;
   fo.wait = wait;
@@ -125,9 +111,7 @@ Status DBImpl::TEST_WaitForCompact() {
   // OR flush to finish.
 
   InstrumentedMutexLock l(&mutex_);
-  while ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
-          bg_flush_scheduled_) &&
-         bg_error_.ok()) {
+  while ((bg_compaction_scheduled_ || bg_flush_scheduled_) && bg_error_.ok()) {
     bg_cv_.Wait();
   }
   return bg_error_;
@@ -201,20 +185,7 @@ Status DBImpl::TEST_GetLatestMutableCFOptions(
 
 int DBImpl::TEST_BGCompactionsAllowed() const {
   InstrumentedMutexLock l(&mutex_);
-  return GetBGJobLimits().max_compactions;
-}
-
-int DBImpl::TEST_BGFlushesAllowed() const {
-  InstrumentedMutexLock l(&mutex_);
-  return GetBGJobLimits().max_flushes;
-}
-
-SequenceNumber DBImpl::TEST_GetLastVisibleSequence() const {
-  if (last_seq_same_as_publish_seq_) {
-    return versions_->LastSequence();
-  } else {
-    return versions_->LastAllocatedSequence();
-  }
+  return BGCompactionsAllowed();
 }
 
 }  // namespace rocksdb

db/db_impl_experimental.cc

@@ -30,10 +30,10 @@ Status DBImpl::SuggestCompactRange(ColumnFamilyHandle* column_family,
   auto cfd = cfh->cfd();
   InternalKey start_key, end_key;
   if (begin != nullptr) {
-    start_key.SetMinPossibleForUserKey(*begin);
+    start_key.SetMaxPossibleForUserKey(*begin);
   }
   if (end != nullptr) {
-    end_key.SetMaxPossibleForUserKey(*end);
+    end_key.SetMinPossibleForUserKey(*end);
   }
   {
     InstrumentedMutexLock l(&mutex_);
@@ -61,8 +61,8 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
   assert(column_family);
 
   if (target_level < 1) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                   "PromoteL0 FAILED. Invalid target level %d\n", target_level);
+    Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+        "PromoteL0 FAILED. Invalid target level %d\n", target_level);
     return Status::InvalidArgument("Invalid target level");
   }
 
@@ -75,9 +75,8 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     const auto* vstorage = cfd->current()->storage_info();
 
     if (target_level >= vstorage->num_levels()) {
-      ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                     "PromoteL0 FAILED. Target level %d does not exist\n",
-                     target_level);
+      Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+          "PromoteL0 FAILED. Target level %d does not exist\n", target_level);
       job_context.Clean();
       return Status::InvalidArgument("Target level does not exist");
     }
@@ -95,9 +94,9 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     for (size_t i = 0; i < l0_files.size(); ++i) {
       auto f = l0_files[i];
       if (f->being_compacted) {
-        ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                       "PromoteL0 FAILED. File %" PRIu64 " being compacted\n",
-                       f->fd.GetNumber());
+        Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+            "PromoteL0 FAILED. File %" PRIu64 " being compacted\n",
+            f->fd.GetNumber());
         job_context.Clean();
         return Status::InvalidArgument("PromoteL0 called during L0 compaction");
       }
@@ -105,10 +104,10 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
       if (i == 0) continue;
       auto prev_f = l0_files[i - 1];
       if (icmp->Compare(prev_f->largest, f->smallest) >= 0) {
-        ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                       "PromoteL0 FAILED. Files %" PRIu64 " and %" PRIu64
-                       " have overlapping ranges\n",
-                       prev_f->fd.GetNumber(), f->fd.GetNumber());
+        Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+            "PromoteL0 FAILED. Files %" PRIu64 " and %" PRIu64
+            " have overlapping ranges\n",
+            prev_f->fd.GetNumber(), f->fd.GetNumber());
         job_context.Clean();
         return Status::InvalidArgument("L0 has overlapping files");
       }
@@ -117,8 +116,8 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     // Check that all levels up to target_level are empty.
     for (int level = 1; level <= target_level; ++level) {
       if (vstorage->NumLevelFiles(level) > 0) {
-        ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                       "PromoteL0 FAILED. Level %d not empty\n", level);
+        Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+            "PromoteL0 FAILED. Level %d not empty\n", level);
         job_context.Clean();
         return Status::InvalidArgument(
             "All levels up to target_level "
@@ -138,9 +137,8 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
                                     &edit, &mutex_, directories_.GetDbDir());
     if (status.ok()) {
-      InstallSuperVersionAndScheduleWork(
-          cfd, &job_context.superversion_context,
-          *cfd->GetLatestMutableCFOptions());
+      InstallSuperVersionAndScheduleWorkWrapper(
+          cfd, &job_context, *cfd->GetLatestMutableCFOptions());
     }
   }  // lock released here
   LogFlush(immutable_db_options_.info_log);

db/db_impl_files.cc

@@ -1,557 +0,0 @@
-//  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).
-//
-// 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.
-#include "db/db_impl.h"
-
-#ifndef __STDC_FORMAT_MACROS
-#define __STDC_FORMAT_MACROS
-#endif
-#include <inttypes.h>
-#include "db/event_helpers.h"
-#include "util/file_util.h"
-#include "util/sst_file_manager_impl.h"
-
-
-namespace rocksdb {
-uint64_t DBImpl::FindMinPrepLogReferencedByMemTable() {
-  if (!allow_2pc()) {
-    return 0;
-  }
-
-  uint64_t min_log = 0;
-
-  // we must look through the memtables for two phase transactions
-  // that have been committed but not yet flushed
-  for (auto loop_cfd : *versions_->GetColumnFamilySet()) {
-    if (loop_cfd->IsDropped()) {
-      continue;
-    }
-
-    auto log = loop_cfd->imm()->GetMinLogContainingPrepSection();
-
-    if (log > 0 && (min_log == 0 || log < min_log)) {
-      min_log = log;
-    }
-
-    log = loop_cfd->mem()->GetMinLogContainingPrepSection();
-
-    if (log > 0 && (min_log == 0 || log < min_log)) {
-      min_log = log;
-    }
-  }
-
-  return min_log;
-}
-
-// TODO(myabandeh): Avoid using locks
-void DBImpl::MarkLogAsHavingPrepSectionFlushed(uint64_t log) {
-  assert(log != 0);
-  std::lock_guard<std::mutex> lock(prep_heap_mutex_);
-  auto it = prepared_section_completed_.find(log);
-  assert(it != prepared_section_completed_.end());
-  it->second += 1;
-}
-
-// TODO(myabandeh): Avoid using locks
-void DBImpl::MarkLogAsContainingPrepSection(uint64_t log) {
-  assert(log != 0);
-  std::lock_guard<std::mutex> lock(prep_heap_mutex_);
-  min_log_with_prep_.push(log);
-  auto it = prepared_section_completed_.find(log);
-  if (it == prepared_section_completed_.end()) {
-    prepared_section_completed_[log] = 0;
-  }
-}
-
-uint64_t DBImpl::FindMinLogContainingOutstandingPrep() {
-
-  if (!allow_2pc()) {
-    return 0;
-  }
-
-  std::lock_guard<std::mutex> lock(prep_heap_mutex_);
-  uint64_t min_log = 0;
-
-  // first we look in the prepared heap where we keep
-  // track of transactions that have been prepared (written to WAL)
-  // but not yet committed.
-  while (!min_log_with_prep_.empty()) {
-    min_log = min_log_with_prep_.top();
-
-    auto it = prepared_section_completed_.find(min_log);
-
-    // value was marked as 'deleted' from heap
-    if (it != prepared_section_completed_.end() && it->second > 0) {
-      it->second -= 1;
-      min_log_with_prep_.pop();
-
-      // back to squere one...
-      min_log = 0;
-      continue;
-    } else {
-      // found a valid value
-      break;
-    }
-  }
-
-  return min_log;
-}
-
-uint64_t DBImpl::MinLogNumberToKeep() {
-  uint64_t log_number = versions_->MinLogNumber();
-
-  if (allow_2pc()) {
-    // if are 2pc we must consider logs containing prepared
-    // sections of outstanding transactions.
-    //
-    // We must check min logs with outstanding prep before we check
-    // logs referneces by memtables because a log referenced by the
-    // first data structure could transition to the second under us.
-    //
-    // TODO(horuff): iterating over all column families under db mutex.
-    // should find more optimial solution
-    auto min_log_in_prep_heap = FindMinLogContainingOutstandingPrep();
-
-    if (min_log_in_prep_heap != 0 && min_log_in_prep_heap < log_number) {
-      log_number = min_log_in_prep_heap;
-    }
-
-    auto min_log_refed_by_mem = FindMinPrepLogReferencedByMemTable();
-
-    if (min_log_refed_by_mem != 0 && min_log_refed_by_mem < log_number) {
-      log_number = min_log_refed_by_mem;
-    }
-  }
-  return log_number;
-}
-
-// * Returns the list of live files in 'sst_live'
-// If it's doing full scan:
-// * Returns the list of all files in the filesystem in
-// 'full_scan_candidate_files'.
-// Otherwise, gets obsolete files from VersionSet.
-// no_full_scan = true -- never do the full scan using GetChildren()
-// force = false -- don't force the full scan, except every
-//  mutable_db_options_.delete_obsolete_files_period_micros
-// force = true -- force the full scan
-void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
-                               bool no_full_scan) {
-  mutex_.AssertHeld();
-
-  // if deletion is disabled, do nothing
-  if (disable_delete_obsolete_files_ > 0) {
-    return;
-  }
-
-  bool doing_the_full_scan = false;
-
-  // logic for figurint out if we're doing the full scan
-  if (no_full_scan) {
-    doing_the_full_scan = false;
-  } else if (force ||
-             mutable_db_options_.delete_obsolete_files_period_micros == 0) {
-    doing_the_full_scan = true;
-  } else {
-    const uint64_t now_micros = env_->NowMicros();
-    if ((delete_obsolete_files_last_run_ +
-         mutable_db_options_.delete_obsolete_files_period_micros) <
-        now_micros) {
-      doing_the_full_scan = true;
-      delete_obsolete_files_last_run_ = now_micros;
-    }
-  }
-
-  // don't delete files that might be currently written to from compaction
-  // threads
-  // Since job_context->min_pending_output is set, until file scan finishes,
-  // mutex_ cannot be released. Otherwise, we might see no min_pending_output
-  // here but later find newer generated unfinalized files while scannint.
-  if (!pending_outputs_.empty()) {
-    job_context->min_pending_output = *pending_outputs_.begin();
-  } else {
-    // delete all of them
-    job_context->min_pending_output = std::numeric_limits<uint64_t>::max();
-  }
-
-  // Get obsolete files.  This function will also update the list of
-  // pending files in VersionSet().
-  versions_->GetObsoleteFiles(&job_context->sst_delete_files,
-                              &job_context->manifest_delete_files,
-                              job_context->min_pending_output);
-
-  // store the current filenum, lognum, etc
-  job_context->manifest_file_number = versions_->manifest_file_number();
-  job_context->pending_manifest_file_number =
-      versions_->pending_manifest_file_number();
-  job_context->log_number = MinLogNumberToKeep();
-
-  job_context->prev_log_number = versions_->prev_log_number();
-
-  versions_->AddLiveFiles(&job_context->sst_live);
-  if (doing_the_full_scan) {
-    for (size_t path_id = 0; path_id < immutable_db_options_.db_paths.size();
-         path_id++) {
-      // set of all files in the directory. We'll exclude files that are still
-      // alive in the subsequent processings.
-      std::vector<std::string> files;
-      env_->GetChildren(immutable_db_options_.db_paths[path_id].path,
-                        &files);  // Ignore errors
-      for (std::string file : files) {
-        // TODO(icanadi) clean up this mess to avoid having one-off "/" prefixes
-        job_context->full_scan_candidate_files.emplace_back(
-            "/" + file, static_cast<uint32_t>(path_id));
-      }
-    }
-
-    // Add log files in wal_dir
-    if (immutable_db_options_.wal_dir != dbname_) {
-      std::vector<std::string> log_files;
-      env_->GetChildren(immutable_db_options_.wal_dir,
-                        &log_files);  // Ignore errors
-      for (std::string log_file : log_files) {
-        job_context->full_scan_candidate_files.emplace_back(log_file, 0);
-      }
-    }
-    // Add info log files in db_log_dir
-    if (!immutable_db_options_.db_log_dir.empty() &&
-        immutable_db_options_.db_log_dir != dbname_) {
-      std::vector<std::string> info_log_files;
-      // Ignore errors
-      env_->GetChildren(immutable_db_options_.db_log_dir, &info_log_files);
-      for (std::string log_file : info_log_files) {
-        job_context->full_scan_candidate_files.emplace_back(log_file, 0);
-      }
-    }
-  }
-
-  // logs_ is empty when called during recovery, in which case there can't yet
-  // be any tracked obsolete logs
-  if (!alive_log_files_.empty() && !logs_.empty()) {
-    uint64_t min_log_number = job_context->log_number;
-    size_t num_alive_log_files = alive_log_files_.size();
-    // find newly obsoleted log files
-    while (alive_log_files_.begin()->number < min_log_number) {
-      auto& earliest = *alive_log_files_.begin();
-      if (immutable_db_options_.recycle_log_file_num >
-          log_recycle_files_.size()) {
-        ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                       "adding log %" PRIu64 " to recycle list\n",
-                       earliest.number);
-        log_recycle_files_.push_back(earliest.number);
-      } else {
-        job_context->log_delete_files.push_back(earliest.number);
-      }
-      if (job_context->size_log_to_delete == 0) {
-        job_context->prev_total_log_size = total_log_size_;
-        job_context->num_alive_log_files = num_alive_log_files;
-      }
-      job_context->size_log_to_delete += earliest.size;
-      total_log_size_ -= earliest.size;
-      if (two_write_queues_) {
-        log_write_mutex_.Lock();
-      }
-      alive_log_files_.pop_front();
-      if (two_write_queues_) {
-        log_write_mutex_.Unlock();
-      }
-      // Current log should always stay alive since it can't have
-      // number < MinLogNumber().
-      assert(alive_log_files_.size());
-    }
-    while (!logs_.empty() && logs_.front().number < min_log_number) {
-      auto& log = logs_.front();
-      if (log.getting_synced) {
-        log_sync_cv_.Wait();
-        // logs_ could have changed while we were waiting.
-        continue;
-      }
-      logs_to_free_.push_back(log.ReleaseWriter());
-      {
-        InstrumentedMutexLock wl(&log_write_mutex_);
-        logs_.pop_front();
-      }
-    }
-    // Current log cannot be obsolete.
-    assert(!logs_.empty());
-  }
-
-  // We're just cleaning up for DB::Write().
-  assert(job_context->logs_to_free.empty());
-  job_context->logs_to_free = logs_to_free_;
-  job_context->log_recycle_files.assign(log_recycle_files_.begin(),
-                                        log_recycle_files_.end());
-  if (job_context->HaveSomethingToDelete()) {
-    ++pending_purge_obsolete_files_;
-  }
-  logs_to_free_.clear();
-}
-
-namespace {
-bool CompareCandidateFile(const JobContext::CandidateFileInfo& first,
-                          const JobContext::CandidateFileInfo& second) {
-  if (first.file_name > second.file_name) {
-    return true;
-  } else if (first.file_name < second.file_name) {
-    return false;
-  } else {
-    return (first.path_id > second.path_id);
-  }
-}
-};  // namespace
-
-// Delete obsolete files and log status and information of file deletion
-void DBImpl::DeleteObsoleteFileImpl(int job_id, const std::string& fname,
-                                    FileType type, uint64_t number,
-                                    uint32_t path_id) {
-  Status file_deletion_status;
-  if (type == kTableFile) {
-    file_deletion_status =
-        DeleteSSTFile(&immutable_db_options_, fname, path_id);
-  } else {
-    file_deletion_status = env_->DeleteFile(fname);
-  }
-  if (file_deletion_status.ok()) {
-    ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
-                    "[JOB %d] Delete %s type=%d #%" PRIu64 " -- %s\n", job_id,
-                    fname.c_str(), type, number,
-                    file_deletion_status.ToString().c_str());
-  } else if (env_->FileExists(fname).IsNotFound()) {
-    ROCKS_LOG_INFO(
-        immutable_db_options_.info_log,
-        "[JOB %d] Tried to delete a non-existing file %s type=%d #%" PRIu64
-        " -- %s\n",
-        job_id, fname.c_str(), type, number,
-        file_deletion_status.ToString().c_str());
-  } else {
-    ROCKS_LOG_ERROR(immutable_db_options_.info_log,
-                    "[JOB %d] Failed to delete %s type=%d #%" PRIu64 " -- %s\n",
-                    job_id, fname.c_str(), type, number,
-                    file_deletion_status.ToString().c_str());
-  }
-  if (type == kTableFile) {
-    EventHelpers::LogAndNotifyTableFileDeletion(
-        &event_logger_, job_id, number, fname, file_deletion_status, GetName(),
-        immutable_db_options_.listeners);
-  }
-}
-
-// Diffs the files listed in filenames and those that do not
-// belong to live files are posibly removed. Also, removes all the
-// files in sst_delete_files and log_delete_files.
-// It is not necessary to hold the mutex when invoking this method.
-void DBImpl::PurgeObsoleteFiles(const JobContext& state, bool schedule_only) {
-  TEST_SYNC_POINT("DBImpl::PurgeObsoleteFiles:Begin");
-  // we'd better have sth to delete
-  assert(state.HaveSomethingToDelete());
-
-  // FindObsoleteFiles() should've populated this so nonzero
-  assert(state.manifest_file_number != 0);
-
-  // Now, convert live list to an unordered map, WITHOUT mutex held;
-  // set is slow.
-  std::unordered_map<uint64_t, const FileDescriptor*> sst_live_map;
-  for (const FileDescriptor& fd : state.sst_live) {
-    sst_live_map[fd.GetNumber()] = &fd;
-  }
-  std::unordered_set<uint64_t> log_recycle_files_set(
-      state.log_recycle_files.begin(), state.log_recycle_files.end());
-
-  auto candidate_files = state.full_scan_candidate_files;
-  candidate_files.reserve(
-      candidate_files.size() + state.sst_delete_files.size() +
-      state.log_delete_files.size() + state.manifest_delete_files.size());
-  // We may ignore the dbname when generating the file names.
-  const char* kDumbDbName = "";
-  for (auto file : state.sst_delete_files) {
-    candidate_files.emplace_back(
-        MakeTableFileName(kDumbDbName, file->fd.GetNumber()),
-        file->fd.GetPathId());
-    if (file->table_reader_handle) {
-      table_cache_->Release(file->table_reader_handle);
-    }
-    delete file;
-  }
-
-  for (auto file_num : state.log_delete_files) {
-    if (file_num > 0) {
-      candidate_files.emplace_back(LogFileName(kDumbDbName, file_num), 0);
-    }
-  }
-  for (const auto& filename : state.manifest_delete_files) {
-    candidate_files.emplace_back(filename, 0);
-  }
-
-  // dedup state.candidate_files so we don't try to delete the same
-  // file twice
-  std::sort(candidate_files.begin(), candidate_files.end(),
-            CompareCandidateFile);
-  candidate_files.erase(
-      std::unique(candidate_files.begin(), candidate_files.end()),
-      candidate_files.end());
-
-  if (state.prev_total_log_size > 0) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                   "[JOB %d] Try to delete WAL files size %" PRIu64
-                   ", prev total WAL file size %" PRIu64
-                   ", number of live WAL files %" ROCKSDB_PRIszt ".\n",
-                   state.job_id, state.size_log_to_delete,
-                   state.prev_total_log_size, state.num_alive_log_files);
-  }
-
-  std::vector<std::string> old_info_log_files;
-  InfoLogPrefix info_log_prefix(!immutable_db_options_.db_log_dir.empty(),
-                                dbname_);
-  for (const auto& candidate_file : candidate_files) {
-    std::string to_delete = candidate_file.file_name;
-    uint32_t path_id = candidate_file.path_id;
-    uint64_t number;
-    FileType type;
-    // Ignore file if we cannot recognize it.
-    if (!ParseFileName(to_delete, &number, info_log_prefix.prefix, &type)) {
-      continue;
-    }
-
-    bool keep = true;
-    switch (type) {
-      case kLogFile:
-        keep = ((number >= state.log_number) ||
-                (number == state.prev_log_number) ||
-                (log_recycle_files_set.find(number) !=
-                 log_recycle_files_set.end()));
-        break;
-      case kDescriptorFile:
-        // Keep my manifest file, and any newer incarnations'
-        // (can happen during manifest roll)
-        keep = (number >= state.manifest_file_number);
-        break;
-      case kTableFile:
-        // If the second condition is not there, this makes
-        // DontDeletePendingOutputs fail
-        keep = (sst_live_map.find(number) != sst_live_map.end()) ||
-               number >= state.min_pending_output;
-        break;
-      case kTempFile:
-        // Any temp files that are currently being written to must
-        // be recorded in pending_outputs_, which is inserted into "live".
-        // Also, SetCurrentFile creates a temp file when writing out new
-        // manifest, which is equal to state.pending_manifest_file_number. We
-        // should not delete that file
-        //
-        // TODO(yhchiang): carefully modify the third condition to safely
-        //                 remove the temp options files.
-        keep = (sst_live_map.find(number) != sst_live_map.end()) ||
-               (number == state.pending_manifest_file_number) ||
-               (to_delete.find(kOptionsFileNamePrefix) != std::string::npos);
-        break;
-      case kInfoLogFile:
-        keep = true;
-        if (number != 0) {
-          old_info_log_files.push_back(to_delete);
-        }
-        break;
-      case kCurrentFile:
-      case kDBLockFile:
-      case kIdentityFile:
-      case kMetaDatabase:
-      case kOptionsFile:
-      case kBlobFile:
-        keep = true;
-        break;
-    }
-
-    if (keep) {
-      continue;
-    }
-
-    std::string fname;
-    if (type == kTableFile) {
-      // evict from cache
-      TableCache::Evict(table_cache_.get(), number);
-      fname = TableFileName(immutable_db_options_.db_paths, number, path_id);
-    } else {
-      fname = ((type == kLogFile) ? immutable_db_options_.wal_dir : dbname_) +
-              "/" + to_delete;
-    }
-
-#ifndef ROCKSDB_LITE
-    if (type == kLogFile && (immutable_db_options_.wal_ttl_seconds > 0 ||
-                             immutable_db_options_.wal_size_limit_mb > 0)) {
-      wal_manager_.ArchiveWALFile(fname, number);
-      continue;
-    }
-#endif  // !ROCKSDB_LITE
-
-    Status file_deletion_status;
-    if (schedule_only) {
-      InstrumentedMutexLock guard_lock(&mutex_);
-      SchedulePendingPurge(fname, type, number, path_id, state.job_id);
-    } else {
-      DeleteObsoleteFileImpl(state.job_id, fname, type, number, path_id);
-    }
-  }
-
-  // Delete old info log files.
-  size_t old_info_log_file_count = old_info_log_files.size();
-  if (old_info_log_file_count != 0 &&
-      old_info_log_file_count >= immutable_db_options_.keep_log_file_num) {
-    std::sort(old_info_log_files.begin(), old_info_log_files.end());
-    size_t end =
-        old_info_log_file_count - immutable_db_options_.keep_log_file_num;
-    for (unsigned int i = 0; i <= end; i++) {
-      std::string& to_delete = old_info_log_files.at(i);
-      std::string full_path_to_delete =
-          (immutable_db_options_.db_log_dir.empty()
-               ? dbname_
-               : immutable_db_options_.db_log_dir) +
-          "/" + to_delete;
-      ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                     "[JOB %d] Delete info log file %s\n", state.job_id,
-                     full_path_to_delete.c_str());
-      Status s = env_->DeleteFile(full_path_to_delete);
-      if (!s.ok()) {
-        if (env_->FileExists(full_path_to_delete).IsNotFound()) {
-          ROCKS_LOG_INFO(
-              immutable_db_options_.info_log,
-              "[JOB %d] Tried to delete non-existing info log file %s FAILED "
-              "-- %s\n",
-              state.job_id, to_delete.c_str(), s.ToString().c_str());
-        } else {
-          ROCKS_LOG_ERROR(immutable_db_options_.info_log,
-                          "[JOB %d] Delete info log file %s FAILED -- %s\n",
-                          state.job_id, to_delete.c_str(),
-                          s.ToString().c_str());
-        }
-      }
-    }
-  }
-#ifndef ROCKSDB_LITE
-  wal_manager_.PurgeObsoleteWALFiles();
-#endif  // ROCKSDB_LITE
-  LogFlush(immutable_db_options_.info_log);
-  InstrumentedMutexLock l(&mutex_);
-  --pending_purge_obsolete_files_;
-  assert(pending_purge_obsolete_files_ >= 0);
-  if (pending_purge_obsolete_files_ == 0) {
-    bg_cv_.SignalAll();
-  }
-  TEST_SYNC_POINT("DBImpl::PurgeObsoleteFiles:End");
-}
-
-void DBImpl::DeleteObsoleteFiles() {
-  mutex_.AssertHeld();
-  JobContext job_context(next_job_id_.fetch_add(1));
-  FindObsoleteFiles(&job_context, true);
-
-  mutex_.Unlock();
-  if (job_context.HaveSomethingToDelete()) {
-    PurgeObsoleteFiles(job_context);
-  }
-  job_context.Clean();
-  mutex_.Lock();
-}
-}  // namespace rocksdb

db/db_impl_readonly.cc

@@ -3,6 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+
 #include "db/db_impl_readonly.h"
 
 #include "db/compacted_db_impl.h"
@@ -10,7 +11,7 @@
 #include "db/db_iter.h"
 #include "db/merge_context.h"
 #include "db/range_del_aggregator.h"
-#include "monitoring/perf_context_imp.h"
+#include "util/perf_context_imp.h"
 
 namespace rocksdb {
 
@@ -19,8 +20,8 @@ namespace rocksdb {
 DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
                                const std::string& dbname)
     : DBImpl(db_options, dbname) {
-  ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                 "Opening the db in read only mode");
+  Log(INFO_LEVEL, immutable_db_options_.info_log,
+      "Opening the db in read only mode");
   LogFlush(immutable_db_options_.info_log);
 }
 
@@ -30,8 +31,7 @@ DBImplReadOnly::~DBImplReadOnly() {
 // Implementations of the DB interface
 Status DBImplReadOnly::Get(const ReadOptions& read_options,
                            ColumnFamilyHandle* column_family, const Slice& key,
-                           PinnableSlice* pinnable_val) {
-  assert(pinnable_val != nullptr);
+                           std::string* value) {
   Status s;
   SequenceNumber snapshot = versions_->LastSequence();
   auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
@@ -40,13 +40,12 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
   MergeContext merge_context;
   RangeDelAggregator range_del_agg(cfd->internal_comparator(), snapshot);
   LookupKey lkey(key, snapshot);
-  if (super_version->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
-                              &range_del_agg, read_options)) {
-    pinnable_val->PinSelf();
+  if (super_version->mem->Get(lkey, value, &s, &merge_context, &range_del_agg,
+                              read_options)) {
   } else {
     PERF_TIMER_GUARD(get_from_output_files_time);
-    super_version->current->Get(read_options, lkey, pinnable_val, &s,
-                                &merge_context, &range_del_agg);
+    super_version->current->Get(read_options, lkey, value, &s, &merge_context,
+                                &range_del_agg);
   }
   return s;
 }
@@ -57,15 +56,14 @@ Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
   auto cfd = cfh->cfd();
   SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
   SequenceNumber latest_snapshot = versions_->LastSequence();
-  ReadCallback* read_callback = nullptr;  // No read callback provided.
   auto db_iter = NewArenaWrappedDbIterator(
-      env_, read_options, *cfd->ioptions(),
+      env_, *cfd->ioptions(), cfd->user_comparator(),
       (read_options.snapshot != nullptr
            ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
                  ->number_
            : latest_snapshot),
       super_version->mutable_cf_options.max_sequential_skip_in_iterations,
-      super_version->version_number, read_callback);
+      super_version->version_number);
   auto internal_iter =
       NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
                           db_iter->GetRangeDelAggregator());
@@ -77,7 +75,6 @@ Status DBImplReadOnly::NewIterators(
     const ReadOptions& read_options,
     const std::vector<ColumnFamilyHandle*>& column_families,
     std::vector<Iterator*>* iterators) {
-  ReadCallback* read_callback = nullptr;  // No read callback provided.
   if (iterators == nullptr) {
     return Status::InvalidArgument("iterators not allowed to be nullptr");
   }
@@ -89,13 +86,13 @@ Status DBImplReadOnly::NewIterators(
     auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
     auto* sv = cfd->GetSuperVersion()->Ref();
     auto* db_iter = NewArenaWrappedDbIterator(
-        env_, read_options, *cfd->ioptions(),
+        env_, *cfd->ioptions(), cfd->user_comparator(),
         (read_options.snapshot != nullptr
              ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
                    ->number_
              : latest_snapshot),
         sv->mutable_cf_options.max_sequential_skip_in_iterations,
-        sv->version_number, read_callback);
+        sv->version_number);
     auto* internal_iter =
         NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
                             db_iter->GetRangeDelAggregator());
@@ -142,7 +139,6 @@ Status DB::OpenForReadOnly(
   *dbptr = nullptr;
   handles->clear();
 
-  SuperVersionContext sv_context(/* create_superversion */ true);
   DBImplReadOnly* impl = new DBImplReadOnly(db_options, dbname);
   impl->mutex_.Lock();
   Status s = impl->Recover(column_families, true /* read only */,
@@ -161,12 +157,10 @@ Status DB::OpenForReadOnly(
   }
   if (s.ok()) {
     for (auto cfd : *impl->versions_->GetColumnFamilySet()) {
-      sv_context.NewSuperVersion();
-      cfd->InstallSuperVersion(&sv_context, &impl->mutex_);
+      delete cfd->InstallSuperVersion(new SuperVersion(), &impl->mutex_);
     }
   }
   impl->mutex_.Unlock();
-  sv_context.Clean();
   if (s.ok()) {
     *dbptr = impl;
     for (auto* h : *handles) {

db/db_impl_readonly.h

@@ -22,7 +22,7 @@ class DBImplReadOnly : public DBImpl {
   using DB::Get;
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
-                     PinnableSlice* value) override;
+                     std::string* value) override;
 
   // TODO: Implement ReadOnly MultiGet?
 

db/db_info_dumper.cc

@@ -15,8 +15,8 @@
 #include <algorithm>
 #include <vector>
 
+#include "db/filename.h"
 #include "rocksdb/env.h"
-#include "util/filename.h"
 
 namespace rocksdb {
 

db/db_info_dumper.h

@@ -6,7 +6,7 @@
 
 #include <string>
 
-#include "options/db_options.h"
+#include "util/db_options.h"
 
 namespace rocksdb {
 void DumpDBFileSummary(const ImmutableDBOptions& options,

db/db_io_failure_test.cc

@@ -204,6 +204,7 @@ TEST_F(DBIOFailureTest, ManifestWriteError) {
     ASSERT_EQ("bar2", Get("foo2"));
   }
 }
+#endif  // ROCKSDB_LITE
 
 TEST_F(DBIOFailureTest, PutFailsParanoid) {
   // Test the following:
@@ -249,316 +250,7 @@ TEST_F(DBIOFailureTest, PutFailsParanoid) {
   // the next put should NOT fail
   ASSERT_TRUE(s.ok());
 }
-#if !(defined NDEBUG) || !defined(OS_WIN)
-TEST_F(DBIOFailureTest, FlushSstRangeSyncError) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  options.write_buffer_size = 256 * 1024 * 1024;
-  options.writable_file_max_buffer_size = 128 * 1024;
-  options.bytes_per_sync = 128 * 1024;
-  options.level0_file_num_compaction_trigger = 4;
-  options.memtable_factory.reset(new SpecialSkipListFactory(10));
-  BlockBasedTableOptions table_options;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(10));
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-
-  std::atomic<int> range_sync_called(0);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "SpecialEnv::SStableFile::RangeSync", [&](void* arg) {
-        if (range_sync_called.fetch_add(1) == 0) {
-          Status* st = static_cast<Status*>(arg);
-          *st = Status::IOError("range sync dummy error");
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Random rnd(301);
-  std::string rnd_str =
-      RandomString(&rnd, static_cast<int>(options.bytes_per_sync / 2));
-  std::string rnd_str_512kb = RandomString(&rnd, 512 * 1024);
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  // First 1MB doesn't get range synced
-  ASSERT_OK(Put(1, "foo0_0", rnd_str_512kb));
-  ASSERT_OK(Put(1, "foo0_1", rnd_str_512kb));
-  ASSERT_OK(Put(1, "foo1_1", rnd_str));
-  ASSERT_OK(Put(1, "foo1_2", rnd_str));
-  ASSERT_OK(Put(1, "foo1_3", rnd_str));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  ASSERT_OK(Put(1, "foo3_1", rnd_str));
-  ASSERT_OK(Put(1, "foo3_2", rnd_str));
-  ASSERT_OK(Put(1, "foo3_3", rnd_str));
-  ASSERT_OK(Put(1, "foo4", "bar"));
-  dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
-
-  // Following writes should fail as flush failed.
-  ASSERT_NOK(Put(1, "foo2", "bar3"));
-  ASSERT_EQ("bar", Get(1, "foo"));
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  ASSERT_GE(1, range_sync_called.load());
-
-  ReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ("bar", Get(1, "foo"));
-}
-
-TEST_F(DBIOFailureTest, CompactSstRangeSyncError) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  options.write_buffer_size = 256 * 1024 * 1024;
-  options.writable_file_max_buffer_size = 128 * 1024;
-  options.bytes_per_sync = 128 * 1024;
-  options.level0_file_num_compaction_trigger = 2;
-  options.target_file_size_base = 256 * 1024 * 1024;
-  options.disable_auto_compactions = true;
-  BlockBasedTableOptions table_options;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(10));
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-
-  Random rnd(301);
-  std::string rnd_str =
-      RandomString(&rnd, static_cast<int>(options.bytes_per_sync / 2));
-  std::string rnd_str_512kb = RandomString(&rnd, 512 * 1024);
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  // First 1MB doesn't get range synced
-  ASSERT_OK(Put(1, "foo0_0", rnd_str_512kb));
-  ASSERT_OK(Put(1, "foo0_1", rnd_str_512kb));
-  ASSERT_OK(Put(1, "foo1_1", rnd_str));
-  ASSERT_OK(Put(1, "foo1_2", rnd_str));
-  ASSERT_OK(Put(1, "foo1_3", rnd_str));
-  Flush(1);
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo3_1", rnd_str));
-  ASSERT_OK(Put(1, "foo3_2", rnd_str));
-  ASSERT_OK(Put(1, "foo3_3", rnd_str));
-  ASSERT_OK(Put(1, "foo4", "bar"));
-  Flush(1);
-  dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
-
-  std::atomic<int> range_sync_called(0);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "SpecialEnv::SStableFile::RangeSync", [&](void* arg) {
-        if (range_sync_called.fetch_add(1) == 0) {
-          Status* st = static_cast<Status*>(arg);
-          *st = Status::IOError("range sync dummy error");
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(dbfull()->SetOptions(handles_[1],
-                                 {
-                                     {"disable_auto_compactions", "false"},
-                                 }));
-  dbfull()->TEST_WaitForCompact();
-
-  // Following writes should fail as flush failed.
-  ASSERT_NOK(Put(1, "foo2", "bar3"));
-  ASSERT_EQ("bar", Get(1, "foo"));
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  ASSERT_GE(1, range_sync_called.load());
-
-  ReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ("bar", Get(1, "foo"));
-}
-
-TEST_F(DBIOFailureTest, FlushSstCloseError) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  options.level0_file_num_compaction_trigger = 4;
-  options.memtable_factory.reset(new SpecialSkipListFactory(2));
-
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-  std::atomic<int> close_called(0);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "SpecialEnv::SStableFile::Close", [&](void* arg) {
-        if (close_called.fetch_add(1) == 0) {
-          Status* st = static_cast<Status*>(arg);
-          *st = Status::IOError("close dummy error");
-        }
-      });
-
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo1", "bar1"));
-  ASSERT_OK(Put(1, "foo", "bar2"));
-  dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
-
-  // Following writes should fail as flush failed.
-  ASSERT_NOK(Put(1, "foo2", "bar3"));
-  ASSERT_EQ("bar2", Get(1, "foo"));
-  ASSERT_EQ("bar1", Get(1, "foo1"));
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  ReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ("bar2", Get(1, "foo"));
-  ASSERT_EQ("bar1", Get(1, "foo1"));
-}
-
-TEST_F(DBIOFailureTest, CompactionSstCloseError) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  options.level0_file_num_compaction_trigger = 2;
-  options.disable_auto_compactions = true;
-
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  Flush(1);
-  ASSERT_OK(Put(1, "foo", "bar2"));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  Flush(1);
-  ASSERT_OK(Put(1, "foo", "bar3"));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  Flush(1);
-  dbfull()->TEST_WaitForCompact();
-
-  std::atomic<int> close_called(0);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "SpecialEnv::SStableFile::Close", [&](void* arg) {
-        if (close_called.fetch_add(1) == 0) {
-          Status* st = static_cast<Status*>(arg);
-          *st = Status::IOError("close dummy error");
-        }
-      });
-
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_OK(dbfull()->SetOptions(handles_[1],
-                                 {
-                                     {"disable_auto_compactions", "false"},
-                                 }));
-  dbfull()->TEST_WaitForCompact();
-
-  // Following writes should fail as compaction failed.
-  ASSERT_NOK(Put(1, "foo2", "bar3"));
-  ASSERT_EQ("bar3", Get(1, "foo"));
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  ReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ("bar3", Get(1, "foo"));
-}
-
-TEST_F(DBIOFailureTest, FlushSstSyncError) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  options.use_fsync = false;
-  options.level0_file_num_compaction_trigger = 4;
-  options.memtable_factory.reset(new SpecialSkipListFactory(2));
-
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-  std::atomic<int> sync_called(0);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "SpecialEnv::SStableFile::Sync", [&](void* arg) {
-        if (sync_called.fetch_add(1) == 0) {
-          Status* st = static_cast<Status*>(arg);
-          *st = Status::IOError("sync dummy error");
-        }
-      });
-
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo1", "bar1"));
-  ASSERT_OK(Put(1, "foo", "bar2"));
-  dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
-
-  // Following writes should fail as flush failed.
-  ASSERT_NOK(Put(1, "foo2", "bar3"));
-  ASSERT_EQ("bar2", Get(1, "foo"));
-  ASSERT_EQ("bar1", Get(1, "foo1"));
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  ReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ("bar2", Get(1, "foo"));
-  ASSERT_EQ("bar1", Get(1, "foo1"));
-}
-
-TEST_F(DBIOFailureTest, CompactionSstSyncError) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  options.level0_file_num_compaction_trigger = 2;
-  options.disable_auto_compactions = true;
-  options.use_fsync = false;
-
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  Flush(1);
-  ASSERT_OK(Put(1, "foo", "bar2"));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  Flush(1);
-  ASSERT_OK(Put(1, "foo", "bar3"));
-  ASSERT_OK(Put(1, "foo2", "bar"));
-  Flush(1);
-  dbfull()->TEST_WaitForCompact();
-
-  std::atomic<int> sync_called(0);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "SpecialEnv::SStableFile::Sync", [&](void* arg) {
-        if (sync_called.fetch_add(1) == 0) {
-          Status* st = static_cast<Status*>(arg);
-          *st = Status::IOError("close dummy error");
-        }
-      });
-
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_OK(dbfull()->SetOptions(handles_[1],
-                                 {
-                                     {"disable_auto_compactions", "false"},
-                                 }));
-  dbfull()->TEST_WaitForCompact();
-
-  // Following writes should fail as compaction failed.
-  ASSERT_NOK(Put(1, "foo2", "bar3"));
-  ASSERT_EQ("bar3", Get(1, "foo"));
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  ReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ("bar3", Get(1, "foo"));
-}
-#endif  // !(defined NDEBUG) || !defined(OS_WIN)
-#endif  // ROCKSDB_LITE
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/db_iter.h

@@ -10,14 +10,13 @@
 #pragma once
 #include <stdint.h>
 #include <string>
-#include "db/db_impl.h"
 #include "db/dbformat.h"
 #include "db/range_del_aggregator.h"
-#include "options/cf_options.h"
 #include "rocksdb/db.h"
 #include "rocksdb/iterator.h"
 #include "util/arena.h"
 #include "util/autovector.h"
+#include "util/cf_options.h"
 
 namespace rocksdb {
 
@@ -28,14 +27,13 @@ class InternalIterator;
 // Return a new iterator that converts internal keys (yielded by
 // "*internal_iter") that were live at the specified "sequence" number
 // into appropriate user keys.
-extern Iterator* NewDBIterator(Env* env, const ReadOptions& read_options,
-                               const ImmutableCFOptions& cf_options,
-                               const Comparator* user_key_comparator,
-                               InternalIterator* internal_iter,
-                               const SequenceNumber& sequence,
-                               uint64_t max_sequential_skip_in_iterations,
-                               ReadCallback* read_callback,
-                               bool allow_blob = false);
+extern Iterator* NewDBIterator(
+    Env* env, const ImmutableCFOptions& options,
+    const Comparator* user_key_comparator, InternalIterator* internal_iter,
+    const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
+    uint64_t version_number, const Slice* iterate_upper_bound = nullptr,
+    bool prefix_same_as_start = false, bool pin_data = false,
+    bool total_order_seek = false);
 
 // A wrapper iterator which wraps DB Iterator and the arena, with which the DB
 // iterator is supposed be allocated. This class is used as an entry point of
@@ -51,6 +49,10 @@ class ArenaWrappedDBIter : public Iterator {
   virtual Arena* GetArena() { return &arena_; }
   virtual RangeDelAggregator* GetRangeDelAggregator();
 
+  // Set the DB Iterator to be wrapped
+
+  virtual void SetDBIter(DBIter* iter);
+
   // Set the internal iterator wrapped inside the DB Iterator. Usually it is
   // a merging iterator.
   virtual void SetIterUnderDBIter(InternalIterator* iter);
@@ -64,47 +66,22 @@ class ArenaWrappedDBIter : public Iterator {
   virtual Slice key() const override;
   virtual Slice value() const override;
   virtual Status status() const override;
-  virtual Status Refresh() override;
-  bool IsBlob() const;
 
+  void RegisterCleanup(CleanupFunction function, void* arg1, void* arg2);
   virtual Status GetProperty(std::string prop_name, std::string* prop) override;
 
-  void Init(Env* env, const ReadOptions& read_options,
-            const ImmutableCFOptions& cf_options,
-            const SequenceNumber& sequence,
-            uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-            ReadCallback* read_callback, bool allow_blob, bool allow_refresh);
-
-  void StoreRefreshInfo(const ReadOptions& read_options, DBImpl* db_impl,
-                        ColumnFamilyData* cfd, ReadCallback* read_callback,
-                        bool allow_blob) {
-    read_options_ = read_options;
-    db_impl_ = db_impl;
-    cfd_ = cfd;
-    read_callback_ = read_callback;
-    allow_blob_ = allow_blob;
-  }
-
  private:
   DBIter* db_iter_;
   Arena arena_;
-  uint64_t sv_number_;
-  ColumnFamilyData* cfd_ = nullptr;
-  DBImpl* db_impl_ = nullptr;
-  ReadOptions read_options_;
-  ReadCallback* read_callback_;
-  bool allow_blob_ = false;
-  bool allow_refresh_ = true;
 };
 
 // Generate the arena wrapped iterator class.
-// `db_impl` and `cfd` are used for reneweal. If left null, renewal will not
-// be supported.
 extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options, const SequenceNumber& sequence,
+    Env* env, const ImmutableCFOptions& options,
+    const Comparator* user_key_comparator, const SequenceNumber& sequence,
     uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl = nullptr,
-    ColumnFamilyData* cfd = nullptr, bool allow_blob = false,
-    bool allow_refresh = true);
+    const Slice* iterate_upper_bound = nullptr,
+    bool prefix_same_as_start = false, bool pin_data = false,
+    bool total_order_seek = false);
+
 }  // namespace rocksdb