Some small improvements to the build_tools

.gitignore

@@ -24,7 +24,6 @@ make_config.mk
 *.vcxproj.filters
 *.sln
 *.cmake
-.watchmanconfig
 CMakeCache.txt
 CMakeFiles/
 build/
@@ -33,8 +32,6 @@ ldb
 manifest_dump
 sst_dump
 blob_dump
-block_cache_trace_analyzer
-tools/block_cache_analyzer/*.pyc
 column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
@@ -48,10 +45,6 @@ etags
 rocksdb_dump
 rocksdb_undump
 db_test2
-trace_analyzer
-trace_analyzer_test
-block_cache_trace_analyzer
-.DS_Store
 
 java/out
 java/target
@@ -79,4 +72,3 @@ tp2/
 fbcode/
 fbcode
 buckifier/*.pyc
-buckifier/__pycache__

.lgtm.yml

@@ -1,4 +0,0 @@
-extraction:
-  cpp:
-    index:
-      build_command: make static_lib

.travis.yml

@@ -1,4 +1,5 @@
-dist: xenial
+sudo: false
+dist: trusty
 language: cpp
 os:
   - linux
@@ -6,34 +7,16 @@ os:
 compiler:
   - clang
   - gcc
-osx_image: xcode9.4
+osx_image: xcode8.3
 jdk:
-  - openjdk7
+  - oraclejdk7
 cache:
   - ccache
+  - apt
 
 addons:
-  apt:
-    sources:
-      - ubuntu-toolchain-r-test
-    packages:
-      - libgflags-dev
-      - libbz2-dev
-      - liblz4-dev
-      - libsnappy-dev
-      - liblzma-dev  # xv
-      - libzstd-dev
-      - zlib1g-dev
-  homebrew:
-    update: true
-    packages:
-      - ccache
-      - gflags
-      - lz4
-      - snappy
-      - xz
-      - zstd
-
+   apt:
+      packages: ['zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev', 'mingw-w64']
 env:
   - TEST_GROUP=platform_dependent # 16-18 minutes
   - TEST_GROUP=1 # 33-35 minutes
@@ -47,7 +30,6 @@ env:
   # Build examples
   - JOB_NAME=examples # 5-7 minutes
   - JOB_NAME=cmake # 3-5 minutes
-  - JOB_NAME=cmake-gcc8 # 3-5 minutes
   - JOB_NAME=cmake-mingw # 3 minutes
 
 matrix:
@@ -60,8 +42,6 @@ matrix:
     env: TEST_GROUP=3
   - os: osx
     env: TEST_GROUP=4
-  - os: osx
-    env: JOB_NAME=cmake-gcc8
   - os : osx
     env: JOB_NAME=cmake-mingw
   - os : linux
@@ -69,22 +49,14 @@ matrix:
   - 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 [ "${JOB_NAME}" == cmake-gcc8 ]; then
-      sudo apt-get install -y g++-8;
-      CC=gcc-8 && CXX=g++-8;
-    fi
-  - if [ "${JOB_NAME}" == cmake-mingw ]; then
-      sudo apt-get install -y mingw-w64 ;
-    fi
   - if [[ "${JOB_NAME}" == cmake* ]] && [ "${TRAVIS_OS_NAME}" == linux ]; then
-      mkdir cmake-dist && curl -sfSL https://github.com/Kitware/CMake/releases/download/v3.14.5/cmake-3.14.5-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
-    fi
-  - if [[ "${JOB_NAME}" == java_test ]]; then
-      java -version && echo "JAVA_HOME=${JAVA_HOME}";
+      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:
@@ -95,41 +67,18 @@ before_script:
 script:
   - ${CXX} --version
   - if [ `command -v ccache` ]; then ccache -C; fi
-  - case $TEST_GROUP in
-    platform_dependent)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=db_block_cache_test make -j4 all_but_some_tests check_some
-      ;;
-    1)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=db_iter_test make -j4 check_some
-      ;;
-    2)
-      OPT=-DTRAVIS V=1 make -j4 tools && OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_iter_test ROCKSDBTESTS_END=options_file_test make -j4 check_some
-      ;;
-    3)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=options_file_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some
-      ;;
-    4)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_prepared_transaction_test make -j4 check_some
-      ;;
-    esac
-  - case $JOB_NAME in
-    java_test)
-      OPT=-DTRAVIS V=1 make rocksdbjava jtest
-      ;;
-    lite_build)
-      OPT='-DTRAVIS -DROCKSDB_LITE' V=1 make -j4 static_lib tools
-      ;;
-    examples)
-      OPT=-DTRAVIS V=1 make -j4 static_lib && cd examples && make -j4
-      ;;
-    cmake-mingw)
-      sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
-      mkdir build && cd build && cmake -DJNI=1 -DWITH_GFLAGS=OFF .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
-      ;;
-    cmake*)
-      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release && make -j4 rocksdb rocksdbjni
-      ;;
-    esac
+  - if [ "${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 [ "${TEST_GROUP}" == '1' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=full_filter_block_test make -j4 check_some; fi
+  - if [ "${TEST_GROUP}" == '2' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=full_filter_block_test ROCKSDBTESTS_END=write_batch_with_index_test make -j4 check_some; fi
+  - if [ "${TEST_GROUP}" == '3' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_batch_with_index_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some; fi
+  - if [ "${TEST_GROUP}" == '4' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_prepared_transaction_test make -j4 check_some; fi
+  - if [ "${JOB_NAME}" == 'java_test' ]; then OPT=-DTRAVIS V=1 make clean jclean && make rocksdbjava jtest; fi
+  - if [ "${JOB_NAME}" == 'lite_build' ]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib tools; fi
+  - if [ "${JOB_NAME}" == 'examples' ]; then OPT=-DTRAVIS V=1 make -j4 static_lib; cd examples; make -j4; fi
+  - if [ "${JOB_NAME}" == 'cmake' ]; then mkdir build && cd build && cmake -DJNI=1 .. && make -j4 rocksdb rocksdbjni; fi
+  - if [ "${JOB_NAME}" == 'cmake-mingw' ]; then mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni; fi
 notifications:
     email:
       - leveldb@fb.com
+    webhooks:
+      - https://buildtimetrend.herokuapp.com/travis

.watchmanconfig

@@ -1,6 +0,0 @@
-{
-  "content_hash_warming": true,
-  "content_hash_max_items": 333333,
-  "hint_num_files_per_dir": 8,
-  "fsevents_latency": 0.05
-}

CODE_OF_CONDUCT.md

@@ -1,77 +1,3 @@
 # Code of Conduct
 
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to make participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, sex characteristics, gender identity and expression,
-level of experience, education, socio-economic status, nationality, personal
-appearance, race, religion, or sexual identity and orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-  advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-  address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies within all project spaces, and it also applies when
-an individual is representing the project or its community in public spaces.
-Examples of representing a project or community include using an official
-project e-mail address, posting via an official social media account, or acting
-as an appointed representative at an online or offline event. Representation of
-a project may be further defined and clarified by project maintainers.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at <opensource-conduct@fb.com>. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
-
+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.

HISTORY.md

@@ -1,417 +1,14 @@
 # Rocksdb Change Log
 ## Unreleased
 ### Public API Change
-* Added a rocksdb::FileSystem class in include/rocksdb/file_system.h to encapsulate file creation/read/write operations, and an option DBOptions::file_system to allow a user to pass in an instance of rocksdb::FileSystem. If its a non-null value, this will take precendence over DBOptions::env for file operations. A new API rocksdb::FileSystem::Default() returns a platform default object. The DBOptions::env option and Env::Default() API will continue to be used for threading and other OS related functions, and where DBOptions::file_system is not specified, for file operations. For storage developers who are accustomed to rocksdb::Env, the interface in rocksdb::FileSystem is new and will probably undergo some changes as more storage systems are ported to it from rocksdb::Env. As of now, no env other than Posix has been ported to the new interface.
-* A new rocksdb::NewSstFileManager() API that allows the caller to pass in separate Env and FileSystem objects.
-* Changed Java API for RocksDB.keyMayExist functions to use Holder<byte[]> instead of StringBuilder, so that retrieved values need not decode to Strings.
-* A new `OptimisticTransactionDBOptions` Option that allows users to configure occ validation policy. The default policy changes from kValidateSerial to kValidateParallel to reduce mutex contention.
-
-### Bug Fixes
-* Fix a bug that can cause unnecessary bg thread to be scheduled(#6104).
-* Fix a bug in which a snapshot read could be affected by a DeleteRange after the snapshot (#6062).
-* Fix crash caused by concurrent CF iterations and drops(#6147).
-* Fixed two performance issues related to memtable history trimming. First, a new SuperVersion is now created only if some memtables were actually trimmed. Second, trimming is only scheduled if there is at least one flushed memtable that is kept in memory for the purposes of transaction conflict checking.
-* Fix a bug in WriteBatchWithIndex::MultiGetFromBatchAndDB, which is called by Transaction::MultiGet, that causes due to stale pointer access when the number of keys is > 32
-* BlobDB no longer updates the SST to blob file mapping upon failed compactions.
-* Fixed a bug where BlobDB was comparing the `ColumnFamilyHandle` pointers themselves instead of only the column family IDs when checking whether an API call uses the default column family or not.
-* Fix a race condition for cfd->log_number_ between manifest switch and memtable switch (PR 6249) when number of column families is greater than 1.
 
 ### New Features
-* It is now possible to enable periodic compactions for the base DB when using BlobDB.
-* BlobDB now garbage collects non-TTL blobs when `enable_garbage_collection` is set to `true` in `BlobDBOptions`. Garbage collection is performed during compaction: any valid blobs located in the oldest N files (where N is the number of non-TTL blob files multiplied by the value of `BlobDBOptions::garbage_collection_cutoff`) encountered during compaction get relocated to new blob files, and old blob files are dropped once they are no longer needed. Note: we recommend enabling periodic compactions for the base DB when using this feature to deal with the case when some old blob files are kept alive by SSTs that otherwise do not get picked for compaction.
-* `db_bench` now supports the `garbage_collection_cutoff` option for BlobDB.
-
-## 6.6.0 (11/25/2019)
-### Bug Fixes
-* Fix data corruption caused by output of intra-L0 compaction on ingested file not being placed in correct order in L0.
-* Fix a data race between Version::GetColumnFamilyMetaData() and Compaction::MarkFilesBeingCompacted() for access to being_compacted (#6056). The current fix acquires the db mutex during Version::GetColumnFamilyMetaData(), which may cause regression.
-* Fix a bug in DBIter that is_blob_ state isn't updated when iterating backward using seek.
-* Fix a bug when format_version=3, partitioned filters, and prefix search are used in conjunction. The bug could result into Seek::(prefix) returning NotFound for an existing prefix.
-* Revert the feature "Merging iterator to avoid child iterator reseek for some cases (#5286)" since it might cause strong results when reseek happens with a different iterator upper bound.
-* Fix a bug causing a crash during ingest external file when background compaction cause severe error (file not found).
-* Fix a bug when partitioned filters and prefix search are used in conjunction, ::SeekForPrev could return invalid for an existing prefix. ::SeekForPrev might be called by the user, or internally on ::Prev, or within ::Seek if the return value involves Delete or a Merge operand.
-* Fix OnFlushCompleted fired before flush result persisted in MANIFEST when there's concurrent flush job. The bug exists since OnFlushCompleted was introduced in rocksdb 3.8.
-* Fixed an sst_dump crash on some plain table SST files.
-* Fixed a memory leak in some error cases of opening plain table SST files.
-* Fix a bug when a crash happens while calling WriteLevel0TableForRecovery for multiple column families, leading to a column family's log number greater than the first corrutped log number when the DB is being opened in PointInTime recovery mode during next recovery attempt (#5856).
-
-### New Features
-* Universal compaction to support options.periodic_compaction_seconds. A full compaction will be triggered if any file is over the threshold.
-* `GetLiveFilesMetaData` and `GetColumnFamilyMetaData` now expose the file number of SST files as well as the oldest blob file referenced by each SST.
-* A batched MultiGet API (DB::MultiGet()) that supports retrieving keys from multiple column families.
-* Full and partitioned filters in the block-based table use an improved Bloom filter implementation, enabled with format_version 5 (or above) because previous releases cannot read this filter. This replacement is faster and more accurate, especially for high bits per key or millions of keys in a single (full) filter. For example, the new Bloom filter has the same false positive rate at 9.55 bits per key as the old one at 10 bits per key, and a lower false positive rate at 16 bits per key than the old one at 100 bits per key.
-* Added AVX2 instructions to USE_SSE builds to accelerate the new Bloom filter and XXH3-based hash function on compatible x86_64 platforms (Haswell and later, ~2014).
-* Support options.ttl or options.periodic_compaction_seconds with options.max_open_files = -1. File's oldest ancester time and file creation time will be written to manifest. If it is availalbe, this information will be used instead of creation_time and file_creation_time in table properties.
-* Setting options.ttl for universal compaction now has the same meaning as setting periodic_compaction_seconds.
-* SstFileMetaData also returns file creation time and oldest ancester time.
-* The `sst_dump` command line tool `recompress` command now displays how many blocks were compressed and how many were not, in particular how many were not compressed because the compression ratio was not met (12.5% threshold for GoodCompressionRatio), as seen in the `number.block.not_compressed` counter stat since version 6.0.0.
-* The block cache usage is now takes into account the overhead of metadata per each entry. This results into more accurate management of memory. A side-effect of this feature is that less items are fit into the block cache of the same size, which would result to higher cache miss rates. This can be remedied by increasing the block cache size or passing kDontChargeCacheMetadata to its constuctor to restore the old behavior.
-* When using BlobDB, a mapping is maintained and persisted in the MANIFEST between each SST file and the oldest non-TTL blob file it references.
-* `db_bench` now supports and by default issues non-TTL Puts to BlobDB. TTL Puts can be enabled by specifying a non-zero value for the `blob_db_max_ttl_range` command line parameter explicitly.
-* `sst_dump` now supports printing BlobDB blob indexes in a human-readable format. This can be enabled by specifying the `decode_blob_index` flag on the command line.
-* A number of new information elements are now exposed through the EventListener interface. For flushes, the file numbers of the new SST file and the oldest blob file referenced by the SST are propagated. For compactions, the level, file number, and the oldest blob file referenced are passed to the client for each compaction input and output file.
-
-### Public API Change
-* RocksDB release 4.1 or older will not be able to open DB generated by the new release. 4.2 was released on Feb 23, 2016.
-* TTL Compactions in Level compaction style now initiate successive cascading compactions on a key range so that it reaches the bottom level quickly on TTL expiry. `creation_time` table property for compaction output files is now set to the minimum of the creation times of all compaction inputs.
-* With FIFO compaction style, options.periodic_compaction_seconds will have the same meaning as options.ttl. Whichever stricter will be used. With the default options.periodic_compaction_seconds value with options.ttl's default of 0, RocksDB will give a default of 30 days.
-* Added an API GetCreationTimeOfOldestFile(uint64_t* creation_time) to get the file_creation_time of the oldest SST file in the DB.
-* FilterPolicy now exposes additional API to make it possible to choose filter configurations based on context, such as table level and compaction style. See `LevelAndStyleCustomFilterPolicy` in db_bloom_filter_test.cc. While most existing custom implementations of FilterPolicy should continue to work as before, those wrapping the return of NewBloomFilterPolicy will require overriding new function `GetBuilderWithContext()`, because calling `GetFilterBitsBuilder()` on the FilterPolicy returned by NewBloomFilterPolicy is no longer supported.
-* An unlikely usage of FilterPolicy is no longer supported. Calling GetFilterBitsBuilder() on the FilterPolicy returned by NewBloomFilterPolicy will now cause an assertion violation in debug builds, because RocksDB has internally migrated to a more elaborate interface that is expected to evolve further. Custom implementations of FilterPolicy should work as before, except those wrapping the return of NewBloomFilterPolicy, which will require a new override of a protected function in FilterPolicy.
-* NewBloomFilterPolicy now takes bits_per_key as a double instead of an int. This permits finer control over the memory vs. accuracy trade-off in the new Bloom filter implementation and should not change source code compatibility.
-* The option BackupableDBOptions::max_valid_backups_to_open is now only used when opening BackupEngineReadOnly. When opening a read/write BackupEngine, anything but the default value logs a warning and is treated as the default. This change ensures that backup deletion has proper accounting of shared files to ensure they are deleted when no longer referenced by a backup.
-* Deprecate `snap_refresh_nanos` option.
-* Added DisableManualCompaction/EnableManualCompaction to stop and resume manual compaction.
-* Add TryCatchUpWithPrimary() to StackableDB in non-LITE mode.
-* Add a new Env::LoadEnv() overloaded function to return a shared_ptr to Env.
-* Flush sets file name to "(nil)" for OnTableFileCreationCompleted() if the flush does not produce any L0. This can happen if the file is empty thus delete by RocksDB.
-
-### Default Option Changes
-* Changed the default value of periodic_compaction_seconds to `UINT64_MAX - 1` which allows RocksDB to auto-tune periodic compaction scheduling. When using the default value, periodic compactions are now auto-enabled if a compaction filter is used. A value of `0` will turn off the feature completely.
-* Changed the default value of ttl to `UINT64_MAX - 1` which allows RocksDB to auto-tune ttl value. When using the default value, TTL will be auto-enabled to 30 days, when the feature is supported. To revert the old behavior, you can explicitly set it to 0.
-
-### Performance Improvements
-* For 64-bit hashing, RocksDB is standardizing on a slightly modified preview version of XXH3. This function is now used for many non-persisted hashes, along with fastrange64() in place of the modulus operator, and some benchmarks show a slight improvement.
-* Level iterator to invlidate the iterator more often in prefix seek and the level is filtered out by prefix bloom.
-
-## 6.5.2 (11/15/2019)
-### Bug Fixes
-* Fix a assertion failure in MultiGet() when BlockBasedTableOptions::no_block_cache is true and there is no compressed block cache
-* Fix a buffer overrun problem in BlockBasedTable::MultiGet() when compression is enabled and no compressed block cache is configured.
-* If a call to BackupEngine::PurgeOldBackups or BackupEngine::DeleteBackup suffered a crash, power failure, or I/O error, files could be left over from old backups that could only be purged with a call to GarbageCollect. Any call to PurgeOldBackups, DeleteBackup, or GarbageCollect should now suffice to purge such files.
-
-## 6.5.1 (10/16/2019)
-### Bug Fixes
-* Revert the feature "Merging iterator to avoid child iterator reseek for some cases (#5286)" since it might cause strange results when reseek happens with a different iterator upper bound.
-* Fix a bug in BlockBasedTableIterator that might return incorrect results when reseek happens with a different iterator upper bound.
-* Fix a bug when partitioned filters and prefix search are used in conjunction, ::SeekForPrev could return invalid for an existing prefix. ::SeekForPrev might be called by the user, or internally on ::Prev, or within ::Seek if the return value involves Delete or a Merge operand.
-
-## 6.5.0 (9/13/2019)
-### Bug Fixes
-* Fixed a number of data races in BlobDB.
-* Fix a bug where the compaction snapshot refresh feature is not disabled as advertised when `snap_refresh_nanos` is set to 0..
-* Fix bloom filter lookups by the MultiGet batching API when BlockBasedTableOptions::whole_key_filtering is false, by checking that a key is in the perfix_extractor domain and extracting the prefix before looking up.
-* Fix a bug in file ingestion caused by incorrect file number allocation when the number of column families involved in the ingestion exceeds 2.
-
-### New Features
-* Introduced DBOptions::max_write_batch_group_size_bytes to configure maximum limit on number of bytes that are written in a single batch of WAL or memtable write. It is followed when the leader write size is larger than 1/8 of this limit.
-* VerifyChecksum() by default will issue readahead. Allow ReadOptions to be passed in to those functions to override the readhead size. For checksum verifying before external SST file ingestion, a new option IngestExternalFileOptions.verify_checksums_readahead_size, is added for this readahead setting.
-* When user uses options.force_consistency_check in RocksDb, instead of crashing the process, we now pass the error back to the users without killing the process.
-* Add an option `memtable_insert_hint_per_batch` to WriteOptions. If it is true, each WriteBatch will maintain its own insert hints for each memtable in concurrent write. See include/rocksdb/options.h for more details.
-
-### Public API Change
-* Added max_write_buffer_size_to_maintain option to better control memory usage of immutable memtables.
-* Added a lightweight API GetCurrentWalFile() to get last live WAL filename and size. Meant to be used as a helper for backup/restore tooling in a larger ecosystem such as MySQL with a MyRocks storage engine.
-* The MemTable Bloom filter, when enabled, now always uses cache locality. Options::bloom_locality now only affects the PlainTable SST format.
-
-### Performance Improvements
-* Improve the speed of the MemTable Bloom filter, reducing the write overhead of enabling it by 1/3 to 1/2, with similar benefit to read performance.
-
-## 6.4.0 (7/30/2019)
-### Default Option Change
-* LRUCacheOptions.high_pri_pool_ratio is set to 0.5 (previously 0.0) by default, which means that by default midpoint insertion is enabled. The same change is made for the default value of high_pri_pool_ratio argument in NewLRUCache(). When block cache is not explicitly created, the small block cache created by BlockBasedTable will still has this option to be 0.0.
-* Change BlockBasedTableOptions.cache_index_and_filter_blocks_with_high_priority's default value from false to true.
-
-### Public API Change
-* Filter and compression dictionary blocks are now handled similarly to data blocks with regards to the block cache: instead of storing objects in the cache, only the blocks themselves are cached. In addition, filter and compression dictionary blocks (as well as filter partitions) no longer get evicted from the cache when a table is closed.
-* Due to the above refactoring, block cache eviction statistics for filter and compression dictionary blocks are temporarily broken. We plan to reintroduce them in a later phase.
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-* Errors related to the retrieval of the compression dictionary are now propagated to the user.
-* db_bench adds a "benchmark" stats_history, which prints out the whole stats history.
-* Overload GetAllKeyVersions() to support non-default column family.
-* Added new APIs ExportColumnFamily() and CreateColumnFamilyWithImport() to support export and import of a Column Family. https://github.com/facebook/rocksdb/issues/3469
-* ldb sometimes uses a string-append merge operator if no merge operator is passed in. This is to allow users to print keys from a DB with a merge operator.
-* Replaces old Registra with ObjectRegistry to allow user to create custom object from string, also add LoadEnv() to Env.
-* Added new overload of GetApproximateSizes which gets SizeApproximationOptions object and returns a Status. The older overloads are redirecting their calls to this new method and no longer assert if the include_flags doesn't have either of INCLUDE_MEMTABLES or INCLUDE_FILES bits set. It's recommended to use the new method only, as it is more type safe and returns a meaningful status in case of errors.
-* LDBCommandRunner::RunCommand() to return the status code as an integer, rather than call exit() using the code.
-
-### New Features
-* Add argument `--secondary_path` to ldb to open the database as the secondary instance. This would keep the original DB intact.
-* Compression dictionary blocks are now prefetched and pinned in the cache (based on the customer's settings) the same way as index and filter blocks.
-* Added DBOptions::log_readahead_size which specifies the number of bytes to prefetch when reading the log. This is mostly useful for reading a remotely located log, as it can save the number of round-trips. If 0 (default), then the prefetching is disabled.
-* Added new option in SizeApproximationOptions used with DB::GetApproximateSizes. When approximating the files total size that is used to store a keys range, allow approximation with an error margin of up to total_files_size * files_size_error_margin. This allows to take some shortcuts in files size approximation, resulting in better performance, while guaranteeing the resulting error is within a reasonable margin.
-* Support loading custom objects in unit tests. In the affected unit tests, RocksDB will create custom Env objects based on environment variable TEST_ENV_URI. Users need to make sure custom object types are properly registered. For example, a static library should expose a `RegisterCustomObjects` function. By linking the unit test binary with the static library, the unit test can execute this function.
-
-### Performance Improvements
-* Reduce iterator key comparison for upper/lower bound check.
-* Improve performance of row_cache: make reads with newer snapshots than data in an SST file share the same cache key, except in some transaction cases.
-* The compression dictionary is no longer copied to a new object upon retrieval.
-
-### Bug Fixes
-* Fix ingested file and directory not being fsync.
-* Return TryAgain status in place of Corruption when new tail is not visible to TransactionLogIterator.
-* Fixed a regression where the fill_cache read option also affected index blocks.
-* Fixed an issue where using cache_index_and_filter_blocks==false affected partitions of partitioned indexes/filters as well.
-
-## 6.3.2 (8/15/2019)
-### Public API Change
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-
-### Bug Fixes
-* Fixed a regression where the fill_cache read option also affected index blocks.
-* Fixed an issue where using cache_index_and_filter_blocks==false affected partitions of partitioned indexes as well.
-
-## 6.3.1 (7/24/2019)
-### Bug Fixes
-* Fix auto rolling bug introduced in 6.3.0, which causes segfault if log file creation fails.
-
-## 6.3.0 (6/18/2019)
-### Public API Change
-* Now DB::Close() will return Aborted() error when there is unreleased snapshot. Users can retry after all snapshots are released.
-* Index blocks are now handled similarly to data blocks with regards to the block cache: instead of storing objects in the cache, only the blocks themselves are cached. In addition, index blocks no longer get evicted from the cache when a table is closed, can now use the compressed block cache (if any), and can be shared among multiple table readers.
-* Partitions of partitioned indexes no longer affect the read amplification statistics.
-* Due to the above refactoring, block cache eviction statistics for indexes are temporarily broken. We plan to reintroduce them in a later phase.
-* options.keep_log_file_num will be enforced strictly all the time. File names of all log files will be tracked, which may take significantly amount of memory if options.keep_log_file_num is large and either of options.max_log_file_size or options.log_file_time_to_roll is set.
-* Add initial support for Get/Put with user timestamps. Users can specify timestamps via ReadOptions and WriteOptions when calling DB::Get and DB::Put.
-* Accessing a partition of a partitioned filter or index through a pinned reference is no longer considered a cache hit.
-* Add C bindings for secondary instance, i.e. DBImplSecondary.
-* Rate limited deletion of WALs is only enabled if DBOptions::wal_dir is not set, or explicitly set to db_name passed to DB::Open and DBOptions::db_paths is empty, or same as db_paths[0].path
-
-### New Features
-* Add an option `snap_refresh_nanos` (default to 0) to periodically refresh the snapshot list in compaction jobs. Assign to 0 to disable the feature.
-* Add an option `unordered_write` which trades snapshot guarantees with higher write throughput. When used with WRITE_PREPARED transactions with two_write_queues=true, it offers higher throughput with however no compromise on guarantees.
-* Allow DBImplSecondary to remove memtables with obsolete data after replaying MANIFEST and WAL.
-* Add an option `failed_move_fall_back_to_copy` (default is true) for external SST ingestion. When `move_files` is true and hard link fails, ingestion falls back to copy if `failed_move_fall_back_to_copy` is true. Otherwise, ingestion reports an error.
-* Add command `list_file_range_deletes` in ldb, which prints out tombstones in SST files.
-
-### Performance Improvements
-* Reduce binary search when iterator reseek into the same data block.
-* DBIter::Next() can skip user key checking if previous entry's seqnum is 0.
-* Merging iterator to avoid child iterator reseek for some cases
-* Log Writer will flush after finishing the whole record, rather than a fragment.
-* Lower MultiGet batching API latency by reading data blocks from disk in parallel
-
-### General Improvements
-* Added new status code kColumnFamilyDropped to distinguish between Column Family Dropped and DB Shutdown in progress.
-* Improve ColumnFamilyOptions validation when creating a new column family.
-
-### Bug Fixes
-* Fix a bug in WAL replay of secondary instance by skipping write batches with older sequence numbers than the current last sequence number.
-* Fix flush's/compaction's merge processing logic which allowed `Put`s covered by range tombstones to reappear. Note `Put`s may exist even if the user only ever called `Merge()` due to an internal conversion during compaction to the bottommost level.
-* Fix/improve memtable earliest sequence assignment and WAL replay so that WAL entries of unflushed column families will not be skipped after replaying the MANIFEST and increasing db sequence due to another flushed/compacted column family.
-* Fix a bug caused by secondary not skipping the beginning of new MANIFEST.
-* On DB open, delete WAL trash files left behind in wal_dir
-
-## 6.2.0 (4/30/2019)
-### New Features
-* Add an option `strict_bytes_per_sync` that causes a file-writing thread to block rather than exceed the limit on bytes pending writeback specified by `bytes_per_sync` or `wal_bytes_per_sync`.
-* Improve range scan performance by avoiding per-key upper bound check in BlockBasedTableIterator.
-* Introduce Periodic Compaction for Level style compaction. Files are re-compacted periodically and put in the same level.
-* Block-based table index now contains exact highest key in the file, rather than an upper bound. This may improve Get() and iterator Seek() performance in some situations, especially when direct IO is enabled and block cache is disabled. A setting BlockBasedTableOptions::index_shortening is introduced to control this behavior. Set it to kShortenSeparatorsAndSuccessor to get the old behavior.
-* When reading from option file/string/map, customized envs can be filled according to object registry.
-* Improve range scan performance when using explicit user readahead by not creating new table readers for every iterator.
-* Add index type BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey. It significantly reduces read amplification in some setups, especially for iterator seeks. It's not fully implemented yet: IO errors are not handled right.
-
-### Public API Change
-* Change the behavior of OptimizeForPointLookup(): move away from hash-based block-based-table index, and use whole key memtable filtering.
-* Change the behavior of OptimizeForSmallDb(): use a 16MB block cache, put index and filter blocks into it, and cost the memtable size to it. DBOptions.OptimizeForSmallDb() and ColumnFamilyOptions.OptimizeForSmallDb() start to take an optional cache object.
-* Added BottommostLevelCompaction::kForceOptimized to avoid double compacting newly compacted files in the bottommost level compaction of manual compaction. Note this option may prohibit the manual compaction to produce a single file in the bottommost level.
-
-### Bug Fixes
-* Adjust WriteBufferManager's dummy entry size to block cache from 1MB to 256KB.
-* Fix a race condition between WritePrepared::Get and ::Put with duplicate keys.
-* Fix crash when memtable prefix bloom is enabled and read/write a key out of domain of prefix extractor.
-* Close a WAL file before another thread deletes it.
-* Fix an assertion failure `IsFlushPending() == true` caused by one bg thread releasing the db mutex in ~ColumnFamilyData and another thread clearing `flush_requested_` flag.
-
-## 6.1.1 (4/9/2019)
-### New Features
-* When reading from option file/string/map, customized comparators and/or merge operators can be filled according to object registry.
-
-### Public API Change
-
-### Bug Fixes
-* Fix a bug in 2PC where a sequence of txn prepare, memtable flush, and crash could result in losing the prepared transaction.
-* Fix a bug in Encryption Env which could cause encrypted files to be read beyond file boundaries.
-
-## 6.1.0 (3/27/2019)
-### New Features
-* Introduce two more stats levels, kExceptHistogramOrTimers and kExceptTimers.
-* Added a feature to perform data-block sampling for compressibility, and report stats to user.
-* Add support for trace filtering.
-* Add DBOptions.avoid_unnecessary_blocking_io. If true, we avoid file deletion when destroying ColumnFamilyHandle and Iterator. Instead, a job is scheduled to delete the files in background.
-
-### Public API Change
-* Remove bundled fbson library.
-* statistics.stats_level_ becomes atomic. It is preferred to use statistics.set_stats_level() and statistics.get_stats_level() to access it.
-* Introduce a new IOError subcode, PathNotFound, to indicate trying to open a nonexistent file or directory for read.
-* Add initial support for multiple db instances sharing the same data in single-writer, multi-reader mode.
-* Removed some "using std::xxx" from public headers.
-
-### Bug Fixes
-* Fix JEMALLOC_CXX_THROW macro missing from older Jemalloc versions, causing build failures on some platforms.
-* Fix SstFileReader not able to open file ingested with write_glbal_seqno=true.
-
-## 6.0.0 (2/19/2019)
-### New Features
-* Enabled checkpoint on readonly db (DBImplReadOnly).
-* Make DB ignore dropped column families while committing results of atomic flush.
-* RocksDB may choose to preopen some files even if options.max_open_files != -1. This may make DB open slightly longer.
-* For users of dictionary compression with ZSTD v0.7.0+, we now reuse the same digested dictionary when compressing each of an SST file's data blocks for faster compression speeds.
-* For all users of dictionary compression who set `cache_index_and_filter_blocks == true`, we now store dictionary data used for decompression in the block cache for better control over memory usage. For users of ZSTD v1.1.4+ who compile with -DZSTD_STATIC_LINKING_ONLY, this includes a digested dictionary, which is used to increase decompression speed.
-* Add support for block checksums verification for external SST files before ingestion.
-* Introduce stats history which periodically saves Statistics snapshots and added `GetStatsHistory` API to retrieve these snapshots.
-* Add a place holder in manifest which indicate a record from future that can be safely ignored.
-* Add support for trace sampling.
-* Enable properties block checksum verification for block-based tables.
-* For all users of dictionary compression, we now generate a separate dictionary for compressing each bottom-level SST file. Previously we reused a single dictionary for a whole compaction to bottom level. The new approach achieves better compression ratios; however, it uses more memory and CPU for buffering/sampling data blocks and training dictionaries.
-* Add whole key bloom filter support in memtable.
-* Files written by `SstFileWriter` will now use dictionary compression if it is configured in the file writer's `CompressionOptions`.
-
-### Public API Change
-* Disallow CompactionFilter::IgnoreSnapshots() = false, because it is not very useful and the behavior is confusing. The filter will filter everything if there is no snapshot declared by the time the compaction starts. However, users can define a snapshot after the compaction starts and before it finishes and this new snapshot won't be repeatable, because after the compaction finishes, some keys may be dropped.
-* CompactionPri = kMinOverlappingRatio also uses compensated file size, which boosts file with lots of tombstones to be compacted first.
-* Transaction::GetForUpdate is extended with a do_validate parameter with default value of true. If false it skips validating the snapshot before doing the read. Similarly ::Merge, ::Put, ::Delete, and ::SingleDelete are extended with assume_tracked with default value of false. If true it indicates that call is assumed to be after a ::GetForUpdate.
-* `TableProperties::num_entries` and `TableProperties::num_deletions` now also account for number of range tombstones.
-* Remove geodb, spatial_db, document_db, json_document, date_tiered_db, and redis_lists.
-* With "ldb ----try_load_options", when wal_dir specified by the option file doesn't exist, ignore it.
-* Change time resolution in FileOperationInfo.
-* Deleting Blob files also go through SStFileManager.
-* Remove CuckooHash memtable.
-* The counter stat `number.block.not_compressed` now also counts blocks not compressed due to poor compression ratio.
-* Remove ttl option from `CompactionOptionsFIFO`. The option has been deprecated and ttl in `ColumnFamilyOptions` is used instead.
-* Support SST file ingestion across multiple column families via DB::IngestExternalFiles. See the function's comment about atomicity.
-* Remove Lua compaction filter.
-
-### Bug Fixes
-* Fix a deadlock caused by compaction and file ingestion waiting for each other in the event of write stalls.
-* Fix a memory leak when files with range tombstones are read in mmap mode and block cache is enabled
-* Fix handling of corrupt range tombstone blocks such that corruptions cannot cause deleted keys to reappear
-* Lock free MultiGet
-* Fix incorrect `NotFound` point lookup result when querying the endpoint of a file that has been extended by a range tombstone.
-* Fix with pipelined write, write leaders's callback failure lead to the whole write group fail.
-
-### Change Default Options
-* Change options.compaction_pri's default to kMinOverlappingRatio
-
-## 5.18.0 (11/30/2018)
-### New Features
-* Introduced `JemallocNodumpAllocator` memory allocator. When being use, block cache will be excluded from core dump.
-* Introduced `PerfContextByLevel` as part of `PerfContext` which allows storing perf context at each level. Also replaced `__thread` with `thread_local` keyword for perf_context. Added per-level perf context for bloom filter and `Get` query.
-* With level_compaction_dynamic_level_bytes = true, level multiplier may be adjusted automatically when Level 0 to 1 compaction is lagged behind.
-* Introduced DB option `atomic_flush`. If true, RocksDB supports flushing multiple column families and atomically committing the result to MANIFEST. Useful when WAL is disabled.
-* Added `num_deletions` and `num_merge_operands` members to `TableProperties`.
-* Added "rocksdb.min-obsolete-sst-number-to-keep" DB property that reports the lower bound on SST file numbers that are being kept from deletion, even if the SSTs are obsolete.
-* Add xxhash64 checksum support
-* Introduced `MemoryAllocator`, which lets the user specify custom memory allocator for block based table.
-* Improved `DeleteRange` to prevent read performance degradation. The feature is no longer marked as experimental.
-
-### Public API Change
-* `DBOptions::use_direct_reads` now affects reads issued by `BackupEngine` on the database's SSTs.
-* `NO_ITERATORS` is divided into two counters `NO_ITERATOR_CREATED` and `NO_ITERATOR_DELETE`. Both of them are only increasing now, just as other counters.
-
-### Bug Fixes
-* Fix corner case where a write group leader blocked due to write stall blocks other writers in queue with WriteOptions::no_slowdown set.
-* Fix in-memory range tombstone truncation to avoid erroneously covering newer keys at a lower level, and include range tombstones in compacted files whose largest key is the range tombstone's start key.
-* Properly set the stop key for a truncated manual CompactRange
-* Fix slow flush/compaction when DB contains many snapshots. The problem became noticeable to us in DBs with 100,000+ snapshots, though it will affect others at different thresholds.
-* Fix the bug that WriteBatchWithIndex's SeekForPrev() doesn't see the entries with the same key.
-* Fix the bug where user comparator was sometimes fed with InternalKey instead of the user key. The bug manifests when during GenerateBottommostFiles.
-* Fix a bug in WritePrepared txns where if the number of old snapshots goes beyond the snapshot cache size (128 default) the rest will not be checked when evicting a commit entry from the commit cache.
-* Fixed Get correctness bug in the presence of range tombstones where merge operands covered by a range tombstone always result in NotFound.
-* Start populating `NO_FILE_CLOSES` ticker statistic, which was always zero previously.
-* The default value of NewBloomFilterPolicy()'s argument use_block_based_builder is changed to false. Note that this new default may cause large temp memory usage when building very large SST files.
-
-## 5.17.0 (10/05/2018)
-### Public API Change
-* `OnTableFileCreated` will now be called for empty files generated during compaction. In that case, `TableFileCreationInfo::file_path` will be "(nil)" and `TableFileCreationInfo::file_size` will be zero.
-* Add `FlushOptions::allow_write_stall`, which controls whether Flush calls start working immediately, even if it causes user writes to stall, or will wait until flush can be performed without causing write stall (similar to `CompactRangeOptions::allow_write_stall`). Note that the default value is false, meaning we add delay to Flush calls until stalling can be avoided when possible. This is behavior change compared to previous RocksDB versions, where Flush calls didn't check if they might cause stall or not.
-* Application using PessimisticTransactionDB is expected to rollback/commit recovered transactions before starting new ones. This assumption is used to skip concurrency control during recovery.
-* Expose column family id to `OnCompactionCompleted`.
-
-### New Features
-* TransactionOptions::skip_concurrency_control allows pessimistic transactions to skip the overhead of concurrency control. Could be used for optimizing certain transactions or during recovery.
-
-### Bug Fixes
-* Avoid creating empty SSTs and subsequently deleting them in certain cases during compaction.
-* Sync CURRENT file contents during checkpoint.
-
-## 5.16.3 (10/1/2018)
-### Bug Fixes
-* Fix crash caused when `CompactFiles` run with `CompactionOptions::compression == CompressionType::kDisableCompressionOption`. Now that setting causes the compression type to be chosen according to the column family-wide compression options.
-
-## 5.16.2 (9/21/2018)
-### Bug Fixes
-* Fix bug in partition filters with format_version=4.
-
-## 5.16.1 (9/17/2018)
-### Bug Fixes
-* Remove trace_analyzer_tool from rocksdb_lib target in TARGETS file.
-* Fix RocksDB Java build and tests.
-* Remove sync point in Block destructor.
-
-## 5.16.0 (8/21/2018)
-### Public API Change
-* The merge operands are passed to `MergeOperator::ShouldMerge` in the reversed order relative to how they were merged (passed to FullMerge or FullMergeV2) for performance reasons
-* GetAllKeyVersions() to take an extra argument of `max_num_ikeys`.
-* Using ZSTD dictionary trainer (i.e., setting `CompressionOptions::zstd_max_train_bytes` to a nonzero value) now requires ZSTD version 1.1.3 or later.
-
-### New Features
-* Changes the format of index blocks by delta encoding the index values, which are the block handles. This saves the encoding of BlockHandle::offset of the non-head index entries in each restart interval. The feature is backward compatible but not forward compatible. It is disabled by default unless format_version 4 or above is used.
-* Add a new tool: trace_analyzer. Trace_analyzer analyzes the trace file generated by using trace_replay API. It can convert the binary format trace file to a human readable txt file, output the statistics of the analyzed query types such as access statistics and size statistics, combining the dumped whole key space file to analyze, support query correlation analyzing, and etc. Current supported query types are: Get, Put, Delete, SingleDelete, DeleteRange, Merge, Iterator (Seek, SeekForPrev only).
-* Add hash index support to data blocks, which helps reducing the cpu utilization of point-lookup operations. This feature is backward compatible with the data block created without the hash index. It is disabled by default unless BlockBasedTableOptions::data_block_index_type is set to data_block_index_type = kDataBlockBinaryAndHash.
-
-### Bug Fixes
-* Fix a bug in misreporting the estimated partition index size in properties block.
-
-## 5.15.0 (7/17/2018)
-### Public API Change
-* Remove managed iterator. ReadOptions.managed is not effective anymore.
-* For bottommost_compression, a compatible CompressionOptions is added via `bottommost_compression_opts`. To keep backward compatible, a new boolean `enabled` is added to CompressionOptions. For compression_opts, it will be always used no matter what value of `enabled` is. For bottommost_compression_opts, it will only be used when user set `enabled=true`, otherwise, compression_opts will be used for bottommost_compression as default.
-* With LRUCache, when high_pri_pool_ratio > 0, midpoint insertion strategy will be enabled to put low-pri items to the tail of low-pri list (the midpoint) when they first inserted into the cache. This is to make cache entries never get hit age out faster, improving cache efficiency when large background scan presents.
-* For users of `Statistics` objects created via `CreateDBStatistics()`, the format of the string returned by its `ToString()` method has changed.
-* The "rocksdb.num.entries" table property no longer counts range deletion tombstones as entries.
-
-### New Features
-* Changes the format of index blocks by storing the key in their raw form rather than converting them to InternalKey. This saves 8 bytes per index key. The feature is backward compatible but not forward compatible. It is disabled by default unless format_version 3 or above is used.
-* Avoid memcpy when reading mmap files with OpenReadOnly and max_open_files==-1.
-* Support dynamically changing `ColumnFamilyOptions::ttl` via `SetOptions()`.
-* Add a new table property, "rocksdb.num.range-deletions", which counts the number of range deletion tombstones in the table.
-* Improve the performance of iterators doing long range scans by using readahead, when using direct IO.
-* pin_top_level_index_and_filter (default true) in BlockBasedTableOptions can be used in combination with cache_index_and_filter_blocks to prefetch and pin the top-level index of partitioned index and filter blocks in cache. It has no impact when cache_index_and_filter_blocks is false.
-* Write properties meta-block at the end of block-based table to save read-ahead IO.
-
-### Bug Fixes
-* Fix deadlock with enable_pipelined_write=true and max_successive_merges > 0
-* Check conflict at output level in CompactFiles.
-* Fix corruption in non-iterator reads when mmap is used for file reads
-* Fix bug with prefix search in partition filters where a shared prefix would be ignored from the later partitions. The bug could report an eixstent key as missing. The bug could be triggered if prefix_extractor is set and partition filters is enabled.
-* Change default value of `bytes_max_delete_chunk` to 0 in NewSstFileManager() as it doesn't work well with checkpoints.
-* Fix a bug caused by not copying the block trailer with compressed SST file, direct IO, prefetcher and no compressed block cache.
-* Fix write can stuck indefinitely if enable_pipelined_write=true. The issue exists since pipelined write was introduced in 5.5.0.
-
-## 5.14.0 (5/16/2018)
-### Public API Change
-* Add a BlockBasedTableOption to align uncompressed data blocks on the smaller of block size or page size boundary, to reduce flash reads by avoiding reads spanning 4K pages.
-* The background thread naming convention changed (on supporting platforms) to "rocksdb:<thread pool priority><thread number>", e.g., "rocksdb:low0".
-* Add a new ticker stat rocksdb.number.multiget.keys.found to count number of keys successfully read in MultiGet calls
-* Touch-up to write-related counters in PerfContext. New counters added: write_scheduling_flushes_compactions_time, write_thread_wait_nanos. Counters whose behavior was fixed or modified: write_memtable_time, write_pre_and_post_process_time, write_delay_time.
-* Posix Env's NewRandomRWFile() will fail if the file doesn't exist.
-* Now, `DBOptions::use_direct_io_for_flush_and_compaction` only applies to background writes, and `DBOptions::use_direct_reads` applies to both user reads and background reads. This conforms with Linux's `open(2)` manpage, which advises against simultaneously reading a file in buffered and direct modes, due to possibly undefined behavior and degraded performance.
-* Iterator::Valid() always returns false if !status().ok(). So, now when doing a Seek() followed by some Next()s, there's no need to check status() after every operation.
-* Iterator::Seek()/SeekForPrev()/SeekToFirst()/SeekToLast() always resets status().
-* Introduced `CompressionOptions::kDefaultCompressionLevel`, which is a generic way to tell RocksDB to use the compression library's default level. It is now the default value for `CompressionOptions::level`. Previously the level defaulted to -1, which gave poor compression ratios in ZSTD.
-
-### New Features
-* Introduce TTL for level compaction so that all files older than ttl go through the compaction process to get rid of old data.
-* TransactionDBOptions::write_policy can be configured to enable WritePrepared 2PC transactions. Read more about them in the wiki.
-* Add DB properties "rocksdb.block-cache-capacity", "rocksdb.block-cache-usage", "rocksdb.block-cache-pinned-usage" to show block cache usage.
-* Add `Env::LowerThreadPoolCPUPriority(Priority)` method, which lowers the CPU priority of background (esp. compaction) threads to minimize interference with foreground tasks.
-* Fsync parent directory after deleting a file in delete scheduler.
-* In level-based compaction, if bottom-pri thread pool was setup via `Env::SetBackgroundThreads()`, compactions to the bottom level will be delegated to that thread pool.
-* `prefix_extractor` has been moved from ImmutableCFOptions to MutableCFOptions, meaning it can be dynamically changed without a DB restart.
 
 ### Bug Fixes
 * Fsync after writing global seq number to the ingestion file in ExternalSstFileIngestionJob.
-* Fix WAL corruption caused by race condition between user write thread and FlushWAL when two_write_queue is not set.
-* Fix `BackupableDBOptions::max_valid_backups_to_open` to not delete backup files when refcount cannot be accurately determined.
-* Fix memory leak when pin_l0_filter_and_index_blocks_in_cache is used with partitioned filters
-* Disable rollback of merge operands in WritePrepared transactions to work around an issue in MyRocks. It can be enabled back by setting TransactionDBOptions::rollback_merge_operands to true.
-* Fix wrong results by ReverseBytewiseComparator::FindShortSuccessor()
 
 ### Java API Changes
 * Add `BlockBasedTableConfig.setBlockCache` to allow sharing a block cache across DB instances.
-* Added SstFileManager to the Java API to allow managing SST files across DB instances.
 
 ## 5.13.0 (3/20/2018)
 ### Public API Change
@@ -488,8 +85,7 @@
 * `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 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);`.
+* `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 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.
@@ -608,7 +204,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 
 ## 5.2.0 (02/08/2017)
 ### Public API Change
-* NewLRUCache() will determine number of shard bits automatically based on capacity, if the user doesn't pass one. This also impacts the default block cache when the user doesn't explicit provide one.
+* NewLRUCache() will determine number of shard bits automatically based on capacity, if the user doesn't pass one. This also impacts the default block cache when the user doesn't explict provide one.
 * Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files.
 * Options::use_direct_writes and Options::use_direct_reads are now ready to use.
 * (Experimental) Two-level indexing that partition the index and creates a 2nd level index on the partitions. The feature can be enabled by setting kTwoLevelIndexSearch as IndexType and configuring index_per_partition.
@@ -679,7 +275,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 
 ### New Features
 * A tool to migrate DB after options change. See include/rocksdb/utilities/option_change_migration.h.
-* Add ReadOptions.background_purge_on_iterator_cleanup. If true, we avoid file deletion when destroying iterators.
+* Add ReadOptions.background_purge_on_iterator_cleanup. If true, we avoid file deletion when destorying iterators.
 
 ## 4.10.0 (7/5/2016)
 ### Public API Change

INSTALL.md

@@ -43,8 +43,6 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
       command line flags processing. You can compile rocksdb library even
       if you don't have gflags installed.
 
-* If you wish to build the RocksJava static target, then cmake is required for building Snappy.
-
 ## Supported platforms
 
 * **Linux - Ubuntu**

LANGUAGE-BINDINGS.md

@@ -1,9 +1,7 @@
 This is the list of all known third-party language bindings for RocksDB. If something is missing, please open a pull request to add it.
 
 * Java - https://github.com/facebook/rocksdb/tree/master/java
-* Python
-    * http://python-rocksdb.readthedocs.io/en/latest/
-    * http://pyrocksdb.readthedocs.org/en/latest/ (unmaintained)
+* Python - http://pyrocksdb.readthedocs.org/en/latest/
 * Perl - https://metacpan.org/pod/RocksDB
 * Node.js - https://npmjs.org/package/rocksdb
 * Go - https://github.com/tecbot/gorocksdb
@@ -12,11 +10,9 @@ This is the list of all known third-party language bindings for RocksDB. If some
 * PHP - https://github.com/Photonios/rocksdb-php
 * C# - https://github.com/warrenfalk/rocksdb-sharp
 * Rust
-    * https://github.com/pingcap/rust-rocksdb (used in production fork of https://github.com/spacejam/rust-rocksdb)
     * https://github.com/spacejam/rust-rocksdb
     * https://github.com/bh1xuw/rust-rocks
 * D programming language - https://github.com/b1naryth1ef/rocksdb
 * Erlang - https://gitlab.com/barrel-db/erlang-rocksdb
 * Elixir - https://github.com/urbint/rox
 * Nim - https://github.com/status-im/nim-rocksdb
-* Swift and Objective-C (iOS/OSX) - https://github.com/iabudiab/ObjectiveRocks 

README.md

@@ -4,16 +4,17 @@
 [![Windows Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
 [![PPC64le Build Status](http://140.211.168.68:8080/buildStatus/icon?job=Rocksdb)](http://140.211.168.68:8080/job/Rocksdb)
 
+
 RocksDB is developed and maintained by Facebook Database Engineering Team.
-It is built on earlier work on [LevelDB](https://github.com/google/leveldb) by Sanjay Ghemawat (sanjay@google.com)
+It is built on earlier work on LevelDB by Sanjay Ghemawat (sanjay@google.com)
 and Jeff Dean (jeff@google.com)
 
 This code is a library that forms the core building block for a fast
-key-value server, especially suited for storing data on flash drives.
+key value server, especially suited for storing data on flash drives.
 It has a Log-Structured-Merge-Database (LSM) design with flexible tradeoffs
 between Write-Amplification-Factor (WAF), Read-Amplification-Factor (RAF)
 and Space-Amplification-Factor (SAF). It has multi-threaded compactions,
-making it especially suitable for storing multiple terabytes of data in a
+making it specially suitable for storing multiple terabytes of data in a
 single database.
 
 Start with example usage here: https://github.com/facebook/rocksdb/tree/master/examples

USERS.md

@@ -12,7 +12,6 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
 6. LogDevice -- a distributed data store for logs [2]
 
 [1] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
-
 [2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/
 
 ## LinkedIn
@@ -27,7 +26,7 @@ Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasu
 Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa. Learn more about it here: http://yahooeng.tumblr.com/post/120730204806/sherpa-scales-new-heights
 
 ## CockroachDB
-CockroachDB is an open-source geo-replicated transactional database. They are using RocksDB as their storage engine. Check out their github: https://github.com/cockroachdb/cockroach
+CockroachDB is an open-source geo-replicated transactional database (still in development). They are using RocksDB as their storage engine. Check out their github: https://github.com/cockroachdb/cockroach
 
 ## DNANexus
 DNANexus is using RocksDB to speed up processing of genomics data.
@@ -50,10 +49,6 @@ Check out their blog post: http://blog.cloudera.com/blog/2015/08/inside-santande
 ## Airbnb
 Airbnb is using RocksDB as a storage engine for their personalized search service. You can learn more about it here: https://www.youtube.com/watch?v=ASQ6XMtogMs
 
-## Alluxio
-[Alluxio](https://www.alluxio.io) uses RocksDB to serve and scale file system metadata to beyond 1 Billion files. The detailed design and implementation is described in this engineering blog:
-https://www.alluxio.io/blog/scalable-metadata-service-in-alluxio-storing-billions-of-files/
-
 ## Pinterest
 Pinterest's Object Retrieval System uses RocksDB for storage: https://www.youtube.com/watch?v=MtFEVEs_2Vo
 
@@ -93,12 +88,3 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 
 ## 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.
-
-## IOTA Foundation
- [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
- 
-## Avrio Project
- [Avrio Project](http://avrio-project.github.io/avrio.network/) is using RocksDB in [Avrio ](https://github.com/avrio-project/avrio) to store blocks, account balances and data and other blockchain-releated data. Avrio is a multiblockchain decentralized cryptocurrency empowering monetary transactions.
- 
-## Crux
-[Crux](https://github.com/juxt/crux) is a document database that uses RocksDB for local [EAV](https://en.wikipedia.org/wiki/Entity%E2%80%93attribute%E2%80%93value_model) index storage to enable point-in-time bitemporal Datalog queries. The "unbundled" architecture uses Kafka to provide horizontal scalability.

WINDOWS_PORT.md

@@ -43,9 +43,9 @@ We plan to use this port for our business purposes here at Bing and this provide
 
 * Certain headers that are not present and not necessary on Windows were simply `#ifndef OS_WIN` in a few places (`unistd.h`)
 * All posix specific headers were replaced to port/port.h which worked well
-* Replaced `dirent.h` for `port/port_dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
+* Replaced `dirent.h` for `port/dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
 * Replaced `sys/time.h` to `port/sys_time.h` (few places) implemented equivalents within `rocksdb::port`
-* `printf %z` specification is not supported on Windows. To imitate existing standards we came up with a string macro `ROCKSDB_PRIszt` which expands to `zu` on posix systems and to `Iu` on windows.
+* `printf %z` specification is not supported on Windows. To imitate existing standards we came up with a string macro `ROCKSDB_PRIszt` which expands to `%z` on posix systems and to Iu on windows.
 * in class member initialization were moved to a __ctors in some cases
 * `constexpr` is not supported. We had to replace `std::numeric_limits<>::max/min()` to its C macros for constants. Sometimes we had to make class members `static const` and place a definition within a .cc file.
 * `constexpr` for functions was replaced to a template specialization (1 place)

appveyor.yml

@@ -1,75 +1,15 @@
 version: 1.0.{build}
-
 image: Visual Studio 2017
-
-environment:
-  JAVA_HOME: C:\Program Files\Java\jdk1.8.0
-  THIRDPARTY_HOME: $(APPVEYOR_BUILD_FOLDER)\thirdparty
-  SNAPPY_HOME: $(THIRDPARTY_HOME)\snappy-1.1.7
-  SNAPPY_INCLUDE: $(SNAPPY_HOME);$(SNAPPY_HOME)\build
-  SNAPPY_LIB_DEBUG: $(SNAPPY_HOME)\build\Debug\snappy.lib
-  SNAPPY_LIB_RELEASE: $(SNAPPY_HOME)\build\Release\snappy.lib
-  LZ4_HOME: $(THIRDPARTY_HOME)\lz4-1.8.3
-  LZ4_INCLUDE: $(LZ4_HOME)\lib
-  LZ4_LIB_DEBUG: $(LZ4_HOME)\visual\VS2010\bin\x64_Debug\liblz4_static.lib
-  LZ4_LIB_RELEASE: $(LZ4_HOME)\visual\VS2010\bin\x64_Release\liblz4_static.lib
-  ZSTD_HOME: $(THIRDPARTY_HOME)\zstd-1.4.0
-  ZSTD_INCLUDE: $(ZSTD_HOME)\lib;$(ZSTD_HOME)\lib\dictBuilder
-  ZSTD_LIB_DEBUG: $(ZSTD_HOME)\build\VS2010\bin\x64_Debug\libzstd_static.lib
-  ZSTD_LIB_RELEASE: $(ZSTD_HOME)\build\VS2010\bin\x64_Release\libzstd_static.lib
-  matrix:
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015
-      CMAKE_GENERATOR: Visual Studio 14 Win64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio 14.0\Common7\IDE\devenv.com
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2017
-      CMAKE_GENERATOR: Visual Studio 15 Win64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com
-
-install:
-  - md %THIRDPARTY_HOME%
-  - echo "Building Snappy dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o snappy-1.1.7.zip https://github.com/google/snappy/archive/1.1.7.zip
-  - unzip snappy-1.1.7.zip
-  - cd snappy-1.1.7
-  - mkdir build
-  - cd build
-  - cmake -G "%CMAKE_GENERATOR%" ..
-  - msbuild Snappy.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild Snappy.sln /p:Configuration=Release /p:Platform=x64
-  - echo "Building LZ4 dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o lz4-1.8.3.zip https://github.com/lz4/lz4/archive/v1.8.3.zip
-  - unzip lz4-1.8.3.zip
-  - cd lz4-1.8.3\visual\VS2010
-  - ps: $CMD="$Env:DEV_ENV"; & $CMD lz4.sln /upgrade
-  - msbuild lz4.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild lz4.sln /p:Configuration=Release /p:Platform=x64
-  - echo "Building ZStd dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o zstd-1.4.0.zip https://github.com/facebook/zstd/archive/v1.4.0.zip
-  - unzip zstd-1.4.0.zip
-  - cd zstd-1.4.0\build\VS2010
-  - ps: $CMD="$Env:DEV_ENV"; & $CMD zstd.sln /upgrade
-  - msbuild zstd.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild zstd.sln /p:Configuration=Release /p:Platform=x64
-
 before_build:
-  - md %APPVEYOR_BUILD_FOLDER%\build
-  - cd %APPVEYOR_BUILD_FOLDER%\build
-  - cmake -G "%CMAKE_GENERATOR%" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1 ..
-  - cd ..
-
+- md %APPVEYOR_BUILD_FOLDER%\build
+- cd %APPVEYOR_BUILD_FOLDER%\build
+- cmake -G "Visual Studio 15 Win64" -DOPTDBG=1 -DWITH_XPRESS=1 -DPORTABLE=1 ..
+- cd ..
 build:
   project: build\rocksdb.sln
   parallel: true
   verbosity: normal
-
 test:
-
 test_script:
-  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test,db_merge_operand_test -Concurrency 8
-
-on_failure:
-  - cmd: 7z a build-failed.zip %APPVEYOR_BUILD_FOLDER%\build\ && appveyor PushArtifact build-failed.zip
+- ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test -Concurrency 8
 

buckifier/buckify_rocksdb.py

@@ -1,37 +1,16 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import str
-except ImportError:
-    from __builtin__ import str
 from targets_builder import TARGETSBuilder
-import json
+from optparse import OptionParser
 import os
 import fnmatch
 import sys
+import tempfile
 
 from util import ColorString
-
-# This script generates TARGETS file for Buck.
-# Buck is a build tool specifying dependencies among different build targets.
-# User can pass extra dependencies as a JSON object via command line, and this
-# script can include these dependencies in the generate TARGETS file.
-# Usage:
-# $python buckifier/buckify_rocksdb.py
-# (This generates a TARGET file without user-specified dependency for unit
-# tests.)
-# $python buckifier/buckify_rocksdb.py \
-#        '{"fake": { \
-#                      "extra_deps": [":test_dep", "//fakes/module:mock1"],  \
-#                      "extra_compiler_flags": ["-DROCKSDB_LITE", "-Os"], \
-#                  } \
-#         }'
-# (Generated TARGETS file has test_dep and mock1 as dependencies for RocksDB
-# unit tests, and will use the extra_compiler_flags to compile the unit test
-# source.)
+import util
 
 # tests to export as libraries for inclusion in other projects
 _EXPORTED_TEST_LIBS = ["env_basic_test"]
@@ -105,36 +84,12 @@ def get_tests(repo_path):
             else:
                 # we consumed all the parallel tests
                 break
-
+    
     return tests
 
 
-# Parse extra dependencies passed by user from command line
-def get_dependencies():
-    deps_map = {
-        '': {
-            'extra_deps': [],
-            'extra_compiler_flags': []
-        }
-    }
-    if len(sys.argv) < 2:
-        return deps_map
-
-    def encode_dict(data):
-        rv = {}
-        for k, v in data.items():
-            if isinstance(v, dict):
-                v = encode_dict(v)
-            rv[k] = v
-        return rv
-    extra_deps = json.loads(sys.argv[1], object_hook=encode_dict)
-    for target_alias, deps in extra_deps.items():
-        deps_map[target_alias] = deps
-    return deps_map
-
-
 # Prepare TARGETS file for buck
-def generate_targets(repo_path, deps_map):
+def generate_targets(repo_path):
     print(ColorString.info("Generating TARGETS"))
     # parsed src.mk file
     src_mk = parse_src_mk(repo_path)
@@ -157,51 +112,33 @@ def generate_targets(repo_path, deps_map):
         "rocksdb_test_lib",
         src_mk.get("MOCK_LIB_SOURCES", []) +
         src_mk.get("TEST_LIB_SOURCES", []) +
-        src_mk.get("EXP_LIB_SOURCES", []) +
-        src_mk.get("ANALYZER_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", []) +
-        src_mk.get("ANALYZER_LIB_SOURCES", []) +
-        ["test_util/testutil.cc"],
-        [":rocksdb_lib"])
-    # rocksdb_stress_lib
-    TARGETS.add_library(
-        "rocksdb_stress_lib",
-        src_mk.get("ANALYZER_LIB_SOURCES", [])
-        + src_mk.get('STRESS_LIB_SOURCES', [])
-        + ["test_util/testutil.cc"],
+        ["util/testutil.cc"],
         [":rocksdb_lib"])
 
-    print("Extra dependencies:\n{0}".format(str(deps_map)))
     # test for every test we found in the Makefile
-    for target_alias, deps in deps_map.items():
-        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
+    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]
-            test_target_name = \
-                test if not target_alias else test + "_" + target_alias
-            TARGETS.register_test(
-                test_target_name,
-                match_src[0],
-                is_parallel,
-                deps['extra_deps'],
-                deps['extra_compiler_flags'])
+        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_target_name
-                TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
+        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:"))
@@ -226,9 +163,8 @@ def exit_with_error(msg):
 
 
 def main():
-    deps_map = get_dependencies()
     # Generate TARGETS file for buck
-    ok = generate_targets(get_rocksdb_path(), deps_map)
+    ok = generate_targets(get_rocksdb_path())
     if not ok:
         exit_with_error("Failed to generate TARGETS files")
 

buckifier/rocks_test_runner.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # Create a tmp directory for the test to use
 TEST_DIR=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
 # shellcheck disable=SC2068

buckifier/targets_builder.py

@@ -1,14 +1,7 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import object
-    from builtins import str
-except ImportError:
-    from __builtin__ import object
-    from __builtin__ import str
 import targets_cfg
 
 def pretty_list(lst, indent=8):
@@ -17,14 +10,14 @@ def pretty_list(lst, indent=8):
 
     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(object):
+class TARGETSBuilder:
     def __init__(self, path):
         self.path = path
         self.targets_file = open(path, 'w')
@@ -38,16 +31,13 @@ class TARGETSBuilder(object):
         self.targets_file.close()
 
     def add_library(self, name, srcs, deps=None, headers=None):
-        headers_attr_prefix = ""
         if headers is None:
-            headers_attr_prefix = "auto_"
             headers = "AutoHeaders.RECURSIVE_GLOB"
-        self.targets_file.write(targets_cfg.library_template.format(
-            name=name,
-            srcs=pretty_list(srcs),
-            headers_attr_prefix=headers_attr_prefix,
-            headers=headers,
-            deps=pretty_list(deps)))
+        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):
@@ -57,21 +47,14 @@ class TARGETSBuilder(object):
             pretty_list(deps)))
         self.total_bin = self.total_bin + 1
 
-    def register_test(self,
-                      test_name,
-                      src,
-                      is_parallel,
-                      extra_deps,
-                      extra_compiler_flags):
+    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),
-            extra_deps,
-            extra_compiler_flags)
+            str(exec_mode))
 
         self.total_test = self.total_test + 1
 

buckifier/targets_cfg.py

@@ -1,30 +1,37 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 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() + "/"
 
-rocksdb_target_header = """# This file \100generated by `python buckifier/buckify_rocksdb.py`
-# --> DO NOT EDIT MANUALLY <--
-# This file is a Facebook-specific integration for buck builds, so can
-# only be validated by Facebook employees.
-#
-load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
-load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
-load(":defs.bzl", "test_binary")
+BUCK_BINS = "buck-out/gen/" + REPO_PATH
 
-REPO_PATH = package_name() + "/"
+TEST_RUNNER = REPO_PATH + "buckifier/rocks_test_runner.sh"
 
-ROCKSDB_COMPILER_FLAGS = [
+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",
-    # Added missing flags from output of build_detect_platform
-    "-Wnarrowing",
-    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
 ]
 
-ROCKSDB_EXTERNAL_DEPS = [
+rocksdb_external_deps = [
     ("bzip2", None, "bz2"),
     ("snappy", None, "snappy"),
     ("zlib", None, "z"),
@@ -32,64 +39,19 @@ ROCKSDB_EXTERNAL_DEPS = [
     ("lz4", None, "lz4"),
     ("zstd", None),
     ("tbb", None),
-    ("liburing", None, "uring"),
+    ("numa", None, "numa"),
     ("googletest", None, "gtest"),
 ]
 
-ROCKSDB_OS_DEPS = [
-    (
-        "linux",
-        ["third-party//numa:numa"],
-    ),
-]
-
-ROCKSDB_OS_PREPROCESSOR_FLAGS = [
-    (
-        "linux",
-        [
-            "-DOS_LINUX",
-            "-DROCKSDB_FALLOCATE_PRESENT",
-            "-DROCKSDB_MALLOC_USABLE_SIZE",
-            "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
-            "-DROCKSDB_RANGESYNC_PRESENT",
-            "-DROCKSDB_SCHED_GETCPU_PRESENT",
-            "-DROCKSDB_IOURING_PRESENT",
-            "-DHAVE_SSE42",
-            "-DNUMA",
-        ],
-    ),
-    (
-        "macos",
-        ["-DOS_MACOSX"],
-    ),
-]
-
-ROCKSDB_PREPROCESSOR_FLAGS = [
-    "-DROCKSDB_PLATFORM_POSIX",
-    "-DROCKSDB_LIB_IO_POSIX",
-    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
-
-    # Flags to enable libs we include
-    "-DSNAPPY",
-    "-DZLIB",
-    "-DBZIP2",
-    "-DLZ4",
-    "-DZSTD",
-    "-DZSTD_STATIC_LINKING_ONLY",
-    "-DGFLAGS=gflags",
-    "-DTBB",
-    "-DLIBURING",
-
-    # Added missing flags from output of build_detect_platform
-    "-DROCKSDB_BACKTRACE",
-
+rocksdb_preprocessor_flags = [
     # Directories with files for #include
     "-I" + REPO_PATH + "include/",
     "-I" + REPO_PATH,
 ]
 
-ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
+rocksdb_arch_preprocessor_flags = {
     "x86_64": [
+        "-DHAVE_SSE42",
         "-DHAVE_PCLMUL",
     ],
 }
@@ -100,36 +62,21 @@ 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.
-ROCKSDB_COMPILER_FLAGS += (["-DNDEBUG"] if is_opt_mode else [])
-
-sanitizer = read_config("fbcode", "sanitizer")
-
-# Do not enable jemalloc if sanitizer presents. RocksDB will further detect
-# whether the binary is linked with jemalloc at runtime.
-ROCKSDB_OS_PREPROCESSOR_FLAGS += ([(
-    "linux",
-    ["-DROCKSDB_JEMALLOC"],
-)] if sanitizer == "" else [])
-
-ROCKSDB_OS_DEPS += ([(
-    "linux",
-    ["third-party//jemalloc:headers"],
-)] if sanitizer == "" else [])
+if is_opt_mode:
+    rocksdb_compiler_flags.append("-DNDEBUG")
 """
 
 
 library_template = """
 cpp_library(
-    name = "{name}",
-    srcs = [{srcs}],
-    {headers_attr_prefix}headers = {headers},
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    os_deps = ROCKSDB_OS_DEPS,
-    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-    deps = [{deps}],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    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,
 )
 """
 
@@ -137,11 +84,11 @@ 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,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
     deps = [%s],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    external_deps = rocksdb_external_deps,
 )
 """
 
@@ -149,34 +96,50 @@ test_cfg_template = """    [
         "%s",
         "%s",
         "%s",
-        %s,
-        %s,
     ],
 """
 
 unittests_template = """
-# [test_name, test_src, test_type, extra_deps, extra_compiler_flags]
+# [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.
-[
-    test_binary(
-        extra_compiler_flags = extra_compiler_flags,
-        extra_deps = extra_deps,
-        parallelism = parallelism,
-        rocksdb_arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-        rocksdb_compiler_flags = ROCKSDB_COMPILER_FLAGS,
-        rocksdb_external_deps = ROCKSDB_EXTERNAL_DEPS,
-        rocksdb_os_deps = ROCKSDB_OS_DEPS,
-        rocksdb_os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
-        rocksdb_preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-        test_cc = test_cc,
-        test_name = test_name,
-    )
-    for test_name, test_cc, parallelism, extra_deps, extra_compiler_flags in ROCKS_TESTS
-    if not is_opt_mode
-]
+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

@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 """
 This module keeps commonly used components.
 """
@@ -6,16 +5,11 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import object
-except ImportError:
-    from __builtin__ import object
 import subprocess
-import sys
 import os
 import time
 
-class ColorString(object):
+class ColorString:
     """ Generate colorful strings on terminal """
     HEADER = '\033[95m'
     BLUE = '\033[94m'
@@ -26,13 +20,7 @@ class ColorString(object):
 
     @staticmethod
     def _make_color_str(text, color):
-        # In Python2, default encoding for unicode string is ASCII
-        if sys.version_info.major <= 2:
-            return "".join(
-                [color, text.encode('utf-8'), ColorString.ENDC])
-        # From Python3, default encoding for unicode string is UTF-8
-        return "".join(
-            [color, text, ColorString.ENDC])
+        return "".join([color, text.encode('utf-8'), ColorString.ENDC])
 
     @staticmethod
     def ok(text):

build_tools/RocksDBCommonHelper.php

@@ -0,0 +1,377 @@
+<?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/amalgamate.py

@@ -1,5 +1,4 @@
 #!/usr/bin/python
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 # amalgamate.py creates an amalgamation from a unity build.
 # It can be run with either Python 2 or 3.

build_tools/build_detect_platform

@@ -53,13 +53,11 @@ 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 [ -n "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
-      # we need this to build with MySQL. Don't use for other purposes.
-      source "$PWD/build_tools/fbcode_config4.8.1.sh"
-    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_5xx" ]; then
+    if [ -z "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
       source "$PWD/build_tools/fbcode_config.sh"
     else
-      source "$PWD/build_tools/fbcode_config_platform007.sh"
+      # we need this to build with MySQL. Don't use for other purposes.
+      source "$PWD/build_tools/fbcode_config4.8.1.sh"
     fi
 fi
 
@@ -68,9 +66,7 @@ rm -f "$OUTPUT"
 touch "$OUTPUT"
 
 if test -z "$CC"; then
-    if [ -x "$(command -v cc)" ]; then
-        CC=cc
-    elif [ -x "$(command -v clang)" ]; then
+    if [ -x "$(command -v clang)" ]; then
         CC=clang
     else
         CC=cc
@@ -78,9 +74,7 @@ if test -z "$CC"; then
 fi
 
 if test -z "$CXX"; then
-    if [ -x "$(command -v g++)" ]; then
-        CXX=g++
-    elif [ -x "$(command -v clang++)" ]; then
+    if [ -x "$(command -v clang++)" ]; then
         CXX=clang++
     else
         CXX=g++
@@ -146,26 +140,8 @@ case "$TARGET_OS" in
         COMMON_FLAGS="$COMMON_FLAGS -DOS_LINUX"
         if [ -z "$USE_CLANG" ]; then
             COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp"
-        else
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
         fi
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
-        # check for liburing
-        $CXX $CFLAGS -x c++ - -luring -o /dev/null 2>/dev/null  <<EOF
-          #include <liburing.h>
-          int main() {
-            struct io_uring ring;
-            io_uring_queue_init(1, &ring, 0);
-            return 0;
-          }
-EOF
-        if [ "$?" = 0 ]; then
-          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
-          COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
-        fi
-        if test -z "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-          USE_FOLLY_DISTRIBUTED_MUTEX=1
-        fi
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
@@ -216,8 +192,6 @@ EOF
         COMMON_FLAGS="$COMMON_FLAGS -DCYGWIN"
         if [ -z "$USE_CLANG" ]; then
             COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp"
-        else
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
         fi
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
         # PORT_FILES=port/linux/linux_specific.cc
@@ -250,7 +224,7 @@ else
           #include <linux/falloc.h>
           int main() {
       int fd = open("/dev/null", 0);
-      fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, 1024);
+      fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
           }
 EOF
         if [ "$?" = 0 ]; then
@@ -386,16 +360,6 @@ EOF
             # JEMALLOC can be enabled either using the flag (like here) or by
             # providing direct link to the jemalloc library
             WITH_JEMALLOC_FLAG=1
-            # check for JEMALLOC installed with HomeBrew
-            if [ "$PLATFORM" == "OS_MACOSX" ]; then
-                if hash brew 2>/dev/null && brew ls --versions jemalloc > /dev/null; then
-                    JEMALLOC_VER=$(brew ls --versions jemalloc | tail -n 1 | cut -f 2 -d ' ')
-                    JEMALLOC_INCLUDE="-I/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/include"
-                    JEMALLOC_LIB="/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/lib/libjemalloc_pic.a"
-                    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS $JEMALLOC_LIB"
-                    JAVA_STATIC_LDFLAGS="$JAVA_STATIC_LDFLAGS $JEMALLOC_LIB"
-                fi
-            fi
         fi
     fi
     if ! test $JEMALLOC && ! test $ROCKSDB_DISABLE_TCMALLOC; then
@@ -413,7 +377,6 @@ EOF
           #include <malloc.h>
           int main() {
             size_t res = malloc_usable_size(0);
-            (void)res;
             return 0;
           }
 EOF
@@ -428,7 +391,6 @@ EOF
           #include <pthread.h>
           int main() {
             int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-            (void)x;
             return 0;
           }
 EOF
@@ -440,7 +402,7 @@ EOF
     if ! test $ROCKSDB_DISABLE_BACKTRACE; then
         # Test whether backtrace is available
         $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <execinfo.h>
+          #include <execinfo.h>>
           int main() {
             void* frames[1];
             backtrace_symbols(frames, backtrace(frames, 1));
@@ -498,24 +460,12 @@ EOF
           #include <sched.h>
           int main() {
             int cpuid = sched_getcpu();
-            (void)cpuid;
           }
 EOF
         if [ "$?" = 0 ]; then
             COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SCHED_GETCPU_PRESENT"
         fi
     fi
-
-    if ! test $ROCKSDB_DISABLE_ALIGNED_NEW; then
-        # Test whether c++17 aligned-new is supported
-        $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
-            struct alignas(1024) t {int a;};
-            int main() {}
-EOF
-        if [ "$?" = 0 ]; then
-            PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS -faligned-new -DHAVE_ALIGNED_NEW"
-        fi
-    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.
@@ -534,11 +484,11 @@ fi
 
 if test "$USE_HDFS"; then
   if test -z "$JAVA_HOME"; then
-    echo "JAVA_HOME has to be set for HDFS usage." >&2
+    echo "JAVA_HOME has to be set for HDFS usage."
     exit 1
   fi
-  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS -I$HADOOP_HOME/include"
-  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64 -L$HADOOP_HOME/lib/native"
+  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64"
   HDFS_LDFLAGS="$HDFS_LDFLAGS -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib"
   HDFS_LDFLAGS="$HDFS_LDFLAGS -ldl -lverify -ljava -ljvm"
   COMMON_FLAGS="$COMMON_FLAGS $HDFS_CCFLAGS"
@@ -546,64 +496,42 @@ if test "$USE_HDFS"; then
   JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi
 
-if test "0$PORTABLE" -eq 0; then
+if test -z "$PORTABLE"; then
   if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
     # Tune for this POWER processor, treating '+' models as base models
     POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
     COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
   elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
     COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep -e^arm -e^aarch64`"; then
+  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^arm`"; then
     # TODO: Handle this with approprite options.
     COMMON_FLAGS="$COMMON_FLAGS"
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^aarch64`"; then
-    COMMON_FLAGS="$COMMON_FLAGS"
   elif [ "$TARGET_OS" == "IOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS"
-  elif [ "$TARGET_OS" == "AIX" ] || [ "$TARGET_OS" == "SunOS" ]; then
-    # TODO: Not sure why we don't use -march=native on these OSes
-    if test "$USE_SSE"; then
-      TRY_SSE_ETC="1"
-    fi
-  else
+  elif [ "$TARGET_OS" != "AIX" ] && [ "$TARGET_OS" != "SunOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS -march=native "
+  elif test "$USE_SSE"; then
+    COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
   fi
-else
-  # PORTABLE=1
-  if test "$USE_SSE"; then
-    TRY_SSE_ETC="1"
-  fi
+elif test "$USE_SSE"; then
+  COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
 fi
 
-if test "$TRY_SSE_ETC"; then
-  # The USE_SSE flag now means "attempt to compile with widely-available
-  # Intel architecture extensions utilized by specific optimizations in the
-  # source code." It's a qualifier on PORTABLE=1 that means "mostly portable."
-  # It doesn't even really check that your current CPU is compatible.
-  #
-  # SSE4.2 available since nehalem, ca. 2008-2010
-  TRY_SSE42="-msse4.2"
-  # PCLMUL available since westmere, ca. 2010-2011
-  TRY_PCLMUL="-mpclmul"
-  # AVX2 available since haswell, ca. 2013-2015
-  TRY_AVX2="-mavx2"
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o /dev/null 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
   #include <cstdint>
   #include <nmmintrin.h>
   int main() {
     volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
   }
 EOF
 if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_SSE42 -DHAVE_SSE42"
+  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_SSE42"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
+  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling"
+  exit 1
 fi
 
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
   #include <cstdint>
   #include <wmmintrin.h>
   int main() {
@@ -611,41 +539,13 @@ $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/n
     const auto b = _mm_set_epi64x(0, 0);
     const auto c = _mm_clmulepi64_si128(a, b, 0x00);
     auto d = _mm_cvtsi128_si64(c);
-    (void)d;
   }
 EOF
 if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_PCLMUL -DHAVE_PCLMUL"
+  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_PCLMUL"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main() {
-    const auto a = _mm256_setr_epi32(0, 1, 2, 3, 4, 7, 6, 5);
-    const auto b = _mm256_permutevar8x32_epi32(a, a);
-    (void)b;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_AVX2 -DHAVE_AVX2"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use AVX2 intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  int main() {
-    uint64_t a = 0xffffFFFFffffFFFF;
-    __uint128_t b = __uint128_t(a) * a;
-    a = static_cast<uint64_t>(b >> 64);
-    (void)a;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_UINT128_EXTENSION"
+  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
@@ -658,7 +558,6 @@ if [ "$PLATFORM" != IOS ]; then
   #endif
   int main() {
     static __thread int tls;
-    (void)tls;
   }
 EOF
   if [ "$?" = 0 ]; then
@@ -666,19 +565,6 @@ EOF
   fi
 fi
 
-if [ "$FBCODE_BUILD" != "true" -a "$PLATFORM" = OS_LINUX ]; then
-  $CXX $COMMON_FLAGS $PLATFORM_SHARED_CFLAGS -x c++ -c - -o test_dl.o 2>/dev/null <<EOF
-  void dummy_func() {}
-EOF
-  if [ "$?" = 0 ]; then
-    $CXX $COMMON_FLAGS $PLATFORM_SHARED_LDFLAGS test_dl.o -o /dev/null 2>/dev/null
-    if [ "$?" = 0 ]; then
-      EXEC_LDFLAGS+="-ldl"
-      rm -f test_dl.o
-    fi
-  fi
-fi
-
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"
 
@@ -723,6 +609,3 @@ if test -n "$WITH_JEMALLOC_FLAG"; then
   echo "WITH_JEMALLOC_FLAG=$WITH_JEMALLOC_FLAG" >> "$OUTPUT"
 fi
 echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
-if test -n "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-  echo "USE_FOLLY_DISTRIBUTED_MUTEX=$USE_FOLLY_DISTRIBUTED_MUTEX" >> "$OUTPUT"
-fi

build_tools/cont_integration.sh

@@ -0,0 +1,137 @@
+#!/usr/bin/env bash
+#
+# Copyright (c) 2016, Facebook. All rights reserved.
+#
+# Overall wrapper script for RocksDB continuous builds. The implementation is a
+# trivial pulling scheme. We loop infinitely, check if any new changes have been
+# committed, if yes then trigger a Sandcastle run, and finally go to sleep again
+# for a certain interval.
+#
+
+SRC_GIT_REPO=/data/git/rocksdb-public
+error=0
+
+function log {
+  DATE=`date +%Y-%m-%d:%H:%M:%S`
+  # shellcheck disable=SC2068
+  echo $DATE $@
+}
+
+function log_err {
+  # shellcheck disable=SC2145
+  log "ERROR: $@ Error code: $error."
+}
+
+function update_repo_status {
+  # Update the parent first.
+  pushd $SRC_GIT_REPO
+
+  # This is a fatal error. Something in the environment isn't right and we will
+  # terminate the execution.
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "Where is $SRC_GIT_REPO?"
+    exit $error
+  fi
+
+  HTTPS_PROXY=fwdproxy:8080 git fetch -f
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git fetch -f failed."
+    popd
+    return $error
+  fi
+
+  git update-ref refs/heads/master refs/remotes/origin/master
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git update-ref failed."
+    popd
+    return $error
+  fi
+
+  popd
+
+  # We're back in an instance-specific directory. Get the latest changes.
+  git pull --rebase
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git pull --rebase failed."
+    return $error
+  fi
+}
+
+#
+# Execution starts here.
+#
+
+# Path to the determinator from the root of the RocksDB repo.
+CONTRUN_DETERMINATOR=./build_tools/RocksDBCommonHelper.php
+
+# Value of the previous commit.
+PREV_COMMIT=
+
+log "Starting to monitor for new RocksDB changes ..."
+log "Running under `pwd` as `whoami`."
+
+# Paranoia. Make sure that we're using the right branch.
+git checkout master
+
+error=$?
+if [ ! $error -eq 0 ]; then
+  log_err "This is not good. Can't checkout master. Bye-bye!"
+  exit 1
+fi
+
+# We'll run forever and let the execution environment terminate us if we'll
+# exceed whatever timeout is set for the job.
+while true;
+do
+  # Get the latest changes committed.
+  update_repo_status
+
+  error=$?
+  if [  $error -eq 0 ]; then
+    LAST_COMMIT=`git log -1 | head -1 | grep commit | awk '{ print $2; }'`
+
+    log "Last commit is '$LAST_COMMIT', previous commit is '$PREV_COMMIT'."
+
+    if [ "$PREV_COMMIT" == "$LAST_COMMIT" ]; then
+      log "There were no changes since the last time I checked. Going to sleep."
+    else
+      if [ ! -z "$LAST_COMMIT" ]; then
+        log "New code has been committed or previous commit not known. " \
+            "Will trigger the tests."
+
+        PREV_COMMIT=$LAST_COMMIT
+        log "Updated previous commit to '$PREV_COMMIT'."
+
+        #
+        # This is where we'll trigger the Sandcastle run. The values for
+        # HTTPS_APP_VALUE and HTTPS_APP_VALUE will be set in the container we're
+        # running in.
+        #
+        POST_RECEIVE_HOOK=1 php $CONTRUN_DETERMINATOR
+
+        error=$?
+        if [ $error -eq 0 ]; then
+          log "Sandcastle run successfully triggered."
+        else
+          log_err "Failed to trigger Sandcastle run."
+        fi
+      else
+        log_err "Previous commit not updated. Don't know what the last one is."
+      fi
+    fi
+  else
+    log_err "Getting latest changes failed. Will skip running tests for now."
+  fi
+
+  # Always sleep, even if errors happens while trying to determine the latest
+  # commit. This will prevent us terminating in case of transient errors.
+  log "Will go to sleep for 5 minutes."
+  sleep 5m
+done

build_tools/dependencies.sh

@@ -1,19 +1,19 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/5.x/centos7-native/c447969
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1bd23f9917738974ad0ff305aa23eb5f93f18305/9.0.0/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/5.x/gcc-5-glibc-2.23/339d858
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.23/gcc-5-glibc-2.23/ca1d1c0
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/gcc-5-glibc-2.23/9bc6787
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/gcc-5-glibc-2.23/9bc6787
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/gcc-5-glibc-2.23/9bc6787
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/gcc-5-glibc-2.23/9bc6787
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/gcc-5-glibc-2.23/03859b5
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/gcc-5-glibc-2.23/9bc6787
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/gcc-5-glibc-2.23/0c8f76d
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/gcc-5-glibc-2.23/9bc6787
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/gcc-5-glibc-2.23/b443de1
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/gcc-5-glibc-2.23/9bc6787
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/2e3cb7d119b3cea5f1e738cc13a1ac69f49eb875/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/gcc-5-glibc-2.23/9bc6787
-LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.2.3/gcc-5-glibc-2.23/65372bd
+# shellcheck disable=SC2148
+GCC_BASE=/mnt/gvfs/third-party2/gcc/8219ec1bcedf8ad9da05e121e193364de2cc4f61/5.x/centos6-native/c447969
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/64d8d58e3d84f8bde7a029763d4f5baf39d0d5b9/stable/centos6-native/6aaf4de
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/ba9be983c81de7299b59fe71950c664a84dcb5f8/5.x/gcc-5-glibc-2.23/339d858
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/f20197cf3d4bd50339c9777aaa0b2ccadad9e2cb/2.23/gcc-5-glibc-2.23/ca1d1c0
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/6427ce8c7496e4ab06c2da81543b94c0de8be3d0/1.1.3/gcc-5-glibc-2.23/9bc6787
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/8f1e8b867d26efef93eac2fabbdb2e1d512665d7/1.2.8/gcc-5-glibc-2.23/9bc6787
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/70471c0571559fe0af7db6d7e8860b93a7eadfe1/1.0.6/gcc-5-glibc-2.23/9bc6787
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/453c89d6f0e68cdf1c151c769197fabedad9cac8/r131/gcc-5-glibc-2.23/9bc6787
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/00a40fa5f8bd2cd0622f2e868552793aef37ccf4/1.3.0/gcc-5-glibc-2.23/03859b5
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/47eef08f9acb77de982fbda6047c26d330739538/2.2.0/gcc-5-glibc-2.23/9bc6787
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/4414ddc78df8008b35cc4adac23590ad29148584/master/gcc-5-glibc-2.23/d506c82
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9d7ae2693d05d62f9a579cb21e6b717cf257a75d/2.0.11/gcc-5-glibc-2.23/9bc6787
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/2b2dd58e3a52ccf2c1d827def59e5f740de0ad15/1.2/gcc-5-glibc-2.23/b443de1
+TBB_BASE=/mnt/gvfs/third-party2/tbb/379addf7ab2468a2b4293b47456cfcd1c9cb318d/4.3/gcc-5-glibc-2.23/9bc6787
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/3f68f5fe65a85b7c2d3e66852268fbd1efdb3151/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/b9fab0aec99d9c36408e810b2677e91c12807afd/2.28/centos6-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/423431d61786b20bcc3bde8972901130cb29e6b3/3.11.0/gcc-5-glibc-2.23/9bc6787
+LUA_BASE=/mnt/gvfs/third-party2/lua/3b0bb3bd9a0f690a069c479fcc0f7424fc7456d2/5.2.3/gcc-5-glibc-2.23/65372bd

build_tools/dependencies_4.8.1.sh

@@ -1,5 +1,4 @@
 # shellcheck disable=SC2148
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 GCC_BASE=/mnt/gvfs/third-party2/gcc/cf7d14c625ce30bae1a4661c2319c5a283e4dd22/4.8.1/centos6-native/cc6c9dc
 CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/8598c375b0e94e1448182eb3df034704144a838d/stable/centos6-native/3f16ddd
 LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d6e0a7da6faba45f5e5b1638f9edd7afc2f34e7d/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc

build_tools/dependencies_platform007.sh

@@ -1,20 +0,0 @@
-# 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
-LIBURING_BASE=/mnt/gvfs/third-party2/liburing/79427253fd0d42677255aacfe6d13bfe63f752eb/20190828/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

@@ -1,3 +1,2 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 docker run -v $PWD:/rocks -w /rocks buildpack-deps make

build_tools/error_filter.py

@@ -64,12 +64,8 @@ class MatchErrorParser(ErrorParserBase):
 
 class CompilerErrorParser(MatchErrorParser):
     def __init__(self):
-        # format (compile error):
-        #   '<filename>:<line #>:<column #>: error: <error msg>'
-        # format (link error):
-        #   '<filename>:<line #>: error: <error msg>'
-        # The below regex catches both
-        super(CompilerErrorParser, self).__init__(r'\S+:\d+: error:')
+        # format: '<filename>:<line #>:<column #>: error: <error msg>'
+        super(CompilerErrorParser, self).__init__(r'\S+:\d+:\d+: error:')
 
 
 class ScanBuildErrorParser(MatchErrorParser):
@@ -132,17 +128,11 @@ _TEST_NAME_TO_PARSERS = {
     'lite': [CompilerErrorParser],
     'lite_test': [CompilerErrorParser, GTestErrorParser],
     'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_atomic_flush': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_txn': [CompilerErrorParser, DbCrashErrorParser],
     'write_stress': [CompilerErrorParser, WriteStressErrorParser],
     'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
     'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_atomic_flush': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_txn': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
     'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
     'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_atomic_flush': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_txn': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
     'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
     'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
     'format_compatible': [CompilerErrorParser, CompatErrorParser],

build_tools/fb_compile_mongo.sh

@@ -1,5 +1,5 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+
 # fail early
 set -e
 

build_tools/fbcode_config.sh

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ and clang compilers and also
@@ -44,15 +43,11 @@ if test -z $PIC_BUILD; then
   LZ4_INCLUDE=" -I $LZ4_BASE/include/"
   LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
   CFLAGS+=" -DLZ4"
-fi
 
-ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-if test -z $PIC_BUILD; then
+  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
   ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-else
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
+  CFLAGS+=" -DZSTD"
 fi
-CFLAGS+=" -DZSTD -DZSTD_STATIC_LINKING_ONLY"
 
 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
@@ -86,10 +81,9 @@ else
 fi
 CFLAGS+=" -DTBB"
 
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -160,6 +154,4 @@ else
   LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
 fi
 
-USE_FOLLY_DISTRIBUTED_MUTEX=1
-
 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

build_tools/fbcode_config4.8.1.sh

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ compiler and also
@@ -53,10 +52,9 @@ LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
 TBB_INCLUDE=" -isystem $TBB_BASE/include/"
 TBB_LIBS="$TBB_BASE/lib/libtbb.a"
 
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"

build_tools/fbcode_config_platform007.sh

@@ -1,170 +0,0 @@
-#!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-#
-# Set environment variables so that we can compile rocksdb using
-# fbcode settings.  It uses the latest g++ and clang compilers and also
-# uses jemalloc
-# Environment variables that change the behavior of this script:
-# PIC_BUILD -- if true, it will only take pic versions of libraries from fbcode. libraries that don't have pic variant will not be included
-
-
-BASEDIR=`dirname $BASH_SOURCE`
-source "$BASEDIR/dependencies_platform007.sh"
-
-CFLAGS=""
-
-# libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/7.3.0"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
-
-# glibc
-GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIBC_BASE/lib"
-
-# snappy
-SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-if test -z $PIC_BUILD; then
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
-else
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
-fi
-CFLAGS+=" -DSNAPPY"
-
-if test -z $PIC_BUILD; then
-  # location of zlib headers and libraries
-  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-  ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
-  CFLAGS+=" -DZLIB"
-
-  # location of bzip headers and libraries
-  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
-  CFLAGS+=" -DBZIP2"
-
-  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
-  CFLAGS+=" -DLZ4"
-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
-  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
-else
-  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags_pic.a"
-fi
-CFLAGS+=" -DGFLAGS=gflags"
-
-# location of jemalloc
-JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
-JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc.a"
-
-if test -z $PIC_BUILD; then
-  # location of numa
-  NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-  NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
-  CFLAGS+=" -DNUMA"
-
-  # location of libunwind
-  LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
-fi
-
-# location of TBB
-TBB_INCLUDE=" -isystem $TBB_BASE/include/"
-if test -z $PIC_BUILD; then
-  TBB_LIBS="$TBB_BASE/lib/libtbb.a"
-else
-  TBB_LIBS="$TBB_BASE/lib/libtbb_pic.a"
-fi
-CFLAGS+=" -DTBB"
-
-# location of LIBURING
-LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
-if test -z $PIC_BUILD; then
-  LIBURING_LIBS="$LIBURING_BASE/lib/liburing.a"
-else
-  LIBURING_LIBS="$LIBURING_BASE/lib/liburing_pic.a"
-fi
-CFLAGS+=" -DLIBURING"
-
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE"
-
-STDLIBS="-L $GCC_BASE/lib64"
-
-CLANG_BIN="$CLANG_BASE/bin"
-CLANG_LIB="$CLANG_BASE/lib"
-CLANG_SRC="$CLANG_BASE/../../src"
-
-CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_SRC/llvm/tools/clang/tools/scan-build/bin/scan-build"
-
-if [ -z "$USE_CLANG" ]; then
-  # gcc
-  CC="$GCC_BASE/bin/gcc"
-  CXX="$GCC_BASE/bin/g++"
-
-  CFLAGS+=" -B$BINUTILS/gold"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  JEMALLOC=1
-else
-  # clang
-  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
-  CC="$CLANG_BIN/clang"
-  CXX="$CLANG_BIN/clang++"
-
-  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
-
-  CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
-  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"
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
-  CFLAGS+=" -Wno-expansion-to-defined "
-  CXXFLAGS="-nostdinc++"
-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 -DROCKSDB_IOURING_PRESENT"
-CXXFLAGS+=" $CFLAGS"
-
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS"
-EXEC_LDFLAGS+=" -B$BINUTILS/gold"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
-EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform007/lib"
-# required by libtbb
-EXEC_LDFLAGS+=" -ldl"
-
-PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
-
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS $LIBURING_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-# lua not supported because it's on track for deprecation, I think
-LUA_PATH=
-LUA_LIB=
-
-USE_FOLLY_DISTRIBUTED_MUTEX=1
-
-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

build_tools/format-diff.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # 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 ]
@@ -13,14 +12,9 @@ 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 "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
-  echo "You can download clang-format by running:"
+  echo "You can download clang-format by running: "
   echo "    brew install clang-format"
-  echo "  Or"
-  echo "    apt install clang-format"
-  echo "  This might work too:"
-  echo "    yum install git-clang-format"
   echo "Then, move both files (i.e. ${CLANG_FORMAT_DIFF} and clang-format) to some directory within PATH=${PATH}"
-  echo "and make sure ${CLANG_FORMAT_DIFF} is executable."
   exit 128
 fi
 
@@ -59,25 +53,15 @@ fi
 set -e
 
 uncommitted_code=`git diff HEAD`
+LAST_MASTER=`git merge-base master HEAD`
 
 # If there's no uncommitted changes, we assume user are doing post-commit
-# format check, in which case we'll try to check the modified lines vs. the
-# facebook/rocksdb.git master branch. Otherwise, we'll check format of the
-# uncommitted code only.
+# format check, in which case we'll check the modified lines since last commit
+# from master. Otherwise, we'll check format of the uncommitted code only.
 if [ -z "$uncommitted_code" ]
 then
-  # Attempt to get name of facebook/rocksdb.git remote.
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE="$(git remote -v | grep 'facebook/rocksdb.git' | head -n 1 | cut -f 1)"
-  # Fall back on 'origin' if that fails
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE=origin
-  # Use master branch from that remote
-  [ "$FORMAT_UPSTREAM" ] || FORMAT_UPSTREAM="$FORMAT_REMOTE/master"
-  # Get the common ancestor with that remote branch. Everything after that
-  # common ancestor would be considered the contents of a pull request, so
-  # should be relevant for formatting fixes.
-  FORMAT_UPSTREAM_MERGE_BASE="$(git merge-base "$FORMAT_UPSTREAM" HEAD)"
-  # Get the differences
-  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1)
+  # Check the format of last commit
+  diffs=$(git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -p 1)
 else
   # Check the format of uncommitted lines,
   diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
@@ -91,12 +75,12 @@ fi
 
 # Highlight the insertion/deletion from the clang-format-diff.py's output
 COLOR_END="\033[0m"
-COLOR_RED="\033[0;31m"
-COLOR_GREEN="\033[0;32m"
+COLOR_RED="\033[0;31m" 
+COLOR_GREEN="\033[0;32m" 
 
 echo -e "Detect lines that doesn't follow the format rules:\r"
 # Add the color to the diff. lines added will be green; lines removed will be red.
-echo "$diffs" |
+echo "$diffs" | 
   sed -e "s/\(^-.*$\)/`echo -e \"$COLOR_RED\1$COLOR_END\"`/" |
   sed -e "s/\(^+.*$\)/`echo -e \"$COLOR_GREEN\1$COLOR_END\"`/"
 
@@ -119,7 +103,7 @@ fi
 # Do in-place format adjustment.
 if [ -z "$uncommitted_code" ]
 then
-  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -i -p 1
 else
   git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -i -p 1
 fi

build_tools/gnu_parallel

@@ -5082,8 +5082,8 @@ sub openoutputfiles {
 	# Set reading FD if using --group (--ungroup does not need)
 	for my $fdno (1,2) {
 	    # Re-open the file for reading
-	    # so fdw can be closed separately
-	    # and fdr can be seeked separately (for --line-buffer)
+	    # so fdw can be closed seperately
+	    # and fdr can be seeked seperately (for --line-buffer)
 	    open(my $fdr,"<", $self->fh($fdno,'name')) ||
 		::die_bug("fdr: Cannot open ".$self->fh($fdno,'name'));
 	    $self->set_fh($fdno,'r',$fdr);

build_tools/make_package.sh

@@ -1,6 +1,5 @@
 # shellcheck disable=SC1113
 #/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 set -e
 

build_tools/precommit_checker.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python2.7
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#!/usr/local/fbcode/gcc-4.9-glibc-2.20-fb/bin/python2.7
 
 from __future__ import absolute_import
 from __future__ import division

build_tools/regression_build_test.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 set -e
 

build_tools/rocksdb-lego-determinator

@@ -63,21 +63,6 @@ CLEANUP_ENV="
     'user':'root'
 }"
 
-UPLOAD_DB_DIR="
-{
-    'name':'Upload database directory',
-    'shell':'tar -cvzf rocksdb_db.tar.gz /dev/shm/rocksdb/',
-    'user':'root',
-    'cleanup':true,
-    'provide_artifacts': [
-    {
-      'name':'rocksdb_db_dir',
-      'paths': ['rocksdb_db.tar.gz'],
-      'bundle': false,
-    },
-    ],
-}"
-
 # We will eventually set the RATIO to 1, but we want do this
 # in steps. RATIO=$(nproc) will make it work as J=1
 if [ -z $RATIO ]; then
@@ -100,12 +85,9 @@ NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-# in gcc-5 there are known problems with TSAN like https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71090.
-# using platform007 gives us gcc-8 or higher which has that bug fixed.
-TSAN="ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007=1 COMPILE_WITH_TSAN=1"
+LITE="OPT=\"-DROCKSDB_LITE -g\""
+TSAN="COMPILE_WITH_TSAN=1"
 UBSAN="COMPILE_WITH_UBSAN=1"
-TSAN_CRASH='CRASH_TEST_EXT_ARGS="--compression_type=zstd --log2_keys_per_lock=22"'
-NON_TSAN_CRASH="CRASH_TEST_EXT_ARGS=--compression_type=zstd"
 DISABLE_JEMALLOC="DISABLE_JEMALLOC=1"
 HTTP_PROXY="https_proxy=http://fwdproxy.29.prn1:8080 http_proxy=http://fwdproxy.29.prn1:8080 ftp_proxy=http://fwdproxy.29.prn1:8080"
 SETUP_JAVA_ENV="export $HTTP_PROXY; export JAVA_HOME=/usr/local/jdk-8u60-64/; export PATH=\$JAVA_HOME/bin:\$PATH"
@@ -124,6 +106,13 @@ else
   TASK_CREATION_TOOL="false"
 fi
 
+ARTIFACTS=" 'artifacts': [
+    {
+        'name':'database',
+        'paths':[ '/dev/shm/rocksdb' ],
+    }
+]"
+
 #
 # A mechanism to disable tests temporarily
 #
@@ -148,7 +137,6 @@ UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -169,7 +157,6 @@ UNIT_TEST_NON_SHM_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -192,7 +179,6 @@ RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -213,7 +199,6 @@ UNIT_TEST_COMMANDS_481="[
     {
         'name':'Rocksdb Unit Test on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -234,7 +219,6 @@ RELEASE_BUILD_COMMANDS_481="[
     {
         'name':'Rocksdb Release on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -255,7 +239,6 @@ CLANG_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -276,7 +259,6 @@ CLANG_RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb CLANG Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -297,7 +279,6 @@ CLANG_ANALYZE_COMMANDS="[
     {
         'name':'Rocksdb analyze',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -318,7 +299,6 @@ CODE_COV_COMMANDS="[
     {
         'name':'Rocksdb Unit Test Code Coverage',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -339,7 +319,6 @@ UNITY_COMMANDS="[
     {
         'name':'Rocksdb Unity',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -360,12 +339,11 @@ LITE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Lite build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Build RocksDB debug version',
-                'shell':'make J=1 LITE=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
+                'shell':'$LITE make J=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -380,7 +358,6 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
     {
         'name':'Rocksdb Lite Binary Size',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -396,86 +373,26 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
 #
 STRESS_CRASH_TEST_COMMANDS="[
     {
-        'name':'Rocksdb Stress and Crash Test',
+        'name':'Rocksdb Stress/Crash Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
             {
                 'name':'Build and run RocksDB debug crash tests',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             }
         ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test with atomic flush
-#
-STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with atomic flush',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests with atomic flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_atomic_flush || $CONTRUN_NAME=crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test with txn
-#
-STRESS_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with txn',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests with txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_txn || $CONTRUN_NAME=crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
+        $ARTIFACTS,
         $REPORT
     }
 ]"
@@ -487,7 +404,6 @@ WRITE_STRESS_COMMANDS="[
     {
         'name':'Rocksdb Write Stress Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -510,7 +426,6 @@ ASAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under ASAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -531,14 +446,13 @@ ASAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under ASAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Build and run RocksDB debug asan_crash_test',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -547,54 +461,6 @@ ASAN_CRASH_TEST_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB crash testing with atomic flush under address sanitizer
-#
-ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with atomic flush under ASAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test_with_atomic_flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_atomic_flush || $CONTRUN_NAME=asan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with txn under address sanitizer
-#
-ASAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with txn under ASAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test_with_txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_txn || $CONTRUN_NAME=asan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB test under undefined behavior sanitizer
 #
@@ -602,12 +468,11 @@ UBSAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under UBSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Test RocksDB debug under UBSAN',
-                'shell':'set -o pipefail && $SHM $UBSAN $CLANG $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $UBSAN $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             }
@@ -623,14 +488,13 @@ UBSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under UBSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Build and run RocksDB debug ubsan_crash_test',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -639,54 +503,6 @@ UBSAN_CRASH_TEST_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB crash testing with atomic flush under undefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with atomic flush under UBSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test_with_atomic_flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with txn under undefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with txn under UBSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test_with_txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_txn || $CONTRUN_NAME=ubsan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB unit test under valgrind
 #
@@ -694,7 +510,6 @@ VALGRIND_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under valgrind',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -717,7 +532,6 @@ TSAN_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under TSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -740,14 +554,13 @@ TSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb Crash Test under TSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Compile and run',
                 'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $DEBUG $TSAN CRASH_TEST_KILL_ODD=1887 CRASH_TEST_EXT_ARGS=--log2_keys_per_lock=22  make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -756,54 +569,6 @@ TSAN_CRASH_TEST_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB crash test with atomic flush under TSAN
-#
-TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test with atomic flush under TSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_atomic_flush || $CONTRUN_NAME=tsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash test with txn under TSAN
-#
-TSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test with txn under TSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_txn || $CONTRUN_NAME=tsan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB format compatible
 #
@@ -821,7 +586,6 @@ FORMAT_COMPATIBLE_COMMANDS="[
     {
         'name':'Rocksdb Format Compatible tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -844,7 +608,7 @@ run_no_compression()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
   make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzstd | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
+  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
   mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
   cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
   mv .tmp.Makefile Makefile
@@ -855,7 +619,6 @@ NO_COMPRESSION_COMMANDS="[
     {
         'name':'Rocksdb No Compression tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -898,12 +661,12 @@ run_regression()
 
   # === lite build ===
   make clean
-  make LITE=1 -j$(nproc) static_lib
+  OPT=-DROCKSDB_LITE make -j$(nproc) static_lib
   send_size_to_ods static_lib_lite $(stat --printf="%s" librocksdb.a)
   strip librocksdb.a
   send_size_to_ods static_lib_lite_stripped $(stat --printf="%s" librocksdb.a)
 
-  make LITE=1 -j$(nproc) shared_lib
+  OPT=-DROCKSDB_LITE make -j$(nproc) shared_lib
   send_size_to_ods shared_lib_lite $(stat --printf="%s" `readlink -f librocksdb.so`)
   strip `readlink -f librocksdb.so`
   send_size_to_ods shared_lib_lite_stripped $(stat --printf="%s" `readlink -f librocksdb.so`)
@@ -933,7 +696,6 @@ JAVA_BUILD_TEST_COMMANDS="[
     {
         'name':'Rocksdb Java Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -988,12 +750,6 @@ case $1 in
   stress_crash)
     echo $STRESS_CRASH_TEST_COMMANDS
     ;;
-  stress_crash_with_atomic_flush)
-    echo $STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  stress_crash_with_txn)
-    echo $STRESS_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   write_stress)
     echo $WRITE_STRESS_COMMANDS
     ;;
@@ -1003,24 +759,12 @@ case $1 in
   asan_crash)
     echo $ASAN_CRASH_TEST_COMMANDS
     ;;
-  asan_crash_with_atomic_flush)
-    echo $ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  asan_crash_with_txn)
-    echo $ASAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   ubsan)
     echo $UBSAN_TEST_COMMANDS
     ;;
   ubsan_crash)
     echo $UBSAN_CRASH_TEST_COMMANDS
     ;;
-  ubsan_crash_with_atomic_flush)
-    echo $UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  ubsan_crash_with_txn)
-    echo $UBSAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   valgrind)
     echo $VALGRIND_TEST_COMMANDS
     ;;
@@ -1030,12 +774,6 @@ case $1 in
   tsan_crash)
     echo $TSAN_CRASH_TEST_COMMANDS
     ;;
-  tsan_crash_with_atomic_flush)
-    echo $TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  tsan_crash_with_txn)
-    echo $TSAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   format_compatible)
     echo $FORMAT_COMPATIBLE_COMMANDS
     ;;

build_tools/run_ci_db_test.ps1

@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # This script enables you running RocksDB tests by running
 # All the tests concurrently and utilizing all the cores
 Param(

build_tools/setup_centos7.sh

@@ -1,5 +1,4 @@
 #!/bin/bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 set -e
 
 ROCKSDB_VERSION="5.10.3"

build_tools/update_dependencies.sh

@@ -1,17 +1,10 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Update dependencies.sh file with the latest avaliable versions
 
 BASEDIR=$(dirname $0)
 OUTPUT=""
 
-function log_header()
-{
-  echo "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved." >> "$OUTPUT"
-}
-
-
 function log_variable()
 {
   echo "$1=${!1}" >> "$OUTPUT"
@@ -60,47 +53,6 @@ function get_lib_base()
   log_variable $__res_var
 }
 
-###########################################################
-#                platform007 dependencies                 #
-###########################################################
-
-OUTPUT="$BASEDIR/dependencies_platform007.sh"
-
-rm -f "$OUTPUT"
-touch "$OUTPUT"
-
-echo "Writing dependencies to $OUTPUT"
-
-# Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/7.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
-
-log_header
-log_variable GCC_BASE
-log_variable CLANG_BASE
-
-# Libraries locations
-get_lib_base libgcc     7.x     platform007
-get_lib_base glibc      2.26    platform007
-get_lib_base snappy     LATEST  platform007
-get_lib_base zlib       LATEST  platform007
-get_lib_base bzip2      LATEST  platform007
-get_lib_base lz4        LATEST  platform007
-get_lib_base zstd       LATEST  platform007
-get_lib_base gflags     LATEST  platform007
-get_lib_base jemalloc   LATEST  platform007
-get_lib_base numa       LATEST  platform007
-get_lib_base libunwind  LATEST  platform007
-get_lib_base tbb        LATEST  platform007
-get_lib_base liburing   LATEST  platform007
-
-get_lib_base kernel-headers fb platform007
-get_lib_base binutils   LATEST centos7-native
-get_lib_base valgrind   LATEST platform007
-get_lib_base lua        5.3.4  platform007
-
-git diff $OUTPUT
-
 ###########################################################
 #                   5.x dependencies                      #
 ###########################################################
@@ -113,10 +65,9 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"
 
 # Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos6-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
@@ -135,7 +86,7 @@ get_lib_base libunwind  LATEST  gcc-5-glibc-2.23
 get_lib_base tbb        LATEST  gcc-5-glibc-2.23
 
 get_lib_base kernel-headers 4.0.9-36_fbk5_2933_gd092e3f gcc-5-glibc-2.23
-get_lib_base binutils   LATEST centos7-native
+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
 
@@ -156,7 +107,6 @@ echo "Writing 4.8.1 dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 

build_tools/version.sh

@@ -1,5 +1,4 @@
-#!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#/usr/bin/env bash
 if [ "$#" = "0" ]; then
   echo "Usage: $0 major|minor|patch|full"
   exit 1

cache/cache_bench.cc

@@ -3,6 +3,9 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
 #ifndef GFLAGS
 #include <cstdio>
 int main() {
@@ -11,9 +14,9 @@ int main() {
 }
 #else
 
-#include <stdio.h>
+#include <inttypes.h>
 #include <sys/types.h>
-#include <cinttypes>
+#include <stdio.h>
 
 #include "port/port.h"
 #include "rocksdb/cache.h"
@@ -49,7 +52,7 @@ namespace rocksdb {
 
 class CacheBench;
 namespace {
-void deleter(const Slice& /*key*/, void* value) {
+void deleter(const Slice& key, void* value) {
     delete reinterpret_cast<char *>(value);
 }
 

cache/cache_test.cc

@@ -16,9 +16,9 @@
 #include <vector>
 #include "cache/clock_cache.h"
 #include "cache/lru_cache.h"
-#include "test_util/testharness.h"
 #include "util/coding.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
 
 namespace rocksdb {
 
@@ -64,8 +64,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
 
   std::vector<int> deleted_keys_;
   std::vector<int> deleted_values_;
-  std::shared_ptr<Cache> cache_;
-  std::shared_ptr<Cache> cache2_;
+  shared_ptr<Cache> cache_;
+  shared_ptr<Cache> cache2_;
 
   CacheTest()
       : cache_(NewCache(kCacheSize, kNumShardBits, false)),
@@ -73,7 +73,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
     current_ = this;
   }
 
-  ~CacheTest() override {}
+  ~CacheTest() {
+  }
 
   std::shared_ptr<Cache> NewCache(size_t capacity) {
     auto type = GetParam();
@@ -86,27 +87,19 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return nullptr;
   }
 
-  std::shared_ptr<Cache> NewCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      CacheMetadataChargePolicy charge_policy = kDontChargeCacheMetadata) {
+  std::shared_ptr<Cache> NewCache(size_t capacity, int num_shard_bits,
+                                  bool strict_capacity_limit) {
     auto type = GetParam();
     if (type == kLRU) {
-      LRUCacheOptions co;
-      co.capacity = capacity;
-      co.num_shard_bits = num_shard_bits;
-      co.strict_capacity_limit = strict_capacity_limit;
-      co.high_pri_pool_ratio = 0;
-      co.metadata_charge_policy = charge_policy;
-      return NewLRUCache(co);
+      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit);
     }
     if (type == kClock) {
-      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit,
-                           charge_policy);
+      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit);
     }
     return nullptr;
   }
 
-  int Lookup(std::shared_ptr<Cache> cache, int key) {
+  int Lookup(shared_ptr<Cache> cache, int key) {
     Cache::Handle* handle = cache->Lookup(EncodeKey(key));
     const int r = (handle == nullptr) ? -1 : DecodeValue(cache->Value(handle));
     if (handle != nullptr) {
@@ -115,16 +108,16 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return r;
   }
 
-  void Insert(std::shared_ptr<Cache> cache, int key, int value,
-              int charge = 1) {
+  void Insert(shared_ptr<Cache> cache, int key, int value, int charge = 1) {
     cache->Insert(EncodeKey(key), EncodeValue(value), charge,
                   &CacheTest::Deleter);
   }
 
-  void Erase(std::shared_ptr<Cache> cache, int key) {
+  void Erase(shared_ptr<Cache> cache, int key) {
     cache->Erase(EncodeKey(key));
   }
 
+
   int Lookup(int key) {
     return Lookup(cache_, key);
   }
@@ -151,15 +144,10 @@ class CacheTest : public testing::TestWithParam<std::string> {
 };
 CacheTest* CacheTest::current_;
 
-class LRUCacheTest : public CacheTest {};
-
 TEST_P(CacheTest, UsageTest) {
-  // cache is std::shared_ptr and will be automatically cleaned up.
+  // cache is shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 0, false, kFullChargeCacheMetadata);
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
+  auto cache = NewCache(kCapacity, 8, false);
 
   size_t usage = 0;
   char value[10] = "abcdef";
@@ -168,45 +156,31 @@ TEST_P(CacheTest, UsageTest) {
     std::string key(i, 'a');
     auto kv_size = key.size() + 5;
     cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter);
     usage += kv_size;
     ASSERT_EQ(usage, cache->GetUsage());
-    ASSERT_LT(usage, precise_cache->GetUsage());
   }
 
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
-
   // make sure the cache will be overloaded
   for (uint64_t i = 1; i < kCapacity; ++i) {
     auto key = ToString(i);
     cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                   dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
   }
 
   // the usage should be close to the capacity
   ASSERT_GT(kCapacity, cache->GetUsage());
-  ASSERT_GT(kCapacity, precise_cache->GetUsage());
   ASSERT_LT(kCapacity * 0.95, cache->GetUsage());
-  ASSERT_LT(kCapacity * 0.95, precise_cache->GetUsage());
 }
 
 TEST_P(CacheTest, PinnedUsageTest) {
-  // cache is std::shared_ptr and will be automatically cleaned up.
-  const uint64_t kCapacity = 200000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 8, false, kFullChargeCacheMetadata);
+  // cache is shared_ptr and will be automatically cleaned up.
+  const uint64_t kCapacity = 100000;
+  auto cache = NewCache(kCapacity, 8, false);
 
   size_t pinned_usage = 0;
   char value[10] = "abcdef";
 
   std::forward_list<Cache::Handle*> unreleased_handles;
-  std::forward_list<Cache::Handle*> unreleased_handles_in_precise_cache;
 
   // Add entries. Unpin some of them after insertion. Then, pin some of them
   // again. Check GetPinnedUsage().
@@ -214,72 +188,40 @@ TEST_P(CacheTest, PinnedUsageTest) {
     std::string key(i, 'a');
     auto kv_size = key.size() + 5;
     Cache::Handle* handle;
-    Cache::Handle* handle_in_precise_cache;
     cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter,
                   &handle);
-    assert(handle);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter, &handle_in_precise_cache);
-    assert(handle_in_precise_cache);
     pinned_usage += kv_size;
     ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-    ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     if (i % 2 == 0) {
       cache->Release(handle);
-      precise_cache->Release(handle_in_precise_cache);
       pinned_usage -= kv_size;
       ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     } else {
       unreleased_handles.push_front(handle);
-      unreleased_handles_in_precise_cache.push_front(handle_in_precise_cache);
     }
     if (i % 3 == 0) {
       unreleased_handles.push_front(cache->Lookup(key));
-      auto x = precise_cache->Lookup(key);
-      assert(x);
-      unreleased_handles_in_precise_cache.push_front(x);
       // If i % 2 == 0, then the entry was unpinned before Lookup, so pinned
       // usage increased
       if (i % 2 == 0) {
         pinned_usage += kv_size;
       }
       ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     }
   }
-  auto precise_cache_pinned_usage = precise_cache->GetPinnedUsage();
-  ASSERT_LT(pinned_usage, precise_cache_pinned_usage);
 
   // check that overloading the cache does not change the pinned usage
   for (uint64_t i = 1; i < 2 * kCapacity; ++i) {
     auto key = ToString(i);
     cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                   dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
   }
   ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
-
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
 
   // release handles for pinned entries to prevent memory leaks
   for (auto handle : unreleased_handles) {
     cache->Release(handle);
   }
-  for (auto handle : unreleased_handles_in_precise_cache) {
-    precise_cache->Release(handle);
-  }
-  ASSERT_EQ(0, cache->GetPinnedUsage());
-  ASSERT_EQ(0, precise_cache->GetPinnedUsage());
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
 }
 
 TEST_P(CacheTest, HitAndMiss) {
@@ -365,7 +307,7 @@ TEST_P(CacheTest, EvictionPolicy) {
   Insert(200, 201);
 
   // Frequently used entry must be kept around
-  for (int i = 0; i < kCacheSize * 2; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
     Insert(1000+i, 2000+i);
     ASSERT_EQ(101, Lookup(100));
   }
@@ -418,7 +360,7 @@ TEST_P(CacheTest, EvictionPolicyRef) {
   Insert(303, 104);
 
   // Insert entries much more than Cache capacity
-  for (int i = 0; i < kCacheSize * 2; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
     Insert(1000 + i, 2000 + i);
   }
 
@@ -609,10 +551,10 @@ TEST_P(CacheTest, SetCapacity) {
   }
 }
 
-TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
+TEST_P(CacheTest, SetStrictCapacityLimit) {
   // test1: set the flag to false. Insert more keys than capacity. See if they
   // all go through.
-  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
+  std::shared_ptr<Cache> cache = NewLRUCache(5, 0, false);
   std::vector<Cache::Handle*> handles(10);
   Status s;
   for (size_t i = 0; i < 10; i++) {
@@ -621,7 +563,6 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
     ASSERT_OK(s);
     ASSERT_NE(nullptr, handles[i]);
   }
-  ASSERT_EQ(10, cache->GetUsage());
 
   // test2: set the flag to true. Insert and check if it fails.
   std::string extra_key = "extra";
@@ -631,14 +572,13 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
   s = cache->Insert(extra_key, extra_value, 1, &deleter, &handle);
   ASSERT_TRUE(s.IsIncomplete());
   ASSERT_EQ(nullptr, handle);
-  ASSERT_EQ(10, cache->GetUsage());
 
   for (size_t i = 0; i < 10; i++) {
     cache->Release(handles[i]);
   }
 
   // test3: init with flag being true.
-  std::shared_ptr<Cache> cache2 = NewCache(5, 0, true);
+  std::shared_ptr<Cache> cache2 = NewLRUCache(5, 0, true);
   for (size_t i = 0; i < 5; i++) {
     std::string key = ToString(i + 1);
     s = cache2->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
@@ -652,7 +592,7 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
   s = cache2->Insert(extra_key, extra_value, 1, &deleter);
   // AS if the key have been inserted into cache but get evicted immediately.
   ASSERT_OK(s);
-  ASSERT_EQ(5, cache2->GetUsage());
+  ASSERT_EQ(5, cache->GetUsage());
   ASSERT_EQ(nullptr, cache2->Lookup(extra_key));
 
   for (size_t i = 0; i < 5; i++) {
@@ -747,23 +687,13 @@ TEST_P(CacheTest, DefaultShardBits) {
   ASSERT_EQ(6, sc->GetNumShardBits());
 }
 
-TEST_P(CacheTest, GetCharge) {
-  Insert(1, 2);
-  Cache::Handle* h1 = cache_->Lookup(EncodeKey(1));
-  ASSERT_EQ(2, DecodeValue(cache_->Value(h1)));
-  ASSERT_EQ(1, cache_->GetCharge(h1));
-  cache_->Release(h1);
-}
-
 #ifdef SUPPORT_CLOCK_CACHE
-std::shared_ptr<Cache> (*new_clock_cache_func)(
-    size_t, int, bool, CacheMetadataChargePolicy) = NewClockCache;
+shared_ptr<Cache> (*new_clock_cache_func)(size_t, int, bool) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                         testing::Values(kLRU, kClock));
 #else
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest, testing::Values(kLRU));
 #endif  // SUPPORT_CLOCK_CACHE
-INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest, testing::Values(kLRU));
 
 }  // namespace rocksdb
 

cache/clock_cache.cc

@@ -13,9 +13,8 @@
 
 namespace rocksdb {
 
-std::shared_ptr<Cache> NewClockCache(
-    size_t /*capacity*/, int /*num_shard_bits*/, bool /*strict_capacity_limit*/,
-    CacheMetadataChargePolicy /*metadata_charge_policy*/) {
+std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
+                                     bool strict_capacity_limit) {
   // Clock cache not supported.
   return nullptr;
 }
@@ -36,7 +35,6 @@ std::shared_ptr<Cache> NewClockCache(
 #include "tbb/concurrent_hash_map.h"
 
 #include "cache/sharded_cache.h"
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 #include "util/mutexlock.h"
@@ -204,27 +202,6 @@ struct CacheHandle {
     deleter = a.deleter;
     return *this;
   }
-
-  inline static size_t CalcTotalCharge(
-      Slice key, size_t charge,
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-      meta_charge += sizeof(CacheHandle);
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge +=
-          malloc_usable_size(static_cast<void*>(const_cast<char*>(key.data())));
-#else
-      meta_charge += key.size();
-#endif
-    }
-    return charge + meta_charge;
-  }
-
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    return CalcTotalCharge(key, charge, metadata_charge_policy);
-  }
 };
 
 // Key of hash map. We store hash value with the key for convenience.
@@ -257,35 +234,38 @@ struct CleanupContext {
 };
 
 // A cache shard which maintains its own CLOCK cache.
-class ClockCacheShard final : public CacheShard {
+class ClockCacheShard : public CacheShard {
  public:
   // Hash map type.
   typedef tbb::concurrent_hash_map<CacheKey, CacheHandle*, CacheKey> HashTable;
 
   ClockCacheShard();
-  ~ClockCacheShard() override;
+  ~ClockCacheShard();
 
   // Interfaces
-  void SetCapacity(size_t capacity) override;
-  void SetStrictCapacityLimit(bool strict_capacity_limit) override;
-  Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value),
-                Cache::Handle** handle, Cache::Priority priority) override;
-  Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
+  virtual void SetCapacity(size_t capacity) override;
+  virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override;
+  virtual Status Insert(const Slice& key, uint32_t hash, void* value,
+                        size_t charge,
+                        void (*deleter)(const Slice& key, void* value),
+                        Cache::Handle** handle,
+                        Cache::Priority priority) override;
+  virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
   // If the entry in in cache, increase reference count and return true.
   // Return false otherwise.
   //
   // Not necessary to hold mutex_ before being called.
-  bool Ref(Cache::Handle* handle) override;
-  bool Release(Cache::Handle* handle, bool force_erase = false) override;
-  void Erase(const Slice& key, uint32_t hash) override;
+  virtual bool Ref(Cache::Handle* handle) override;
+  virtual bool Release(Cache::Handle* handle,
+                       bool force_erase = false) override;
+  virtual void Erase(const Slice& key, uint32_t hash) override;
   bool EraseAndConfirm(const Slice& key, uint32_t hash,
                        CleanupContext* context);
-  size_t GetUsage() const override;
-  size_t GetPinnedUsage() const override;
-  void EraseUnRefEntries() override;
-  void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
-                              bool thread_safe) override;
+  virtual size_t GetUsage() const override;
+  virtual size_t GetPinnedUsage() const override;
+  virtual void EraseUnRefEntries() override;
+  virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
+                                      bool thread_safe) override;
 
  private:
   static const uint32_t kInCacheBit = 1;
@@ -387,9 +367,7 @@ ClockCacheShard::~ClockCacheShard() {
   for (auto& handle : list_) {
     uint32_t flags = handle.flags.load(std::memory_order_relaxed);
     if (InCache(flags) || CountRefs(flags) > 0) {
-      if (handle.deleter != nullptr) {
-        (*handle.deleter)(handle.key, handle.value);
-      }
+      (*handle.deleter)(handle.key, handle.value);
       delete[] handle.key.data();
     }
   }
@@ -427,12 +405,11 @@ void ClockCacheShard::RecycleHandle(CacheHandle* handle,
   assert(!InCache(handle->flags) && CountRefs(handle->flags) == 0);
   context->to_delete_key.push_back(handle->key.data());
   context->to_delete_value.emplace_back(*handle);
-  size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
   handle->key.clear();
   handle->value = nullptr;
   handle->deleter = nullptr;
   recycle_.push_back(handle);
-  usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+  usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
 }
 
 void ClockCacheShard::Cleanup(const CleanupContext& context) {
@@ -458,8 +435,7 @@ bool ClockCacheShard::Ref(Cache::Handle* h) {
                                             std::memory_order_relaxed)) {
       if (CountRefs(flags) == 0) {
         // No reference count before the operation.
-        size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-        pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+        pinned_usage_.fetch_add(handle->charge, std::memory_order_relaxed);
       }
       return true;
     }
@@ -479,8 +455,7 @@ bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
   assert(CountRefs(flags) > 0);
   if (CountRefs(flags) == 1) {
     // this is the last reference.
-    size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-    pinned_usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
     // Cleanup if it is the last reference.
     if (!InCache(flags)) {
       MutexLock l(&mutex_);
@@ -565,10 +540,8 @@ CacheHandle* ClockCacheShard::Insert(
     const Slice& key, uint32_t hash, void* value, size_t charge,
     void (*deleter)(const Slice& key, void* value), bool hold_reference,
     CleanupContext* context) {
-  size_t total_charge =
-      CacheHandle::CalcTotalCharge(key, charge, metadata_charge_policy_);
   MutexLock l(&mutex_);
-  bool success = EvictFromCache(total_charge, context);
+  bool success = EvictFromCache(charge, context);
   bool strict = strict_capacity_limit_.load(std::memory_order_relaxed);
   if (!success && (strict || !hold_reference)) {
     context->to_delete_key.push_back(key.data());
@@ -603,9 +576,9 @@ CacheHandle* ClockCacheShard::Insert(
   }
   table_.insert(HashTable::value_type(CacheKey(key, hash), handle));
   if (hold_reference) {
-    pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_add(charge, std::memory_order_relaxed);
   }
-  usage_.fetch_add(total_charge, std::memory_order_relaxed);
+  usage_.fetch_add(charge, std::memory_order_relaxed);
   return handle;
 }
 
@@ -700,45 +673,41 @@ void ClockCacheShard::EraseUnRefEntries() {
   Cleanup(context);
 }
 
-class ClockCache final : public ShardedCache {
+class ClockCache : public ShardedCache {
  public:
-  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-             CacheMetadataChargePolicy metadata_charge_policy)
+  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit)
       : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
     int num_shards = 1 << num_shard_bits;
     shards_ = new ClockCacheShard[num_shards];
-    for (int i = 0; i < num_shards; i++) {
-      shards_[i].set_metadata_charge_policy(metadata_charge_policy);
-    }
     SetCapacity(capacity);
     SetStrictCapacityLimit(strict_capacity_limit);
   }
 
-  ~ClockCache() override { delete[] shards_; }
+  virtual ~ClockCache() { delete[] shards_; }
 
-  const char* Name() const override { return "ClockCache"; }
+  virtual const char* Name() const override { return "ClockCache"; }
 
-  CacheShard* GetShard(int shard) override {
+  virtual CacheShard* GetShard(int shard) override {
     return reinterpret_cast<CacheShard*>(&shards_[shard]);
   }
 
-  const CacheShard* GetShard(int shard) const override {
+  virtual const CacheShard* GetShard(int shard) const override {
     return reinterpret_cast<CacheShard*>(&shards_[shard]);
   }
 
-  void* Value(Handle* handle) override {
+  virtual void* Value(Handle* handle) override {
     return reinterpret_cast<const CacheHandle*>(handle)->value;
   }
 
-  size_t GetCharge(Handle* handle) const override {
+  virtual size_t GetCharge(Handle* handle) const override {
     return reinterpret_cast<const CacheHandle*>(handle)->charge;
   }
 
-  uint32_t GetHash(Handle* handle) const override {
+  virtual uint32_t GetHash(Handle* handle) const override {
     return reinterpret_cast<const CacheHandle*>(handle)->hash;
   }
 
-  void DisownData() override { shards_ = nullptr; }
+  virtual void DisownData() override { shards_ = nullptr; }
 
  private:
   ClockCacheShard* shards_;
@@ -746,14 +715,13 @@ class ClockCache final : public ShardedCache {
 
 }  // end anonymous namespace
 
-std::shared_ptr<Cache> NewClockCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
+                                     bool strict_capacity_limit) {
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  return std::make_shared<ClockCache>(
-      capacity, num_shard_bits, strict_capacity_limit, metadata_charge_policy);
+  return std::make_shared<ClockCache>(capacity, num_shard_bits,
+                                      strict_capacity_limit);
 }
 
 }  // namespace rocksdb

cache/lru_cache.cc

@@ -7,6 +7,10 @@
 // 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.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/lru_cache.h"
 
 #include <assert.h>
@@ -24,7 +28,7 @@ LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {
 
 LRUHandleTable::~LRUHandleTable() {
   ApplyToAllCacheEntries([](LRUHandle* h) {
-    if (!h->HasRefs()) {
+    if (h->refs == 1) {
       h->Free();
     }
   });
@@ -95,40 +99,40 @@ void LRUHandleTable::Resize() {
   length_ = new_length;
 }
 
-LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                             double high_pri_pool_ratio,
-                             bool use_adaptive_mutex,
-                             CacheMetadataChargePolicy metadata_charge_policy)
-    : capacity_(0),
-      high_pri_pool_usage_(0),
-      strict_capacity_limit_(strict_capacity_limit),
-      high_pri_pool_ratio_(high_pri_pool_ratio),
-      high_pri_pool_capacity_(0),
-      usage_(0),
-      lru_usage_(0),
-      mutex_(use_adaptive_mutex) {
-  set_metadata_charge_policy(metadata_charge_policy);
+LRUCacheShard::LRUCacheShard()
+    : capacity_(0), high_pri_pool_usage_(0), strict_capacity_limit_(false),
+      high_pri_pool_ratio_(0), high_pri_pool_capacity_(0), usage_(0),
+      lru_usage_(0) {
   // Make empty circular linked list
   lru_.next = &lru_;
   lru_.prev = &lru_;
   lru_low_pri_ = &lru_;
-  SetCapacity(capacity);
 }
 
+LRUCacheShard::~LRUCacheShard() {}
+
+bool LRUCacheShard::Unref(LRUHandle* e) {
+  assert(e->refs > 0);
+  e->refs--;
+  return e->refs == 0;
+}
+
+// Call deleter and free
+
 void LRUCacheShard::EraseUnRefEntries() {
   autovector<LRUHandle*> last_reference_list;
   {
     MutexLock l(&mutex_);
     while (lru_.next != &lru_) {
       LRUHandle* old = lru_.next;
-      // LRU list contains only elements which can be evicted
-      assert(old->InCache() && !old->HasRefs());
+      assert(old->InCache());
+      assert(old->refs ==
+             1);  // LRU list contains elements which may be evicted
       LRU_Remove(old);
       table_.Remove(old->key(), old->hash);
       old->SetInCache(false);
-      size_t total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
+      Unref(old);
+      usage_ -= old->charge;
       last_reference_list.push_back(old);
     }
   }
@@ -140,27 +144,22 @@ void LRUCacheShard::EraseUnRefEntries() {
 
 void LRUCacheShard::ApplyToAllCacheEntries(void (*callback)(void*, size_t),
                                            bool thread_safe) {
-  const auto applyCallback = [&]() {
-    table_.ApplyToAllCacheEntries(
-        [callback](LRUHandle* h) { callback(h->value, h->charge); });
-  };
-
   if (thread_safe) {
-    MutexLock l(&mutex_);
-    applyCallback();
-  } else {
-    applyCallback();
+    mutex_.Lock();
+  }
+  table_.ApplyToAllCacheEntries(
+      [callback](LRUHandle* h) { callback(h->value, h->charge); });
+  if (thread_safe) {
+    mutex_.Unlock();
   }
 }
 
 void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
-  MutexLock l(&mutex_);
   *lru = &lru_;
   *lru_low_pri = lru_low_pri_;
 }
 
 size_t LRUCacheShard::TEST_GetLRUSize() {
-  MutexLock l(&mutex_);
   LRUHandle* lru_handle = lru_.next;
   size_t lru_size = 0;
   while (lru_handle != &lru_) {
@@ -184,27 +183,24 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   e->next->prev = e->prev;
   e->prev->next = e->next;
   e->prev = e->next = nullptr;
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-  assert(lru_usage_ >= total_charge);
-  lru_usage_ -= total_charge;
+  lru_usage_ -= e->charge;
   if (e->InHighPriPool()) {
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    assert(high_pri_pool_usage_ >= e->charge);
+    high_pri_pool_usage_ -= e->charge;
   }
 }
 
 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
   assert(e->next == nullptr);
   assert(e->prev == nullptr);
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-  if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
+  if (high_pri_pool_ratio_ > 0 && e->IsHighPri()) {
     // Inset "e" to head of LRU list.
     e->next = &lru_;
     e->prev = lru_.prev;
     e->prev->next = e;
     e->next->prev = e;
     e->SetInHighPriPool(true);
-    high_pri_pool_usage_ += total_charge;
+    high_pri_pool_usage_ += e->charge;
     MaintainPoolSize();
   } else {
     // Insert "e" to the head of low-pri pool. Note that when
@@ -216,7 +212,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->SetInHighPriPool(false);
     lru_low_pri_ = e;
   }
-  lru_usage_ += total_charge;
+  lru_usage_ += e->charge;
 }
 
 void LRUCacheShard::MaintainPoolSize() {
@@ -225,29 +221,41 @@ void LRUCacheShard::MaintainPoolSize() {
     lru_low_pri_ = lru_low_pri_->next;
     assert(lru_low_pri_ != &lru_);
     lru_low_pri_->SetInHighPriPool(false);
-    size_t total_charge =
-        lru_low_pri_->CalcTotalCharge(metadata_charge_policy_);
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    high_pri_pool_usage_ -= lru_low_pri_->charge;
   }
 }
 
 void LRUCacheShard::EvictFromLRU(size_t charge,
                                  autovector<LRUHandle*>* deleted) {
-  while ((usage_ + charge) > capacity_ && lru_.next != &lru_) {
+  while (usage_ + charge > capacity_ && lru_.next != &lru_) {
     LRUHandle* old = lru_.next;
-    // LRU list contains only elements which can be evicted
-    assert(old->InCache() && !old->HasRefs());
+    assert(old->InCache());
+    assert(old->refs == 1);  // LRU list contains elements which may be evicted
     LRU_Remove(old);
     table_.Remove(old->key(), old->hash);
     old->SetInCache(false);
-    size_t old_total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-    assert(usage_ >= old_total_charge);
-    usage_ -= old_total_charge;
+    Unref(old);
+    usage_ -= old->charge;
     deleted->push_back(old);
   }
 }
 
+void* LRUCacheShard::operator new(size_t size) {
+  return port::cacheline_aligned_alloc(size);
+}
+
+void* LRUCacheShard::operator new[](size_t size) {
+  return port::cacheline_aligned_alloc(size);
+}
+
+void LRUCacheShard::operator delete(void *memblock) {
+  port::cacheline_aligned_free(memblock);
+}
+
+void LRUCacheShard::operator delete[](void* memblock) {
+  port::cacheline_aligned_free(memblock);
+}
+
 void LRUCacheShard::SetCapacity(size_t capacity) {
   autovector<LRUHandle*> last_reference_list;
   {
@@ -256,8 +264,8 @@ void LRUCacheShard::SetCapacity(size_t capacity) {
     high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
     EvictFromLRU(0, &last_reference_list);
   }
-
-  // Free the entries outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
   for (auto entry : last_reference_list) {
     entry->Free();
   }
@@ -273,22 +281,21 @@ Cache::Handle* LRUCacheShard::Lookup(const Slice& key, uint32_t hash) {
   LRUHandle* e = table_.Lookup(key, hash);
   if (e != nullptr) {
     assert(e->InCache());
-    if (!e->HasRefs()) {
-      // The entry is in LRU since it's in hash and has no external references
+    if (e->refs == 1) {
       LRU_Remove(e);
     }
-    e->Ref();
-    e->SetHit();
+    e->refs++;
   }
   return reinterpret_cast<Cache::Handle*>(e);
 }
 
 bool LRUCacheShard::Ref(Cache::Handle* h) {
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(h);
+  LRUHandle* handle = reinterpret_cast<LRUHandle*>(h);
   MutexLock l(&mutex_);
-  // To create another reference - entry must be already externally referenced
-  assert(e->HasRefs());
-  e->Ref();
+  if (handle->InCache() && handle->refs == 1) {
+    LRU_Remove(handle);
+  }
+  handle->refs++;
   return true;
 }
 
@@ -307,29 +314,30 @@ bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
   bool last_reference = false;
   {
     MutexLock l(&mutex_);
-    last_reference = e->Unref();
-    if (last_reference && e->InCache()) {
+    last_reference = Unref(e);
+    if (last_reference) {
+      usage_ -= e->charge;
+    }
+    if (e->refs == 1 && e->InCache()) {
       // The item is still in cache, and nobody else holds a reference to it
       if (usage_ > capacity_ || force_erase) {
+        // the cache is full
         // The LRU list must be empty since the cache is full
-        assert(lru_.next == &lru_ || force_erase);
-        // Take this opportunity and remove the item
+        assert(!(usage_ > capacity_) || lru_.next == &lru_);
+        // take this opportunity and remove the item
         table_.Remove(e->key(), e->hash);
         e->SetInCache(false);
+        Unref(e);
+        usage_ -= e->charge;
+        last_reference = true;
       } else {
-        // Put the item back on the LRU list, and don't free it
+        // put the item on the list to be potentially freed
         LRU_Insert(e);
-        last_reference = false;
       }
     }
-    if (last_reference) {
-      size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
-    }
   }
 
-  // Free the entry here outside of mutex for performance reasons
+  // free outside of mutex
   if (last_reference) {
     e->Free();
   }
@@ -345,7 +353,7 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   // It shouldn't happen very often though.
   LRUHandle* e = reinterpret_cast<LRUHandle*>(
       new char[sizeof(LRUHandle) - 1 + key.size()]);
-  Status s = Status::OK();
+  Status s;
   autovector<LRUHandle*> last_reference_list;
 
   e->value = value;
@@ -354,26 +362,26 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   e->key_length = key.size();
   e->flags = 0;
   e->hash = hash;
-  e->refs = 0;
+  e->refs = (handle == nullptr
+                 ? 1
+                 : 2);  // One from LRUCache, one for the returned handle
   e->next = e->prev = nullptr;
   e->SetInCache(true);
   e->SetPriority(priority);
   memcpy(e->key_data, key.data(), key.size());
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
 
   {
     MutexLock l(&mutex_);
 
     // Free the space following strict LRU policy until enough space
     // is freed or the lru list is empty
-    EvictFromLRU(total_charge, &last_reference_list);
+    EvictFromLRU(charge, &last_reference_list);
 
-    if ((usage_ + total_charge) > capacity_ &&
+    if (usage_ - lru_usage_ + charge > capacity_ &&
         (strict_capacity_limit_ || handle == nullptr)) {
       if (handle == nullptr) {
         // Don't insert the entry but still return ok, as if the entry inserted
         // into cache and get evicted immediately.
-        e->SetInCache(false);
         last_reference_list.push_back(e);
       } else {
         delete[] reinterpret_cast<char*>(e);
@@ -381,33 +389,32 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
         s = Status::Incomplete("Insert failed due to LRU cache being full.");
       }
     } else {
-      // Insert into the cache. Note that the cache might get larger than its
-      // capacity if not enough space was freed up.
+      // insert into the cache
+      // note that the cache might get larger than its capacity if not enough
+      // space was freed
       LRUHandle* old = table_.Insert(e);
-      usage_ += total_charge;
+      usage_ += e->charge;
       if (old != nullptr) {
-        assert(old->InCache());
         old->SetInCache(false);
-        if (!old->HasRefs()) {
-          // old is on LRU because it's in cache and its reference count is 0
+        if (Unref(old)) {
+          usage_ -= old->charge;
+          // old is on LRU because it's in cache and its reference count
+          // was just 1 (Unref returned 0)
           LRU_Remove(old);
-          size_t old_total_charge =
-              old->CalcTotalCharge(metadata_charge_policy_);
-          assert(usage_ >= old_total_charge);
-          usage_ -= old_total_charge;
           last_reference_list.push_back(old);
         }
       }
       if (handle == nullptr) {
         LRU_Insert(e);
       } else {
-        e->Ref();
         *handle = reinterpret_cast<Cache::Handle*>(e);
       }
+      s = Status::OK();
     }
   }
 
-  // Free the entries here outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
   for (auto entry : last_reference_list) {
     entry->Free();
   }
@@ -422,20 +429,18 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
     MutexLock l(&mutex_);
     e = table_.Remove(key, hash);
     if (e != nullptr) {
-      assert(e->InCache());
-      e->SetInCache(false);
-      if (!e->HasRefs()) {
-        // The entry is in LRU since it's in hash and has no external references
-        LRU_Remove(e);
-        size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-        assert(usage_ >= total_charge);
-        usage_ -= total_charge;
-        last_reference = true;
+      last_reference = Unref(e);
+      if (last_reference) {
+        usage_ -= e->charge;
       }
+      if (last_reference && e->InCache()) {
+        LRU_Remove(e);
+      }
+      e->SetInCache(false);
     }
   }
 
-  // Free the entry here outside of mutex for performance reasons
+  // mutex not held here
   // last_reference will only be true if e != nullptr
   if (last_reference) {
     e->Free();
@@ -465,32 +470,18 @@ std::string LRUCacheShard::GetPrintableOptions() const {
 }
 
 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit, double high_pri_pool_ratio,
-                   std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex,
-                   CacheMetadataChargePolicy metadata_charge_policy)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
-                   std::move(allocator)) {
+                   bool strict_capacity_limit, double high_pri_pool_ratio)
+    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
   num_shards_ = 1 << num_shard_bits;
-  shards_ = reinterpret_cast<LRUCacheShard*>(
-      port::cacheline_aligned_alloc(sizeof(LRUCacheShard) * num_shards_));
-  size_t per_shard = (capacity + (num_shards_ - 1)) / num_shards_;
+  shards_ = new LRUCacheShard[num_shards_];
+  SetCapacity(capacity);
+  SetStrictCapacityLimit(strict_capacity_limit);
   for (int i = 0; i < num_shards_; i++) {
-    new (&shards_[i])
-        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio,
-                      use_adaptive_mutex, metadata_charge_policy);
+    shards_[i].SetHighPriorityPoolRatio(high_pri_pool_ratio);
   }
 }
 
-LRUCache::~LRUCache() {
-  if (shards_ != nullptr) {
-    assert(num_shards_ > 0);
-    for (int i = 0; i < num_shards_; i++) {
-      shards_[i].~LRUCacheShard();
-    }
-    port::cacheline_aligned_free(shards_);
-  }
-}
+LRUCache::~LRUCache() { delete[] shards_; }
 
 CacheShard* LRUCache::GetShard(int shard) {
   return reinterpret_cast<CacheShard*>(&shards_[shard]);
@@ -514,17 +505,9 @@ uint32_t LRUCache::GetHash(Handle* handle) const {
 
 void LRUCache::DisownData() {
 // Do not drop data if compile with ASAN to suppress leak warning.
-#if defined(__clang__)
-#if !defined(__has_feature) || !__has_feature(address_sanitizer)
-  shards_ = nullptr;
-  num_shards_ = 0;
-#endif
-#else  // __clang__
 #ifndef __SANITIZE_ADDRESS__
   shards_ = nullptr;
-  num_shards_ = 0;
 #endif  // !__SANITIZE_ADDRESS__
-#endif  // __clang__
 }
 
 size_t LRUCache::TEST_GetLRUSize() {
@@ -546,16 +529,12 @@ double LRUCache::GetHighPriPoolRatio() {
 std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
   return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
                      cache_opts.strict_capacity_limit,
-                     cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-                     cache_opts.metadata_charge_policy);
+                     cache_opts.high_pri_pool_ratio);
 }
 
-std::shared_ptr<Cache> NewLRUCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
+                                   bool strict_capacity_limit,
+                                   double high_pri_pool_ratio) {
   if (num_shard_bits >= 20) {
     return nullptr;  // the cache cannot be sharded into too many fine pieces
   }
@@ -566,9 +545,8 @@ std::shared_ptr<Cache> NewLRUCache(
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  return std::make_shared<LRUCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      std::move(memory_allocator), use_adaptive_mutex, metadata_charge_policy);
+  return std::make_shared<LRUCache>(capacity, num_shard_bits,
+                                    strict_capacity_limit, high_pri_pool_ratio);
 }
 
 }  // namespace rocksdb

cache/lru_cache.h

@@ -12,40 +12,36 @@
 
 #include "cache/sharded_cache.h"
 
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 
 namespace rocksdb {
 
-// LRU cache implementation. This class is not thread-safe.
+// LRU cache implementation
 
 // An entry is a variable length heap-allocated structure.
 // Entries are referenced by cache and/or by any external entity.
-// The cache keeps all its entries in a hash table. Some elements
+// The cache keeps all its entries in table. Some elements
 // are also stored on LRU list.
 //
 // LRUHandle can be in these states:
 // 1. Referenced externally AND in hash table.
-//    In that case the entry is *not* in the LRU list
-//    (refs >= 1 && in_cache == true)
-// 2. Not referenced externally AND in hash table.
-//    In that case the entry is in the LRU list and can be freed.
-//    (refs == 0 && in_cache == true)
-// 3. Referenced externally AND not in hash table.
-//    In that case the entry is not in the LRU list and not in hash table.
-//    The entry can be freed when refs becomes 0.
-//    (refs >= 1 && in_cache == false)
+//  In that case the entry is *not* in the LRU. (refs > 1 && in_cache == true)
+// 2. Not referenced externally and in hash table. In that case the entry is
+// in the LRU and can be freed. (refs == 1 && in_cache == true)
+// 3. Referenced externally and not in hash table. In that case the entry is
+// in not on LRU and not in table. (refs >= 1 && in_cache == false)
 //
 // All newly created LRUHandles are in state 1. If you call
-// LRUCacheShard::Release on entry in state 1, it will go into state 2.
-// To move from state 1 to state 3, either call LRUCacheShard::Erase or
-// LRUCacheShard::Insert with the same key (but possibly different value).
+// LRUCacheShard::Release
+// on entry in state 1, it will go into state 2. To move from state 1 to
+// state 3, either call LRUCacheShard::Erase or LRUCacheShard::Insert with the
+// same key.
 // To move from state 2 to state 1, use LRUCacheShard::Lookup.
 // Before destruction, make sure that no handles are in state 1. This means
 // that any successful LRUCacheShard::Lookup/LRUCacheShard::Insert have a
-// matching LRUCache::Release (to move into state 2) or LRUCacheShard::Erase
-// (to move into state 3).
+// matching
+// RUCache::Release (to move into state 2) or LRUCacheShard::Erase (for state 3)
 
 struct LRUHandle {
   void* value;
@@ -55,95 +51,64 @@ struct LRUHandle {
   LRUHandle* prev;
   size_t charge;  // TODO(opt): Only allow uint32_t?
   size_t key_length;
-  // The hash of key(). Used for fast sharding and comparisons.
-  uint32_t hash;
-  // The number of external refs to this entry. The cache itself is not counted.
-  uint32_t refs;
+  uint32_t refs;     // a number of refs to this entry
+                     // cache itself is counted as 1
 
-  enum Flags : uint8_t {
-    // Whether this entry is referenced by the hash table.
-    IN_CACHE = (1 << 0),
-    // Whether this entry is high priority entry.
-    IS_HIGH_PRI = (1 << 1),
-    // Whether this entry is in high-pri pool.
-    IN_HIGH_PRI_POOL = (1 << 2),
-    // Wwhether this entry has had any lookups (hits).
-    HAS_HIT = (1 << 3),
-  };
+  // Include the following flags:
+  //   in_cache:    whether this entry is referenced by the hash table.
+  //   is_high_pri: whether this entry is high priority entry.
+  //   in_high_pri_pool: whether this entry is in high-pri pool.
+  char flags;
 
-  uint8_t flags;
+  uint32_t hash;     // Hash of key(); used for fast sharding and comparisons
 
-  // Beginning of the key (MUST BE THE LAST FIELD IN THIS STRUCT!)
-  char key_data[1];
+  char key_data[1];  // Beginning of key
 
-  Slice key() const { return Slice(key_data, key_length); }
-
-  // Increase the reference count by 1.
-  void Ref() { refs++; }
-
-  // Just reduce the reference count by 1. Return true if it was last reference.
-  bool Unref() {
-    assert(refs > 0);
-    refs--;
-    return refs == 0;
+  Slice key() const {
+    // For cheaper lookups, we allow a temporary Handle object
+    // to store a pointer to a key in "value".
+    if (next == this) {
+      return *(reinterpret_cast<Slice*>(value));
+    } else {
+      return Slice(key_data, key_length);
+    }
   }
 
-  // Return true if there are external refs, false otherwise.
-  bool HasRefs() const { return refs > 0; }
-
-  bool InCache() const { return flags & IN_CACHE; }
-  bool IsHighPri() const { return flags & IS_HIGH_PRI; }
-  bool InHighPriPool() const { return flags & IN_HIGH_PRI_POOL; }
-  bool HasHit() const { return flags & HAS_HIT; }
+  bool InCache() { return flags & 1; }
+  bool IsHighPri() { return flags & 2; }
+  bool InHighPriPool() { return flags & 4; }
 
   void SetInCache(bool in_cache) {
     if (in_cache) {
-      flags |= IN_CACHE;
+      flags |= 1;
     } else {
-      flags &= ~IN_CACHE;
+      flags &= ~1;
     }
   }
 
   void SetPriority(Cache::Priority priority) {
     if (priority == Cache::Priority::HIGH) {
-      flags |= IS_HIGH_PRI;
+      flags |= 2;
     } else {
-      flags &= ~IS_HIGH_PRI;
+      flags &= ~2;
     }
   }
 
   void SetInHighPriPool(bool in_high_pri_pool) {
     if (in_high_pri_pool) {
-      flags |= IN_HIGH_PRI_POOL;
+      flags |= 4;
     } else {
-      flags &= ~IN_HIGH_PRI_POOL;
+      flags &= ~4;
     }
   }
 
-  void SetHit() { flags |= HAS_HIT; }
-
   void Free() {
-    assert(refs == 0);
+    assert((refs == 1 && InCache()) || (refs == 0 && !InCache()));
     if (deleter) {
       (*deleter)(key(), value);
     }
     delete[] reinterpret_cast<char*>(this);
   }
-
-  // Caclculate the memory usage by metadata
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge += malloc_usable_size(static_cast<void*>(this));
-#else
-      // This is the size that is used when a new handle is created
-      meta_charge += sizeof(LRUHandle) - 1 + key_length;
-#endif
-    }
-    return charge + meta_charge;
-  }
 };
 
 // We provide our own simple hash table since it removes a whole bunch
@@ -189,12 +154,10 @@ class LRUHandleTable {
 };
 
 // A single shard of sharded cache.
-class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
+class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
  public:
-  LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                double high_pri_pool_ratio, bool use_adaptive_mutex,
-                CacheMetadataChargePolicy metadata_charge_policy);
-  virtual ~LRUCacheShard() override = default;
+  LRUCacheShard();
+  virtual ~LRUCacheShard();
 
   // Separate from constructor so caller can easily make an array of LRUCache
   // if current usage is more than new capacity, the function will attempt to
@@ -242,6 +205,15 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   //  Retrives high pri pool ratio
   double GetHighPriPoolRatio();
 
+  // Overloading to aligned it to cache line size
+  void* operator new(size_t);
+
+  void* operator new[](size_t);
+
+  void operator delete(void *);
+
+  void operator delete[](void*);
+
  private:
   void LRU_Remove(LRUHandle* e);
   void LRU_Insert(LRUHandle* e);
@@ -250,6 +222,10 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   // high-pri pool is no larger than the size specify by high_pri_pool_pct.
   void MaintainPoolSize();
 
+  // Just reduce the reference count by 1.
+  // Return true if last reference
+  bool Unref(LRUHandle* e);
+
   // Free some space following strict LRU policy until enough space
   // to hold (usage_ + charge) is freed or the lru list is empty
   // This function is not thread safe - it needs to be executed while
@@ -305,18 +281,10 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   mutable port::Mutex mutex_;
 };
 
-class LRUCache
-#ifdef NDEBUG
-    final
-#endif
-    : public ShardedCache {
+class LRUCache : public ShardedCache {
  public:
   LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-           double high_pri_pool_ratio,
-           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
+           double high_pri_pool_ratio);
   virtual ~LRUCache();
   virtual const char* Name() const override { return "LRUCache"; }
   virtual CacheShard* GetShard(int shard) override;
@@ -332,7 +300,7 @@ class LRUCache
   double GetHighPriPoolRatio();
 
  private:
-  LRUCacheShard* shards_ = nullptr;
+  LRUCacheShard* shards_;
   int num_shards_ = 0;
 };
 

cache/lru_cache_test.cc

@@ -7,32 +7,29 @@
 
 #include <string>
 #include <vector>
-#include "port/port.h"
-#include "test_util/testharness.h"
+#include "util/testharness.h"
 
 namespace rocksdb {
 
 class LRUCacheTest : public testing::Test {
  public:
   LRUCacheTest() {}
-  ~LRUCacheTest() override { DeleteCache(); }
+  ~LRUCacheTest() {}
 
-  void DeleteCache() {
-    if (cache_ != nullptr) {
-      cache_->~LRUCacheShard();
-      port::cacheline_aligned_free(cache_);
-      cache_ = nullptr;
-    }
-  }
-
-  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0,
-                bool use_adaptive_mutex = kDefaultToAdaptiveMutex) {
-    DeleteCache();
-    cache_ = reinterpret_cast<LRUCacheShard*>(
-        port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
-    new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
-                               high_pri_pool_ratio, use_adaptive_mutex,
-                               kDontChargeCacheMetadata);
+  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0) {
+    cache_.reset(
+#if defined(_MSC_VER)
+#pragma warning(push)
+#pragma warning(disable: 4316) // We've validated the alignment with the new operators
+#endif
+      new LRUCacheShard()
+#if defined(_MSC_VER)
+#pragma warning(pop)
+#endif
+    );
+    cache_->SetCapacity(capacity);
+    cache_->SetStrictCapacityLimit(false);
+    cache_->SetHighPriorityPoolRatio(high_pri_pool_ratio);
   }
 
   void Insert(const std::string& key,
@@ -88,7 +85,7 @@ class LRUCacheTest : public testing::Test {
   }
 
  private:
-  LRUCacheShard* cache_ = nullptr;
+  std::unique_ptr<LRUCacheShard> cache_;
 };
 
 TEST_F(LRUCacheTest, BasicLRU) {
@@ -117,30 +114,7 @@ TEST_F(LRUCacheTest, BasicLRU) {
   ValidateLRUList({"e", "z", "d", "u", "v"});
 }
 
-TEST_F(LRUCacheTest, MidpointInsertion) {
-  // Allocate 2 cache entries to high-pri pool.
-  NewCache(5, 0.45);
-
-  Insert("a", Cache::Priority::LOW);
-  Insert("b", Cache::Priority::LOW);
-  Insert("c", Cache::Priority::LOW);
-  Insert("x", Cache::Priority::HIGH);
-  Insert("y", Cache::Priority::HIGH);
-  ValidateLRUList({"a", "b", "c", "x", "y"}, 2);
-
-  // Low-pri entries inserted to the tail of low-pri list (the midpoint).
-  // After lookup, it will move to the tail of the full list.
-  Insert("d", Cache::Priority::LOW);
-  ValidateLRUList({"b", "c", "d", "x", "y"}, 2);
-  ASSERT_TRUE(Lookup("d"));
-  ValidateLRUList({"b", "c", "x", "y", "d"}, 2);
-
-  // High-pri entries will be inserted to the tail of full list.
-  Insert("z", Cache::Priority::HIGH);
-  ValidateLRUList({"c", "x", "y", "d", "z"}, 2);
-}
-
-TEST_F(LRUCacheTest, EntriesWithPriority) {
+TEST_F(LRUCacheTest, MidPointInsertion) {
   // Allocate 2 cache entries to high-pri pool.
   NewCache(5, 0.45);
 
@@ -166,15 +140,15 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   Insert("a", Cache::Priority::LOW);
   ValidateLRUList({"v", "X", "a", "Y", "Z"}, 2);
 
-  // Low-pri entries will be inserted to head of high-pri pool after lookup.
+  // Low-pri entries will be inserted to head of low-pri pool after lookup.
   ASSERT_TRUE(Lookup("v"));
-  ValidateLRUList({"X", "a", "Y", "Z", "v"}, 2);
+  ValidateLRUList({"X", "a", "v", "Y", "Z"}, 2);
 
   // High-pri entries will be inserted to the head of the list after lookup.
   ASSERT_TRUE(Lookup("X"));
-  ValidateLRUList({"a", "Y", "Z", "v", "X"}, 2);
+  ValidateLRUList({"a", "v", "Y", "Z", "X"}, 2);
   ASSERT_TRUE(Lookup("Z"));
-  ValidateLRUList({"a", "Y", "v", "X", "Z"}, 2);
+  ValidateLRUList({"a", "v", "Y", "X", "Z"}, 2);
 
   Erase("Y");
   ValidateLRUList({"a", "v", "X", "Z"}, 2);
@@ -187,7 +161,7 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   Insert("g", Cache::Priority::LOW);
   ValidateLRUList({"d", "e", "f", "g", "Z"}, 1);
   ASSERT_TRUE(Lookup("d"));
-  ValidateLRUList({"e", "f", "g", "Z", "d"}, 2);
+  ValidateLRUList({"e", "f", "g", "d", "Z"}, 1);
 }
 
 }  // namespace rocksdb

cache/sharded_cache.cc

@@ -7,6 +7,10 @@
 // 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.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/sharded_cache.h"
 
 #include <string>
@@ -16,10 +20,8 @@
 namespace rocksdb {
 
 ShardedCache::ShardedCache(size_t capacity, int num_shard_bits,
-                           bool strict_capacity_limit,
-                           std::shared_ptr<MemoryAllocator> allocator)
-    : Cache(std::move(allocator)),
-      num_shard_bits_(num_shard_bits),
+                           bool strict_capacity_limit)
+    : num_shard_bits_(num_shard_bits),
       capacity_(capacity),
       strict_capacity_limit_(strict_capacity_limit),
       last_id_(1) {}
@@ -140,9 +142,6 @@ std::string ShardedCache::GetPrintableOptions() const {
              strict_capacity_limit_);
     ret.append(buffer);
   }
-  snprintf(buffer, kBufferSize, "    memory_allocator : %s\n",
-           memory_allocator() ? memory_allocator()->Name() : "None");
-  ret.append(buffer);
   ret.append(GetShard(0)->GetPrintableOptions());
   return ret;
 }

cache/sharded_cache.h

@@ -40,13 +40,6 @@ class CacheShard {
                                       bool thread_safe) = 0;
   virtual void EraseUnRefEntries() = 0;
   virtual std::string GetPrintableOptions() const { return ""; }
-  void set_metadata_charge_policy(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    metadata_charge_policy_ = metadata_charge_policy;
-  }
-
- protected:
-  CacheMetadataChargePolicy metadata_charge_policy_ = kDontChargeCacheMetadata;
 };
 
 // Generic cache interface which shards cache by hash of keys. 2^num_shard_bits
@@ -54,15 +47,13 @@ class CacheShard {
 // Keys are sharded by the highest num_shard_bits bits of hash value.
 class ShardedCache : public Cache {
  public:
-  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-               std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
+  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit);
   virtual ~ShardedCache() = default;
   virtual const char* Name() const override = 0;
   virtual CacheShard* GetShard(int shard) = 0;
   virtual const CacheShard* GetShard(int shard) const = 0;
   virtual void* Value(Handle* handle) override = 0;
-  virtual size_t GetCharge(Handle* handle) const override = 0;
-
+  virtual size_t GetCharge(Handle* handle) const = 0;
   virtual uint32_t GetHash(Handle* handle) const = 0;
   virtual void DisownData() override = 0;
 
@@ -91,7 +82,7 @@ class ShardedCache : public Cache {
 
  private:
   static inline uint32_t HashSlice(const Slice& s) {
-    return static_cast<uint32_t>(GetSliceNPHash64(s));
+    return Hash(s.data(), s.size(), 0);
   }
 
   uint32_t Shard(uint32_t hash) {

cmake/modules/FindJeMalloc.cmake

@@ -1,29 +1,21 @@
 # - Find JeMalloc library
 # Find the native JeMalloc includes and library
 #
-# JeMalloc_INCLUDE_DIRS - where to find jemalloc.h, etc.
-# JeMalloc_LIBRARIES - List of libraries when using jemalloc.
-# JeMalloc_FOUND - True if jemalloc found.
+# 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_DIRS
+find_path(JEMALLOC_INCLUDE_DIR
   NAMES jemalloc/jemalloc.h
   HINTS ${JEMALLOC_ROOT_DIR}/include)
 
-find_library(JeMalloc_LIBRARIES
+find_library(JEMALLOC_LIBRARIES
   NAMES jemalloc
   HINTS ${JEMALLOC_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(JeMalloc DEFAULT_MSG JeMalloc_LIBRARIES JeMalloc_INCLUDE_DIRS)
+find_package_handle_standard_args(jemalloc DEFAULT_MSG JEMALLOC_LIBRARIES JEMALLOC_INCLUDE_DIR)
 
 mark_as_advanced(
-  JeMalloc_LIBRARIES
-  JeMalloc_INCLUDE_DIRS)
-
-if(JeMalloc_FOUND AND NOT (TARGET JeMalloc::JeMalloc))
-  add_library (JeMalloc::JeMalloc UNKNOWN IMPORTED)
-  set_target_properties(JeMalloc::JeMalloc
-    PROPERTIES
-      IMPORTED_LOCATION ${JeMalloc_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${JeMalloc_INCLUDE_DIRS})
-endif()
+  JEMALLOC_LIBRARIES
+  JEMALLOC_INCLUDE_DIR)

cmake/modules/FindNUMA.cmake

@@ -1,11 +1,11 @@
 # - Find NUMA
 # Find the NUMA library and includes
 #
-# NUMA_INCLUDE_DIRS - where to find numa.h, etc.
+# 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_DIRS
+find_path(NUMA_INCLUDE_DIR
   NAMES numa.h numaif.h
   HINTS ${NUMA_ROOT_DIR}/include)
 
@@ -14,16 +14,8 @@ find_library(NUMA_LIBRARIES
   HINTS ${NUMA_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIRS)
+find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIR)
 
 mark_as_advanced(
   NUMA_LIBRARIES
-  NUMA_INCLUDE_DIRS)
-
-if(NUMA_FOUND AND NOT (TARGET NUMA::NUMA))
-  add_library (NUMA::NUMA UNKNOWN IMPORTED)
-  set_target_properties(NUMA::NUMA
-    PROPERTIES
-      IMPORTED_LOCATION ${NUMA_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${NUMA_INCLUDE_DIRS})
-endif()
+  NUMA_INCLUDE_DIR)

cmake/modules/FindTBB.cmake

@@ -1,33 +1,21 @@
 # - Find TBB
 # Find the Thread Building Blocks library and includes
 #
-# TBB_INCLUDE_DIRS - where to find tbb.h, etc.
+# TBB_INCLUDE_DIR - where to find tbb.h, etc.
 # TBB_LIBRARIES - List of libraries when using TBB.
 # TBB_FOUND - True if TBB found.
 
-if(NOT DEFINED TBB_ROOT_DIR)
-  set(TBB_ROOT_DIR "$ENV{TBBROOT}")
-endif()
-
-find_path(TBB_INCLUDE_DIRS
-  NAMES tbb/tbb.h
-  HINTS ${TBB_ROOT_DIR}/include)
+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 ENV LIBRARY_PATH)
+NAMES tbb
+HINTS ${TBB_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIRS)
+find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIR)
 
 mark_as_advanced(
-  TBB_LIBRARIES
-  TBB_INCLUDE_DIRS)
-
-if(TBB_FOUND AND NOT (TARGET TBB::TBB))
-  add_library (TBB::TBB UNKNOWN IMPORTED)
-  set_target_properties(TBB::TBB
-    PROPERTIES
-      IMPORTED_LOCATION ${TBB_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${TBB_INCLUDE_DIRS})
-endif()
+TBB_LIBRARIES
+TBB_INCLUDE_DIR)

cmake/modules/Findbzip2.cmake

@@ -0,0 +1,21 @@
+# - Find Bzip2
+# Find the bzip2 compression library and includes
+#
+# BZIP2_INCLUDE_DIR - where to find bzlib.h, etc.
+# BZIP2_LIBRARIES - List of libraries when using bzip2.
+# BZIP2_FOUND - True if bzip2 found.
+
+find_path(BZIP2_INCLUDE_DIR
+  NAMES bzlib.h
+  HINTS ${BZIP2_ROOT_DIR}/include)
+
+find_library(BZIP2_LIBRARIES
+  NAMES bz2
+  HINTS ${BZIP2_ROOT_DIR}/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(bzip2 DEFAULT_MSG BZIP2_LIBRARIES BZIP2_INCLUDE_DIR)
+
+mark_as_advanced(
+  BZIP2_LIBRARIES
+  BZIP2_INCLUDE_DIR)

cmake/modules/Findgflags.cmake

@@ -1,29 +0,0 @@
-# - Find gflags library
-# Find the gflags includes and library
-#
-# gflags_INCLUDE_DIR - where to find gflags.h.
-# gflags_LIBRARIES - List of libraries when using gflags.
-# gflags_FOUND - True if gflags found.
-
-find_path(GFLAGS_INCLUDE_DIR
-  NAMES gflags/gflags.h)
-
-find_library(GFLAGS_LIBRARIES
-  NAMES gflags)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(gflags
-  DEFAULT_MSG GFLAGS_LIBRARIES GFLAGS_INCLUDE_DIR)
-
-mark_as_advanced(
-  GFLAGS_LIBRARIES
-  GFLAGS_INCLUDE_DIR)
-
-if(gflags_FOUND AND NOT (TARGET gflags::gflags))
-  add_library(gflags::gflags UNKNOWN IMPORTED)
-  set_target_properties(gflags::gflags
-    PROPERTIES
-      IMPORTED_LOCATION ${GFLAGS_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${GFLAGS_INCLUDE_DIR}
-      IMPORTED_LINK_INTERFACE_LANGUAGES "CXX")
-endif()

cmake/modules/Findlz4.cmake

@@ -1,29 +1,21 @@
 # - Find Lz4
 # Find the lz4 compression library and includes
 #
-# lz4_INCLUDE_DIRS - where to find lz4.h, etc.
-# lz4_LIBRARIES - List of libraries when using lz4.
-# lz4_FOUND - True if lz4 found.
+# 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_DIRS
+find_path(LZ4_INCLUDE_DIR
   NAMES lz4.h
-  HINTS ${lz4_ROOT_DIR}/include)
+  HINTS ${LZ4_ROOT_DIR}/include)
 
-find_library(lz4_LIBRARIES
+find_library(LZ4_LIBRARIES
   NAMES lz4
-  HINTS ${lz4_ROOT_DIR}/lib)
+  HINTS ${LZ4_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(lz4 DEFAULT_MSG lz4_LIBRARIES lz4_INCLUDE_DIRS)
+find_package_handle_standard_args(lz4 DEFAULT_MSG LZ4_LIBRARIES LZ4_INCLUDE_DIR)
 
 mark_as_advanced(
-  lz4_LIBRARIES
-  lz4_INCLUDE_DIRS)
-
-if(lz4_FOUND AND NOT (TARGET lz4::lz4))
-  add_library(lz4::lz4 UNKNOWN IMPORTED)
-  set_target_properties(lz4::lz4
-    PROPERTIES
-      IMPORTED_LOCATION ${lz4_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${lz4_INCLUDE_DIRS})
-endif()
+  LZ4_LIBRARIES
+  LZ4_INCLUDE_DIR)

cmake/modules/Findsnappy.cmake

@@ -1,29 +1,21 @@
 # - Find Snappy
 # Find the snappy compression library and includes
 #
-# snappy_INCLUDE_DIRS - where to find snappy.h, etc.
-# snappy_LIBRARIES - List of libraries when using snappy.
-# snappy_FOUND - True if snappy found.
+# SNAPPY_INCLUDE_DIR - where to find snappy.h, etc.
+# SNAPPY_LIBRARIES - List of libraries when using snappy.
+# SNAPPY_FOUND - True if snappy found.
 
-find_path(snappy_INCLUDE_DIRS
+find_path(SNAPPY_INCLUDE_DIR
   NAMES snappy.h
-  HINTS ${snappy_ROOT_DIR}/include)
+  HINTS ${SNAPPY_ROOT_DIR}/include)
 
-find_library(snappy_LIBRARIES
+find_library(SNAPPY_LIBRARIES
   NAMES snappy
-  HINTS ${snappy_ROOT_DIR}/lib)
+  HINTS ${SNAPPY_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(snappy DEFAULT_MSG snappy_LIBRARIES snappy_INCLUDE_DIRS)
+find_package_handle_standard_args(snappy DEFAULT_MSG SNAPPY_LIBRARIES SNAPPY_INCLUDE_DIR)
 
 mark_as_advanced(
-  snappy_LIBRARIES
-  snappy_INCLUDE_DIRS)
-
-if(snappy_FOUND AND NOT (TARGET snappy::snappy))
-  add_library (snappy::snappy UNKNOWN IMPORTED)
-  set_target_properties(snappy::snappy
-    PROPERTIES
-      IMPORTED_LOCATION ${snappy_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${snappy_INCLUDE_DIRS})
-endif()
+  SNAPPY_LIBRARIES
+  SNAPPY_INCLUDE_DIR)

cmake/modules/Findzlib.cmake

@@ -0,0 +1,21 @@
+# - Find zlib
+# Find the zlib compression library and includes
+#
+# ZLIB_INCLUDE_DIR - where to find zlib.h, etc.
+# ZLIB_LIBRARIES - List of libraries when using zlib.
+# ZLIB_FOUND - True if zlib found.
+
+find_path(ZLIB_INCLUDE_DIR
+  NAMES zlib.h
+  HINTS ${ZLIB_ROOT_DIR}/include)
+
+find_library(ZLIB_LIBRARIES
+  NAMES z
+  HINTS ${ZLIB_ROOT_DIR}/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(zlib DEFAULT_MSG ZLIB_LIBRARIES ZLIB_INCLUDE_DIR)
+
+mark_as_advanced(
+  ZLIB_LIBRARIES
+  ZLIB_INCLUDE_DIR)

cmake/modules/Findzstd.cmake

@@ -1,29 +1,21 @@
 # - Find zstd
 # Find the zstd compression library and includes
 #
-# zstd_INCLUDE_DIRS - where to find zstd.h, etc.
-# zstd_LIBRARIES - List of libraries when using zstd.
-# zstd_FOUND - True if zstd found.
+# 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_DIRS
+find_path(ZSTD_INCLUDE_DIR
   NAMES zstd.h
-  HINTS ${zstd_ROOT_DIR}/include)
+  HINTS ${ZSTD_ROOT_DIR}/include)
 
-find_library(zstd_LIBRARIES
+find_library(ZSTD_LIBRARIES
   NAMES zstd
-  HINTS ${zstd_ROOT_DIR}/lib)
+  HINTS ${ZSTD_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(zstd DEFAULT_MSG zstd_LIBRARIES zstd_INCLUDE_DIRS)
+find_package_handle_standard_args(zstd DEFAULT_MSG ZSTD_LIBRARIES ZSTD_INCLUDE_DIR)
 
 mark_as_advanced(
-  zstd_LIBRARIES
-  zstd_INCLUDE_DIRS)
-
-if(zstd_FOUND AND NOT (TARGET zstd::zstd))
-  add_library (zstd::zstd UNKNOWN IMPORTED)
-  set_target_properties(zstd::zstd
-    PROPERTIES
-      IMPORTED_LOCATION ${zstd_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${zstd_INCLUDE_DIRS})
-endif()
+  ZSTD_LIBRARIES
+  ZSTD_INCLUDE_DIR)

cmake/modules/ReadVersion.cmake

@@ -1,10 +0,0 @@
-# Read rocksdb version from version.h header file.
-
-function(get_rocksdb_version version_var)
-  file(READ "${CMAKE_CURRENT_SOURCE_DIR}/include/rocksdb/version.h" version_header_file)
-  foreach(component MAJOR MINOR PATCH)
-    string(REGEX MATCH "#define ROCKSDB_${component} ([0-9]+)" _ ${version_header_file})
-    set(ROCKSDB_VERSION_${component} ${CMAKE_MATCH_1})
-  endforeach()
-  set(${version_var} "${ROCKSDB_VERSION_MAJOR}.${ROCKSDB_VERSION_MINOR}.${ROCKSDB_VERSION_PATCH}" PARENT_SCOPE)
-endfunction()

coverage/coverage_test.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 # Exit on error.
 set -e

coverage/parse_gcov_output.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python2
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+import optparse
 import re
 import sys
 

db/arena_wrapped_db_iter.cc

@@ -1,106 +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/arena_wrapped_db_iter.h"
-#include "memory/arena.h"
-#include "rocksdb/env.h"
-#include "rocksdb/iterator.h"
-#include "rocksdb/options.h"
-#include "table/internal_iterator.h"
-#include "table/iterator_wrapper.h"
-#include "util/user_comparator_wrapper.h"
-
-namespace rocksdb {
-
-Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
-                                       std::string* prop) {
-  if (prop_name == "rocksdb.iterator.super-version-number") {
-    // First try to pass the value returned from inner iterator.
-    if (!db_iter_->GetProperty(prop_name, prop).ok()) {
-      *prop = ToString(sv_number_);
-    }
-    return Status::OK();
-  }
-  return db_iter_->GetProperty(prop_name, prop);
-}
-
-void ArenaWrappedDBIter::Init(Env* env, const ReadOptions& read_options,
-                              const ImmutableCFOptions& cf_options,
-                              const MutableCFOptions& mutable_cf_options,
-                              const SequenceNumber& sequence,
-                              uint64_t max_sequential_skip_in_iteration,
-                              uint64_t version_number,
-                              ReadCallback* read_callback, DBImpl* db_impl,
-                              ColumnFamilyData* cfd, bool allow_blob,
-                              bool allow_refresh) {
-  auto mem = arena_.AllocateAligned(sizeof(DBIter));
-  db_iter_ = new (mem) DBIter(env, read_options, cf_options, mutable_cf_options,
-                              cf_options.user_comparator, nullptr, sequence,
-                              true, max_sequential_skip_in_iteration,
-                              read_callback, db_impl, cfd, allow_blob);
-  sv_number_ = version_number;
-  allow_refresh_ = allow_refresh;
-}
-
-Status ArenaWrappedDBIter::Refresh() {
-  if (cfd_ == nullptr || db_impl_ == nullptr || !allow_refresh_) {
-    return Status::NotSupported("Creating renew iterator is not allowed.");
-  }
-  assert(db_iter_ != nullptr);
-  // TODO(yiwu): For last_seq_same_as_publish_seq_==false, this is not the
-  // correct behavior. Will be corrected automatically when we take a snapshot
-  // here for the case of WritePreparedTxnDB.
-  SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
-  uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
-  if (sv_number_ != cur_sv_number) {
-    Env* env = db_iter_->env();
-    db_iter_->~DBIter();
-    arena_.~Arena();
-    new (&arena_) Arena();
-
-    SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
-    if (read_callback_) {
-      read_callback_->Refresh(latest_seq);
-    }
-    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
-         latest_seq, sv->mutable_cf_options.max_sequential_skip_in_iterations,
-         cur_sv_number, read_callback_, db_impl_, cfd_, allow_blob_,
-         allow_refresh_);
-
-    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
-        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
-        latest_seq);
-    SetIterUnderDBIter(internal_iter);
-  } else {
-    db_iter_->set_sequence(latest_seq);
-    db_iter_->set_valid(false);
-  }
-  return Status::OK();
-}
-
-ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-    bool allow_blob, bool allow_refresh) {
-  ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
-  iter->Init(env, read_options, cf_options, mutable_cf_options, sequence,
-             max_sequential_skip_in_iterations, version_number, read_callback,
-             db_impl, cfd, allow_blob, allow_refresh);
-  if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
-    iter->StoreRefreshInfo(read_options, db_impl, cfd, read_callback,
-                           allow_blob);
-  }
-
-  return iter;
-}
-
-}  // namespace rocksdb

db/arena_wrapped_db_iter.h

@@ -1,112 +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
-#include <stdint.h>
-#include <string>
-#include "db/db_impl/db_impl.h"
-#include "db/db_iter.h"
-#include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
-#include "memory/arena.h"
-#include "options/cf_options.h"
-#include "rocksdb/db.h"
-#include "rocksdb/iterator.h"
-#include "util/autovector.h"
-
-namespace rocksdb {
-
-class Arena;
-
-// A wrapper iterator which wraps DB Iterator and the arena, with which the DB
-// iterator is supposed to be allocated. This class is used as an entry point of
-// a iterator hierarchy whose memory can be allocated inline. In that way,
-// accessing the iterator tree can be more cache friendly. It is also faster
-// to allocate.
-// When using the class's Iterator interface, the behavior is exactly
-// the same as the inner DBIter.
-class ArenaWrappedDBIter : public Iterator {
- public:
-  virtual ~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
-
-  // Get the arena to be used to allocate memory for DBIter to be wrapped,
-  // as well as child iterators in it.
-  virtual Arena* GetArena() { return &arena_; }
-  virtual ReadRangeDelAggregator* GetRangeDelAggregator() {
-    return db_iter_->GetRangeDelAggregator();
-  }
-
-  // Set the internal iterator wrapped inside the DB Iterator. Usually it is
-  // a merging iterator.
-  virtual void SetIterUnderDBIter(InternalIterator* iter) {
-    static_cast<DBIter*>(db_iter_)->SetIter(iter);
-  }
-
-  virtual bool Valid() const override { return db_iter_->Valid(); }
-  virtual void SeekToFirst() override { db_iter_->SeekToFirst(); }
-  virtual void SeekToLast() override { db_iter_->SeekToLast(); }
-  virtual void Seek(const Slice& target) override { db_iter_->Seek(target); }
-  virtual void SeekForPrev(const Slice& target) override {
-    db_iter_->SeekForPrev(target);
-  }
-  virtual void Next() override { db_iter_->Next(); }
-  virtual void Prev() override { db_iter_->Prev(); }
-  virtual Slice key() const override { return db_iter_->key(); }
-  virtual Slice value() const override { return db_iter_->value(); }
-  virtual Status status() const override { return db_iter_->status(); }
-  bool IsBlob() const { return db_iter_->IsBlob(); }
-
-  virtual Status GetProperty(std::string prop_name, std::string* prop) override;
-
-  virtual Status Refresh() override;
-
-  void Init(Env* env, const ReadOptions& read_options,
-            const ImmutableCFOptions& cf_options,
-            const MutableCFOptions& mutable_cf_options,
-            const SequenceNumber& sequence,
-            uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-            ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-            bool allow_blob, bool allow_refresh);
-
-  // Store some parameters so we can refresh the iterator at a later point
-  // with these same params
-  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 MutableCFOptions& mutable_cf_options, 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);
-}  // namespace rocksdb

db/builder.cc

@@ -13,17 +13,13 @@
 #include <deque>
 #include <vector>
 
-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
-#include "db/range_del_aggregator.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
-#include "file/filename.h"
-#include "file/read_write_util.h"
-#include "file/writable_file_writer.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -31,47 +27,43 @@
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block_based_table_builder.h"
-#include "table/format.h"
+#include "table/block_based_table_builder.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
+#include "util/file_reader_writer.h"
+#include "util/filename.h"
 #include "util/stop_watch.h"
+#include "util/sync_point.h"
 
 namespace rocksdb {
 
 class TableFactory;
 
 TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
+    const ImmutableCFOptions& ioptions,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
     WritableFileWriter* file, const CompressionType compression_type,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    int level, const bool skip_filters, const uint64_t creation_time,
-    const uint64_t oldest_key_time, const uint64_t target_file_size,
-    const uint64_t file_creation_time) {
+    const CompressionOptions& compression_opts, int level,
+    const std::string* compression_dict, const bool skip_filters,
+    const uint64_t creation_time, const uint64_t oldest_key_time) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
   return ioptions.table_factory->NewTableBuilder(
-      TableBuilderOptions(ioptions, moptions, internal_comparator,
-                          int_tbl_prop_collector_factories, compression_type,
-                          sample_for_compression, compression_opts,
-                          skip_filters, column_family_name, level,
-                          creation_time, oldest_key_time, target_file_size,
-                          file_creation_time),
+      TableBuilderOptions(
+          ioptions, internal_comparator, int_tbl_prop_collector_factories,
+          compression_type, compression_opts, compression_dict, skip_filters,
+          column_family_name, level, creation_time, oldest_key_time),
       column_family_id, file);
 }
 
 Status BuildTable(
-    const std::string& dbname, Env* env, FileSystem* fs,
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, const FileOptions& file_options,
-    TableCache* table_cache, InternalIterator* iter,
-    std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
-        range_del_iters,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
+    const MutableCFOptions& /*mutable_cf_options*/,
+    const EnvOptions& env_options, TableCache* table_cache,
+    InternalIterator* iter, std::unique_ptr<InternalIterator> range_del_iter,
     FileMetaData* meta, const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
@@ -79,12 +71,11 @@ Status BuildTable(
     std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     SnapshotChecker* snapshot_checker, const CompressionType compression,
-    uint64_t sample_for_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, const uint64_t file_creation_time) {
+    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) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
@@ -93,13 +84,15 @@ Status BuildTable(
   Status s;
   meta->fd.file_size = 0;
   iter->SeekToFirst();
-  std::unique_ptr<CompactionRangeDelAggregator> range_del_agg(
-      new CompactionRangeDelAggregator(&internal_comparator, snapshots));
-  for (auto& range_del_iter : range_del_iters) {
-    range_del_agg->AddTombstones(std::move(range_del_iter));
+  std::unique_ptr<RangeDelAggregator> range_del_agg(
+      new RangeDelAggregator(internal_comparator, snapshots));
+  s = range_del_agg->AddTombstones(std::move(range_del_iter));
+  if (!s.ok()) {
+    // may be non-ok if a range tombstone key is unparsable
+    return s;
   }
 
-  std::string fname = TableFileName(ioptions.cf_paths, meta->fd.GetNumber(),
+  std::string fname = TableFileName(ioptions.db_paths, meta->fd.GetNumber(),
                                     meta->fd.GetPathId());
 #ifndef ROCKSDB_LITE
   EventHelpers::NotifyTableFileCreationStarted(
@@ -107,40 +100,32 @@ Status BuildTable(
 #endif  // !ROCKSDB_LITE
   TableProperties tp;
 
-  if (iter->Valid() || !range_del_agg->IsEmpty()) {
+  if (iter->Valid() || range_del_agg->ShouldAddTombstones()) {
     TableBuilder* builder;
-    std::unique_ptr<WritableFileWriter> file_writer;
-    // Currently we only enable dictionary compression during compaction to the
-    // bottommost level.
-    CompressionOptions compression_opts_for_flush(compression_opts);
-    compression_opts_for_flush.max_dict_bytes = 0;
-    compression_opts_for_flush.zstd_max_train_bytes = 0;
+    unique_ptr<WritableFileWriter> file_writer;
     {
-      std::unique_ptr<FSWritableFile> file;
+      unique_ptr<WritableFile> file;
 #ifndef NDEBUG
-      bool use_direct_writes = file_options.use_direct_writes;
+      bool use_direct_writes = env_options.use_direct_writes;
       TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
 #endif  // !NDEBUG
-      s = NewWritableFile(fs, fname, &file, file_options);
+      s = NewWritableFile(env, fname, &file, env_options);
       if (!s.ok()) {
         EventHelpers::LogAndNotifyTableFileCreationFinished(
             event_logger, ioptions.listeners, dbname, column_family_name, fname,
-            job_id, meta->fd, kInvalidBlobFileNumber, tp, reason, s);
+            job_id, meta->fd, tp, reason, s);
         return s;
       }
       file->SetIOPriority(io_priority);
       file->SetWriteLifeTimeHint(write_hint);
 
-      file_writer.reset(
-          new WritableFileWriter(std::move(file), fname, file_options, env,
-                                 ioptions.statistics, ioptions.listeners));
+      file_writer.reset(new WritableFileWriter(std::move(file), env_options,
+                                               ioptions.statistics));
       builder = NewTableBuilder(
-          ioptions, mutable_cf_options, internal_comparator,
-          int_tbl_prop_collector_factories, column_family_id,
-          column_family_name, file_writer.get(), compression,
-          sample_for_compression, compression_opts_for_flush, level,
-          false /* skip_filters */, creation_time, oldest_key_time,
-          0 /*target_file_size*/, file_creation_time);
+          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);
     }
 
     MergeHelper merge(env, internal_comparator.user_comparator(),
@@ -152,15 +137,13 @@ Status BuildTable(
     CompactionIterator c_iter(
         iter, internal_comparator.user_comparator(), &merge, kMaxSequenceNumber,
         &snapshots, earliest_write_conflict_snapshot, snapshot_checker, env,
-        ShouldReportDetailedTime(env, ioptions.statistics),
         true /* internal key corruption is not ok */, range_del_agg.get());
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
-      const ParsedInternalKey& ikey = c_iter.ikey();
       builder->Add(key, value);
-      meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
+      meta->UpdateBoundaries(key, c_iter.ikey().sequence);
 
       // TODO(noetzli): Update stats after flush, too.
       if (io_priority == Env::IO_HIGH &&
@@ -169,20 +152,12 @@ Status BuildTable(
             ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
       }
     }
-
-    auto range_del_it = range_del_agg->NewIterator();
-    for (range_del_it->SeekToFirst(); range_del_it->Valid();
-         range_del_it->Next()) {
-      auto tombstone = range_del_it->Tombstone();
-      auto kv = tombstone.Serialize();
-      builder->Add(kv.first.Encode(), kv.second);
-      meta->UpdateBoundariesForRange(kv.first, tombstone.SerializeEndKey(),
-                                     tombstone.seq_, internal_comparator);
-    }
+    // nullptr for table_{min,max} so all range tombstones will be flushed
+    range_del_agg->AddToBuilder(builder, nullptr /* lower_bound */,
+                                nullptr /* upper_bound */, meta);
 
     // Finish and check for builder errors
-    tp = builder->GetTableProperties();
-    bool empty = builder->NumEntries() == 0 && tp.num_range_deletions == 0;
+    bool empty = builder->NumEntries() == 0;
     s = c_iter.status();
     if (!s.ok() || empty) {
       builder->Abandon();
@@ -195,7 +170,7 @@ Status BuildTable(
       meta->fd.file_size = file_size;
       meta->marked_for_compaction = builder->NeedCompact();
       assert(meta->fd.GetFileSize() > 0);
-      tp = builder->GetTableProperties(); // refresh now that builder is finished
+      tp = builder->GetTableProperties();
       if (table_properties) {
         *table_properties = tp;
       }
@@ -219,14 +194,12 @@ Status BuildTable(
       // 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(), file_options, internal_comparator, *meta,
-          nullptr /* range_del_agg */,
-          mutable_cf_options.prefix_extractor.get(), nullptr,
+          ReadOptions(), env_options, internal_comparator, meta->fd,
+          nullptr /* range_del_agg */, nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : internal_stats->GetFileReadHist(0),
-          TableReaderCaller::kFlush, /*arena=*/nullptr,
-          /*skip_filter=*/false, level, /*smallest_compaction_key=*/nullptr,
-          /*largest_compaction_key*/ nullptr));
+          false /* for_compaction */, nullptr /* arena */,
+          false /* skip_filter */, level));
       s = it->status();
       if (s.ok() && paranoid_file_checks) {
         for (it->SeekToFirst(); it->Valid(); it->Next()) {
@@ -242,16 +215,13 @@ Status BuildTable(
   }
 
   if (!s.ok() || meta->fd.GetFileSize() == 0) {
-    fs->DeleteFile(fname, IOOptions(), nullptr);
+    env->DeleteFile(fname);
   }
 
-  if (meta->fd.GetFileSize() == 0) {
-    fname = "(nil)";
-  }
   // Output to event logger and fire events.
   EventHelpers::LogAndNotifyTableFileCreationFinished(
       event_logger, ioptions.listeners, dbname, column_family_name, fname,
-      job_id, meta->fd, meta->oldest_blob_file_number, tp, reason, s);
+      job_id, meta->fd, tp, reason, s);
 
   return s;
 }

db/builder.h

@@ -9,9 +9,7 @@
 #include <string>
 #include <utility>
 #include <vector>
-#include "db/range_tombstone_fragmenter.h"
 #include "db/table_properties_collector.h"
-#include "logging/event_logger.h"
 #include "options/cf_options.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/env.h"
@@ -21,6 +19,7 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/event_logger.h"
 
 namespace rocksdb {
 
@@ -36,22 +35,24 @@ class VersionEdit;
 class TableBuilder;
 class WritableFileWriter;
 class InternalStats;
+class InternalIterator;
 
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown. It must outlive the
 //    TableBuilder returned by this function.
+// @param compression_dict Data for presetting the compression library's
+//    dictionary, or nullptr.
 TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& options, const MutableCFOptions& moptions,
+    const ImmutableCFOptions& options,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
     WritableFileWriter* file, const CompressionType compression_type,
-    const uint64_t sample_for_compression,
     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 uint64_t target_file_size = 0,
-    const uint64_t file_creation_time = 0);
+    const uint64_t oldest_key_time = 0);
 
 // Build a Table file from the contents of *iter.  The generated file
 // will be named according to number specified in meta. On success, the rest of
@@ -62,27 +63,23 @@ TableBuilder* NewTableBuilder(
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown.
 extern Status BuildTable(
-    const std::string& dbname, Env* env, FileSystem* fs,
-    const ImmutableCFOptions& options,
-    const MutableCFOptions& mutable_cf_options, const FileOptions& file_options,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& options,
+    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
-    std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
-        range_del_iters,
-    FileMetaData* meta, const InternalKeyComparator& internal_comparator,
+    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
+    const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     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 uint64_t sample_for_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,
-    const uint64_t file_creation_time = 0);
+    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET);
 
 }  // namespace rocksdb

db/c.cc

@@ -33,7 +33,6 @@
 #include "rocksdb/utilities/backupable_db.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/db_ttl.h"
-#include "rocksdb/utilities/memory_util.h"
 #include "rocksdb/utilities/optimistic_transaction_db.h"
 #include "rocksdb/utilities/transaction.h"
 #include "rocksdb/utilities/transaction_db.h"
@@ -42,10 +41,6 @@
 #include "rocksdb/perf_context.h"
 #include "utilities/merge_operators.h"
 
-#include <vector>
-#include <unordered_set>
-#include <map>
-
 using rocksdb::BytewiseComparator;
 using rocksdb::Cache;
 using rocksdb::ColumnFamilyDescriptor;
@@ -95,10 +90,8 @@ using rocksdb::LiveFileMetaData;
 using rocksdb::BackupEngine;
 using rocksdb::BackupableDBOptions;
 using rocksdb::BackupInfo;
-using rocksdb::BackupID;
 using rocksdb::RestoreOptions;
 using rocksdb::CompactRangeOptions;
-using rocksdb::BottommostLevelCompaction;
 using rocksdb::RateLimiter;
 using rocksdb::NewGenericRateLimiter;
 using rocksdb::PinnableSlice;
@@ -109,16 +102,10 @@ using rocksdb::OptimisticTransactionDB;
 using rocksdb::OptimisticTransactionOptions;
 using rocksdb::Transaction;
 using rocksdb::Checkpoint;
-using rocksdb::TransactionLogIterator;
-using rocksdb::BatchResult;
 using rocksdb::PerfLevel;
 using rocksdb::PerfContext;
-using rocksdb::MemoryUtil;
 
 using std::shared_ptr;
-using std::vector;
-using std::unordered_set;
-using std::map;
 
 extern "C" {
 
@@ -148,23 +135,15 @@ struct rocksdb_cuckoo_table_options_t  { CuckooTableOptions rep; };
 struct rocksdb_seqfile_t         { SequentialFile*   rep; };
 struct rocksdb_randomfile_t      { RandomAccessFile* rep; };
 struct rocksdb_writablefile_t    { WritableFile*     rep; };
-struct rocksdb_wal_iterator_t { TransactionLogIterator* rep; };
-struct rocksdb_wal_readoptions_t { TransactionLogIterator::ReadOptions rep; };
 struct rocksdb_filelock_t        { FileLock*         rep; };
-struct rocksdb_logger_t {
-  std::shared_ptr<Logger> rep;
-};
-struct rocksdb_cache_t {
-  std::shared_ptr<Cache> rep;
-};
+struct rocksdb_logger_t          { shared_ptr<Logger>  rep; };
+struct rocksdb_cache_t           { shared_ptr<Cache>   rep; };
 struct rocksdb_livefiles_t       { std::vector<LiveFileMetaData> rep; };
 struct rocksdb_column_family_handle_t  { ColumnFamilyHandle* rep; };
 struct rocksdb_envoptions_t      { EnvOptions        rep; };
 struct rocksdb_ingestexternalfileoptions_t  { IngestExternalFileOptions rep; };
 struct rocksdb_sstfilewriter_t   { SstFileWriter*    rep; };
-struct rocksdb_ratelimiter_t {
-  std::shared_ptr<RateLimiter> rep;
-};
+struct rocksdb_ratelimiter_t     { RateLimiter*      rep; };
 struct rocksdb_perfcontext_t     { PerfContext*      rep; };
 struct rocksdb_pinnableslice_t {
   PinnableSlice rep;
@@ -208,10 +187,13 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
   const char* (*name_)(void*);
   unsigned char ignore_snapshots_;
 
-  ~rocksdb_compactionfilter_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_compactionfilter_t() {
+    (*destructor_)(state_);
+  }
 
-  bool Filter(int level, const Slice& key, const Slice& existing_value,
-              std::string* new_value, bool* value_changed) const override {
+  virtual bool Filter(int level, const Slice& key, const Slice& existing_value,
+                      std::string* new_value,
+                      bool* value_changed) const override {
     char* c_new_value = nullptr;
     size_t new_value_length = 0;
     unsigned char c_value_changed = 0;
@@ -228,9 +210,9 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
     return result;
   }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  bool IgnoreSnapshots() const override { return ignore_snapshots_; }
+  virtual bool IgnoreSnapshots() const override { return ignore_snapshots_; }
 };
 
 struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
@@ -240,9 +222,9 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
       void*, rocksdb_compactionfiltercontext_t* context);
   const char* (*name_)(void*);
 
-  ~rocksdb_compactionfilterfactory_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_compactionfilterfactory_t() { (*destructor_)(state_); }
 
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
       const CompactionFilter::Context& context) override {
     rocksdb_compactionfiltercontext_t ccontext;
     ccontext.rep = context;
@@ -250,7 +232,7 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
     return std::unique_ptr<CompactionFilter>(cf);
   }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 };
 
 struct rocksdb_comparator_t : public Comparator {
@@ -262,17 +244,20 @@ struct rocksdb_comparator_t : public Comparator {
       const char* b, size_t blen);
   const char* (*name_)(void*);
 
-  ~rocksdb_comparator_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_comparator_t() {
+    (*destructor_)(state_);
+  }
 
-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
     return (*compare_)(state_, a.data(), a.size(), b.data(), b.size());
   }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
   // No-ops since the C binding does not support key shortening methods.
-  void FindShortestSeparator(std::string*, const Slice&) const override {}
-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortestSeparator(std::string*,
+                                     const Slice&) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 
 struct rocksdb_filterpolicy_t : public FilterPolicy {
@@ -292,11 +277,14 @@ struct rocksdb_filterpolicy_t : public FilterPolicy {
       void*,
       const char* filter, size_t filter_length);
 
-  ~rocksdb_filterpolicy_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_filterpolicy_t() {
+    (*destructor_)(state_);
+  }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  void CreateFilter(const Slice* keys, int n, std::string* dst) const override {
+  virtual void CreateFilter(const Slice* keys, int n,
+                            std::string* dst) const override {
     std::vector<const char*> key_pointers(n);
     std::vector<size_t> key_sizes(n);
     for (int i = 0; i < n; i++) {
@@ -314,7 +302,8 @@ struct rocksdb_filterpolicy_t : public FilterPolicy {
     }
   }
 
-  bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
+  virtual bool KeyMayMatch(const Slice& key,
+                           const Slice& filter) const override {
     return (*key_match_)(state_, key.data(), key.size(),
                          filter.data(), filter.size());
   }
@@ -339,12 +328,14 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
       void*,
       const char* value, size_t value_length);
 
-  ~rocksdb_mergeoperator_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_mergeoperator_t() {
+    (*destructor_)(state_);
+  }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  bool FullMergeV2(const MergeOperationInput& merge_in,
-                   MergeOperationOutput* merge_out) const override {
+  virtual bool FullMergeV2(const MergeOperationInput& merge_in,
+                           MergeOperationOutput* merge_out) const override {
     size_t n = merge_in.operand_list.size();
     std::vector<const char*> operand_pointers(n);
     std::vector<size_t> operand_sizes(n);
@@ -378,10 +369,10 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
     return success;
   }
 
-  bool PartialMergeMulti(const Slice& key,
-                         const std::deque<Slice>& operand_list,
-                         std::string* new_value,
-                         Logger* /*logger*/) const override {
+  virtual bool PartialMergeMulti(const Slice& key,
+                                 const std::deque<Slice>& operand_list,
+                                 std::string* new_value,
+                                 Logger* /*logger*/) const override {
     size_t operand_count = operand_list.size();
     std::vector<const char*> operand_pointers(operand_count);
     std::vector<size_t> operand_sizes(operand_count);
@@ -432,21 +423,23 @@ struct rocksdb_slicetransform_t : public SliceTransform {
       void*,
       const char* key, size_t length);
 
-  ~rocksdb_slicetransform_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_slicetransform_t() {
+    (*destructor_)(state_);
+  }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  Slice Transform(const Slice& src) const override {
+  virtual Slice Transform(const Slice& src) const override {
     size_t len;
     char* dst = (*transform_)(state_, src.data(), src.size(), &len);
     return Slice(dst, len);
   }
 
-  bool InDomain(const Slice& src) const override {
+  virtual bool InDomain(const Slice& src) const override {
     return (*in_domain_)(state_, src.data(), src.size());
   }
 
-  bool InRange(const Slice& src) const override {
+  virtual bool InRange(const Slice& src) const override {
     return (*in_range_)(state_, src.data(), src.size());
   }
 };
@@ -517,21 +510,6 @@ rocksdb_t* rocksdb_open_for_read_only(
   return result;
 }
 
-rocksdb_t* rocksdb_open_as_secondary(const rocksdb_options_t* options,
-                                     const char* name,
-                                     const char* secondary_path,
-                                     char** errptr) {
-  DB* db;
-  if (SaveError(errptr,
-                DB::OpenAsSecondary(options->rep, std::string(name),
-                                    std::string(secondary_path), &db))) {
-    return nullptr;
-  }
-  rocksdb_t* result = new rocksdb_t;
-  result->rep = db;
-  return result;
-}
-
 rocksdb_backup_engine_t* rocksdb_backup_engine_open(
     const rocksdb_options_t* options, const char* path, char** errptr) {
   BackupEngine* be;
@@ -549,18 +527,10 @@ rocksdb_backup_engine_t* rocksdb_backup_engine_open(
 }
 
 void rocksdb_backup_engine_create_new_backup(rocksdb_backup_engine_t* be,
-                                             rocksdb_t* db,
-                                             char** errptr) {
+                                             rocksdb_t* db, char** errptr) {
   SaveError(errptr, be->rep->CreateNewBackup(db->rep));
 }
 
-void rocksdb_backup_engine_create_new_backup_flush(rocksdb_backup_engine_t* be,
-                                                   rocksdb_t* db,
-                                                   unsigned char flush_before_backup,
-                                                   char** errptr) {
-  SaveError(errptr, be->rep->CreateNewBackup(db->rep, flush_before_backup));
-}
-
 void rocksdb_backup_engine_purge_old_backups(rocksdb_backup_engine_t* be,
                                              uint32_t num_backups_to_keep,
                                              char** errptr) {
@@ -580,12 +550,6 @@ void rocksdb_restore_options_set_keep_log_files(rocksdb_restore_options_t* opt,
   opt->rep.keep_log_files = v;
 }
 
-
-void rocksdb_backup_engine_verify_backup(rocksdb_backup_engine_t* be,
-    uint32_t backup_id, char** errptr) {
-  SaveError(errptr, be->rep->VerifyBackup(static_cast<BackupID>(backup_id)));
-}
-
 void rocksdb_backup_engine_restore_db_from_latest_backup(
     rocksdb_backup_engine_t* be, const char* db_dir, const char* wal_dir,
     const rocksdb_restore_options_t* restore_options, char** errptr) {
@@ -732,37 +696,6 @@ rocksdb_t* rocksdb_open_for_read_only_column_families(
   return result;
 }
 
-rocksdb_t* rocksdb_open_as_secondary_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    const char* secondary_path, int num_column_families,
-    const char** column_family_names,
-    const rocksdb_options_t** column_family_options,
-    rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
-  std::vector<ColumnFamilyDescriptor> column_families;
-  for (int i = 0; i != num_column_families; ++i) {
-    column_families.emplace_back(
-        std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
-  }
-  DB* db;
-  std::vector<ColumnFamilyHandle*> handles;
-  if (SaveError(errptr, DB::OpenAsSecondary(DBOptions(db_options->rep),
-                                            std::string(name),
-                                            std::string(secondary_path),
-                                            column_families, &handles, &db))) {
-    return nullptr;
-  }
-  for (size_t i = 0; i != handles.size(); ++i) {
-    rocksdb_column_family_handle_t* c_handle =
-        new rocksdb_column_family_handle_t;
-    c_handle->rep = handles[i];
-    column_family_handles[i] = c_handle;
-  }
-  rocksdb_t* result = new rocksdb_t;
-  result->rep = db;
-  return result;
-}
-
 char** rocksdb_list_column_families(
     const rocksdb_options_t* options,
     const char* name,
@@ -852,17 +785,6 @@ void rocksdb_delete_cf(
         Slice(key, keylen)));
 }
 
-void rocksdb_delete_range_cf(rocksdb_t* db,
-                             const rocksdb_writeoptions_t* options,
-                             rocksdb_column_family_handle_t* column_family,
-                             const char* start_key, size_t start_key_len,
-                             const char* end_key, size_t end_key_len,
-                             char** errptr) {
-  SaveError(errptr, db->rep->DeleteRange(options->rep, column_family->rep,
-                                         Slice(start_key, start_key_len),
-                                         Slice(end_key, end_key_len)));
-}
-
 void rocksdb_merge(
     rocksdb_t* db,
     const rocksdb_writeoptions_t* options,
@@ -1008,54 +930,6 @@ rocksdb_iterator_t* rocksdb_create_iterator(
   return result;
 }
 
-rocksdb_wal_iterator_t* rocksdb_get_updates_since(
-        rocksdb_t* db, uint64_t seq_number,
-        const rocksdb_wal_readoptions_t* options,
-        char** errptr) {
-  std::unique_ptr<TransactionLogIterator> iter;
-  TransactionLogIterator::ReadOptions ro;
-  if (options!=nullptr) {
-      ro = options->rep;
-  }
-  if (SaveError(errptr, db->rep->GetUpdatesSince(seq_number, &iter, ro))) {
-    return nullptr;
-  }
-  rocksdb_wal_iterator_t* result = new rocksdb_wal_iterator_t;
-  result->rep = iter.release();
-  return result;
-}
-
-void rocksdb_wal_iter_next(rocksdb_wal_iterator_t* iter) {
-    iter->rep->Next();
-}
-
-unsigned char rocksdb_wal_iter_valid(const rocksdb_wal_iterator_t* iter) {
-    return iter->rep->Valid();
-}
-
-void rocksdb_wal_iter_status (const rocksdb_wal_iterator_t* iter, char** errptr) {
-    SaveError(errptr, iter->rep->status());
-}
-
-void rocksdb_wal_iter_destroy (const rocksdb_wal_iterator_t* iter) {
-  delete iter->rep;
-  delete iter;
-}
-
-rocksdb_writebatch_t* rocksdb_wal_iter_get_batch (const rocksdb_wal_iterator_t* iter, uint64_t* seq) {
-  rocksdb_writebatch_t* result = rocksdb_writebatch_create();
-  BatchResult wal_batch = iter->rep->GetBatch();
-  result->rep = std::move(*wal_batch.writeBatchPtr);
-  if (seq != nullptr) {
-    *seq = wal_batch.sequence;
-  }
-  return result;
-}
-
-uint64_t rocksdb_get_latest_sequence_number (rocksdb_t *db) {
-    return db->rep->GetLatestSequenceNumber();
-}
-
 rocksdb_iterator_t* rocksdb_create_iterator_cf(
     rocksdb_t* db,
     const rocksdb_readoptions_t* options,
@@ -1127,18 +1001,6 @@ int rocksdb_property_int(
   }
 }
 
-int rocksdb_property_int_cf(
-    rocksdb_t* db,
-    rocksdb_column_family_handle_t* column_family,
-    const char* propname,
-    uint64_t *out_val) {
-  if (db->rep->GetIntProperty(column_family->rep, Slice(propname), out_val)) {
-    return 0;
-  } else {
-    return -1;
-  }
-}
-
 char* rocksdb_property_value_cf(
     rocksdb_t* db,
     rocksdb_column_family_handle_t* column_family,
@@ -1252,14 +1114,6 @@ void rocksdb_flush(
   SaveError(errptr, db->rep->Flush(options->rep));
 }
 
-void rocksdb_flush_cf(
-    rocksdb_t* db,
-    const rocksdb_flushoptions_t* options,
-    rocksdb_column_family_handle_t* column_family,
-    char** errptr) {
-  SaveError(errptr, db->rep->Flush(options->rep, column_family->rep));
-}
-
 void rocksdb_disable_file_deletions(
     rocksdb_t* db,
     char** errptr) {
@@ -1553,24 +1407,23 @@ void rocksdb_writebatch_put_log_data(
   b->rep.PutLogData(Slice(blob, len));
 }
 
-class H : public WriteBatch::Handler {
- public:
-  void* state_;
-  void (*put_)(void*, const char* k, size_t klen, const char* v, size_t vlen);
-  void (*deleted_)(void*, const char* k, size_t klen);
-  void Put(const Slice& key, const Slice& value) override {
-    (*put_)(state_, key.data(), key.size(), value.data(), value.size());
-  }
-  void Delete(const Slice& key) override {
-    (*deleted_)(state_, key.data(), key.size());
-  }
-};
-
 void rocksdb_writebatch_iterate(
     rocksdb_writebatch_t* b,
     void* state,
     void (*put)(void*, const char* k, size_t klen, const char* v, size_t vlen),
     void (*deleted)(void*, const char* k, size_t klen)) {
+  class H : public WriteBatch::Handler {
+   public:
+    void* state_;
+    void (*put_)(void*, const char* k, size_t klen, const char* v, size_t vlen);
+    void (*deleted_)(void*, const char* k, size_t klen);
+    virtual void Put(const Slice& key, const Slice& value) override {
+      (*put_)(state_, key.data(), key.size(), value.data(), value.size());
+    }
+    virtual void Delete(const Slice& key) override {
+      (*deleted_)(state_, key.data(), key.size());
+    }
+  };
   H handler;
   handler.state_ = state;
   handler.put_ = put;
@@ -1815,6 +1668,18 @@ void rocksdb_writebatch_wi_iterate(
     void* state,
     void (*put)(void*, const char* k, size_t klen, const char* v, size_t vlen),
     void (*deleted)(void*, const char* k, size_t klen)) {
+  class H : public WriteBatch::Handler {
+   public:
+    void* state_;
+    void (*put_)(void*, const char* k, size_t klen, const char* v, size_t vlen);
+    void (*deleted_)(void*, const char* k, size_t klen);
+    virtual void Put(const Slice& key, const Slice& value) override {
+      (*put_)(state_, key.data(), key.size(), value.data(), value.size());
+    }
+    virtual void Delete(const Slice& key) override {
+      (*deleted_)(state_, key.data(), key.size());
+    }
+  };
   H handler;
   handler.state_ = state;
   handler.put_ = put;
@@ -1847,11 +1712,11 @@ rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base(
 }
 
 rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base_cf(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
+    rocksdb_writebatch_wi_t* wbwi,
+    rocksdb_iterator_t* base_iterator,
     rocksdb_column_family_handle_t* column_family) {
   rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep =
-      wbwi->rep->NewIteratorWithBase(column_family->rep, base_iterator->rep);
+  result->rep = wbwi->rep->NewIteratorWithBase(column_family->rep, base_iterator->rep);
   delete base_iterator;
   return result;
 }
@@ -2043,17 +1908,6 @@ void rocksdb_block_based_options_set_index_type(
   options->rep.index_type = static_cast<BlockBasedTableOptions::IndexType>(v);
 }
 
-void rocksdb_block_based_options_set_data_block_index_type(
-    rocksdb_block_based_table_options_t* options, int v) {
-  options->rep.data_block_index_type =
-          static_cast<BlockBasedTableOptions::DataBlockIndexType>(v);
-}
-
-void rocksdb_block_based_options_set_data_block_hash_ratio(
-    rocksdb_block_based_table_options_t* options, double v) {
-  options->rep.data_block_hash_table_util_ratio = v;
-}
-
 void rocksdb_block_based_options_set_hash_index_allow_collision(
     rocksdb_block_based_table_options_t* options, unsigned char v) {
   options->rep.hash_index_allow_collision = v;
@@ -2074,11 +1928,6 @@ void rocksdb_block_based_options_set_pin_l0_filter_and_index_blocks_in_cache(
   options->rep.pin_l0_filter_and_index_blocks_in_cache = v;
 }
 
-void rocksdb_block_based_options_set_pin_top_level_index_and_filter(
-    rocksdb_block_based_table_options_t* options, unsigned char v) {
-  options->rep.pin_top_level_index_and_filter = v;
-}
-
 void rocksdb_options_set_block_based_table_factory(
     rocksdb_options_t *opt,
     rocksdb_block_based_table_options_t* table_options) {
@@ -2141,15 +1990,6 @@ void rocksdb_set_options(
             db->rep->SetOptions(options_map));
     }
 
-void rocksdb_set_options_cf(
-    rocksdb_t* db, rocksdb_column_family_handle_t* handle, int count, const char* const keys[], const char* const values[], char** errptr) {
-        std::unordered_map<std::string, std::string> options_map;
-        for (int i=0; i<count; i++)
-            options_map[keys[i]] = values[i];
-        SaveError(errptr,
-            db->rep->SetOptions(handle->rep, options_map));
-    }
-
 rocksdb_options_t* rocksdb_options_create() {
   return new rocksdb_options_t;
 }
@@ -2366,18 +2206,6 @@ void rocksdb_options_set_compression_per_level(rocksdb_options_t* opt,
   }
 }
 
-void rocksdb_options_set_bottommost_compression_options(rocksdb_options_t* opt,
-                                                        int w_bits, int level,
-                                                        int strategy,
-                                                        int max_dict_bytes,
-                                                        bool enabled) {
-  opt->rep.bottommost_compression_opts.window_bits = w_bits;
-  opt->rep.bottommost_compression_opts.level = level;
-  opt->rep.bottommost_compression_opts.strategy = strategy;
-  opt->rep.bottommost_compression_opts.max_dict_bytes = max_dict_bytes;
-  opt->rep.bottommost_compression_opts.enabled = enabled;
-}
-
 void rocksdb_options_set_compression_options(rocksdb_options_t* opt, int w_bits,
                                              int level, int strategy,
                                              int max_dict_bytes) {
@@ -2500,7 +2328,7 @@ void rocksdb_options_set_bytes_per_sync(
 
 void rocksdb_options_set_writable_file_max_buffer_size(rocksdb_options_t* opt,
                                                        uint64_t v) {
-  opt->rep.writable_file_max_buffer_size = static_cast<size_t>(v);
+  opt->rep.writable_file_max_buffer_size = v;
 }
 
 void rocksdb_options_set_allow_concurrent_memtable_write(rocksdb_options_t* opt,
@@ -2531,30 +2359,6 @@ void rocksdb_options_set_max_write_buffer_number_to_maintain(
   opt->rep.max_write_buffer_number_to_maintain = n;
 }
 
-void rocksdb_options_set_max_write_buffer_size_to_maintain(
-    rocksdb_options_t* opt, int64_t n) {
-  opt->rep.max_write_buffer_size_to_maintain = n;
-}
-
-void rocksdb_options_set_enable_pipelined_write(rocksdb_options_t* opt,
-                                                unsigned char v) {
-  opt->rep.enable_pipelined_write = v;
-}
-
-void rocksdb_options_set_unordered_write(rocksdb_options_t* opt,
-                                         unsigned char v) {
-  opt->rep.unordered_write = v;
-}
-
-void rocksdb_options_set_max_subcompactions(rocksdb_options_t* opt,
-                                            uint32_t n) {
-  opt->rep.max_subcompactions = n;
-}
-
-void rocksdb_options_set_max_background_jobs(rocksdb_options_t* opt, int n) {
-  opt->rep.max_background_jobs = n;
-}
-
 void rocksdb_options_set_max_background_compactions(rocksdb_options_t* opt, int n) {
   opt->rep.max_background_compactions = n;
 }
@@ -2731,9 +2535,8 @@ char *rocksdb_options_statistics_get_string(rocksdb_options_t *opt) {
 }
 
 void rocksdb_options_set_ratelimiter(rocksdb_options_t *opt, rocksdb_ratelimiter_t *limiter) {
-  if (limiter) {
-    opt->rep.rate_limiter = limiter->rep;
-  }
+  opt->rep.rate_limiter.reset(limiter->rep);
+  limiter->rep = nullptr;
 }
 
 rocksdb_ratelimiter_t* rocksdb_ratelimiter_create(
@@ -2741,13 +2544,15 @@ rocksdb_ratelimiter_t* rocksdb_ratelimiter_create(
     int64_t refill_period_us,
     int32_t fairness) {
   rocksdb_ratelimiter_t* rate_limiter = new rocksdb_ratelimiter_t;
-  rate_limiter->rep.reset(
-               NewGenericRateLimiter(rate_bytes_per_sec,
-                                     refill_period_us, fairness));
+  rate_limiter->rep = NewGenericRateLimiter(rate_bytes_per_sec,
+                                            refill_period_us, fairness);
   return rate_limiter;
 }
 
 void rocksdb_ratelimiter_destroy(rocksdb_ratelimiter_t *limiter) {
+  if (limiter->rep) {
+    delete limiter->rep;
+  }
   delete limiter;
 }
 
@@ -2950,7 +2755,7 @@ rocksdb_compactionfilter_t* rocksdb_compactionfilter_create(
   result->state_ = state;
   result->destructor_ = destructor;
   result->filter_ = filter;
-  result->ignore_snapshots_ = true;
+  result->ignore_snapshots_ = false;
   result->name_ = name;
   return result;
 }
@@ -3050,7 +2855,7 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
   // supplied C functions.
   struct Wrapper : public rocksdb_filterpolicy_t {
     const FilterPolicy* rep_;
-    ~Wrapper() override { delete rep_; }
+    ~Wrapper() { delete rep_; }
     const char* Name() const override { return rep_->Name(); }
     void CreateFilter(const Slice* keys, int n,
                       std::string* dst) const override {
@@ -3059,16 +2864,7 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
     bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
       return rep_->KeyMayMatch(key, filter);
     }
-    // No need to override GetFilterBitsBuilder if this one is overridden
-    rocksdb::FilterBitsBuilder* GetBuilderWithContext(
-        const rocksdb::FilterBuildingContext& context) const override {
-      return rep_->GetBuilderWithContext(context);
-    }
-    rocksdb::FilterBitsReader* GetFilterBitsReader(
-        const Slice& contents) const override {
-      return rep_->GetFilterBitsReader(contents);
-    }
-    static void DoNothing(void*) {}
+    static void DoNothing(void*) { }
   };
   Wrapper* wrapper = new Wrapper;
   wrapper->rep_ = NewBloomFilterPolicy(bits_per_key, original_format);
@@ -3250,11 +3046,6 @@ void rocksdb_writeoptions_set_low_pri(
   opt->rep.low_pri = v;
 }
 
-void rocksdb_writeoptions_set_memtable_insert_hint_per_batch(
-    rocksdb_writeoptions_t* opt, unsigned char v) {
-  opt->rep.memtable_insert_hint_per_batch = v;
-}
-
 rocksdb_compactoptions_t* rocksdb_compactoptions_create() {
   return new rocksdb_compactoptions_t;
 }
@@ -3263,11 +3054,6 @@ void rocksdb_compactoptions_destroy(rocksdb_compactoptions_t* opt) {
   delete opt;
 }
 
-void rocksdb_compactoptions_set_bottommost_level_compaction(
-    rocksdb_compactoptions_t* opt, unsigned char v) {
-  opt->rep.bottommost_level_compaction = static_cast<BottommostLevelCompaction>(v);
-}
-
 void rocksdb_compactoptions_set_exclusive_manual_compaction(
     rocksdb_compactoptions_t* opt, unsigned char v) {
   opt->rep.exclusive_manual_compaction = v;
@@ -3355,22 +3141,6 @@ void rocksdb_env_join_all_threads(rocksdb_env_t* env) {
   env->rep->WaitForJoin();
 }
 
-void rocksdb_env_lower_thread_pool_io_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolIOPriority();
-}
-
-void rocksdb_env_lower_high_priority_thread_pool_io_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolIOPriority(Env::HIGH);
-}
-
-void rocksdb_env_lower_thread_pool_cpu_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolCPUPriority();
-}
-
-void rocksdb_env_lower_high_priority_thread_pool_cpu_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolCPUPriority(Env::HIGH);
-}
-
 void rocksdb_env_destroy(rocksdb_env_t* env) {
   if (!env->is_default) delete env->rep;
   delete env;
@@ -3433,11 +3203,6 @@ void rocksdb_sstfilewriter_finish(rocksdb_sstfilewriter_t* writer,
   SaveError(errptr, writer->rep->Finish(nullptr));
 }
 
-void rocksdb_sstfilewriter_file_size(rocksdb_sstfilewriter_t* writer,
-                                  uint64_t* file_size) {
-  *file_size = writer->rep->FileSize();
-}
-
 void rocksdb_sstfilewriter_destroy(rocksdb_sstfilewriter_t* writer) {
   delete writer->rep;
   delete writer;
@@ -3505,10 +3270,6 @@ void rocksdb_ingest_external_file_cf(
   SaveError(errptr, db->rep->IngestExternalFile(handle->rep, files, opt->rep));
 }
 
-void rocksdb_try_catch_up_with_primary(rocksdb_t* db, char** errptr) {
-  SaveError(errptr, db->rep->TryCatchUpWithPrimary());
-}
-
 rocksdb_slicetransform_t* rocksdb_slicetransform_create(
     void* state,
     void (*destructor)(void*),
@@ -3537,21 +3298,20 @@ void rocksdb_slicetransform_destroy(rocksdb_slicetransform_t* st) {
   delete st;
 }
 
-struct Wrapper : public rocksdb_slicetransform_t {
-  const SliceTransform* rep_;
-  ~Wrapper() override { delete rep_; }
-  const char* Name() const override { return rep_->Name(); }
-  Slice Transform(const Slice& src) const override {
-    return rep_->Transform(src);
-  }
-  bool InDomain(const Slice& src) const override {
-    return rep_->InDomain(src);
-  }
-  bool InRange(const Slice& src) const override { return rep_->InRange(src); }
-  static void DoNothing(void*) { }
-};
-
 rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t prefixLen) {
+  struct Wrapper : public rocksdb_slicetransform_t {
+    const SliceTransform* rep_;
+    ~Wrapper() { delete rep_; }
+    const char* Name() const override { return rep_->Name(); }
+    Slice Transform(const Slice& src) const override {
+      return rep_->Transform(src);
+    }
+    bool InDomain(const Slice& src) const override {
+      return rep_->InDomain(src);
+    }
+    bool InRange(const Slice& src) const override { return rep_->InRange(src); }
+    static void DoNothing(void*) { }
+  };
   Wrapper* wrapper = new Wrapper;
   wrapper->rep_ = rocksdb::NewFixedPrefixTransform(prefixLen);
   wrapper->state_ = nullptr;
@@ -3560,6 +3320,19 @@ rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t pref
 }
 
 rocksdb_slicetransform_t* rocksdb_slicetransform_create_noop() {
+  struct Wrapper : public rocksdb_slicetransform_t {
+    const SliceTransform* rep_;
+    ~Wrapper() { delete rep_; }
+    const char* Name() const override { return rep_->Name(); }
+    Slice Transform(const Slice& src) const override {
+      return rep_->Transform(src);
+    }
+    bool InDomain(const Slice& src) const override {
+      return rep_->InDomain(src);
+    }
+    bool InRange(const Slice& src) const override { return rep_->InRange(src); }
+    static void DoNothing(void*) { }
+  };
   Wrapper* wrapper = new Wrapper;
   wrapper->rep_ = rocksdb::NewNoopTransform();
   wrapper->state_ = nullptr;
@@ -3677,18 +3450,6 @@ const char* rocksdb_livefiles_largestkey(
   return lf->rep[index].largestkey.data();
 }
 
-uint64_t rocksdb_livefiles_entries(
-    const rocksdb_livefiles_t* lf,
-    int index) {
-  return lf->rep[index].num_entries;
-}
-
-uint64_t rocksdb_livefiles_deletions(
-    const rocksdb_livefiles_t* lf,
-    int index) {
-  return lf->rep[index].num_deletions;
-}
-
 extern void rocksdb_livefiles_destroy(
   const rocksdb_livefiles_t* lf) {
   delete lf;
@@ -3834,38 +3595,6 @@ rocksdb_transactiondb_t* rocksdb_transactiondb_open(
   return result;
 }
 
-rocksdb_transactiondb_t* rocksdb_transactiondb_open_column_families(
-    const rocksdb_options_t* options,
-    const rocksdb_transactiondb_options_t* txn_db_options, const char* name,
-    int num_column_families, const char** column_family_names,
-    const rocksdb_options_t** column_family_options,
-    rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
-  std::vector<ColumnFamilyDescriptor> column_families;
-  for (int i = 0; i < num_column_families; i++) {
-    column_families.push_back(ColumnFamilyDescriptor(
-        std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep)));
-  }
-
-  TransactionDB* txn_db;
-  std::vector<ColumnFamilyHandle*> handles;
-  if (SaveError(errptr, TransactionDB::Open(options->rep, txn_db_options->rep,
-                                            std::string(name), column_families,
-                                            &handles, &txn_db))) {
-    return nullptr;
-  }
-
-  for (size_t i = 0; i < handles.size(); i++) {
-    rocksdb_column_family_handle_t* c_handle =
-        new rocksdb_column_family_handle_t;
-    c_handle->rep = handles[i];
-    column_family_handles[i] = c_handle;
-  }
-  rocksdb_transactiondb_t* result = new rocksdb_transactiondb_t;
-  result->rep = txn_db;
-  return result;
-}
-
 const rocksdb_snapshot_t* rocksdb_transactiondb_create_snapshot(
     rocksdb_transactiondb_t* txn_db) {
   rocksdb_snapshot_t* result = new rocksdb_snapshot_t;
@@ -3986,26 +3715,6 @@ char* rocksdb_transaction_get_for_update(rocksdb_transaction_t* txn,
   return result;
 }
 
-char* rocksdb_transaction_get_for_update_cf(
-    rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key, size_t klen,
-    size_t* vlen, unsigned char exclusive, char** errptr) {
-  char* result = nullptr;
-  std::string tmp;
-  Status s = txn->rep->GetForUpdate(options->rep, column_family->rep,
-                                    Slice(key, klen), &tmp, exclusive);
-  if (s.ok()) {
-    *vlen = tmp.size();
-    result = CopyString(tmp);
-  } else {
-    *vlen = 0;
-    if (!s.IsNotFound()) {
-      SaveError(errptr, s);
-    }
-  }
-  return result;
-}
-
 // Read a key outside a transaction
 char* rocksdb_transactiondb_get(
     rocksdb_transactiondb_t* txn_db,
@@ -4098,14 +3807,6 @@ void rocksdb_transaction_merge(rocksdb_transaction_t* txn, const char* key,
   SaveError(errptr, txn->rep->Merge(Slice(key, klen), Slice(val, vlen)));
 }
 
-void rocksdb_transaction_merge_cf(rocksdb_transaction_t* txn,
-                                  rocksdb_column_family_handle_t* column_family,
-                                  const char* key, size_t klen, const char* val,
-                                  size_t vlen, char** errptr) {
-  SaveError(errptr, txn->rep->Merge(column_family->rep, Slice(key, klen),
-                                    Slice(val, vlen)));
-}
-
 // Merge a key outside a transaction
 void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
                                  const rocksdb_writeoptions_t* options,
@@ -4115,14 +3816,6 @@ void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
                                        Slice(val, vlen)));
 }
 
-void rocksdb_transactiondb_merge_cf(
-    rocksdb_transactiondb_t* txn_db, const rocksdb_writeoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key, size_t klen,
-    const char* val, size_t vlen, char** errptr) {
-  SaveError(errptr, txn_db->rep->Merge(options->rep, column_family->rep,
-                                       Slice(key, klen), Slice(val, vlen)));
-}
-
 // Delete a key inside a transaction
 void rocksdb_transaction_delete(rocksdb_transaction_t* txn, const char* key,
                                 size_t klen, char** errptr) {
@@ -4175,14 +3868,6 @@ rocksdb_iterator_t* rocksdb_transactiondb_create_iterator(
   return result;
 }
 
-rocksdb_iterator_t* rocksdb_transactiondb_create_iterator_cf(
-    rocksdb_transactiondb_t* txn_db, const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family) {
-  rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep = txn_db->rep->NewIterator(options->rep, column_family->rep);
-  return result;
-}
-
 void rocksdb_transactiondb_close(rocksdb_transactiondb_t* txn_db) {
   delete txn_db->rep;
   delete txn_db;
@@ -4331,98 +4016,6 @@ const char* rocksdb_pinnableslice_value(const rocksdb_pinnableslice_t* v,
   *vlen = v->rep.size();
   return v->rep.data();
 }
-
-// container to keep databases and caches in order to use rocksdb::MemoryUtil
-struct rocksdb_memory_consumers_t {
-  std::vector<rocksdb_t*> dbs;
-  std::unordered_set<rocksdb_cache_t*> caches;
-};
-
-// initializes new container of memory consumers
-rocksdb_memory_consumers_t* rocksdb_memory_consumers_create() {
-  return new rocksdb_memory_consumers_t;
-}
-
-// adds datatabase to the container of memory consumers
-void rocksdb_memory_consumers_add_db(rocksdb_memory_consumers_t* consumers,
-                                     rocksdb_t* db) {
-  consumers->dbs.push_back(db);
-}
-
-// adds cache to the container of memory consumers
-void rocksdb_memory_consumers_add_cache(rocksdb_memory_consumers_t* consumers,
-                                        rocksdb_cache_t* cache) {
-  consumers->caches.insert(cache);
-}
-
-// deletes container with memory consumers
-void rocksdb_memory_consumers_destroy(rocksdb_memory_consumers_t* consumers) {
-  delete consumers;
-}
-
-// contains memory usage statistics provided by rocksdb::MemoryUtil
-struct rocksdb_memory_usage_t {
-  uint64_t mem_table_total;
-  uint64_t mem_table_unflushed;
-  uint64_t mem_table_readers_total;
-  uint64_t cache_total;
-};
-
-// estimates amount of memory occupied by consumers (dbs and caches)
-rocksdb_memory_usage_t* rocksdb_approximate_memory_usage_create(
-    rocksdb_memory_consumers_t* consumers, char** errptr) {
-
-  vector<DB*> dbs;
-  for (auto db : consumers->dbs) {
-    dbs.push_back(db->rep);
-  }
-
-  unordered_set<const Cache*> cache_set;
-  for (auto cache : consumers->caches) {
-    cache_set.insert(const_cast<const Cache*>(cache->rep.get()));
-  }
-
-  std::map<rocksdb::MemoryUtil::UsageType, uint64_t> usage_by_type;
-
-  auto status = MemoryUtil::GetApproximateMemoryUsageByType(dbs, cache_set,
-                                                            &usage_by_type);
-  if (SaveError(errptr, status)) {
-    return nullptr;
-  }
-
-  auto result = new rocksdb_memory_usage_t;
-  result->mem_table_total = usage_by_type[MemoryUtil::kMemTableTotal];
-  result->mem_table_unflushed = usage_by_type[MemoryUtil::kMemTableUnFlushed];
-  result->mem_table_readers_total = usage_by_type[MemoryUtil::kTableReadersTotal];
-  result->cache_total = usage_by_type[MemoryUtil::kCacheTotal];
-  return result;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_mem_table_total(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->mem_table_total;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_mem_table_unflushed(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->mem_table_unflushed;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_mem_table_readers_total(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->mem_table_readers_total;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_cache_total(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->cache_total;
-}
-
-// deletes container with memory usage estimates
-void rocksdb_approximate_memory_usage_destroy(rocksdb_memory_usage_t* usage) {
-  delete usage;
-}
-
 }  // end extern "C"
 
 #endif  // !ROCKSDB_LITE

db/c_test.c

@@ -1,7 +1,6 @@
 /* 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. */
-// Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 #include <stdio.h>
 
@@ -20,8 +19,11 @@
 
 // Can not use port/port.h macros as this is a c file
 #ifdef OS_WIN
+
 #include <windows.h>
 
+#define snprintf _snprintf
+
 // Ok for uniqueness
 int geteuid() {
   int result = 0;
@@ -32,11 +34,6 @@ int geteuid() {
   return result;
 }
 
-// VS < 2015
-#if defined(_MSC_VER) && (_MSC_VER < 1900)
-#define snprintf _snprintf
-#endif
-
 #endif
 
 const char* phase = "";
@@ -45,25 +42,17 @@ static char sstfilename[200];
 static char dbbackupname[200];
 static char dbcheckpointname[200];
 static char dbpathname[200];
-static char secondary_path[200];
 
 static void StartPhase(const char* name) {
   fprintf(stderr, "=== Test %s\n", name);
   phase = name;
 }
-#ifdef _MSC_VER
-#pragma warning(push)
-#pragma warning (disable: 4996) // getenv security warning
-#endif
 static const char* GetTempDir(void) {
     const char* ret = getenv("TEST_TMPDIR");
     if (ret == NULL || ret[0] == '\0')
         ret = "/tmp";
     return ret;
 }
-#ifdef _MSC_VER
-#pragma warning(pop)
-#endif
 
 #define CheckNoError(err)                                               \
   if ((err) != NULL) {                                                  \
@@ -203,11 +192,10 @@ static void CheckDel(void* ptr, const char* k, size_t klen) {
   (*state)++;
 }
 
-static void CmpDestroy(void* arg) { (void)arg; }
+static void CmpDestroy(void* arg) { }
 
 static int CmpCompare(void* arg, const char* a, size_t alen,
                       const char* b, size_t blen) {
-  (void)arg;
   size_t n = (alen < blen) ? alen : blen;
   int r = memcmp(a, b, n);
   if (r == 0) {
@@ -218,15 +206,13 @@ static int CmpCompare(void* arg, const char* a, size_t alen,
 }
 
 static const char* CmpName(void* arg) {
-  (void)arg;
   return "foo";
 }
 
 // Custom filter policy
 static unsigned char fake_filter_result = 1;
-static void FilterDestroy(void* arg) { (void)arg; }
+static void FilterDestroy(void* arg) { }
 static const char* FilterName(void* arg) {
-  (void)arg;
   return "TestFilter";
 }
 static char* FilterCreate(
@@ -234,10 +220,6 @@ static char* FilterCreate(
     const char* const* key_array, const size_t* key_length_array,
     int num_keys,
     size_t* filter_length) {
-  (void)arg;
-  (void)key_array;
-  (void)key_length_array;
-  (void)num_keys;
   *filter_length = 4;
   char* result = malloc(4);
   memcpy(result, "fake", 4);
@@ -247,30 +229,20 @@ static unsigned char FilterKeyMatch(
     void* arg,
     const char* key, size_t length,
     const char* filter, size_t filter_length) {
-  (void)arg;
-  (void)key;
-  (void)length;
   CheckCondition(filter_length == 4);
   CheckCondition(memcmp(filter, "fake", 4) == 0);
   return fake_filter_result;
 }
 
 // Custom compaction filter
-static void CFilterDestroy(void* arg) { (void)arg; }
-static const char* CFilterName(void* arg) {
-  (void)arg;
-  return "foo";
-}
+static void CFilterDestroy(void* arg) {}
+static const char* CFilterName(void* arg) { return "foo"; }
 static unsigned char CFilterFilter(void* arg, int level, const char* key,
                                    size_t key_length,
                                    const char* existing_value,
                                    size_t value_length, char** new_value,
                                    size_t* new_value_length,
                                    unsigned char* value_changed) {
-  (void)arg;
-  (void)level;
-  (void)existing_value;
-  (void)value_length;
   if (key_length == 3) {
     if (memcmp(key, "bar", key_length) == 0) {
       return 1;
@@ -284,15 +256,10 @@ static unsigned char CFilterFilter(void* arg, int level, const char* key,
   return 0;
 }
 
-static void CFilterFactoryDestroy(void* arg) { (void)arg; }
-static const char* CFilterFactoryName(void* arg) {
-  (void)arg;
-  return "foo";
-}
+static void CFilterFactoryDestroy(void* arg) {}
+static const char* CFilterFactoryName(void* arg) { return "foo"; }
 static rocksdb_compactionfilter_t* CFilterCreate(
     void* arg, rocksdb_compactionfiltercontext_t* context) {
-  (void)arg;
-  (void)context;
   return rocksdb_compactionfilter_create(NULL, CFilterDestroy, CFilterFilter,
                                          CFilterName);
 }
@@ -323,9 +290,8 @@ static rocksdb_t* CheckCompaction(rocksdb_t* db, rocksdb_options_t* options,
 }
 
 // Custom merge operator
-static void MergeOperatorDestroy(void* arg) { (void)arg; }
+static void MergeOperatorDestroy(void* arg) { }
 static const char* MergeOperatorName(void* arg) {
-  (void)arg;
   return "TestMergeOperator";
 }
 static char* MergeOperatorFullMerge(
@@ -335,14 +301,6 @@ static char* MergeOperatorFullMerge(
     const char* const* operands_list, const size_t* operands_list_length,
     int num_operands,
     unsigned char* success, size_t* new_value_length) {
-  (void)arg;
-  (void)key;
-  (void)key_length;
-  (void)existing_value;
-  (void)existing_value_length;
-  (void)operands_list;
-  (void)operands_list_length;
-  (void)num_operands;
   *new_value_length = 4;
   *success = 1;
   char* result = malloc(4);
@@ -355,12 +313,6 @@ static char* MergeOperatorPartialMerge(
     const char* const* operands_list, const size_t* operands_list_length,
     int num_operands,
     unsigned char* success, size_t* new_value_length) {
-  (void)arg;
-  (void)key;
-  (void)key_length;
-  (void)operands_list;
-  (void)operands_list_length;
-  (void)num_operands;
   *new_value_length = 4;
   *success = 1;
   char* result = malloc(4);
@@ -425,8 +377,6 @@ static void CheckTxnDBGetCF(rocksdb_transactiondb_t* txn_db,
 }
 
 int main(int argc, char** argv) {
-  (void)argc;
-  (void)argv;
   rocksdb_t* db;
   rocksdb_comparator_t* cmp;
   rocksdb_cache_t* cache;
@@ -487,11 +437,8 @@ int main(int argc, char** argv) {
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
   rocksdb_options_set_base_background_compactions(options, 1);
-
   table_options = rocksdb_block_based_options_create();
   rocksdb_block_based_options_set_block_cache(table_options, cache);
-  rocksdb_block_based_options_set_data_block_index_type(table_options, 1);
-  rocksdb_block_based_options_set_data_block_hash_ratio(table_options, 0.75);
   rocksdb_options_set_block_based_table_factory(options, table_options);
 
   rocksdb_options_set_compression(options, rocksdb_no_compression);
@@ -657,7 +604,7 @@ int main(int argc, char** argv) {
     rocksdb_sstfilewriter_t* writer =
         rocksdb_sstfilewriter_create(env_opt, io_options);
 
-    remove(sstfilename);
+    unlink(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_put(writer, "sstk1", 5, "v1", 2, &err);
@@ -678,7 +625,7 @@ int main(int argc, char** argv) {
     CheckGet(db, roptions, "sstk2", "v2");
     CheckGet(db, roptions, "sstk3", "v3");
 
-    remove(sstfilename);
+    unlink(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v4", 2, &err);
@@ -922,8 +869,7 @@ int main(int argc, char** argv) {
     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);
+    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));
@@ -1051,20 +997,17 @@ int main(int argc, char** argv) {
   }
 
   StartPhase("filter");
-  for (run = 0; run <= 2; run++) {
-    // First run uses custom filter
-    // Second run uses old block-based bloom filter
-    // Third run uses full bloom filter
+  for (run = 0; run < 2; run++) {
+    // First run uses custom filter, second run uses bloom filter
     CheckNoError(err);
     rocksdb_filterpolicy_t* policy;
     if (run == 0) {
-      policy = rocksdb_filterpolicy_create(NULL, FilterDestroy, FilterCreate,
-                                           FilterKeyMatch, NULL, FilterName);
-    } else if (run == 1) {
-      policy = rocksdb_filterpolicy_create_bloom(8);
+      policy = rocksdb_filterpolicy_create(
+          NULL, FilterDestroy, FilterCreate, FilterKeyMatch, NULL, FilterName);
     } else {
-      policy = rocksdb_filterpolicy_create_bloom_full(8);
+      policy = rocksdb_filterpolicy_create_bloom(10);
     }
+
     rocksdb_block_based_options_set_filter_policy(table_options, policy);
 
     // Create new database
@@ -1077,24 +1020,12 @@ int main(int argc, char** argv) {
     CheckNoError(err);
     rocksdb_put(db, woptions, "bar", 3, "barvalue", 8, &err);
     CheckNoError(err);
-
-    {
-      // Add enough keys to get just one reasonably populated Bloom filter
-      const int keys_to_add = 1500;
-      int i;
-      char keybuf[100];
-      for (i = 0; i < keys_to_add; i++) {
-        snprintf(keybuf, sizeof(keybuf), "yes%020d", i);
-        rocksdb_put(db, woptions, keybuf, strlen(keybuf), "val", 3, &err);
-        CheckNoError(err);
-      }
-    }
     rocksdb_compact_range(db, NULL, 0, NULL, 0);
 
     fake_filter_result = 1;
     CheckGet(db, roptions, "foo", "foovalue");
     CheckGet(db, roptions, "bar", "barvalue");
-    if (run == 0) {
+    if (phase == 0) {
       // Must not find value when custom filter returns false
       fake_filter_result = 0;
       CheckGet(db, roptions, "foo", NULL);
@@ -1104,43 +1035,6 @@ int main(int argc, char** argv) {
       CheckGet(db, roptions, "foo", "foovalue");
       CheckGet(db, roptions, "bar", "barvalue");
     }
-
-    {
-      // Query some keys not added to identify Bloom filter implementation
-      // from false positive queries, using perfcontext to detect Bloom
-      // filter behavior
-      rocksdb_perfcontext_t* perf = rocksdb_perfcontext_create();
-      rocksdb_perfcontext_reset(perf);
-
-      const int keys_to_query = 10000;
-      int i;
-      char keybuf[100];
-      for (i = 0; i < keys_to_query; i++) {
-        fake_filter_result = i % 2;
-        snprintf(keybuf, sizeof(keybuf), "no%020d", i);
-        CheckGet(db, roptions, keybuf, NULL);
-      }
-
-      const int hits =
-          (int)rocksdb_perfcontext_metric(perf, rocksdb_bloom_sst_hit_count);
-      if (run == 0) {
-        // Due to half true, half false with fake filter result
-        CheckCondition(hits == keys_to_query / 2);
-      } else if (run == 1) {
-        // Essentially a fingerprint of the block-based Bloom schema
-        CheckCondition(hits == 241);
-      } else {
-        // Essentially a fingerprint of the full Bloom schema(s),
-        // format_version < 5, which vary for three different CACHE_LINE_SIZEs
-        CheckCondition(hits == 224 || hits == 180 || hits == 125);
-      }
-      CheckCondition(
-          (keys_to_query - hits) ==
-          (int)rocksdb_perfcontext_metric(perf, rocksdb_bloom_sst_miss_count));
-
-      rocksdb_perfcontext_destroy(perf);
-    }
-
     // Reset the policy
     rocksdb_block_based_options_set_filter_policy(table_options, NULL);
     rocksdb_options_set_block_based_table_factory(options, table_options);
@@ -1244,31 +1138,12 @@ int main(int argc, char** argv) {
     rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &err);
     CheckNoError(err);
 
-    rocksdb_put_cf(db, woptions, handles[1], "foobar1", 7, "hello1", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar2", 7, "hello2", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar3", 7, "hello3", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar4", 7, "hello4", 6, &err);
-    CheckNoError(err);
-
-    rocksdb_flushoptions_t *flush_options = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_options, 1);
-    rocksdb_flush_cf(db, flush_options, handles[1], &err);
-    CheckNoError(err)
-    rocksdb_flushoptions_destroy(flush_options);
-
     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);
 
-    rocksdb_delete_range_cf(db, woptions, handles[1], "foobar2", 7, "foobar4",
-                            7, &err);
-    CheckNoError(err);
-
     CheckGetCF(db, roptions, handles[1], "foo", NULL);
     CheckPinGetCF(db, roptions, handles[1], "foo", NULL);
 
@@ -1321,7 +1196,7 @@ int main(int argc, char** argv) {
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
-    CheckCondition(i == 3);
+    CheckCondition(i == 1);
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -1345,7 +1220,7 @@ int main(int argc, char** argv) {
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
-    CheckCondition(i == 3);
+    CheckCondition(i == 1);
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -1420,47 +1295,6 @@ int main(int argc, char** argv) {
     rocksdb_destroy_db(options, dbname, &err);
   }
 
-  // Check memory usage stats
-  StartPhase("approximate_memory_usage");
-  {
-    // Create database
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_memory_consumers_t* consumers;
-    consumers = rocksdb_memory_consumers_create();
-    rocksdb_memory_consumers_add_db(consumers, db);
-    rocksdb_memory_consumers_add_cache(consumers, cache);
-
-    // take memory usage report before write-read operation
-    rocksdb_memory_usage_t* mu1;
-    mu1 = rocksdb_approximate_memory_usage_create(consumers, &err);
-    CheckNoError(err);
-
-    // Put data (this should affect memtables)
-    rocksdb_put(db, woptions, "memory", 6, "test", 4, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "memory", "test");
-
-    // take memory usage report after write-read operation
-    rocksdb_memory_usage_t* mu2;
-    mu2 = rocksdb_approximate_memory_usage_create(consumers, &err);
-    CheckNoError(err);
-
-    // amount of memory used within memtables should grow
-    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_total(mu2) >=
-                   rocksdb_approximate_memory_usage_get_mem_table_total(mu1));
-    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu2) >=
-                   rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu1));
-
-    rocksdb_memory_consumers_destroy(consumers);
-    rocksdb_approximate_memory_usage_destroy(mu1);
-    rocksdb_approximate_memory_usage_destroy(mu2);
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-  }
-
   StartPhase("cuckoo_options");
   {
     rocksdb_cuckoo_table_options_t* cuckoo_options;
@@ -1535,7 +1369,6 @@ int main(int argc, char** argv) {
        CheckCondition(!rocksdb_iter_valid(iter));
 
        rocksdb_iter_destroy(iter);
-       rocksdb_readoptions_set_iterate_upper_bound(roptions, NULL, 0);
     }
   }
 
@@ -1605,7 +1438,7 @@ int main(int argc, char** argv) {
     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);
 
@@ -1792,59 +1625,6 @@ int main(int argc, char** argv) {
     CheckNoError(err);
   }
 
-  // Check that secondary instance works.
-  StartPhase("open_as_secondary");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-
-    rocksdb_options_t* db_options = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(db_options, 1);
-    db = rocksdb_open(db_options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_t* db1;
-    rocksdb_options_t* opts = rocksdb_options_create();
-    rocksdb_options_set_max_open_files(opts, -1);
-    rocksdb_options_set_create_if_missing(opts, 1);
-    snprintf(secondary_path, sizeof(secondary_path),
-             "%s/rocksdb_c_test_secondary-%d", GetTempDir(), ((int)geteuid()));
-    db1 = rocksdb_open_as_secondary(opts, dbname, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_writeoptions_set_sync(woptions, 0);
-    rocksdb_writeoptions_disable_WAL(woptions, 1);
-    rocksdb_put(db, woptions, "key0", 4, "value0", 6, &err);
-    CheckNoError(err);
-    rocksdb_flushoptions_t* flush_opts = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_opts, 1);
-    rocksdb_flush(db, flush_opts, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    rocksdb_readoptions_t* ropts = rocksdb_readoptions_create();
-    rocksdb_readoptions_set_verify_checksums(ropts, 1);
-    rocksdb_readoptions_set_snapshot(ropts, NULL);
-    CheckGet(db, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key0", "value0");
-
-    rocksdb_writeoptions_disable_WAL(woptions, 0);
-    rocksdb_put(db, woptions, "key1", 4, "value1", 6, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    CheckGet(db1, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key1", "value1");
-
-    rocksdb_close(db1);
-    rocksdb_destroy_db(opts, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_options_destroy(db_options);
-    rocksdb_options_destroy(opts);
-    rocksdb_readoptions_destroy(ropts);
-    rocksdb_flushoptions_destroy(flush_opts);
-  }
-
   // Simple sanity check that options setting db_paths work.
   StartPhase("open_db_paths");
   {
@@ -1856,7 +1636,7 @@ int main(int argc, char** argv) {
     db = rocksdb_open(options, dbname, &err);
     CheckNoError(err);
   }
-
+  
   StartPhase("cleanup");
   rocksdb_close(db);
   rocksdb_options_destroy(options);

db/column_family.cc

@@ -9,29 +9,28 @@
 
 #include "db/column_family.h"
 
-#include <algorithm>
-#include <cinttypes>
-#include <limits>
-#include <string>
-#include <vector>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
 
-#include "db/compaction/compaction_picker.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
-#include "db/db_impl/db_impl.h"
+#include <inttypes.h>
+#include <vector>
+#include <string>
+#include <algorithm>
+#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"
-#include "db/range_del_aggregator.h"
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
-#include "file/sst_file_manager_impl.h"
 #include "memtable/hash_skiplist_rep.h"
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
-#include "port/port.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "util/autovector.h"
 #include "util/compression.h"
@@ -60,22 +59,13 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
     ColumnFamilyOptions initial_cf_options_copy = cfd_->initial_cf_options();
     JobContext job_context(0);
     mutex_->Lock();
-    bool dropped = cfd_->IsDropped();
-    if (cfd_->UnrefAndTryDelete()) {
-      if (dropped) {
-        db_->FindObsoleteFiles(&job_context, false, true);
-      }
+    if (cfd_->Unref()) {
+      delete cfd_;
     }
+    db_->FindObsoleteFiles(&job_context, false, true);
     mutex_->Unlock();
     if (job_context.HaveSomethingToDelete()) {
-      bool defer_purge =
-          db_->immutable_db_options().avoid_unnecessary_blocking_io;
-      db_->PurgeObsoleteFiles(job_context, defer_purge);
-      if (defer_purge) {
-        mutex_->Lock();
-        db_->SchedulePurge();
-        mutex_->Unlock();
-      }
+      db_->PurgeObsoleteFiles(job_context);
     }
     job_context.Clean();
   }
@@ -94,7 +84,6 @@ Status ColumnFamilyHandleImpl::GetDescriptor(ColumnFamilyDescriptor* desc) {
   *desc = ColumnFamilyDescriptor(cfd()->GetName(), cfd()->GetLatestCFOptions());
   return Status::OK();
 #else
-  (void)desc;
   return Status::NotSupported();
 #endif  // !ROCKSDB_LITE
 }
@@ -114,6 +103,9 @@ void GetIntTblPropCollectorFactory(
     int_tbl_prop_collector_factories->emplace_back(
         new UserKeyTablePropertiesCollectorFactory(collector_factories[i]));
   }
+  // Add collector to collect internal key statistics
+  int_tbl_prop_collector_factories->emplace_back(
+      new InternalKeyPropertiesCollectorFactory);
 }
 
 Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
@@ -136,10 +128,14 @@ Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
     }
   }
   if (cf_options.compression_opts.zstd_max_train_bytes > 0) {
-    if (!ZSTD_TrainDictionarySupported()) {
+    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 ZSTD 1.1.3+ "
-          "is not linked with the binary.");
+          "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(
@@ -160,41 +156,9 @@ Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options) {
     return Status::InvalidArgument(
         "Memtable doesn't concurrent writes (allow_concurrent_memtable_write)");
   }
-  if (cf_options.max_successive_merges != 0) {
-    return Status::InvalidArgument(
-        "max_successive_merges > 0 is incompatible "
-        "with concurrent writes (allow_concurrent_memtable_write)");
-  }
   return Status::OK();
 }
 
-Status CheckCFPathsSupported(const DBOptions& db_options,
-                             const ColumnFamilyOptions& cf_options) {
-  // More than one cf_paths are supported only in universal
-  // and level compaction styles. This function also checks the case
-  // in which cf_paths is not specified, which results in db_paths
-  // being used.
-  if ((cf_options.compaction_style != kCompactionStyleUniversal) &&
-      (cf_options.compaction_style != kCompactionStyleLevel)) {
-    if (cf_options.cf_paths.size() > 1) {
-      return Status::NotSupported(
-          "More than one CF paths are only supported in "
-          "universal and level compaction styles. ");
-    } else if (cf_options.cf_paths.empty() &&
-               db_options.db_paths.size() > 1) {
-      return Status::NotSupported(
-          "More than one DB paths are only supported in "
-          "universal and level compaction styles. ");
-    }
-  }
-  return Status::OK();
-}
-
-namespace {
-const uint64_t kDefaultTtl = 0xfffffffffffffffe;
-const uint64_t kDefaultPeriodicCompSecs = 0xfffffffffffffffe;
-};  // namespace
-
 ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                     const ColumnFamilyOptions& src) {
   ColumnFamilyOptions result = src;
@@ -235,14 +199,7 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
   if (result.max_write_buffer_number < 2) {
     result.max_write_buffer_number = 2;
   }
-  // fall back max_write_buffer_number_to_maintain if
-  // max_write_buffer_size_to_maintain is not set
-  if (result.max_write_buffer_size_to_maintain < 0) {
-    result.max_write_buffer_size_to_maintain =
-        result.max_write_buffer_number *
-        static_cast<int64_t>(result.write_buffer_size);
-  } else if (result.max_write_buffer_size_to_maintain == 0 &&
-             result.max_write_buffer_number_to_maintain < 0) {
+  if (result.max_write_buffer_number_to_maintain < 0) {
     result.max_write_buffer_number_to_maintain = result.max_write_buffer_number;
   }
   // bloom filter size shouldn't exceed 1/4 of memtable size.
@@ -320,24 +277,9 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
         result.hard_pending_compaction_bytes_limit;
   }
 
-#ifndef ROCKSDB_LITE
-  // When the DB is stopped, it's possible that there are some .trash files that
-  // were not deleted yet, when we open the DB we will find these .trash files
-  // and schedule them to be deleted (or delete immediately if SstFileManager
-  // was not used)
-  auto sfm = static_cast<SstFileManagerImpl*>(db_options.sst_file_manager.get());
-  for (size_t i = 0; i < result.cf_paths.size(); i++) {
-    DeleteScheduler::CleanupDirectory(db_options.env, sfm, result.cf_paths[i].path);
-  }
-#endif
-
-  if (result.cf_paths.empty()) {
-    result.cf_paths = db_options.db_paths;
-  }
-
   if (result.level_compaction_dynamic_level_bytes) {
     if (result.compaction_style != kCompactionStyleLevel ||
-        result.cf_paths.size() > 1U) {
+        db_options.db_paths.size() > 1U) {
       // 1. level_compaction_dynamic_level_bytes only makes sense for
       //    level-based compaction.
       // 2. we don't yet know how to make both of this feature and multiple
@@ -350,61 +292,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     result.max_compaction_bytes = result.target_file_size_base * 25;
   }
 
-  bool is_block_based_table =
-      (result.table_factory->Name() == BlockBasedTableFactory().Name());
-
-  const uint64_t kAdjustedTtl = 30 * 24 * 60 * 60;
-  if (result.ttl == kDefaultTtl) {
-    if (is_block_based_table &&
-        result.compaction_style != kCompactionStyleFIFO) {
-      result.ttl = kAdjustedTtl;
-    } else {
-      result.ttl = 0;
-    }
-  }
-
-  const uint64_t kAdjustedPeriodicCompSecs = 30 * 24 * 60 * 60;
-
-  // Turn on periodic compactions and set them to occur once every 30 days if
-  // compaction filters are used and periodic_compaction_seconds is set to the
-  // default value.
-  if (result.compaction_style != kCompactionStyleFIFO) {
-    if ((result.compaction_filter != nullptr ||
-         result.compaction_filter_factory != nullptr) &&
-        result.periodic_compaction_seconds == kDefaultPeriodicCompSecs &&
-        is_block_based_table) {
-      result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-    }
-  } else {
-    // result.compaction_style == kCompactionStyleFIFO
-    if (result.ttl == 0) {
-      if (is_block_based_table) {
-        if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-          result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-        }
-        result.ttl = result.periodic_compaction_seconds;
-      }
-    } else if (result.periodic_compaction_seconds != 0) {
-      result.ttl = std::min(result.ttl, result.periodic_compaction_seconds);
-    }
-  }
-
-  // TTL compactions would work similar to Periodic Compactions in Universal in
-  // most of the cases. So, if ttl is set, execute the periodic compaction
-  // codepath.
-  if (result.compaction_style == kCompactionStyleUniversal && result.ttl != 0) {
-    if (result.periodic_compaction_seconds != 0) {
-      result.periodic_compaction_seconds =
-          std::min(result.ttl, result.periodic_compaction_seconds);
-    } else {
-      result.periodic_compaction_seconds = result.ttl;
-    }
-  }
-
-  if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-    result.periodic_compaction_seconds = 0;
-  }
-
   return result;
 }
 
@@ -441,18 +328,13 @@ void SuperVersion::Cleanup() {
     to_delete.push_back(m);
   }
   current->Unref();
-  if (cfd->Unref()) {
-    delete cfd;
-  }
 }
 
-void SuperVersion::Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
-                        MemTableListVersion* new_imm, Version* new_current) {
-  cfd = new_cfd;
+void SuperVersion::Init(MemTable* new_mem, MemTableListVersion* new_imm,
+                        Version* new_current) {
   mem = new_mem;
   imm = new_imm;
   current = new_current;
-  cfd->Ref();
   mem->Ref();
   imm->Ref();
   current->Ref();
@@ -480,8 +362,7 @@ ColumnFamilyData::ColumnFamilyData(
     uint32_t id, const std::string& name, Version* _dummy_versions,
     Cache* _table_cache, WriteBufferManager* write_buffer_manager,
     const ColumnFamilyOptions& cf_options, const ImmutableDBOptions& db_options,
-    const FileOptions& file_options, ColumnFamilySet* column_family_set,
-    BlockCacheTracer* const block_cache_tracer)
+    const EnvOptions& env_options, ColumnFamilySet* column_family_set)
     : id_(id),
       name_(name),
       dummy_versions_(_dummy_versions),
@@ -498,8 +379,7 @@ ColumnFamilyData::ColumnFamilyData(
       write_buffer_manager_(write_buffer_manager),
       mem_(nullptr),
       imm_(ioptions_.min_write_buffer_number_to_merge,
-           ioptions_.max_write_buffer_number_to_maintain,
-           ioptions_.max_write_buffer_size_to_maintain),
+           ioptions_.max_write_buffer_number_to_maintain),
       super_version_(nullptr),
       super_version_number_(0),
       local_sv_(new ThreadLocalPtr(&SuperVersionUnrefHandle)),
@@ -508,8 +388,8 @@ ColumnFamilyData::ColumnFamilyData(
       log_number_(0),
       flush_reason_(FlushReason::kOthers),
       column_family_set_(column_family_set),
-      queued_for_flush_(false),
-      queued_for_compaction_(false),
+      pending_flush_(false),
+      pending_compaction_(false),
       prev_compaction_needed_bytes_(0),
       allow_2pc_(db_options.allow_2pc),
       last_memtable_id_(0) {
@@ -522,8 +402,7 @@ ColumnFamilyData::ColumnFamilyData(
   if (_dummy_versions != nullptr) {
     internal_stats_.reset(
         new InternalStats(ioptions_.num_levels, db_options.env, this));
-    table_cache_.reset(new TableCache(ioptions_, file_options, _table_cache,
-                                      block_cache_tracer));
+    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache));
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
           new LevelCompactionPicker(ioptions_, &internal_comparator_));
@@ -586,9 +465,23 @@ ColumnFamilyData::~ColumnFamilyData() {
 
   // It would be wrong if this ColumnFamilyData is in flush_queue_ or
   // compaction_queue_ and we destroyed it
-  assert(!queued_for_flush_);
-  assert(!queued_for_compaction_);
-  assert(super_version_ == nullptr);
+  assert(!pending_flush_);
+  assert(!pending_compaction_);
+
+  if (super_version_ != nullptr) {
+    // Release SuperVersion reference kept in ThreadLocalPtr.
+    // This must be done outside of mutex_ since unref handler can lock mutex.
+    super_version_->db_mutex->Unlock();
+    local_sv_.reset();
+    super_version_->db_mutex->Lock();
+
+    bool is_last_reference __attribute__((__unused__));
+    is_last_reference = super_version_->Unref();
+    assert(is_last_reference);
+    super_version_->Cleanup();
+    delete super_version_;
+    super_version_ = nullptr;
+  }
 
   if (dummy_versions_ != nullptr) {
     // List must be empty
@@ -608,36 +501,6 @@ ColumnFamilyData::~ColumnFamilyData() {
   }
 }
 
-bool ColumnFamilyData::UnrefAndTryDelete() {
-  int old_refs = refs_.fetch_sub(1);
-  assert(old_refs > 0);
-
-  if (old_refs == 1) {
-    assert(super_version_ == nullptr);
-    delete this;
-    return true;
-  }
-
-  if (old_refs == 2 && super_version_ != nullptr) {
-    // Only the super_version_ holds me
-    SuperVersion* sv = super_version_;
-    super_version_ = nullptr;
-    // Release SuperVersion reference kept in ThreadLocalPtr.
-    // This must be done outside of mutex_ since unref handler can lock mutex.
-    sv->db_mutex->Unlock();
-    local_sv_.reset();
-    sv->db_mutex->Lock();
-
-    if (sv->Unref()) {
-      // May delete this ColumnFamilyData after calling Cleanup()
-      sv->Cleanup();
-      delete sv;
-      return true;
-    }
-  }
-  return false;
-}
-
 void ColumnFamilyData::SetDropped() {
   // can't drop default CF
   assert(id_ != 0);
@@ -656,9 +519,7 @@ uint64_t ColumnFamilyData::OldestLogToKeep() {
   auto current_log = GetLogNumber();
 
   if (allow_2pc_) {
-    autovector<MemTable*> empty_list;
-    auto imm_prep_log =
-        imm()->PrecomputeMinLogContainingPrepSection(empty_list);
+    auto imm_prep_log = imm()->GetMinLogContainingPrepSection();
     auto mem_prep_log = mem()->GetMinLogContainingPrepSection();
 
     if (imm_prep_log > 0 && imm_prep_log < current_log) {
@@ -972,8 +833,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
   return write_stall_condition;
 }
 
-const FileOptions* ColumnFamilyData::soptions() const {
-  return &(column_family_set_->file_options_);
+const EnvOptions* ColumnFamilyData::soptions() const {
+  return &(column_family_set_->env_options_);
 }
 
 void ColumnFamilyData::SetCurrent(Version* current_version) {
@@ -1013,12 +874,8 @@ bool ColumnFamilyData::NeedsCompaction() const {
 
 Compaction* ColumnFamilyData::PickCompaction(
     const MutableCFOptions& mutable_options, LogBuffer* log_buffer) {
-  SequenceNumber earliest_mem_seqno =
-      std::min(mem_->GetEarliestSequenceNumber(),
-               imm_.current()->GetEarliestSequenceNumber(false));
   auto* result = compaction_picker_->PickCompaction(
-      GetName(), mutable_options, current_->storage_info(), log_buffer,
-      earliest_mem_seqno);
+      GetName(), mutable_options, current_->storage_info(), log_buffer);
   if (result != nullptr) {
     result->SetInputVersion(current_);
   }
@@ -1047,16 +904,26 @@ Status ColumnFamilyData::RangesOverlapWithMemtables(
   super_version->imm->AddIterators(read_opts, &merge_iter_builder);
   ScopedArenaIterator memtable_iter(merge_iter_builder.Finish());
 
-  auto read_seq = super_version->current->version_set()->LastSequence();
-  ReadRangeDelAggregator range_del_agg(&internal_comparator_, read_seq);
+  std::vector<InternalIterator*> memtable_range_del_iters;
   auto* active_range_del_iter =
-      super_version->mem->NewRangeTombstoneIterator(read_opts, read_seq);
-  range_del_agg.AddTombstones(
-      std::unique_ptr<FragmentedRangeTombstoneIterator>(active_range_del_iter));
-  super_version->imm->AddRangeTombstoneIterators(read_opts, nullptr /* arena */,
-                                                 &range_del_agg);
-
+      super_version->mem->NewRangeTombstoneIterator(read_opts);
+  if (active_range_del_iter != nullptr) {
+    memtable_range_del_iters.push_back(active_range_del_iter);
+  }
+  super_version->imm->AddRangeTombstoneIterators(read_opts,
+                                                 &memtable_range_del_iters);
+  RangeDelAggregator range_del_agg(internal_comparator_, {} /* snapshots */,
+                                   false /* collapse_deletions */);
   Status status;
+  {
+    std::unique_ptr<InternalIterator> memtable_range_del_iter(
+        NewMergingIterator(&internal_comparator_,
+                           memtable_range_del_iters.empty()
+                               ? nullptr
+                               : &memtable_range_del_iters[0],
+                           static_cast<int>(memtable_range_del_iters.size())));
+    status = range_del_agg.AddTombstones(std::move(memtable_range_del_iter));
+  }
   for (size_t i = 0; i < ranges.size() && status.ok() && !*overlap; ++i) {
     auto* vstorage = super_version->current->storage_info();
     auto* ucmp = vstorage->InternalComparator()->user_comparator();
@@ -1089,22 +956,20 @@ const int ColumnFamilyData::kCompactToBaseLevel = -2;
 
 Compaction* ColumnFamilyData::CompactRange(
     const MutableCFOptions& mutable_cf_options, int input_level,
-    int output_level, const CompactRangeOptions& compact_range_options,
-    const InternalKey* begin, const InternalKey* end,
-    InternalKey** compaction_end, bool* conflict,
-    uint64_t max_file_num_to_ignore) {
+    int output_level, uint32_t output_path_id, const InternalKey* begin,
+    const InternalKey* end, InternalKey** compaction_end, bool* conflict) {
   auto* result = compaction_picker_->CompactRange(
       GetName(), mutable_cf_options, current_->storage_info(), input_level,
-      output_level, compact_range_options, begin, end, compaction_end, conflict,
-      max_file_num_to_ignore);
+      output_level, output_path_id, begin, end, compaction_end, conflict);
   if (result != nullptr) {
     result->SetInputVersion(current_);
   }
   return result;
 }
 
-SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(DBImpl* db) {
-  SuperVersion* sv = GetThreadLocalSuperVersion(db);
+SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
+    InstrumentedMutex* db_mutex) {
+  SuperVersion* sv = GetThreadLocalSuperVersion(db_mutex);
   sv->Ref();
   if (!ReturnThreadLocalSuperVersion(sv)) {
     // This Unref() corresponds to the Ref() in GetThreadLocalSuperVersion()
@@ -1116,7 +981,8 @@ SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(DBImpl* db) {
   return sv;
 }
 
-SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
+SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
+    InstrumentedMutex* db_mutex) {
   // The SuperVersion is cached in thread local storage to avoid acquiring
   // mutex when SuperVersion does not change since the last use. When a new
   // SuperVersion is installed, the compaction or flush thread cleans up
@@ -1143,21 +1009,16 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
 
     if (sv && sv->Unref()) {
       RecordTick(ioptions_.statistics, NUMBER_SUPERVERSION_CLEANUPS);
-      db->mutex()->Lock();
+      db_mutex->Lock();
       // NOTE: underlying resources held by superversion (sst files) might
       // not be released until the next background job.
       sv->Cleanup();
-      if (db->immutable_db_options().avoid_unnecessary_blocking_io) {
-        db->AddSuperVersionsToFreeQueue(sv);
-        db->SchedulePurge();
-      } else {
-        sv_to_delete = sv;
-      }
+      sv_to_delete = sv;
     } else {
-      db->mutex()->Lock();
+      db_mutex->Lock();
     }
     sv = super_version_->Ref();
-    db->mutex()->Unlock();
+    db_mutex->Unlock();
 
     delete sv_to_delete;
   }
@@ -1195,7 +1056,7 @@ void ColumnFamilyData::InstallSuperVersion(
   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(this, mem_, imm_.current(), current_);
+  new_superversion->Init(mem_, imm_.current(), current_);
   SuperVersion* old_superversion = super_version_;
   super_version_ = new_superversion;
   ++super_version_number_;
@@ -1245,51 +1106,12 @@ void ColumnFamilyData::ResetThreadLocalSuperVersions() {
   }
 }
 
-Status ColumnFamilyData::ValidateOptions(
-    const DBOptions& db_options, const ColumnFamilyOptions& cf_options) {
-  Status s;
-  s = CheckCompressionSupported(cf_options);
-  if (s.ok() && db_options.allow_concurrent_memtable_write) {
-    s = CheckConcurrentWritesSupported(cf_options);
-  }
-  if (s.ok()) {
-    s = CheckCFPathsSupported(db_options, cf_options);
-  }
-  if (!s.ok()) {
-    return s;
-  }
-
-  if (cf_options.ttl > 0 && cf_options.ttl != kDefaultTtl) {
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "TTL is only supported in Block-Based Table format. ");
-    }
-  }
-
-  if (cf_options.periodic_compaction_seconds > 0 &&
-      cf_options.periodic_compaction_seconds != kDefaultPeriodicCompSecs) {
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported in "
-          "Block-Based Table format. ");
-    }
-  }
-  return s;
-}
-
 #ifndef ROCKSDB_LITE
 Status ColumnFamilyData::SetOptions(
-    const DBOptions& db_options,
-    const std::unordered_map<std::string, std::string>& options_map) {
+      const std::unordered_map<std::string, std::string>& options_map) {
   MutableCFOptions new_mutable_cf_options;
-  Status s =
-      GetMutableOptionsFromStrings(mutable_cf_options_, options_map,
-                                   ioptions_.info_log, &new_mutable_cf_options);
-  if (s.ok()) {
-    ColumnFamilyOptions cf_options =
-        BuildColumnFamilyOptions(initial_cf_options_, new_mutable_cf_options);
-    s = ValidateOptions(db_options, cf_options);
-  }
+  Status s = GetMutableOptionsFromStrings(mutable_cf_options_, options_map,
+                                          &new_mutable_cf_options);
   if (s.ok()) {
     mutable_cf_options_ = new_mutable_cf_options;
     mutable_cf_options_.RefreshDerivedOptions(ioptions_);
@@ -1311,59 +1133,28 @@ Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
   // L1: medium, L2: long, ...
   if (level - base_level >= 2) {
     return Env::WLTH_EXTREME;
-  } else if (level < base_level) {
-    // There is no restriction which prevents level passed in to be smaller
-    // than base_level.
-    return Env::WLTH_MEDIUM;
   }
   return static_cast<Env::WriteLifeTimeHint>(level - base_level +
                             static_cast<int>(Env::WLTH_MEDIUM));
 }
 
-Status ColumnFamilyData::AddDirectories() {
-  Status s;
-  assert(data_dirs_.empty());
-  for (auto& p : ioptions_.cf_paths) {
-    std::unique_ptr<Directory> path_directory;
-    s = DBImpl::CreateAndNewDirectory(ioptions_.env, p.path, &path_directory);
-    if (!s.ok()) {
-      return s;
-    }
-    assert(path_directory != nullptr);
-    data_dirs_.emplace_back(path_directory.release());
-  }
-  assert(data_dirs_.size() == ioptions_.cf_paths.size());
-  return s;
-}
-
-Directory* ColumnFamilyData::GetDataDir(size_t path_id) const {
-  if (data_dirs_.empty()) {
-    return nullptr;
-  }
-
-  assert(path_id < data_dirs_.size());
-  return data_dirs_[path_id].get();
-}
-
 ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                  const ImmutableDBOptions* db_options,
-                                 const FileOptions& file_options,
+                                 const EnvOptions& env_options,
                                  Cache* table_cache,
                                  WriteBufferManager* write_buffer_manager,
-                                 WriteController* write_controller,
-                                 BlockCacheTracer* const block_cache_tracer)
+                                 WriteController* write_controller)
     : max_column_family_(0),
-      dummy_cfd_(new ColumnFamilyData(
-          0, "", nullptr, nullptr, nullptr, ColumnFamilyOptions(), *db_options,
-          file_options, nullptr, block_cache_tracer)),
+      dummy_cfd_(new ColumnFamilyData(0, "", nullptr, nullptr, nullptr,
+                                      ColumnFamilyOptions(), *db_options,
+                                      env_options, nullptr)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
-      file_options_(file_options),
+      env_options_(env_options),
       table_cache_(table_cache),
       write_buffer_manager_(write_buffer_manager),
-      write_controller_(write_controller),
-      block_cache_tracer_(block_cache_tracer) {
+      write_controller_(write_controller) {
   // initialize linked list
   dummy_cfd_->prev_ = dummy_cfd_;
   dummy_cfd_->next_ = dummy_cfd_;
@@ -1374,12 +1165,14 @@ ColumnFamilySet::~ColumnFamilySet() {
     // cfd destructor will delete itself from column_family_data_
     auto cfd = column_family_data_.begin()->second;
     bool last_ref __attribute__((__unused__));
-    last_ref = cfd->UnrefAndTryDelete();
+    last_ref = cfd->Unref();
     assert(last_ref);
+    delete cfd;
   }
   bool dummy_last_ref __attribute__((__unused__));
-  dummy_last_ref = dummy_cfd_->UnrefAndTryDelete();
+  dummy_last_ref = dummy_cfd_->Unref();
   assert(dummy_last_ref);
+  delete dummy_cfd_;
 }
 
 ColumnFamilyData* ColumnFamilySet::GetDefault() const {
@@ -1429,7 +1222,7 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
   assert(column_families_.find(name) == column_families_.end());
   ColumnFamilyData* new_cfd = new ColumnFamilyData(
       id, name, dummy_versions, table_cache_, write_buffer_manager_, options,
-      *db_options_, file_options_, this, block_cache_tracer_);
+      *db_options_, env_options_, this);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   max_column_family_ = std::max(max_column_family_, id);

db/column_family.h

@@ -24,7 +24,6 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
-#include "trace_replay/block_cache_tracer.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
@@ -46,112 +45,6 @@ class InstrumentedMutexLock;
 struct SuperVersionContext;
 
 extern const double kIncSlowdownRatio;
-// This file contains a list of data structures for managing column family
-// level metadata.
-//
-// The basic relationships among classes declared here are illustrated as
-// following:
-//
-//       +----------------------+    +----------------------+   +--------+
-//   +---+ ColumnFamilyHandle 1 | +--+ ColumnFamilyHandle 2 |   | DBImpl |
-//   |   +----------------------+ |  +----------------------+   +----+---+
-//   | +--------------------------+                                  |
-//   | |                               +-----------------------------+
-//   | |                               |
-//   | | +-----------------------------v-------------------------------+
-//   | | |                                                             |
-//   | | |                      ColumnFamilySet                        |
-//   | | |                                                             |
-//   | | +-------------+--------------------------+----------------+---+
-//   | |               |                          |                |
-//   | +-------------------------------------+    |                |
-//   |                 |                     |    |                v
-//   |   +-------------v-------------+ +-----v----v---------+
-//   |   |                           | |                    |
-//   |   |     ColumnFamilyData 1    | | ColumnFamilyData 2 |    ......
-//   |   |                           | |                    |
-//   +--->                           | |                    |
-//       |                 +---------+ |                    |
-//       |                 | MemTable| |                    |
-//       |                 |  List   | |                    |
-//       +--------+---+--+-+----+----+ +--------------------++
-//                |   |  |      |
-//                |   |  |      |
-//                |   |  |      +-----------------------+
-//                |   |  +-----------+                  |
-//                v   +--------+     |                  |
-//       +--------+--------+   |     |                  |
-//       |                 |   |     |       +----------v----------+
-// +---> |SuperVersion 1.a +----------------->                     |
-//       |                 +------+  |       | MemTableListVersion |
-//       +---+-------------+   |  |  |       |                     |
-//           |                 |  |  |       +----+------------+---+
-//           |      current    |  |  |            |            |
-//           |   +-------------+  |  |mem         |            |
-//           |   |                |  |            |            |
-//         +-v---v-------+    +---v--v---+  +-----v----+  +----v-----+
-//         |             |    |          |  |          |  |          |
-//         | Version 1.a |    | memtable |  | memtable |  | memtable |
-//         |             |    |   1.a    |  |   1.b    |  |   1.c    |
-//         +-------------+    |          |  |          |  |          |
-//                            +----------+  +----------+  +----------+
-//
-// DBImpl keeps a ColumnFamilySet, which references to all column families by
-// pointing to respective ColumnFamilyData object of each column family.
-// This is how DBImpl can list and operate on all the column families.
-// ColumnFamilyHandle also points to ColumnFamilyData directly, so that
-// when a user executes a query, it can directly find memtables and Version
-// as well as SuperVersion to the column family, without going through
-// ColumnFamilySet.
-//
-// ColumnFamilySet points to the latest view of the LSM-tree (list of memtables
-// and SST files) indirectly, while ongoing operations may hold references
-// to a current or an out-of-date SuperVersion, which in turn points to a
-// point-in-time view of the LSM-tree. This guarantees the memtables and SST
-// files being operated on will not go away, until the SuperVersion is
-// unreferenced to 0 and destoryed.
-//
-// The following graph illustrates a possible referencing relationships:
-//
-// Column       +--------------+      current       +-----------+
-// Family +---->+              +------------------->+           |
-//  Data        | SuperVersion +----------+         | Version A |
-//              |      3       |   imm    |         |           |
-// Iter2 +----->+              |  +-------v------+  +-----------+
-//              +-----+--------+  | MemtableList +----------------> Empty
-//                    |           |   Version r  |  +-----------+
-//                    |           +--------------+  |           |
-//                    +------------------+   current| Version B |
-//              +--------------+         |   +----->+           |
-//              |              |         |   |      +-----+-----+
-// Compaction +>+ SuperVersion +-------------+            ^
-//    Job       |      2       +------+  |                |current
-//              |              +----+ |  |     mem        |    +------------+
-//              +--------------+    | |  +--------------------->            |
-//                                  | +------------------------> MemTable a |
-//                                  |          mem        |    |            |
-//              +--------------+    |                     |    +------------+
-//              |              +--------------------------+
-//  Iter1 +-----> SuperVersion |    |                          +------------+
-//              |      1       +------------------------------>+            |
-//              |              +-+  |        mem               | MemTable b |
-//              +--------------+ |  |                          |            |
-//                               |  |    +--------------+      +-----^------+
-//                               |  |imm | MemtableList |            |
-//                               |  +--->+   Version s  +------------+
-//                               |       +--------------+
-//                               |       +--------------+
-//                               |       | MemtableList |
-//                               +------>+   Version t  +-------->  Empty
-//                                 imm   +--------------+
-//
-// In this example, even if the current LSM-tree consists of Version A and
-// memtable a, which is also referenced by SuperVersion, two older SuperVersion
-// SuperVersion2 and Superversion1 still exist, and are referenced by a
-// compaction job and an old iterator Iter1, respectively. SuperVersion2
-// contains Version B, memtable a and memtable b; SuperVersion1 contains
-// Version B and memtable b (mutable). As a result, Version B and memtable b
-// are prevented from being destroyed or deleted.
 
 // ColumnFamilyHandleImpl is the class that clients use to access different
 // column families. It has non-trivial destructor, which gets called when client
@@ -198,7 +91,6 @@ class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
 struct SuperVersion {
   // Accessing members of this class is not thread-safe and requires external
   // synchronization (ie db mutex held or on write thread).
-  ColumnFamilyData* cfd;
   MemTable* mem;
   MemTableListVersion* imm;
   Version* current;
@@ -222,8 +114,8 @@ struct SuperVersion {
   // that needs to be deleted in to_delete vector. Unrefing those
   // objects needs to be done in the mutex
   void Cleanup();
-  void Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
-            MemTableListVersion* new_imm, Version* new_current);
+  void Init(MemTable* new_mem, MemTableListVersion* new_imm,
+            Version* new_current);
 
   // The value of dummy is not actually used. kSVInUse takes its address as a
   // mark in the thread local storage to indicate the SuperVersion is in use
@@ -247,9 +139,6 @@ extern Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options);
 extern Status CheckConcurrentWritesSupported(
     const ColumnFamilyOptions& cf_options);
 
-extern Status CheckCFPathsSupported(const DBOptions& db_options,
-                                    const ColumnFamilyOptions& cf_options);
-
 extern ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                            const ColumnFamilyOptions& src);
 // Wrap user defined table proproties collector factories `from cf_options`
@@ -276,7 +165,7 @@ class ColumnFamilyData {
   // Ref() can only be called from a context where the caller can guarantee
   // that ColumnFamilyData is alive (while holding a non-zero ref already,
   // holding a DB mutex, or as the leader in a write batch group).
-  void Ref() { refs_.fetch_add(1); }
+  void Ref() { refs_.fetch_add(1, std::memory_order_relaxed); }
 
   // Unref decreases the reference count, but does not handle deletion
   // when the count goes to 0.  If this method returns true then the
@@ -284,16 +173,11 @@ class ColumnFamilyData {
   // FreeDeadColumnFamilies().  Unref() can only be called while holding
   // a DB mutex, or during single-threaded recovery.
   bool Unref() {
-    int old_refs = refs_.fetch_sub(1);
+    int old_refs = refs_.fetch_sub(1, std::memory_order_relaxed);
     assert(old_refs > 0);
     return old_refs == 1;
   }
 
-  // UnrefAndTryDelete() decreases the reference count and do free if needed,
-  // return true if this is freed else false, UnrefAndTryDelete() can only
-  // be called while holding a DB mutex, or during single-threaded recovery.
-  bool UnrefAndTryDelete();
-
   // SetDropped() can only be called under following conditions:
   // 1) Holding a DB mutex,
   // 2) from single-threaded write thread, AND
@@ -324,7 +208,7 @@ class ColumnFamilyData {
   }
   FlushReason GetFlushReason() const { return flush_reason_; }
   // thread-safe
-  const FileOptions* soptions() const;
+  const EnvOptions* soptions() const;
   const ImmutableCFOptions* ioptions() const { return &ioptions_; }
   // REQUIRES: DB mutex held
   // This returns the MutableCFOptions used by current SuperVersion
@@ -345,13 +229,9 @@ class ColumnFamilyData {
 
   bool is_delete_range_supported() { return is_delete_range_supported_; }
 
-  // Validate CF options against DB options
-  static Status ValidateOptions(const DBOptions& db_options,
-                                const ColumnFamilyOptions& cf_options);
 #ifndef ROCKSDB_LITE
   // REQUIRES: DB mutex held
   Status SetOptions(
-      const DBOptions& db_options,
       const std::unordered_map<std::string, std::string>& options_map);
 #endif  // ROCKSDB_LITE
 
@@ -413,10 +293,9 @@ class ColumnFamilyData {
   // REQUIRES: DB mutex held
   Compaction* CompactRange(const MutableCFOptions& mutable_cf_options,
                            int input_level, int output_level,
-                           const CompactRangeOptions& compact_range_options,
-                           const InternalKey* begin, const InternalKey* end,
-                           InternalKey** compaction_end, bool* manual_conflict,
-                           uint64_t max_file_num_to_ignore);
+                           uint32_t output_path_id, const InternalKey* begin,
+                           const InternalKey* end, InternalKey** compaction_end,
+                           bool* manual_conflict);
 
   CompactionPicker* compaction_picker() { return compaction_picker_.get(); }
   // thread-safe
@@ -436,11 +315,11 @@ class ColumnFamilyData {
   SuperVersion* GetSuperVersion() { return super_version_; }
   // thread-safe
   // Return a already referenced SuperVersion to be used safely.
-  SuperVersion* GetReferencedSuperVersion(DBImpl* db);
+  SuperVersion* GetReferencedSuperVersion(InstrumentedMutex* db_mutex);
   // thread-safe
   // Get SuperVersion stored in thread local storage. If it does not exist,
   // get a reference from a current SuperVersion.
-  SuperVersion* GetThreadLocalSuperVersion(DBImpl* db);
+  SuperVersion* GetThreadLocalSuperVersion(InstrumentedMutex* db_mutex);
   // Try to return SuperVersion back to thread local storage. Retrun true on
   // success and false on failure. It fails when the thread local storage
   // contains anything other than SuperVersion::kSVInUse flag.
@@ -463,10 +342,10 @@ class ColumnFamilyData {
   void ResetThreadLocalSuperVersions();
 
   // Protected by DB mutex
-  void set_queued_for_flush(bool value) { queued_for_flush_ = value; }
-  void set_queued_for_compaction(bool value) { queued_for_compaction_ = value; }
-  bool queued_for_flush() { return queued_for_flush_; }
-  bool queued_for_compaction() { return queued_for_compaction_; }
+  void set_pending_flush(bool value) { pending_flush_ = value; }
+  void set_pending_compaction(bool value) { pending_compaction_ = value; }
+  bool pending_flush() { return pending_flush_; }
+  bool pending_compaction() { return pending_compaction_; }
 
   enum class WriteStallCause {
     kNone,
@@ -497,12 +376,6 @@ class ColumnFamilyData {
 
   Env::WriteLifeTimeHint CalculateSSTWriteHint(int level);
 
-  Status AddDirectories();
-
-  Directory* GetDataDir(size_t path_id) const;
-
-  ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
-
  private:
   friend class ColumnFamilySet;
   ColumnFamilyData(uint32_t id, const std::string& name,
@@ -510,9 +383,8 @@ class ColumnFamilyData {
                    WriteBufferManager* write_buffer_manager,
                    const ColumnFamilyOptions& options,
                    const ImmutableDBOptions& db_options,
-                   const FileOptions& file_options,
-                   ColumnFamilySet* column_family_set,
-                   BlockCacheTracer* const block_cache_tracer);
+                   const EnvOptions& env_options,
+                   ColumnFamilySet* column_family_set);
 
   uint32_t id_;
   const std::string name_;
@@ -574,11 +446,11 @@ class ColumnFamilyData {
   std::unique_ptr<WriteControllerToken> write_controller_token_;
 
   // If true --> this ColumnFamily is currently present in DBImpl::flush_queue_
-  bool queued_for_flush_;
+  bool pending_flush_;
 
   // If true --> this ColumnFamily is currently present in
   // DBImpl::compaction_queue_
-  bool queued_for_compaction_;
+  bool pending_compaction_;
 
   uint64_t prev_compaction_needed_bytes_;
 
@@ -587,9 +459,6 @@ class ColumnFamilyData {
 
   // Memtable id to track flush.
   std::atomic<uint64_t> last_memtable_id_;
-
-  // Directories corresponding to cf_paths.
-  std::vector<std::unique_ptr<Directory>> data_dirs_;
 };
 
 // ColumnFamilySet has interesting thread-safety requirements
@@ -638,10 +507,9 @@ class ColumnFamilySet {
 
   ColumnFamilySet(const std::string& dbname,
                   const ImmutableDBOptions* db_options,
-                  const FileOptions& file_options, Cache* table_cache,
+                  const EnvOptions& env_options, Cache* table_cache,
                   WriteBufferManager* write_buffer_manager,
-                  WriteController* write_controller,
-                  BlockCacheTracer* const block_cache_tracer);
+                  WriteController* write_controller);
   ~ColumnFamilySet();
 
   ColumnFamilyData* GetDefault() const;
@@ -696,11 +564,10 @@ class ColumnFamilySet {
 
   const std::string db_name_;
   const ImmutableDBOptions* const db_options_;
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
   Cache* table_cache_;
   WriteBufferManager* write_buffer_manager_;
   WriteController* write_controller_;
-  BlockCacheTracer* const block_cache_tracer_;
 };
 
 // We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access

db/compact_files_test.cc

@@ -10,13 +10,13 @@
 #include <thread>
 #include <vector>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
 
 namespace rocksdb {
 
@@ -24,7 +24,7 @@ class CompactFilesTest : public testing::Test {
  public:
   CompactFilesTest() {
     env_ = Env::Default();
-    db_name_ = test::PerThreadDBPath("compact_files_test");
+    db_name_ = test::TmpDir(env_) + "/compact_files_test";
   }
 
   std::string db_name_;
@@ -35,9 +35,9 @@ class CompactFilesTest : public testing::Test {
 class FlushedFileCollector : public EventListener {
  public:
   FlushedFileCollector() {}
-  ~FlushedFileCollector() override {}
+  ~FlushedFileCollector() {}
 
-  void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
+  virtual void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
     std::lock_guard<std::mutex> lock(mutex_);
     flushed_files_.push_back(info.file_path);
   }
@@ -256,9 +256,9 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
 TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   class FilterWithGet : public CompactionFilter {
    public:
-    bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-                std::string* /*new_value*/,
-                bool* /*value_changed*/) const override {
+    virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                        const Slice& /*value*/, std::string* /*new_value*/,
+                        bool* /*value_changed*/) const override {
       if (db_ == nullptr) {
         return true;
       }
@@ -271,7 +271,7 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
       db_ = db;
     }
 
-    const char* Name() const override { return "FilterWithGet"; }
+    virtual const char* Name() const override { return "FilterWithGet"; }
 
    private:
     DB* db_;
@@ -308,100 +308,6 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   delete db;
 }
 
-TEST_F(CompactFilesTest, SentinelCompressionType) {
-  if (!Zlib_Supported()) {
-    fprintf(stderr, "zlib compression not supported, skip this test\n");
-    return;
-  }
-  if (!Snappy_Supported()) {
-    fprintf(stderr, "snappy compression not supported, skip this test\n");
-    return;
-  }
-  // Check that passing `CompressionType::kDisableCompressionOption` to
-  // `CompactFiles` causes it to use the column family compression options.
-  for (auto compaction_style :
-       {CompactionStyle::kCompactionStyleLevel,
-        CompactionStyle::kCompactionStyleUniversal,
-        CompactionStyle::kCompactionStyleNone}) {
-    DestroyDB(db_name_, Options());
-    Options options;
-    options.compaction_style = compaction_style;
-    // L0: Snappy, L1: ZSTD, L2: Snappy
-    options.compression_per_level = {CompressionType::kSnappyCompression,
-                                     CompressionType::kZlibCompression,
-                                     CompressionType::kSnappyCompression};
-    options.create_if_missing = true;
-    FlushedFileCollector* collector = new FlushedFileCollector();
-    options.listeners.emplace_back(collector);
-    DB* db = nullptr;
-    ASSERT_OK(DB::Open(options, db_name_, &db));
-
-    db->Put(WriteOptions(), "key", "val");
-    db->Flush(FlushOptions());
-
-    auto l0_files = collector->GetFlushedFiles();
-    ASSERT_EQ(1, l0_files.size());
-
-    // L0->L1 compaction, so output should be ZSTD-compressed
-    CompactionOptions compaction_opts;
-    compaction_opts.compression = CompressionType::kDisableCompressionOption;
-    ASSERT_OK(db->CompactFiles(compaction_opts, l0_files, 1));
-
-    rocksdb::TablePropertiesCollection all_tables_props;
-    ASSERT_OK(db->GetPropertiesOfAllTables(&all_tables_props));
-    for (const auto& name_and_table_props : all_tables_props) {
-      ASSERT_EQ(CompressionTypeToString(CompressionType::kZlibCompression),
-                name_and_table_props.second->compression_name);
-    }
-    delete db;
-  }
-}
-
-TEST_F(CompactFilesTest, GetCompactionJobInfo) {
-  Options options;
-  options.create_if_missing = true;
-  // Disable RocksDB background compaction.
-  options.compaction_style = kCompactionStyleNone;
-  options.level0_slowdown_writes_trigger = 1000;
-  options.level0_stop_writes_trigger = 1000;
-  options.write_buffer_size = 65536;
-  options.max_write_buffer_number = 2;
-  options.compression = kNoCompression;
-  options.max_compaction_bytes = 5000;
-
-  // Add listener
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  // create couple files
-  for (int i = 0; i < 500; ++i) {
-    db->Put(WriteOptions(), ToString(i), std::string(1000, 'a' + (i % 26)));
-  }
-  reinterpret_cast<DBImpl*>(db)->TEST_WaitForFlushMemTable();
-  auto l0_files_1 = collector->GetFlushedFiles();
-  CompactionOptions co;
-  co.compression = CompressionType::kLZ4Compression;
-  CompactionJobInfo compaction_job_info{};
-  ASSERT_OK(
-      db->CompactFiles(co, l0_files_1, 0, -1, nullptr, &compaction_job_info));
-  ASSERT_EQ(compaction_job_info.base_input_level, 0);
-  ASSERT_EQ(compaction_job_info.cf_id, db->DefaultColumnFamily()->GetID());
-  ASSERT_EQ(compaction_job_info.cf_name, db->DefaultColumnFamily()->GetName());
-  ASSERT_EQ(compaction_job_info.compaction_reason,
-            CompactionReason::kManualCompaction);
-  ASSERT_EQ(compaction_job_info.compression, CompressionType::kLZ4Compression);
-  ASSERT_EQ(compaction_job_info.output_level, 0);
-  ASSERT_OK(compaction_job_info.status);
-  // no assertion failure
-  delete db;
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
@@ -412,7 +318,7 @@ int main(int argc, char** argv) {
 #else
 #include <stdio.h>
 
-int main(int /*argc*/, char** /*argv*/) {
+int main(int argc, char** argv) {
   fprintf(stderr,
           "SKIPPED as DBImpl::CompactFiles is not supported in ROCKSDB_LITE\n");
   return 0;

db/compacted_db_impl.cc

@@ -5,7 +5,7 @@
 
 #ifndef ROCKSDB_LITE
 #include "db/compacted_db_impl.h"
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/version_set.h"
 #include "table/get_context.h"
 
@@ -25,22 +25,32 @@ CompactedDBImpl::~CompactedDBImpl() {
 }
 
 size_t CompactedDBImpl::FindFile(const Slice& key) {
+  size_t left = 0;
   size_t right = files_.num_files - 1;
-  auto cmp = [&](const FdWithKeyRange& f, const Slice& k) -> bool {
-    return user_comparator_->Compare(ExtractUserKey(f.largest_key), k) < 0;
-  };
-  return static_cast<size_t>(std::lower_bound(files_.files,
-                            files_.files + right, key, cmp) - files_.files);
+  while (left < right) {
+    size_t mid = (left + right) >> 1;
+    const FdWithKeyRange& f = files_.files[mid];
+    if (user_comparator_->Compare(ExtractUserKey(f.largest_key), key) < 0) {
+      // Key at "mid.largest" is < "target".  Therefore all
+      // files at or before "mid" are uninteresting.
+      left = mid + 1;
+    } else {
+      // Key at "mid.largest" is >= "target".  Therefore all files
+      // after "mid" are uninteresting.
+      right = mid;
+    }
+  }
+  return right;
 }
 
 Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                             const Slice& key, PinnableSlice* value) {
   GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                          GetContext::kNotFound, key, value, nullptr, nullptr,
-                         true, nullptr, nullptr);
+                         nullptr, nullptr);
   LookupKey lkey(key, kMaxSequenceNumber);
-  files_.files[FindFile(key)].fd.table_reader->Get(options, lkey.internal_key(),
-                                                   &get_context, nullptr);
+  files_.files[FindFile(key)].fd.table_reader->Get(
+      options, lkey.internal_key(), &get_context);
   if (get_context.State() == GetContext::kFound) {
     return Status::OK();
   }
@@ -70,9 +80,9 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
       std::string& value = (*values)[idx];
       GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                              GetContext::kNotFound, keys[idx], &pinnable_val,
-                             nullptr, nullptr, true, nullptr, nullptr);
+                             nullptr, nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
-      r->Get(options, lkey.internal_key(), &get_context, nullptr);
+      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();
@@ -147,7 +157,6 @@ Status CompactedDBImpl::Open(const Options& options,
   std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
   Status s = db->Init(options);
   if (s.ok()) {
-    db->StartTimedTasks();
     ROCKS_LOG_INFO(db->immutable_db_options_.info_log,
                    "Opened the db as fully compacted mode");
     LogFlush(db->immutable_db_options_.info_log);

db/compacted_db_impl.h

@@ -5,19 +5,15 @@
 
 #pragma once
 #ifndef ROCKSDB_LITE
-#include <string>
+#include "db/db_impl.h"
 #include <vector>
-#include "db/db_impl/db_impl.h"
+#include <string>
 
 namespace rocksdb {
 
 class CompactedDBImpl : public DBImpl {
  public:
   CompactedDBImpl(const DBOptions& options, const std::string& dbname);
-  // No copying allowed
-  CompactedDBImpl(const CompactedDBImpl&) = delete;
-  void operator=(const CompactedDBImpl&) = delete;
-
   virtual ~CompactedDBImpl();
 
   static Status Open(const Options& options, const std::string& dbname,
@@ -71,11 +67,10 @@ class CompactedDBImpl : public DBImpl {
   virtual Status EnableFileDeletions(bool /*force*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  virtual Status GetLiveFiles(std::vector<std::string>& ret,
-                              uint64_t* manifest_file_size,
-                              bool /*flush_memtable*/) override {
-    return DBImpl::GetLiveFiles(ret, manifest_file_size,
-                                false /* flush_memtable */);
+  virtual Status GetLiveFiles(std::vector<std::string>&,
+                              uint64_t* /*manifest_file_size*/,
+                              bool /*flush_memtable*/ = true) override {
+    return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DBImpl::Flush;
   virtual Status Flush(const FlushOptions& /*options*/,
@@ -89,15 +84,6 @@ class CompactedDBImpl : public DBImpl {
       const IngestExternalFileOptions& /*ingestion_options*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  using DB::CreateColumnFamilyWithImport;
-  virtual Status CreateColumnFamilyWithImport(
-      const ColumnFamilyOptions& /*options*/,
-      const std::string& /*column_family_name*/,
-      const ImportColumnFamilyOptions& /*import_options*/,
-      const ExportImportFilesMetaData& /*metadata*/,
-      ColumnFamilyHandle** /*handle*/) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
 
  private:
   friend class DB;
@@ -108,6 +94,10 @@ class CompactedDBImpl : public DBImpl {
   Version* version_;
   const Comparator* user_comparator_;
   LevelFilesBrief files_;
+
+  // No copying allowed
+  CompactedDBImpl(const CompactedDBImpl&);
+  void operator=(const CompactedDBImpl&);
 };
 }
 #endif  // ROCKSDB_LITE

db/compaction.cc

@@ -7,54 +7,22 @@
 // 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 <cinttypes>
+#include "db/compaction.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <vector>
 
 #include "db/column_family.h"
-#include "db/compaction/compaction.h"
 #include "rocksdb/compaction_filter.h"
-#include "test_util/sync_point.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
 namespace rocksdb {
 
-const uint64_t kRangeTombstoneSentinel =
-    PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b) {
-  auto c = user_cmp->Compare(a.user_key(), b.user_key());
-  if (c != 0) {
-    return c;
-  }
-  auto a_footer = ExtractInternalKeyFooter(a.Encode());
-  auto b_footer = ExtractInternalKeyFooter(b.Encode());
-  if (a_footer == kRangeTombstoneSentinel) {
-    if (b_footer != kRangeTombstoneSentinel) {
-      return -1;
-    }
-  } else if (b_footer == kRangeTombstoneSentinel) {
-    return 1;
-  }
-  return 0;
-}
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
-                      const InternalKey& b) {
-  if (a == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, *a, b);
-}
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey* b) {
-  if (b == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, a, *b);
-}
-
 uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
   uint64_t sum = 0;
   for (size_t i = 0; i < files.size() && files[i]; i++) {
@@ -113,49 +81,6 @@ void Compaction::GetBoundaryKeys(
   }
 }
 
-std::vector<CompactionInputFiles> Compaction::PopulateWithAtomicBoundaries(
-    VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs) {
-  const Comparator* ucmp = vstorage->InternalComparator()->user_comparator();
-  for (size_t i = 0; i < inputs.size(); i++) {
-    if (inputs[i].level == 0 || inputs[i].files.empty()) {
-      continue;
-    }
-    inputs[i].atomic_compaction_unit_boundaries.reserve(inputs[i].files.size());
-    AtomicCompactionUnitBoundary cur_boundary;
-    size_t first_atomic_idx = 0;
-    auto add_unit_boundary = [&](size_t to) {
-      if (first_atomic_idx == to) return;
-      for (size_t k = first_atomic_idx; k < to; k++) {
-        inputs[i].atomic_compaction_unit_boundaries.push_back(cur_boundary);
-      }
-      first_atomic_idx = to;
-    };
-    for (size_t j = 0; j < inputs[i].files.size(); j++) {
-      const auto* f = inputs[i].files[j];
-      if (j == 0) {
-        // First file in a level.
-        cur_boundary.smallest = &f->smallest;
-        cur_boundary.largest = &f->largest;
-      } else if (sstableKeyCompare(ucmp, *cur_boundary.largest, f->smallest) ==
-                 0) {
-        // SSTs overlap but the end key of the previous file was not
-        // artificially extended by a range tombstone. Extend the current
-        // boundary.
-        cur_boundary.largest = &f->largest;
-      } else {
-        // Atomic compaction unit has ended.
-        add_unit_boundary(j);
-        cur_boundary.smallest = &f->smallest;
-        cur_boundary.largest = &f->largest;
-      }
-    }
-    add_unit_boundary(inputs[i].files.size());
-    assert(inputs[i].files.size() ==
-           inputs[i].atomic_compaction_unit_boundaries.size());
-  }
-  return inputs;
-}
-
 // helper function to determine if compaction is creating files at the
 // bottommost level
 bool Compaction::IsBottommostLevel(
@@ -209,8 +134,6 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
                        int _output_level, uint64_t _target_file_size,
                        uint64_t _max_compaction_bytes, uint32_t _output_path_id,
                        CompressionType _compression,
-                       CompressionOptions _compression_opts,
-                       uint32_t _max_subcompactions,
                        std::vector<FileMetaData*> _grandparents,
                        bool _manual_compaction, double _score,
                        bool _deletion_compaction,
@@ -220,7 +143,6 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
       output_level_(_output_level),
       max_output_file_size_(_target_file_size),
       max_compaction_bytes_(_max_compaction_bytes),
-      max_subcompactions_(_max_subcompactions),
       immutable_cf_options_(_immutable_cf_options),
       mutable_cf_options_(_mutable_cf_options),
       input_version_(nullptr),
@@ -228,9 +150,8 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
       cfd_(nullptr),
       output_path_id_(_output_path_id),
       output_compression_(_compression),
-      output_compression_opts_(_compression_opts),
       deletion_compaction_(_deletion_compaction),
-      inputs_(PopulateWithAtomicBoundaries(vstorage, std::move(_inputs))),
+      inputs_(std::move(_inputs)),
       grandparents_(std::move(_grandparents)),
       score_(_score),
       bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
@@ -242,15 +163,6 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
   if (is_manual_compaction_) {
     compaction_reason_ = CompactionReason::kManualCompaction;
   }
-  if (max_subcompactions_ == 0) {
-    max_subcompactions_ = immutable_cf_options_.max_subcompactions;
-  }
-  if (!bottommost_level_) {
-    // Currently we only enable dictionary compression during compaction to the
-    // bottommost level.
-    output_compression_opts_.max_dict_bytes = 0;
-    output_compression_opts_.zstd_max_train_bytes = 0;
-  }
 
 #ifndef NDEBUG
   for (size_t i = 1; i < inputs_.size(); ++i) {
@@ -275,7 +187,9 @@ Compaction::~Compaction() {
     input_version_->Unref();
   }
   if (cfd_ != nullptr) {
-    cfd_->UnrefAndTryDelete();
+    if (cfd_->Unref()) {
+      delete cfd_;
+    }
   }
 }
 
@@ -372,8 +286,8 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
         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 it may
-            // exist beyond output level
+            // Key falls in this file's range, so definitely
+            // exists beyond output level
             return false;
           }
           break;
@@ -410,14 +324,12 @@ const char* Compaction::InputLevelSummary(
     if (!is_first) {
       len +=
           snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len, " + ");
-      len = std::min(len, static_cast<int>(sizeof(scratch->buffer)));
     } else {
       is_first = false;
     }
     len += snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
                     "%" ROCKSDB_PRIszt "@%d", input_level.size(),
                     input_level.level);
-    len = std::min(len, static_cast<int>(sizeof(scratch->buffer)));
   }
   snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
            " files to L%d", output_level());
@@ -530,7 +442,7 @@ bool Compaction::IsOutputLevelEmpty() const {
 }
 
 bool Compaction::ShouldFormSubcompactions() const {
-  if (max_subcompactions_ <= 1 || cfd_ == nullptr) {
+  if (immutable_cf_options_.max_subcompactions <= 1 || cfd_ == nullptr) {
     return false;
   }
   if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
@@ -543,20 +455,17 @@ bool Compaction::ShouldFormSubcompactions() const {
   }
 }
 
-uint64_t Compaction::MinInputFileOldestAncesterTime() const {
-  uint64_t min_oldest_ancester_time = port::kMaxUint64;
+uint64_t Compaction::MaxInputFileCreationTime() const {
+  uint64_t max_creation_time = 0;
   for (const auto& file : inputs_[0].files) {
-    uint64_t oldest_ancester_time = file->TryGetOldestAncesterTime();
-    if (oldest_ancester_time != 0) {
-      min_oldest_ancester_time =
-          std::min(min_oldest_ancester_time, oldest_ancester_time);
+    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 min_oldest_ancester_time;
-}
-
-int Compaction::GetInputBaseLevel() const {
-  return input_vstorage_->base_level();
+  return max_creation_time;
 }
 
 }  // namespace rocksdb

db/compaction.h

@@ -9,51 +9,17 @@
 
 #pragma once
 #include "db/version_set.h"
-#include "memory/arena.h"
 #include "options/cf_options.h"
+#include "util/arena.h"
 #include "util/autovector.h"
 
 namespace rocksdb {
-// The file contains class Compaction, as well as some helper functions
-// and data structures used by the class.
-
-// Utility for comparing sstable boundary keys. Returns -1 if either a or b is
-// null which provides the property that a==null indicates a key that is less
-// than any key and b==null indicates a key that is greater than any key. Note
-// that the comparison is performed primarily on the user-key portion of the
-// key. If the user-keys compare equal, an additional test is made to sort
-// range tombstone sentinel keys before other keys with the same user-key. The
-// result is that 2 user-keys will compare equal if they differ purely on
-// their sequence number and value, but the range tombstone sentinel for that
-// user-key will compare not equal. This is necessary because the range
-// tombstone sentinel key is set as the largest key for an sstable even though
-// that key never appears in the database. We don't want adjacent sstables to
-// be considered overlapping if they are separated by the range tombstone
-// sentinel.
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b);
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
-                      const InternalKey& b);
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey* b);
-
-// An AtomicCompactionUnitBoundary represents a range of keys [smallest,
-// largest] that exactly spans one ore more neighbouring SSTs on the same
-// level. Every pair of  SSTs in this range "overlap" (i.e., the largest
-// user key of one file is the smallest user key of the next file). These
-// boundaries are propagated down to RangeDelAggregator during compaction
-// to provide safe truncation boundaries for range tombstones.
-struct AtomicCompactionUnitBoundary {
-  const InternalKey* smallest = nullptr;
-  const InternalKey* largest = nullptr;
-};
 
 // The structure that manages compaction input files associated
 // with the same physical level.
 struct CompactionInputFiles {
   int level;
   std::vector<FileMetaData*> files;
-  std::vector<AtomicCompactionUnitBoundary> atomic_compaction_unit_boundaries;
   inline bool empty() const { return files.empty(); }
   inline size_t size() const { return files.size(); }
   inline void clear() { files.clear(); }
@@ -65,7 +31,7 @@ class ColumnFamilyData;
 class VersionStorageInfo;
 class CompactionFilter;
 
-// A Compaction encapsulates metadata about a compaction.
+// A Compaction encapsulates information about a compaction.
 class Compaction {
  public:
   Compaction(VersionStorageInfo* input_version,
@@ -74,7 +40,6 @@ class Compaction {
              std::vector<CompactionInputFiles> inputs, int output_level,
              uint64_t target_file_size, uint64_t max_compaction_bytes,
              uint32_t output_path_id, CompressionType compression,
-             CompressionOptions compression_opts, uint32_t max_subcompactions,
              std::vector<FileMetaData*> grandparents,
              bool manual_compaction = false, double score = -1,
              bool deletion_compaction = false,
@@ -130,12 +95,6 @@ class Compaction {
     return inputs_[compaction_input_level][i];
   }
 
-  const std::vector<AtomicCompactionUnitBoundary>* boundaries(
-      size_t compaction_input_level) const {
-    assert(compaction_input_level < inputs_.size());
-    return &inputs_[compaction_input_level].atomic_compaction_unit_boundaries;
-  }
-
   // Returns the list of file meta data of the specified compaction
   // input level.
   // REQUIREMENT: "compaction_input_level" must be >= 0 and
@@ -159,11 +118,6 @@ class Compaction {
   // What compression for output
   CompressionType output_compression() const { return output_compression_; }
 
-  // What compression options for output
-  CompressionOptions output_compression_opts() const {
-    return output_compression_opts_;
-  }
-
   // Whether need to write output file to second DB path.
   uint32_t output_path_id() const { return output_path_id_; }
 
@@ -279,8 +233,6 @@ class Compaction {
 
   Slice GetLargestUserKey() const { return largest_user_key_; }
 
-  int GetInputBaseLevel() const;
-
   CompactionReason compaction_reason() { return compaction_reason_; }
 
   const std::vector<FileMetaData*>& grandparents() const {
@@ -289,9 +241,7 @@ class Compaction {
 
   uint64_t max_compaction_bytes() const { return max_compaction_bytes_; }
 
-  uint32_t max_subcompactions() const { return max_subcompactions_; }
-
-  uint64_t MinInputFileOldestAncesterTime() const;
+  uint64_t MaxInputFileCreationTime() const;
 
  private:
   // mark (or clear) all files that are being compacted
@@ -302,13 +252,6 @@ class Compaction {
                               const std::vector<CompactionInputFiles>& inputs,
                               Slice* smallest_key, Slice* largest_key);
 
-  // Get the atomic file boundaries for all files in the compaction. Necessary
-  // in order to avoid the scenario described in
-  // https://github.com/facebook/rocksdb/pull/4432#discussion_r221072219 and plumb
-  // down appropriate key boundaries to RangeDelAggregator during compaction.
-  static std::vector<CompactionInputFiles> PopulateWithAtomicBoundaries(
-      VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs);
-
   // helper function to determine if compaction with inputs and storage is
   // bottommost
   static bool IsBottommostLevel(
@@ -324,7 +267,6 @@ class Compaction {
   const int output_level_;  // levels to which output files are stored
   uint64_t max_output_file_size_;
   uint64_t max_compaction_bytes_;
-  uint32_t max_subcompactions_;
   const ImmutableCFOptions immutable_cf_options_;
   const MutableCFOptions mutable_cf_options_;
   Version* input_version_;
@@ -335,7 +277,6 @@ class Compaction {
 
   const uint32_t output_path_id_;
   CompressionType output_compression_;
-  CompressionOptions output_compression_opts_;
   // If true, then the comaction can be done by simply deleting input files.
   const bool deletion_compaction_;
 
@@ -378,7 +319,7 @@ class Compaction {
   CompactionReason compaction_reason_;
 };
 
-// Return sum of sizes of all files in `files`.
+// Utility function
 extern uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);
 
 }  // namespace rocksdb

db/compaction/compaction_picker_fifo.cc

@@ -1,242 +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/compaction_picker_fifo.h"
-#ifndef ROCKSDB_LITE
-
-#include <cinttypes>
-#include <string>
-#include <vector>
-#include "db/column_family.h"
-#include "logging/log_buffer.h"
-#include "util/string_util.h"
-
-namespace rocksdb {
-namespace {
-uint64_t GetTotalFilesSize(const std::vector<FileMetaData*>& files) {
-  uint64_t total_size = 0;
-  for (const auto& f : files) {
-    total_size += f->fd.file_size;
-  }
-  return total_size;
-}
-}  // anonymous namespace
-
-bool FIFOCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  const int kLevel0 = 0;
-  return vstorage->CompactionScore(kLevel0) >= 1;
-}
-
-Compaction* FIFOCompactionPicker::PickTTLCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(mutable_cf_options.ttl > 0);
-
-  const int kLevel0 = 0;
-  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
-  uint64_t total_size = GetTotalFilesSize(level_files);
-
-  int64_t _current_time;
-  auto status = ioptions_.env->GetCurrentTime(&_current_time);
-  if (!status.ok()) {
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: Couldn't get current time: %s. "
-                     "Not doing compactions based on TTL. ",
-                     cf_name.c_str(), status.ToString().c_str());
-    return nullptr;
-  }
-  const uint64_t current_time = static_cast<uint64_t>(_current_time);
-
-  if (!level0_compactions_in_progress_.empty()) {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: Already executing compaction. No need "
-        "to run parallel compactions since compactions are very fast",
-        cf_name.c_str());
-    return nullptr;
-  }
-
-  std::vector<CompactionInputFiles> inputs;
-  inputs.emplace_back();
-  inputs[0].level = 0;
-
-  // avoid underflow
-  if (current_time > mutable_cf_options.ttl) {
-    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-      auto f = *ritr;
-      if (f->fd.table_reader != nullptr &&
-          f->fd.table_reader->GetTableProperties() != nullptr) {
-        auto creation_time =
-            f->fd.table_reader->GetTableProperties()->creation_time;
-        if (creation_time == 0 ||
-            creation_time >= (current_time - mutable_cf_options.ttl)) {
-          break;
-        }
-        total_size -= f->compensated_file_size;
-        inputs[0].files.push_back(f);
-      }
-    }
-  }
-
-  // Return a nullptr and proceed to size-based FIFO compaction if:
-  // 1. there are no files older than ttl OR
-  // 2. there are a few files older than ttl, but deleting them will not bring
-  //    the total size to be less than max_table_files_size threshold.
-  if (inputs[0].files.empty() ||
-      total_size >
-          mutable_cf_options.compaction_options_fifo.max_table_files_size) {
-    return nullptr;
-  }
-
-  for (const auto& f : inputs[0].files) {
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: picking file %" PRIu64
-                     " with creation time %" PRIu64 " for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(),
-                     f->fd.table_reader->GetTableProperties()->creation_time);
-  }
-
-  Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
-      {}, /* is manual */ false, vstorage->CompactionScore(0),
-      /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::PickSizeCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  const int kLevel0 = 0;
-  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
-  uint64_t total_size = GetTotalFilesSize(level_files);
-
-  if (total_size <=
-          mutable_cf_options.compaction_options_fifo.max_table_files_size ||
-      level_files.size() == 0) {
-    // total size not exceeded
-    if (mutable_cf_options.compaction_options_fifo.allow_compaction &&
-        level_files.size() > 0) {
-      CompactionInputFiles comp_inputs;
-      // try to prevent same files from being compacted multiple times, which
-      // could produce large files that may never TTL-expire. Achieve this by
-      // disallowing compactions with files larger than memtable (inflate its
-      // size by 10% to account for uncompressed L0 files that may have size
-      // slightly greater than memtable size limit).
-      size_t max_compact_bytes_per_del_file =
-          static_cast<size_t>(MultiplyCheckOverflow(
-              static_cast<uint64_t>(mutable_cf_options.write_buffer_size),
-              1.1));
-      if (FindIntraL0Compaction(
-              level_files,
-              mutable_cf_options
-                  .level0_file_num_compaction_trigger /* min_files_to_compact */
-              ,
-              max_compact_bytes_per_del_file,
-              mutable_cf_options.max_compaction_bytes, &comp_inputs)) {
-        Compaction* c = new Compaction(
-            vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
-            16 * 1024 * 1024 /* output file size limit */,
-            0 /* max compaction bytes, not applicable */,
-            0 /* output path ID */, mutable_cf_options.compression,
-            ioptions_.compression_opts, 0 /* max_subcompactions */, {},
-            /* is manual */ false, vstorage->CompactionScore(0),
-            /* is deletion compaction */ false,
-            CompactionReason::kFIFOReduceNumFiles);
-        return c;
-      }
-    }
-
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: nothing to do. Total size %" PRIu64
-        ", max size %" PRIu64 "\n",
-        cf_name.c_str(), total_size,
-        mutable_cf_options.compaction_options_fifo.max_table_files_size);
-    return nullptr;
-  }
-
-  if (!level0_compactions_in_progress_.empty()) {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: Already executing compaction. No need "
-        "to run parallel compactions since compactions are very fast",
-        cf_name.c_str());
-    return nullptr;
-  }
-
-  std::vector<CompactionInputFiles> inputs;
-  inputs.emplace_back();
-  inputs[0].level = 0;
-
-  for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-    auto f = *ritr;
-    total_size -= f->compensated_file_size;
-    inputs[0].files.push_back(f);
-    char tmp_fsize[16];
-    AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: picking file %" PRIu64
-                     " with size %s for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
-    if (total_size <=
-        mutable_cf_options.compaction_options_fifo.max_table_files_size) {
-      break;
-    }
-  }
-
-  Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
-      {}, /* is manual */ false, vstorage->CompactionScore(0),
-      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber /*earliest_memtable_seqno*/) {
-  assert(vstorage->num_levels() == 1);
-
-  Compaction* c = nullptr;
-  if (mutable_cf_options.ttl > 0) {
-    c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
-  }
-  if (c == nullptr) {
-    c = PickSizeCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
-  }
-  RegisterCompaction(c);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::CompactRange(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, int input_level, int output_level,
-    const CompactRangeOptions& /*compact_range_options*/,
-    const InternalKey* /*begin*/, const InternalKey* /*end*/,
-    InternalKey** compaction_end, bool* /*manual_conflict*/,
-    uint64_t /*max_file_num_to_ignore*/) {
-#ifdef NDEBUG
-  (void)input_level;
-  (void)output_level;
-#endif
-  assert(input_level == 0);
-  assert(output_level == 0);
-  *compaction_end = nullptr;
-  LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, ioptions_.info_log);
-  Compaction* c =
-      PickCompaction(cf_name, mutable_cf_options, vstorage, &log_buffer);
-  log_buffer.FlushBufferToLog();
-  return c;
-}
-
-}  // namespace rocksdb
-#endif  // !ROCKSDB_LITE

db/compaction/compaction_picker_fifo.h

@@ -1,53 +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/compaction_picker.h"
-
-namespace rocksdb {
-class FIFOCompactionPicker : public CompactionPicker {
- public:
-  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
-                       const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* version, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
-
-  virtual Compaction* CompactRange(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, int input_level, int output_level,
-      const CompactRangeOptions& compact_range_options,
-      const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore) override;
-
-  // The maximum allowed output level.  Always returns 0.
-  virtual int MaxOutputLevel() const override { return 0; }
-
-  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);
-};
-}  // namespace rocksdb
-#endif  // !ROCKSDB_LITE

db/compaction/compaction_picker_level.cc

@@ -1,558 +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 <string>
-#include <utility>
-#include <vector>
-
-#include "db/compaction/compaction_picker_level.h"
-#include "logging/log_buffer.h"
-#include "test_util/sync_point.h"
-
-namespace rocksdb {
-
-bool LevelCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  if (!vstorage->ExpiredTtlFiles().empty()) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForPeriodicCompaction().empty()) {
-    return true;
-  }
-  if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  for (int i = 0; i <= vstorage->MaxInputLevel(); i++) {
-    if (vstorage->CompactionScore(i) >= 1) {
-      return true;
-    }
-  }
-  return false;
-}
-
-namespace {
-// A class to build a leveled compaction step-by-step.
-class LevelCompactionBuilder {
- public:
-  LevelCompactionBuilder(const std::string& cf_name,
-                         VersionStorageInfo* vstorage,
-                         SequenceNumber earliest_mem_seqno,
-                         CompactionPicker* compaction_picker,
-                         LogBuffer* log_buffer,
-                         const MutableCFOptions& mutable_cf_options,
-                         const ImmutableCFOptions& ioptions)
-      : cf_name_(cf_name),
-        vstorage_(vstorage),
-        earliest_mem_seqno_(earliest_mem_seqno),
-        compaction_picker_(compaction_picker),
-        log_buffer_(log_buffer),
-        mutable_cf_options_(mutable_cf_options),
-        ioptions_(ioptions) {}
-
-  // Pick and return a compaction.
-  Compaction* PickCompaction();
-
-  // Pick the initial files to compact to the next level. (or together
-  // in Intra-L0 compactions)
-  void SetupInitialFiles();
-
-  // If the initial files are from L0 level, pick other L0
-  // files if needed.
-  bool SetupOtherL0FilesIfNeeded();
-
-  // Based on initial files, setup other files need to be compacted
-  // in this compaction, accordingly.
-  bool SetupOtherInputsIfNeeded();
-
-  Compaction* GetCompaction();
-
-  // 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 PickFileToCompact();
-
-  // For L0->L0, picks the longest span of files that aren't currently
-  // undergoing compaction for which work-per-deleted-file decreases. The span
-  // always starts from the newest L0 file.
-  //
-  // Intra-L0 compaction is independent of all other files, so it can be
-  // performed even when L0->base_level compactions are blocked.
-  //
-  // Returns true if `inputs` is populated with a span of files to be compacted;
-  // otherwise, returns false.
-  bool PickIntraL0Compaction();
-
-  void PickExpiredTtlFiles();
-
-  void PickFilesMarkedForPeriodicCompaction();
-
-  const std::string& cf_name_;
-  VersionStorageInfo* vstorage_;
-  SequenceNumber earliest_mem_seqno_;
-  CompactionPicker* compaction_picker_;
-  LogBuffer* log_buffer_;
-  int start_level_ = -1;
-  int output_level_ = -1;
-  int parent_index_ = -1;
-  int base_index_ = -1;
-  double start_level_score_ = 0;
-  bool is_manual_ = false;
-  CompactionInputFiles start_level_inputs_;
-  std::vector<CompactionInputFiles> compaction_inputs_;
-  CompactionInputFiles output_level_inputs_;
-  std::vector<FileMetaData*> grandparents_;
-  CompactionReason compaction_reason_ = CompactionReason::kUnknown;
-
-  const MutableCFOptions& mutable_cf_options_;
-  const ImmutableCFOptions& ioptions_;
-  // 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);
-
-  static const int kMinFilesForIntraL0Compaction = 4;
-};
-
-void LevelCompactionBuilder::PickExpiredTtlFiles() {
-  if (vstorage_->ExpiredTtlFiles().empty()) {
-    return;
-  }
-
-  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    start_level_ = level_file.first;
-    output_level_ =
-        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-
-    if ((start_level_ == vstorage_->num_non_empty_levels() - 1) ||
-        (start_level_ == 0 &&
-         !compaction_picker_->level0_compactions_in_progress()->empty())) {
-      return false;
-    }
-
-    start_level_inputs_.files = {level_file.second};
-    start_level_inputs_.level = start_level_;
-    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                      &start_level_inputs_);
-  };
-
-  for (auto& level_file : vstorage_->ExpiredTtlFiles()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-
-  start_level_inputs_.files.clear();
-}
-
-void LevelCompactionBuilder::PickFilesMarkedForPeriodicCompaction() {
-  if (vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
-    return;
-  }
-
-  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    output_level_ = start_level_ = level_file.first;
-
-    if (start_level_ == 0 &&
-        !compaction_picker_->level0_compactions_in_progress()->empty()) {
-      return false;
-    }
-
-    start_level_inputs_.files = {level_file.second};
-    start_level_inputs_.level = start_level_;
-    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                      &start_level_inputs_);
-  };
-
-  for (auto& level_file : vstorage_->FilesMarkedForPeriodicCompaction()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-
-  start_level_inputs_.files.clear();
-}
-
-void LevelCompactionBuilder::SetupInitialFiles() {
-  // Find the compactions by size on all levels.
-  bool skipped_l0_to_base = false;
-  for (int i = 0; i < compaction_picker_->NumberLevels() - 1; i++) {
-    start_level_score_ = vstorage_->CompactionScore(i);
-    start_level_ = vstorage_->CompactionScoreLevel(i);
-    assert(i == 0 || start_level_score_ <= vstorage_->CompactionScore(i - 1));
-    if (start_level_score_ >= 1) {
-      if (skipped_l0_to_base && start_level_ == vstorage_->base_level()) {
-        // If L0->base_level compaction is pending, don't schedule further
-        // compaction from base level. Otherwise L0->base_level compaction
-        // may starve.
-        continue;
-      }
-      output_level_ =
-          (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-      if (PickFileToCompact()) {
-        // found the compaction!
-        if (start_level_ == 0) {
-          // L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
-          compaction_reason_ = CompactionReason::kLevelL0FilesNum;
-        } else {
-          // L1+ score = `Level files size` / `MaxBytesForLevel`
-          compaction_reason_ = CompactionReason::kLevelMaxLevelSize;
-        }
-        break;
-      } else {
-        // didn't find the compaction, clear the inputs
-        start_level_inputs_.clear();
-        if (start_level_ == 0) {
-          skipped_l0_to_base = true;
-          // L0->base_level may be blocked due to ongoing L0->base_level
-          // compactions. It may also be blocked by an ongoing compaction from
-          // base_level downwards.
-          //
-          // In these cases, to reduce L0 file count and thus reduce likelihood
-          // of write stalls, we can attempt compacting a span of files within
-          // L0.
-          if (PickIntraL0Compaction()) {
-            output_level_ = 0;
-            compaction_reason_ = CompactionReason::kLevelL0FilesNum;
-            break;
-          }
-        }
-      }
-    }
-  }
-
-  // if we didn't find a compaction, check if there are any files marked for
-  // compaction
-  if (start_level_inputs_.empty()) {
-    parent_index_ = base_index_ = -1;
-
-    compaction_picker_->PickFilesMarkedForCompaction(
-        cf_name_, vstorage_, &start_level_, &output_level_,
-        &start_level_inputs_);
-    if (!start_level_inputs_.empty()) {
-      is_manual_ = true;
-      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
-      return;
-    }
-  }
-
-  // Bottommost Files Compaction on deleting tombstones
-  if (start_level_inputs_.empty()) {
-    size_t i;
-    for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
-         ++i) {
-      auto& level_and_file = vstorage_->BottommostFilesMarkedForCompaction()[i];
-      assert(!level_and_file.second->being_compacted);
-      start_level_inputs_.level = output_level_ = start_level_ =
-          level_and_file.first;
-      start_level_inputs_.files = {level_and_file.second};
-      if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                     &start_level_inputs_)) {
-        break;
-      }
-    }
-    if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
-      start_level_inputs_.clear();
-    } else {
-      assert(!start_level_inputs_.empty());
-      compaction_reason_ = CompactionReason::kBottommostFiles;
-      return;
-    }
-  }
-
-  // TTL Compaction
-  if (start_level_inputs_.empty()) {
-    PickExpiredTtlFiles();
-    if (!start_level_inputs_.empty()) {
-      compaction_reason_ = CompactionReason::kTtl;
-      return;
-    }
-  }
-
-  // Periodic Compaction
-  if (start_level_inputs_.empty()) {
-    PickFilesMarkedForPeriodicCompaction();
-    if (!start_level_inputs_.empty()) {
-      compaction_reason_ = CompactionReason::kPeriodicCompaction;
-      return;
-    }
-  }
-}
-
-bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
-  if (start_level_ == 0 && output_level_ != 0) {
-    return compaction_picker_->GetOverlappingL0Files(
-        vstorage_, &start_level_inputs_, output_level_, &parent_index_);
-  }
-  return true;
-}
-
-bool LevelCompactionBuilder::SetupOtherInputsIfNeeded() {
-  // Setup input files from output level. For output to L0, we only compact
-  // spans of files that do not interact with any pending compactions, so don't
-  // need to consider other levels.
-  if (output_level_ != 0) {
-    output_level_inputs_.level = output_level_;
-    if (!compaction_picker_->SetupOtherInputs(
-            cf_name_, mutable_cf_options_, vstorage_, &start_level_inputs_,
-            &output_level_inputs_, &parent_index_, base_index_)) {
-      return false;
-    }
-
-    compaction_inputs_.push_back(start_level_inputs_);
-    if (!output_level_inputs_.empty()) {
-      compaction_inputs_.push_back(output_level_inputs_);
-    }
-
-    // In some edge cases we could pick a compaction that will be compacting
-    // a key range that overlap with another running compaction, and both
-    // of them have the same output level. This could happen if
-    // (1) we are running a non-exclusive manual compaction
-    // (2) AddFile ingest a new file into the LSM tree
-    // We need to disallow this from happening.
-    if (compaction_picker_->FilesRangeOverlapWithCompaction(compaction_inputs_,
-                                                            output_level_)) {
-      // This compaction output could potentially conflict with the output
-      // of a currently running compaction, we cannot run it.
-      return false;
-    }
-    compaction_picker_->GetGrandparents(vstorage_, start_level_inputs_,
-                                        output_level_inputs_, &grandparents_);
-  } else {
-    compaction_inputs_.push_back(start_level_inputs_);
-  }
-  return true;
-}
-
-Compaction* LevelCompactionBuilder::PickCompaction() {
-  // Pick up the first file to start compaction. It may have been extended
-  // to a clean cut.
-  SetupInitialFiles();
-  if (start_level_inputs_.empty()) {
-    return nullptr;
-  }
-  assert(start_level_ >= 0 && output_level_ >= 0);
-
-  // If it is a L0 -> base level compaction, we need to set up other L0
-  // files if needed.
-  if (!SetupOtherL0FilesIfNeeded()) {
-    return nullptr;
-  }
-
-  // Pick files in the output level and expand more files in the start level
-  // if needed.
-  if (!SetupOtherInputsIfNeeded()) {
-    return nullptr;
-  }
-
-  // Form a compaction object containing the files we picked.
-  Compaction* c = GetCompaction();
-
-  TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
-
-  return c;
-}
-
-Compaction* LevelCompactionBuilder::GetCompaction() {
-  auto c = new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(compaction_inputs_),
-      output_level_,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level_,
-                          ioptions_.compaction_style, vstorage_->base_level(),
-                          ioptions_.level_compaction_dynamic_level_bytes),
-      mutable_cf_options_.max_compaction_bytes,
-      GetPathId(ioptions_, mutable_cf_options_, output_level_),
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
-                         output_level_, vstorage_->base_level()),
-      GetCompressionOptions(ioptions_, vstorage_, output_level_),
-      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
-      start_level_score_, false /* deletion_compaction */, compaction_reason_);
-
-  // If it's level 0 compaction, make sure we don't execute any other level 0
-  // compactions in parallel
-  compaction_picker_->RegisterCompaction(c);
-
-  // Creating a compaction influences the compaction score because the score
-  // takes running compactions into account (by skipping files that are already
-  // being compacted). Since we just changed compaction score, we recalculate it
-  // here
-  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
-  return c;
-}
-
-/*
- * Find the optimal path to place a file
- * Given a level, finds the path where levels up to it will fit in levels
- * up to and including this path
- */
-uint32_t LevelCompactionBuilder::GetPathId(
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, int level) {
-  uint32_t p = 0;
-  assert(!ioptions.cf_paths.empty());
-
-  // size remaining in the most recent path
-  uint64_t current_path_size = ioptions.cf_paths[0].target_size;
-
-  uint64_t level_size;
-  int cur_level = 0;
-
-  // max_bytes_for_level_base denotes L1 size.
-  // We estimate L0 size to be the same as L1.
-  level_size = mutable_cf_options.max_bytes_for_level_base;
-
-  // Last path is the fallback
-  while (p < ioptions.cf_paths.size() - 1) {
-    if (level_size <= current_path_size) {
-      if (cur_level == level) {
-        // Does desired level fit in this path?
-        return p;
-      } else {
-        current_path_size -= level_size;
-        if (cur_level > 0) {
-          if (ioptions.level_compaction_dynamic_level_bytes) {
-            // Currently, level_compaction_dynamic_level_bytes is ignored when
-            // multiple db paths are specified. https://github.com/facebook/
-            // rocksdb/blob/master/db/column_family.cc.
-            // Still, adding this check to avoid accidentally using
-            // max_bytes_for_level_multiplier_additional
-            level_size = static_cast<uint64_t>(
-                level_size * mutable_cf_options.max_bytes_for_level_multiplier);
-          } else {
-            level_size = static_cast<uint64_t>(
-                level_size * mutable_cf_options.max_bytes_for_level_multiplier *
-                mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
-          }
-        }
-        cur_level++;
-        continue;
-      }
-    }
-    p++;
-    current_path_size = ioptions.cf_paths[p].target_size;
-  }
-  return p;
-}
-
-bool LevelCompactionBuilder::PickFileToCompact() {
-  // level 0 files are overlapping. So we cannot pick more
-  // than one concurrent compactions at this level. This
-  // could be made better by looking at key-ranges that are
-  // being compacted at level 0.
-  if (start_level_ == 0 &&
-      !compaction_picker_->level0_compactions_in_progress()->empty()) {
-    TEST_SYNC_POINT("LevelCompactionPicker::PickCompactionBySize:0");
-    return false;
-  }
-
-  start_level_inputs_.clear();
-
-  assert(start_level_ >= 0);
-
-  // Pick the largest file in this level that is not already
-  // being compacted
-  const std::vector<int>& file_size =
-      vstorage_->FilesByCompactionPri(start_level_);
-  const std::vector<FileMetaData*>& level_files =
-      vstorage_->LevelFiles(start_level_);
-
-  unsigned int cmp_idx;
-  for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
-       cmp_idx < file_size.size(); cmp_idx++) {
-    int index = file_size[cmp_idx];
-    auto* f = level_files[index];
-
-    // do not pick a file to compact if it is being compacted
-    // from n-1 level.
-    if (f->being_compacted) {
-      continue;
-    }
-
-    start_level_inputs_.files.push_back(f);
-    start_level_inputs_.level = start_level_;
-    if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                    &start_level_inputs_) ||
-        compaction_picker_->FilesRangeOverlapWithCompaction(
-            {start_level_inputs_}, output_level_)) {
-      // A locked (pending compaction) input-level file was pulled in due to
-      // user-key overlap.
-      start_level_inputs_.clear();
-      continue;
-    }
-
-    // Now that input level is fully expanded, we check whether any output files
-    // are locked due to pending compaction.
-    //
-    // Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
-    // level files are locked, not just the extra ones pulled in for user-key
-    // overlap.
-    InternalKey smallest, largest;
-    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
-    CompactionInputFiles output_level_inputs;
-    output_level_inputs.level = output_level_;
-    vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
-                                    &output_level_inputs.files);
-    if (!output_level_inputs.empty() &&
-        !compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                    &output_level_inputs)) {
-      start_level_inputs_.clear();
-      continue;
-    }
-    base_index_ = index;
-    break;
-  }
-
-  // store where to start the iteration in the next call to PickCompaction
-  vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
-
-  return start_level_inputs_.size() > 0;
-}
-
-bool LevelCompactionBuilder::PickIntraL0Compaction() {
-  start_level_inputs_.clear();
-  const std::vector<FileMetaData*>& level_files =
-      vstorage_->LevelFiles(0 /* level */);
-  if (level_files.size() <
-          static_cast<size_t>(
-              mutable_cf_options_.level0_file_num_compaction_trigger + 2) ||
-      level_files[0]->being_compacted) {
-    // If L0 isn't accumulating much files beyond the regular trigger, don't
-    // resort to L0->L0 compaction yet.
-    return false;
-  }
-  return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
-                               port::kMaxUint64,
-                               mutable_cf_options_.max_compaction_bytes,
-                               &start_level_inputs_, earliest_mem_seqno_);
-}
-}  // namespace
-
-Compaction* LevelCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber earliest_mem_seqno) {
-  LevelCompactionBuilder builder(cf_name, vstorage, earliest_mem_seqno, this,
-                                 log_buffer, mutable_cf_options, ioptions_);
-  return builder.PickCompaction();
-}
-}  // namespace rocksdb

db/compaction/compaction_picker_level.h

@@ -1,32 +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
-
-#include "db/compaction/compaction_picker.h"
-
-namespace rocksdb {
-// Picking compactions for leveled compaction. See wiki page
-// https://github.com/facebook/rocksdb/wiki/Leveled-Compaction
-// for description of Leveled compaction.
-class LevelCompactionPicker : public CompactionPicker {
- public:
-  LevelCompactionPicker(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,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-
-}  // namespace rocksdb

db/compaction/compaction_picker_universal.h

@@ -1,31 +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/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,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
-  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-}  // namespace rocksdb
-#endif  // !ROCKSDB_LITE

db/compaction_iterator.cc

@@ -3,30 +3,12 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#include <cinttypes>
+#include "db/compaction_iterator.h"
 
-#include "db/compaction/compaction_iterator.h"
 #include "db/snapshot_checker.h"
 #include "port/likely.h"
 #include "rocksdb/listener.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
-
-#define DEFINITELY_IN_SNAPSHOT(seq, snapshot)                       \
-  ((seq) <= (snapshot) &&                                           \
-   (snapshot_checker_ == nullptr ||                                 \
-    LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) == \
-           SnapshotCheckerResult::kInSnapshot)))
-
-#define DEFINITELY_NOT_IN_SNAPSHOT(seq, snapshot)                     \
-  ((seq) > (snapshot) ||                                              \
-   (snapshot_checker_ != nullptr &&                                   \
-    UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) == \
-             SnapshotCheckerResult::kNotInSnapshot)))
-
-#define IN_EARLIEST_SNAPSHOT(seq) \
-  ((seq) <= earliest_snapshot_ && \
-   (snapshot_checker_ == nullptr || LIKELY(IsInEarliestSnapshot(seq))))
 
 namespace rocksdb {
 
@@ -35,35 +17,28 @@ CompactionIterator::CompactionIterator(
     SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     const SnapshotChecker* snapshot_checker, Env* env,
-    bool report_detailed_time, bool expect_valid_internal_key,
-    CompactionRangeDelAggregator* range_del_agg, const Compaction* compaction,
-    const CompactionFilter* compaction_filter,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
+    const Compaction* compaction, const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused,
-    const std::shared_ptr<Logger> info_log)
+    const SequenceNumber preserve_deletes_seqnum)
     : CompactionIterator(
           input, cmp, merge_helper, last_sequence, snapshots,
           earliest_write_conflict_snapshot, snapshot_checker, env,
-          report_detailed_time, expect_valid_internal_key, range_del_agg,
+          expect_valid_internal_key, range_del_agg,
           std::unique_ptr<CompactionProxy>(
               compaction ? new CompactionProxy(compaction) : nullptr),
-          compaction_filter, shutting_down, preserve_deletes_seqnum,
-          manual_compaction_paused, info_log) {}
+          compaction_filter, shutting_down, preserve_deletes_seqnum) {}
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber /*last_sequence*/, std::vector<SequenceNumber>* snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     const SnapshotChecker* snapshot_checker, Env* env,
-    bool report_detailed_time, bool expect_valid_internal_key,
-    CompactionRangeDelAggregator* range_del_agg,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
     std::unique_ptr<CompactionProxy> compaction,
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused,
-    const std::shared_ptr<Logger> info_log)
+    const SequenceNumber preserve_deletes_seqnum)
     : input_(input),
       cmp_(cmp),
       merge_helper_(merge_helper),
@@ -71,46 +46,42 @@ CompactionIterator::CompactionIterator(
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
       snapshot_checker_(snapshot_checker),
       env_(env),
-      report_detailed_time_(report_detailed_time),
       expect_valid_internal_key_(expect_valid_internal_key),
       range_del_agg_(range_del_agg),
       compaction_(std::move(compaction)),
       compaction_filter_(compaction_filter),
       shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
       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),
-      info_log_(info_log) {
+      current_key_committed_(false) {
   assert(compaction_filter_ == nullptr || compaction_ != nullptr);
-  assert(snapshots_ != nullptr);
   bottommost_level_ =
       compaction_ == nullptr ? false : compaction_->bottommost_level();
   if (compaction_ != nullptr) {
     level_ptrs_ = std::vector<size_t>(compaction_->number_levels(), 0);
   }
+
   if (snapshots_->size() == 0) {
     // optimize for fast path if there are no snapshots
     visible_at_tip_ = true;
-    earliest_snapshot_iter_ = snapshots_->end();
     earliest_snapshot_ = kMaxSequenceNumber;
     latest_snapshot_ = 0;
   } else {
     visible_at_tip_ = false;
-    earliest_snapshot_iter_ = snapshots_->begin();
     earliest_snapshot_ = snapshots_->at(0);
     latest_snapshot_ = snapshots_->back();
   }
-#ifndef NDEBUG
-  // findEarliestVisibleSnapshot assumes this ordering.
-  for (size_t i = 1; i < snapshots_->size(); ++i) {
-    assert(snapshots_->at(i - 1) < snapshots_->at(i));
+  if (compaction_filter_ != nullptr) {
+    if (compaction_filter_->IgnoreSnapshots()) {
+      ignore_snapshots_ = true;
+    }
+  } else {
+    ignore_snapshots_ = false;
   }
-#endif
   input_->SetPinnedItersMgr(&pinned_iters_mgr_);
-  TEST_SYNC_POINT_CALLBACK("CompactionIterator:AfterInit", compaction_.get());
 }
 
 CompactionIterator::~CompactionIterator() {
@@ -147,11 +118,6 @@ void CompactionIterator::Next() {
       // 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);
-      if (!valid_key) {
-        ROCKS_LOG_FATAL(info_log_, "Invalid key (%s) in compaction",
-                        key_.ToString(true).c_str());
-      }
-
       // Keep current_key_ in sync.
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
       key_ = current_key_.GetInternalKey();
@@ -185,7 +151,12 @@ void CompactionIterator::Next() {
 void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
                                               Slice* skip_until) {
   if (compaction_filter_ != nullptr &&
-      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex)) {
+      (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,
@@ -200,12 +171,12 @@ void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
     // to get sequence number.
     Slice& filter_key = ikey_.type == kTypeValue ? ikey_.user_key : key_;
     {
-      StopWatchNano timer(env_, report_detailed_time_);
+      StopWatchNano timer(env_, true);
       filter = compaction_filter_->FilterV2(
           compaction_->level(), filter_key, value_type, value_,
           &compaction_filter_value_, compaction_filter_skip_until_.rep());
       iter_stats_.total_filter_time +=
-          env_ != nullptr && report_detailed_time_ ? timer.ElapsedNanos() : 0;
+          env_ != nullptr ? timer.ElapsedNanos() : 0;
     }
 
     if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
@@ -239,8 +210,7 @@ void CompactionIterator::NextFromInput() {
   at_next_ = false;
   valid_ = false;
 
-  while (!valid_ && input_->Valid() && !IsPausingManualCompaction() &&
-         !IsShuttingDown()) {
+  while (!valid_ && input_->Valid() && !IsShuttingDown()) {
     key_ = input_->key();
     value_ = input_->value();
     iter_stats_.num_input_records++;
@@ -262,7 +232,6 @@ void CompactionIterator::NextFromInput() {
       valid_ = true;
       break;
     }
-    TEST_SYNC_POINT_CALLBACK("CompactionIterator:ProcessKV", &ikey_);
 
     // Update input statistics
     if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
@@ -291,7 +260,9 @@ void CompactionIterator::NextFromInput() {
       has_outputted_key_ = false;
       current_user_key_sequence_ = kMaxSequenceNumber;
       current_user_key_snapshot_ = 0;
-      current_key_committed_ = KeyCommitted(ikey_.sequence);
+      current_key_committed_ =
+          (snapshot_checker_ == nullptr ||
+           snapshot_checker_->IsInSnapshot(ikey_.sequence, kMaxSequenceNumber));
 
       // Apply the compaction filter to the first committed version of the user
       // key.
@@ -313,7 +284,8 @@ void CompactionIterator::NextFromInput() {
       // to query snapshot_checker_ in that case.
       if (UNLIKELY(!current_key_committed_)) {
         assert(snapshot_checker_ != nullptr);
-        current_key_committed_ = KeyCommitted(ikey_.sequence);
+        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_) {
@@ -348,18 +320,7 @@ void CompactionIterator::NextFromInput() {
       // not compact out.  We will keep this Put, but can drop it's data.
       // (See Optimization 3, below.)
       assert(ikey_.type == kTypeValue);
-      if (ikey_.type != kTypeValue) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "Unexpected key type %d for compaction output",
-                        ikey_.type);
-      }
       assert(current_user_key_snapshot_ == last_snapshot);
-      if (current_user_key_snapshot_ != last_snapshot) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "current_user_key_snapshot_ (%" PRIu64
-                        ") != last_snapshot (%" PRIu64 ")",
-                        current_user_key_snapshot_, last_snapshot);
-      }
 
       value_.clear();
       valid_ = true;
@@ -408,8 +369,10 @@ void CompactionIterator::NextFromInput() {
           cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
         // Check whether the next key belongs to the same snapshot as the
         // SingleDelete.
-        if (prev_snapshot == 0 ||
-            DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot)) {
+        if (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot ||
+            (snapshot_checker_ != nullptr &&
+             UNLIKELY(!snapshot_checker_->IsInSnapshot(next_ikey.sequence,
+                                                       prev_snapshot)))) {
           if (next_ikey.type == kTypeSingleDeletion) {
             // We encountered two SingleDeletes in a row.  This could be due to
             // unexpected user input.
@@ -421,8 +384,11 @@ void CompactionIterator::NextFromInput() {
             ++iter_stats_.num_record_drop_obsolete;
             ++iter_stats_.num_single_del_mismatch;
           } else if (has_outputted_key_ ||
-                     DEFINITELY_IN_SNAPSHOT(
-                         ikey_.sequence, earliest_write_conflict_snapshot_)) {
+                     (ikey_.sequence <= earliest_write_conflict_snapshot_ &&
+                      (snapshot_checker_ == nullptr ||
+                       LIKELY(snapshot_checker_->IsInSnapshot(
+                           ikey_.sequence,
+                           earliest_write_conflict_snapshot_))))) {
             // Found a matching value, we can drop the single delete and the
             // value.  It is safe to drop both records since we've already
             // outputted a key in this snapshot, or there is no earlier
@@ -432,8 +398,7 @@ void CompactionIterator::NextFromInput() {
             // is an unexpected Merge or Delete.  We will compact it out
             // either way. We will maintain counts of how many mismatches
             // happened
-            if (next_ikey.type != kTypeValue &&
-                next_ikey.type != kTypeBlobIndex) {
+            if (next_ikey.type != kTypeValue) {
               ++iter_stats_.num_single_del_mismatch;
             }
 
@@ -470,7 +435,10 @@ void CompactionIterator::NextFromInput() {
         // iteration. If the next key is corrupt, we return before the
         // comparison, so the value of has_current_user_key does not matter.
         has_current_user_key_ = false;
-        if (compaction_ != nullptr && IN_EARLIEST_SNAPSHOT(ikey_.sequence) &&
+        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.
@@ -489,29 +457,24 @@ void CompactionIterator::NextFromInput() {
       if (valid_) {
         at_next_ = true;
       }
-    } else if (last_snapshot == current_user_key_snapshot_ ||
-               (last_snapshot > 0 &&
-                last_snapshot < current_user_key_snapshot_)) {
+    } else if (last_snapshot == current_user_key_snapshot_) {
       // If the earliest snapshot is which this key is visible in
       // 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 > ?
       //
       // Note: Dropping this key will not affect TransactionDB write-conflict
       // checking since there has already been a record returned for this key
       // in this snapshot.
       assert(last_sequence >= current_user_key_sequence_);
-      if (last_sequence < current_user_key_sequence_) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "last_sequence (%" PRIu64
-                        ") < current_user_key_sequence_ (%" PRIu64 ")",
-                        last_sequence, current_user_key_sequence_);
-      }
-
       ++iter_stats_.num_record_drop_hidden;  // (A)
       input_->Next();
     } else if (compaction_ != nullptr && ikey_.type == kTypeDeletion &&
-               IN_EARLIEST_SNAPSHOT(ikey_.sequence) &&
+               ikey_.sequence <= earliest_snapshot_ &&
+               (snapshot_checker_ == nullptr ||
+                LIKELY(snapshot_checker_->IsInSnapshot(ikey_.sequence,
+                                                       earliest_snapshot_))) &&
                ikeyNotNeededForIncrementalSnapshot() &&
                compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                           &level_ptrs_)) {
@@ -539,28 +502,6 @@ void CompactionIterator::NextFromInput() {
         ++iter_stats_.num_optimized_del_drop_obsolete;
       }
       input_->Next();
-    } else if ((ikey_.type == kTypeDeletion) && bottommost_level_ &&
-               ikeyNotNeededForIncrementalSnapshot()) {
-      // Handle the case where we have a delete key at the bottom most level
-      // We can skip outputting the key iff there are no subsequent puts for this
-      // key
-      ParsedInternalKey next_ikey;
-      input_->Next();
-      // Skip over all versions of this key that happen to occur in the same snapshot
-      // range as the delete
-      while (input_->Valid() && ParseInternalKey(input_->key(), &next_ikey) &&
-             cmp_->Equal(ikey_.user_key, next_ikey.user_key) &&
-             (prev_snapshot == 0 ||
-              DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot))) {
-        input_->Next();
-      }
-      // If you find you still need to output a row with this key, we need to output the
-      // delete too
-      if (input_->Valid() && ParseInternalKey(input_->key(), &next_ikey) &&
-          cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
-        valid_ = true;
-        at_next_ = true;
-      }
     } else if (ikey_.type == kTypeMerge) {
       if (!merge_helper_->HasOperator()) {
         status_ = Status::InvalidArgument(
@@ -590,10 +531,6 @@ void CompactionIterator::NextFromInput() {
         // 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);
-        if (!valid_key) {
-          ROCKS_LOG_FATAL(info_log_, "Invalid key (%s) in compaction",
-                          key_.ToString(true).c_str());
-        }
         // Keep current_key_ in sync.
         current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
         key_ = current_key_.GetInternalKey();
@@ -614,7 +551,7 @@ void CompactionIterator::NextFromInput() {
       // 1. new user key -OR-
       // 2. different snapshot stripe
       bool should_delete = range_del_agg_->ShouldDelete(
-          key_, RangeDelPositioningMode::kForwardTraversal);
+          key_, RangeDelAggregator::RangePositioningMode::kForwardTraversal);
       if (should_delete) {
         ++iter_stats_.num_record_drop_hidden;
         ++iter_stats_.num_record_drop_range_del;
@@ -632,100 +569,49 @@ void CompactionIterator::NextFromInput() {
   if (!valid_ && IsShuttingDown()) {
     status_ = Status::ShutdownInProgress();
   }
-
-  if (IsPausingManualCompaction()) {
-    status_ = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
-  }
 }
 
 void CompactionIterator::PrepareOutput() {
-  if (valid_) {
-    if (compaction_filter_ && ikey_.type == kTypeBlobIndex) {
-      const auto blob_decision = compaction_filter_->PrepareBlobOutput(
-          user_key(), value_, &compaction_filter_value_);
-
-      if (blob_decision == CompactionFilter::BlobDecision::kCorruption) {
-        status_ = Status::Corruption(
-            "Corrupted blob reference encountered during GC");
-        valid_ = false;
-      } else if (blob_decision == CompactionFilter::BlobDecision::kIOError) {
-        status_ = Status::IOError("Could not relocate blob during GC");
-        valid_ = false;
-      } else if (blob_decision ==
-                 CompactionFilter::BlobDecision::kChangeValue) {
-        value_ = compaction_filter_value_;
-      }
-    }
-
-    // Zeroing out the sequence number leads to better compression.
-    // If this is the bottommost level (no files in lower levels)
-    // and the earliest snapshot is larger than this seqno
-    // and the userkey differs from the last userkey in compaction
-    // then we can squash the seqno to zero.
-    //
-    // This is safe for TransactionDB write-conflict checking since transactions
-    // only care about sequence number larger than any active snapshots.
-    //
-    // Can we do the same for levels above bottom level as long as
-    // KeyNotExistsBeyondOutputLevel() return true?
-    if (valid_ && compaction_ != nullptr &&
-        !compaction_->allow_ingest_behind() &&
-        ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ &&
-        IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
-      assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
-      if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "Unexpected key type %d for seq-zero optimization",
-                        ikey_.type);
-      }
-      ikey_.sequence = 0;
-      current_key_.UpdateInternalKey(0, ikey_.type);
-    }
+  // Zeroing out the sequence number leads to better compression.
+  // If this is the bottommost level (no files in lower levels)
+  // and the earliest snapshot is larger than this seqno
+  // and the userkey differs from the last userkey in compaction
+  // then we can squash the seqno to zero.
+  //
+  // This is safe for TransactionDB write-conflict checking since transactions
+  // only care about sequence number larger than any active snapshots.
+  //
+  // Can we do the same for levels above bottom level as long as
+  // KeyNotExistsBeyondOutputLevel() return true?
+  if ((compaction_ != nullptr &&
+      !compaction_->allow_ingest_behind()) &&
+      ikeyNotNeededForIncrementalSnapshot() &&
+      bottommost_level_ && valid_ && ikey_.sequence <= earliest_snapshot_ &&
+      (snapshot_checker_ == nullptr || LIKELY(snapshot_checker_->IsInSnapshot(
+        ikey_.sequence, earliest_snapshot_))) &&
+      ikey_.type != kTypeMerge &&
+      !cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
+    assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
+    ikey_.sequence = 0;
+    current_key_.UpdateInternalKey(0, ikey_.type);
   }
 }
 
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  if (snapshots_->size() == 0) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "No snapshot left in findEarliestVisibleSnapshot");
-  }
-  auto snapshots_iter = std::lower_bound(
-      snapshots_->begin(), snapshots_->end(), in);
-  if (snapshots_iter == snapshots_->begin()) {
-    *prev_snapshot = 0;
-  } else {
-    *prev_snapshot = *std::prev(snapshots_iter);
-    assert(*prev_snapshot < in);
-    if (*prev_snapshot >= in) {
-      ROCKS_LOG_FATAL(info_log_,
-                      "*prev_snapshot >= in in findEarliestVisibleSnapshot");
-    }
-  }
-  if (snapshot_checker_ == nullptr) {
-    return snapshots_iter != snapshots_->end()
-      ? *snapshots_iter : kMaxSequenceNumber;
-  }
-  bool has_released_snapshot = !released_snapshots_.empty();
-  for (; snapshots_iter != snapshots_->end(); ++snapshots_iter) {
-    auto cur = *snapshots_iter;
-    assert(in <= cur);
-    if (in > cur) {
-      ROCKS_LOG_FATAL(info_log_, "in > cur in findEarliestVisibleSnapshot");
-    }
-    // Skip if cur is in released_snapshots.
-    if (has_released_snapshot && released_snapshots_.count(cur) > 0) {
-      continue;
-    }
-    auto res = snapshot_checker_->CheckInSnapshot(in, cur);
-    if (res == SnapshotCheckerResult::kInSnapshot) {
+  SequenceNumber prev = kMaxSequenceNumber;
+  for (const auto cur : *snapshots_) {
+    assert(prev == kMaxSequenceNumber || prev <= cur);
+    if (cur >= in && (snapshot_checker_ == nullptr ||
+                      snapshot_checker_->IsInSnapshot(in, cur))) {
+      *prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
       return cur;
-    } else if (res == SnapshotCheckerResult::kSnapshotReleased) {
-      released_snapshots_.insert(cur);
     }
-    *prev_snapshot = cur;
+    prev = cur;
+    assert(prev < kMaxSequenceNumber);
   }
+  *prev_snapshot = prev;
   return kMaxSequenceNumber;
 }
 
@@ -736,39 +622,4 @@ inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
          (ikey_.sequence < preserve_deletes_seqnum_);
 }
 
-bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
-  assert(snapshot_checker_ != nullptr);
-  bool pre_condition = (earliest_snapshot_ == kMaxSequenceNumber ||
-                        (earliest_snapshot_iter_ != snapshots_->end() &&
-                         *earliest_snapshot_iter_ == earliest_snapshot_));
-  assert(pre_condition);
-  if (!pre_condition) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "Pre-Condition is not hold in IsInEarliestSnapshot");
-  }
-  auto in_snapshot =
-      snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
-  while (UNLIKELY(in_snapshot == SnapshotCheckerResult::kSnapshotReleased)) {
-    // Avoid the the current earliest_snapshot_ being return as
-    // earliest visible snapshot for the next value. So if a value's sequence
-    // is zero-ed out by PrepareOutput(), the next value will be compact out.
-    released_snapshots_.insert(earliest_snapshot_);
-    earliest_snapshot_iter_++;
-
-    if (earliest_snapshot_iter_ == snapshots_->end()) {
-      earliest_snapshot_ = kMaxSequenceNumber;
-    } else {
-      earliest_snapshot_ = *earliest_snapshot_iter_;
-    }
-    in_snapshot =
-        snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
-  }
-  assert(in_snapshot != SnapshotCheckerResult::kSnapshotReleased);
-  if (in_snapshot == SnapshotCheckerResult::kSnapshotReleased) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "Unexpected released snapshot in IsInEarliestSnapshot");
-  }
-  return in_snapshot == SnapshotCheckerResult::kInSnapshot;
-}
-
 }  // namespace rocksdb

db/compaction_iterator.h

@@ -7,11 +7,10 @@
 #include <algorithm>
 #include <deque>
 #include <string>
-#include <unordered_set>
 #include <vector>
 
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_iteration_stats.h"
+#include "db/compaction.h"
+#include "db/compaction_iteration_stats.h"
 #include "db/merge_helper.h"
 #include "db/pinned_iterators_manager.h"
 #include "db/range_del_aggregator.h"
@@ -59,34 +58,30 @@ class CompactionIterator {
     const Compaction* compaction_;
   };
 
-  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,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      const Compaction* compaction = nullptr,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr,
-      const std::shared_ptr<Logger> info_log = nullptr);
+  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,
+                     bool expect_valid_internal_key,
+                     RangeDelAggregator* range_del_agg,
+                     const Compaction* compaction = nullptr,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0);
 
   // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      std::unique_ptr<CompactionProxy> compaction,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr,
-      const std::shared_ptr<Logger> info_log = nullptr);
+  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,
+                     bool expect_valid_internal_key,
+                     RangeDelAggregator* range_del_agg,
+                     std::unique_ptr<CompactionProxy> compaction,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0);
 
   ~CompactionIterator();
 
@@ -137,41 +132,25 @@ class CompactionIterator {
   // or seqnum be zero-ed out even if all other conditions for it are met.
   inline bool ikeyNotNeededForIncrementalSnapshot();
 
-  inline bool KeyCommitted(SequenceNumber sequence) {
-    return snapshot_checker_ == nullptr ||
-           snapshot_checker_->CheckInSnapshot(sequence, kMaxSequenceNumber) ==
-               SnapshotCheckerResult::kInSnapshot;
-  }
-
-  bool IsInEarliestSnapshot(SequenceNumber sequence);
-
   InternalIterator* input_;
   const Comparator* cmp_;
   MergeHelper* merge_helper_;
   const std::vector<SequenceNumber>* snapshots_;
-  // List of snapshots released during compaction.
-  // findEarliestVisibleSnapshot() find them out from return of
-  // snapshot_checker, and make sure they will not be returned as
-  // earliest visible snapshot of an older value.
-  // See WritePreparedTransactionTest::ReleaseSnapshotDuringCompaction3.
-  std::unordered_set<SequenceNumber> released_snapshots_;
-  std::vector<SequenceNumber>::const_iterator earliest_snapshot_iter_;
   const SequenceNumber earliest_write_conflict_snapshot_;
   const SnapshotChecker* const snapshot_checker_;
   Env* env_;
-  bool report_detailed_time_;
   bool expect_valid_internal_key_;
-  CompactionRangeDelAggregator* range_del_agg_;
+  RangeDelAggregator* range_del_agg_;
   std::unique_ptr<CompactionProxy> compaction_;
   const CompactionFilter* compaction_filter_;
   const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
   const SequenceNumber preserve_deletes_seqnum_;
   bool bottommost_level_;
   bool valid_ = false;
   bool visible_at_tip_;
   SequenceNumber earliest_snapshot_;
   SequenceNumber latest_snapshot_;
+  bool ignore_snapshots_;
 
   // State
   //
@@ -224,17 +203,10 @@ class CompactionIterator {
   // Used to avoid purging uncommitted values. The application can specify
   // uncommitted values by providing a SnapshotChecker object.
   bool current_key_committed_;
-  std::shared_ptr<Logger> info_log_;
 
   bool IsShuttingDown() {
     // This is a best-effort facility, so memory_order_relaxed is sufficient.
     return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
   }
-
-  bool IsPausingManualCompaction() {
-    // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return manual_compaction_paused_ &&
-           manual_compaction_paused_->load(std::memory_order_relaxed);
-  }
 };
 }  // namespace rocksdb

db/compaction_iterator_test.cc

@@ -3,15 +3,15 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#include "db/compaction_iterator.h"
 
 #include <string>
 #include <vector>
 
-#include "db/compaction/compaction_iterator.h"
 #include "port/port.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
 namespace rocksdb {
@@ -112,39 +112,39 @@ class LoggingForwardVectorIterator : public InternalIterator {
     assert(keys_.size() == values_.size());
   }
 
-  bool Valid() const override { return current_ < keys_.size(); }
+  virtual bool Valid() const override { return current_ < keys_.size(); }
 
-  void SeekToFirst() override {
+  virtual void SeekToFirst() override {
     log.emplace_back(Action::Type::SEEK_TO_FIRST);
     current_ = 0;
   }
-  void SeekToLast() override { assert(false); }
+  virtual void SeekToLast() override { assert(false); }
 
-  void Seek(const Slice& target) override {
+  virtual void Seek(const Slice& target) override {
     log.emplace_back(Action::Type::SEEK, target.ToString());
     current_ = std::lower_bound(keys_.begin(), keys_.end(), target.ToString()) -
                keys_.begin();
   }
 
-  void SeekForPrev(const Slice& /*target*/) override { assert(false); }
+  virtual void SeekForPrev(const Slice& /*target*/) override { assert(false); }
 
-  void Next() override {
+  virtual void Next() override {
     assert(Valid());
     log.emplace_back(Action::Type::NEXT);
     current_++;
   }
-  void Prev() override { assert(false); }
+  virtual void Prev() override { assert(false); }
 
-  Slice key() const override {
+  virtual Slice key() const override {
     assert(Valid());
     return Slice(keys_[current_]);
   }
-  Slice value() const override {
+  virtual Slice value() const override {
     assert(Valid());
     return Slice(values_[current_]);
   }
 
-  Status status() const override { return Status::OK(); }
+  virtual Status status() const override { return Status::OK(); }
 
   std::vector<Action> log;
 
@@ -158,20 +158,22 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
  public:
   FakeCompaction() = default;
 
-  int level(size_t /*compaction_input_level*/) const override { return 0; }
-  bool KeyNotExistsBeyondOutputLevel(
+  virtual int level(size_t /*compaction_input_level*/) const override {
+    return 0;
+  }
+  virtual bool KeyNotExistsBeyondOutputLevel(
       const Slice& /*user_key*/,
       std::vector<size_t>* /*level_ptrs*/) const override {
     return is_bottommost_level || key_not_exists_beyond_output_level;
   }
-  bool bottommost_level() const override { return is_bottommost_level; }
-  int number_levels() const override { return 1; }
-  Slice GetLargestUserKey() const override {
+  virtual bool bottommost_level() const override { return is_bottommost_level; }
+  virtual int number_levels() const override { return 1; }
+  virtual Slice GetLargestUserKey() const override {
     return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
   }
-  bool allow_ingest_behind() const override { return false; }
+  virtual bool allow_ingest_behind() const override { return false; }
 
-  bool preserve_deletes() const override { return false; }
+  virtual bool preserve_deletes() const override { return false; }
 
   bool key_not_exists_beyond_output_level = false;
 
@@ -184,21 +186,17 @@ class TestSnapshotChecker : public SnapshotChecker {
  public:
   explicit TestSnapshotChecker(
       SequenceNumber last_committed_sequence,
-      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {{}})
+      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {})
       : last_committed_sequence_(last_committed_sequence),
         snapshots_(snapshots) {}
 
-  SnapshotCheckerResult CheckInSnapshot(
-      SequenceNumber seq, SequenceNumber snapshot_seq) const override {
+  bool IsInSnapshot(SequenceNumber seq,
+                    SequenceNumber snapshot_seq) const override {
     if (snapshot_seq == kMaxSequenceNumber) {
-      return seq <= last_committed_sequence_
-                 ? SnapshotCheckerResult::kInSnapshot
-                 : SnapshotCheckerResult::kNotInSnapshot;
+      return seq <= last_committed_sequence_;
     }
     assert(snapshots_.count(snapshot_seq) > 0);
-    return seq <= snapshots_.at(snapshot_seq)
-               ? SnapshotCheckerResult::kInSnapshot
-               : SnapshotCheckerResult::kNotInSnapshot;
+    return seq <= snapshots_.at(snapshot_seq);
   }
 
  private:
@@ -223,15 +221,10 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
       MergeOperator* merge_op = nullptr, CompactionFilter* filter = nullptr,
       bool bottommost_level = false,
       SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
-    std::unique_ptr<InternalIterator> unfragmented_range_del_iter(
+    std::unique_ptr<InternalIterator> range_del_iter(
         new test::VectorIterator(range_del_ks, range_del_vs));
-    auto tombstone_list = std::make_shared<FragmentedRangeTombstoneList>(
-        std::move(unfragmented_range_del_iter), icmp_);
-    std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
-        new FragmentedRangeTombstoneIterator(tombstone_list, icmp_,
-                                             kMaxSequenceNumber));
-    range_del_agg_.reset(new CompactionRangeDelAggregator(&icmp_, snapshots_));
-    range_del_agg_->AddTombstones(std::move(range_del_iter));
+    range_del_agg_.reset(new RangeDelAggregator(icmp_, snapshots_));
+    ASSERT_OK(range_del_agg_->AddTombstones(std::move(range_del_iter)));
 
     std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
     if (filter || bottommost_level) {
@@ -254,8 +247,8 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
     c_iter_.reset(new CompactionIterator(
         iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
         earliest_write_conflict_snapshot, snapshot_checker_.get(),
-        Env::Default(), false /* report_detailed_time */, false,
-        range_del_agg_.get(), std::move(compaction), filter, &shutting_down_));
+        Env::Default(), false, range_del_agg_.get(), std::move(compaction),
+        filter, &shutting_down_));
   }
 
   void AddSnapshot(SequenceNumber snapshot,
@@ -299,7 +292,7 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
   std::unique_ptr<MergeHelper> merge_helper_;
   std::unique_ptr<LoggingForwardVectorIterator> iter_;
   std::unique_ptr<CompactionIterator> c_iter_;
-  std::unique_ptr<CompactionRangeDelAggregator> range_del_agg_;
+  std::unique_ptr<RangeDelAggregator> range_del_agg_;
   std::unique_ptr<SnapshotChecker> snapshot_checker_;
   std::atomic<bool> shutting_down_{false};
   FakeCompaction* compaction_proxy_;
@@ -375,9 +368,10 @@ TEST_P(CompactionIteratorTest, RangeDeletionWithSnapshots) {
 
 TEST_P(CompactionIteratorTest, CompactionFilterSkipUntil) {
   class Filter : public CompactionFilter {
-    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                      const Slice& existing_value, std::string* /*new_value*/,
-                      std::string* skip_until) const override {
+    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
@@ -557,9 +551,10 @@ TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
 
 TEST_P(CompactionIteratorTest, SingleMergeOperand) {
   class Filter : public CompactionFilter {
-    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                      const Slice& existing_value, std::string* /*new_value*/,
-                      std::string* /*skip_until*/) const override {
+    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();
 
@@ -676,12 +671,8 @@ TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
 TEST_P(CompactionIteratorTest, RemoveDeletionAtBottomLevel) {
   AddSnapshot(1);
   RunTest({test::KeyStr("a", 1, kTypeDeletion),
-           test::KeyStr("b", 3, kTypeDeletion),
-           test::KeyStr("b", 1, kTypeValue)},
-          {"", "", ""},
-          {test::KeyStr("b", 3, kTypeDeletion),
-           test::KeyStr("b", 0, kTypeValue)},
-          {"", ""},
+           test::KeyStr("b", 2, kTypeDeletion)},
+          {"", ""}, {test::KeyStr("b", 2, kTypeDeletion)}, {""},
           kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
           nullptr /*compaction_filter*/, true /*bottommost_level*/);
 }
@@ -850,26 +841,13 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
       {test::KeyStr("a", 1, kTypeDeletion), test::KeyStr("b", 2, kTypeDeletion),
        test::KeyStr("c", 3, kTypeDeletion)},
       {"", "", ""},
-      {},
+      {test::KeyStr("b", 2, kTypeDeletion),
+       test::KeyStr("c", 3, kTypeDeletion)},
       {"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
       nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
       true /*bottommost_level*/);
 }
 
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       NotRemoveDeletionIfValuePresentToEarlierSnapshot) {
-  AddSnapshot(2,1);
-  RunTest(
-      {test::KeyStr("a", 4, kTypeDeletion), test::KeyStr("a", 1, kTypeValue),
-          test::KeyStr("b", 3, kTypeValue)},
-      {"", "", ""},
-      {test::KeyStr("a", 4, kTypeDeletion), test::KeyStr("a", 0, kTypeValue),
-            test::KeyStr("b", 3, kTypeValue)},
-      {"", "", ""}, kMaxSequenceNumber /*last_commited_seq*/,
-      nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-      true /*bottommost_level*/);
-}
-
 TEST_F(CompactionIteratorWithSnapshotCheckerTest,
        NotRemoveSingleDeletionIfNotVisibleToEarliestSnapshot) {
   AddSnapshot(2, 1);

db/compaction_job.h

@@ -18,7 +18,7 @@
 #include <vector>
 
 #include "db/column_family.h"
-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/flush_scheduler.h"
 #include "db/internal_stats.h"
@@ -29,8 +29,6 @@
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
-#include "logging/event_logger.h"
-#include "options/cf_options.h"
 #include "options/db_options.h"
 #include "port/port.h"
 #include "rocksdb/compaction_filter.h"
@@ -41,13 +39,13 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
 
 class Arena;
-class ErrorHandler;
 class MemTable;
 class SnapshotChecker;
 class TableCache;
@@ -55,30 +53,24 @@ class Version;
 class VersionEdit;
 class VersionSet;
 
-// CompactionJob is responsible for executing the compaction. Each (manual or
-// automated) compaction corresponds to a CompactionJob object, and usually
-// goes through the stages of `Prepare()`->`Run()`->`Install()`. CompactionJob
-// will divide the compaction into subcompactions and execute them in parallel
-// if needed.
 class CompactionJob {
  public:
   CompactionJob(int job_id, Compaction* compaction,
                 const ImmutableDBOptions& db_options,
-                const FileOptions& file_options, VersionSet* versions,
+                const EnvOptions env_options, VersionSet* versions,
                 const std::atomic<bool>* shutting_down,
                 const SequenceNumber preserve_deletes_seqnum,
-                LogBuffer* log_buffer, Directory* db_directory,
-                Directory* output_directory, Statistics* stats,
-                InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
+                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,
-                Env::Priority thread_pri,
-                const std::atomic<bool>* manual_compaction_paused = nullptr);
+                CompactionJobStats* compaction_job_stats);
 
   ~CompactionJob();
 
@@ -88,28 +80,17 @@ class CompactionJob {
   CompactionJob& operator=(const CompactionJob& job) = delete;
 
   // REQUIRED: mutex held
-  // Prepare for the compaction by setting up boundaries for each subcompaction
   void Prepare();
   // REQUIRED mutex not held
-  // Launch threads for each subcompaction and wait for them to finish. After
-  // that, verify table is usable and finally do bookkeeping to unify
-  // subcompaction results
   Status Run();
 
   // REQUIRED: mutex held
-  // Add compaction input/output to the current version
   Status Install(const MutableCFOptions& mutable_cf_options);
 
  private:
   struct SubcompactionState;
 
   void AggregateStatistics();
-
-  // Generates a histogram representing potential divisions of key ranges from
-  // the input. It adds the starting and/or ending keys of certain input files
-  // to the working set and then finds the approximate size of data in between
-  // each consecutive pair of slices. Then it divides these ranges into
-  // consecutive groups such that each group has a similar size.
   void GenSubcompactionBoundaries();
 
   // update the thread status for starting a compaction.
@@ -121,7 +102,7 @@ class CompactionJob {
 
   Status FinishCompactionOutputFile(
       const Status& input_status, SubcompactionState* sub_compact,
-      CompactionRangeDelAggregator* range_del_agg,
+      RangeDelAggregator* range_del_agg,
       CompactionIterationStats* range_del_out_stats,
       const Slice* next_table_min_key = nullptr);
   Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
@@ -150,22 +131,20 @@ class CompactionJob {
   // DBImpl state
   const std::string& dbname_;
   const ImmutableDBOptions& db_options_;
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
 
   Env* env_;
-  FileSystem* fs_;
   // env_option optimized for compaction table reads
-  FileOptions file_options_for_read_;
+  EnvOptions env_optiosn_for_read_;
   VersionSet* versions_;
   const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
   const SequenceNumber preserve_deletes_seqnum_;
   LogBuffer* log_buffer_;
   Directory* db_directory_;
   Directory* output_directory_;
   Statistics* stats_;
   InstrumentedMutex* db_mutex_;
-  ErrorHandler* db_error_handler_;
+  Status* db_bg_error_;
   // If there were two snapshots with seq numbers s1 and
   // s2 and s1 < s2, and if we find two instances of a key k1 then lies
   // entirely within s1 and s2, then the earlier version of k1 can be safely
@@ -183,7 +162,6 @@ class CompactionJob {
 
   EventLogger* event_logger_;
 
-  // Is this compaction creating a file in the bottom most level?
   bool bottommost_level_;
   bool paranoid_file_checks_;
   bool measure_io_stats_;
@@ -192,7 +170,6 @@ class CompactionJob {
   // Stores the approx size of keys covered in the range of each subcompaction
   std::vector<uint64_t> sizes_;
   Env::WriteLifeTimeHint write_hint_;
-  Env::Priority thread_pri_;
 };
 
 }  // namespace rocksdb

db/compaction_job_stats_test.cc

@@ -7,8 +7,12 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
-#include <cinttypes>
 #include <iostream>
 #include <mutex>
 #include <queue>
@@ -17,14 +21,12 @@
 #include <unordered_set>
 #include <utility>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/dbformat.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "db/write_batch_internal.h"
 #include "env/mock_env.h"
-#include "file/filename.h"
-#include "logging/logging.h"
 #include "memtable/hash_linklist_rep.h"
 #include "monitoring/statistics.h"
 #include "monitoring/thread_status_util.h"
@@ -45,18 +47,20 @@
 #include "rocksdb/thread_status.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/write_batch_with_index.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/mock_table.h"
-#include "table/plain/plain_table_factory.h"
+#include "table/plain_table_factory.h"
 #include "table/scoped_arena_iterator.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/compression.h"
+#include "util/filename.h"
 #include "util/hash.h"
+#include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/rate_limiter.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
 #if !defined(IOS_CROSS_COMPILE)
@@ -94,7 +98,7 @@ class CompactionJobStatsTest : public testing::Test,
   CompactionJobStatsTest() : env_(Env::Default()) {
     env_->SetBackgroundThreads(1, Env::LOW);
     env_->SetBackgroundThreads(1, Env::HIGH);
-    dbname_ = test::PerThreadDBPath("compaction_job_stats_test");
+    dbname_ = test::TmpDir(env_) + "/compaction_job_stats_test";
     alternative_wal_dir_ = dbname_ + "/wal";
     Options options;
     options.create_if_missing = true;
@@ -109,7 +113,7 @@ class CompactionJobStatsTest : public testing::Test,
     Reopen(options);
   }
 
-  ~CompactionJobStatsTest() override {
+  ~CompactionJobStatsTest() {
     rocksdb::SyncPoint::GetInstance()->DisableProcessing();
     rocksdb::SyncPoint::GetInstance()->LoadDependency({});
     rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -422,7 +426,7 @@ class CompactionJobStatsChecker : public EventListener {
   // Once a compaction completed, this function will verify the returned
   // CompactionJobInfo with the oldest CompactionJobInfo added earlier
   // in "expected_stats_" which has not yet being used for verification.
-  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
+  virtual void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) {
     if (verify_next_comp_io_stats_) {
       ASSERT_GT(ci.stats.file_write_nanos, 0);
       ASSERT_GT(ci.stats.file_range_sync_nanos, 0);
@@ -519,7 +523,7 @@ class CompactionJobDeletionStatsChecker : public CompactionJobStatsChecker {
  public:
   // Verifies whether two CompactionJobStats match.
   void Verify(const CompactionJobStats& current_stats,
-              const CompactionJobStats& stats) override {
+              const CompactionJobStats& stats) {
     ASSERT_EQ(
       current_stats.num_input_deletion_records,
       stats.num_input_deletion_records);
@@ -802,7 +806,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
     stats_checker->set_verify_next_comp_io_stats(true);
     std::atomic<bool> first_prepare_write(true);
     rocksdb::SyncPoint::GetInstance()->SetCallBack(
-        "WritableFileWriter::Append:BeforePrepareWrite", [&](void* /*arg*/) {
+        "WritableFileWriter::Append:BeforePrepareWrite", [&](void* arg) {
           if (first_prepare_write.load()) {
             options.env->SleepForMicroseconds(3);
             first_prepare_write.store(false);
@@ -811,7 +815,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
 
     std::atomic<bool> first_flush(true);
     rocksdb::SyncPoint::GetInstance()->SetCallBack(
-        "WritableFileWriter::Flush:BeforeAppend", [&](void* /*arg*/) {
+        "WritableFileWriter::Flush:BeforeAppend", [&](void* arg) {
           if (first_flush.load()) {
             options.env->SleepForMicroseconds(3);
             first_flush.store(false);
@@ -820,7 +824,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
 
     std::atomic<bool> first_sync(true);
     rocksdb::SyncPoint::GetInstance()->SetCallBack(
-        "WritableFileWriter::SyncInternal:0", [&](void* /*arg*/) {
+        "WritableFileWriter::SyncInternal:0", [&](void* arg) {
           if (first_sync.load()) {
             options.env->SleepForMicroseconds(3);
             first_sync.store(false);
@@ -829,7 +833,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
 
     std::atomic<bool> first_range_sync(true);
     rocksdb::SyncPoint::GetInstance()->SetCallBack(
-        "WritableFileWriter::RangeSync:0", [&](void* /*arg*/) {
+        "WritableFileWriter::RangeSync:0", [&](void* arg) {
           if (first_range_sync.load()) {
             options.env->SleepForMicroseconds(3);
             first_range_sync.store(false);
@@ -1030,7 +1034,7 @@ int main(int argc, char** argv) {
 #else
 #include <stdio.h>
 
-int main(int /*argc*/, char** /*argv*/) {
+int main(int argc, char** argv) {
   fprintf(stderr, "SKIPPED, not supported in ROCKSDB_LITE\n");
   return 0;
 }
@@ -1039,5 +1043,5 @@ int main(int /*argc*/, char** /*argv*/) {
 
 #else
 
-int main(int /*argc*/, char** /*argv*/) { return 0; }
+int main(int argc, char** argv) { return 0; }
 #endif  // !defined(IOS_CROSS_COMPILE)

db/compaction_job_test.cc

@@ -6,27 +6,22 @@
 #ifndef ROCKSDB_LITE
 
 #include <algorithm>
-#include <array>
-#include <cinttypes>
 #include <map>
 #include <string>
 #include <tuple>
 
-#include "db/blob_index.h"
 #include "db/column_family.h"
-#include "db/compaction/compaction_job.h"
-#include "db/db_impl/db_impl.h"
-#include "db/error_handler.h"
+#include "db/compaction_job.h"
 #include "db/version_set.h"
-#include "file/writable_file_writer.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/options.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/mock_table.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/file_reader_writer.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
 namespace rocksdb {
@@ -72,23 +67,18 @@ class CompactionJobTest : public testing::Test {
  public:
   CompactionJobTest()
       : env_(Env::Default()),
-        fs_(std::make_shared<LegacyFileSystemWrapper>(env_)),
-        dbname_(test::PerThreadDBPath("compaction_job_test")),
+        dbname_(test::TmpDir() + "/compaction_job_test"),
         db_options_(),
         mutable_cf_options_(cf_options_),
         table_cache_(NewLRUCache(50000, 16)),
         write_buffer_manager_(db_options_.db_write_buffer_size),
         versions_(new VersionSet(dbname_, &db_options_, env_options_,
                                  table_cache_.get(), &write_buffer_manager_,
-                                 &write_controller_,
-                                 /*block_cache_tracer=*/nullptr)),
+                                 &write_controller_)),
         shutting_down_(false),
         preserve_deletes_seqnum_(0),
-        mock_table_factory_(new mock::MockTableFactory()),
-        error_handler_(nullptr, db_options_, &mutex_) {
+        mock_table_factory_(new mock::MockTableFactory()) {
     EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    db_options_.env = env_;
-    db_options_.fs = fs_;
     db_options_.db_paths.emplace_back(dbname_,
                                       std::numeric_limits<uint64_t>::max());
   }
@@ -101,34 +91,11 @@ class CompactionJobTest : public testing::Test {
     return TableFileName(db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());
   }
 
-  static std::string KeyStr(const std::string& user_key,
-                            const SequenceNumber seq_num, const ValueType t) {
+  std::string KeyStr(const std::string& user_key, const SequenceNumber seq_num,
+      const ValueType t) {
     return InternalKey(user_key, seq_num, t).Encode().ToString();
   }
 
-  static std::string BlobStr(uint64_t blob_file_number, uint64_t offset,
-                             uint64_t size) {
-    std::string blob_index;
-    BlobIndex::EncodeBlob(&blob_index, blob_file_number, offset, size,
-                          kNoCompression);
-    return blob_index;
-  }
-
-  static std::string BlobStrTTL(uint64_t blob_file_number, uint64_t offset,
-                                uint64_t size, uint64_t expiration) {
-    std::string blob_index;
-    BlobIndex::EncodeBlobTTL(&blob_index, expiration, blob_file_number, offset,
-                             size, kNoCompression);
-    return blob_index;
-  }
-
-  static std::string BlobStrInlinedTTL(const Slice& value,
-                                       uint64_t expiration) {
-    std::string blob_index;
-    BlobIndex::EncodeInlinedTTL(&blob_index, expiration, value);
-    return blob_index;
-  }
-
   void AddMockFile(const stl_wrappers::KVMap& contents, int level = 0) {
     assert(contents.size() > 0);
 
@@ -137,13 +104,12 @@ class CompactionJobTest : public testing::Test {
     InternalKey smallest_key, largest_key;
     SequenceNumber smallest_seqno = kMaxSequenceNumber;
     SequenceNumber largest_seqno = 0;
-    uint64_t oldest_blob_file_number = kInvalidBlobFileNumber;
     for (auto kv : contents) {
       ParsedInternalKey key;
       std::string skey;
       std::string value;
       std::tie(skey, value) = kv;
-      bool parsed = ParseInternalKey(skey, &key);
+      ParseInternalKey(skey, &key);
 
       smallest_seqno = std::min(smallest_seqno, key.sequence);
       largest_seqno = std::max(largest_seqno, key.sequence);
@@ -160,24 +126,6 @@ class CompactionJobTest : public testing::Test {
       }
 
       first_key = false;
-
-      if (parsed && key.type == kTypeBlobIndex) {
-        BlobIndex blob_index;
-        const Status s = blob_index.DecodeFrom(value);
-        if (!s.ok()) {
-          continue;
-        }
-
-        if (blob_index.IsInlined() || blob_index.HasTTL() ||
-            blob_index.file_number() == kInvalidBlobFileNumber) {
-          continue;
-        }
-
-        if (oldest_blob_file_number == kInvalidBlobFileNumber ||
-            oldest_blob_file_number > blob_index.file_number()) {
-          oldest_blob_file_number = blob_index.file_number();
-        }
-      }
     }
 
     uint64_t file_number = versions_->NewFileNumber();
@@ -186,8 +134,7 @@ class CompactionJobTest : public testing::Test {
 
     VersionEdit edit;
     edit.AddFile(level, file_number, 0, 10, smallest_key, largest_key,
-                 smallest_seqno, largest_seqno, false, oldest_blob_file_number,
-                 kUnknownOldestAncesterTime, kUnknownFileCreationTime);
+        smallest_seqno, largest_seqno, false);
 
     mutex_.Lock();
     versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
@@ -223,7 +170,7 @@ class CompactionJobTest : public testing::Test {
         // This is how the key will look like once it's written in bottommost
         // file
         InternalKey bottommost_internal_key(
-            key, 0, kTypeValue);
+            key, (key == "9999") ? sequence_number : 0, kTypeValue);
 
         if (corrupt_id(k)) {
           test::CorruptKeyType(&internal_key);
@@ -245,33 +192,18 @@ class CompactionJobTest : public testing::Test {
   }
 
   void NewDB() {
-    DestroyDB(dbname_, Options());
-    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    versions_.reset(new VersionSet(dbname_, &db_options_, env_options_,
-                                   table_cache_.get(), &write_buffer_manager_,
-                                   &write_controller_,
-                                   /*block_cache_tracer=*/nullptr));
-    compaction_job_stats_.Reset();
-    SetIdentityFile(env_, dbname_);
-
     VersionEdit new_db;
-    if (db_options_.write_dbid_to_manifest) {
-      DBImpl* impl = new DBImpl(DBOptions(), dbname_);
-      std::string db_id;
-      impl->GetDbIdentityFromIdentityFile(&db_id);
-      new_db.SetDBId(db_id);
-    }
     new_db.SetLogNumber(0);
     new_db.SetNextFile(2);
     new_db.SetLastSequence(0);
 
     const std::string manifest = DescriptorFileName(dbname_, 1);
-    std::unique_ptr<WritableFile> file;
+    unique_ptr<WritableFile> file;
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
-    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-        NewLegacyWritableFileWrapper(std::move(file)), manifest, env_options_));
+    unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), env_options_));
     {
       log::Writer log(std::move(file_writer), 0, false);
       std::string record;
@@ -296,9 +228,7 @@ class CompactionJobTest : public testing::Test {
       const std::vector<std::vector<FileMetaData*>>& input_files,
       const stl_wrappers::KVMap& expected_results,
       const std::vector<SequenceNumber>& snapshots = {},
-      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber,
-      int output_level = 1, bool verify = true,
-      uint64_t expected_oldest_blob_file_number = kInvalidBlobFileNumber) {
+      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
     auto cfd = versions_->GetColumnFamilySet()->GetDefault();
 
     size_t num_input_files = 0;
@@ -315,9 +245,8 @@ class CompactionJobTest : public testing::Test {
 
     Compaction compaction(cfd->current()->storage_info(), *cfd->ioptions(),
                           *cfd->GetLatestMutableCFOptions(),
-                          compaction_input_files, output_level, 1024 * 1024,
-                          10 * 1024 * 1024, 0, kNoCompression,
-                          cfd->ioptions()->compression_opts, 0, {}, true);
+                          compaction_input_files, 1, 1024 * 1024,
+                          10 * 1024 * 1024, 0, kNoCompression, {}, true);
     compaction.SetInputVersion(cfd->current());
 
     LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
@@ -325,13 +254,13 @@ class CompactionJobTest : public testing::Test {
     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_, &error_handler_, snapshots,
-        earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_,
-        Env::Priority::USER);
+    CompactionJob compaction_job(0, &compaction, db_options_, env_options_,
+                                 versions_.get(), &shutting_down_,
+                                 preserve_deletes_seqnum_, &log_buffer,
+                                 nullptr, nullptr, nullptr, &mutex_, &bg_error_,
+                                 snapshots, earliest_write_conflict_snapshot,
+                                 snapshot_checker, table_cache_, &event_logger,
+                                 false, false, dbname_, &compaction_job_stats_);
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 
     compaction_job.Prepare();
@@ -343,27 +272,19 @@ class CompactionJobTest : public testing::Test {
     ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions()));
     mutex_.Unlock();
 
-    if (verify) {
+    if (expected_results.size() == 0) {
       ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
       ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-
-      if (expected_results.empty()) {
-        ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
-      } else {
-        ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
-        mock_table_factory_->AssertLatestFile(expected_results);
-
-        auto output_files =
-            cfd->current()->storage_info()->LevelFiles(output_level);
-        ASSERT_EQ(output_files.size(), 1);
-        ASSERT_EQ(output_files[0]->oldest_blob_file_number,
-                  expected_oldest_blob_file_number);
-      }
+      ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
+    } else {
+      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
+      ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
+      mock_table_factory_->AssertLatestFile(expected_results);
     }
   }
 
   Env* env_;
-  std::shared_ptr<FileSystem> fs_;
   std::string dbname_;
   EnvOptions env_options_;
   ImmutableDBOptions db_options_;
@@ -381,7 +302,7 @@ class CompactionJobTest : public testing::Test {
   ColumnFamilyData* cfd_;
   std::unique_ptr<CompactionFilter> compaction_filter_;
   std::shared_ptr<MergeOperator> merge_op_;
-  ErrorHandler error_handler_;
+  Status bg_error_;
 };
 
 TEST_F(CompactionJobTest, Simple) {
@@ -456,7 +377,7 @@ TEST_F(CompactionJobTest, SimpleOverwrite) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "val2"},
-                          {KeyStr("b", 0U, kTypeValue), "val3"}});
+                          {KeyStr("b", 4U, kTypeValue), "val3"}});
 
   SetLastSequence(4U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -509,7 +430,7 @@ TEST_F(CompactionJobTest, SimpleMerge) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 0U, kTypeValue), "1,2"}});
+                          {KeyStr("b", 2U, kTypeValue), "1,2"}});
 
   SetLastSequence(5U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -533,7 +454,8 @@ TEST_F(CompactionJobTest, NonAssocMerge) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 0U, kTypeValue), "1,2"}});
+                          {KeyStr("b", 2U, kTypeMerge), "2"},
+                          {KeyStr("b", 1U, kTypeMerge), "1"}});
 
   SetLastSequence(5U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -560,7 +482,7 @@ TEST_F(CompactionJobTest, MergeOperandFilter) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), test::EncodeInt(8U)},
-                          {KeyStr("b", 0U, kTypeValue), test::EncodeInt(2U)}});
+                          {KeyStr("b", 2U, kTypeMerge), test::EncodeInt(2U)}});
 
   SetLastSequence(5U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -823,7 +745,7 @@ TEST_F(CompactionJobTest, SingleDeleteZeroSeq) {
   AddMockFile(file2);
 
   auto expected_results = mock::MakeMockFile({
-      {KeyStr("dummy", 0U, kTypeValue), "val2"},
+      {KeyStr("dummy", 5U, kTypeValue), "val2"},
   });
 
   SetLastSequence(22U);
@@ -1007,61 +929,13 @@ TEST_F(CompactionJobTest, CorruptionAfterDeletion) {
       mock::MakeMockFile({{test::KeyStr("A", 0U, kTypeValue), "val3"},
                           {test::KeyStr("a", 0U, kTypeValue, true), "val"},
                           {test::KeyStr("b", 0U, kTypeValue, true), "val"},
-                          {test::KeyStr("c", 0U, kTypeValue), "val2"}});
+                          {test::KeyStr("c", 1U, kTypeValue), "val2"}});
 
   SetLastSequence(6U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
   RunCompaction({files}, expected_results);
 }
 
-TEST_F(CompactionJobTest, OldestBlobFileNumber) {
-  NewDB();
-
-  // Note: blob1 is inlined TTL, so it will not be considered for the purposes
-  // of identifying the oldest referenced blob file. Similarly, blob6 will be
-  // ignored because it has TTL and hence refers to a TTL blob file.
-  const stl_wrappers::KVMap::value_type blob1(
-      KeyStr("a", 1U, kTypeBlobIndex), BlobStrInlinedTTL("foo", 1234567890ULL));
-  const stl_wrappers::KVMap::value_type blob2(KeyStr("b", 2U, kTypeBlobIndex),
-                                              BlobStr(59, 123456, 999));
-  const stl_wrappers::KVMap::value_type blob3(KeyStr("c", 3U, kTypeBlobIndex),
-                                              BlobStr(138, 1000, 1 << 8));
-  auto file1 = mock::MakeMockFile({blob1, blob2, blob3});
-  AddMockFile(file1);
-
-  const stl_wrappers::KVMap::value_type blob4(KeyStr("d", 4U, kTypeBlobIndex),
-                                              BlobStr(199, 3 << 10, 1 << 20));
-  const stl_wrappers::KVMap::value_type blob5(KeyStr("e", 5U, kTypeBlobIndex),
-                                              BlobStr(19, 6789, 333));
-  const stl_wrappers::KVMap::value_type blob6(
-      KeyStr("f", 6U, kTypeBlobIndex),
-      BlobStrTTL(5, 2048, 1 << 7, 1234567890ULL));
-  auto file2 = mock::MakeMockFile({blob4, blob5, blob6});
-  AddMockFile(file2);
-
-  const stl_wrappers::KVMap::value_type expected_blob1(
-      KeyStr("a", 0U, kTypeBlobIndex), blob1.second);
-  const stl_wrappers::KVMap::value_type expected_blob2(
-      KeyStr("b", 0U, kTypeBlobIndex), blob2.second);
-  const stl_wrappers::KVMap::value_type expected_blob3(
-      KeyStr("c", 0U, kTypeBlobIndex), blob3.second);
-  const stl_wrappers::KVMap::value_type expected_blob4(
-      KeyStr("d", 0U, kTypeBlobIndex), blob4.second);
-  const stl_wrappers::KVMap::value_type expected_blob5(
-      KeyStr("e", 0U, kTypeBlobIndex), blob5.second);
-  const stl_wrappers::KVMap::value_type expected_blob6(
-      KeyStr("f", 0U, kTypeBlobIndex), blob6.second);
-  auto expected_results =
-      mock::MakeMockFile({expected_blob1, expected_blob2, expected_blob3,
-                          expected_blob4, expected_blob5, expected_blob6});
-
-  SetLastSequence(6U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, std::vector<SequenceNumber>(),
-                kMaxSequenceNumber, /* output_level */ 1, /* verify */ true,
-                /* expected_oldest_blob_file_number */ 19);
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
@@ -1072,7 +946,7 @@ int main(int argc, char** argv) {
 #else
 #include <stdio.h>
 
-int main(int /*argc*/, char** /*argv*/) {
+int main(int argc, char** argv) {
   fprintf(stderr,
           "SKIPPED as CompactionJobStats is not supported in ROCKSDB_LITE\n");
   return 0;

db/compaction_picker.h

@@ -15,7 +15,7 @@
 #include <unordered_set>
 #include <vector>
 
-#include "db/compaction/compaction.h"
+#include "db/compaction.h"
 #include "db/version_set.h"
 #include "options/cf_options.h"
 #include "rocksdb/env.h"
@@ -24,26 +24,11 @@
 
 namespace rocksdb {
 
-// The file contains an abstract class CompactionPicker, and its two
-// sub-classes LevelCompactionPicker and NullCompactionPicker, as
-// well as some helper functions used by them.
-
 class LogBuffer;
 class Compaction;
 class VersionStorageInfo;
 struct CompactionInputFiles;
 
-// An abstract class to pick compactions from an existing LSM-tree.
-//
-// Each compaction style inherits the class and implement the
-// interface to form automatic compactions. If NeedCompaction() is true,
-// then call PickCompaction() to find what files need to be compacted
-// and where to put the output files.
-//
-// Non-virtual functions CompactRange() and CompactFiles() are used to
-// pick files to compact based on users' DB::CompactRange() and
-// DB::CompactFiles() requests, respectively. There is little
-// compaction style specific logic for them.
 class CompactionPicker {
  public:
   CompactionPicker(const ImmutableCFOptions& ioptions,
@@ -54,10 +39,10 @@ class CompactionPicker {
   // Returns nullptr if there is no compaction to be done.
   // Otherwise returns a pointer to a heap-allocated object that
   // describes the compaction.  Caller should delete the result.
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) = 0;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) = 0;
 
   // Return a compaction object for compacting the range [begin,end] in
   // the specified level.  Returns nullptr if there is nothing in that
@@ -73,10 +58,8 @@ class CompactionPicker {
   virtual Compaction* CompactRange(
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
       VersionStorageInfo* vstorage, int input_level, int output_level,
-      const CompactRangeOptions& compact_range_options,
-      const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore);
+      uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
+      InternalKey** compaction_end, bool* manual_conflict);
 
   // The maximum allowed output level.  Default value is NumberLevels() - 1.
   virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
@@ -167,8 +150,7 @@ class CompactionPicker {
   // Will return false if it is impossible to apply this compaction.
   bool ExpandInputsToCleanCut(const std::string& cf_name,
                               VersionStorageInfo* vstorage,
-                              CompactionInputFiles* inputs,
-                              InternalKey** next_smallest = nullptr);
+                              CompactionInputFiles* inputs);
 
   // Returns true if any one of the parent files are being compacted
   bool IsRangeInCompaction(VersionStorageInfo* vstorage,
@@ -192,15 +174,6 @@ class CompactionPicker {
                        const CompactionInputFiles& output_level_inputs,
                        std::vector<FileMetaData*>* grandparents);
 
-  void PickFilesMarkedForCompaction(const std::string& cf_name,
-                                    VersionStorageInfo* vstorage,
-                                    int* start_level, int* output_level,
-                                    CompactionInputFiles* start_level_inputs);
-
-  bool GetOverlappingL0Files(VersionStorageInfo* vstorage,
-                             CompactionInputFiles* start_level_inputs,
-                             int output_level, int* parent_index);
-
   // Register this compaction in the set of running compactions
   void RegisterCompaction(Compaction* c);
 
@@ -236,9 +209,56 @@ class CompactionPicker {
   const InternalKeyComparator* const icmp_;
 };
 
+class LevelCompactionPicker : public CompactionPicker {
+ public:
+  LevelCompactionPicker(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 bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+};
+
 #ifndef ROCKSDB_LITE
-// A dummy compaction that never triggers any automatic
-// compaction.
+class FIFOCompactionPicker : public CompactionPicker {
+ public:
+  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
+                       const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* version,
+                                     LogBuffer* log_buffer) override;
+
+  virtual Compaction* CompactRange(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, int input_level, int output_level,
+      uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
+      InternalKey** compaction_end, bool* manual_conflict) override;
+
+  // The maximum allowed output level.  Always returns 0.
+  virtual int MaxOutputLevel() const override { return 0; }
+
+  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 {
  public:
   NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -247,11 +267,10 @@ class NullCompactionPicker : public CompactionPicker {
   virtual ~NullCompactionPicker() {}
 
   // Always return "nullptr"
-  Compaction* PickCompaction(
-      const std::string& /*cf_name*/,
-      const MutableCFOptions& /*mutable_cf_options*/,
-      VersionStorageInfo* /*vstorage*/, LogBuffer* /* log_buffer */,
-      SequenceNumber /* earliest_memtable_seqno */) override {
+  Compaction* PickCompaction(const std::string& /*cf_name*/,
+                             const MutableCFOptions& /*mutable_cf_options*/,
+                             VersionStorageInfo* /*vstorage*/,
+                             LogBuffer* /*log_buffer*/) override {
     return nullptr;
   }
 
@@ -260,12 +279,11 @@ class NullCompactionPicker : public CompactionPicker {
                            const MutableCFOptions& /*mutable_cf_options*/,
                            VersionStorageInfo* /*vstorage*/,
                            int /*input_level*/, int /*output_level*/,
-                           const CompactRangeOptions& /*compact_range_options*/,
+                           uint32_t /*output_path_id*/,
                            const InternalKey* /*begin*/,
                            const InternalKey* /*end*/,
                            InternalKey** /*compaction_end*/,
-                           bool* /*manual_conflict*/,
-                           uint64_t /*max_file_num_to_ignore*/) override {
+                           bool* /*manual_conflict*/) override {
     return nullptr;
   }
 
@@ -277,37 +295,10 @@ class NullCompactionPicker : public CompactionPicker {
 };
 #endif  // !ROCKSDB_LITE
 
-// Attempts to find an intra L0 compaction conforming to the given parameters.
-//
-// @param level_files                     Metadata for L0 files.
-// @param min_files_to_compact            Minimum number of files required to
-//                                        do the compaction.
-// @param max_compact_bytes_per_del_file  Maximum average size in bytes per
-//                                        file that is going to get deleted by
-//                                        the compaction.
-// @param max_compaction_bytes            Maximum total size in bytes (in terms
-//                                        of compensated file size) for files
-//                                        to be compacted.
-// @param [out] comp_inputs               If a compaction was found, will be
-//                                        initialized with corresponding input
-//                                        files. Cannot be nullptr.
-//
-// @return                                true iff compaction was found.
-bool FindIntraL0Compaction(
-    const std::vector<FileMetaData*>& level_files, size_t min_files_to_compact,
-    uint64_t max_compact_bytes_per_del_file, uint64_t max_compaction_bytes,
-    CompactionInputFiles* comp_inputs,
-    SequenceNumber earliest_mem_seqno = kMaxSequenceNumber);
-
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
                                    const VersionStorageInfo* vstorage,
                                    const MutableCFOptions& mutable_cf_options,
                                    int level, int base_level,
                                    const bool enable_compression = true);
 
-CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
-                                         const VersionStorageInfo* vstorage,
-                                         int level,
-                                         const bool enable_compression = true);
-
 }  // namespace rocksdb

db/compaction_picker_test.cc

@@ -3,26 +3,26 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-
+#include "db/compaction_picker.h"
 #include <limits>
 #include <string>
 #include <utility>
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
+#include "db/compaction.h"
+#include "db/compaction_picker_universal.h"
 
-#include "logging/logging.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/logging.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
 class CountingLogger : public Logger {
  public:
   using Logger::Logv;
-  void Logv(const char* /*format*/, va_list /*ap*/) override { log_count++; }
+  virtual void Logv(const char* /*format*/, va_list /*ap*/) override {
+    log_count++;
+  }
   size_t log_count;
 };
 
@@ -57,18 +57,14 @@ class CompactionPickerTest : public testing::Test {
         log_buffer_(InfoLogLevel::INFO_LEVEL, &logger_),
         file_num_(1),
         vstorage_(nullptr) {
-    mutable_cf_options_.ttl = 0;
-    mutable_cf_options_.periodic_compaction_seconds = 0;
-    // ioptions_.compaction_pri = kMinOverlappingRatio has its own set of
-    // tests to cover.
-    ioptions_.compaction_pri = kByCompensatedSize;
     fifo_options_.max_table_files_size = 1;
     mutable_cf_options_.RefreshDerivedOptions(ioptions_);
-    ioptions_.cf_paths.emplace_back("dummy",
+    ioptions_.db_paths.emplace_back("dummy",
                                     std::numeric_limits<uint64_t>::max());
   }
 
-  ~CompactionPickerTest() override {}
+  ~CompactionPickerTest() {
+  }
 
   void NewVersionStorage(int num_levels, CompactionStyle style) {
     DeleteVersionStorage();
@@ -87,17 +83,17 @@ class CompactionPickerTest : public testing::Test {
 
   void Add(int level, uint32_t file_number, const char* smallest,
            const char* largest, uint64_t file_size = 1, uint32_t path_id = 0,
-           SequenceNumber smallest_seq = 100, SequenceNumber largest_seq = 100,
-           size_t compensated_file_size = 0) {
+           SequenceNumber smallest_seq = 100,
+           SequenceNumber largest_seq = 100) {
     assert(level < vstorage_->num_levels());
-    FileMetaData* f = new FileMetaData(
-        file_number, path_id, file_size,
-        InternalKey(smallest, smallest_seq, kTypeValue),
-        InternalKey(largest, largest_seq, kTypeValue), smallest_seq,
-        largest_seq, /* marked_for_compact */ false, kInvalidBlobFileNumber,
-        kUnknownOldestAncesterTime, kUnknownFileCreationTime);
-    f->compensated_file_size =
-        (compensated_file_size != 0) ? compensated_file_size : file_size;
+    FileMetaData* f = new FileMetaData;
+    f->fd = FileDescriptor(file_number, path_id, file_size);
+    f->smallest = InternalKey(smallest, smallest_seq, kTypeValue);
+    f->largest = InternalKey(largest, largest_seq, kTypeValue);
+    f->smallest_seqno = smallest_seq;
+    f->largest_seqno = largest_seq;
+    f->compensated_file_size = file_size;
+    f->refs = 0;
     vstorage_->AddFile(level, f);
     files_.emplace_back(f);
     file_map_.insert({file_number, {f, level}});
@@ -395,10 +391,10 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(
       ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);
+  UpdateVersionStorageInfo();
 
   // verify the trigger given different number of L0 files.
   for (int i = 1;
@@ -419,7 +415,6 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
   ioptions_.allow_ingest_behind = true;
   ioptions_.num_levels = 3;
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);
@@ -453,7 +448,6 @@ TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
   mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);
@@ -502,168 +496,6 @@ TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
   ASSERT_TRUE(compaction->is_trivial_move());
 }
 
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction1) {
-  // The case where universal periodic compaction can be picked
-  // with some newer files being compacted.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, 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(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[2].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(4, file_map_[3].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(4, compaction->output_level());
-  ASSERT_EQ(0, compaction->start_level());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction2) {
-  // The case where universal periodic compaction does not
-  // pick up only level to compact if it doesn't cover
-  // any file marked as periodic compaction.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[5].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[1].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_FALSE(compaction);
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction3) {
-  // The case where universal periodic compaction does not
-  // pick up only the last sorted run which is an L0 file if it isn't
-  // marked as periodic compaction.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(0, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[5].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[1].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_FALSE(compaction);
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction4) {
-  // The case where universal periodic compaction couldn't form
-  // a compaction that inlcudes any file marked for periodic compaction.
-  // Right now we form the compaction anyway if it is more than one
-  // sorted run. Just put the case here to validate that it doesn't
-  // crash.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(2, 2U, "010", "080", kFileSize, 0, 200, 251);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[2].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[2].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(!compaction ||
-              compaction->start_level() != compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction5) {
-  // Test single L0 file periodic compaction triggering.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 6U, "150", "200", kFileSize, 0, 500, 550);
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[6].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(0, compaction->start_level());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(6U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(4, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction6) {
-  // Test single sorted run non-L0 periodic compaction
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(4, 5U, "150", "200", kFileSize, 0, 500, 550);
-  Add(4, 6U, "350", "400", kFileSize, 0, 500, 550);
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(4, file_map_[6].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(4, compaction->start_level());
-  ASSERT_EQ(2U, compaction->num_input_files(0));
-  ASSERT_EQ(5U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(6U, compaction->input(0, 1)->fd.GetNumber());
-  ASSERT_EQ(4, compaction->output_level());
-}
-
 TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const int kFileCount =
@@ -781,35 +613,6 @@ TEST_F(CompactionPickerTest, CompactionPriMinOverlapping3) {
   ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, CompactionPriMinOverlapping4) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.max_bytes_for_level_base = 10000000;
-  mutable_cf_options_.max_bytes_for_level_multiplier = 10;
-
-  // file 7 and 8 over lap with the same file, but file 8 is smaller so
-  // it will be picked.
-  // Overlaps with file 26, 27. And the file is compensated so will be
-  // picked up.
-  Add(2, 6U, "150", "167", 60000000U, 0, 100, 100, 180000000U);
-  Add(2, 7U, "168", "169", 60000000U);  // Overlaps with file 27
-  Add(2, 8U, "201", "300", 61000000U);  // Overlaps with file 28
-
-  Add(3, 26U, "160", "165", 60000000U);
-  // Boosted file size in output level is not considered.
-  Add(3, 27U, "166", "170", 60000000U, 0, 100, 100, 260000000U);
-  Add(3, 28U, "180", "400", 60000000U);
-  Add(3, 29U, "401", "500", 60000000U);
-  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_files(0));
-  // Picking file 8 because overlapping ratio is the biggest.
-  ASSERT_EQ(6U, compaction->input(0, 0)->fd.GetNumber());
-}
-
 // This test exhibits the bug where we don't properly reset parent_index in
 // PickCompaction()
 TEST_F(CompactionPickerTest, ParentIndexResetBug) {
@@ -1641,97 +1444,6 @@ TEST_F(CompactionPickerTest, CacheNextCompactionIndex) {
   ASSERT_EQ(4, vstorage_->NextCompactionIndex(1 /* level */));
 }
 
-TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesNotHit) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 1000000u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // All 5 L0 files will be picked for intra L0 compaction. The one L1 file
-  // spans entire L0 key range and is marked as being compacted to avoid
-  // L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U, 0, 100, 101);
-  Add(0, 2U, "151", "200", 200000U, 0, 102, 103);
-  Add(0, 3U, "201", "250", 200000U, 0, 104, 105);
-  Add(0, 4U, "251", "300", 200000U, 0, 106, 107);
-  Add(0, 5U, "301", "350", 200000U, 0, 108, 109);
-  Add(1, 6U, "100", "350", 200000U, 0, 110, 111);
-  vstorage_->LevelFiles(1)[0]->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(5U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesHit) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 999999u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // 4 out of 5 L0 files will be picked for intra L0 compaction due to
-  // max_compaction_bytes limit (the minimum number of files for triggering
-  // intra L0 compaction is 4). The one L1 file spans entire L0 key range and
-  // is marked as being compacted to avoid L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U, 0, 100, 101);
-  Add(0, 2U, "151", "200", 200000U, 0, 102, 103);
-  Add(0, 3U, "201", "250", 200000U, 0, 104, 105);
-  Add(0, 4U, "251", "300", 200000U, 0, 106, 107);
-  Add(0, 5U, "301", "350", 200000U, 0, 108, 109);
-  Add(1, 6U, "100", "350", 200000U, 0, 109, 110);
-  vstorage_->LevelFiles(1)[0]->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(4U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, IntraL0ForEarliestSeqno) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 999999u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // 4 out of 6 L0 files will be picked for intra L0 compaction due to
-  // being_compact limit. And the latest one L0 will be skipped due to earliest
-  // seqno. The one L1 file spans entire L0 key range and is marked as being
-  // compacted to avoid L0->L1 compaction.
-  Add(1, 1U, "100", "350", 200000U, 0, 110, 111);
-  Add(0, 2U, "301", "350", 1U, 0, 108, 109);
-  Add(0, 3U, "251", "300", 1U, 0, 106, 107);
-  Add(0, 4U, "201", "250", 1U, 0, 104, 105);
-  Add(0, 5U, "151", "200", 1U, 0, 102, 103);
-  Add(0, 6U, "100", "150", 1U, 0, 100, 101);
-  Add(0, 7U, "100", "100", 1U, 0, 99, 100);
-  vstorage_->LevelFiles(0)[5]->being_compacted = true;
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_, 107));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(4U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/compaction_picker_universal.cc

@@ -0,0 +1,755 @@
+//  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::kUniversalSizeRatio;
+  } else {
+    compaction_reason = CompactionReason::kUniversalSortedRunNum;
+  }
+  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

@@ -0,0 +1,93 @@
+//  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/comparator_db_test.cc

@@ -2,18 +2,17 @@
 //  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 <array>
 #include <map>
 #include <string>
 
 #include "memtable/stl_wrappers.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/hash.h"
 #include "util/kv_map.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
 using std::unique_ptr;
@@ -27,24 +26,24 @@ class KVIter : public Iterator {
  public:
   explicit KVIter(const stl_wrappers::KVMap* map)
       : map_(map), iter_(map_->end()) {}
-  bool Valid() const override { return iter_ != map_->end(); }
-  void SeekToFirst() override { iter_ = map_->begin(); }
-  void SeekToLast() override {
+  virtual bool Valid() const override { return iter_ != map_->end(); }
+  virtual void SeekToFirst() override { iter_ = map_->begin(); }
+  virtual void SeekToLast() override {
     if (map_->empty()) {
       iter_ = map_->end();
     } else {
       iter_ = map_->find(map_->rbegin()->first);
     }
   }
-  void Seek(const Slice& k) override {
+  virtual void Seek(const Slice& k) override {
     iter_ = map_->lower_bound(k.ToString());
   }
-  void SeekForPrev(const Slice& k) override {
+  virtual void SeekForPrev(const Slice& k) override {
     iter_ = map_->upper_bound(k.ToString());
     Prev();
   }
-  void Next() override { ++iter_; }
-  void Prev() override {
+  virtual void Next() override { ++iter_; }
+  virtual void Prev() override {
     if (iter_ == map_->begin()) {
       iter_ = map_->end();
       return;
@@ -52,9 +51,9 @@ class KVIter : public Iterator {
     --iter_;
   }
 
-  Slice key() const override { return iter_->first; }
-  Slice value() const override { return iter_->second; }
-  Status status() const override { return Status::OK(); }
+  virtual Slice key() const override { return iter_->first; }
+  virtual Slice value() const override { return iter_->second; }
+  virtual Status status() const override { return Status::OK(); }
 
  private:
   const stl_wrappers::KVMap* const map_;
@@ -171,9 +170,9 @@ class DoubleComparator : public Comparator {
  public:
   DoubleComparator() {}
 
-  const char* Name() const override { return "DoubleComparator"; }
+  virtual const char* Name() const override { return "DoubleComparator"; }
 
-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
 #ifndef CYGWIN
     double da = std::stod(a.ToString());
     double db = std::stod(b.ToString());
@@ -189,19 +188,19 @@ class DoubleComparator : public Comparator {
       return -1;
     }
   }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}
 
-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 
 class HashComparator : public Comparator {
  public:
   HashComparator() {}
 
-  const char* Name() const override { return "HashComparator"; }
+  virtual const char* Name() const override { return "HashComparator"; }
 
-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
     uint32_t ha = Hash(a.data(), a.size(), 66);
     uint32_t hb = Hash(b.data(), b.size(), 66);
     if (ha == hb) {
@@ -212,19 +211,19 @@ class HashComparator : public Comparator {
       return -1;
     }
   }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}
 
-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 
 class TwoStrComparator : public Comparator {
  public:
   TwoStrComparator() {}
 
-  const char* Name() const override { return "TwoStrComparator"; }
+  virtual const char* Name() const override { return "TwoStrComparator"; }
 
-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
     assert(a.size() >= 2);
     assert(b.size() >= 2);
     size_t size_a1 = static_cast<size_t>(a[0]);
@@ -244,16 +243,14 @@ class TwoStrComparator : public Comparator {
     }
     return a2.compare(b2);
   }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}
 
-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 }  // namespace
 
-class ComparatorDBTest
-    : public testing::Test,
-      virtual public ::testing::WithParamInterface<uint32_t> {
+class ComparatorDBTest : public testing::Test {
  private:
   std::string dbname_;
   Env* env_;
@@ -264,15 +261,11 @@ class ComparatorDBTest
  public:
   ComparatorDBTest() : env_(Env::Default()), db_(nullptr) {
     comparator = BytewiseComparator();
-    dbname_ = test::PerThreadDBPath("comparator_db_test");
-    BlockBasedTableOptions toptions;
-    toptions.format_version = GetParam();
-    last_options_.table_factory.reset(
-        rocksdb::NewBlockBasedTableFactory(toptions));
+    dbname_ = test::TmpDir() + "/comparator_db_test";
     EXPECT_OK(DestroyDB(dbname_, last_options_));
   }
 
-  ~ComparatorDBTest() override {
+  ~ComparatorDBTest() {
     delete db_;
     EXPECT_OK(DestroyDB(dbname_, last_options_));
     comparator = BytewiseComparator();
@@ -280,12 +273,8 @@ class ComparatorDBTest
 
   DB* GetDB() { return db_; }
 
-  void SetOwnedComparator(const Comparator* cmp, bool owner = true) {
-    if (owner) {
-      comparator_guard.reset(cmp);
-    } else {
-      comparator_guard.reset();
-    }
+  void SetOwnedComparator(const Comparator* cmp) {
+    comparator_guard.reset(cmp);
     comparator = cmp;
     last_options_.comparator = cmp;
   }
@@ -314,12 +303,7 @@ class ComparatorDBTest
   }
 };
 
-INSTANTIATE_TEST_CASE_P(FormatDef, ComparatorDBTest,
-                        testing::Values(test::kDefaultFormatVersion));
-INSTANTIATE_TEST_CASE_P(FormatLatest, ComparatorDBTest,
-                        testing::Values(test::kLatestFormatVersion));
-
-TEST_P(ComparatorDBTest, Bytewise) {
+TEST_F(ComparatorDBTest, Bytewise) {
   for (int rand_seed = 301; rand_seed < 306; rand_seed++) {
     DestroyAndReopen();
     Random rnd(rand_seed);
@@ -329,7 +313,7 @@ TEST_P(ComparatorDBTest, Bytewise) {
   }
 }
 
-TEST_P(ComparatorDBTest, SimpleSuffixReverseComparator) {
+TEST_F(ComparatorDBTest, SimpleSuffixReverseComparator) {
   SetOwnedComparator(new test::SimpleSuffixReverseComparator());
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -355,8 +339,8 @@ TEST_P(ComparatorDBTest, SimpleSuffixReverseComparator) {
   }
 }
 
-TEST_P(ComparatorDBTest, Uint64Comparator) {
-  SetOwnedComparator(test::Uint64Comparator(), false /* owner */);
+TEST_F(ComparatorDBTest, Uint64Comparator) {
+  SetOwnedComparator(test::Uint64Comparator());
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
     Options* opt = GetOptions();
@@ -379,7 +363,7 @@ TEST_P(ComparatorDBTest, Uint64Comparator) {
   }
 }
 
-TEST_P(ComparatorDBTest, DoubleComparator) {
+TEST_F(ComparatorDBTest, DoubleComparator) {
   SetOwnedComparator(new DoubleComparator());
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -404,7 +388,7 @@ TEST_P(ComparatorDBTest, DoubleComparator) {
   }
 }
 
-TEST_P(ComparatorDBTest, HashComparator) {
+TEST_F(ComparatorDBTest, HashComparator) {
   SetOwnedComparator(new HashComparator());
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -423,7 +407,7 @@ TEST_P(ComparatorDBTest, HashComparator) {
   }
 }
 
-TEST_P(ComparatorDBTest, TwoStrComparator) {
+TEST_F(ComparatorDBTest, TwoStrComparator) {
   SetOwnedComparator(new TwoStrComparator());
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -449,209 +433,6 @@ TEST_P(ComparatorDBTest, TwoStrComparator) {
   }
 }
 
-TEST_P(ComparatorDBTest, IsSameLengthImmediateSuccessor) {
-  {
-    // different length
-    Slice s("abcxy");
-    Slice t("abcxyz");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    Slice s("abcxyz");
-    Slice t("abcxy");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    // not last byte different
-    Slice s("abc1xyz");
-    Slice t("abc2xyz");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    // same string
-    Slice s("abcxyz");
-    Slice t("abcxyz");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    Slice s("abcxy");
-    Slice t("abcxz");
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    Slice s("abcxz");
-    Slice t("abcxy");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xac";
-    const char t_array[] = "\x50\x8a\xad";
-    Slice s(s_array);
-    Slice t(t_array);
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xff";
-    const char t_array[] = "\x50\x8b\x00";
-    Slice s(s_array, 3);
-    Slice t(t_array, 3);
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xff\xff";
-    const char t_array[] = "\x50\x8b\x00\x00";
-    Slice s(s_array, 4);
-    Slice t(t_array, 4);
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xff\xff";
-    const char t_array[] = "\x50\x8b\x00\x01";
-    Slice s(s_array, 4);
-    Slice t(t_array, 4);
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-}
-
-TEST_P(ComparatorDBTest, FindShortestSeparator) {
-  std::string s1 = "abc1xyz";
-  std::string s2 = "abc3xy";
-
-  BytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc2", s1);
-
-  s1 = "abc5xyztt";
-
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc5", s1);
-
-  s1 = "abc3";
-  s2 = "abc2xy";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc3", s1);
-
-  s1 = "abc3xyz";
-  s2 = "abc2xy";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc3", s1);
-
-  s1 = "abc3xyz";
-  s2 = "abc2";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc3", s1);
-
-  std::string old_s1 = s1 = "abc2xy";
-  s2 = "abc2";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_TRUE(old_s1 >= s1);
-  ASSERT_TRUE(s1 > s2);
-}
-
-TEST_P(ComparatorDBTest, SeparatorSuccessorRandomizeTest) {
-  // Char list for boundary cases.
-  std::array<unsigned char, 6> char_list{{0, 1, 2, 253, 254, 255}};
-  Random rnd(301);
-
-  for (int attempts = 0; attempts < 1000; attempts++) {
-    uint32_t size1 = rnd.Skewed(4);
-    uint32_t size2;
-
-    if (rnd.OneIn(2)) {
-      // size2 to be random size
-      size2 = rnd.Skewed(4);
-    } else {
-      // size1 is within [-2, +2] of size1
-      int diff = static_cast<int>(rnd.Uniform(5)) - 2;
-      int tmp_size2 = static_cast<int>(size1) + diff;
-      if (tmp_size2 < 0) {
-        tmp_size2 = 0;
-      }
-      size2 = static_cast<uint32_t>(tmp_size2);
-    }
-
-    std::string s1;
-    std::string s2;
-    for (uint32_t i = 0; i < size1; i++) {
-      if (rnd.OneIn(2)) {
-        // Use random byte
-        s1 += static_cast<char>(rnd.Uniform(256));
-      } else {
-        // Use one byte in char_list
-        char c = static_cast<char>(char_list[rnd.Uniform(sizeof(char_list))]);
-        s1 += c;
-      }
-    }
-
-    // First set s2 to be the same as s1, and then modify s2.
-    s2 = s1;
-    s2.resize(size2);
-    // We start from the back of the string
-    if (size2 > 0) {
-      uint32_t pos = size2 - 1;
-      do {
-        if (pos >= size1 || rnd.OneIn(4)) {
-          // For 1/4 chance, use random byte
-          s2[pos] = static_cast<char>(rnd.Uniform(256));
-        } else if (rnd.OneIn(4)) {
-          // In 1/4 chance, stop here.
-          break;
-        } else {
-          // Create a char within [-2, +2] of the matching char of s1.
-          int diff = static_cast<int>(rnd.Uniform(5)) - 2;
-          // char may be signed or unsigned based on platform.
-          int s1_char = static_cast<int>(static_cast<unsigned char>(s1[pos]));
-          int s2_char = s1_char + diff;
-          if (s2_char < 0) {
-            s2_char = 0;
-          }
-          if (s2_char > 255) {
-            s2_char = 255;
-          }
-          s2[pos] = static_cast<char>(s2_char);
-        }
-      } while (pos-- != 0);
-    }
-
-    // Test separators
-    for (int rev = 0; rev < 2; rev++) {
-      if (rev == 1) {
-        // switch s1 and s2
-        std::string t = s1;
-        s1 = s2;
-        s2 = t;
-      }
-      std::string separator = s1;
-      BytewiseComparator()->FindShortestSeparator(&separator, s2);
-      std::string rev_separator = s1;
-      ReverseBytewiseComparator()->FindShortestSeparator(&rev_separator, s2);
-
-      if (s1 == s2) {
-        ASSERT_EQ(s1, separator);
-        ASSERT_EQ(s2, rev_separator);
-      } else if (s1 < s2) {
-        ASSERT_TRUE(s1 <= separator);
-        ASSERT_TRUE(s2 > separator);
-        ASSERT_LE(separator.size(), std::max(s1.size(), s2.size()));
-        ASSERT_EQ(s1, rev_separator);
-      } else {
-        ASSERT_TRUE(s1 >= rev_separator);
-        ASSERT_TRUE(s2 < rev_separator);
-        ASSERT_LE(rev_separator.size(), std::max(s1.size(), s2.size()));
-        ASSERT_EQ(s1, separator);
-      }
-    }
-
-    // Test successors
-    std::string succ = s1;
-    BytewiseComparator()->FindShortSuccessor(&succ);
-    ASSERT_TRUE(succ >= s1);
-
-    succ = s1;
-    ReverseBytewiseComparator()->FindShortSuccessor(&succ);
-    ASSERT_TRUE(succ <= s1);
-  }
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/convenience.cc

@@ -8,7 +8,7 @@
 
 #include "rocksdb/convenience.h"
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "util/cast_util.h"
 
 namespace rocksdb {
@@ -35,40 +35,29 @@ Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
 Status VerifySstFileChecksum(const Options& options,
                              const EnvOptions& env_options,
                              const std::string& file_path) {
-  return VerifySstFileChecksum(options, env_options, ReadOptions(), file_path);
-}
-Status VerifySstFileChecksum(const Options& options,
-                             const EnvOptions& env_options,
-                             const ReadOptions& read_options,
-                             const std::string& file_path) {
-  std::unique_ptr<FSRandomAccessFile> file;
+  unique_ptr<RandomAccessFile> file;
   uint64_t file_size;
   InternalKeyComparator internal_comparator(options.comparator);
   ImmutableCFOptions ioptions(options);
 
-  Status s = ioptions.fs->NewRandomAccessFile(file_path,
-                                              FileOptions(env_options),
-                                              &file, nullptr);
+  Status s = ioptions.env->NewRandomAccessFile(file_path, &file, env_options);
   if (s.ok()) {
-    s = ioptions.fs->GetFileSize(file_path, IOOptions(), &file_size, nullptr);
+    s = ioptions.env->GetFileSize(file_path, &file_size);
   } else {
     return s;
   }
-  std::unique_ptr<TableReader> table_reader;
+  unique_ptr<TableReader> table_reader;
   std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(std::move(file), file_path));
-  const bool kImmortal = true;
   s = ioptions.table_factory->NewTableReader(
-      TableReaderOptions(ioptions, options.prefix_extractor.get(), env_options,
-                         internal_comparator, false /* skip_filters */,
-                         !kImmortal, -1 /* level */),
+      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(read_options,
-                                   TableReaderCaller::kUserVerifyChecksum);
+  s = table_reader->VerifyChecksum();
   return s;
 }
 

db/corruption_test.cc

@@ -13,25 +13,21 @@
 
 #include <errno.h>
 #include <fcntl.h>
+#include <inttypes.h>
 #include <sys/stat.h>
 #include <sys/types.h>
-#include <cinttypes>
-#include "db/db_impl/db_impl.h"
-#include "db/db_test_util.h"
+#include "db/db_impl.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "env/composite_env_wrapper.h"
-#include "file/filename.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/convenience.h"
 #include "rocksdb/env.h"
 #include "rocksdb/table.h"
 #include "rocksdb/write_batch.h"
-#include "table/block_based/block_based_table_builder.h"
-#include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/filename.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
@@ -41,7 +37,7 @@ class CorruptionTest : public testing::Test {
  public:
   test::ErrorEnv env_;
   std::string dbname_;
-  std::shared_ptr<Cache> tiny_cache_;
+  shared_ptr<Cache> tiny_cache_;
   Options options_;
   DB* db_;
 
@@ -52,7 +48,7 @@ class CorruptionTest : public testing::Test {
     tiny_cache_ = NewLRUCache(100, 4);
     options_.wal_recovery_mode = WALRecoveryMode::kTolerateCorruptedTailRecords;
     options_.env = &env_;
-    dbname_ = test::PerThreadDBPath("corruption_test");
+    dbname_ = test::TmpDir() + "/corruption_test";
     DestroyDB(dbname_, options_);
 
     db_ = nullptr;
@@ -64,9 +60,9 @@ class CorruptionTest : public testing::Test {
     options_.create_if_missing = false;
   }
 
-  ~CorruptionTest() override {
-    delete db_;
-    DestroyDB(dbname_, Options());
+  ~CorruptionTest() {
+     delete db_;
+     DestroyDB(dbname_, Options());
   }
 
   void CloseDb() {
@@ -78,11 +74,7 @@ class CorruptionTest : public testing::Test {
     delete db_;
     db_ = nullptr;
     Options opt = (options ? *options : options_);
-    if (opt.env == Options().env) {
-      // If env is not overridden, replace it with ErrorEnv.
-      // Otherwise, the test already uses a non-default Env.
-      opt.env = &env_;
-    }
+    opt.env = &env_;
     opt.arena_block_size = 4096;
     BlockBasedTableOptions table_options;
     table_options.block_cache = tiny_cache_;
@@ -190,7 +182,6 @@ class CorruptionTest : public testing::Test {
     ASSERT_TRUE(s.ok()) << s.ToString();
     Options options;
     EnvOptions env_options;
-    options.file_system.reset(new LegacyFileSystemWrapper(options.env));
     ASSERT_NOK(VerifySstFileChecksum(options, env_options, fname));
   }
 
@@ -328,59 +319,6 @@ TEST_F(CorruptionTest, TableFile) {
   ASSERT_NOK(dbi->VerifyChecksum());
 }
 
-TEST_F(CorruptionTest, VerifyChecksumReadahead) {
-  Options options;
-  SpecialEnv senv(Env::Default());
-  options.env = &senv;
-  // Disable block cache as we are going to check checksum for
-  // the same file twice and measure number of reads.
-  BlockBasedTableOptions table_options_no_bc;
-  table_options_no_bc.no_block_cache = true;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options_no_bc));
-
-  Reopen(&options);
-
-  Build(10000);
-  DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
-  dbi->TEST_FlushMemTable();
-  dbi->TEST_CompactRange(0, nullptr, nullptr);
-  dbi->TEST_CompactRange(1, nullptr, nullptr);
-
-  senv.count_random_reads_ = true;
-  senv.random_read_counter_.Reset();
-  ASSERT_OK(dbi->VerifyChecksum());
-
-  // Make sure the counter is enabled.
-  ASSERT_GT(senv.random_read_counter_.Read(), 0);
-
-  // The SST file is about 10MB. Default readahead size is 256KB.
-  // Give a conservative 20 reads for metadata blocks, The number
-  // of random reads should be within 10 MB / 256KB + 20 = 60.
-  ASSERT_LT(senv.random_read_counter_.Read(), 60);
-
-  senv.random_read_bytes_counter_ = 0;
-  ReadOptions ro;
-  ro.readahead_size = size_t{32 * 1024};
-  ASSERT_OK(dbi->VerifyChecksum(ro));
-  // The SST file is about 10MB. We set readahead size to 32KB.
-  // Give 0 to 20 reads for metadata blocks, and allow real read
-  // to range from 24KB to 48KB. The lower bound would be:
-  //   10MB / 48KB + 0 = 213
-  // The higher bound is
-  //   10MB / 24KB + 20 = 447.
-  ASSERT_GE(senv.random_read_counter_.Read(), 213);
-  ASSERT_LE(senv.random_read_counter_.Read(), 447);
-
-  // Test readahead shouldn't break mmap mode (where it should be
-  // disabled).
-  options.allow_mmap_reads = true;
-  Reopen(&options);
-  dbi = static_cast<DBImpl*>(db_);
-  ASSERT_OK(dbi->VerifyChecksum(ro));
-
-  CloseDb();
-}
-
 TEST_F(CorruptionTest, TableFileIndexData) {
   Options options;
   // very big, we'll trigger flushes manually
@@ -395,9 +333,9 @@ TEST_F(CorruptionTest, TableFileIndexData) {
   Corrupt(kTableFile, -2000, 500);
   Reopen();
   dbi = reinterpret_cast<DBImpl*>(db_);
-  // one full file may be readable, since only one was corrupted
+  // one full file should be readable, since only one was corrupted
   // the other file should be fully non-readable, since index was corrupted
-  Check(0, 5000);
+  Check(5000, 5000);
   ASSERT_NOK(dbi->VerifyChecksum());
 }
 
@@ -529,40 +467,6 @@ TEST_F(CorruptionTest, UnrelatedKeys) {
   ASSERT_EQ(Value(1000, &tmp2).ToString(), v);
 }
 
-TEST_F(CorruptionTest, RangeDeletionCorrupted) {
-  ASSERT_OK(
-      db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), "a", "b"));
-  ASSERT_OK(db_->Flush(FlushOptions()));
-  std::vector<LiveFileMetaData> metadata;
-  db_->GetLiveFilesMetaData(&metadata);
-  ASSERT_EQ(static_cast<size_t>(1), metadata.size());
-  std::string filename = dbname_ + metadata[0].name;
-
-  std::unique_ptr<RandomAccessFile> file;
-  ASSERT_OK(options_.env->NewRandomAccessFile(filename, &file, EnvOptions()));
-  std::unique_ptr<RandomAccessFileReader> file_reader(
-      new RandomAccessFileReader(NewLegacyRandomAccessFileWrapper(file),
-                                 filename));
-
-  uint64_t file_size;
-  ASSERT_OK(options_.env->GetFileSize(filename, &file_size));
-
-  BlockHandle range_del_handle;
-  ASSERT_OK(FindMetaBlock(
-      file_reader.get(), file_size, kBlockBasedTableMagicNumber,
-      ImmutableCFOptions(options_), kRangeDelBlock, &range_del_handle));
-
-  ASSERT_OK(TryReopen());
-  CorruptFile(filename, static_cast<int>(range_del_handle.offset()), 1);
-  // The test case does not fail on TryReopen because failure to preload table
-  // handlers is not considered critical.
-  ASSERT_OK(TryReopen());
-  std::string val;
-  // However, it does fail on any read involving that file since that file
-  // cannot be opened with a corrupt range deletion meta-block.
-  ASSERT_TRUE(db_->Get(ReadOptions(), "a", &val).IsCorruption());
-}
-
 TEST_F(CorruptionTest, FileSystemStateCorrupted) {
   for (int iter = 0; iter < 2; ++iter) {
     Options options;
@@ -581,7 +485,7 @@ TEST_F(CorruptionTest, FileSystemStateCorrupted) {
     db_ = nullptr;
 
     if (iter == 0) {  // corrupt file size
-      std::unique_ptr<WritableFile> file;
+      unique_ptr<WritableFile> file;
       env_.NewWritableFile(filename, &file, EnvOptions());
       file->Append(Slice("corrupted sst"));
       file.reset();
@@ -606,7 +510,7 @@ int main(int argc, char** argv) {
 #else
 #include <stdio.h>
 
-int main(int /*argc*/, char** /*argv*/) {
+int main(int argc, char** argv) {
   fprintf(stderr, "SKIPPED as RepairDB() is not supported in ROCKSDB_LITE\n");
   return 0;
 }

db/cuckoo_table_db_test.cc

@@ -5,15 +5,15 @@
 
 #ifndef ROCKSDB_LITE
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "table/cuckoo/cuckoo_table_factory.h"
-#include "table/cuckoo/cuckoo_table_reader.h"
+#include "table/cuckoo_table_factory.h"
+#include "table/cuckoo_table_reader.h"
 #include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
@@ -25,13 +25,13 @@ class CuckooTableDBTest : public testing::Test {
 
  public:
   CuckooTableDBTest() : env_(Env::Default()) {
-    dbname_ = test::PerThreadDBPath("cuckoo_table_db_test");
+    dbname_ = test::TmpDir() + "/cuckoo_table_db_test";
     EXPECT_OK(DestroyDB(dbname_, Options()));
     db_ = nullptr;
     Reopen();
   }
 
-  ~CuckooTableDBTest() override {
+  ~CuckooTableDBTest() {
     delete db_;
     EXPECT_OK(DestroyDB(dbname_, Options()));
   }
@@ -285,9 +285,6 @@ TEST_F(CuckooTableDBTest, SameKeyInsertedInTwoDifferentFilesAndCompacted) {
 TEST_F(CuckooTableDBTest, AdaptiveTable) {
   Options options = CurrentOptions();
 
-  // Ensure options compatible with PlainTable
-  options.prefix_extractor.reset(NewCappedPrefixTransform(8));
-
   // Write some keys using cuckoo table.
   options.table_factory.reset(NewCuckooTableFactory());
   Reopen(&options);
@@ -336,7 +333,7 @@ int main(int argc, char** argv) {
 #else
 #include <stdio.h>
 
-int main(int /*argc*/, char** /*argv*/) {
+int main(int argc, char** argv) {
   fprintf(stderr, "SKIPPED as Cuckoo table is not supported in ROCKSDB_LITE\n");
   return 0;
 }