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

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

Differential Revision: D4945577

Pulled By: lightmark

fbshipit-source-id: 4e679150f2c9443d3be0b6008b26b65fabbda75a

.arcconfig

@@ -0,0 +1,17 @@
+{
+  "project_id" : "rocksdb",
+  "conduit_uri" : "https://phabricator.fb.com/api/",
+  "copyright_holder" : "Facebook",
+  "load" : [
+    "arcanist_util"
+  ],
+  "lint.engine" : "FacebookFbcodeLintEngine",
+  "lint.engine.single.linter" : "FbcodeCppLinter",
+  "unit.engine" : "FacebookFbcodeUnitTestEngine",
+  "arcanist_configuration" : "FacebookArcanistConfiguration",
+  "base" : "git:HEAD^, hg:.^",
+  "git.default-relative-commit" : "HEAD^",
+  "git:arc.feature.start.default" : "origin/master",
+  "arc.feature.start.default" : "master",
+  "history.immutable" : false
+}

.gitignore

@@ -1,3 +1,4 @@
+TARGETS
 make_config.mk
 
 *.a
@@ -24,7 +25,6 @@ make_config.mk
 *.vcxproj.filters
 *.sln
 *.cmake
-.watchmanconfig
 CMakeCache.txt
 CMakeFiles/
 build/
@@ -32,9 +32,6 @@ build/
 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/
@@ -42,16 +39,12 @@ coverage/COVERAGE_REPORT
 .gdbhistory
 .gdb_history
 package/
+.phutil_module_cache
 unity.a
 tags
-etags
 rocksdb_dump
 rocksdb_undump
 db_test2
-trace_analyzer
-trace_analyzer_test
-block_cache_trace_analyzer
-.DS_Store
 
 java/out
 java/target
@@ -67,7 +60,7 @@ rocksdb.h
 unity.cc
 java/crossbuild/.vagrant
 .vagrant/
-java/**/*.asc
+java/**.asc
 java/javadoc
 
 scan_build_report/
@@ -78,5 +71,3 @@ db_logs/
 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
@@ -6,130 +7,54 @@ os:
 compiler:
   - clang
   - gcc
-osx_image: xcode9.4
 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:
+      sources: ['ubuntu-toolchain-r-test', 'llvm-toolchain-precise-3.6']
+      packages: ['clang-3.6' , 'g++-6', 'zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev']
 env:
-  - TEST_GROUP=platform_dependent # 16-18 minutes
-  - TEST_GROUP=1 # 33-35 minutes
-  - TEST_GROUP=2 # 18-20 minutes
-  - TEST_GROUP=3 # 20-22 minutes
-  - TEST_GROUP=4 # 12-14 minutes
+  - TEST_GROUP=platform_dependent1
+  - TEST_GROUP=platform_dependent2
+  - TEST_GROUP=platform_dependent3
+  - TEST_GROUP=1
+  - TEST_GROUP=2
   # Run java tests
-  - JOB_NAME=java_test # 4-11 minutes
+  - JOB_NAME=java_test
   # Build ROCKSDB_LITE
-  - JOB_NAME=lite_build # 3-4 minutes
-  # Build examples
-  - JOB_NAME=examples # 5-7 minutes
-  - JOB_NAME=cmake # 3-5 minutes
-  - JOB_NAME=cmake-gcc8 # 3-5 minutes
-  - JOB_NAME=cmake-mingw # 3 minutes
+  - JOB_NAME=lite_build
 
 matrix:
   exclude:
+  - os: osx
+    compiler: gcc
   - os: osx
     env: TEST_GROUP=1
   - os: osx
     env: TEST_GROUP=2
-  - os: osx
-    env: TEST_GROUP=3
-  - os: osx
-    env: TEST_GROUP=4
-  - os: osx
-    env: JOB_NAME=cmake-gcc8
-  - os : osx
-    env: JOB_NAME=cmake-mingw
-  - os : linux
-    compiler: clang
-  - os : osx
-    compiler: gcc
-
-install:
-  - if [ "${TRAVIS_OS_NAME}" == osx ]; then
-      PATH=$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}";
-    fi
 
 before_script:
-  # Increase the maximum number of open file descriptors, since some tests use
-  # more FDs than the default limit.
-  - ulimit -n 8192
+  - if [[ "${TRAVIS_OS_NAME}" == 'linux' && "${CXX}" == 'clang++' ]]; then CXX=clang++-3.6; fi
+  # test one linux g++ build with g++-6
+  - if [[ "${TRAVIS_OS_NAME}" == 'linux' && "${CXX}" == 'g++' && "${JOB_NAME}" == 'unittests' ]]; then CXX=g++-6; fi
+  # Limit the maximum number of open file descriptors to 8192
+  - ulimit -n 8192 || true
 
 script:
   - ${CXX} --version
-  - if [ `command -v ccache` ]; then ccache -C; fi
-  - 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_dependent1' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=external_sst_file_basic_test make -j4 check_some; fi
+  - if [[ "${TEST_GROUP}" == 'platform_dependent2' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=external_sst_file_basic_test ROCKSDBTESTS_END=checkpoint_test make -j4 check_some; fi
+  - if [[ "${TEST_GROUP}" == 'platform_dependent3' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=checkpoint_test ROCKSDBTESTS_END=db_block_cache_test make -j4 check_some; fi
+  - if [[ "${TEST_GROUP}" == '1' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=comparator_db_test make -j4 check_some; fi
+  - if [[ "${TEST_GROUP}" == '2' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=comparator_db_test make -j4 check_some; fi
+  - if [[ "${JOB_NAME}" == 'java_test' ]]; then OPT=-DTRAVIS V=1 make clean jclean rocksdbjava jtest; fi
+  - if [[ "${JOB_NAME}" == 'lite_build' ]]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib; fi
 notifications:
     email:
       - leveldb@fb.com
+    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
-}

AUTHORS

@@ -9,4 +9,3 @@ Sanjay Ghemawat <sanjay@google.com>
 # Partial list of contributors:
 Kevin Regan <kevin.d.regan@gmail.com>
 Johan Bilien <jobi@litl.com>
-Matthew Von-Maszewski <https://github.com/matthewvon> (Basho Technologies)

CODE_OF_CONDUCT.md

@@ -1,77 +0,0 @@
-# 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
-

CONTRIBUTING.md

@@ -1,8 +1,5 @@
 # Contributing to RocksDB
 
-## Code of Conduct
-The code of conduct is described in [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md)
-
 ## Contributor License Agreement ("CLA")
 
 In order to accept your pull request, we need you to submit a CLA. You

DEFAULT_OPTIONS_HISTORY.md

@@ -1,8 +1,5 @@
 # RocksDB default options change log
 ## Unreleased
-* delayed_write_rate takes the rate given by rate_limiter if not specified.
-
-## 5.2
 * Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files.
 
 ## 5.0 (11/17/2016)

HISTORY.md

@@ -1,619 +1,6 @@
 # Rocksdb Change Log
-## Unreleased
-### Bug Fixes
-* Fix incorrect results while block-based table uses kHashSearch, together with Prev()/SeekForPrev().
-
-## 6.7.0 (01/21/2020)
-### 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 crash caused by concurrent CF iterations and drops(#6147).
-* 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.
-* Fix a bug on fractional cascading index when multiple files at the same level contain the same smallest user key, and those user keys are for merge operands. In this case, Get() the exact key may miss some merge operands.
-* Delcare kHashSearch index type feature-incompatible with index_block_restart_interval larger than 1.
-* Fixed an issue where the thread pools were not resized upon setting `max_background_jobs` dynamically through the `SetDBOptions` interface.
-* Fix a bug that can cause write threads to hang when a slowdown/stall happens and there is a mix of writers with WriteOptions::no_slowdown set/unset.
-* Fixed an issue where an incorrect "number of input records" value was used to compute the "records dropped" statistics for compactions.
-* Fix a regression bug that causes segfault when hash is used, max_open_files != -1 and total order seek is used and switched back.
-
-### 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.
-
-## 6.6.2 (01/13/2020)
-### Bug Fixes
-* Fixed a bug where non-L0 compaction input files were not considered to compute the `creation_time` of new compaction outputs.
-
-## 6.6.1 (01/02/2020)
-### Bug Fixes
-* 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
-* 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.
-* BlobDB no longer updates the SST to blob file mapping upon failed compactions.
-* Fix a bug in which a snapshot read through an iterator could be affected by a DeleteRange after the snapshot (#6062).
-* 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.
-* Delete superversions in BackgroundCallPurge.
-* Fix use-after-free and double-deleting files in BackgroundCallPurge().
-
-## 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
-* RocksDBOptionsParser::Parse()'s `ignore_unknown_options` argument will only be effective if the option file shows it is generated using a higher version of RocksDB than the current version.
-* Remove CompactionEventListener.
-
-### New Features
-* SstFileManager now can cancel compactions if they will result in max space errors. SstFileManager users can also use SetCompactionBufferSize to specify how much space must be leftover during a compaction for auxiliary file functions such as logging and flushing.
-* Avoid unnecessarily flushing in `CompactRange()` when the range specified by the user does not overlap unflushed memtables.
-* If `ColumnFamilyOptions::max_subcompactions` is set greater than one, we now parallelize large manual level-based compactions.
-* Add "rocksdb.live-sst-files-size" DB property to return total bytes of all SST files belong to the latest LSM tree.
-* NewSstFileManager to add an argument bytes_max_delete_chunk with default 64MB. With this argument, a file larger than 64MB will be ftruncated multiple times based on this size.
-
-### Bug Fixes
-* Fix a leak in prepared_section_completed_ where the zeroed entries would not removed from the map.
-* Fix WAL corruption caused by race condition between user write thread and backup/checkpoint thread.
-
-## 5.12.0 (2/14/2018)
-### Public API Change
-* Iterator::SeekForPrev is now a pure virtual method. This is to prevent user who implement the Iterator interface fail to implement SeekForPrev by mistake.
-* Add `include_end` option to make the range end exclusive when `include_end == false` in `DeleteFilesInRange()`.
-* Add `CompactRangeOptions::allow_write_stall`, which makes `CompactRange` start working immediately, even if it causes user writes to stall. The default value is false, meaning we add delay to `CompactRange` calls until stalling can be avoided when possible. Note this delay is not present in previous RocksDB versions.
-* Creating checkpoint with empty directory now returns `Status::InvalidArgument`; previously, it returned `Status::IOError`.
-* Adds a BlockBasedTableOption to turn off index block compression.
-* Close() method now returns a status when closing a db.
-
-### New Features
-* Improve the performance of iterators doing long range scans by using readahead.
-* Add new function `DeleteFilesInRanges()` to delete files in multiple ranges at once for better performance.
-* FreeBSD build support for RocksDB and RocksJava.
-* Improved performance of long range scans with readahead.
-* Updated to and now continuously tested in Visual Studio 2017.
-
-### Bug Fixes
-* Fix `DisableFileDeletions()` followed by `GetSortedWalFiles()` to not return obsolete WAL files that `PurgeObsoleteFiles()` is going to delete.
-* Fix Handle error return from WriteBuffer() during WAL file close and DB close.
-* Fix advance reservation of arena block addresses.
-* Fix handling of empty string as checkpoint directory.
-
-## 5.11.0 (01/08/2018)
-### Public API Change
-* Add `autoTune` and `getBytesPerSecond()` to RocksJava RateLimiter
-
-### New Features
-* Add a new histogram stat called rocksdb.db.flush.micros for memtable flush.
-* Add "--use_txn" option to use transactional API in db_stress.
-* Disable onboard cache for compaction output in Windows platform.
-* Improve the performance of iterators doing long range scans by using readahead.
-
-### Bug Fixes
-* Fix a stack-use-after-scope bug in ForwardIterator.
-* Fix builds on platforms including Linux, Windows, and PowerPC.
-* Fix buffer overrun in backup engine for DBs with huge number of files.
-* Fix a mislabel bug for bottom-pri compaction threads.
-* Fix DB::Flush() keep waiting after flush finish under certain condition.
-
-## 5.10.0 (12/11/2017)
-### Public API Change
-* When running `make` with environment variable `USE_SSE` set and `PORTABLE` unset, will use all machine features available locally. Previously this combination only compiled SSE-related features.
-
-### New Features
-* Provide lifetime hints when writing files on Linux. This reduces hardware write-amp on storage devices supporting multiple streams.
-* Add a DB stat, `NUMBER_ITER_SKIP`, which returns how many internal keys were skipped during iterations (e.g., due to being tombstones or duplicate versions of a key).
-* Add PerfContext counters, `key_lock_wait_count` and `key_lock_wait_time`, which measure the number of times transactions wait on key locks and total amount of time waiting.
-
-### Bug Fixes
-* Fix IOError on WAL write doesn't propagate to write group follower
-* Make iterator invalid on merge error.
-* Fix performance issue in `IngestExternalFile()` affecting databases with large number of SST files.
-* Fix possible corruption to LSM structure when `DeleteFilesInRange()` deletes a subset of files spanned by a `DeleteRange()` marker.
-
-## 5.9.0 (11/1/2017)
-### Public API Change
-* `BackupableDBOptions::max_valid_backups_to_open == 0` now means no backups will be opened during BackupEngine initialization. Previously this condition disabled limiting backups opened.
-* `DBOptions::preserve_deletes` is a new option that allows one to specify that DB should not drop tombstones for regular deletes if they have sequence number larger than what was set by the new API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)`. Disabled by default.
-* API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)` was added, users who wish to preserve deletes are expected to periodically call this function to advance the cutoff seqnum (all deletes made before this seqnum can be dropped by DB). It's user responsibility to figure out how to advance the seqnum in the way so the tombstones are kept for the desired period of time, yet are eventually processed in time and don't eat up too much space.
-* `ReadOptions::iter_start_seqnum` was added;
-if set to something > 0 user will see 2 changes in iterators behavior 1) only keys written with sequence larger than this parameter would be returned and 2) the `Slice` returned by iter->key() now points to the memory that keep User-oriented representation of the internal key, rather than user key. New struct `FullKey` was added to represent internal keys, along with a new helper function `ParseFullKey(const Slice& internal_key, FullKey* result);`.
-* Deprecate trash_dir param in NewSstFileManager, right now we will rename deleted files to <name>.trash instead of moving them to trash directory
-* Allow setting a custom trash/DB size ratio limit in the SstFileManager, after which files that are to be scheduled for deletion are deleted immediately, regardless of any delete ratelimit.
-* Return an error on write if write_options.sync = true and write_options.disableWAL = true to warn user of inconsistent options. Previously we will not write to WAL and not respecting the sync options in this case.
-
-### New Features
-* CRC32C is now using the 3-way pipelined SSE algorithm `crc32c_3way` on supported platforms to improve performance. The system will choose to use this algorithm on supported platforms automatically whenever possible. If PCLMULQDQ is not supported it will fall back to the old Fast_CRC32 algorithm.
-* `DBOptions::writable_file_max_buffer_size` can now be changed dynamically.
-* `DBOptions::bytes_per_sync`, `DBOptions::compaction_readahead_size`, and `DBOptions::wal_bytes_per_sync` can now be changed dynamically, `DBOptions::wal_bytes_per_sync` will flush all memtables and switch to a new WAL file.
-* Support dynamic adjustment of rate limit according to demand for background I/O. It can be enabled by passing `true` to the `auto_tuned` parameter in `NewGenericRateLimiter()`. The value passed as `rate_bytes_per_sec` will still be respected as an upper-bound.
-* Support dynamically changing `ColumnFamilyOptions::compaction_options_fifo`.
-* Introduce `EventListener::OnStallConditionsChanged()` callback. Users can implement it to be notified when user writes are stalled, stopped, or resumed.
-* Add a new db property "rocksdb.estimate-oldest-key-time" to return oldest data timestamp. The property is available only for FIFO compaction with compaction_options_fifo.allow_compaction = false.
-* Upon snapshot release, recompact bottommost files containing deleted/overwritten keys that previously could not be dropped due to the snapshot. This alleviates space-amp caused by long-held snapshots.
-* Support lower bound on iterators specified via `ReadOptions::iterate_lower_bound`.
-* Support for differential snapshots (via iterator emitting the sequence of key-values representing the difference between DB state at two different sequence numbers). Supports preserving and emitting puts and regular deletes, doesn't support SingleDeletes, MergeOperator, Blobs and Range Deletes.
-
-### Bug Fixes
-* Fix a potential data inconsistency issue during point-in-time recovery. `DB:Open()` will abort if column family inconsistency is found during PIT recovery.
-* Fix possible metadata corruption in databases using `DeleteRange()`.
-
-## 5.8.0 (08/30/2017)
-### Public API Change
-* Users of `Statistics::getHistogramString()` will see fewer histogram buckets and different bucket endpoints.
-* `Slice::compare` and BytewiseComparator `Compare` no longer accept `Slice`s containing nullptr.
-* `Transaction::Get` and `Transaction::GetForUpdate` variants with `PinnableSlice` added.
-
-### New Features
-* Add Iterator::Refresh(), which allows users to update the iterator state so that they can avoid some initialization costs of recreating iterators.
-* Replace dynamic_cast<> (except unit test) so people can choose to build with RTTI off. With make, release mode is by default built with -fno-rtti and debug mode is built without it. Users can override it by setting USE_RTTI=0 or 1.
-* Universal compactions including the bottom level can be executed in a dedicated thread pool. This alleviates head-of-line blocking in the compaction queue, which cause write stalling, particularly in multi-instance use cases. Users can enable this feature via `Env::SetBackgroundThreads(N, Env::Priority::BOTTOM)`, where `N > 0`.
-* Allow merge operator to be called even with a single merge operand during compactions, by appropriately overriding `MergeOperator::AllowSingleOperand`.
-* Add `DB::VerifyChecksum()`, which verifies the checksums in all SST files in a running DB.
-* Block-based table support for disabling checksums by setting `BlockBasedTableOptions::checksum = kNoChecksum`.
-
-### Bug Fixes
-* Fix wrong latencies in `rocksdb.db.get.micros`, `rocksdb.db.write.micros`, and `rocksdb.sst.read.micros`.
-* Fix incorrect dropping of deletions during intra-L0 compaction.
-* Fix transient reappearance of keys covered by range deletions when memtable prefix bloom filter is enabled.
-* Fix potentially wrong file smallest key when range deletions separated by snapshot are written together.
-
-## 5.7.0 (07/13/2017)
-### Public API Change
-* DB property "rocksdb.sstables" now prints keys in hex form.
-
-### New Features
-* Measure estimated number of reads per file. The information can be accessed through DB::GetColumnFamilyMetaData or "rocksdb.sstables" DB property.
-* RateLimiter support for throttling background reads, or throttling the sum of background reads and writes. This can give more predictable I/O usage when compaction reads more data than it writes, e.g., due to lots of deletions.
-* [Experimental] FIFO compaction with TTL support. It can be enabled by setting CompactionOptionsFIFO.ttl > 0.
-* Introduce `EventListener::OnBackgroundError()` callback. Users can implement it to be notified of errors causing the DB to enter read-only mode, and optionally override them.
-* Partitioned Index/Filters exiting the experimental mode. To enable partitioned indexes set index_type to kTwoLevelIndexSearch and to further enable partitioned filters set partition_filters to true. To configure the partition size set metadata_block_size.
-
-
-### Bug Fixes
-* Fix discarding empty compaction output files when `DeleteRange()` is used together with subcompactions.
-
-## 5.6.0 (06/06/2017)
-### Public API Change
-* Scheduling flushes and compactions in the same thread pool is no longer supported by setting `max_background_flushes=0`. Instead, users can achieve this by configuring their high-pri thread pool to have zero threads.
-* Replace `Options::max_background_flushes`, `Options::max_background_compactions`, and `Options::base_background_compactions` all with `Options::max_background_jobs`, which automatically decides how many threads to allocate towards flush/compaction.
-* options.delayed_write_rate by default take the value of options.rate_limiter rate.
-* Replace global variable `IOStatsContext iostats_context` with `IOStatsContext* get_iostats_context()`; replace global variable `PerfContext perf_context` with `PerfContext* get_perf_context()`.
-
-### New Features
-* Change ticker/histogram statistics implementations to use core-local storage. This improves aggregation speed compared to our previous thread-local approach, particularly for applications with many threads.
-* Users can pass a cache object to write buffer manager, so that they can cap memory usage for memtable and block cache using one single limit.
-* Flush will be triggered when 7/8 of the limit introduced by write_buffer_manager or db_write_buffer_size is triggered, so that the hard threshold is hard to hit.
-* Introduce WriteOptions.low_pri. If it is true, low priority writes will be throttled if the compaction is behind.
-* `DB::IngestExternalFile()` now supports ingesting files into a database containing range deletions.
-
-### Bug Fixes
-* Shouldn't ignore return value of fsync() in flush.
-
-## 5.5.0 (05/17/2017)
-### New Features
-* FIFO compaction to support Intra L0 compaction too with CompactionOptionsFIFO.allow_compaction=true.
-* DB::ResetStats() to reset internal stats.
-* Statistics::Reset() to reset user stats.
-* ldb add option --try_load_options, which will open DB with its own option file.
-* Introduce WriteBatch::PopSavePoint to pop the most recent save point explicitly.
-* Support dynamically change `max_open_files` option via SetDBOptions()
-* Added DB::CreateColumnFamilie() and DB::DropColumnFamilies() to bulk create/drop column families.
-* Add debugging function `GetAllKeyVersions` to see internal versions of a range of keys.
-* Support file ingestion with universal compaction style
-* Support file ingestion behind with option `allow_ingest_behind`
-* New option enable_pipelined_write which may improve write throughput in case writing from multiple threads and WAL enabled.
-
-### Bug Fixes
-* Fix the bug that Direct I/O uses direct reads for non-SST file
-
-## 5.4.0 (04/11/2017)
-### Public API Change
-* random_access_max_buffer_size no longer has any effect
-* Removed Env::EnableReadAhead(), Env::ShouldForwardRawRequest()
-* Support dynamically change `stats_dump_period_sec` option via SetDBOptions().
-* Added ReadOptions::max_skippable_internal_keys to set a threshold to fail a request as incomplete when too many keys are being skipped when using iterators.
-* DB::Get in place of std::string accepts PinnableSlice, which avoids the extra memcpy of value to std::string in most of cases.
-    * PinnableSlice releases the pinned resources that contain the value when it is destructed or when ::Reset() is called on it.
-    * The old API that accepts std::string, although discouraged, is still supported.
-* Replace Options::use_direct_writes with Options::use_direct_io_for_flush_and_compaction. Read Direct IO wiki for details.
-* Added CompactionEventListener and EventListener::OnFlushBegin interfaces.
-
-### New Features
-* Memtable flush can be avoided during checkpoint creation if total log file size is smaller than a threshold specified by the user.
-* Introduce level-based L0->L0 compactions to reduce file count, so write delays are incurred less often.
-* (Experimental) Partitioning filters which creates an index on the partitions. The feature can be enabled by setting partition_filters when using kFullFilter. Currently the feature also requires two-level indexing to be enabled. Number of partitions is the same as the number of partitions for indexes, which is controlled by metadata_block_size.
+## 5.3.7
+* Change license to Apache + GPLv2
 
 ## 5.3.0 (03/08/2017)
 ### Public API Change
@@ -622,12 +9,15 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 * Remove option min_partial_merge_operands. Partial merge operands will always be merged in flush or compaction if there are more than one.
 * Remove option verify_checksums_in_compaction. Compaction will always verify checksum.
 
+### New Features
+* Memtable flush can be avoided during checkpoint creation if total log file size is smaller than a threshold specified by the user.
+
 ### Bug Fixes
 * Fix the bug that iterator may skip keys
 
 ## 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.
@@ -698,7 +88,7 @@ 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
@@ -840,7 +230,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 * Added a new way to report QPS from db_bench (check out --report_file and --report_interval_seconds)
 * Added a cache for individual rows. See DBOptions::row_cache for more info.
 * Several new features on EventListener (see include/rocksdb/listener.h):
- - OnCompationCompleted() now returns per-compaction job statistics, defined in include/rocksdb/compaction_job_stats.h.
+ - OnCompationCompleted() now returns per-compaciton job statistics, defined in include/rocksdb/compaction_job_stats.h.
  - Added OnTableFileCreated() and OnTableFileDeleted().
 * Add compaction_options_universal.enable_trivial_move to true, to allow trivial move while performing universal compaction. Trivial move will happen only when all the input files are non overlapping.
 

INSTALL.md

@@ -1,6 +1,6 @@
 ## Compilation
 
-**Important**: If you plan to run RocksDB in production, don't compile using default
+**Important**: If you plan to run RocksDB in production, don't compile using default 
 `make` or `make all`. That will compile RocksDB in debug mode, which is much slower
 than release mode.
 
@@ -21,18 +21,14 @@ depend on gflags. You will need to have gflags installed to run `make all`. This
 use binaries compiled by `make all` in production.
 
 * By default the binary we produce is optimized for the platform you're compiling on
-(`-march=native` or the equivalent). SSE4.2 will thus be enabled automatically if your
-CPU supports it. To print a warning if your CPU does not support SSE4.2, build with
-`USE_SSE=1 make static_lib` or, if using CMake, `cmake -DFORCE_SSE42=ON`. If you want
-to build a portable binary, add `PORTABLE=1` before your make commands, like this:
-`PORTABLE=1 make static_lib`.
+(-march=native or the equivalent). If you want to build a portable binary, add 'PORTABLE=1' before
+your make commands, like this: `PORTABLE=1 make static_lib`
 
 ## Dependencies
 
 * You can link RocksDB with following compression libraries:
   - [zlib](http://www.zlib.net/) - a library for data compression.
   - [bzip2](http://www.bzip.org/) - a library for data compression.
-  - [lz4](https://github.com/lz4/lz4) - a library for extremely fast data compression.
   - [snappy](http://google.github.io/snappy/) - a library for fast
       data compression.
   - [zstandard](http://www.zstd.net) - Fast real-time compression
@@ -43,8 +39,6 @@ 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**
@@ -56,7 +50,6 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
       `sudo apt-get install libsnappy-dev`.
     * Install zlib. Try: `sudo apt-get install zlib1g-dev`.
     * Install bzip2: `sudo apt-get install libbz2-dev`.
-    * Install lz4: `sudo apt-get install liblz4-dev`.
     * Install zstandard: `sudo apt-get install libzstd-dev`.
 
 * **Linux - CentOS / RHEL**
@@ -65,38 +58,31 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
     * Install gflags:
 
               git clone https://github.com/gflags/gflags.git
-              cd gflags
               git checkout v2.0
+              cd gflags
               ./configure && make && sudo make install
 
-      **Notice**: Once installed, please add the include path for gflags to your `CPATH` environment variable and the
-      lib path to `LIBRARY_PATH`. If installed with default settings, the include path will be `/usr/local/include`
-      and the lib path will be `/usr/local/lib`.
-
     * Install snappy:
 
-              sudo yum install snappy snappy-devel
+              wget https://github.com/google/snappy/releases/download/1.1.4/snappy-1.1.4.tar.gz
+              tar -xzvf snappy-1.1.4.tar.gz
+              cd snappy-1.1.4
+              ./configure && make && sudo make install
 
     * Install zlib:
 
-              sudo yum install zlib zlib-devel
+              sudo yum install zlib
+              sudo yum install zlib-devel
 
     * Install bzip2:
 
-              sudo yum install bzip2 bzip2-devel
-
-    * Install lz4:
-
-              sudo yum install lz4-devel
-
-    * Install ASAN (optional for debugging):
-
-              sudo yum install libasan
+              sudo yum install bzip2
+              sudo yum install bzip2-devel
 
     * Install zstandard:
 
              wget https://github.com/facebook/zstd/archive/v1.1.3.tar.gz
-             mv v1.1.3.tar.gz zstd-1.1.3.tar.gz
+             mv v1.1.3.tar.gz zstandard-1.1.3.tar.gz
              tar zxvf zstd-1.1.3.tar.gz
              cd zstd-1.1.3
              make && sudo make install
@@ -109,94 +95,9 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
             * run `brew tap homebrew/versions; brew install gcc48 --use-llvm` to install gcc 4.8 (or higher).
     * run `brew install rocksdb`
 
-* **FreeBSD** (11.01):
-
-    * You can either install RocksDB from the Ports system using `cd /usr/ports/databases/rocksdb && make install`, or you can follow the details below to install dependencies and compile from source code:
-
-    * Install the dependencies for RocksDB:
-
-        export BATCH=YES
-        cd /usr/ports/devel/gmake && make install
-        cd /usr/ports/devel/gflags && make install
-
-        cd /usr/ports/archivers/snappy && make install
-        cd /usr/ports/archivers/bzip2 && make install
-        cd /usr/ports/archivers/liblz4 && make install
-        cd /usr/ports/archivesrs/zstd && make install
-
-        cd /usr/ports/devel/git && make install
-
-
-    * Install the dependencies for RocksJava (optional):
-
-        export BATCH=yes
-        cd /usr/ports/java/openjdk7 && make install
-
-    * Build RocksDB from source:
-        cd ~
-        git clone https://github.com/facebook/rocksdb.git
-        cd rocksdb
-        gmake static_lib
-
-    * Build RocksJava from source (optional):
-        cd rocksdb
-        export JAVA_HOME=/usr/local/openjdk7
-        gmake rocksdbjava
-
-* **OpenBSD** (6.3/-current):
-
-    * As RocksDB is not available in the ports yet you have to build it on your own:
-
-    * Install the dependencies for RocksDB:
-
-        pkg_add gmake gflags snappy bzip2 lz4 zstd git jdk bash findutils gnuwatch 
-
-    * Build RocksDB from source:
-
-        cd ~
-        git clone https://github.com/facebook/rocksdb.git
-        cd rocksdb
-        gmake static_lib
-
-    * Build RocksJava from source (optional):
-
-        cd rocksdb
-        export JAVA_HOME=/usr/local/jdk-1.8.0
-        export PATH=$PATH:/usr/local/jdk-1.8.0/bin
-        gmake rocksdbjava
-
 * **iOS**:
   * Run: `TARGET_OS=IOS make static_lib`. When building the project which uses rocksdb iOS library, make sure to define two important pre-processing macros: `ROCKSDB_LITE` and `IOS_CROSS_COMPILE`.
 
 * **Windows**:
   * For building with MS Visual Studio 13 you will need Update 4 installed.
   * Read and follow the instructions at CMakeLists.txt
-  * Or install via [vcpkg](https://github.com/microsoft/vcpkg) 
-       * run `vcpkg install rocksdb:x64-windows`
-
-* **AIX 6.1**
-    * Install AIX Toolbox rpms with gcc
-    * Use these environment variables:
-  
-             export PORTABLE=1
-             export CC=gcc
-             export AR="ar -X64"
-             export EXTRA_ARFLAGS=-X64
-             export EXTRA_CFLAGS=-maix64
-             export EXTRA_CXXFLAGS=-maix64
-             export PLATFORM_LDFLAGS="-static-libstdc++ -static-libgcc"
-             export LIBPATH=/opt/freeware/lib
-             export JAVA_HOME=/usr/java8_64
-             export PATH=/opt/freeware/bin:$PATH
-  
-* **Solaris Sparc**
-    * Install GCC 4.8.2 and higher.
-    * Use these environment variables:
-
-             export CC=gcc
-             export EXTRA_CFLAGS=-m64
-             export EXTRA_CXXFLAGS=-m64
-             export EXTRA_LDFLAGS=-m64
-             export PORTABLE=1
-             export PLATFORM_LDFLAGS="-static-libstdc++ -static-libgcc"
-

LANGUAGE-BINDINGS.md

@@ -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
@@ -11,12 +9,5 @@ This is the list of all known third-party language bindings for RocksDB. If some
 * Haskell - https://hackage.haskell.org/package/rocksdb-haskell
 * PHP - https://github.com/Photonios/rocksdb-php
 * C# - https://github.com/warrenfalk/rocksdb-sharp
-* Rust
-    * https://github.com/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
+* Rust - https://github.com/spacejam/rust-rocksdb
 * D programming language - https://github.com/b1naryth1ef/rocksdb
-* Erlang - https://gitlab.com/barrel-db/erlang-rocksdb
-* Elixir - https://github.com/urbint/rox
-* Nim - https://github.com/status-im/nim-rocksdb
-* Swift and Objective-C (iOS/OSX) - https://github.com/iabudiab/ObjectiveRocks 

README.md

@@ -1,19 +1,19 @@
 ## RocksDB: A Persistent Key-Value Store for Flash and RAM Storage
 
-[![Linux/Mac Build Status](https://travis-ci.org/facebook/rocksdb.svg?branch=master)](https://travis-ci.org/facebook/rocksdb)
-[![Windows Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
-[![PPC64le Build Status](http://140.211.168.68:8080/buildStatus/icon?job=Rocksdb)](http://140.211.168.68:8080/job/Rocksdb)
+[![Build Status](https://travis-ci.org/facebook/rocksdb.svg?branch=master)](https://travis-ci.org/facebook/rocksdb)
+[![Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
+
 
 RocksDB is developed and maintained by Facebook Database Engineering Team.
-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
@@ -25,7 +25,3 @@ rely on the details of any other header files in this package.  Those
 internal APIs may be changed without warning.
 
 Design discussions are conducted in https://www.facebook.com/groups/rocksdb.dev/
-
-## License
-
-RocksDB is dual-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).  You may select, at your option, one of the above-listed licenses.

ROCKSDB_LITE.md

@@ -5,7 +5,7 @@ RocksDBLite is a project focused on mobile use cases, which don't need a lot of
 Some examples of the features disabled by ROCKSDB_LITE:
 * compiled-in support for LDB tool
 * No backupable DB
-* No support for replication (which we provide in form of TransactionalIterator)
+* No support for replication (which we provide in form of TrasactionalIterator)
 * No advanced monitoring tools
 * No special-purpose memtables that are highly optimized for specific use cases
 * No Transactions

USERS.md

@@ -5,15 +5,12 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
 
 1. MyRocks -- https://github.com/MySQLOnRocksDB/mysql-5.6
 2. MongoRocks -- https://github.com/mongodb-partners/mongo-rocks
-3. ZippyDB --  Facebook's distributed key-value store with Paxos-style replication, built on top of RocksDB.[1] https://www.youtube.com/watch?v=DfiN7pG0D0khtt
-4. Laser -- Laser is a high query throughput, low (millisecond) latency, key-value storage service built on top of RocksDB.[1]
+3. ZippyDB --  Facebook's distributed key-value store with Paxos-style replication, built on top of RocksDB.[*] https://www.youtube.com/watch?v=DfiN7pG0D0khtt
+4. Laser -- Laser is a high query throughput, low (millisecond) latency, key-value storage service built on top of RocksDB.[*]
 4. Dragon -- a distributed graph query engine. https://code.facebook.com/posts/1737605303120405/dragon-a-distributed-graph-query-engine/
-5. Stylus -- a low-level stream processing framework writtenin C++.[1]
-6. LogDevice -- a distributed data store for logs [2]
+5. Stylus -- a low-level stream processing framework writtenin C++.[*]
 
-[1] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
-
-[2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/
+[*] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
 
 ## LinkedIn
 Two different use cases at Linkedin are using RocksDB as a storage engine:
@@ -27,7 +24,7 @@ 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 +47,6 @@ 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
 
@@ -83,26 +76,7 @@ quasardb uses a heavily tuned RocksDB as its persistence layer.
 [Dgraph](https://github.com/dgraph-io/dgraph) is an open-source, scalable, distributed, low latency, high throughput Graph database .They use RocksDB to store state locally on a machine.
 
 ## Uber
-[Uber](http://eng.uber.com/cherami/) uses RocksDB as a durable and scalable task queue.
+[Uber](http://eng.uber.com/cherami/) uses RocksDB as a durable and and scalable task queue.
 
 ## 360 Pika
 [360](http://www.360.cn/) [Pika](https://github.com/Qihoo360/pika) is a nosql compatible with redis. With the huge amount of data stored, redis may suffer for a capacity bottleneck, and pika was born for solving it. It has widely been widely used in many company
-
-## LzLabs
-LzLabs is using RocksDB as a storage engine in their multi-database distributed framework to store application configuration and user data.
-
-## ProfaneDB
-[ProfaneDB](https://profanedb.gitlab.io/) is a database for Protocol Buffers, and uses RocksDB for storage. It is accessible via gRPC, and the schema is defined using directly `.proto` files.
-
-## 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.
-
-## Nebula Graph
-
-[Nebula Graph](https://github.com/vesoft-inc/nebula) is a distributed, scalable, lightning-fast, open source graph database capable of hosting super large scale graphs with dozens of billions of vertices (nodes) and trillions of edges, with milliseconds of latency.

Vagrantfile

@@ -14,11 +14,6 @@ Vagrant.configure("2") do |config|
     box.vm.box = "chef/centos-6.5"
   end
 
-  config.vm.define "centos7" do |box|
-    box.vm.box = "centos/7"
-    box.vm.provision "shell", path: "build_tools/setup_centos7.sh"
-  end
-
   config.vm.define "FreeBSD10" do |box|
     box.vm.guest = :freebsd
     box.vm.box = "robin/freebsd-10"

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 +1,18 @@
 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
-
+image: Visual Studio 2015
 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 14 2015 Win64" -DOPTDBG=1 -DXPRESS=1 ..
+- cd ..
 build:
   project: build\rocksdb.sln
   parallel: true
-  verbosity: normal
-
+  verbosity: minimal
 test:
-
 test_script:
-  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test,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 -Run db_basic_test -Concurrency 8
+- ps: build_tools\run_ci_db_test.ps1 -Run db_test2 -Concurrency 8
+- ps: build_tools\run_ci_db_test.ps1 -Run db_test -Concurrency 8
+- ps: build_tools\run_ci_db_test.ps1 -Run env_test,env_basic_test -Concurrency 2
 

buckifier/buckify_rocksdb.py

@@ -1,236 +0,0 @@
-# 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
-import os
-import fnmatch
-import sys
-
-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.)
-
-# tests to export as libraries for inclusion in other projects
-_EXPORTED_TEST_LIBS = ["env_basic_test"]
-
-# Parse src.mk files as a Dictionary of
-# VAR_NAME => list of files
-def parse_src_mk(repo_path):
-    src_mk = repo_path + "/src.mk"
-    src_files = {}
-    for line in open(src_mk):
-        line = line.strip()
-        if len(line) == 0 or line[0] == '#':
-            continue
-        if '=' in line:
-            current_src = line.split('=')[0].strip()
-            src_files[current_src] = []
-        elif '.cc' in line:
-            src_path = line.split('.cc')[0].strip() + '.cc'
-            src_files[current_src].append(src_path)
-    return src_files
-
-
-# get all .cc / .c files
-def get_cc_files(repo_path):
-    cc_files = []
-    for root, dirnames, filenames in os.walk(repo_path):  # noqa: B007 T25377293 Grandfathered in
-        root = root[(len(repo_path) + 1):]
-        if "java" in root:
-            # Skip java
-            continue
-        for filename in fnmatch.filter(filenames, '*.cc'):
-            cc_files.append(os.path.join(root, filename))
-        for filename in fnmatch.filter(filenames, '*.c'):
-            cc_files.append(os.path.join(root, filename))
-    return cc_files
-
-
-# Get tests from Makefile
-def get_tests(repo_path):
-    Makefile = repo_path + "/Makefile"
-
-    # Dictionary TEST_NAME => IS_PARALLEL
-    tests = {}
-
-    found_tests = False
-    for line in open(Makefile):
-        line = line.strip()
-        if line.startswith("TESTS ="):
-            found_tests = True
-        elif found_tests:
-            if line.endswith("\\"):
-                # remove the trailing \
-                line = line[:-1]
-                line = line.strip()
-                tests[line] = False
-            else:
-                # we consumed all the tests
-                break
-
-    found_parallel_tests = False
-    for line in open(Makefile):
-        line = line.strip()
-        if line.startswith("PARALLEL_TEST ="):
-            found_parallel_tests = True
-        elif found_parallel_tests:
-            if line.endswith("\\"):
-                # remove the trailing \
-                line = line[:-1]
-                line = line.strip()
-                tests[line] = True
-            else:
-                # we consumed all the parallel tests
-                break
-
-    return tests
-
-
-# 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):
-    print(ColorString.info("Generating TARGETS"))
-    # parsed src.mk file
-    src_mk = parse_src_mk(repo_path)
-    # get all .cc files
-    cc_files = get_cc_files(repo_path)
-    # get tests from Makefile
-    tests = get_tests(repo_path)
-
-    if src_mk is None or cc_files is None or tests is None:
-        return False
-
-    TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path)
-    # rocksdb_lib
-    TARGETS.add_library(
-        "rocksdb_lib",
-        src_mk["LIB_SOURCES"] +
-        src_mk["TOOL_LIB_SOURCES"])
-    # rocksdb_test_lib
-    TARGETS.add_library(
-        "rocksdb_test_lib",
-        src_mk.get("MOCK_LIB_SOURCES", []) +
-        src_mk.get("TEST_LIB_SOURCES", []) +
-        src_mk.get("EXP_LIB_SOURCES", []) +
-        src_mk.get("ANALYZER_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"],
-        [":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
-
-            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'])
-
-            if test in _EXPORTED_TEST_LIBS:
-                test_library = "%s_lib" % test_target_name
-                TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
-    TARGETS.flush_tests()
-
-    print(ColorString.info("Generated TARGETS Summary:"))
-    print(ColorString.info("- %d libs" % TARGETS.total_lib))
-    print(ColorString.info("- %d binarys" % TARGETS.total_bin))
-    print(ColorString.info("- %d tests" % TARGETS.total_test))
-    return True
-
-
-def get_rocksdb_path():
-    # rocksdb = {script_dir}/..
-    script_dir = os.path.dirname(sys.argv[0])
-    script_dir = os.path.abspath(script_dir)
-    rocksdb_path = os.path.abspath(
-        os.path.join(script_dir, "../"))
-
-    return rocksdb_path
-
-def exit_with_error(msg):
-    print(ColorString.error(msg))
-    sys.exit(1)
-
-
-def main():
-    deps_map = get_dependencies()
-    # Generate TARGETS file for buck
-    ok = generate_targets(get_rocksdb_path(), deps_map)
-    if not ok:
-        exit_with_error("Failed to generate TARGETS files")
-
-if __name__ == "__main__":
-    main()

buckifier/rocks_test_runner.sh

@@ -1,6 +0,0 @@
-#!/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=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
-# shellcheck disable=SC2068
-TEST_TMPDIR="$TEST_DIR" $@ && rm -rf "$TEST_DIR"

buckifier/targets_builder.py

@@ -1,80 +0,0 @@
-# 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):
-    if lst is None or len(lst) == 0:
-        return ""
-
-    if len(lst) == 1:
-        return "\"%s\"" % lst[0]
-
-    separator = "\",\n%s\"" % (" " * indent)
-    res = separator.join(sorted(lst))
-    res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 4))
-    return res
-
-
-class TARGETSBuilder(object):
-    def __init__(self, path):
-        self.path = path
-        self.targets_file = open(path, 'w')
-        self.targets_file.write(targets_cfg.rocksdb_target_header)
-        self.total_lib = 0
-        self.total_bin = 0
-        self.total_test = 0
-        self.tests_cfg = ""
-
-    def __del__(self):
-        self.targets_file.close()
-
-    def add_library(self, name, srcs, deps=None, headers=None):
-        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.total_lib = self.total_lib + 1
-
-    def add_binary(self, name, srcs, deps=None):
-        self.targets_file.write(targets_cfg.binary_template % (
-            name,
-            pretty_list(srcs),
-            pretty_list(deps)))
-        self.total_bin = self.total_bin + 1
-
-    def register_test(self,
-                      test_name,
-                      src,
-                      is_parallel,
-                      extra_deps,
-                      extra_compiler_flags):
-        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)
-
-        self.total_test = self.total_test + 1
-
-    def flush_tests(self):
-        self.targets_file.write(targets_cfg.unittests_template % self.tests_cfg)
-        self.tests_cfg = ""

buckifier/targets_cfg.py

@@ -1,182 +0,0 @@
-# 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 = """# 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")
-
-REPO_PATH = package_name() + "/"
-
-ROCKSDB_COMPILER_FLAGS = [
-    "-fno-builtin-memcmp",
-    # 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 = [
-    ("bzip2", None, "bz2"),
-    ("snappy", None, "snappy"),
-    ("zlib", None, "z"),
-    ("gflags", None, "gflags"),
-    ("lz4", None, "lz4"),
-    ("zstd", None),
-    ("tbb", None),
-    ("liburing", None, "uring"),
-    ("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",
-
-    # Directories with files for #include
-    "-I" + REPO_PATH + "include/",
-    "-I" + REPO_PATH,
-]
-
-ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
-    "x86_64": [
-        "-DHAVE_PCLMUL",
-    ],
-}
-
-build_mode = read_config("fbcode", "build_mode")
-
-is_opt_mode = build_mode.startswith("opt")
-
-# -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
-# doesn't harm and avoid forgetting to add it.
-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 [])
-"""
-
-
-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,
-)
-"""
-
-binary_template = """
-cpp_binary(
-    name = "%s",
-    srcs = [%s],
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-    deps = [%s],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
-)
-"""
-
-test_cfg_template = """    [
-        "%s",
-        "%s",
-        "%s",
-        %s,
-        %s,
-    ],
-"""
-
-unittests_template = """
-# [test_name, test_src, test_type, extra_deps, extra_compiler_flags]
-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
-]
-"""

buckifier/util.py

@@ -1,119 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-"""
-This module keeps commonly used components.
-"""
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-try:
-    from builtins import object
-except ImportError:
-    from __builtin__ import object
-import subprocess
-import sys
-import os
-import time
-
-class ColorString(object):
-    """ Generate colorful strings on terminal """
-    HEADER = '\033[95m'
-    BLUE = '\033[94m'
-    GREEN = '\033[92m'
-    WARNING = '\033[93m'
-    FAIL = '\033[91m'
-    ENDC = '\033[0m'
-
-    @staticmethod
-    def _make_color_str(text, color):
-        # 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])
-
-    @staticmethod
-    def ok(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.GREEN)
-
-    @staticmethod
-    def info(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.BLUE)
-
-    @staticmethod
-    def header(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.HEADER)
-
-    @staticmethod
-    def error(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.FAIL)
-
-    @staticmethod
-    def warning(text):
-        if ColorString.is_disabled:
-            return text
-        return ColorString._make_color_str(text, ColorString.WARNING)
-
-    is_disabled = False
-
-
-def run_shell_command(shell_cmd, cmd_dir=None):
-    """ Run a single shell command.
-        @returns a tuple of shell command return code, stdout, stderr """
-
-    if cmd_dir is not None and not os.path.exists(cmd_dir):
-        run_shell_command("mkdir -p %s" % cmd_dir)
-
-    start = time.time()
-    print("\t>>> Running: " + shell_cmd)
-    p = subprocess.Popen(shell_cmd,
-                         shell=True,
-                         stdout=subprocess.PIPE,
-                         stderr=subprocess.PIPE,
-                         cwd=cmd_dir)
-    stdout, stderr = p.communicate()
-    end = time.time()
-
-    # Report time if we spent more than 5 minutes executing a command
-    execution_time = end - start
-    if execution_time > (60 * 5):
-        mins = (execution_time / 60)
-        secs = (execution_time % 60)
-        print("\t>time spent: %d minutes %d seconds" % (mins, secs))
-
-
-    return p.returncode, stdout, stderr
-
-
-def run_shell_commands(shell_cmds, cmd_dir=None, verbose=False):
-    """ Execute a sequence of shell commands, which is equivalent to
-        running `cmd1 && cmd2 && cmd3`
-        @returns boolean indication if all commands succeeds.
-    """
-
-    if cmd_dir:
-        print("\t=== Set current working directory => %s" % cmd_dir)
-
-    for shell_cmd in shell_cmds:
-        ret_code, stdout, stderr = run_shell_command(shell_cmd, cmd_dir)
-        if stdout:
-            if verbose or ret_code != 0:
-                print(ColorString.info("stdout: \n"), stdout)
-        if stderr:
-            # contents in stderr is not necessarily to be error messages.
-            if verbose or ret_code != 0:
-                print(ColorString.error("stderr: \n"), stderr)
-        if ret_code != 0:
-            return False
-
-    return True

build_tools/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

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/sh
 #
 # Detects OS we're compiling on and outputs a file specified by the first
 # argument, which in turn gets read while processing Makefile.
@@ -16,8 +16,6 @@
 #   PLATFORM_CXXFLAGS           C++ compiler flags.  Will contain:
 #   PLATFORM_SHARED_VERSIONED   Set to 'true' if platform supports versioned
 #                               shared libraries, empty otherwise.
-#   FIND			Command for the find utility
-#   WATCH			Command for the watch utility
 #
 # The PLATFORM_CCFLAGS and PLATFORM_CXXFLAGS might include the following:
 #
@@ -53,14 +51,7 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
     FBCODE_BUILD="true"
     # If we're compiling with TSAN we need pic build
     PIC_BUILD=$COMPILE_WITH_TSAN
-    if [ -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 "$ROCKSDB_FBCODE_BUILD_WITH_5xx" ]; then
-      source "$PWD/build_tools/fbcode_config.sh"
-    else
-      source "$PWD/build_tools/fbcode_config_platform007.sh"
-    fi
+    source "$PWD/build_tools/fbcode_config.sh"
 fi
 
 # Delete existing output, if it exists
@@ -68,23 +59,11 @@ rm -f "$OUTPUT"
 touch "$OUTPUT"
 
 if test -z "$CC"; then
-    if [ -x "$(command -v cc)" ]; then
-        CC=cc
-    elif [ -x "$(command -v clang)" ]; then
-        CC=clang
-    else
-        CC=cc
-    fi
+   CC=cc
 fi
 
 if test -z "$CXX"; then
-    if [ -x "$(command -v g++)" ]; then
-        CXX=g++
-    elif [ -x "$(command -v clang++)" ]; then
-        CXX=clang++
-    else
-        CXX=g++
-    fi
+    CXX=g++
 fi
 
 # Detect OS
@@ -101,15 +80,7 @@ if test -z "$CLANG_SCAN_BUILD"; then
 fi
 
 if test -z "$CLANG_ANALYZER"; then
-    CLANG_ANALYZER=$(command -v clang++ 2> /dev/null)
-fi
-
-if test -z "$FIND"; then
-    FIND=find
-fi
-
-if test -z "$WATCH"; then
-    WATCH=watch
+    CLANG_ANALYZER=$(which clang++ 2> /dev/null)
 fi
 
 COMMON_FLAGS="$COMMON_FLAGS ${CFLAGS}"
@@ -146,44 +117,18 @@ case "$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 "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-          USE_FOLLY_DISTRIBUTED_MUTEX=1
-        fi
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
         PLATFORM=OS_SOLARIS
-        COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_SOLARIS -m64"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt -static-libstdc++ -static-libgcc -m64"
+        COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_SOLARIS"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
         # PORT_FILES=port/sunos/sunos_specific.cc
         ;;
-    AIX)
-        PLATFORM=OS_AIX
-        CC=gcc
-        COMMON_FLAGS="$COMMON_FLAGS -maix64 -pthread -fno-builtin-memcmp -D_REENTRANT -DOS_AIX -D__STDC_FORMAT_MACROS"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -pthread -lpthread -lrt -maix64 -static-libstdc++ -static-libgcc"
-        # PORT_FILES=port/aix/aix_specific.cc
-        ;;
     FreeBSD)
         PLATFORM=OS_FREEBSD
-        CXX=clang++
         COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_FREEBSD"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread"
         # PORT_FILES=port/freebsd/freebsd_specific.cc
@@ -196,12 +141,9 @@ EOF
         ;;
     OpenBSD)
         PLATFORM=OS_OPENBSD
-	CXX=clang++
         COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_OPENBSD"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -pthread"
         # PORT_FILES=port/openbsd/openbsd_specific.cc
-	FIND=gfind
-	WATCH=gnuwatch
         ;;
     DragonFly)
         PLATFORM=OS_DRAGONFLYBSD
@@ -216,8 +158,6 @@ EOF
         COMMON_FLAGS="$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 +190,7 @@ 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
@@ -258,147 +198,117 @@ EOF
         fi
     fi
 
-    if ! test $ROCKSDB_DISABLE_SNAPPY; then
-        # Test whether Snappy library is installed
-        # http://code.google.com/p/snappy/
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <snappy.h>
-          int main() {}
+    # Test whether Snappy library is installed
+    # http://code.google.com/p/snappy/
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <snappy.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DSNAPPY"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lsnappy"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lsnappy"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DSNAPPY"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lsnappy"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lsnappy"
     fi
 
-    if ! test $ROCKSDB_DISABLE_GFLAGS; then
-        # Test whether gflags library is installed
-        # http://gflags.github.io/gflags/
-        # check if the namespace is gflags
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
-          #include <gflags/gflags.h>
-          int main() {}
+    # Test whether gflags library is installed
+    # http://gflags.github.io/gflags/
+    # check if the namespace is gflags
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+      #include <gflags/gflags.h>
+      using namespace gflags;
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
-        else
-          # check if namespace is google
-          $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
-            #include <gflags/gflags.h>
-            using namespace google;
-            int main() {}
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=gflags"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
+    else
+      # check if namespace is google
+      $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+        #include <gflags/gflags.h>
+        using namespace google;
+        int main() {}
 EOF
-          if [ "$?" = 0 ]; then
-              COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
-              PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
-          fi
-        fi
+      if [ "$?" = 0 ]; then
+          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
+          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
+      fi
     fi
 
-    if ! test $ROCKSDB_DISABLE_ZLIB; then
-        # Test whether zlib library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <zlib.h>
-          int main() {}
+    # Test whether zlib library is installed
+    $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <zlib.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DZLIB"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lz"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lz"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DZLIB"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lz"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lz"
     fi
 
-    if ! test $ROCKSDB_DISABLE_BZIP; then
-        # Test whether bzip library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <bzlib.h>
-          int main() {}
+    # Test whether bzip library is installed
+    $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <bzlib.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DBZIP2"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbz2"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lbz2"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DBZIP2"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbz2"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lbz2"
     fi
 
-    if ! test $ROCKSDB_DISABLE_LZ4; then
-        # Test whether lz4 library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <lz4.h>
-          #include <lz4hc.h>
-          int main() {}
+    # Test whether lz4 library is installed
+    $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <lz4.h>
+      #include <lz4hc.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DLZ4"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -llz4"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -llz4"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DLZ4"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -llz4"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -llz4"
     fi
 
-    if ! test $ROCKSDB_DISABLE_ZSTD; then
-        # Test whether zstd library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <zstd.h>
-          int main() {}
+    # Test whether zstd library is installed
+    $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <zstd.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DZSTD"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lzstd"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lzstd"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DZSTD"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lzstd"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lzstd"
     fi
 
-    if ! test $ROCKSDB_DISABLE_NUMA; then
-        # Test whether numa is available
-        $CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
-          #include <numa.h>
-          #include <numaif.h>
-          int main() {}
+    # Test whether numa is available
+    $CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
+      #include <numa.h>
+      #include <numaif.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DNUMA"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lnuma"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DNUMA"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lnuma"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
     fi
 
-    if ! test $ROCKSDB_DISABLE_TBB; then
-        # Test whether tbb is available
-        $CXX $CFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null  <<EOF
-          #include <tbb/tbb.h>
-          int main() {}
+    # Test whether tbb is available
+    $CXX $CFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null  <<EOF
+      #include <tbb/tbb.h>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DTBB"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltbb"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -ltbb"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DTBB"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltbb"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -ltbb"
     fi
 
-    if ! test $ROCKSDB_DISABLE_JEMALLOC; then
-        # Test whether jemalloc is available
-        if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
-          2>/dev/null; then
-            # This will enable some preprocessor identifiers in the Makefile
-            JEMALLOC=1
-            # JEMALLOC can be enabled either using the flag (like here) or by
-            # providing direct link to the jemalloc library
-            WITH_JEMALLOC_FLAG=1
-            # check for JEMALLOC installed with HomeBrew
-            if [ "$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
+    # Test whether jemalloc is available
+    if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
+      2>/dev/null; then
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ljemalloc"
+        JAVA_LDFLAGS="$JAVA_LDFLAGS -ljemalloc"
+        JEMALLOC=1
+    else
         # jemalloc is not available. Let's try tcmalloc
         if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null \
           -ltcmalloc 2>/dev/null; then
@@ -407,114 +317,65 @@ EOF
         fi
     fi
 
-    if ! test $ROCKSDB_DISABLE_MALLOC_USABLE_SIZE; then
-        # Test whether malloc_usable_size is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <malloc.h>
-          int main() {
-            size_t res = malloc_usable_size(0);
-            (void)res;
-            return 0;
-          }
+    # Test whether malloc_usable_size is available
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <malloc.h>
+      int main() {
+        size_t res = malloc_usable_size(0);
+        return 0;
+      }
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
     fi
 
-    if ! test $ROCKSDB_DISABLE_PTHREAD_MUTEX_ADAPTIVE_NP; then
-        # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <pthread.h>
-          int main() {
-            int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-            (void)x;
-            return 0;
-          }
+    # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <pthread.h>
+      int main() {
+        int x = PTHREAD_MUTEX_ADAPTIVE_NP;
+        return 0;
+      }
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
     fi
 
-    if ! test $ROCKSDB_DISABLE_BACKTRACE; then
-        # Test whether backtrace is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+    # Test whether backtrace is available
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <execinfo.h>>
+      int main() {
+        void* frames[1];
+        backtrace_symbols(frames, backtrace(frames, 1));
+        return 0;
+      }
+EOF
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
+    else
+        # Test whether execinfo library is installed
+        $CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
           #include <execinfo.h>
           int main() {
             void* frames[1];
             backtrace_symbols(frames, backtrace(frames, 1));
-            return 0;
           }
 EOF
         if [ "$?" = 0 ]; then
             COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-        else
-            # Test whether execinfo library is installed
-            $CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
-              #include <execinfo.h>
-              int main() {
-                void* frames[1];
-                backtrace_symbols(frames, backtrace(frames, 1));
-              }
-EOF
-            if [ "$?" = 0 ]; then
-                COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-                PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
-                JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
-            fi
+            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
+            JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
         fi
     fi
 
-    if ! test $ROCKSDB_DISABLE_PG; then
-        # Test if -pg is supported
-        $CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          int main() {
-            return 0;
-          }
+    # Test if -pg is supported
+    $CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      int main() {
+        return 0;
+      }
 EOF
-        if [ "$?" = 0 ]; then
-            PROFILING_FLAGS=-pg
-        fi
-    fi
-
-    if ! test $ROCKSDB_DISABLE_SYNC_FILE_RANGE; then
-        # Test whether sync_file_range is supported for compatibility with an old glibc
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <fcntl.h>
-          int main() {
-            int fd = open("/dev/null", 0);
-            sync_file_range(fd, 0, 1024, SYNC_FILE_RANGE_WRITE);
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_RANGESYNC_PRESENT"
-        fi
-    fi
-
-    if ! test $ROCKSDB_DISABLE_SCHED_GETCPU; then
-        # Test whether sched_getcpu is supported
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <sched.h>
-          int main() {
-            int cpuid = sched_getcpu();
-            (void)cpuid;
-          }
-EOF
-        if [ "$?" = 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="$PLATFORM_CXXFLAGS -faligned-new -DHAVE_ALIGNED_NEW"
-        fi
+    if [ "$?" = 0 ]; then
+        PROFILING_FLAGS=-pg
     fi
 fi
 
@@ -534,11 +395,11 @@ 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 $HDFS_CCFLAGS"
@@ -546,137 +407,24 @@ if test "$USE_HDFS"; then
   JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi
 
-if test "0$PORTABLE" -eq 0; then
+if [ "$TARGET_OS" = FreeBSD -a "$TARGET_ARCHITECTURE" = i386 ]; then
+  # Intel SSE instructions breaks compilation on FreeBSD i386
+  unset USE_SSE
+fi
+
+if test "$USE_SSE"; then
+  # if Intel SSE instruction set is supported, set USE_SSE=1
+  COMMON_FLAGS="$COMMON_FLAGS -msse -msse4.2 "
+elif test -z "$PORTABLE"; then
   if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
     # Tune for this POWER processor, treating '+' models as base models
     POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
     COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
   elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
     COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep -e^arm -e^aarch64`"; then
-    # TODO: Handle this with approprite options.
-    COMMON_FLAGS="$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 "$USE_SSE"; then
-      TRY_SSE_ETC="1"
-    fi
   else
     COMMON_FLAGS="$COMMON_FLAGS -march=native "
   fi
-else
-  # PORTABLE=1
-  if test "$USE_SSE"; then
-    TRY_SSE_ETC="1"
-  fi
-fi
-
-if test "$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 $TRY_SSE42 -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <nmmintrin.h>
-  int main() {
-    volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_SSE42 -DHAVE_SSE42"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <wmmintrin.h>
-  int main() {
-    const auto a = _mm_set_epi64x(0, 0);
-    const auto b = _mm_set_epi64x(0, 0);
-    const auto c = _mm_clmulepi64_si128(a, b, 0x00);
-    auto d = _mm_cvtsi128_si64(c);
-    (void)d;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_PCLMUL -DHAVE_PCLMUL"
-elif test "$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="$COMMON_FLAGS -DHAVE_UINT128_EXTENSION"
-fi
-
-# iOS doesn't support thread-local storage, but this check would erroneously
-# succeed because the cross-compiler flags are added by the Makefile, not this
-# script.
-if [ "$PLATFORM" != IOS ]; then
-  $CXX $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #if defined(_MSC_VER) && !defined(__thread)
-  #define __thread __declspec(thread)
-  #endif
-  int main() {
-    static __thread int tls;
-    (void)tls;
-  }
-EOF
-  if [ "$?" = 0 ]; then
-    COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SUPPORT_THREAD_LOCAL"
-  fi
-fi
-
-if [ "$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 $COMMON_FLAGS"
@@ -710,19 +458,7 @@ echo "ROCKSDB_PATCH=$ROCKSDB_PATCH" >> "$OUTPUT"
 echo "CLANG_SCAN_BUILD=$CLANG_SCAN_BUILD" >> "$OUTPUT"
 echo "CLANG_ANALYZER=$CLANG_ANALYZER" >> "$OUTPUT"
 echo "PROFILING_FLAGS=$PROFILING_FLAGS" >> "$OUTPUT"
-echo "FIND=$FIND" >> "$OUTPUT"
-echo "WATCH=$WATCH" >> "$OUTPUT"
-# This will enable some related identifiers for the preprocessor
 if test -n "$JEMALLOC"; then
   echo "JEMALLOC=1" >> "$OUTPUT"
 fi
-# Indicates that jemalloc should be enabled using -ljemalloc flag
-# The alternative is to porvide a direct link to the library via JEMALLOC_LIB
-# and JEMALLOC_INCLUDE
-if test -n "$WITH_JEMALLOC_FLAG"; then
-  echo "WITH_JEMALLOC_FLAG=$WITH_JEMALLOC_FLAG" >> "$OUTPUT"
-fi
 echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
-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 +1,135 @@
+#!/bin/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`
+  echo $DATE $@
+}
+
+function log_err {
+  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 $error
+  fi
+}
+
+#
+# Execution starts here.
+#
+
+# Path to the determinator from the root of the RocksDB repo.
+CONTRUN_DETERMINATOR=./arcanist_util/config/RocksDBCommonHelper.php
+
+# Value of the previous commit.
+PREV_COMMIT=
+
+log "Starting to monitor for new RocksDB changes ..."
+log "Running under `pwd` as `whoami`."
+
+# Paranoia. Make sure that we're using the right branch.
+git checkout master
+
+error=$?
+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
+GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/963d9aeda70cc4779885b1277484fe7544a04e3e/9.0.0/platform007/9e92d53/
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
+NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/ab9f09bba370e7066cafd4eb59752db93f2e8312/2.29.1/platform007/15a3614
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832

build_tools/dependencies_4.8.1.sh

@@ -1,5 +1,3 @@
-# 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.
+#!/bin/bash
 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
@@ -14,7 +13,7 @@ source "$BASEDIR/dependencies.sh"
 CFLAGS=""
 
 # libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include"
+LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/7.3.0"
 LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
 
 # glibc
@@ -52,7 +51,7 @@ if test -z $PIC_BUILD; then
 else
   ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
 fi
-CFLAGS+=" -DZSTD -DZSTD_STATIC_LINKING_ONLY"
+CFLAGS+=" -DZSTD"
 
 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
@@ -86,10 +85,8 @@ 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
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -111,8 +108,8 @@ if [ -z "$USE_CLANG" ]; then
   CXX="$GCC_BASE/bin/g++"
 
   CFLAGS+=" -B$BINUTILS/gold"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
   CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
   JEMALLOC=1
 else
   # clang
@@ -123,8 +120,8 @@ else
   KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
 
   CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/5.x "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/5.x/x86_64-facebook-linux "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x/x86_64-facebook-linux "
   CFLAGS+=" -isystem $GLIBC_INCLUDE"
   CFLAGS+=" -isystem $LIBGCC_INCLUDE"
   CFLAGS+=" -isystem $CLANG_INCLUDE"
@@ -140,9 +137,9 @@ CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
 EXEC_LDFLAGS+=" -B$BINUTILS/gold"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-5-glibc-2.23/lib/ld.so"
+EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-5-glibc-2.23/lib"
+EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform007/lib"
 # required by libtbb
 EXEC_LDFLAGS+=" -ldl"
 
@@ -152,14 +149,4 @@ EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GF
 
 VALGRIND_VER="$VALGRIND_BASE/bin/"
 
-LUA_PATH="$LUA_BASE"
-
-if test -z $PIC_BUILD; then
-  LUA_LIB=" $LUA_PATH/lib/liblua.a"
-else
-  LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
-fi
-
-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
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD 

build_tools/fbcode_config4.8.1.sh

@@ -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 +52,8 @@ 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
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -96,7 +93,7 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
 CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA -DTBB"
 CXXFLAGS+=" $CFLAGS"
 

build_tools/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.
+#!/bin/bash
 # If clang_format_diff.py command is not specfied, we assume we are able to
 # access directly without any path.
 if [ -z $CLANG_FORMAT_DIFF ]
@@ -10,17 +9,10 @@ fi
 # Check clang-format-diff.py
 if ! which $CLANG_FORMAT_DIFF &> /dev/null
 then
-  echo "You didn't have clang-format-diff.py and/or clang-format available in your computer!"
-  echo "You can download clang-format-diff.py by running: "
+  echo "You didn't have clang-format-diff.py available in your computer!"
+  echo "You can download it by running: "
   echo "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
-  echo "You can download clang-format by running:"
-  echo "    brew install clang-format"
-  echo "  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."
+  echo "and move ${CLANG_FORMAT_DIFF} to some directory within PATH=${PATH}"
   exit 128
 fi
 
@@ -59,25 +51,15 @@ 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 +73,12 @@ 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 +101,7 @@ 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 +1,4 @@
-# shellcheck disable=SC1113
 #/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 set -e
 
@@ -30,14 +28,12 @@ function package() {
     if dpkg --get-selections | grep --quiet $1; then
       log "$1 is already installed. skipping."
     else
-      # shellcheck disable=SC2068
       apt-get install $@ -y
     fi
   elif [[ $OS = "centos" ]]; then
     if rpm -qa | grep --quiet $1; then
       log "$1 is already installed. skipping."
     else
-      # shellcheck disable=SC2068
       yum install $@ -y
     fi
   fi
@@ -56,7 +52,6 @@ function gem_install() {
   if gem list | grep --quiet $1; then
     log "$1 is already installed. skipping."
   else
-    # shellcheck disable=SC2068
     gem install $@
   fi
 }
@@ -104,18 +99,6 @@ function main() {
 
   make static_lib
   make install INSTALL_PATH=package
-
-  cd package
-
-  LIB_DIR=lib
-  if [[ -z "$ARCH" ]]; then
-      ARCH=$(getconf LONG_BIT)
-  fi
-  if [[ ("$FPM_OUTPUT" = "rpm") && ($ARCH -eq 64) ]]; then
-      mv lib lib64
-      LIB_DIR=lib64
-  fi
-
   fpm \
     -s dir \
     -t $FPM_OUTPUT \
@@ -127,8 +110,7 @@ function main() {
     --license BSD \
     --vendor Facebook \
     --description "RocksDB is an embeddable persistent key-value store for fast storage." \
-    include $LIB_DIR
+    package
 }
 
-# shellcheck disable=SC2068
 main $@

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.
+#!/bin/bash
 
 set -e
 

build_tools/rocksdb-lego-determinator

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 # This script is executed by Sandcastle
 # to determine next steps to run
 
@@ -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 $RATIO ]; then
@@ -96,16 +81,12 @@ PARALLELISM="$PARALLEL_J $PARALLEL_j"
 
 DEBUG="OPT=-g"
 SHM="TEST_TMPDIR=/dev/shm/rocksdb"
-NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-# 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 +105,13 @@ else
   TASK_CREATION_TOOL="false"
 fi
 
+ARTIFACTS=" 'artifacts': [
+    {
+        'name':'database',
+        'paths':[ '/dev/shm/rocksdb' ],
+    }
+]"
+
 #
 # A mechanism to disable tests temporarily
 #
@@ -141,6 +129,35 @@ DISABLE_COMMANDS="[
     }
 ]"
 
+#
+# RocksDB unit test in parallel
+# Currently we always have noise in our parallel runs. This job is to help
+# manage the noise
+#
+PARALLEL_UNIT_TEST_COMMANDS="[
+    {
+        'name':'Rocksdb Parallel Unit Test',
+        'oncall':'$ONCALL',
+        'steps': [
+            $CLEANUP_ENV,
+            {
+                'name':'Build and test RocksDB debug version',
+                'shell':'$DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || $CONTRUN_NAME=punit_check $TASK_CREATION_TOOL || cat t/log-*',
+                'user':'root',
+                $PARSER
+            },
+            $CLEANUP_ENV,
+            {
+                'name':'Build and test RocksDB debug version under gcc-4.8.1',
+                'shell':'$GCC_481 $DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || $CONTRUN_NAME=punit_check_gcc481 $TASK_CREATION_TOOL || cat t/log-*',
+                'user':'root',
+                $PARSER
+            },
+        ],
+        $REPORT
+    }
+]"
+
 #
 # RocksDB unit test
 #
@@ -148,7 +165,6 @@ UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -169,14 +185,13 @@ UNIT_TEST_NON_SHM_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Build and test RocksDB debug version',
                 'timeout': 86400,
-                'shell':'$NON_SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
+                'shell':'$DEBUG make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -192,7 +207,6 @@ RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -213,7 +227,6 @@ UNIT_TEST_COMMANDS_481="[
     {
         'name':'Rocksdb Unit Test on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -234,7 +247,6 @@ RELEASE_BUILD_COMMANDS_481="[
     {
         'name':'Rocksdb Release on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -255,7 +267,6 @@ CLANG_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -276,7 +287,6 @@ CLANG_RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb CLANG Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -297,7 +307,6 @@ CLANG_ANALYZE_COMMANDS="[
     {
         'name':'Rocksdb analyze',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -318,7 +327,6 @@ CODE_COV_COMMANDS="[
     {
         'name':'Rocksdb Unit Test Code Coverage',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -339,7 +347,6 @@ UNITY_COMMANDS="[
     {
         'name':'Rocksdb Unity',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -360,12 +367,11 @@ LITE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Lite build',
         'oncall':'$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 static_lib || $CONTRUN_NAME=lite_static_lib $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -375,20 +381,23 @@ LITE_BUILD_COMMANDS="[
 ]"
 
 #
-# Report RocksDB lite binary size to scuba
-REPORT_LITE_BINARY_SIZE_COMMANDS="[
+# RocksDB lite tests
+#
+LITE_UNIT_TEST_COMMANDS="[
     {
-        'name':'Rocksdb Lite Binary Size',
+        'name':'Rocksdb Lite Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
-                'name':'Report RocksDB Lite binary size to scuba',
-                'shell':'tools/report_lite_binary_size.sh',
+                'name':'Build RocksDB debug version',
+                'shell':'$SHM $LITE make J=1 check || $CONTRUN_NAME=lite_check $TASK_CREATION_TOOL',
                 'user':'root',
+                $PARSER
             },
         ],
+        $REPORT
+    }
 ]"
 
 #
@@ -396,86 +405,26 @@ 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,
         $REPORT
     }
 ]"
@@ -487,7 +436,6 @@ WRITE_STRESS_COMMANDS="[
     {
         'name':'Rocksdb Write Stress Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -510,7 +458,6 @@ ASAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under ASAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -531,14 +478,13 @@ ASAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under ASAN',
         'oncall':'$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 +493,6 @@ 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB test under undefined behavior sanitizer
 #
@@ -602,12 +500,11 @@ UBSAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under UBSAN',
         'oncall':'$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',
                 $PARSER
             }
@@ -623,14 +520,13 @@ UBSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under UBSAN',
         'oncall':'$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 +535,6 @@ 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB unit test under valgrind
 #
@@ -694,7 +542,6 @@ VALGRIND_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under valgrind',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -717,7 +564,6 @@ TSAN_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under TSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -740,14 +586,13 @@ TSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb Crash Test under TSAN',
         'oncall':'$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 make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -756,54 +601,6 @@ 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
 #
@@ -814,14 +611,45 @@ run_format_compatible()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
 
-  tools/check_format_compatible.sh
+  echo '
+  if [ -e "build_tools/build_detect_platform" ]
+  then
+    sed "s/tcmalloc/nothingnothingnothing/g" build_tools/build_detect_platform > $TEST_TMPDIR/temp_build_file
+    rm -rf build_tools/build_detect_platform
+    cp $TEST_TMPDIR/temp_build_file build_tools/build_detect_platform
+    chmod +x build_tools/build_detect_platform
+  fi
+
+  if [ -e "build_detect_platform" ]
+  then
+    sed "s/tcmalloc/nothingnothingnothing/g" build_detect_platform > $TEST_TMPDIR/temp_build_file
+    rm -rf build_detect_platform
+    cp $TEST_TMPDIR/temp_build_file build_detect_platform
+    chmod +x build_detect_platform
+  fi
+
+  make ldb -j32
+
+  if [ -e "build_detect_platform" ]
+  then
+    git checkout -- build_detect_platform
+  fi
+
+  if [ -e "build_tools/build_detect_platform" ]
+  then
+    git checkout -- build_tools/build_detect_platform
+  fi
+  ' > temp_build_ldb.sh
+
+  sed "s/make ldb -j32/source temp_build_ldb.sh/g" tools/check_format_compatible.sh > tools/temp_check_format_compatible.sh
+  chmod +x tools/temp_check_format_compatible.sh
+  tools/temp_check_format_compatible.sh
 }
 
 FORMAT_COMPATIBLE_COMMANDS="[
     {
         'name':'Rocksdb Format Compatible tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -844,7 +672,7 @@ run_no_compression()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
   make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzstd | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
+  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
   mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
   cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
   mv .tmp.Makefile Makefile
@@ -855,7 +683,6 @@ NO_COMPRESSION_COMMANDS="[
     {
         'name':'Rocksdb No Compression tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -898,12 +725,12 @@ 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 $(stat --printf="%s" `readlink -f librocksdb.so`)
@@ -933,7 +760,6 @@ JAVA_BUILD_TEST_COMMANDS="[
     {
         'name':'Rocksdb Java Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -949,6 +775,9 @@ JAVA_BUILD_TEST_COMMANDS="[
 
 
 case $1 in
+  punit)
+    echo $PARALLEL_UNIT_TEST_COMMANDS
+    ;;
   unit)
     echo $UNIT_TEST_COMMANDS
     ;;
@@ -982,18 +811,12 @@ case $1 in
   lite)
     echo $LITE_BUILD_COMMANDS
     ;;
-  report_lite_binary_size)
-    echo $REPORT_LITE_BINARY_SIZE_COMMANDS
+  lite_test)
+    echo $LITE_UNIT_TEST_COMMANDS
     ;;
   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 +826,12 @@ 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 +841,6 @@ 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

@@ -1,59 +1,24 @@
-# 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
+# All the tests in parallel and utilizing all the cores
+# For db_test the script first lists and parses the tests
+# and then fires them up in parallel using async PS Job functionality
+# Run the script from the enlistment
 Param(
-  [switch]$EnableJE = $false,  # Look for and use test executable, append _je to listed exclusions
-  [switch]$RunAll = $false,    # Will attempt discover all *_test[_je].exe binaries and run all
-                               # of them as Google suites. I.e. It will run test cases concurrently
-                               # except those mentioned as $Run, those will run as individual test cases
-                               # And any execlued with $ExcludeExes or $ExcludeCases
-                               # It will also not run any individual test cases
-                               # excluded but $ExcludeCasese
-  [switch]$RunAllExe = $false, # Look for and use test exdcutables, append _je to exclusions automatically
-                               # It will attempt to run them in parallel w/o breaking them up on individual
-                               # test cases. Those listed with $ExcludeExes will be excluded
-  [string]$SuiteRun = "",      # Split test suites in test cases and run in parallel, not compatible with $RunAll
-  [string]$Run = "",           # Run specified executables in parallel but do not split to test cases
-  [string]$ExcludeCases = "",  # Exclude test cases, expects a comma separated list, no spaces
-                               # Takes effect when $RunAll or $SuiteRun is specified. Must have full
-                               # Test cases name including a group and a parameter if any
-  [string]$ExcludeExes = "",   # Exclude exes from consideration, expects a comma separated list,
-                               # no spaces. Takes effect only when $RunAll is specified
-  [string]$WorkFolder = "",    # Direct tests to use that folder. SSD or Ram drive are better options.
+  [switch]$EnableJE = $false,  # Use je executable
+  [switch]$EnableRerun = $false, # Rerun failed tests sequentially at the end
+  [string]$WorkFolder = "",  # Direct tests to use that folder
+  [int]$Limit = -1, # -1 means run all otherwise limit for testing purposes
+  [string]$Exclude = "", # Expect a comma separated list, no spaces
+  [string]$Run = "db_test",  # Run db_test|db_test2|tests|testname1,testname2...
    # Number of async tasks that would run concurrently. Recommend a number below 64.
    # However, CPU utlization really depends on the storage media. Recommend ram based disk.
    # a value of 1 will run everything serially
-  [int]$Concurrency = 8,
-  [int]$Limit = -1 # -1 means do not limit for test purposes
+  [int]$Concurrency = 16
 )
 
 # Folders and commands must be fullpath to run assuming
 # the current folder is at the root of the git enlistment
-$StartDate = (Get-Date)
-$StartDate
-
-
-$DebugPreference = "Continue"
-
-# These tests are not google test suites and we should guard
-# Against running them as suites
-$RunOnly = New-Object System.Collections.Generic.HashSet[string]
-$RunOnly.Add("c_test") | Out-Null
-$RunOnly.Add("compact_on_deletion_collector_test") | Out-Null
-$RunOnly.Add("merge_test") | Out-Null
-$RunOnly.Add("stringappend_test") | Out-Null # Apparently incorrectly written
-$RunOnly.Add("backupable_db_test") | Out-Null # Disabled
-$RunOnly.Add("timer_queue_test") | Out-Null # Not a gtest
-
-if($RunAll -and $SuiteRun -ne "") {
-    Write-Error "$RunAll and $SuiteRun are not compatible"
-    exit 1
-}
-
-if($RunAllExe -and $Run -ne "") {
-    Write-Error "$RunAllExe and $Run are not compatible"
-    exit 1
-}
+Get-Date
 
 # If running under Appveyor assume that root
 [string]$Appveyor = $Env:APPVEYOR_BUILD_FOLDER
@@ -82,32 +47,40 @@ if($WorkFolder -eq "") {
 }
 
 Write-Output "Root: $RootFolder, WorkFolder: $WorkFolder"
-Write-Output "BinariesFolder: $BinariesFolder, LogFolder: $LogFolder"
+
+# Use JEMALLOC executables
+if($Run -ceq "db_test" -or
+   $Run -ceq "db_test2" -or
+   $Run -ceq "db_basic_test") {
+
+   $file_name = $Run
+
+   if($EnableJE) {
+     $file_name += "_je"
+   }
+
+   $file_name += ".exe"
+
+   $db_test = -Join ($BinariesFolder, $file_name)
+
+   Write-Output "Binaries: $BinariesFolder db_test: $db_test"
+}
+
+
+#Exclusions that we do not want to run
+$ExcludeTests = New-Object System.Collections.Generic.HashSet[string]
+
+
+if($Exclude -ne "") {
+    Write-Host "Exclude: $Exclude"
+    $l = $Exclude -split ' '
+    ForEach($t in $l) { $ExcludeTests.Add($t) | Out-Null }
+}
 
 # Create test directories in the current folder
 md -Path $WorkFolder -ErrorAction Ignore | Out-Null
 md -Path $LogFolder -ErrorAction Ignore | Out-Null
 
-
-$ExcludeCasesSet = New-Object System.Collections.Generic.HashSet[string]
-if($ExcludeCases -ne "") {
-    Write-Host "ExcludeCases: $ExcludeCases"
-    $l = $ExcludeCases -split ' '
-    ForEach($t in $l) { 
-      $ExcludeCasesSet.Add($t) | Out-Null
-    }
-}
-
-$ExcludeExesSet = New-Object System.Collections.Generic.HashSet[string]
-if($ExcludeExes -ne "") {
-    Write-Host "ExcludeExe: $ExcludeExes"
-    $l = $ExcludeExes -split ' '
-    ForEach($t in $l) { 
-      $ExcludeExesSet.Add($t) | Out-Null
-    }
-}
-
-
 # Extract the names of its tests by running db_test with --gtest_list_tests.
 # This filter removes the "#"-introduced comments, and expands to
 # fully-qualified names by changing input like this:
@@ -125,33 +98,28 @@ if($ExcludeExes -ne "") {
 #   DBTest.WriteEmptyBatch
 #   MultiThreaded/MultiThreadedDBTest.MultiThreaded/0
 #   MultiThreaded/MultiThreadedDBTest.MultiThreaded/1
-#
 # Output into the parameter in a form TestName -> Log File Name
-function ExtractTestCases([string]$GTestExe, $HashTable) {
+function Normalize-DbTests($HashTable) {
 
     $Tests = @()
 # Run db_test to get a list of tests and store it into $a array
-    &$GTestExe --gtest_list_tests | tee -Variable Tests | Out-Null
+    &$db_test --gtest_list_tests | tee -Variable Tests | Out-Null
 
     # Current group
     $Group=""
 
     ForEach( $l in $Tests) {
-
-      # Leading whitespace is fine
-      $l = $l -replace '^\s+',''
-      # Trailing dot is a test group but no whitespace
-      if ($l -match "\.$" -and $l -notmatch "\s+") {
+      # Trailing dot is a test group
+      if( $l -match "\.$") {
         $Group = $l
       }  else {
         # Otherwise it is a test name, remove leading space
-        $test = $l
+        $test = $l -replace '^\s+',''
         # remove trailing comment if any and create a log name
         $test = $test -replace '\s+\#.*',''
         $test = "$Group$test"
 
-        if($ExcludeCasesSet.Contains($test)) {
-            Write-Warning "$test case is excluded"
+        if($ExcludeTests.Contains($test)) {
             continue
         }
 
@@ -167,157 +135,61 @@ function ExtractTestCases([string]$GTestExe, $HashTable) {
 
 # The function removes trailing .exe siffix if any,
 # creates a name for the log file
-# Then adds the test name if it was not excluded into
-# a HashTable in a form of test_name -> log_path
 function MakeAndAdd([string]$token, $HashTable) {
-
     $test_name = $token -replace '.exe$', ''
     $log_name =  -join ($test_name, ".log")
     $log_path = -join ($LogFolder, $log_name)
-    $HashTable.Add($test_name, $log_path)
-}
-
-# This function takes a list of Suites to run
-# Lists all the test cases in each of the suite
-# and populates HashOfHashes
-# Ordered by suite(exe) @{ Exe = @{ TestCase = LogName }}
-function ProcessSuites($ListOfSuites, $HashOfHashes) {
-
-  $suite_list = $ListOfSuites
-  # Problem: if you run --gtest_list_tests on
-  # a non Google Test executable then it will start executing
-  # and we will get nowhere
-  ForEach($suite in $suite_list) {
-
-    if($RunOnly.Contains($suite)) {
-      Write-Warning "$suite is excluded from running as Google test suite"
-      continue
-    }
-
-    if($EnableJE) {
-      $suite += "_je"
-    }
-
-    $Cases = [ordered]@{}
-    $Cases.Clear()
-    $suite_exe = -Join ($BinariesFolder, $suite)
-    ExtractTestCases -GTestExe $suite_exe -HashTable $Cases
-    if($Cases.Count -gt 0) {
-      $HashOfHashes.Add($suite, $Cases);
-    }
-  }
-
-  # Make logs and run
-  if($CasesToRun.Count -lt 1) {
-     Write-Error "Failed to extract tests from $SuiteRun"
-     exit 1
-  }
-
-}
-
-# This will contain all test executables to run
-
-# Hash table that contains all non suite
-# Test executable to run
-$TestExes = [ordered]@{}
-
-# Check for test exe that are not
-# Google Test Suites
-# Since this is explicitely mentioned it is not subject
-# for exclusions
-if($Run -ne "") {
-
-  $test_list = $Run -split ' '
-  ForEach($t in $test_list) {
-
-    if($EnableJE) {
-      $t += "_je"
-    }
-    MakeAndAdd -token $t -HashTable $TestExes
-  }
-
-  if($TestExes.Count -lt 1) {
-     Write-Error "Failed to extract tests from $Run"
-     exit 1
-  }
-} elseif($RunAllExe) {
-  # Discover all the test binaries
-  if($EnableJE) {
-    $pattern = "*_test_je.exe"
-  } else {
-    $pattern = "*_test.exe"
-  }
-
-  $search_path = -join ($BinariesFolder, $pattern)
-  Write-Host "Binaries Search Path: $search_path"
-
-  $DiscoveredExe = @()
-  dir -Path $search_path | ForEach-Object {
-     $DiscoveredExe += ($_.Name)     
-  }
-
-  # Remove exclusions
-  ForEach($e in $DiscoveredExe) {
-    $e = $e -replace '.exe$', ''
-    $bare_name = $e -replace '_je$', ''
-
-    if($ExcludeExesSet.Contains($bare_name)) {
-      Write-Warning "Test $e is excluded"
-      continue
-    }
-    MakeAndAdd -token $e -HashTable $TestExes
-  }
-
-  if($TestExes.Count -lt 1) {
-     Write-Error "Failed to discover test executables"
-     exit 1
-  }
-}
-
-# Ordered by exe @{ Exe = @{ TestCase = LogName }}
-$CasesToRun = [ordered]@{}
-
-if($SuiteRun -ne "") {
-  $suite_list = $SuiteRun -split ' '
-  ProcessSuites -ListOfSuites $suite_list -HashOfHashes $CasesToRun
-} elseif ($RunAll) {
-# Discover all the test binaries
-  if($EnableJE) {
-    $pattern = "*_test_je.exe"
-  } else {
-    $pattern = "*_test.exe"
-  }
-
-  $search_path = -join ($BinariesFolder, $pattern)
-  Write-Host "Binaries Search Path: $search_path"
-
-  $ListOfExe = @()
-  dir -Path $search_path | ForEach-Object {
-     $ListOfExe += ($_.Name)     
-  }
-
-  # Exclude those in RunOnly from running as suites
-  $ListOfSuites = @()
-  ForEach($e in $ListOfExe) {
-
-    $e = $e -replace '.exe$', ''
-    $bare_name = $e -replace '_je$', ''
-
-    if($ExcludeExesSet.Contains($bare_name)) {
-      Write-Warning "Test $e is excluded"
-      continue
-    }
-
-    if($RunOnly.Contains($bare_name)) {
-      MakeAndAdd -token $e -HashTable $TestExes
+    if(!$ExcludeTests.Contains($test_name)) {
+        $HashTable.Add($test_name, $log_path)
     } else {
-      $ListOfSuites += $bare_name
+        Write-Warning "Test $test_name is excluded"
     }
-  }
-
-  ProcessSuites -ListOfSuites $ListOfSuites -HashOfHashes $CasesToRun
 }
 
+# The function scans build\Debug folder to discover
+# Test executables. It then populates a table with
+# Test executable name -> Log file
+function Discover-TestBinaries([string]$Pattern, $HashTable) {
+
+    $Exclusions = @("db_test*", "db_sanity_test*", "db_basic_test*")
+
+    $p = -join ($BinariesFolder, $pattern)
+
+    Write-Host "Path: $p"
+
+    dir -Path $p -Exclude $Exclusions | ForEach-Object {
+       MakeAndAdd -token ($_.Name) -HashTable $HashTable
+    }
+}
+
+$TestsToRun = [ordered]@{}
+
+if($Run -ceq "db_test" -or
+   $Run -ceq "db_test2" -or
+   $Run -ceq "db_basic_test") {
+    Normalize-DbTests -HashTable $TestsToRun
+} elseif($Run -ceq "tests") {
+    if($EnableJE) {
+        $pattern = "*_test_je.exe"
+    } else {
+        $pattern = "*_test.exe"
+    }
+    Discover-TestBinaries -Pattern $pattern -HashTable $TestsToRun
+} else {
+
+    $test_list = $Run -split ' '
+
+    ForEach($t in $test_list) {
+       MakeAndAdd -token $t -HashTable $TestsToRun
+    }
+}
+
+$NumTestsToStart = $TestsToRun.Count
+if($Limit -ge 0 -and $NumTestsToStart -gt $Limit) {
+    $NumTestsToStart = $Limit
+}
+
+Write-Host "Attempting to start: $NumTestsToStart tests"
 
 # Invoke a test with a filter and redirect all output
 $InvokeTestCase = {
@@ -333,13 +205,13 @@ $InvokeTestAsync = {
 
 # Hash that contains tests to rerun if any failed
 # Those tests will be rerun sequentially
-# $Rerun = [ordered]@{}
+$Rerun = [ordered]@{}
 # Test limiting factor here
-[int]$count = 0
+$count = 0
 # Overall status
-[bool]$script:success = $true;
+[bool]$success = $true;
 
-function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
+function RunJobs($TestToLog, [int]$ConcurrencyVal, [bool]$AddForRerun)
 {
     # Array to wait for any of the running jobs
     $jobs = @()
@@ -348,67 +220,38 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
 
     # Wait for all to finish and get the results
     while(($JobToLog.Count -gt 0) -or
-          ($TestCmds.Count -gt 0) -or 
-           ($Suites.Count -gt 0)) {
+          ($TestToLog.Count -gt 0)) {
 
         # Make sure we have maximum concurrent jobs running if anything
         # and the $Limit either not set or allows to proceed
         while(($JobToLog.Count -lt $ConcurrencyVal) -and
-              ((($TestCmds.Count -gt 0) -or ($Suites.Count -gt 0)) -and
+              (($TestToLog.Count -gt 0) -and
               (($Limit -lt 0) -or ($count -lt $Limit)))) {
 
-            # We always favore suites to run if available
-            [string]$exe_name = ""
-            [string]$log_path = ""
-            $Cases = @{}
 
-            if($Suites.Count -gt 0) {
-              # Will the first one
-              ForEach($e in $Suites.Keys) {
-                $exe_name = $e
-                $Cases = $Suites[$e]
+            # We only need the first key
+            foreach($key in $TestToLog.keys) {
+                $k = $key
                 break
-              }
-              [string]$test_case = ""
-              [string]$log_path = ""
-              ForEach($c in $Cases.Keys) {
-                 $test_case = $c
-                 $log_path = $Cases[$c]
-                 break
-              }
-
-              Write-Host "Starting $exe_name::$test_case"
-              [string]$Exe =  -Join ($BinariesFolder, $exe_name)
-              $job = Start-Job -Name "$exe_name::$test_case" -ArgumentList @($Exe,$test_case,$log_path) -ScriptBlock $InvokeTestCase
-              $JobToLog.Add($job, $log_path)
-
-              $Cases.Remove($test_case)
-              if($Cases.Count -lt 1) {
-                $Suites.Remove($exe_name)
-              }
-
-            } elseif ($TestCmds.Count -gt 0) {
-
-               ForEach($e in $TestCmds.Keys) {
-                 $exe_name = $e
-                 $log_path = $TestCmds[$e]
-                 break
-               }
-
-              Write-Host "Starting $exe_name"
-              [string]$Exe =  -Join ($BinariesFolder, $exe_name)
-              $job = Start-Job -Name $exe_name -ScriptBlock $InvokeTestAsync -ArgumentList @($Exe,$log_path)
-              $JobToLog.Add($job, $log_path)
-
-              $TestCmds.Remove($exe_name)
-
-            } else {
-                Write-Error "In the job loop but nothing to run"
-                exit 1
             }
 
+            Write-Host "Starting $k"
+            $log_path = ($TestToLog.$k)
+
+            if($Run -ceq "db_test" -or
+               $Run -ceq "db_test2" -or
+               $Run -ceq "db_basic_test") {
+              $job = Start-Job -Name $k -ScriptBlock $InvokeTestCase -ArgumentList @($db_test,$k,$log_path)
+            } else {
+              [string]$Exe =  -Join ($BinariesFolder, $k)
+               $job = Start-Job -Name $k -ScriptBlock $InvokeTestAsync -ArgumentList @($exe,$log_path)
+            }
+
+            $JobToLog.Add($job, $log_path)
+            $TestToLog.Remove($k)
+
             ++$count
-        } # End of Job starting loop
+        }
 
         if($JobToLog.Count -lt 1) {
           break
@@ -426,7 +269,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
         $log_content = @(Get-Content $log)
 
         if($completed.State -ne "Completed") {
-            $script:success = $false
+            $success = $false
             Write-Warning $message
             $log_content | Write-Warning
         } else {
@@ -450,9 +293,12 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
             }
 
             if(!$pass_found) {
-                $script:success = $false;
+                $success = $false;
                 Write-Warning $message
                 $log_content | Write-Warning
+                if($AddForRerun) {
+                    $Rerun.Add($completed.Name, $log)
+                }
             } else {
                 Write-Host $message
             }
@@ -464,24 +310,24 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
     }
 }
 
-RunJobs -Suites $CasesToRun -TestCmds $TestExes -ConcurrencyVal $Concurrency
+RunJobs -TestToLog $TestsToRun -ConcurrencyVal $Concurrency -AddForRerun $EnableRerun
 
-$EndDate = (Get-Date)
+if($Rerun.Count -gt 0) {
+    Write-Host "Rerunning " ($Rerun.Count) " tests sequentially"
+    $success = $true
+    $count = 0
+    RunJobs -TestToLog $Rerun -ConcurrencyVal 1 -AddForRerun $false
+}
 
-New-TimeSpan -Start $StartDate -End $EndDate | 
-  ForEach-Object { 
-    "Elapsed time: {0:g}" -f $_
-  }
+Get-Date
 
 
-if(!$script:success) {
+if(!$success) {
 # This does not succeed killing off jobs quick
 # So we simply exit
 #    Remove-Job -Job $jobs -Force
 # indicate failure using this exit code
-    exit 1
+    exit 12345
  }
 
- exit 0
-
  

build_tools/setup_centos7.sh

@@ -1,44 +0,0 @@
-#!/bin/bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-set -e
-
-ROCKSDB_VERSION="5.10.3"
-ZSTD_VERSION="1.1.3"
-
-echo "This script configures CentOS with everything needed to build and run RocksDB"
-
-yum update -y && yum install epel-release -y
-
-yum install -y \
-  wget \
-  gcc-c++ \
-  snappy snappy-devel \
-  zlib zlib-devel \
-  bzip2 bzip2-devel \
-  lz4-devel \
-  libasan \
-  gflags
-
-mkdir -pv /usr/local/rocksdb-${ROCKSDB_VERSION}
-ln -sfT /usr/local/rocksdb-${ROCKSDB_VERSION} /usr/local/rocksdb
-
-wget -qO /tmp/zstd-${ZSTD_VERSION}.tar.gz https://github.com/facebook/zstd/archive/v${ZSTD_VERSION}.tar.gz
-wget -qO /tmp/rocksdb-${ROCKSDB_VERSION}.tar.gz https://github.com/facebook/rocksdb/archive/v${ROCKSDB_VERSION}.tar.gz
-
-cd /tmp
-
-tar xzvf zstd-${ZSTD_VERSION}.tar.gz
-tar xzvf rocksdb-${ROCKSDB_VERSION}.tar.gz -C /usr/local/
-
-echo "Installing ZSTD..."
-pushd zstd-${ZSTD_VERSION}
-make && make install
-popd
-
-echo "Compiling RocksDB..."
-cd /usr/local/rocksdb
-chown -R vagrant:vagrant /usr/local/rocksdb/
-sudo -u vagrant make static_lib
-cd examples/
-sudo -u vagrant make all
-sudo -u vagrant ./c_simple_example

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"
@@ -45,7 +38,6 @@ function get_lib_base()
     # platform is not provided, use latest gcc
     result=`ls -dr1v $result/gcc-*[^fb]/ | head -n1`
   else
-    echo $lib_platform
     result="$result/$lib_platform/"
   fi
   
@@ -61,48 +53,7 @@ function get_lib_base()
 }
 
 ###########################################################
-#                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                      #
+#                   4.9.x dependencies                    #
 ###########################################################
 
 OUTPUT="$BASEDIR/dependencies.sh"
@@ -113,31 +64,30 @@ touch "$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/4.9.x/centos6-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
 # Libraries locations
-get_lib_base libgcc     5.x     gcc-5-glibc-2.23
-get_lib_base glibc      2.23    gcc-5-glibc-2.23
-get_lib_base snappy     LATEST  gcc-5-glibc-2.23
-get_lib_base zlib       LATEST  gcc-5-glibc-2.23
-get_lib_base bzip2      LATEST  gcc-5-glibc-2.23
-get_lib_base lz4        LATEST  gcc-5-glibc-2.23
-get_lib_base zstd       LATEST  gcc-5-glibc-2.23
-get_lib_base gflags     LATEST  gcc-5-glibc-2.23
-get_lib_base jemalloc   LATEST  gcc-5-glibc-2.23
-get_lib_base numa       LATEST  gcc-5-glibc-2.23
-get_lib_base libunwind  LATEST  gcc-5-glibc-2.23
-get_lib_base tbb        LATEST  gcc-5-glibc-2.23
+get_lib_base libgcc     4.9.x
+get_lib_base glibc      2.20
+get_lib_base snappy     LATEST gcc-4.9-glibc-2.20
+get_lib_base zlib       LATEST
+get_lib_base bzip2      LATEST
+get_lib_base lz4        LATEST
+get_lib_base zstd       LATEST
+get_lib_base gflags     LATEST
+get_lib_base jemalloc   LATEST
+get_lib_base numa       LATEST
+get_lib_base libunwind  LATEST
+get_lib_base tbb        4.0_update2 gcc-4.9-glibc-2.20
 
-get_lib_base kernel-headers 4.0.9-36_fbk5_2933_gd092e3f gcc-5-glibc-2.23
-get_lib_base binutils   LATEST centos7-native
-get_lib_base valgrind   LATEST gcc-5-glibc-2.23
-get_lib_base lua        5.2.3 gcc-5-glibc-2.23
+get_lib_base kernel-headers LATEST 
+get_lib_base binutils   LATEST centos6-native 
+get_lib_base valgrind   3.10.0 gcc-4.9-glibc-2.20
+get_lib_base lua        5.2.3 gcc-4.9-glibc-2.20
 
 git diff $OUTPUT
 
@@ -156,7 +106,6 @@ 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.
+#!/bin/sh
 if [ "$#" = "0" ]; then
   echo "Usage: $0 major|minor|patch|full"
   exit 1

cmake/RocksDBConfig.cmake.in

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

cmake/modules/FindJeMalloc.cmake

@@ -1,29 +1,22 @@
 # - Find JeMalloc library
 # Find the native JeMalloc includes and library
+# This module defines
+#  JEMALLOC_INCLUDE_DIRS, where to find jemalloc.h, Set when
+#                        JEMALLOC_INCLUDE_DIR is found.
+#  JEMALLOC_LIBRARIES, libraries to link against to use JeMalloc.
+#  JEMALLOC_FOUND, If false, do not try to use JeMalloc.
 #
-# JeMalloc_INCLUDE_DIRS - where to find jemalloc.h, etc.
-# JeMalloc_LIBRARIES - List of libraries when using jemalloc.
-# JeMalloc_FOUND - True if jemalloc found.
+find_path(JEMALLOC_INCLUDE_DIR
+  jemalloc/jemalloc.h)
 
-find_path(JeMalloc_INCLUDE_DIRS
-  NAMES jemalloc/jemalloc.h
-  HINTS ${JEMALLOC_ROOT_DIR}/include)
-
-find_library(JeMalloc_LIBRARIES
-  NAMES jemalloc
-  HINTS ${JEMALLOC_ROOT_DIR}/lib)
+find_library(JEMALLOC_LIBRARIES
+  jemalloc)
 
 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()
+MARK_AS_ADVANCED(
+  JEMALLOC_INCLUDE_DIR
+  JEMALLOC_LIBRARIES
+)

cmake/modules/FindNUMA.cmake

@@ -1,29 +0,0 @@
-# - Find NUMA
-# Find the NUMA library and includes
-#
-# NUMA_INCLUDE_DIRS - 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
-  NAMES numa.h numaif.h
-  HINTS ${NUMA_ROOT_DIR}/include)
-
-find_library(NUMA_LIBRARIES
-  NAMES numa
-  HINTS ${NUMA_ROOT_DIR}/lib)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIRS)
-
-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()

cmake/modules/FindTBB.cmake

@@ -1,33 +0,0 @@
-# - Find TBB
-# Find the Thread Building Blocks library and includes
-#
-# TBB_INCLUDE_DIRS - 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_library(TBB_LIBRARIES
-  NAMES tbb
-  HINTS ${TBB_ROOT_DIR}/lib ENV LIBRARY_PATH)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIRS)
-
-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()

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 +0,0 @@
-# - 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.
-
-find_path(lz4_INCLUDE_DIRS
-  NAMES lz4.h
-  HINTS ${lz4_ROOT_DIR}/include)
-
-find_library(lz4_LIBRARIES
-  NAMES lz4
-  HINTS ${lz4_ROOT_DIR}/lib)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(lz4 DEFAULT_MSG lz4_LIBRARIES lz4_INCLUDE_DIRS)
-
-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()

cmake/modules/Findsnappy.cmake

@@ -1,29 +1,23 @@
 # - 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)
 
+# handle the QUIETLY and REQUIRED arguments and set UUID_FOUND to TRUE if
+# all listed variables are TRUE
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(snappy DEFAULT_MSG snappy_LIBRARIES snappy_INCLUDE_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/Findzstd.cmake

@@ -1,29 +0,0 @@
-# - 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.
-
-find_path(zstd_INCLUDE_DIRS
-  NAMES zstd.h
-  HINTS ${zstd_ROOT_DIR}/include)
-
-find_library(zstd_LIBRARIES
-  NAMES zstd
-  HINTS ${zstd_ROOT_DIR}/lib)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(zstd DEFAULT_MSG zstd_LIBRARIES zstd_INCLUDE_DIRS)
-
-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()

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.
+#!/bin/bash
 
 # 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
 
@@ -73,7 +72,7 @@ def display_file_coverage(per_file_coverage, total_coverage):
     header_template = \
         "%" + str(max_file_name_length) + "s\t%s\t%s"
     separator = "-" * (max_file_name_length + 10 + 20)
-    print header_template % ("Filename", "Coverage", "Lines")  # noqa: E999 T25377293 Grandfathered in
+    print header_template % ("Filename", "Coverage", "Lines")
     print separator
 
     # -- Print body

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/auto_roll_logger.cc

@@ -3,54 +3,13 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 //
-#include "logging/auto_roll_logger.h"
-
-#include <algorithm>
-#include "file/filename.h"
-#include "logging/logging.h"
+#include "db/auto_roll_logger.h"
 #include "util/mutexlock.h"
 
 namespace rocksdb {
 
 #ifndef ROCKSDB_LITE
 // -- AutoRollLogger
-
-AutoRollLogger::AutoRollLogger(Env* env, const std::string& dbname,
-                               const std::string& db_log_dir,
-                               size_t log_max_size,
-                               size_t log_file_time_to_roll,
-                               size_t keep_log_file_num,
-                               const InfoLogLevel log_level)
-    : Logger(log_level),
-      dbname_(dbname),
-      db_log_dir_(db_log_dir),
-      env_(env),
-      status_(Status::OK()),
-      kMaxLogFileSize(log_max_size),
-      kLogFileTimeToRoll(log_file_time_to_roll),
-      kKeepLogFileNum(keep_log_file_num),
-      cached_now(static_cast<uint64_t>(env_->NowMicros() * 1e-6)),
-      ctime_(cached_now),
-      cached_now_access_count(0),
-      call_NowMicros_every_N_records_(100),
-      mutex_() {
-  Status s = env->GetAbsolutePath(dbname, &db_absolute_path_);
-  if (s.IsNotSupported()) {
-    db_absolute_path_ = dbname;
-  } else {
-    status_ = s;
-  }
-  log_fname_ = InfoLogFileName(dbname_, db_absolute_path_, db_log_dir_);
-  if (env_->FileExists(log_fname_).ok()) {
-    RollLogFile();
-  }
-  GetExistingFiles();
-  ResetLogger();
-  if (status_.ok()) {
-    status_ = TrimOldLogFiles();
-  }
-}
-
 Status AutoRollLogger::ResetLogger() {
   TEST_SYNC_POINT("AutoRollLogger::ResetLogger:BeforeNewLogger");
   status_ = env_->NewLogger(log_fname_, &logger_);
@@ -85,58 +44,6 @@ void AutoRollLogger::RollLogFile() {
     now++;
   } while (env_->FileExists(old_fname).ok());
   env_->RenameFile(log_fname_, old_fname);
-  old_log_files_.push(old_fname);
-}
-
-void AutoRollLogger::GetExistingFiles() {
-  {
-    // Empty the queue to avoid duplicated entries in the queue.
-    std::queue<std::string> empty;
-    std::swap(old_log_files_, empty);
-  }
-
-  std::string parent_dir;
-  std::vector<std::string> info_log_files;
-  Status s =
-      GetInfoLogFiles(env_, db_log_dir_, dbname_, &parent_dir, &info_log_files);
-  if (status_.ok()) {
-    status_ = s;
-  }
-  // We need to sort the file before enqueing it so that when we
-  // delete file from the front, it is the oldest file.
-  std::sort(info_log_files.begin(), info_log_files.end());
-
-  for (const std::string& f : info_log_files) {
-    old_log_files_.push(parent_dir + "/" + f);
-  }
-}
-
-Status AutoRollLogger::TrimOldLogFiles() {
-  // Here we directly list info files and delete them through Env.
-  // The deletion isn't going through DB, so there are shortcomes:
-  // 1. the deletion is not rate limited by SstFileManager
-  // 2. there is a chance that an I/O will be issued here
-  // Since it's going to be complicated to pass DB object down to
-  // here, we take a simple approach to keep the code easier to
-  // maintain.
-
-  // old_log_files_.empty() is helpful for the corner case that
-  // kKeepLogFileNum == 0. We can instead check kKeepLogFileNum != 0 but
-  // it's essentially the same thing, and checking empty before accessing
-  // the queue feels safer.
-  while (!old_log_files_.empty() && old_log_files_.size() >= kKeepLogFileNum) {
-    Status s = env_->DeleteFile(old_log_files_.front());
-    // Remove the file from the tracking anyway. It's possible that
-    // DB cleaned up the old log file, or people cleaned it up manually.
-    old_log_files_.pop();
-    // To make the file really go away, we should sync parent directory.
-    // Since there isn't any consistency issue involved here, skipping
-    // this part to avoid one I/O here.
-    if (!s.ok()) {
-      return s;
-    }
-  }
-  return Status::OK();
 }
 
 std::string AutoRollLogger::ValistToString(const char* format,
@@ -155,11 +62,6 @@ std::string AutoRollLogger::ValistToString(const char* format,
 
 void AutoRollLogger::LogInternal(const char* format, ...) {
   mutex_.AssertHeld();
-
-  if (!logger_) {
-    return;
-  }
-
   va_list args;
   va_start(args, format);
   logger_->Logv(format, args);
@@ -168,9 +70,6 @@ void AutoRollLogger::LogInternal(const char* format, ...) {
 
 void AutoRollLogger::Logv(const char* format, va_list ap) {
   assert(GetStatus().ok());
-  if (!logger_) {
-    return;
-  }
 
   std::shared_ptr<Logger> logger;
   {
@@ -179,19 +78,12 @@ void AutoRollLogger::Logv(const char* format, va_list ap) {
         (kMaxLogFileSize > 0 && logger_->GetLogFileSize() >= kMaxLogFileSize)) {
       RollLogFile();
       Status s = ResetLogger();
-      Status s2 = TrimOldLogFiles();
-
       if (!s.ok()) {
         // can't really log the error if creating a new LOG file failed
         return;
       }
 
       WriteHeaderInfo();
-
-      if (!s2.ok()) {
-        ROCKS_LOG_WARN(logger.get(), "Fail to trim old info log file: %s",
-                       s2.ToString().c_str());
-      }
     }
 
     // pin down the current logger_ instance before releasing the mutex.
@@ -215,10 +107,6 @@ void AutoRollLogger::WriteHeaderInfo() {
 }
 
 void AutoRollLogger::LogHeader(const char* format, va_list args) {
-  if (!logger_) {
-    return;
-  }
-
   // header message are to be retained in memory. Since we cannot make any
   // assumptions about the data contained in va_list, we will retain them as
   // strings
@@ -265,8 +153,7 @@ Status CreateLoggerFromOptions(const std::string& dbname,
   if (options.log_file_time_to_roll > 0 || options.max_log_file_size > 0) {
     AutoRollLogger* result = new AutoRollLogger(
         env, dbname, options.db_log_dir, options.max_log_file_size,
-        options.log_file_time_to_roll, options.keep_log_file_num,
-        options.info_log_level);
+        options.log_file_time_to_roll, options.info_log_level);
     Status s = result->GetStatus();
     if (!s.ok()) {
       delete result;

db/auto_roll_logger.h

@@ -8,13 +8,12 @@
 
 #pragma once
 #include <list>
-#include <queue>
 #include <string>
 
-#include "file/filename.h"
+#include "db/filename.h"
 #include "port/port.h"
 #include "port/util_logger.h"
-#include "test_util/sync_point.h"
+#include "util/sync_point.h"
 #include "util/mutexlock.h"
 
 namespace rocksdb {
@@ -25,8 +24,25 @@ class AutoRollLogger : public Logger {
  public:
   AutoRollLogger(Env* env, const std::string& dbname,
                  const std::string& db_log_dir, size_t log_max_size,
-                 size_t log_file_time_to_roll, size_t keep_log_file_num,
-                 const InfoLogLevel log_level = InfoLogLevel::INFO_LEVEL);
+                 size_t log_file_time_to_roll,
+                 const InfoLogLevel log_level = InfoLogLevel::INFO_LEVEL)
+      : Logger(log_level),
+        dbname_(dbname),
+        db_log_dir_(db_log_dir),
+        env_(env),
+        status_(Status::OK()),
+        kMaxLogFileSize(log_max_size),
+        kLogFileTimeToRoll(log_file_time_to_roll),
+        cached_now(static_cast<uint64_t>(env_->NowMicros() * 1e-6)),
+        ctime_(cached_now),
+        cached_now_access_count(0),
+        call_NowMicros_every_N_records_(100),
+        mutex_() {
+    env->GetAbsolutePath(dbname, &db_absolute_path_);
+    log_fname_ = InfoLogFileName(dbname_, db_absolute_path_, db_log_dir_);
+    RollLogFile();
+    ResetLogger();
+  }
 
   using Logger::Logv;
   void Logv(const char* format, va_list ap) override;
@@ -41,10 +57,6 @@ class AutoRollLogger : public Logger {
   }
 
   size_t GetLogFileSize() const override {
-    if (!logger_) {
-      return 0;
-    }
-
     std::shared_ptr<Logger> logger;
     {
       MutexLock l(&mutex_);
@@ -68,9 +80,6 @@ class AutoRollLogger : public Logger {
   }
 
   virtual ~AutoRollLogger() {
-    if (logger_ && !closed_) {
-      logger_->Close();
-    }
   }
 
   void SetCallNowMicrosEveryNRecords(uint64_t call_NowMicros_every_N_records) {
@@ -82,33 +91,17 @@ class AutoRollLogger : public Logger {
     return log_fname_;
   }
 
-  uint64_t TEST_ctime() const { return ctime_; }
-
- protected:
-  // Implementation of Close()
-  virtual Status CloseImpl() override {
-    if (logger_) {
-      return logger_->Close();
-    } else {
-      return Status::OK();
-    }
-  }
-
  private:
   bool LogExpired();
   Status ResetLogger();
   void RollLogFile();
-  // Read all names of old log files into old_log_files_
-  // If there is any error, put the error code in status_
-  void GetExistingFiles();
-  // Delete old log files if it excceeds the limit.
-  Status TrimOldLogFiles();
   // Log message to logger without rolling
   void LogInternal(const char* format, ...);
   // Serialize the va_list to a string
   std::string ValistToString(const char* format, va_list args) const;
   // Write the logs marked as headers to the new log file
   void WriteHeaderInfo();
+
   std::string log_fname_; // Current active info log's file name.
   std::string dbname_;
   std::string db_log_dir_;
@@ -119,14 +112,8 @@ class AutoRollLogger : public Logger {
   Status status_;
   const size_t kMaxLogFileSize;
   const size_t kLogFileTimeToRoll;
-  const size_t kKeepLogFileNum;
   // header information
   std::list<std::string> headers_;
-  // List of all existing info log files. Used for enforcing number of
-  // info log files.
-  // Full path is stored here. It consumes signifianctly more memory
-  // than only storing file name. Can optimize if it causes a problem.
-  std::queue<std::string> old_log_files_;
   // to avoid frequent env->NowMicros() calls, we cached the current time
   uint64_t cached_now;
   uint64_t ctime_;

db/auto_roll_logger_test.cc

@@ -6,56 +6,23 @@
 
 #ifndef ROCKSDB_LITE
 
-#include "logging/auto_roll_logger.h"
-#include <errno.h>
-#include <sys/stat.h>
-#include <algorithm>
-#include <cmath>
-#include <fstream>
-#include <iostream>
-#include <iterator>
 #include <string>
 #include <thread>
 #include <vector>
-#include "logging/logging.h"
+#include <cmath>
+#include <iostream>
+#include <fstream>
+#include <iterator>
+#include <algorithm>
+#include "db/auto_roll_logger.h"
 #include "port/port.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
 #include "rocksdb/db.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include <sys/stat.h>
+#include <errno.h>
 
 namespace rocksdb {
-namespace {
-class NoSleepEnv : public EnvWrapper {
- public:
-  NoSleepEnv(Env* base) : EnvWrapper(base) {}
-  void SleepForMicroseconds(int micros) override {
-    fake_time_ += static_cast<uint64_t>(micros);
-  }
-
-  uint64_t NowNanos() override { return fake_time_ * 1000; }
-
-  uint64_t NowMicros() override { return fake_time_; }
-
- private:
-  uint64_t fake_time_ = 6666666666;
-};
-}  // namespace
-
-// In this test we only want to Log some simple log message with
-// no format. LogMessage() provides such a simple interface and
-// avoids the [format-security] warning which occurs when you
-// call ROCKS_LOG_INFO(logger, log_message) directly.
-namespace {
-void LogMessage(Logger* logger, const char* message) {
-  ROCKS_LOG_INFO(logger, "%s", message);
-}
-
-void LogMessage(const InfoLogLevel log_level, Logger* logger,
-                const char* message) {
-  Log(log_level, logger, "%s", message);
-}
-}  // namespace
 
 class AutoRollLoggerTest : public testing::Test {
  public:
@@ -76,57 +43,46 @@ class AutoRollLoggerTest : public testing::Test {
 
   void RollLogFileBySizeTest(AutoRollLogger* logger, size_t log_max_size,
                              const std::string& log_message);
-  void RollLogFileByTimeTest(Env*, AutoRollLogger* logger, size_t time,
-                             const std::string& log_message);
-  // return list of files under kTestDir that contains "LOG"
-  std::vector<std::string> GetLogFiles() {
-    std::vector<std::string> ret;
-    std::vector<std::string> files;
-    Status s = default_env->GetChildren(kTestDir, &files);
-    // Should call ASSERT_OK() here but it doesn't compile. It's not
-    // worth the time figuring out why.
-    EXPECT_TRUE(s.ok());
-    for (const auto& f : files) {
-      if (f.find("LOG") != std::string::npos) {
-        ret.push_back(f);
-      }
-    }
-    return ret;
-  }
-
-  // Delete all log files under kTestDir
-  void CleanupLogFiles() {
-    for (const std::string& f : GetLogFiles()) {
-      ASSERT_OK(default_env->DeleteFile(kTestDir + "/" + f));
-    }
-  }
-
-  void RollNTimesBySize(Logger* auto_roll_logger, size_t file_num,
-                        size_t max_log_file_size) {
-    // Roll the log 4 times, and it will trim to 3 files.
-    std::string dummy_large_string;
-    dummy_large_string.assign(max_log_file_size, '=');
-    auto_roll_logger->SetInfoLogLevel(InfoLogLevel::INFO_LEVEL);
-    for (size_t i = 0; i < file_num + 1; i++) {
-      // Log enough bytes to trigger at least one roll.
-      LogMessage(auto_roll_logger, dummy_large_string.c_str());
-      LogMessage(auto_roll_logger, "");
-    }
-  }
+  uint64_t RollLogFileByTimeTest(AutoRollLogger* logger, size_t time,
+                                 const std::string& log_message);
 
   static const std::string kSampleMessage;
   static const std::string kTestDir;
   static const std::string kLogFile;
-  static Env* default_env;
+  static Env* env;
 };
 
 const std::string AutoRollLoggerTest::kSampleMessage(
     "this is the message to be written to the log file!!");
-const std::string AutoRollLoggerTest::kTestDir(
-    test::PerThreadDBPath("db_log_test"));
-const std::string AutoRollLoggerTest::kLogFile(
-    test::PerThreadDBPath("db_log_test") + "/LOG");
-Env* AutoRollLoggerTest::default_env = Env::Default();
+const std::string AutoRollLoggerTest::kTestDir(test::TmpDir() + "/db_log_test");
+const std::string AutoRollLoggerTest::kLogFile(test::TmpDir() +
+                                               "/db_log_test/LOG");
+Env* AutoRollLoggerTest::env = Env::Default();
+
+// In this test we only want to Log some simple log message with
+// no format. LogMessage() provides such a simple interface and
+// avoids the [format-security] warning which occurs when you
+// call Log(logger, log_message) directly.
+namespace {
+void LogMessage(Logger* logger, const char* message) {
+  Log(logger, "%s", message);
+}
+
+void LogMessage(const InfoLogLevel log_level, Logger* logger,
+                const char* message) {
+  Log(log_level, logger, "%s", message);
+}
+}  // namespace
+
+namespace {
+void GetFileCreateTime(const std::string& fname, uint64_t* file_ctime) {
+  struct stat s;
+  if (stat(fname.c_str(), &s) != 0) {
+    *file_ctime = (uint64_t)0;
+  }
+  *file_ctime = static_cast<uint64_t>(s.st_ctime);
+}
+}  // namespace
 
 void AutoRollLoggerTest::RollLogFileBySizeTest(AutoRollLogger* logger,
                                                size_t log_max_size,
@@ -154,71 +110,68 @@ void AutoRollLoggerTest::RollLogFileBySizeTest(AutoRollLogger* logger,
   ASSERT_TRUE(message_size == logger->GetLogFileSize());
 }
 
-void AutoRollLoggerTest::RollLogFileByTimeTest(Env* env, AutoRollLogger* logger,
-                                               size_t time,
-                                               const std::string& log_message) {
-  uint64_t expected_ctime;
-  uint64_t actual_ctime;
-
+uint64_t AutoRollLoggerTest::RollLogFileByTimeTest(
+    AutoRollLogger* logger, size_t time, const std::string& log_message) {
+  uint64_t expected_create_time;
+  uint64_t actual_create_time;
   uint64_t total_log_size;
   EXPECT_OK(env->GetFileSize(kLogFile, &total_log_size));
-  expected_ctime = logger->TEST_ctime();
+  GetFileCreateTime(kLogFile, &expected_create_time);
   logger->SetCallNowMicrosEveryNRecords(0);
 
   // -- Write to the log for several times, which is supposed
   // to be finished before time.
   for (int i = 0; i < 10; ++i) {
-    env->SleepForMicroseconds(50000);
-    LogMessage(logger, log_message.c_str());
-    EXPECT_OK(logger->GetStatus());
-    // Make sure we always write to the same log file (by
-    // checking the create time);
+     LogMessage(logger, log_message.c_str());
+     EXPECT_OK(logger->GetStatus());
+     // Make sure we always write to the same log file (by
+     // checking the create time);
+     GetFileCreateTime(kLogFile, &actual_create_time);
 
-    actual_ctime = logger->TEST_ctime();
-
-    // Also make sure the log size is increasing.
-    EXPECT_EQ(expected_ctime, actual_ctime);
-    EXPECT_GT(logger->GetLogFileSize(), total_log_size);
-    total_log_size = logger->GetLogFileSize();
+     // Also make sure the log size is increasing.
+     EXPECT_EQ(expected_create_time, actual_create_time);
+     EXPECT_GT(logger->GetLogFileSize(), total_log_size);
+     total_log_size = logger->GetLogFileSize();
   }
 
   // -- Make the log file expire
-  env->SleepForMicroseconds(static_cast<int>(time * 1000000));
+#ifdef OS_WIN
+  Sleep(static_cast<unsigned int>(time) * 1000);
+#else
+  sleep(static_cast<unsigned int>(time));
+#endif
   LogMessage(logger, log_message.c_str());
 
   // At this time, the new log file should be created.
-  actual_ctime = logger->TEST_ctime();
-  EXPECT_LT(expected_ctime, actual_ctime);
+  GetFileCreateTime(kLogFile, &actual_create_time);
+  EXPECT_GT(actual_create_time, expected_create_time);
   EXPECT_LT(logger->GetLogFileSize(), total_log_size);
+  expected_create_time = actual_create_time;
+
+  return expected_create_time;
 }
 
 TEST_F(AutoRollLoggerTest, RollLogFileBySize) {
     InitTestDb();
     size_t log_max_size = 1024 * 5;
-    size_t keep_log_file_num = 10;
 
-    AutoRollLogger logger(Env::Default(), kTestDir, "", log_max_size, 0,
-                          keep_log_file_num);
+    AutoRollLogger logger(Env::Default(), kTestDir, "", log_max_size, 0);
 
     RollLogFileBySizeTest(&logger, log_max_size,
                           kSampleMessage + ":RollLogFileBySize");
 }
 
 TEST_F(AutoRollLoggerTest, RollLogFileByTime) {
-  NoSleepEnv nse(Env::Default());
+    size_t time = 2;
+    size_t log_size = 1024 * 5;
 
-  size_t time = 2;
-  size_t log_size = 1024 * 5;
-  size_t keep_log_file_num = 10;
+    InitTestDb();
+    // -- Test the existence of file during the server restart.
+    ASSERT_EQ(Status::NotFound(), env->FileExists(kLogFile));
+    AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, time);
+    ASSERT_OK(env->FileExists(kLogFile));
 
-  InitTestDb();
-  // -- Test the existence of file during the server restart.
-  ASSERT_EQ(Status::NotFound(), default_env->FileExists(kLogFile));
-  AutoRollLogger logger(&nse, kTestDir, "", log_size, time, keep_log_file_num);
-  ASSERT_OK(default_env->FileExists(kLogFile));
-
-  RollLogFileByTimeTest(&nse, &logger, time,
-                        kSampleMessage + ":RollLogFileByTime");
+    RollLogFileByTimeTest(&logger, time, kSampleMessage + ":RollLogFileByTime");
 }
 
 TEST_F(AutoRollLoggerTest, OpenLogFilesMultipleTimesWithOptionLog_max_size) {
@@ -231,38 +184,36 @@ TEST_F(AutoRollLoggerTest, OpenLogFilesMultipleTimesWithOptionLog_max_size) {
   // treated as "singed".
   size_t kZero = 0;
   size_t log_size = 1024;
-  size_t keep_log_file_num = 10;
 
-  AutoRollLogger* logger = new AutoRollLogger(Env::Default(), kTestDir, "",
-                                              log_size, 0, keep_log_file_num);
+  AutoRollLogger* logger = new AutoRollLogger(
+    Env::Default(), kTestDir, "", log_size, 0);
 
   LogMessage(logger, kSampleMessage.c_str());
   ASSERT_GT(logger->GetLogFileSize(), kZero);
   delete logger;
 
   // reopens the log file and an empty log file will be created.
-  logger = new AutoRollLogger(Env::Default(), kTestDir, "", log_size, 0, 10);
+  logger = new AutoRollLogger(
+    Env::Default(), kTestDir, "", log_size, 0);
   ASSERT_EQ(logger->GetLogFileSize(), kZero);
   delete logger;
 }
 
 TEST_F(AutoRollLoggerTest, CompositeRollByTimeAndSizeLogger) {
   size_t time = 2, log_max_size = 1024 * 5;
-  size_t keep_log_file_num = 10;
 
   InitTestDb();
 
-  NoSleepEnv nse(Env::Default());
-  AutoRollLogger logger(&nse, kTestDir, "", log_max_size, time,
-                        keep_log_file_num);
+  AutoRollLogger logger(Env::Default(), kTestDir, "", log_max_size, time);
 
   // Test the ability to roll by size
-  RollLogFileBySizeTest(&logger, log_max_size,
-                        kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
+  RollLogFileBySizeTest(
+      &logger, log_max_size,
+      kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
 
   // Test the ability to roll by Time
-  RollLogFileByTimeTest(&nse, &logger, time,
-                        kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
+  RollLogFileByTimeTest( &logger, time,
+      kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
 }
 
 #ifndef OS_WIN
@@ -270,8 +221,7 @@ TEST_F(AutoRollLoggerTest, CompositeRollByTimeAndSizeLogger) {
 // port
 TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
   DBOptions options;
-  NoSleepEnv nse(Env::Default());
-  std::shared_ptr<Logger> logger;
+  shared_ptr<Logger> logger;
 
   // Normal logger
   ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
@@ -289,15 +239,15 @@ TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
       kSampleMessage + ":CreateLoggerFromOptions - size");
 
   // Only roll by Time
-  options.env = &nse;
   InitTestDb();
   options.max_log_file_size = 0;
   options.log_file_time_to_roll = 2;
   ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
   auto_roll_logger =
     dynamic_cast<AutoRollLogger*>(logger.get());
-  RollLogFileByTimeTest(&nse, auto_roll_logger, options.log_file_time_to_roll,
-                        kSampleMessage + ":CreateLoggerFromOptions - time");
+  RollLogFileByTimeTest(
+      auto_roll_logger, options.log_file_time_to_roll,
+      kSampleMessage + ":CreateLoggerFromOptions - time");
 
   // roll by both Time and size
   InitTestDb();
@@ -306,116 +256,17 @@ TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
   ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
   auto_roll_logger =
     dynamic_cast<AutoRollLogger*>(logger.get());
-  RollLogFileBySizeTest(auto_roll_logger, options.max_log_file_size,
-                        kSampleMessage + ":CreateLoggerFromOptions - both");
-  RollLogFileByTimeTest(&nse, auto_roll_logger, options.log_file_time_to_roll,
-                        kSampleMessage + ":CreateLoggerFromOptions - both");
-
-  // Set keep_log_file_num
-  {
-    const size_t kFileNum = 3;
-    InitTestDb();
-    options.max_log_file_size = 512;
-    options.log_file_time_to_roll = 2;
-    options.keep_log_file_num = kFileNum;
-    ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
-    auto_roll_logger = dynamic_cast<AutoRollLogger*>(logger.get());
-
-    // Roll the log 4 times, and it will trim to 3 files.
-    std::string dummy_large_string;
-    dummy_large_string.assign(options.max_log_file_size, '=');
-    auto_roll_logger->SetInfoLogLevel(InfoLogLevel::INFO_LEVEL);
-    for (size_t i = 0; i < kFileNum + 1; i++) {
-      // Log enough bytes to trigger at least one roll.
-      LogMessage(auto_roll_logger, dummy_large_string.c_str());
-      LogMessage(auto_roll_logger, "");
-    }
-
-    std::vector<std::string> files = GetLogFiles();
-    ASSERT_EQ(kFileNum, files.size());
-
-    CleanupLogFiles();
-  }
-
-  // Set keep_log_file_num and dbname is different from
-  // db_log_dir.
-  {
-    const size_t kFileNum = 3;
-    InitTestDb();
-    options.max_log_file_size = 512;
-    options.log_file_time_to_roll = 2;
-    options.keep_log_file_num = kFileNum;
-    options.db_log_dir = kTestDir;
-    ASSERT_OK(CreateLoggerFromOptions("/dummy/db/name", options, &logger));
-    auto_roll_logger = dynamic_cast<AutoRollLogger*>(logger.get());
-
-    // Roll the log 4 times, and it will trim to 3 files.
-    std::string dummy_large_string;
-    dummy_large_string.assign(options.max_log_file_size, '=');
-    auto_roll_logger->SetInfoLogLevel(InfoLogLevel::INFO_LEVEL);
-    for (size_t i = 0; i < kFileNum + 1; i++) {
-      // Log enough bytes to trigger at least one roll.
-      LogMessage(auto_roll_logger, dummy_large_string.c_str());
-      LogMessage(auto_roll_logger, "");
-    }
-
-    std::vector<std::string> files = GetLogFiles();
-    ASSERT_EQ(kFileNum, files.size());
-    for (const auto& f : files) {
-      ASSERT_TRUE(f.find("dummy") != std::string::npos);
-    }
-
-    // Cleaning up those files.
-    CleanupLogFiles();
-  }
-}
-
-TEST_F(AutoRollLoggerTest, AutoDeleting) {
-  for (int attempt = 0; attempt < 2; attempt++) {
-    // In the first attemp, db_log_dir is not set, while in the
-    // second it is set.
-    std::string dbname = (attempt == 0) ? kTestDir : "/test/dummy/dir";
-    std::string db_log_dir = (attempt == 0) ? "" : kTestDir;
-
-    InitTestDb();
-    const size_t kMaxFileSize = 512;
-    {
-      size_t log_num = 8;
-      AutoRollLogger logger(Env::Default(), dbname, db_log_dir, kMaxFileSize, 0,
-                            log_num);
-      RollNTimesBySize(&logger, log_num, kMaxFileSize);
-
-      ASSERT_EQ(log_num, GetLogFiles().size());
-    }
-    // Shrink number of files
-    {
-      size_t log_num = 5;
-      AutoRollLogger logger(Env::Default(), dbname, db_log_dir, kMaxFileSize, 0,
-                            log_num);
-      ASSERT_EQ(log_num, GetLogFiles().size());
-
-      RollNTimesBySize(&logger, 3, kMaxFileSize);
-      ASSERT_EQ(log_num, GetLogFiles().size());
-    }
-
-    // Increase number of files again.
-    {
-      size_t log_num = 7;
-      AutoRollLogger logger(Env::Default(), dbname, db_log_dir, kMaxFileSize, 0,
-                            log_num);
-      ASSERT_EQ(6, GetLogFiles().size());
-
-      RollNTimesBySize(&logger, 3, kMaxFileSize);
-      ASSERT_EQ(log_num, GetLogFiles().size());
-    }
-
-    CleanupLogFiles();
-  }
+  RollLogFileBySizeTest(
+      auto_roll_logger, options.max_log_file_size,
+      kSampleMessage + ":CreateLoggerFromOptions - both");
+  RollLogFileByTimeTest(
+      auto_roll_logger, options.log_file_time_to_roll,
+      kSampleMessage + ":CreateLoggerFromOptions - both");
 }
 
 TEST_F(AutoRollLoggerTest, LogFlushWhileRolling) {
   DBOptions options;
-  std::shared_ptr<Logger> logger;
+  shared_ptr<Logger> logger;
 
   InitTestDb();
   options.max_log_file_size = 1024 * 5;
@@ -445,7 +296,7 @@ TEST_F(AutoRollLoggerTest, LogFlushWhileRolling) {
        {"AutoRollLogger::Flush:PinnedLogger", "PosixLogger::Flush:Begin2"}});
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  flush_thread = port::Thread([&]() { auto_roll_logger->Flush(); });
+  flush_thread = port::Thread ([&]() { auto_roll_logger->Flush(); });
   TEST_SYNC_POINT(
       "AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit");
   RollLogFileBySizeTest(auto_roll_logger, options.max_log_file_size,
@@ -464,7 +315,7 @@ TEST_F(AutoRollLoggerTest, InfoLogLevel) {
   // an extra-scope to force the AutoRollLogger to flush the log file when it
   // becomes out of scope.
   {
-    AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, 0, 10);
+    AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, 0);
     for (int log_level = InfoLogLevel::HEADER_LEVEL;
          log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
       logger.SetInfoLogLevel((InfoLogLevel)log_level);
@@ -481,12 +332,12 @@ TEST_F(AutoRollLoggerTest, InfoLogLevel) {
       logger.SetInfoLogLevel((InfoLogLevel)log_level);
 
       // again, messages with level smaller than log_level will not be logged.
-      ROCKS_LOG_HEADER(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_DEBUG(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_INFO(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_WARN(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_ERROR(&logger, "%s", kSampleMessage.c_str());
-      ROCKS_LOG_FATAL(&logger, "%s", kSampleMessage.c_str());
+      Log(InfoLogLevel::HEADER_LEVEL, &logger, "%s", kSampleMessage.c_str());
+      Debug(&logger, "%s", kSampleMessage.c_str());
+      Info(&logger, "%s", kSampleMessage.c_str());
+      Warn(&logger, "%s", kSampleMessage.c_str());
+      Error(&logger, "%s", kSampleMessage.c_str());
+      Fatal(&logger, "%s", kSampleMessage.c_str());
       log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
     }
   }
@@ -497,45 +348,6 @@ TEST_F(AutoRollLoggerTest, InfoLogLevel) {
   inFile.close();
 }
 
-TEST_F(AutoRollLoggerTest, Close) {
-  InitTestDb();
-
-  size_t log_size = 8192;
-  size_t log_lines = 0;
-  AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, 0, 10);
-  for (int log_level = InfoLogLevel::HEADER_LEVEL;
-       log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
-    logger.SetInfoLogLevel((InfoLogLevel)log_level);
-    for (int log_type = InfoLogLevel::DEBUG_LEVEL;
-         log_type <= InfoLogLevel::HEADER_LEVEL; log_type++) {
-      // log messages with log level smaller than log_level will not be
-      // logged.
-      LogMessage((InfoLogLevel)log_type, &logger, kSampleMessage.c_str());
-    }
-    log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
-  }
-  for (int log_level = InfoLogLevel::HEADER_LEVEL;
-       log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
-    logger.SetInfoLogLevel((InfoLogLevel)log_level);
-
-    // again, messages with level smaller than log_level will not be logged.
-    ROCKS_LOG_HEADER(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_DEBUG(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_INFO(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_WARN(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_ERROR(&logger, "%s", kSampleMessage.c_str());
-    ROCKS_LOG_FATAL(&logger, "%s", kSampleMessage.c_str());
-    log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
-  }
-  ASSERT_EQ(logger.Close(), Status::OK());
-
-  std::ifstream inFile(AutoRollLoggerTest::kLogFile.c_str());
-  size_t lines = std::count(std::istreambuf_iterator<char>(inFile),
-                         std::istreambuf_iterator<char>(), '\n');
-  ASSERT_EQ(log_lines, lines);
-  inFile.close();
-}
-
 // Test the logger Header function for roll over logs
 // We expect the new logs creates as roll over to carry the headers specified
 static std::vector<std::string> GetOldFileNames(const std::string& path) {
@@ -558,6 +370,25 @@ static std::vector<std::string> GetOldFileNames(const std::string& path) {
   return ret;
 }
 
+// Return the number of lines where a given pattern was found in the file
+static size_t GetLinesCount(const std::string& fname,
+                            const std::string& pattern) {
+  std::stringstream ssbuf;
+  std::string line;
+  size_t count = 0;
+
+  std::ifstream inFile(fname.c_str());
+  ssbuf << inFile.rdbuf();
+
+  while (getline(ssbuf, line)) {
+    if (line.find(pattern) != std::string::npos) {
+      count++;
+    }
+  }
+
+  return count;
+}
+
 TEST_F(AutoRollLoggerTest, LogHeaderTest) {
   static const size_t MAX_HEADERS = 10;
   static const size_t LOG_MAX_SIZE = 1024 * 5;
@@ -569,19 +400,19 @@ TEST_F(AutoRollLoggerTest, LogHeaderTest) {
 
     InitTestDb();
 
-    AutoRollLogger logger(Env::Default(), kTestDir, /*db_log_dir=*/"",
-                          LOG_MAX_SIZE, /*log_file_time_to_roll=*/0,
-                          /*keep_log_file_num=*/10);
+    AutoRollLogger logger(Env::Default(), kTestDir, /*db_log_dir=*/ "",
+                          LOG_MAX_SIZE, /*log_file_time_to_roll=*/ 0);
 
     if (test_num == 0) {
       // Log some headers explicitly using Header()
       for (size_t i = 0; i < MAX_HEADERS; i++) {
-        Header(&logger, "%s %" ROCKSDB_PRIszt, HEADER_STR.c_str(), i);
+        Header(&logger, "%s %d", HEADER_STR.c_str(), i);
       }
     } else if (test_num == 1) {
       // HEADER_LEVEL should make this behave like calling Header()
       for (size_t i = 0; i < MAX_HEADERS; i++) {
-        ROCKS_LOG_HEADER(&logger, "%s %" ROCKSDB_PRIszt, HEADER_STR.c_str(), i);
+        Log(InfoLogLevel::HEADER_LEVEL, &logger, "%s %d",
+            HEADER_STR.c_str(), i);
       }
     }
 
@@ -609,7 +440,7 @@ TEST_F(AutoRollLoggerTest, LogHeaderTest) {
       // verify that the files rolled over
       ASSERT_NE(oldfname, newfname);
       // verify that the old log contains all the header logs
-      ASSERT_EQ(test::GetLinesCount(oldfname, HEADER_STR), MAX_HEADERS);
+      ASSERT_EQ(GetLinesCount(oldfname, HEADER_STR), MAX_HEADERS);
     }
   }
 }
@@ -631,19 +462,10 @@ TEST_F(AutoRollLoggerTest, LogFileExistence) {
   options.max_log_file_size = 100 * 1024 * 1024;
   options.create_if_missing = true;
   ASSERT_OK(rocksdb::DB::Open(options, kTestDir, &db));
-  ASSERT_OK(default_env->FileExists(kLogFile));
+  ASSERT_OK(env->FileExists(kLogFile));
   delete db;
 }
 
-TEST_F(AutoRollLoggerTest, FileCreateFailure) {
-  Options options;
-  options.max_log_file_size = 100 * 1024 * 1024;
-  options.db_log_dir = "/a/dir/does/not/exist/at/all";
-
-  std::shared_ptr<Logger> logger;
-  ASSERT_NOK(CreateLoggerFromOptions("", options, &logger));
-  ASSERT_TRUE(!logger);
-}
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
@@ -654,7 +476,7 @@ 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 AutoRollLogger is not supported in ROCKSDB_LITE\n");
   return 0;

db/blob_index.h

@@ -1,179 +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).
-#pragma once
-#ifndef ROCKSDB_LITE
-
-#include <sstream>
-#include <string>
-
-#include "rocksdb/options.h"
-#include "util/coding.h"
-#include "util/string_util.h"
-
-namespace rocksdb {
-
-// BlobIndex is a pointer to the blob and metadata of the blob. The index is
-// stored in base DB as ValueType::kTypeBlobIndex.
-// There are three types of blob index:
-//
-//    kInlinedTTL:
-//      +------+------------+---------------+
-//      | type | expiration | value         |
-//      +------+------------+---------------+
-//      | char | varint64   | variable size |
-//      +------+------------+---------------+
-//
-//    kBlob:
-//      +------+-------------+----------+----------+-------------+
-//      | type | file number | offset   | size     | compression |
-//      +------+-------------+----------+----------+-------------+
-//      | char | varint64    | varint64 | varint64 | char        |
-//      +------+-------------+----------+----------+-------------+
-//
-//    kBlobTTL:
-//      +------+------------+-------------+----------+----------+-------------+
-//      | type | expiration | file number | offset   | size     | compression |
-//      +------+------------+-------------+----------+----------+-------------+
-//      | char | varint64   | varint64    | varint64 | varint64 | char        |
-//      +------+------------+-------------+----------+----------+-------------+
-//
-// There isn't a kInlined (without TTL) type since we can store it as a plain
-// value (i.e. ValueType::kTypeValue).
-class BlobIndex {
- public:
-  enum class Type : unsigned char {
-    kInlinedTTL = 0,
-    kBlob = 1,
-    kBlobTTL = 2,
-    kUnknown = 3,
-  };
-
-  BlobIndex() : type_(Type::kUnknown) {}
-
-  bool IsInlined() const { return type_ == Type::kInlinedTTL; }
-
-  bool HasTTL() const {
-    return type_ == Type::kInlinedTTL || type_ == Type::kBlobTTL;
-  }
-
-  uint64_t expiration() const {
-    assert(HasTTL());
-    return expiration_;
-  }
-
-  const Slice& value() const {
-    assert(IsInlined());
-    return value_;
-  }
-
-  uint64_t file_number() const {
-    assert(!IsInlined());
-    return file_number_;
-  }
-
-  uint64_t offset() const {
-    assert(!IsInlined());
-    return offset_;
-  }
-
-  uint64_t size() const {
-    assert(!IsInlined());
-    return size_;
-  }
-
-  Status DecodeFrom(Slice slice) {
-    static const std::string kErrorMessage = "Error while decoding blob index";
-    assert(slice.size() > 0);
-    type_ = static_cast<Type>(*slice.data());
-    if (type_ >= Type::kUnknown) {
-      return Status::Corruption(
-          kErrorMessage,
-          "Unknown blob index type: " + ToString(static_cast<char>(type_)));
-    }
-    slice = Slice(slice.data() + 1, slice.size() - 1);
-    if (HasTTL()) {
-      if (!GetVarint64(&slice, &expiration_)) {
-        return Status::Corruption(kErrorMessage, "Corrupted expiration");
-      }
-    }
-    if (IsInlined()) {
-      value_ = slice;
-    } else {
-      if (GetVarint64(&slice, &file_number_) && GetVarint64(&slice, &offset_) &&
-          GetVarint64(&slice, &size_) && slice.size() == 1) {
-        compression_ = static_cast<CompressionType>(*slice.data());
-      } else {
-        return Status::Corruption(kErrorMessage, "Corrupted blob offset");
-      }
-    }
-    return Status::OK();
-  }
-
-  std::string DebugString(bool output_hex) const {
-    std::ostringstream oss;
-
-    if (IsInlined()) {
-      oss << "[inlined blob] value:" << value_.ToString(output_hex);
-    } else {
-      oss << "[blob ref] file:" << file_number_ << " offset:" << offset_
-          << " size:" << size_;
-    }
-
-    if (HasTTL()) {
-      oss << " exp:" << expiration_;
-    }
-
-    return oss.str();
-  }
-
-  static void EncodeInlinedTTL(std::string* dst, uint64_t expiration,
-                               const Slice& value) {
-    assert(dst != nullptr);
-    dst->clear();
-    dst->reserve(1 + kMaxVarint64Length + value.size());
-    dst->push_back(static_cast<char>(Type::kInlinedTTL));
-    PutVarint64(dst, expiration);
-    dst->append(value.data(), value.size());
-  }
-
-  static void EncodeBlob(std::string* dst, uint64_t file_number,
-                         uint64_t offset, uint64_t size,
-                         CompressionType compression) {
-    assert(dst != nullptr);
-    dst->clear();
-    dst->reserve(kMaxVarint64Length * 3 + 2);
-    dst->push_back(static_cast<char>(Type::kBlob));
-    PutVarint64(dst, file_number);
-    PutVarint64(dst, offset);
-    PutVarint64(dst, size);
-    dst->push_back(static_cast<char>(compression));
-  }
-
-  static void EncodeBlobTTL(std::string* dst, uint64_t expiration,
-                            uint64_t file_number, uint64_t offset,
-                            uint64_t size, CompressionType compression) {
-    assert(dst != nullptr);
-    dst->clear();
-    dst->reserve(kMaxVarint64Length * 4 + 2);
-    dst->push_back(static_cast<char>(Type::kBlobTTL));
-    PutVarint64(dst, expiration);
-    PutVarint64(dst, file_number);
-    PutVarint64(dst, offset);
-    PutVarint64(dst, size);
-    dst->push_back(static_cast<char>(compression));
-  }
-
- private:
-  Type type_ = Type::kUnknown;
-  uint64_t expiration_ = 0;
-  Slice value_;
-  uint64_t file_number_ = 0;
-  uint64_t offset_ = 0;
-  uint64_t size_ = 0;
-  CompressionType compression_ = kNoCompression;
-};
-
-}  // namespace rocksdb
-#endif  // ROCKSDB_LITE

db/builder.cc

@@ -13,78 +13,67 @@
 #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/filename.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"
 #include "rocksdb/env.h"
 #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/iostats_context_imp.h"
 #include "util/stop_watch.h"
+#include "util/thread_status_util.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) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
   return ioptions.table_factory->NewTableBuilder(
-      TableBuilderOptions(ioptions, moptions, internal_comparator,
+      TableBuilderOptions(ioptions, 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),
+                          compression_opts, compression_dict, skip_filters,
+                          column_family_name, level),
       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,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
+    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,
-    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 CompressionType compression,
+    const CompressionOptions& compression_opts, bool paranoid_file_checks,
+    InternalStats* internal_stats, TableFileCreationReason reason,
+    EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
+    TableProperties* table_properties, int level) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
@@ -93,13 +82,15 @@ 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(
@@ -107,60 +98,44 @@ 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;
-#ifndef NDEBUG
-      bool use_direct_writes = file_options.use_direct_writes;
-      TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
-#endif  // !NDEBUG
-      s = NewWritableFile(fs, fname, &file, file_options);
+      unique_ptr<WritableFile> file;
+      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);
     }
 
     MergeHelper merge(env, internal_comparator.user_comparator(),
                       ioptions.merge_operator, nullptr, ioptions.info_log,
                       true /* internal key corruption is not ok */,
-                      snapshots.empty() ? 0 : snapshots.back(),
-                      snapshot_checker);
+                      snapshots.empty() ? 0 : snapshots.back());
 
     CompactionIterator c_iter(
         iter, internal_comparator.user_comparator(), &merge, kMaxSequenceNumber,
-        &snapshots, earliest_write_conflict_snapshot, snapshot_checker, env,
-        ShouldReportDetailedTime(env, ioptions.statistics),
+        &snapshots, earliest_write_conflict_snapshot, env,
         true /* internal key corruption is not ok */, range_del_agg.get());
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
       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 +144,12 @@ 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 +162,7 @@ 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;
       }
@@ -205,7 +172,7 @@ Status BuildTable(
     // Finish and check for file errors
     if (s.ok() && !empty) {
       StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
-      s = file_writer->Sync(ioptions.use_fsync);
+      file_writer->Sync(ioptions.use_fsync);
     }
     if (s.ok() && !empty) {
       s = file_writer->Close();
@@ -213,20 +180,13 @@ Status BuildTable(
 
     if (s.ok() && !empty) {
       // Verify that the table is usable
-      // We set for_compaction to false and don't OptimizeForCompactionTableRead
-      // here because this is a special case after we finish the table building
-      // No matter whether use_direct_io_for_flush_and_compaction is true,
-      // we will regrad this verification as user reads since the goal is
-      // to cache it here for further user reads
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          ReadOptions(), 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 +202,13 @@ 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

@@ -9,10 +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"
 #include "rocksdb/listener.h"
@@ -21,6 +18,8 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/cf_options.h"
+#include "util/event_logger.h"
 
 namespace rocksdb {
 
@@ -30,28 +29,29 @@ struct FileMetaData;
 class Env;
 struct EnvOptions;
 class Iterator;
-class SnapshotChecker;
 class TableCache;
 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 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 CompressionOptions& compression_opts,
+    int level,
+    const std::string* compression_dict = nullptr,
+    const bool skip_filters = false);
 
 // Build a Table file from the contents of *iter.  The generated file
 // will be named according to number specified in meta. On success, the rest of
@@ -62,27 +62,21 @@ 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 CompressionType compression,
     const CompressionOptions& compression_opts, bool paranoid_file_checks,
     InternalStats* internal_stats, TableFileCreationReason reason,
     EventLogger* event_logger = nullptr, int job_id = 0,
     const Env::IOPriority io_priority = Env::IO_HIGH,
-    TableProperties* table_properties = nullptr, int level = -1,
-    const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
-    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
-    const uint64_t file_creation_time = 0);
+    TableProperties* table_properties = nullptr, int level = -1);
 
 }  // namespace rocksdb

db/column_family.h

@@ -19,19 +19,17 @@
 #include "db/table_properties_collector.h"
 #include "db/write_batch_internal.h"
 #include "db/write_controller.h"
-#include "options/cf_options.h"
 #include "rocksdb/compaction_job_stats.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
-#include "trace_replay/block_cache_tracer.h"
+#include "util/cf_options.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
 
 class Version;
 class VersionSet;
-class VersionStorageInfo;
 class MemTable;
 class MemTableListVersion;
 class CompactionPicker;
@@ -43,115 +41,8 @@ class DBImpl;
 class LogBuffer;
 class InstrumentedMutex;
 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
@@ -185,7 +76,7 @@ class ColumnFamilyHandleImpl : public ColumnFamilyHandle {
 class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
  public:
   ColumnFamilyHandleInternal()
-      : ColumnFamilyHandleImpl(nullptr, nullptr, nullptr), internal_cfd_(nullptr) {}
+      : ColumnFamilyHandleImpl(nullptr, nullptr, nullptr) {}
 
   void SetCFD(ColumnFamilyData* _cfd) { internal_cfd_ = _cfd; }
   virtual ColumnFamilyData* cfd() const override { return internal_cfd_; }
@@ -198,14 +89,12 @@ 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;
   MutableCFOptions mutable_cf_options;
   // Version number of the current SuperVersion
   uint64_t version_number;
-  WriteStallCondition write_stall_condition;
 
   InstrumentedMutex* db_mutex;
 
@@ -222,8 +111,8 @@ 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 +136,6 @@ 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 +162,7 @@ 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 +170,11 @@ 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
@@ -311,7 +192,7 @@ class ColumnFamilyData {
   // *) delete all memory associated with that column family
   // *) delete all the files associated with that column family
   void SetDropped();
-  bool IsDropped() const { return dropped_.load(std::memory_order_relaxed); }
+  bool IsDropped() const { return dropped_; }
 
   // thread-safe
   int NumberLevels() const { return ioptions_.num_levels; }
@@ -319,12 +200,8 @@ class ColumnFamilyData {
   void SetLogNumber(uint64_t log_number) { log_number_ = log_number; }
   uint64_t GetLogNumber() const { return log_number_; }
 
-  void SetFlushReason(FlushReason flush_reason) {
-    flush_reason_ = flush_reason;
-  }
-  FlushReason GetFlushReason() const { return flush_reason_; }
   // thread-safe
-  const 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 +222,9 @@ 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
 
@@ -364,12 +237,7 @@ class ColumnFamilyData {
   void SetCurrent(Version* _current);
   uint64_t GetNumLiveVersions() const;  // REQUIRE: DB mutex held
   uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
-  uint64_t GetLiveSstFilesSize() const;   // REQUIRE: DB mutex held
-  void SetMemtable(MemTable* new_mem) {
-    uint64_t memtable_id = last_memtable_id_.fetch_add(1) + 1;
-    new_mem->SetID(memtable_id);
-    mem_ = new_mem;
-  }
+  void SetMemtable(MemTable* new_mem) { mem_ = new_mem; }
 
   // calculate the oldest log needed for the durability of this column family
   uint64_t OldestLogToKeep();
@@ -395,28 +263,17 @@ class ColumnFamilyData {
                                   const Slice& largest_user_key,
                                   int level) const;
 
-  // Check if the passed ranges overlap with any unflushed memtables
-  // (immutable or mutable).
-  //
-  // @param super_version A referenced SuperVersion that will be held for the
-  //    duration of this function.
-  //
-  // Thread-safe
-  Status RangesOverlapWithMemtables(const autovector<Range>& ranges,
-                                    SuperVersion* super_version, bool* overlap);
-
   // A flag to tell a manual compaction is to compact all levels together
-  // instead of a specific level.
+  // instad of for specific level.
   static const int kCompactAllLevels;
   // A flag to tell a manual compaction's output is base level.
   static const int kCompactToBaseLevel;
   // 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 +293,11 @@ 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.
@@ -454,55 +311,28 @@ class ColumnFamilyData {
   // As argument takes a pointer to allocated SuperVersion to enable
   // the clients to allocate SuperVersion outside of mutex.
   // IMPORTANT: Only call this from DBImpl::InstallSuperVersion()
-  void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex,
-                           const MutableCFOptions& mutable_cf_options);
-  void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex);
+  SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
+                                    InstrumentedMutex* db_mutex,
+                                    const MutableCFOptions& mutable_cf_options);
+  SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
+                                    InstrumentedMutex* db_mutex);
 
   void ResetThreadLocalSuperVersions();
 
   // 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_; }
-
-  enum class WriteStallCause {
-    kNone,
-    kMemtableLimit,
-    kL0FileCountLimit,
-    kPendingCompactionBytes,
-  };
-  static std::pair<WriteStallCondition, WriteStallCause>
-  GetWriteStallConditionAndCause(int num_unflushed_memtables, int num_l0_files,
-                                 uint64_t num_compaction_needed_bytes,
-                                 const MutableCFOptions& mutable_cf_options);
+  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_; }
 
   // Recalculate some small conditions, which are changed only during
   // compaction, adding new memtable and/or
   // recalculation of compaction score. These values are used in
   // DBImpl::MakeRoomForWrite function to decide, if it need to make
   // a write stall
-  WriteStallCondition RecalculateWriteStallConditions(
+  void RecalculateWriteStallConditions(
       const MutableCFOptions& mutable_cf_options);
 
-  void set_initialized() { initialized_.store(true); }
-
-  bool initialized() const { return initialized_.load(); }
-
-  const ColumnFamilyOptions& initial_cf_options() {
-    return initial_cf_options_;
-  }
-
-  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 +340,8 @@ 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_;
@@ -520,8 +349,7 @@ class ColumnFamilyData {
   Version* current_;         // == dummy_versions->prev_
 
   std::atomic<int> refs_;      // outstanding references to ColumnFamilyData
-  std::atomic<bool> initialized_;
-  std::atomic<bool> dropped_;  // true if client dropped it
+  bool dropped_;               // true if client dropped it
 
   const InternalKeyComparator internal_comparator_;
   std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
@@ -563,8 +391,6 @@ class ColumnFamilyData {
   // recovered from
   uint64_t log_number_;
 
-  std::atomic<FlushReason> flush_reason_;
-
   // An object that keeps all the compaction stats
   // and picks the next compaction
   std::unique_ptr<CompactionPicker> compaction_picker_;
@@ -574,22 +400,16 @@ 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_;
 
   // if the database was opened with 2pc enabled
   bool allow_2pc_;
-
-  // 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 +458,9 @@ 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 +515,10 @@ 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 +35,10 @@ 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 +257,9 @@ 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 +272,7 @@ 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 +309,6 @@ 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 +319,7 @@ 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"
 
@@ -17,30 +17,39 @@ extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
 
 CompactedDBImpl::CompactedDBImpl(
   const DBOptions& options, const std::string& dbname)
-  : DBImpl(options, dbname), cfd_(nullptr), version_(nullptr),
-    user_comparator_(nullptr) {
+  : DBImpl(options, dbname) {
 }
 
 CompactedDBImpl::~CompactedDBImpl() {
 }
 
 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) {
+Status CompactedDBImpl::Get(const ReadOptions& options,
+     ColumnFamilyHandle*, const Slice& key, std::string* value) {
   GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                          GetContext::kNotFound, key, value, nullptr, nullptr,
-                         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();
   }
@@ -66,14 +75,11 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
   int idx = 0;
   for (auto* r : reader_list) {
     if (r != nullptr) {
-      PinnableSlice pinnable_val;
-      std::string& value = (*values)[idx];
       GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
-                             GetContext::kNotFound, keys[idx], &pinnable_val,
-                             nullptr, nullptr, true, nullptr, nullptr);
+                             GetContext::kNotFound, keys[idx], &(*values)[idx],
+                             nullptr, nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
-      r->Get(options, lkey.internal_key(), &get_context, nullptr);
-      value.assign(pinnable_val.data(), pinnable_val.size());
+      r->Get(options, lkey.internal_key(), &get_context);
       if (get_context.State() == GetContext::kFound) {
         statuses[idx] = Status::OK();
       }
@@ -84,7 +90,6 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
 }
 
 Status CompactedDBImpl::Init(const Options& options) {
-  SuperVersionContext sv_context(/* create_superversion */ true);
   mutex_.Lock();
   ColumnFamilyDescriptor cf(kDefaultColumnFamilyName,
                             ColumnFamilyOptions(options));
@@ -92,10 +97,9 @@ Status CompactedDBImpl::Init(const Options& options) {
   if (s.ok()) {
     cfd_ = reinterpret_cast<ColumnFamilyHandleImpl*>(
               DefaultColumnFamily())->cfd();
-    cfd_->InstallSuperVersion(&sv_context, &mutex_);
+    delete cfd_->InstallSuperVersion(new SuperVersion(), &mutex_);
   }
   mutex_.Unlock();
-  sv_context.Clean();
   if (!s.ok()) {
     return s;
   }
@@ -147,9 +151,8 @@ Status CompactedDBImpl::Open(const Options& options,
   std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
   Status s = db->Init(options);
   if (s.ok()) {
-    db->StartTimedTasks();
-    ROCKS_LOG_INFO(db->immutable_db_options_.info_log,
-                   "Opened the db as fully compacted mode");
+    Log(INFO_LEVEL, db->immutable_db_options_.info_log,
+        "Opened the db as fully compacted mode");
     LogFlush(db->immutable_db_options_.info_log);
     *dbptr = db.release();
   }

db/compacted_db_impl.h

@@ -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,
@@ -27,7 +23,7 @@ class CompactedDBImpl : public DBImpl {
   using DB::Get;
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
-                     PinnableSlice* value) override;
+                     std::string* value) override;
   using DB::MultiGet;
   virtual std::vector<Status> MultiGet(
       const ReadOptions& options,
@@ -36,66 +32,55 @@ class CompactedDBImpl : public DBImpl {
     override;
 
   using DBImpl::Put;
-  virtual Status Put(const WriteOptions& /*options*/,
-                     ColumnFamilyHandle* /*column_family*/,
-                     const Slice& /*key*/, const Slice& /*value*/) override {
+  virtual Status Put(const WriteOptions& options,
+                     ColumnFamilyHandle* column_family, const Slice& key,
+                     const Slice& value) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DBImpl::Merge;
-  virtual Status Merge(const WriteOptions& /*options*/,
-                       ColumnFamilyHandle* /*column_family*/,
-                       const Slice& /*key*/, const Slice& /*value*/) override {
+  virtual Status Merge(const WriteOptions& options,
+                       ColumnFamilyHandle* column_family, const Slice& key,
+                       const Slice& value) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DBImpl::Delete;
-  virtual Status Delete(const WriteOptions& /*options*/,
-                        ColumnFamilyHandle* /*column_family*/,
-                        const Slice& /*key*/) override {
+  virtual Status Delete(const WriteOptions& options,
+                        ColumnFamilyHandle* column_family,
+                        const Slice& key) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  virtual Status Write(const WriteOptions& /*options*/,
-                       WriteBatch* /*updates*/) override {
+  virtual Status Write(const WriteOptions& options,
+                       WriteBatch* updates) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DBImpl::CompactRange;
-  virtual Status CompactRange(const CompactRangeOptions& /*options*/,
-                              ColumnFamilyHandle* /*column_family*/,
-                              const Slice* /*begin*/,
-                              const Slice* /*end*/) override {
+  virtual Status CompactRange(const CompactRangeOptions& options,
+                              ColumnFamilyHandle* column_family,
+                              const Slice* begin, const Slice* end) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
 
   virtual Status DisableFileDeletions() override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  virtual Status EnableFileDeletions(bool /*force*/) override {
+  virtual Status EnableFileDeletions(bool force) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  virtual Status GetLiveFiles(std::vector<std::string>& ret,
+  virtual Status GetLiveFiles(std::vector<std::string>&,
                               uint64_t* manifest_file_size,
-                              bool /*flush_memtable*/) override {
-    return DBImpl::GetLiveFiles(ret, manifest_file_size,
-                                false /* flush_memtable */);
+                              bool flush_memtable = true) override {
+    return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DBImpl::Flush;
-  virtual Status Flush(const FlushOptions& /*options*/,
-                       ColumnFamilyHandle* /*column_family*/) override {
+  virtual Status Flush(const FlushOptions& options,
+                       ColumnFamilyHandle* column_family) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DB::IngestExternalFile;
   virtual Status IngestExternalFile(
-      ColumnFamilyHandle* /*column_family*/,
-      const std::vector<std::string>& /*external_files*/,
-      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 {
+      ColumnFamilyHandle* column_family,
+      const std::vector<std::string>& external_files,
+      const IngestExternalFileOptions& ingestion_options) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
 
@@ -108,6 +93,10 @@ 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/logging.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++) {
@@ -113,71 +81,40 @@ 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(
     int output_level, VersionStorageInfo* vstorage,
     const std::vector<CompactionInputFiles>& inputs) {
-  int output_l0_idx;
-  if (output_level == 0) {
-    output_l0_idx = 0;
-    for (const auto* file : vstorage->LevelFiles(0)) {
-      if (inputs[0].files.back() == file) {
-        break;
-      }
-      ++output_l0_idx;
-    }
-    assert(static_cast<size_t>(output_l0_idx) < vstorage->LevelFiles(0).size());
-  } else {
-    output_l0_idx = -1;
+  if (inputs[0].level == 0 &&
+      inputs[0].files.back() != vstorage->LevelFiles(0).back()) {
+    return false;
   }
+
   Slice smallest_key, largest_key;
   GetBoundaryKeys(vstorage, inputs, &smallest_key, &largest_key);
-  return !vstorage->RangeMightExistAfterSortedRun(smallest_key, largest_key,
-                                                  output_level, output_l0_idx);
+
+  // Checks whether there are files living beyond the output_level.
+  // If lower levels have files, it checks for overlap between files
+  // if the compaction process and those files.
+  // Bottomlevel optimizations can be made if there are no files in
+  // lower levels or if there is no overlap with the files in
+  // the lower levels.
+  for (int i = output_level + 1; i < vstorage->num_levels(); i++) {
+    // It is not the bottommost level if there are files in higher
+    // levels when the output level is 0 or if there are files in
+    // higher levels which overlap with files to be compacted.
+    // output_level == 0 means that we want it to be considered
+    // s the bottommost level only if the last file on the level
+    // is a part of the files to be compacted - this is verified by
+    // the first if condition in this function
+    if (vstorage->NumLevelFiles(i) > 0 &&
+        (output_level == 0 ||
+         vstorage->OverlapInLevel(i, &smallest_key, &largest_key))) {
+      return false;
+    }
+  }
+  return true;
 }
 
 // test function to validate the functionality of IsBottommostLevel()
@@ -209,8 +146,6 @@ 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 +155,6 @@ 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),
@@ -228,29 +162,18 @@ 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_)),
       is_full_compaction_(IsFullCompaction(vstorage, inputs_)),
       is_manual_compaction_(_manual_compaction),
-      is_trivial_move_(false),
       compaction_reason_(_compaction_reason) {
   MarkFilesBeingCompacted(true);
   if (is_manual_compaction_) {
     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 +198,9 @@ Compaction::~Compaction() {
     input_version_->Unref();
   }
   if (cfd_ != nullptr) {
-    cfd_->UnrefAndTryDelete();
+    if (cfd_->Unref()) {
+      delete cfd_;
+    }
   }
 }
 
@@ -315,7 +240,7 @@ bool Compaction::IsTrivialMove() const {
 
   // Used in universal compaction, where trivial move can be done if the
   // input files are non overlapping
-  if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
+  if ((immutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
       (output_level_ != 0)) {
     return is_trivial_move_;
   }
@@ -358,31 +283,28 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   assert(input_version_ != nullptr);
   assert(level_ptrs != nullptr);
   assert(level_ptrs->size() == static_cast<size_t>(number_levels_));
-  if (bottommost_level_) {
-    return true;
-  } else if (output_level_ != 0 &&
-             cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
-    // Maybe use binary search to find right entry instead of linear search?
-    const Comparator* user_cmp = cfd_->user_comparator();
-    for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
-      const std::vector<FileMetaData*>& files =
-          input_vstorage_->LevelFiles(lvl);
-      for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
-        auto* f = files[level_ptrs->at(lvl)];
-        if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
-          // We've advanced far enough
-          if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
-            // Key falls in this file's range, so it may
-            // exist beyond output level
-            return false;
-          }
-          break;
+  assert(cfd_->ioptions()->compaction_style != kCompactionStyleFIFO);
+  if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
+    return bottommost_level_;
+  }
+  // Maybe use binary search to find right entry instead of linear search?
+  const Comparator* user_cmp = cfd_->user_comparator();
+  for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
+    const std::vector<FileMetaData*>& files = input_vstorage_->LevelFiles(lvl);
+    for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
+      auto* f = files[level_ptrs->at(lvl)];
+      if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
+        // We've advanced far enough
+        if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
+          // Key falls in this file's range, so definitely
+          // exists beyond output level
+          return false;
         }
+        break;
       }
     }
-    return true;
   }
-  return false;
+  return true;
 }
 
 // Mark (or clear) each file that is being compacted
@@ -410,14 +332,12 @@ 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());
@@ -493,23 +413,19 @@ void Compaction::Summary(char* output, int len) {
 uint64_t Compaction::OutputFilePreallocationSize() const {
   uint64_t preallocation_size = 0;
 
-  for (const auto& level_files : inputs_) {
-    for (const auto& file : level_files.files) {
-      preallocation_size += file->fd.GetFileSize();
+  if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel ||
+      output_level() > 0) {
+    preallocation_size = max_output_file_size_;
+  } else {
+    // output_level() == 0
+    assert(num_input_levels() > 0);
+    for (const auto& f : inputs_[0].files) {
+      preallocation_size += f->fd.GetFileSize();
     }
   }
-
-  if (max_output_file_size_ != port::kMaxUint64 &&
-      (immutable_cf_options_.compaction_style == kCompactionStyleLevel ||
-       output_level() > 0)) {
-    preallocation_size = std::min(max_output_file_size_, preallocation_size);
-  }
-
   // Over-estimate slightly so we don't end up just barely crossing
   // the threshold
-  // No point to prellocate more than 1GB.
-  return std::min(uint64_t{1073741824},
-                  preallocation_size + (preallocation_size / 10));
+  return preallocation_size + (preallocation_size / 10);
 }
 
 std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
@@ -530,12 +446,11 @@ 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) {
-    return (start_level_ == 0 || is_manual_compaction_) && output_level_ > 0 &&
-           !IsOutputLevelEmpty();
+    return start_level_ == 0 && !IsOutputLevelEmpty();
   } else if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
     return number_levels_ > 1 && output_level_ > 0;
   } else {
@@ -543,22 +458,4 @@ bool Compaction::ShouldFormSubcompactions() const {
   }
 }
 
-uint64_t Compaction::MinInputFileOldestAncesterTime() const {
-  uint64_t min_oldest_ancester_time = port::kMaxUint64;
-  for (const auto& level_files : inputs_) {
-    for (const auto& file : level_files.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);
-      }
-    }
-  }
-  return min_oldest_ancester_time;
-}
-
-int Compaction::GetInputBaseLevel() const {
-  return input_vstorage_->base_level();
-}
-
 }  // 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"
+#include "util/cf_options.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,
@@ -130,18 +95,11 @@ 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
   //              < "input_levels()"
-  const std::vector<FileMetaData*>* inputs(
-      size_t compaction_input_level) const {
+  const std::vector<FileMetaData*>* inputs(size_t compaction_input_level) {
     assert(compaction_input_level < inputs_.size());
     return &inputs_[compaction_input_level].files;
   }
@@ -159,11 +117,6 @@ 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 +232,6 @@ class Compaction {
 
   Slice GetLargestUserKey() const { return largest_user_key_; }
 
-  int GetInputBaseLevel() const;
-
   CompactionReason compaction_reason() { return compaction_reason_; }
 
   const std::vector<FileMetaData*>& grandparents() const {
@@ -289,10 +240,6 @@ class Compaction {
 
   uint64_t max_compaction_bytes() const { return max_compaction_bytes_; }
 
-  uint32_t max_subcompactions() const { return max_subcompactions_; }
-
-  uint64_t MinInputFileOldestAncesterTime() const;
-
  private:
   // mark (or clear) all files that are being compacted
   void MarkFilesBeingCompacted(bool mark_as_compacted);
@@ -302,13 +249,6 @@ 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 +264,6 @@ 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 +274,6 @@ 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 +316,7 @@ 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_iterator_test.cc

@@ -1,976 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-
-#include <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 "utilities/merge_operators.h"
-
-namespace rocksdb {
-
-// Expects no merging attempts.
-class NoMergingMergeOp : public MergeOperator {
- public:
-  bool FullMergeV2(const MergeOperationInput& /*merge_in*/,
-                   MergeOperationOutput* /*merge_out*/) const override {
-    ADD_FAILURE();
-    return false;
-  }
-  bool PartialMergeMulti(const Slice& /*key*/,
-                         const std::deque<Slice>& /*operand_list*/,
-                         std::string* /*new_value*/,
-                         Logger* /*logger*/) const override {
-    ADD_FAILURE();
-    return false;
-  }
-  const char* Name() const override {
-    return "CompactionIteratorTest NoMergingMergeOp";
-  }
-};
-
-// Compaction filter that gets stuck when it sees a particular key,
-// then gets unstuck when told to.
-// Always returns Decition::kRemove.
-class StallingFilter : public CompactionFilter {
- public:
-  Decision FilterV2(int /*level*/, const Slice& key, ValueType /*type*/,
-                    const Slice& /*existing_value*/, std::string* /*new_value*/,
-                    std::string* /*skip_until*/) const override {
-    int k = std::atoi(key.ToString().c_str());
-    last_seen.store(k);
-    while (k >= stall_at.load()) {
-      std::this_thread::yield();
-    }
-    return Decision::kRemove;
-  }
-
-  const char* Name() const override {
-    return "CompactionIteratorTest StallingFilter";
-  }
-
-  // Wait until the filter sees a key >= k and stalls at that key.
-  // If `exact`, asserts that the seen key is equal to k.
-  void WaitForStall(int k, bool exact = true) {
-    stall_at.store(k);
-    while (last_seen.load() < k) {
-      std::this_thread::yield();
-    }
-    if (exact) {
-      EXPECT_EQ(k, last_seen.load());
-    }
-  }
-
-  // Filter will stall on key >= stall_at. Advance stall_at to unstall.
-  mutable std::atomic<int> stall_at{0};
-  // Last key the filter was called with.
-  mutable std::atomic<int> last_seen{0};
-};
-
-// Compaction filter that filter out all keys.
-class FilterAllKeysCompactionFilter : public CompactionFilter {
- public:
-  Decision FilterV2(int /*level*/, const Slice& /*key*/, ValueType /*type*/,
-                    const Slice& /*existing_value*/, std::string* /*new_value*/,
-                    std::string* /*skip_until*/) const override {
-    return Decision::kRemove;
-  }
-
-  const char* Name() const override { return "AllKeysCompactionFilter"; }
-};
-
-class LoggingForwardVectorIterator : public InternalIterator {
- public:
-  struct Action {
-    enum class Type {
-      SEEK_TO_FIRST,
-      SEEK,
-      NEXT,
-    };
-
-    Type type;
-    std::string arg;
-
-    explicit Action(Type _type, std::string _arg = "")
-        : type(_type), arg(_arg) {}
-
-    bool operator==(const Action& rhs) const {
-      return std::tie(type, arg) == std::tie(rhs.type, rhs.arg);
-    }
-  };
-
-  LoggingForwardVectorIterator(const std::vector<std::string>& keys,
-                               const std::vector<std::string>& values)
-      : keys_(keys), values_(values), current_(keys.size()) {
-    assert(keys_.size() == values_.size());
-  }
-
-  bool Valid() const override { return current_ < keys_.size(); }
-
-  void SeekToFirst() override {
-    log.emplace_back(Action::Type::SEEK_TO_FIRST);
-    current_ = 0;
-  }
-  void SeekToLast() override { assert(false); }
-
-  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); }
-
-  void Next() override {
-    assert(Valid());
-    log.emplace_back(Action::Type::NEXT);
-    current_++;
-  }
-  void Prev() override { assert(false); }
-
-  Slice key() const override {
-    assert(Valid());
-    return Slice(keys_[current_]);
-  }
-  Slice value() const override {
-    assert(Valid());
-    return Slice(values_[current_]);
-  }
-
-  Status status() const override { return Status::OK(); }
-
-  std::vector<Action> log;
-
- private:
-  std::vector<std::string> keys_;
-  std::vector<std::string> values_;
-  size_t current_;
-};
-
-class FakeCompaction : public CompactionIterator::CompactionProxy {
- public:
-  FakeCompaction() = default;
-
-  int level(size_t /*compaction_input_level*/) const override { return 0; }
-  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 {
-    return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
-  }
-  bool allow_ingest_behind() const override { return false; }
-
-  bool preserve_deletes() const override { return false; }
-
-  bool key_not_exists_beyond_output_level = false;
-
-  bool is_bottommost_level = false;
-};
-
-// A simplifed snapshot checker which assumes each snapshot has a global
-// last visible sequence.
-class TestSnapshotChecker : public SnapshotChecker {
- public:
-  explicit TestSnapshotChecker(
-      SequenceNumber last_committed_sequence,
-      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {{}})
-      : last_committed_sequence_(last_committed_sequence),
-        snapshots_(snapshots) {}
-
-  SnapshotCheckerResult CheckInSnapshot(
-      SequenceNumber seq, SequenceNumber snapshot_seq) const override {
-    if (snapshot_seq == kMaxSequenceNumber) {
-      return seq <= last_committed_sequence_
-                 ? SnapshotCheckerResult::kInSnapshot
-                 : SnapshotCheckerResult::kNotInSnapshot;
-    }
-    assert(snapshots_.count(snapshot_seq) > 0);
-    return seq <= snapshots_.at(snapshot_seq)
-               ? SnapshotCheckerResult::kInSnapshot
-               : SnapshotCheckerResult::kNotInSnapshot;
-  }
-
- private:
-  SequenceNumber last_committed_sequence_;
-  // A map of valid snapshot to last visible sequence to the snapshot.
-  std::unordered_map<SequenceNumber, SequenceNumber> snapshots_;
-};
-
-// Test param:
-//   bool: whether to pass snapshot_checker to compaction iterator.
-class CompactionIteratorTest : public testing::TestWithParam<bool> {
- public:
-  CompactionIteratorTest()
-      : cmp_(BytewiseComparator()), icmp_(cmp_), snapshots_({}) {}
-
-  void InitIterators(
-      const std::vector<std::string>& ks, const std::vector<std::string>& vs,
-      const std::vector<std::string>& range_del_ks,
-      const std::vector<std::string>& range_del_vs,
-      SequenceNumber last_sequence,
-      SequenceNumber last_committed_sequence = kMaxSequenceNumber,
-      MergeOperator* merge_op = nullptr, CompactionFilter* filter = nullptr,
-      bool bottommost_level = false,
-      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
-    std::unique_ptr<InternalIterator> unfragmented_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));
-
-    std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
-    if (filter || bottommost_level) {
-      compaction_proxy_ = new FakeCompaction();
-      compaction_proxy_->is_bottommost_level = bottommost_level;
-      compaction.reset(compaction_proxy_);
-    }
-    bool use_snapshot_checker = UseSnapshotChecker() || GetParam();
-    if (use_snapshot_checker || last_committed_sequence < kMaxSequenceNumber) {
-      snapshot_checker_.reset(
-          new TestSnapshotChecker(last_committed_sequence, snapshot_map_));
-    }
-    merge_helper_.reset(
-        new MergeHelper(Env::Default(), cmp_, merge_op, filter, nullptr, false,
-                        0 /*latest_snapshot*/, snapshot_checker_.get(),
-                        0 /*level*/, nullptr /*statistics*/, &shutting_down_));
-
-    iter_.reset(new LoggingForwardVectorIterator(ks, vs));
-    iter_->SeekToFirst();
-    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_));
-  }
-
-  void AddSnapshot(SequenceNumber snapshot,
-                   SequenceNumber last_visible_seq = kMaxSequenceNumber) {
-    snapshots_.push_back(snapshot);
-    snapshot_map_[snapshot] = last_visible_seq;
-  }
-
-  virtual bool UseSnapshotChecker() const { return false; }
-
-  void RunTest(
-      const std::vector<std::string>& input_keys,
-      const std::vector<std::string>& input_values,
-      const std::vector<std::string>& expected_keys,
-      const std::vector<std::string>& expected_values,
-      SequenceNumber last_committed_seq = kMaxSequenceNumber,
-      MergeOperator* merge_operator = nullptr,
-      CompactionFilter* compaction_filter = nullptr,
-      bool bottommost_level = false,
-      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
-    InitIterators(input_keys, input_values, {}, {}, kMaxSequenceNumber,
-                  last_committed_seq, merge_operator, compaction_filter,
-                  bottommost_level, earliest_write_conflict_snapshot);
-    c_iter_->SeekToFirst();
-    for (size_t i = 0; i < expected_keys.size(); i++) {
-      std::string info = "i = " + ToString(i);
-      ASSERT_TRUE(c_iter_->Valid()) << info;
-      ASSERT_OK(c_iter_->status()) << info;
-      ASSERT_EQ(expected_keys[i], c_iter_->key().ToString()) << info;
-      ASSERT_EQ(expected_values[i], c_iter_->value().ToString()) << info;
-      c_iter_->Next();
-    }
-    ASSERT_FALSE(c_iter_->Valid());
-  }
-
-  const Comparator* cmp_;
-  const InternalKeyComparator icmp_;
-  std::vector<SequenceNumber> snapshots_;
-  // A map of valid snapshot to last visible sequence to the snapshot.
-  std::unordered_map<SequenceNumber, SequenceNumber> snapshot_map_;
-  std::unique_ptr<MergeHelper> merge_helper_;
-  std::unique_ptr<LoggingForwardVectorIterator> iter_;
-  std::unique_ptr<CompactionIterator> c_iter_;
-  std::unique_ptr<CompactionRangeDelAggregator> range_del_agg_;
-  std::unique_ptr<SnapshotChecker> snapshot_checker_;
-  std::atomic<bool> shutting_down_{false};
-  FakeCompaction* compaction_proxy_;
-};
-
-// It is possible that the output of the compaction iterator is empty even if
-// the input is not.
-TEST_P(CompactionIteratorTest, EmptyResult) {
-  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
-                 test::KeyStr("a", 3, kTypeValue)},
-                {"", "val"}, {}, {}, 5);
-  c_iter_->SeekToFirst();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-// If there is a corruption after a single deletion, the corrupted key should
-// be preserved.
-TEST_P(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
-  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
-                 test::KeyStr("a", 3, kTypeValue, true),
-                 test::KeyStr("b", 10, kTypeValue)},
-                {"", "val", "val2"}, {}, {}, 10);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 5, kTypeSingleDeletion),
-            c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 3, kTypeValue, true), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("b", 10, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-TEST_P(CompactionIteratorTest, SimpleRangeDeletion) {
-  InitIterators({test::KeyStr("morning", 5, kTypeValue),
-                 test::KeyStr("morning", 2, kTypeValue),
-                 test::KeyStr("night", 3, kTypeValue)},
-                {"zao", "zao", "wan"},
-                {test::KeyStr("ma", 4, kTypeRangeDeletion)}, {"mz"}, 5);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 3, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-TEST_P(CompactionIteratorTest, RangeDeletionWithSnapshots) {
-  AddSnapshot(10);
-  std::vector<std::string> ks1;
-  ks1.push_back(test::KeyStr("ma", 28, kTypeRangeDeletion));
-  std::vector<std::string> vs1{"mz"};
-  std::vector<std::string> ks2{test::KeyStr("morning", 15, kTypeValue),
-                               test::KeyStr("morning", 5, kTypeValue),
-                               test::KeyStr("night", 40, kTypeValue),
-                               test::KeyStr("night", 20, kTypeValue)};
-  std::vector<std::string> vs2{"zao 15", "zao 5", "wan 40", "wan 20"};
-  InitIterators(ks2, vs2, ks1, vs1, 40);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 40, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-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 {
-      std::string k = key.ToString();
-      std::string v = existing_value.ToString();
-      // See InitIterators() call below for the sequence of keys and their
-      // filtering decisions. Here we closely assert that compaction filter is
-      // called with the expected keys and only them, and with the right values.
-      if (k == "a") {
-        EXPECT_EQ(ValueType::kValue, t);
-        EXPECT_EQ("av50", v);
-        return Decision::kKeep;
-      }
-      if (k == "b") {
-        EXPECT_EQ(ValueType::kValue, t);
-        EXPECT_EQ("bv60", v);
-        *skip_until = "d+";
-        return Decision::kRemoveAndSkipUntil;
-      }
-      if (k == "e") {
-        EXPECT_EQ(ValueType::kMergeOperand, t);
-        EXPECT_EQ("em71", v);
-        return Decision::kKeep;
-      }
-      if (k == "f") {
-        if (v == "fm65") {
-          EXPECT_EQ(ValueType::kMergeOperand, t);
-          *skip_until = "f";
-        } else {
-          EXPECT_EQ("fm30", v);
-          EXPECT_EQ(ValueType::kMergeOperand, t);
-          *skip_until = "g+";
-        }
-        return Decision::kRemoveAndSkipUntil;
-      }
-      if (k == "h") {
-        EXPECT_EQ(ValueType::kValue, t);
-        EXPECT_EQ("hv91", v);
-        return Decision::kKeep;
-      }
-      if (k == "i") {
-        EXPECT_EQ(ValueType::kMergeOperand, t);
-        EXPECT_EQ("im95", v);
-        *skip_until = "z";
-        return Decision::kRemoveAndSkipUntil;
-      }
-      ADD_FAILURE();
-      return Decision::kKeep;
-    }
-
-    const char* Name() const override {
-      return "CompactionIteratorTest.CompactionFilterSkipUntil::Filter";
-    }
-  };
-
-  NoMergingMergeOp merge_op;
-  Filter filter;
-  InitIterators(
-      {test::KeyStr("a", 50, kTypeValue),  // keep
-       test::KeyStr("a", 45, kTypeMerge),
-       test::KeyStr("b", 60, kTypeValue),  // skip to "d+"
-       test::KeyStr("b", 40, kTypeValue), test::KeyStr("c", 35, kTypeValue),
-       test::KeyStr("d", 70, kTypeMerge),
-       test::KeyStr("e", 71, kTypeMerge),  // keep
-       test::KeyStr("f", 65, kTypeMerge),  // skip to "f", aka keep
-       test::KeyStr("f", 30, kTypeMerge),  // skip to "g+"
-       test::KeyStr("f", 25, kTypeValue), test::KeyStr("g", 90, kTypeValue),
-       test::KeyStr("h", 91, kTypeValue),  // keep
-       test::KeyStr("i", 95, kTypeMerge),  // skip to "z"
-       test::KeyStr("j", 99, kTypeValue)},
-      {"av50", "am45", "bv60", "bv40", "cv35", "dm70", "em71", "fm65", "fm30",
-       "fv25", "gv90", "hv91", "im95", "jv99"},
-      {}, {}, kMaxSequenceNumber, kMaxSequenceNumber, &merge_op, &filter);
-
-  // Compaction should output just "a", "e" and "h" keys.
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 50, kTypeValue), c_iter_->key().ToString());
-  ASSERT_EQ("av50", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("e", 71, kTypeMerge), c_iter_->key().ToString());
-  ASSERT_EQ("em71", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("h", 91, kTypeValue), c_iter_->key().ToString());
-  ASSERT_EQ("hv91", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-
-  // Check that the compaction iterator did the correct sequence of calls on
-  // the underlying iterator.
-  using A = LoggingForwardVectorIterator::Action;
-  using T = A::Type;
-  std::vector<A> expected_actions = {
-      A(T::SEEK_TO_FIRST),
-      A(T::NEXT),
-      A(T::NEXT),
-      A(T::SEEK, test::KeyStr("d+", kMaxSequenceNumber, kValueTypeForSeek)),
-      A(T::NEXT),
-      A(T::NEXT),
-      A(T::SEEK, test::KeyStr("g+", kMaxSequenceNumber, kValueTypeForSeek)),
-      A(T::NEXT),
-      A(T::SEEK, test::KeyStr("z", kMaxSequenceNumber, kValueTypeForSeek))};
-  ASSERT_EQ(expected_actions, iter_->log);
-}
-
-TEST_P(CompactionIteratorTest, ShuttingDownInFilter) {
-  NoMergingMergeOp merge_op;
-  StallingFilter filter;
-  InitIterators(
-      {test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeValue),
-       test::KeyStr("3", 3, kTypeValue), test::KeyStr("4", 4, kTypeValue)},
-      {"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, kMaxSequenceNumber,
-      &merge_op, &filter);
-  // Don't leave tombstones (kTypeDeletion) for filtered keys.
-  compaction_proxy_->key_not_exists_beyond_output_level = true;
-
-  std::atomic<bool> seek_done{false};
-  rocksdb::port::Thread compaction_thread([&] {
-    c_iter_->SeekToFirst();
-    EXPECT_FALSE(c_iter_->Valid());
-    EXPECT_TRUE(c_iter_->status().IsShutdownInProgress());
-    seek_done.store(true);
-  });
-
-  // Let key 1 through.
-  filter.WaitForStall(1);
-
-  // Shutdown during compaction filter call for key 2.
-  filter.WaitForStall(2);
-  shutting_down_.store(true);
-  EXPECT_FALSE(seek_done.load());
-
-  // Unstall filter and wait for SeekToFirst() to return.
-  filter.stall_at.store(3);
-  compaction_thread.join();
-  assert(seek_done.load());
-
-  // Check that filter was never called again.
-  EXPECT_EQ(2, filter.last_seen.load());
-}
-
-// Same as ShuttingDownInFilter, but shutdown happens during filter call for
-// a merge operand, not for a value.
-TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
-  NoMergingMergeOp merge_op;
-  StallingFilter filter;
-  InitIterators(
-      {test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeMerge),
-       test::KeyStr("3", 3, kTypeMerge), test::KeyStr("4", 4, kTypeValue)},
-      {"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, kMaxSequenceNumber,
-      &merge_op, &filter);
-  compaction_proxy_->key_not_exists_beyond_output_level = true;
-
-  std::atomic<bool> seek_done{false};
-  rocksdb::port::Thread compaction_thread([&] {
-    c_iter_->SeekToFirst();
-    ASSERT_FALSE(c_iter_->Valid());
-    ASSERT_TRUE(c_iter_->status().IsShutdownInProgress());
-    seek_done.store(true);
-  });
-
-  // Let key 1 through.
-  filter.WaitForStall(1);
-
-  // Shutdown during compaction filter call for key 2.
-  filter.WaitForStall(2);
-  shutting_down_.store(true);
-  EXPECT_FALSE(seek_done.load());
-
-  // Unstall filter and wait for SeekToFirst() to return.
-  filter.stall_at.store(3);
-  compaction_thread.join();
-  assert(seek_done.load());
-
-  // Check that filter was never called again.
-  EXPECT_EQ(2, filter.last_seen.load());
-}
-
-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 {
-      std::string k = key.ToString();
-      std::string v = existing_value.ToString();
-
-      // See InitIterators() call below for the sequence of keys and their
-      // filtering decisions. Here we closely assert that compaction filter is
-      // called with the expected keys and only them, and with the right values.
-      if (k == "a") {
-        EXPECT_EQ(ValueType::kMergeOperand, t);
-        EXPECT_EQ("av1", v);
-        return Decision::kKeep;
-      } else if (k == "b") {
-        EXPECT_EQ(ValueType::kMergeOperand, t);
-        return Decision::kKeep;
-      } else if (k == "c") {
-        return Decision::kKeep;
-      }
-
-      ADD_FAILURE();
-      return Decision::kKeep;
-    }
-
-    const char* Name() const override {
-      return "CompactionIteratorTest.SingleMergeOperand::Filter";
-    }
-  };
-
-  class SingleMergeOp : public MergeOperator {
-   public:
-    bool FullMergeV2(const MergeOperationInput& merge_in,
-                     MergeOperationOutput* merge_out) const override {
-      // See InitIterators() call below for why "c" is the only key for which
-      // FullMergeV2 should be called.
-      EXPECT_EQ("c", merge_in.key.ToString());
-
-      std::string temp_value;
-      if (merge_in.existing_value != nullptr) {
-        temp_value = merge_in.existing_value->ToString();
-      }
-
-      for (auto& operand : merge_in.operand_list) {
-        temp_value.append(operand.ToString());
-      }
-      merge_out->new_value = temp_value;
-
-      return true;
-    }
-
-    bool PartialMergeMulti(const Slice& key,
-                           const std::deque<Slice>& operand_list,
-                           std::string* new_value,
-                           Logger* /*logger*/) const override {
-      std::string string_key = key.ToString();
-      EXPECT_TRUE(string_key == "a" || string_key == "b");
-
-      if (string_key == "a") {
-        EXPECT_EQ(1, operand_list.size());
-      } else if (string_key == "b") {
-        EXPECT_EQ(2, operand_list.size());
-      }
-
-      std::string temp_value;
-      for (auto& operand : operand_list) {
-        temp_value.append(operand.ToString());
-      }
-      swap(temp_value, *new_value);
-
-      return true;
-    }
-
-    const char* Name() const override {
-      return "CompactionIteratorTest SingleMergeOp";
-    }
-
-    bool AllowSingleOperand() const override { return true; }
-  };
-
-  SingleMergeOp merge_op;
-  Filter filter;
-  InitIterators(
-      // a should invoke PartialMergeMulti with a single merge operand.
-      {test::KeyStr("a", 50, kTypeMerge),
-       // b should invoke PartialMergeMulti with two operands.
-       test::KeyStr("b", 70, kTypeMerge), test::KeyStr("b", 60, kTypeMerge),
-       // c should invoke FullMerge due to kTypeValue at the beginning.
-       test::KeyStr("c", 90, kTypeMerge), test::KeyStr("c", 80, kTypeValue)},
-      {"av1", "bv2", "bv1", "cv2", "cv1"}, {}, {}, kMaxSequenceNumber,
-      kMaxSequenceNumber, &merge_op, &filter);
-
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 50, kTypeMerge), c_iter_->key().ToString());
-  ASSERT_EQ("av1", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ("bv1bv2", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_EQ("cv1cv2", c_iter_->value().ToString());
-}
-
-// In bottommost level, values earlier than earliest snapshot can be output
-// with sequence = 0.
-TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
-  AddSnapshot(1);
-  RunTest({test::KeyStr("a", 1, kTypeValue), test::KeyStr("b", 2, kTypeValue)},
-          {"v1", "v2"},
-          {test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 2, kTypeValue)},
-          {"v1", "v2"}, kMaxSequenceNumber /*last_commited_seq*/,
-          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-          true /*bottommost_level*/);
-}
-
-// In bottommost level, deletions earlier than earliest snapshot can be removed
-// permanently.
-TEST_P(CompactionIteratorTest, RemoveDeletionAtBottomLevel) {
-  AddSnapshot(1);
-  RunTest({test::KeyStr("a", 1, kTypeDeletion),
-           test::KeyStr("b", 3, kTypeDeletion),
-           test::KeyStr("b", 1, kTypeValue)},
-          {"", "", ""},
-          {test::KeyStr("b", 3, kTypeDeletion),
-           test::KeyStr("b", 0, kTypeValue)},
-          {"", ""},
-          kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
-          nullptr /*compaction_filter*/, true /*bottommost_level*/);
-}
-
-// In bottommost level, single deletions earlier than earliest snapshot can be
-// removed permanently.
-TEST_P(CompactionIteratorTest, RemoveSingleDeletionAtBottomLevel) {
-  AddSnapshot(1);
-  RunTest({test::KeyStr("a", 1, kTypeSingleDeletion),
-           test::KeyStr("b", 2, kTypeSingleDeletion)},
-          {"", ""}, {test::KeyStr("b", 2, kTypeSingleDeletion)}, {""},
-          kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
-          nullptr /*compaction_filter*/, true /*bottommost_level*/);
-}
-
-INSTANTIATE_TEST_CASE_P(CompactionIteratorTestInstance, CompactionIteratorTest,
-                        testing::Values(true, false));
-
-// Tests how CompactionIterator work together with SnapshotChecker.
-class CompactionIteratorWithSnapshotCheckerTest
-    : public CompactionIteratorTest {
- public:
-  bool UseSnapshotChecker() const override { return true; }
-};
-
-// Uncommitted keys (keys with seq > last_committed_seq) should be output as-is
-// while committed version of these keys should get compacted as usual.
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       PreserveUncommittedKeys_Value) {
-  RunTest(
-      {test::KeyStr("foo", 3, kTypeValue), test::KeyStr("foo", 2, kTypeValue),
-       test::KeyStr("foo", 1, kTypeValue)},
-      {"v3", "v2", "v1"},
-      {test::KeyStr("foo", 3, kTypeValue), test::KeyStr("foo", 2, kTypeValue)},
-      {"v3", "v2"}, 2 /*last_committed_seq*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       PreserveUncommittedKeys_Deletion) {
-  RunTest({test::KeyStr("foo", 2, kTypeDeletion),
-           test::KeyStr("foo", 1, kTypeValue)},
-          {"", "v1"},
-          {test::KeyStr("foo", 2, kTypeDeletion),
-           test::KeyStr("foo", 1, kTypeValue)},
-          {"", "v1"}, 1 /*last_committed_seq*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       PreserveUncommittedKeys_Merge) {
-  auto merge_op = MergeOperators::CreateStringAppendOperator();
-  RunTest(
-      {test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 2, kTypeMerge),
-       test::KeyStr("foo", 1, kTypeValue)},
-      {"v3", "v2", "v1"},
-      {test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 2, kTypeValue)},
-      {"v3", "v1,v2"}, 2 /*last_committed_seq*/, merge_op.get());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       PreserveUncommittedKeys_SingleDelete) {
-  RunTest({test::KeyStr("foo", 2, kTypeSingleDeletion),
-           test::KeyStr("foo", 1, kTypeValue)},
-          {"", "v1"},
-          {test::KeyStr("foo", 2, kTypeSingleDeletion),
-           test::KeyStr("foo", 1, kTypeValue)},
-          {"", "v1"}, 1 /*last_committed_seq*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       PreserveUncommittedKeys_BlobIndex) {
-  RunTest({test::KeyStr("foo", 3, kTypeBlobIndex),
-           test::KeyStr("foo", 2, kTypeBlobIndex),
-           test::KeyStr("foo", 1, kTypeBlobIndex)},
-          {"v3", "v2", "v1"},
-          {test::KeyStr("foo", 3, kTypeBlobIndex),
-           test::KeyStr("foo", 2, kTypeBlobIndex)},
-          {"v3", "v2"}, 2 /*last_committed_seq*/);
-}
-
-// Test compaction iterator dedup keys visible to the same snapshot.
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Value) {
-  AddSnapshot(2, 1);
-  RunTest(
-      {test::KeyStr("foo", 4, kTypeValue), test::KeyStr("foo", 3, kTypeValue),
-       test::KeyStr("foo", 2, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
-      {"v4", "v3", "v2", "v1"},
-      {test::KeyStr("foo", 4, kTypeValue), test::KeyStr("foo", 3, kTypeValue),
-       test::KeyStr("foo", 1, kTypeValue)},
-      {"v4", "v3", "v1"}, 3 /*last_committed_seq*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Deletion) {
-  AddSnapshot(2, 1);
-  RunTest(
-      {test::KeyStr("foo", 4, kTypeValue),
-       test::KeyStr("foo", 3, kTypeDeletion),
-       test::KeyStr("foo", 2, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
-      {"v4", "", "v2", "v1"},
-      {test::KeyStr("foo", 4, kTypeValue),
-       test::KeyStr("foo", 3, kTypeDeletion),
-       test::KeyStr("foo", 1, kTypeValue)},
-      {"v4", "", "v1"}, 3 /*last_committed_seq*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Merge) {
-  AddSnapshot(2, 1);
-  AddSnapshot(4, 3);
-  auto merge_op = MergeOperators::CreateStringAppendOperator();
-  RunTest(
-      {test::KeyStr("foo", 5, kTypeMerge), test::KeyStr("foo", 4, kTypeMerge),
-       test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 2, kTypeMerge),
-       test::KeyStr("foo", 1, kTypeValue)},
-      {"v5", "v4", "v3", "v2", "v1"},
-      {test::KeyStr("foo", 5, kTypeMerge), test::KeyStr("foo", 4, kTypeMerge),
-       test::KeyStr("foo", 3, kTypeMerge), test::KeyStr("foo", 1, kTypeValue)},
-      {"v5", "v4", "v2,v3", "v1"}, 4 /*last_committed_seq*/, merge_op.get());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       DedupSameSnapshot_SingleDeletion) {
-  AddSnapshot(2, 1);
-  RunTest(
-      {test::KeyStr("foo", 4, kTypeValue),
-       test::KeyStr("foo", 3, kTypeSingleDeletion),
-       test::KeyStr("foo", 2, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
-      {"v4", "", "v2", "v1"},
-      {test::KeyStr("foo", 4, kTypeValue), test::KeyStr("foo", 1, kTypeValue)},
-      {"v4", "v1"}, 3 /*last_committed_seq*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_BlobIndex) {
-  AddSnapshot(2, 1);
-  RunTest({test::KeyStr("foo", 4, kTypeBlobIndex),
-           test::KeyStr("foo", 3, kTypeBlobIndex),
-           test::KeyStr("foo", 2, kTypeBlobIndex),
-           test::KeyStr("foo", 1, kTypeBlobIndex)},
-          {"v4", "v3", "v2", "v1"},
-          {test::KeyStr("foo", 4, kTypeBlobIndex),
-           test::KeyStr("foo", 3, kTypeBlobIndex),
-           test::KeyStr("foo", 1, kTypeBlobIndex)},
-          {"v4", "v3", "v1"}, 3 /*last_committed_seq*/);
-}
-
-// At bottom level, sequence numbers can be zero out, and deletions can be
-// removed, but only when they are visible to earliest snapshot.
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       NotZeroOutSequenceIfNotVisibleToEarliestSnapshot) {
-  AddSnapshot(2, 1);
-  RunTest({test::KeyStr("a", 1, kTypeValue), test::KeyStr("b", 2, kTypeValue),
-           test::KeyStr("c", 3, kTypeValue)},
-          {"v1", "v2", "v3"},
-          {test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 2, kTypeValue),
-           test::KeyStr("c", 3, kTypeValue)},
-          {"v1", "v2", "v3"}, kMaxSequenceNumber /*last_commited_seq*/,
-          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-          true /*bottommost_level*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       NotRemoveDeletionIfNotVisibleToEarliestSnapshot) {
-  AddSnapshot(2, 1);
-  RunTest(
-      {test::KeyStr("a", 1, kTypeDeletion), test::KeyStr("b", 2, kTypeDeletion),
-       test::KeyStr("c", 3, kTypeDeletion)},
-      {"", "", ""},
-      {},
-      {"", ""}, 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);
-  RunTest({test::KeyStr("a", 1, kTypeSingleDeletion),
-           test::KeyStr("b", 2, kTypeSingleDeletion),
-           test::KeyStr("c", 3, kTypeSingleDeletion)},
-          {"", "", ""},
-          {test::KeyStr("b", 2, kTypeSingleDeletion),
-           test::KeyStr("c", 3, kTypeSingleDeletion)},
-          {"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
-          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-          true /*bottommost_level*/);
-}
-
-// Single delete should not cancel out values that not visible to the
-// same set of snapshots
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       SingleDeleteAcrossSnapshotBoundary) {
-  AddSnapshot(2, 1);
-  RunTest({test::KeyStr("a", 2, kTypeSingleDeletion),
-           test::KeyStr("a", 1, kTypeValue)},
-          {"", "v1"},
-          {test::KeyStr("a", 2, kTypeSingleDeletion),
-           test::KeyStr("a", 1, kTypeValue)},
-          {"", "v1"}, 2 /*last_committed_seq*/);
-}
-
-// Single delete should be kept in case it is not visible to the
-// earliest write conflict snapshot. If a single delete is kept for this reason,
-// corresponding value can be trimmed to save space.
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       KeepSingleDeletionForWriteConflictChecking) {
-  AddSnapshot(2, 0);
-  RunTest({test::KeyStr("a", 2, kTypeSingleDeletion),
-           test::KeyStr("a", 1, kTypeValue)},
-          {"", "v1"},
-          {test::KeyStr("a", 2, kTypeSingleDeletion),
-           test::KeyStr("a", 1, kTypeValue)},
-          {"", ""}, 2 /*last_committed_seq*/, nullptr /*merge_operator*/,
-          nullptr /*compaction_filter*/, false /*bottommost_level*/,
-          2 /*earliest_write_conflict_snapshot*/);
-}
-
-// Compaction filter should keep uncommitted key as-is, and
-//   * Convert the latest velue to deletion, and/or
-//   * if latest value is a merge, apply filter to all suequent merges.
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Value) {
-  std::unique_ptr<CompactionFilter> compaction_filter(
-      new FilterAllKeysCompactionFilter());
-  RunTest(
-      {test::KeyStr("a", 2, kTypeValue), test::KeyStr("a", 1, kTypeValue),
-       test::KeyStr("b", 3, kTypeValue), test::KeyStr("c", 1, kTypeValue)},
-      {"v2", "v1", "v3", "v4"},
-      {test::KeyStr("a", 2, kTypeValue), test::KeyStr("a", 1, kTypeDeletion),
-       test::KeyStr("b", 3, kTypeValue), test::KeyStr("c", 1, kTypeDeletion)},
-      {"v2", "", "v3", ""}, 1 /*last_committed_seq*/,
-      nullptr /*merge_operator*/, compaction_filter.get());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Deletion) {
-  std::unique_ptr<CompactionFilter> compaction_filter(
-      new FilterAllKeysCompactionFilter());
-  RunTest(
-      {test::KeyStr("a", 2, kTypeDeletion), test::KeyStr("a", 1, kTypeValue)},
-      {"", "v1"},
-      {test::KeyStr("a", 2, kTypeDeletion),
-       test::KeyStr("a", 1, kTypeDeletion)},
-      {"", ""}, 1 /*last_committed_seq*/, nullptr /*merge_operator*/,
-      compaction_filter.get());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       CompactionFilter_PartialMerge) {
-  std::shared_ptr<MergeOperator> merge_op =
-      MergeOperators::CreateStringAppendOperator();
-  std::unique_ptr<CompactionFilter> compaction_filter(
-      new FilterAllKeysCompactionFilter());
-  RunTest({test::KeyStr("a", 3, kTypeMerge), test::KeyStr("a", 2, kTypeMerge),
-           test::KeyStr("a", 1, kTypeMerge)},
-          {"v3", "v2", "v1"}, {test::KeyStr("a", 3, kTypeMerge)}, {"v3"},
-          2 /*last_committed_seq*/, merge_op.get(), compaction_filter.get());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_FullMerge) {
-  std::shared_ptr<MergeOperator> merge_op =
-      MergeOperators::CreateStringAppendOperator();
-  std::unique_ptr<CompactionFilter> compaction_filter(
-      new FilterAllKeysCompactionFilter());
-  RunTest(
-      {test::KeyStr("a", 3, kTypeMerge), test::KeyStr("a", 2, kTypeMerge),
-       test::KeyStr("a", 1, kTypeValue)},
-      {"v3", "v2", "v1"},
-      {test::KeyStr("a", 3, kTypeMerge), test::KeyStr("a", 1, kTypeDeletion)},
-      {"v3", ""}, 2 /*last_committed_seq*/, merge_op.get(),
-      compaction_filter.get());
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

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_iteration_stats.h

@@ -16,8 +16,6 @@ struct CompactionIterationStats {
   int64_t num_record_drop_obsolete = 0;
   int64_t num_record_drop_range_del = 0;
   int64_t num_range_del_drop_obsolete = 0;
-  // Deletions obsoleted before bottom level due to file gap optimization.
-  int64_t num_optimized_del_drop_obsolete = 0;
   uint64_t total_filter_time = 0;
 
   // Input statistics

db/compaction_iterator.cc

@@ -3,114 +3,69 @@
 //  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/compaction_iterator.h"
-#include "db/snapshot_checker.h"
-#include "port/likely.h"
-#include "rocksdb/listener.h"
+#include "db/compaction_iterator.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 {
 
 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, 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)
+    SequenceNumber earliest_write_conflict_snapshot, Env* env,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
+    const Compaction* compaction, const CompactionFilter* compaction_filter,
+    const std::atomic<bool>* shutting_down)
     : 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,
+          earliest_write_conflict_snapshot, env, 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) {}
 
 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,
+    SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
+    SequenceNumber earliest_write_conflict_snapshot, Env* env,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
     std::unique_ptr<CompactionProxy> compaction,
     const CompactionFilter* compaction_filter,
-    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 std::atomic<bool>* shutting_down)
     : input_(input),
       cmp_(cmp),
       merge_helper_(merge_helper),
       snapshots_(snapshots),
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
-      snapshot_checker_(snapshot_checker),
       env_(env),
-      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),
-      current_user_key_sequence_(0),
-      current_user_key_snapshot_(0),
-      merge_out_iter_(merge_helper_),
-      current_key_committed_(false),
-      info_log_(info_log) {
+      merge_out_iter_(merge_helper_) {
   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;
+    earliest_snapshot_ = last_sequence;
     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 && 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() {
@@ -124,7 +79,6 @@ void CompactionIterator::ResetRecordCounts() {
   iter_stats_.num_record_drop_obsolete = 0;
   iter_stats_.num_record_drop_range_del = 0;
   iter_stats_.num_range_del_drop_obsolete = 0;
-  iter_stats_.num_optimized_del_drop_obsolete = 0;
 }
 
 void CompactionIterator::SeekToFirst() {
@@ -142,19 +96,14 @@ void CompactionIterator::Next() {
     if (merge_out_iter_.Valid()) {
       key_ = merge_out_iter_.key();
       value_ = merge_out_iter_.value();
-      bool valid_key __attribute__((__unused__));
-      valid_key =  ParseInternalKey(key_, &ikey_);
+      bool valid_key __attribute__((__unused__)) =
+          ParseInternalKey(key_, &ikey_);
       // MergeUntil stops when it encounters a corrupt key and does not
       // include them in the result, so we expect the keys here to be valid.
       assert(valid_key);
-      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();
+      key_ = current_key_.GetKey();
       ikey_.user_key = current_key_.GetUserKey();
       valid_ = true;
     } else {
@@ -182,65 +131,11 @@ void CompactionIterator::Next() {
   PrepareOutput();
 }
 
-void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
-                                              Slice* skip_until) {
-  if (compaction_filter_ != nullptr &&
-      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex)) {
-    // If the user has specified a compaction filter and the sequence
-    // number is greater than any external snapshot, then invoke the
-    // filter. If the return value of the compaction filter is true,
-    // replace the entry with a deletion marker.
-    CompactionFilter::Decision filter;
-    compaction_filter_value_.clear();
-    compaction_filter_skip_until_.Clear();
-    CompactionFilter::ValueType value_type =
-        ikey_.type == kTypeValue ? CompactionFilter::ValueType::kValue
-                                 : CompactionFilter::ValueType::kBlobIndex;
-    // Hack: pass internal key to BlobIndexCompactionFilter since it needs
-    // to get sequence number.
-    Slice& filter_key = ikey_.type == kTypeValue ? ikey_.user_key : key_;
-    {
-      StopWatchNano timer(env_, report_detailed_time_);
-      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;
-    }
-
-    if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
-        cmp_->Compare(*compaction_filter_skip_until_.rep(), ikey_.user_key) <=
-            0) {
-      // Can't skip to a key smaller than the current one.
-      // Keep the key as per FilterV2 documentation.
-      filter = CompactionFilter::Decision::kKeep;
-    }
-
-    if (filter == CompactionFilter::Decision::kRemove) {
-      // convert the current key to a delete; key_ is pointing into
-      // current_key_ at this point, so updating current_key_ updates key()
-      ikey_.type = kTypeDeletion;
-      current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
-      // no value associated with delete
-      value_.clear();
-      iter_stats_.num_record_drop_user++;
-    } else if (filter == CompactionFilter::Decision::kChangeValue) {
-      value_ = compaction_filter_value_;
-    } else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
-      *need_skip = true;
-      compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
-                                                       kValueTypeForSeek);
-      *skip_until = compaction_filter_skip_until_.Encode();
-    }
-  }
-}
-
 void CompactionIterator::NextFromInput() {
   at_next_ = false;
   valid_ = false;
 
-  while (!valid_ && input_->Valid() && !IsPausingManualCompaction() &&
-         !IsShuttingDown()) {
+  while (!valid_ && input_->Valid() && !IsShuttingDown()) {
     key_ = input_->key();
     value_ = input_->value();
     iter_stats_.num_input_records++;
@@ -254,7 +149,7 @@ void CompactionIterator::NextFromInput() {
         status_ = Status::Corruption("Corrupted internal key not expected.");
         break;
       }
-      key_ = current_key_.SetInternalKey(key_);
+      key_ = current_key_.SetKey(key_);
       has_current_user_key_ = false;
       current_user_key_sequence_ = kMaxSequenceNumber;
       current_user_key_snapshot_ = 0;
@@ -262,7 +157,6 @@ void CompactionIterator::NextFromInput() {
       valid_ = true;
       break;
     }
-    TEST_SYNC_POINT_CALLBACK("CompactionIterator:ProcessKV", &ikey_);
 
     // Update input statistics
     if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
@@ -285,18 +179,58 @@ void CompactionIterator::NextFromInput() {
         !cmp_->Equal(ikey_.user_key, current_user_key_)) {
       // First occurrence of this user key
       // Copy key for output
-      key_ = current_key_.SetInternalKey(key_, &ikey_);
+      key_ = current_key_.SetKey(key_, &ikey_);
       current_user_key_ = ikey_.user_key;
       has_current_user_key_ = true;
       has_outputted_key_ = false;
       current_user_key_sequence_ = kMaxSequenceNumber;
       current_user_key_snapshot_ = 0;
-      current_key_committed_ = KeyCommitted(ikey_.sequence);
 
-      // Apply the compaction filter to the first committed version of the user
-      // key.
-      if (current_key_committed_) {
-        InvokeFilterIfNeeded(&need_skip, &skip_until);
+      // apply the compaction filter to the first occurrence of the user key
+      if (compaction_filter_ != nullptr && ikey_.type == kTypeValue &&
+          (visible_at_tip_ || ikey_.sequence > latest_snapshot_ ||
+           ignore_snapshots_)) {
+        // If the user has specified a compaction filter and the sequence
+        // number is greater than any external snapshot, then invoke the
+        // filter. If the return value of the compaction filter is true,
+        // replace the entry with a deletion marker.
+        CompactionFilter::Decision filter;
+        compaction_filter_value_.clear();
+        compaction_filter_skip_until_.Clear();
+        {
+          StopWatchNano timer(env_, true);
+          filter = compaction_filter_->FilterV2(
+              compaction_->level(), ikey_.user_key,
+              CompactionFilter::ValueType::kValue, value_,
+              &compaction_filter_value_, compaction_filter_skip_until_.rep());
+          iter_stats_.total_filter_time +=
+              env_ != nullptr ? timer.ElapsedNanos() : 0;
+        }
+
+        if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
+            cmp_->Compare(*compaction_filter_skip_until_.rep(),
+                          ikey_.user_key) <= 0) {
+          // Can't skip to a key smaller than the current one.
+          // Keep the key as per FilterV2 documentation.
+          filter = CompactionFilter::Decision::kKeep;
+        }
+
+        if (filter == CompactionFilter::Decision::kRemove) {
+          // convert the current key to a delete; key_ is pointing into
+          // current_key_ at this point, so updating current_key_ updates key()
+          ikey_.type = kTypeDeletion;
+          current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
+          // no value associated with delete
+          value_.clear();
+          iter_stats_.num_record_drop_user++;
+        } else if (filter == CompactionFilter::Decision::kChangeValue) {
+          value_ = compaction_filter_value_;
+        } else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
+          need_skip = true;
+          compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
+                                                           kValueTypeForSeek);
+          skip_until = compaction_filter_skip_until_.Encode();
+        }
       }
     } else {
       // Update the current key to reflect the new sequence number/type without
@@ -305,34 +239,15 @@ void CompactionIterator::NextFromInput() {
       // Need to have the compaction filter process multiple versions
       // if we have versions on both sides of a snapshot
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      key_ = current_key_.GetInternalKey();
+      key_ = current_key_.GetKey();
       ikey_.user_key = current_key_.GetUserKey();
-
-      // Note that newer version of a key is ordered before older versions. If a
-      // newer version of a key is committed, so as the older version. No need
-      // to query snapshot_checker_ in that case.
-      if (UNLIKELY(!current_key_committed_)) {
-        assert(snapshot_checker_ != nullptr);
-        current_key_committed_ = KeyCommitted(ikey_.sequence);
-        // Apply the compaction filter to the first committed version of the
-        // user key.
-        if (current_key_committed_) {
-          InvokeFilterIfNeeded(&need_skip, &skip_until);
-        }
-      }
-    }
-
-    if (UNLIKELY(!current_key_committed_)) {
-      assert(snapshot_checker_ != nullptr);
-      valid_ = true;
-      break;
     }
 
     // If there are no snapshots, then this kv affect visibility at tip.
     // Otherwise, search though all existing snapshots to find the earliest
     // snapshot that is affected by this kv.
-    SequenceNumber last_sequence __attribute__((__unused__));
-    last_sequence = current_user_key_sequence_;
+    SequenceNumber last_sequence __attribute__((__unused__)) =
+        current_user_key_sequence_;
     current_user_key_sequence_ = ikey_.sequence;
     SequenceNumber last_snapshot = current_user_key_snapshot_;
     SequenceNumber prev_snapshot = 0;  // 0 means no previous snapshot
@@ -348,18 +263,7 @@ 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 +312,7 @@ void CompactionIterator::NextFromInput() {
           cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
         // Check whether the next key belongs to the same snapshot as the
         // SingleDelete.
-        if (prev_snapshot == 0 ||
-            DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot)) {
+        if (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot) {
           if (next_ikey.type == kTypeSingleDeletion) {
             // We encountered two SingleDeletes in a row.  This could be due to
             // unexpected user input.
@@ -420,9 +323,8 @@ void CompactionIterator::NextFromInput() {
             // input_->Next().
             ++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_)) {
+          } else if ((ikey_.sequence <= earliest_write_conflict_snapshot_) ||
+                     has_outputted_key_) {
             // Found a matching value, we can drop the single delete and the
             // value.  It is safe to drop both records since we've already
             // outputted a key in this snapshot, or there is no earlier
@@ -432,8 +334,7 @@ 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;
             }
 
@@ -470,16 +371,13 @@ 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_ &&
             compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                        &level_ptrs_)) {
           // Key doesn't exist outside of this range.
           // Can compact out this SingleDelete.
           ++iter_stats_.num_record_drop_obsolete;
           ++iter_stats_.num_single_del_fallthru;
-          if (!bottommost_level_) {
-            ++iter_stats_.num_optimized_del_drop_obsolete;
-          }
         } else {
           // Output SingleDelete
           valid_ = true;
@@ -489,30 +387,21 @@ 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: 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) &&
-               ikeyNotNeededForIncrementalSnapshot() &&
+               ikey_.sequence <= earliest_snapshot_ &&
                compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                           &level_ptrs_)) {
       // TODO(noetzli): This is the only place where we use compaction_
@@ -529,38 +418,8 @@ void CompactionIterator::NextFromInput() {
       //
       // Note:  Dropping this Delete will not affect TransactionDB
       // write-conflict checking since it is earlier than any snapshot.
-      //
-      // It seems that we can also drop deletion later than earliest snapshot
-      // given that:
-      // (1) The deletion is earlier than earliest_write_conflict_snapshot, and
-      // (2) No value exist earlier than the deletion.
       ++iter_stats_.num_record_drop_obsolete;
-      if (!bottommost_level_) {
-        ++iter_stats_.num_optimized_del_drop_obsolete;
-      }
       input_->Next();
-    } else if ((ikey_.type == 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(
@@ -585,18 +444,14 @@ void CompactionIterator::NextFromInput() {
         //       These will be correctly set below.
         key_ = merge_out_iter_.key();
         value_ = merge_out_iter_.value();
-        bool valid_key __attribute__((__unused__));
-        valid_key = ParseInternalKey(key_, &ikey_);
+        bool valid_key __attribute__((__unused__)) =
+            ParseInternalKey(key_, &ikey_);
         // MergeUntil stops when it encounters a corrupt key and does not
         // include them in the result, so we expect the keys here to valid.
         assert(valid_key);
-        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();
+        key_ = current_key_.GetKey();
         ikey_.user_key = current_key_.GetUserKey();
         valid_ = true;
       } else {
@@ -614,7 +469,7 @@ 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;
@@ -632,143 +487,41 @@ 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_);
+  // 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.
 
-      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);
-    }
+  // This is safe for TransactionDB write-conflict checking since transactions
+  // only care about sequence number larger than any active snapshots.
+  if (bottommost_level_ && valid_ && ikey_.sequence < earliest_snapshot_ &&
+      ikey_.type != kTypeMerge &&
+      !cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
+    assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
+    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 __attribute__((__unused__)) = kMaxSequenceNumber;
+  for (const auto cur : *snapshots_) {
+    assert(prev == kMaxSequenceNumber || prev <= cur);
+    if (cur >= in) {
+      *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;
 }
 
-// used in 2 places - prevents deletion markers to be dropped if they may be
-// needed and disables seqnum zero-out in PrepareOutput for recent keys.
-inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
-  return (!compaction_->preserve_deletes()) ||
-         (ikey_.sequence < preserve_deletes_seqnum_);
-}
-
-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

@@ -7,16 +7,13 @@
 #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"
-#include "db/snapshot_checker.h"
-#include "options/cf_options.h"
 #include "rocksdb/compaction_filter.h"
 
 namespace rocksdb {
@@ -31,7 +28,7 @@ class CompactionIterator {
         : compaction_(compaction) {}
 
     virtual ~CompactionProxy() = default;
-    virtual int level(size_t /*compaction_input_level*/ = 0) const {
+    virtual int level(size_t compaction_input_level = 0) const {
       return compaction_->level();
     }
     virtual bool KeyNotExistsBeyondOutputLevel(
@@ -45,12 +42,6 @@ class CompactionIterator {
     virtual Slice GetLargestUserKey() const {
       return compaction_->GetLargestUserKey();
     }
-    virtual bool allow_ingest_behind() const {
-      return compaction_->immutable_cf_options()->allow_ingest_behind;
-    }
-    virtual bool preserve_deletes() const {
-      return compaction_->immutable_cf_options()->preserve_deletes;
-    }
 
    protected:
     CompactionProxy() = default;
@@ -59,34 +50,26 @@ 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, 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);
 
   // 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, 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);
 
   ~CompactionIterator();
 
@@ -120,9 +103,6 @@ class CompactionIterator {
   // compression.
   void PrepareOutput();
 
-  // Invoke compaction filter if needed.
-  void InvokeFilterIfNeeded(bool* need_skip, Slice* skip_until);
-
   // Given a sequence number, return the sequence number of the
   // earliest snapshot that this sequence number is visible in.
   // The snapshots themselves are arranged in ascending order of
@@ -132,46 +112,23 @@ class CompactionIterator {
   inline SequenceNumber findEarliestVisibleSnapshot(
       SequenceNumber in, SequenceNumber* prev_snapshot);
 
-  // Checks whether the currently seen ikey_ is needed for
-  // incremental (differential) snapshot and hence can't be dropped
-  // or seqnum be zero-ed out even if all other conditions for it are met.
-  inline bool ikeyNotNeededForIncrementalSnapshot();
-
-  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
   //
@@ -221,20 +178,9 @@ class CompactionIterator {
   std::vector<size_t> level_ptrs_;
   CompactionIterationStats iter_stats_;
 
-  // Used to avoid purging uncommitted values. The application can specify
-  // uncommitted values by providing a SnapshotChecker object.
-  bool current_key_committed_;
-  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

@@ -0,0 +1,462 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/compaction_iterator.h"
+
+#include <string>
+#include <vector>
+
+#include "port/port.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+
+namespace rocksdb {
+
+// Expects no merging attempts.
+class NoMergingMergeOp : public MergeOperator {
+ public:
+  bool FullMergeV2(const MergeOperationInput& merge_in,
+                   MergeOperationOutput* merge_out) const override {
+    ADD_FAILURE();
+    return false;
+  }
+  bool PartialMergeMulti(const Slice& key,
+                         const std::deque<Slice>& operand_list,
+                         std::string* new_value,
+                         Logger* logger) const override {
+    ADD_FAILURE();
+    return false;
+  }
+  const char* Name() const override {
+    return "CompactionIteratorTest NoMergingMergeOp";
+  }
+};
+
+// Compaction filter that gets stuck when it sees a particular key,
+// then gets unstuck when told to.
+// Always returns Decition::kRemove.
+class StallingFilter : public CompactionFilter {
+ public:
+  virtual Decision FilterV2(int level, const Slice& key, ValueType t,
+                            const Slice& existing_value, std::string* new_value,
+                            std::string* skip_until) const override {
+    int k = std::atoi(key.ToString().c_str());
+    last_seen.store(k);
+    while (k >= stall_at.load()) {
+      std::this_thread::yield();
+    }
+    return Decision::kRemove;
+  }
+
+  const char* Name() const override {
+    return "CompactionIteratorTest StallingFilter";
+  }
+
+  // Wait until the filter sees a key >= k and stalls at that key.
+  // If `exact`, asserts that the seen key is equal to k.
+  void WaitForStall(int k, bool exact = true) {
+    stall_at.store(k);
+    while (last_seen.load() < k) {
+      std::this_thread::yield();
+    }
+    if (exact) {
+      EXPECT_EQ(k, last_seen.load());
+    }
+  }
+
+  // Filter will stall on key >= stall_at. Advance stall_at to unstall.
+  mutable std::atomic<int> stall_at{0};
+  // Last key the filter was called with.
+  mutable std::atomic<int> last_seen{0};
+};
+
+class LoggingForwardVectorIterator : public InternalIterator {
+ public:
+  struct Action {
+    enum class Type {
+      SEEK_TO_FIRST,
+      SEEK,
+      NEXT,
+    };
+
+    Type type;
+    std::string arg;
+
+    explicit Action(Type _type, std::string _arg = "")
+        : type(_type), arg(_arg) {}
+
+    bool operator==(const Action& rhs) const {
+      return std::tie(type, arg) == std::tie(rhs.type, rhs.arg);
+    }
+  };
+
+  LoggingForwardVectorIterator(const std::vector<std::string>& keys,
+                               const std::vector<std::string>& values)
+      : keys_(keys), values_(values), current_(keys.size()) {
+    assert(keys_.size() == values_.size());
+  }
+
+  virtual bool Valid() const override { return current_ < keys_.size(); }
+
+  virtual void SeekToFirst() override {
+    log.emplace_back(Action::Type::SEEK_TO_FIRST);
+    current_ = 0;
+  }
+  virtual void SeekToLast() override { assert(false); }
+
+  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();
+  }
+
+  virtual void SeekForPrev(const Slice& target) override { assert(false); }
+
+  virtual void Next() override {
+    assert(Valid());
+    log.emplace_back(Action::Type::NEXT);
+    current_++;
+  }
+  virtual void Prev() override { assert(false); }
+
+  virtual Slice key() const override {
+    assert(Valid());
+    return Slice(keys_[current_]);
+  }
+  virtual Slice value() const override {
+    assert(Valid());
+    return Slice(values_[current_]);
+  }
+
+  virtual Status status() const override { return Status::OK(); }
+
+  std::vector<Action> log;
+
+ private:
+  std::vector<std::string> keys_;
+  std::vector<std::string> values_;
+  size_t current_;
+};
+
+class FakeCompaction : public CompactionIterator::CompactionProxy {
+ public:
+  FakeCompaction() = default;
+
+  virtual int level(size_t compaction_input_level) const { return 0; }
+  virtual bool KeyNotExistsBeyondOutputLevel(
+      const Slice& user_key, std::vector<size_t>* level_ptrs) const {
+    return key_not_exists_beyond_output_level;
+  }
+  virtual bool bottommost_level() const { return false; }
+  virtual int number_levels() const { return 1; }
+  virtual Slice GetLargestUserKey() const {
+    return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
+  }
+
+  bool key_not_exists_beyond_output_level = false;
+};
+
+class CompactionIteratorTest : public testing::Test {
+ public:
+  CompactionIteratorTest()
+      : cmp_(BytewiseComparator()), icmp_(cmp_), snapshots_({}) {}
+
+  void InitIterators(const std::vector<std::string>& ks,
+                     const std::vector<std::string>& vs,
+                     const std::vector<std::string>& range_del_ks,
+                     const std::vector<std::string>& range_del_vs,
+                     SequenceNumber last_sequence,
+                     MergeOperator* merge_op = nullptr,
+                     CompactionFilter* filter = nullptr) {
+    std::unique_ptr<InternalIterator> range_del_iter(
+        new test::VectorIterator(range_del_ks, range_del_vs));
+    range_del_agg_.reset(new RangeDelAggregator(icmp_, snapshots_));
+    ASSERT_OK(range_del_agg_->AddTombstones(std::move(range_del_iter)));
+
+    std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
+    if (filter) {
+      compaction_proxy_ = new FakeCompaction();
+      compaction.reset(compaction_proxy_);
+    }
+
+    merge_helper_.reset(new MergeHelper(Env::Default(), cmp_, merge_op, filter,
+                                        nullptr, false, 0, 0, nullptr,
+                                        &shutting_down_));
+    iter_.reset(new LoggingForwardVectorIterator(ks, vs));
+    iter_->SeekToFirst();
+    c_iter_.reset(new CompactionIterator(
+        iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
+        kMaxSequenceNumber, Env::Default(), false, range_del_agg_.get(),
+        std::move(compaction), filter, &shutting_down_));
+  }
+
+  void AddSnapshot(SequenceNumber snapshot) { snapshots_.push_back(snapshot); }
+
+  const Comparator* cmp_;
+  const InternalKeyComparator icmp_;
+  std::vector<SequenceNumber> snapshots_;
+  std::unique_ptr<MergeHelper> merge_helper_;
+  std::unique_ptr<LoggingForwardVectorIterator> iter_;
+  std::unique_ptr<CompactionIterator> c_iter_;
+  std::unique_ptr<RangeDelAggregator> range_del_agg_;
+  std::atomic<bool> shutting_down_{false};
+  FakeCompaction* compaction_proxy_;
+};
+
+// It is possible that the output of the compaction iterator is empty even if
+// the input is not.
+TEST_F(CompactionIteratorTest, EmptyResult) {
+  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
+                 test::KeyStr("a", 3, kTypeValue)},
+                {"", "val"}, {}, {}, 5);
+  c_iter_->SeekToFirst();
+  ASSERT_FALSE(c_iter_->Valid());
+}
+
+// If there is a corruption after a single deletion, the corrupted key should
+// be preserved.
+TEST_F(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
+  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
+                 test::KeyStr("a", 3, kTypeValue, true),
+                 test::KeyStr("b", 10, kTypeValue)},
+                {"", "val", "val2"}, {}, {}, 10);
+  c_iter_->SeekToFirst();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("a", 5, kTypeSingleDeletion),
+            c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("a", 3, kTypeValue, true), c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("b", 10, kTypeValue), c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_FALSE(c_iter_->Valid());
+}
+
+TEST_F(CompactionIteratorTest, SimpleRangeDeletion) {
+  InitIterators({test::KeyStr("morning", 5, kTypeValue),
+                 test::KeyStr("morning", 2, kTypeValue),
+                 test::KeyStr("night", 3, kTypeValue)},
+                {"zao", "zao", "wan"},
+                {test::KeyStr("ma", 4, kTypeRangeDeletion)}, {"mz"}, 5);
+  c_iter_->SeekToFirst();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValue), c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("night", 3, kTypeValue), c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_FALSE(c_iter_->Valid());
+}
+
+TEST_F(CompactionIteratorTest, RangeDeletionWithSnapshots) {
+  AddSnapshot(10);
+  std::vector<std::string> ks1;
+  ks1.push_back(test::KeyStr("ma", 28, kTypeRangeDeletion));
+  std::vector<std::string> vs1{"mz"};
+  std::vector<std::string> ks2{test::KeyStr("morning", 15, kTypeValue),
+                               test::KeyStr("morning", 5, kTypeValue),
+                               test::KeyStr("night", 40, kTypeValue),
+                               test::KeyStr("night", 20, kTypeValue)};
+  std::vector<std::string> vs2{"zao 15", "zao 5", "wan 40", "wan 20"};
+  InitIterators(ks2, vs2, ks1, vs1, 40);
+  c_iter_->SeekToFirst();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValue), c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("night", 40, kTypeValue), c_iter_->key().ToString());
+  c_iter_->Next();
+  ASSERT_FALSE(c_iter_->Valid());
+}
+
+TEST_F(CompactionIteratorTest, CompactionFilterSkipUntil) {
+  class Filter : public CompactionFilter {
+    virtual Decision FilterV2(int level, const Slice& key, ValueType t,
+                              const Slice& existing_value,
+                              std::string* new_value,
+                              std::string* skip_until) const override {
+      std::string k = key.ToString();
+      std::string v = existing_value.ToString();
+      // See InitIterators() call below for the sequence of keys and their
+      // filtering decisions. Here we closely assert that compaction filter is
+      // called with the expected keys and only them, and with the right values.
+      if (k == "a") {
+        EXPECT_EQ(ValueType::kValue, t);
+        EXPECT_EQ("av50", v);
+        return Decision::kKeep;
+      }
+      if (k == "b") {
+        EXPECT_EQ(ValueType::kValue, t);
+        EXPECT_EQ("bv60", v);
+        *skip_until = "d+";
+        return Decision::kRemoveAndSkipUntil;
+      }
+      if (k == "e") {
+        EXPECT_EQ(ValueType::kMergeOperand, t);
+        EXPECT_EQ("em71", v);
+        return Decision::kKeep;
+      }
+      if (k == "f") {
+        if (v == "fm65") {
+          EXPECT_EQ(ValueType::kMergeOperand, t);
+          *skip_until = "f";
+        } else {
+          EXPECT_EQ("fm30", v);
+          EXPECT_EQ(ValueType::kMergeOperand, t);
+          *skip_until = "g+";
+        }
+        return Decision::kRemoveAndSkipUntil;
+      }
+      if (k == "h") {
+        EXPECT_EQ(ValueType::kValue, t);
+        EXPECT_EQ("hv91", v);
+        return Decision::kKeep;
+      }
+      if (k == "i") {
+        EXPECT_EQ(ValueType::kMergeOperand, t);
+        EXPECT_EQ("im95", v);
+        *skip_until = "z";
+        return Decision::kRemoveAndSkipUntil;
+      }
+      ADD_FAILURE();
+      return Decision::kKeep;
+    }
+
+    const char* Name() const override {
+      return "CompactionIteratorTest.CompactionFilterSkipUntil::Filter";
+    }
+  };
+
+  NoMergingMergeOp merge_op;
+  Filter filter;
+  InitIterators(
+      {test::KeyStr("a", 50, kTypeValue),  // keep
+       test::KeyStr("a", 45, kTypeMerge),
+       test::KeyStr("b", 60, kTypeValue),  // skip to "d+"
+       test::KeyStr("b", 40, kTypeValue), test::KeyStr("c", 35, kTypeValue),
+       test::KeyStr("d", 70, kTypeMerge),
+       test::KeyStr("e", 71, kTypeMerge),  // keep
+       test::KeyStr("f", 65, kTypeMerge),  // skip to "f", aka keep
+       test::KeyStr("f", 30, kTypeMerge),  // skip to "g+"
+       test::KeyStr("f", 25, kTypeValue), test::KeyStr("g", 90, kTypeValue),
+       test::KeyStr("h", 91, kTypeValue),  // keep
+       test::KeyStr("i", 95, kTypeMerge),  // skip to "z"
+       test::KeyStr("j", 99, kTypeValue)},
+      {"av50", "am45", "bv60", "bv40", "cv35", "dm70", "em71", "fm65", "fm30",
+       "fv25", "gv90", "hv91", "im95", "jv99"},
+      {}, {}, kMaxSequenceNumber, &merge_op, &filter);
+
+  // Compaction should output just "a", "e" and "h" keys.
+  c_iter_->SeekToFirst();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("a", 50, kTypeValue), c_iter_->key().ToString());
+  ASSERT_EQ("av50", c_iter_->value().ToString());
+  c_iter_->Next();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("e", 71, kTypeMerge), c_iter_->key().ToString());
+  ASSERT_EQ("em71", c_iter_->value().ToString());
+  c_iter_->Next();
+  ASSERT_TRUE(c_iter_->Valid());
+  ASSERT_EQ(test::KeyStr("h", 91, kTypeValue), c_iter_->key().ToString());
+  ASSERT_EQ("hv91", c_iter_->value().ToString());
+  c_iter_->Next();
+  ASSERT_FALSE(c_iter_->Valid());
+
+  // Check that the compaction iterator did the correct sequence of calls on
+  // the underlying iterator.
+  using A = LoggingForwardVectorIterator::Action;
+  using T = A::Type;
+  std::vector<A> expected_actions = {
+      A(T::SEEK_TO_FIRST),
+      A(T::NEXT),
+      A(T::NEXT),
+      A(T::SEEK, test::KeyStr("d+", kMaxSequenceNumber, kValueTypeForSeek)),
+      A(T::NEXT),
+      A(T::NEXT),
+      A(T::SEEK, test::KeyStr("g+", kMaxSequenceNumber, kValueTypeForSeek)),
+      A(T::NEXT),
+      A(T::SEEK, test::KeyStr("z", kMaxSequenceNumber, kValueTypeForSeek))};
+  ASSERT_EQ(expected_actions, iter_->log);
+}
+
+TEST_F(CompactionIteratorTest, ShuttingDownInFilter) {
+  NoMergingMergeOp merge_op;
+  StallingFilter filter;
+  InitIterators(
+      {test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeValue),
+       test::KeyStr("3", 3, kTypeValue), test::KeyStr("4", 4, kTypeValue)},
+      {"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, &merge_op, &filter);
+  // Don't leave tombstones (kTypeDeletion) for filtered keys.
+  compaction_proxy_->key_not_exists_beyond_output_level = true;
+
+  std::atomic<bool> seek_done{false};
+  rocksdb::port::Thread compaction_thread([&] {
+    c_iter_->SeekToFirst();
+    EXPECT_FALSE(c_iter_->Valid());
+    EXPECT_TRUE(c_iter_->status().IsShutdownInProgress());
+    seek_done.store(true);
+  });
+
+  // Let key 1 through.
+  filter.WaitForStall(1);
+
+  // Shutdown during compaction filter call for key 2.
+  filter.WaitForStall(2);
+  shutting_down_.store(true);
+  EXPECT_FALSE(seek_done.load());
+
+  // Unstall filter and wait for SeekToFirst() to return.
+  filter.stall_at.store(3);
+  compaction_thread.join();
+  assert(seek_done.load());
+
+  // Check that filter was never called again.
+  EXPECT_EQ(2, filter.last_seen.load());
+}
+
+// Same as ShuttingDownInFilter, but shutdown happens during filter call for
+// a merge operand, not for a value.
+TEST_F(CompactionIteratorTest, ShuttingDownInMerge) {
+  NoMergingMergeOp merge_op;
+  StallingFilter filter;
+  InitIterators(
+      {test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeMerge),
+       test::KeyStr("3", 3, kTypeMerge), test::KeyStr("4", 4, kTypeValue)},
+      {"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, &merge_op, &filter);
+  compaction_proxy_->key_not_exists_beyond_output_level = true;
+
+  std::atomic<bool> seek_done{false};
+  rocksdb::port::Thread compaction_thread([&] {
+    c_iter_->SeekToFirst();
+    ASSERT_FALSE(c_iter_->Valid());
+    ASSERT_TRUE(c_iter_->status().IsShutdownInProgress());
+    seek_done.store(true);
+  });
+
+  // Let key 1 through.
+  filter.WaitForStall(1);
+
+  // Shutdown during compaction filter call for key 2.
+  filter.WaitForStall(2);
+  shutting_down_.store(true);
+  EXPECT_FALSE(seek_done.load());
+
+  // Unstall filter and wait for SeekToFirst() to return.
+  filter.stall_at.store(3);
+  compaction_thread.join();
+  assert(seek_done.load());
+
+  // Check that filter was never called again.
+  EXPECT_EQ(2, filter.last_seen.load());
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

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"
@@ -29,9 +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"
 #include "rocksdb/compaction_job_stats.h"
@@ -41,44 +38,35 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/db_options.h"
+#include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
 
-class Arena;
-class ErrorHandler;
 class MemTable;
-class SnapshotChecker;
 class TableCache;
 class Version;
 class VersionEdit;
 class VersionSet;
+class Arena;
 
-// 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 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,
+                const EnvOptions& env_options, VersionSet* versions,
+                const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
+                Directory* db_directory, Directory* output_directory,
+                Statistics* stats, InstrumentedMutex* db_mutex,
+                Status* db_bg_error,
                 std::vector<SequenceNumber> existing_snapshots,
                 SequenceNumber earliest_write_conflict_snapshot,
-                const SnapshotChecker* snapshot_checker,
                 std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
                 bool paranoid_file_checks, bool measure_io_stats,
                 const std::string& dbname,
-                CompactionJobStats* compaction_job_stats,
-                Env::Priority thread_pri,
-                const std::atomic<bool>* manual_compaction_paused = nullptr);
+                CompactionJobStats* compaction_job_stats);
 
   ~CompactionJob();
 
@@ -88,28 +76,17 @@ 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 +98,7 @@ 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 +127,17 @@ 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_;
   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
@@ -177,13 +149,10 @@ class CompactionJob {
   // should make sure not to remove evidence that a write occurred.
   SequenceNumber earliest_write_conflict_snapshot_;
 
-  const SnapshotChecker* const snapshot_checker_;
-
   std::shared_ptr<Cache> table_cache_;
 
   EventLogger* event_logger_;
 
-  // Is this compaction creating a file in the bottom most level?
   bool bottommost_level_;
   bool paranoid_file_checks_;
   bool measure_io_stats_;
@@ -191,8 +160,6 @@ class CompactionJob {
   std::vector<Slice> boundaries_;
   // Stores the approx size of keys covered in the range of each subcompaction
   std::vector<uint64_t> sizes_;
-  Env::WriteLifeTimeHint write_hint_;
-  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>
@@ -17,17 +21,13 @@
 #include <unordered_set>
 #include <utility>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/dbformat.h"
+#include "db/filename.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "db/write_batch_internal.h"
-#include "env/mock_env.h"
-#include "file/filename.h"
-#include "logging/logging.h"
 #include "memtable/hash_linklist_rep.h"
-#include "monitoring/statistics.h"
-#include "monitoring/thread_status_util.h"
 #include "port/stack_trace.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/compaction_filter.h"
@@ -45,18 +45,22 @@
 #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/hash.h"
+#include "util/logging.h"
+#include "util/mock_env.h"
 #include "util/mutexlock.h"
 #include "util/rate_limiter.h"
+#include "util/statistics.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+#include "util/thread_status_util.h"
 #include "utilities/merge_operators.h"
 
 #if !defined(IOS_CROSS_COMPILE)
@@ -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);
@@ -650,6 +654,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
   Options options;
   options.listeners.emplace_back(stats_checker);
   options.create_if_missing = true;
+  options.max_background_flushes = 0;
   // just enough setting to hold off auto-compaction.
   options.level0_file_num_compaction_trigger = kTestScale + 1;
   options.num_levels = 3;
@@ -802,7 +807,7 @@ 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 +816,7 @@ 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 +825,7 @@ 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 +834,7 @@ 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);
@@ -871,6 +876,7 @@ TEST_P(CompactionJobStatsTest, DeletionStatsTest) {
   Options options;
   options.listeners.emplace_back(stats_checker);
   options.create_if_missing = true;
+  options.max_background_flushes = 0;
   options.level0_file_num_compaction_trigger = kTestScale+1;
   options.num_levels = 3;
   options.compression = kNoCompression;
@@ -1030,7 +1036,7 @@ 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 +1045,5 @@ 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 +67,17 @@ 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 +90,11 @@ 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 +103,12 @@ 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 +125,6 @@ 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 +133,7 @@ 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(),
@@ -196,8 +142,6 @@ class CompactionJobTest : public testing::Test {
   }
 
   void SetLastSequence(const SequenceNumber sequence_number) {
-    versions_->SetLastAllocatedSequence(sequence_number + 1);
-    versions_->SetLastPublishedSequence(sequence_number + 1);
     versions_->SetLastSequence(sequence_number + 1);
   }
 
@@ -223,7 +167,7 @@ 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 +189,18 @@ 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 +225,7 @@ 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;
@@ -315,23 +242,19 @@ 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());
     mutex_.Lock();
     EventLogger event_logger(db_options_.info_log.get());
-    // TODO(yiwu) add a mock snapshot checker and add test for it.
-    SnapshotChecker* snapshot_checker = nullptr;
     CompactionJob compaction_job(
         0, &compaction, db_options_, env_options_, versions_.get(),
-        &shutting_down_, preserve_deletes_seqnum_, &log_buffer, nullptr,
-        nullptr, nullptr, &mutex_, &error_handler_, snapshots,
-        earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_,
-        Env::Priority::USER);
+        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, &mutex_,
+        &bg_error_, snapshots, earliest_write_conflict_snapshot, table_cache_,
+        &event_logger, false, false, dbname_, &compaction_job_stats_);
+
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 
     compaction_job.Prepare();
@@ -343,27 +266,19 @@ 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_;
@@ -375,13 +290,12 @@ class CompactionJobTest : public testing::Test {
   std::unique_ptr<VersionSet> versions_;
   InstrumentedMutex mutex_;
   std::atomic<bool> shutting_down_;
-  SequenceNumber preserve_deletes_seqnum_;
   std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
   CompactionJobStats compaction_job_stats_;
   ColumnFamilyData* cfd_;
   std::unique_ptr<CompactionFilter> compaction_filter_;
   std::shared_ptr<MergeOperator> merge_op_;
-  ErrorHandler error_handler_;
+  Status bg_error_;
 };
 
 TEST_F(CompactionJobTest, Simple) {
@@ -423,24 +337,6 @@ TEST_F(CompactionJobTest, SimpleDeletion) {
   RunCompaction({files}, expected_results);
 }
 
-TEST_F(CompactionJobTest, OutputNothing) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({{KeyStr("a", 1U, kTypeValue), "val"}});
-
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({{KeyStr("a", 2U, kTypeDeletion), ""}});
-
-  AddMockFile(file2);
-
-  auto expected_results = mock::MakeMockFile();
-
-  SetLastSequence(4U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
 TEST_F(CompactionJobTest, SimpleOverwrite) {
   NewDB();
 
@@ -456,7 +352,7 @@ 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 +405,7 @@ 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 +429,8 @@ 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 +457,7 @@ 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 +720,7 @@ 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 +904,13 @@ 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 +921,7 @@ 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

@@ -15,35 +15,20 @@
 #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"
 #include "rocksdb/options.h"
 #include "rocksdb/status.h"
+#include "util/cf_options.h"
 
 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; }
@@ -101,19 +84,15 @@ class CompactionPicker {
   void ReleaseCompactionFiles(Compaction* c, Status status);
 
   // Returns true if any one of the specified files are being compacted
-  bool AreFilesInCompaction(const std::vector<FileMetaData*>& files);
+  bool FilesInCompaction(const std::vector<FileMetaData*>& files);
 
   // Takes a list of CompactionInputFiles and returns a (manual) Compaction
   // object.
-  //
-  // Caller must provide a set of input files that has been passed through
-  // `SanitizeCompactionInputFiles` earlier. The lock should not be released
-  // between that call and this one.
-  Compaction* CompactFiles(const CompactionOptions& compact_options,
-                           const std::vector<CompactionInputFiles>& input_files,
-                           int output_level, VersionStorageInfo* vstorage,
-                           const MutableCFOptions& mutable_cf_options,
-                           uint32_t output_path_id);
+  Compaction* FormCompaction(
+      const CompactionOptions& compact_options,
+      const std::vector<CompactionInputFiles>& input_files, int output_level,
+      VersionStorageInfo* vstorage, const MutableCFOptions& mutable_cf_options,
+      uint32_t output_path_id);
 
   // Converts a set of compaction input file numbers into
   // a list of CompactionInputFiles.
@@ -123,6 +102,12 @@ class CompactionPicker {
       const VersionStorageInfo* vstorage,
       const CompactionOptions& compact_options) const;
 
+  // Used in universal compaction when the enabled_trivial_move
+  // option is set. Checks whether there are any overlapping files
+  // in the input. Returns true if the input files are non
+  // overlapping.
+  bool IsInputNonOverlapping(Compaction* c);
+
   // Is there currently a compaction involving level 0 taking place
   bool IsLevel0CompactionInProgress() const {
     return !level0_compactions_in_progress_.empty();
@@ -153,6 +138,7 @@ class CompactionPicker {
   void GetRange(const std::vector<CompactionInputFiles>& inputs,
                 InternalKey* smallest, InternalKey* largest) const;
 
+ protected:
   int NumberLevels() const { return ioptions_.num_levels; }
 
   // Add more files to the inputs on "level" to make sure that
@@ -165,15 +151,14 @@ class CompactionPicker {
   // populated.
   //
   // Will return false if it is impossible to apply this compaction.
-  bool ExpandInputsToCleanCut(const std::string& cf_name,
+  bool ExpandWhileOverlapping(const std::string& cf_name,
                               VersionStorageInfo* vstorage,
-                              CompactionInputFiles* inputs,
-                              InternalKey** next_smallest = nullptr);
+                              CompactionInputFiles* inputs);
 
   // Returns true if any one of the parent files are being compacted
-  bool IsRangeInCompaction(VersionStorageInfo* vstorage,
-                           const InternalKey* smallest,
-                           const InternalKey* largest, int level, int* index);
+  bool RangeInCompaction(VersionStorageInfo* vstorage,
+                         const InternalKey* smallest,
+                         const InternalKey* largest, int level, int* index);
 
   // Returns true if the key range that `inputs` files cover overlap with the
   // key range of a currently running compaction.
@@ -192,29 +177,6 @@ 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);
-
-  // Remove this compaction from the set of running compactions
-  void UnregisterCompaction(Compaction* c);
-
-  std::set<Compaction*>* level0_compactions_in_progress() {
-    return &level0_compactions_in_progress_;
-  }
-  std::unordered_set<Compaction*>* compactions_in_progress() {
-    return &compactions_in_progress_;
-  }
-
- protected:
   const ImmutableCFOptions& ioptions_;
 
 // A helper function to SanitizeCompactionInputFiles() that
@@ -225,6 +187,12 @@ class CompactionPicker {
       const ColumnFamilyMetaData& cf_meta, const int output_level) const;
 #endif  // ROCKSDB_LITE
 
+  // Register this compaction in the set of running compactions
+  void RegisterCompaction(Compaction* c);
+
+  // Remove this compaction from the set of running compactions
+  void UnregisterCompaction(Compaction* c);
+
   // Keeps track of all compactions that are running on Level0.
   // Protected by DB mutex
   std::set<Compaction*> level0_compactions_in_progress_;
@@ -236,9 +204,137 @@ 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;
+
+  // Pick a path ID to place a newly generated file, with its level
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            int level);
+
+ private:
+  // For the specfied level, pick a file that we want to compact.
+  // Returns false if there is no file to compact.
+  // If it returns true, inputs->files.size() will be exactly one.
+  // If level is 0 and there is already a compaction on that level, this
+  // function will return false.
+  bool PickCompactionBySize(VersionStorageInfo* vstorage, int level,
+                            int output_level, CompactionInputFiles* inputs,
+                            int* parent_index, int* base_index);
+
+  // If there is any file marked for compaction, put put it into inputs.
+  // This is still experimental. It will return meaningful results only if
+  // clients call experimental feature SuggestCompactRange()
+  void PickFilesMarkedForCompactionExperimental(const std::string& cf_name,
+                                                VersionStorageInfo* vstorage,
+                                                CompactionInputFiles* inputs,
+                                                int* level, int* output_level);
+};
+
 #ifndef ROCKSDB_LITE
-// A dummy compaction that never triggers any automatic
-// compaction.
+class UniversalCompactionPicker : public CompactionPicker {
+ public:
+  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
+                            const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+
+ private:
+  struct SortedRun {
+    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
+              uint64_t _compensated_file_size, bool _being_compacted)
+        : level(_level),
+          file(_file),
+          size(_size),
+          compensated_file_size(_compensated_file_size),
+          being_compacted(_being_compacted) {
+      assert(compensated_file_size > 0);
+      assert(level != 0 || file != nullptr);
+    }
+
+    void Dump(char* out_buf, size_t out_buf_size,
+              bool print_path = false) const;
+
+    // sorted_run_count is added into the string to print
+    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
+                      size_t sorted_run_count) const;
+
+    int level;
+    // `file` Will be null for level > 0. For level = 0, the sorted run is
+    // for this file.
+    FileMetaData* file;
+    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
+    // files in the level. `being_compacted` should be the same for all files
+    // in a non-zero level. Use the value here.
+    uint64_t size;
+    uint64_t compensated_file_size;
+    bool being_compacted;
+  };
+
+  // Pick Universal compaction to limit read amplification
+  Compaction* PickCompactionUniversalReadAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score, unsigned int ratio,
+      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
+      LogBuffer* log_buffer);
+
+  // Pick Universal compaction to limit space amplification.
+  Compaction* PickCompactionUniversalSizeAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  static std::vector<SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions);
+
+  // Pick a path ID to place a newly generated file, with its estimated file
+  // size.
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            uint64_t file_size);
+};
+
+class FIFOCompactionPicker : public CompactionPicker {
+ public:
+  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
+                       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;
+};
+
 class NullCompactionPicker : public CompactionPicker {
  public:
   NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -247,67 +343,36 @@ 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;
   }
 
   // Always return "nullptr"
-  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 {
+  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 {
     return nullptr;
   }
 
   // Always returns false.
   virtual bool NeedsCompaction(
-      const VersionStorageInfo* /*vstorage*/) const override {
+      const VersionStorageInfo* vstorage) const override {
     return false;
   }
 };
 #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 +3,23 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-
+#include "db/compaction.h"
+#include "db/compaction_picker.h"
 #include <limits>
 #include <string>
 #include <utility>
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/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 +54,14 @@ 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 +80,17 @@ 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}});
@@ -181,8 +174,6 @@ TEST_F(CompactionPickerTest, Level1Trigger) {
 }
 
 TEST_F(CompactionPickerTest, Level1Trigger2) {
-  mutable_cf_options_.target_file_size_base = 10000000000;
-  mutable_cf_options_.RefreshDerivedOptions(ioptions_);
   NewVersionStorage(6, kCompactionStyleLevel);
   Add(1, 66U, "150", "200", 1000000001U);
   Add(1, 88U, "201", "300", 1000000000U);
@@ -199,15 +190,14 @@ TEST_F(CompactionPickerTest, Level1Trigger2) {
   ASSERT_EQ(66U, compaction->input(0, 0)->fd.GetNumber());
   ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
   ASSERT_EQ(7U, compaction->input(1, 1)->fd.GetNumber());
-  ASSERT_EQ(uint64_t{1073741824}, compaction->OutputFilePreallocationSize());
 }
 
 TEST_F(CompactionPickerTest, LevelMaxScore) {
   NewVersionStorage(6, kCompactionStyleLevel);
   mutable_cf_options_.target_file_size_base = 10000000;
+  mutable_cf_options_.target_file_size_multiplier = 10;
   mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
-  mutable_cf_options_.RefreshDerivedOptions(ioptions_);
-  Add(0, 1U, "150", "200", 1000000U);
+  Add(0, 1U, "150", "200", 1000000000U);
   // Level 1 score 1.2
   Add(1, 66U, "150", "200", 6000000U);
   Add(1, 88U, "201", "300", 6000000U);
@@ -227,9 +217,6 @@ TEST_F(CompactionPickerTest, LevelMaxScore) {
   ASSERT_TRUE(compaction.get() != nullptr);
   ASSERT_EQ(1U, compaction->num_input_files(0));
   ASSERT_EQ(7U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(mutable_cf_options_.target_file_size_base +
-                mutable_cf_options_.target_file_size_base / 10,
-            compaction->OutputFilePreallocationSize());
 }
 
 TEST_F(CompactionPickerTest, NeedsCompactionLevel) {
@@ -395,10 +382,10 @@ 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;
@@ -412,36 +399,6 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
               vstorage_->CompactionScore(0) >= 1);
   }
 }
-
-TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
-  const uint64_t kFileSize = 100000;
-  NewVersionStorage(1, kCompactionStyleUniversal);
-  ioptions_.allow_ingest_behind = true;
-  ioptions_.num_levels = 3;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
-  // must return false when there's no files.
-  ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
-            false);
-
-  NewVersionStorage(3, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 2U, "201", "250", kFileSize, 0, 401, 450);
-  Add(0, 4U, "260", "300", kFileSize, 0, 260, 300);
-  Add(1, 5U, "100", "151", kFileSize, 0, 200, 251);
-  Add(1, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(2, 6U, "120", "200", kFileSize, 0, 20, 100);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  // output level should be the one above the bottom-most
-  ASSERT_EQ(1, compaction->output_level());
-}
 // Tests if the files can be trivially moved in multi level
 // universal compaction when allow_trivial_move option is set
 // In this test as the input files overlaps, they cannot
@@ -450,10 +407,9 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
 TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
   const uint64_t kFileSize = 100000;
 
-  mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
+  ioptions_.compaction_options_universal.allow_trivial_move = true;
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);
@@ -482,7 +438,7 @@ TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
 TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
   const uint64_t kFileSize = 100000;
 
-  mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
+  ioptions_.compaction_options_universal.allow_trivial_move = true;
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
 
   NewVersionStorage(3, kCompactionStyleUniversal);
@@ -502,168 +458,6 @@ 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 =
@@ -672,7 +466,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   const uint64_t kMaxSize = kFileSize * kFileCount / 2;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  ioptions_.compaction_options_fifo = fifo_options_;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
   UpdateVersionStorageInfo();
   // must return false when there's no files.
@@ -688,7 +482,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
         kFileSize, 0, i * 100, i * 100 + 99);
     current_size += kFileSize;
     UpdateVersionStorageInfo();
-    ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()),
+    ASSERT_EQ(level_compaction_picker.NeedsCompaction(vstorage_.get()),
               vstorage_->CompactionScore(0) >= 1);
   }
 }
@@ -697,10 +491,9 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
 TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
   NewVersionStorage(6, kCompactionStyleLevel);
   ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.target_file_size_base = 100000000000;
+  mutable_cf_options_.target_file_size_base = 10000000;
   mutable_cf_options_.target_file_size_multiplier = 10;
   mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
-  mutable_cf_options_.RefreshDerivedOptions(ioptions_);
 
   Add(2, 6U, "150", "179", 50000000U);
   Add(2, 7U, "180", "220", 50000000U);
@@ -720,8 +513,6 @@ TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
   ASSERT_EQ(1U, compaction->num_input_files(0));
   // Pick file 8 because it overlaps with 0 files on level 3.
   ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
-  // Compaction input size * 1.1
-  ASSERT_GE(uint64_t{55000000}, compaction->OutputFilePreallocationSize());
 }
 
 TEST_F(CompactionPickerTest, CompactionPriMinOverlapping2) {
@@ -781,35 +572,6 @@ 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) {
@@ -1060,80 +822,6 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys9) {
   ASSERT_EQ(8U, compaction->input(1, 1)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, OverlappingUserKeys10) {
-  // Locked file encountered when pulling in extra input-level files with same
-  // user keys. Verify we pick the next-best file from the same input level.
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_compaction_bytes = 100000000000u;
-
-  // file_number 2U is largest and thus first choice. But it overlaps with
-  // file_number 1U which is being compacted. So instead we pick the next-
-  // biggest file, 3U, which is eligible for compaction.
-  Add(1 /* level */, 1U /* file_number */, "100" /* smallest */,
-      "150" /* largest */, 1U /* file_size */);
-  file_map_[1U].first->being_compacted = true;
-  Add(1 /* level */, 2U /* file_number */, "150" /* smallest */,
-      "200" /* largest */, 1000000000U /* file_size */, 0 /* smallest_seq */,
-      0 /* largest_seq */);
-  Add(1 /* level */, 3U /* file_number */, "201" /* smallest */,
-      "250" /* largest */, 900000000U /* file_size */);
-  Add(2 /* level */, 4U /* file_number */, "100" /* smallest */,
-      "150" /* largest */, 1U /* file_size */);
-  Add(2 /* level */, 5U /* file_number */, "151" /* smallest */,
-      "200" /* largest */, 1U /* file_size */);
-  Add(2 /* level */, 6U /* file_number */, "201" /* smallest */,
-      "250" /* largest */, 1U /* file_size */);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(1U, compaction->num_input_files(1));
-  ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, OverlappingUserKeys11) {
-  // Locked file encountered when pulling in extra output-level files with same
-  // user keys. Expected to skip that compaction and pick the next-best choice.
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_compaction_bytes = 100000000000u;
-
-  // score(L1) = 3.7
-  // score(L2) = 1.85
-  // There is no eligible file in L1 to compact since both candidates pull in
-  // file_number 5U, which overlaps with a file pending compaction (6U). The
-  // first eligible compaction is from L2->L3.
-  Add(1 /* level */, 2U /* file_number */, "151" /* smallest */,
-      "200" /* largest */, 1000000000U /* file_size */);
-  Add(1 /* level */, 3U /* file_number */, "201" /* smallest */,
-      "250" /* largest */, 1U /* file_size */);
-  Add(2 /* level */, 4U /* file_number */, "100" /* smallest */,
-      "149" /* largest */, 5000000000U /* file_size */);
-  Add(2 /* level */, 5U /* file_number */, "150" /* smallest */,
-      "201" /* largest */, 1U /* file_size */);
-  Add(2 /* level */, 6U /* file_number */, "201" /* smallest */,
-      "249" /* largest */, 1U /* file_size */, 0 /* smallest_seq */,
-      0 /* largest_seq */);
-  file_map_[6U].first->being_compacted = true;
-  Add(3 /* level */, 7U /* file_number */, "100" /* smallest */,
-      "149" /* largest */, 1U /* file_size */);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(1U, compaction->num_input_files(1));
-  ASSERT_EQ(4U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(7U, compaction->input(1, 0)->fd.GetNumber());
-}
-
 TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri1) {
   NewVersionStorage(6, kCompactionStyleLevel);
   mutable_cf_options_.level0_file_num_compaction_trigger = 2;
@@ -1232,7 +920,7 @@ TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri3) {
 TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded1) {
   int num_levels = ioptions_.num_levels;
   ioptions_.level_compaction_dynamic_level_bytes = false;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 4;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
   mutable_cf_options_.max_bytes_for_level_base = 1000;
   mutable_cf_options_.max_bytes_for_level_multiplier = 10;
   NewVersionStorage(num_levels, kCompactionStyleLevel);
@@ -1322,8 +1010,7 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
 
   // Set Last level size 50000
   // num_levels - 1 target 5000
-  // num_levels - 2 is base level with target 1000 (rounded up to
-  // max_bytes_for_level_base).
+  // num_levels - 2 is base level with taret 500
   Add(num_levels - 1, 10U, "400", "500", 50000);
 
   Add(0, 1U, "150", "200", 200);
@@ -1332,16 +1019,16 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
   Add(0, 5U, "150", "200", 200);
   Add(0, 6U, "150", "200", 200);
   // num_levels - 3 is over target by 100 + 1000
-  Add(num_levels - 3, 7U, "400", "500", 550);
-  Add(num_levels - 3, 8U, "600", "700", 550);
+  Add(num_levels - 3, 7U, "400", "500", 300);
+  Add(num_levels - 3, 8U, "600", "700", 300);
   // num_levels - 2 is over target by 1100 + 200
   Add(num_levels - 2, 9U, "150", "200", 5200);
 
   UpdateVersionStorageInfo();
 
-  // Merging to the second last level: (5200 / 2100 + 1) * 1100
+  // Merging to the second last level: (5200 / 1600 + 1) * 1100
   // Merging to the last level: (50000 / 6300 + 1) * 1300
-  ASSERT_EQ(2100u + 3823u + 11617u,
+  ASSERT_EQ(1600u + 4675u + 11617u,
             vstorage_->estimated_compaction_needed_bytes());
 }
 
@@ -1598,140 +1285,6 @@ TEST_F(CompactionPickerTest, IsTrivialMoveOff) {
   ASSERT_FALSE(compaction->IsTrivialMove());
 }
 
-TEST_F(CompactionPickerTest, CacheNextCompactionIndex) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_compaction_bytes = 100000000000u;
-
-  Add(1 /* level */, 1U /* file_number */, "100" /* smallest */,
-      "149" /* largest */, 1000000000U /* file_size */);
-  file_map_[1U].first->being_compacted = true;
-  Add(1 /* level */, 2U /* file_number */, "150" /* smallest */,
-      "199" /* largest */, 900000000U /* file_size */);
-  Add(1 /* level */, 3U /* file_number */, "200" /* smallest */,
-      "249" /* largest */, 800000000U /* file_size */);
-  Add(1 /* level */, 4U /* file_number */, "250" /* smallest */,
-      "299" /* largest */, 700000000U /* file_size */);
-  Add(2 /* level */, 5U /* file_number */, "150" /* smallest */,
-      "199" /* largest */, 1U /* file_size */);
-  file_map_[5U].first->being_compacted = true;
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(0U, compaction->num_input_files(1));
-  ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(2, vstorage_->NextCompactionIndex(1 /* level */));
-
-  compaction.reset(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(0U, compaction->num_input_files(1));
-  ASSERT_EQ(4U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(3, vstorage_->NextCompactionIndex(1 /* level */));
-
-  compaction.reset(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() == nullptr);
-  ASSERT_EQ(4, vstorage_->NextCompactionIndex(1 /* level */));
-}
-
-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/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

@@ -8,68 +8,18 @@
 
 #include "rocksdb/convenience.h"
 
-#include "db/db_impl/db_impl.h"
-#include "util/cast_util.h"
+#include "db/db_impl.h"
 
 namespace rocksdb {
 
 void CancelAllBackgroundWork(DB* db, bool wait) {
-  (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
-      ->CancelAllBackgroundWork(wait);
+  (dynamic_cast<DBImpl*>(db))->CancelAllBackgroundWork(wait);
 }
 
 Status DeleteFilesInRange(DB* db, ColumnFamilyHandle* column_family,
-                          const Slice* begin, const Slice* end,
-                          bool include_end) {
-  RangePtr range(begin, end);
-  return DeleteFilesInRanges(db, column_family, &range, 1, include_end);
-}
-
-Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
-                           const RangePtr* ranges, size_t n,
-                           bool include_end) {
-  return (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
-      ->DeleteFilesInRanges(column_family, ranges, n, include_end);
-}
-
-Status VerifySstFileChecksum(const Options& options,
-                             const EnvOptions& env_options,
-                             const std::string& file_path) {
-  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;
-  uint64_t file_size;
-  InternalKeyComparator internal_comparator(options.comparator);
-  ImmutableCFOptions ioptions(options);
-
-  Status s = ioptions.fs->NewRandomAccessFile(file_path,
-                                              FileOptions(env_options),
-                                              &file, nullptr);
-  if (s.ok()) {
-    s = ioptions.fs->GetFileSize(file_path, IOOptions(), &file_size, nullptr);
-  } else {
-    return s;
-  }
-  std::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 */),
-      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);
-  return s;
+                          const Slice* begin, const Slice* end) {
+  return (dynamic_cast<DBImpl*>(db))
+      ->DeleteFilesInRange(column_family, begin, end);
 }
 
 }  // namespace rocksdb

db/corruption_test.cc

@@ -11,27 +11,22 @@
 
 #include "rocksdb/db.h"
 
+#include <inttypes.h>
 #include <errno.h>
 #include <fcntl.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/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/string_util.h"
+#include "db/db_impl.h"
+#include "db/filename.h"
+#include "db/log_format.h"
+#include "db/version_set.h"
+#include "util/logging.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
@@ -41,7 +36,7 @@ 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 +47,7 @@ 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 +59,9 @@ 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 +73,7 @@ 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_;
@@ -161,7 +152,7 @@ class CorruptionTest : public testing::Test {
     struct stat sbuf;
     if (stat(fname.c_str(), &sbuf) != 0) {
       const char* msg = strerror(errno);
-      FAIL() << fname << ": " << msg;
+      ASSERT_TRUE(false) << fname << ": " << msg;
     }
 
     if (offset < 0) {
@@ -188,10 +179,6 @@ class CorruptionTest : public testing::Test {
     }
     s = WriteStringToFile(Env::Default(), contents, fname);
     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));
   }
 
   void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
@@ -226,7 +213,7 @@ class CorruptionTest : public testing::Test {
         return;
       }
     }
-    FAIL() << "no file found at level";
+    ASSERT_TRUE(false) << "no file found at level";
   }
 
 
@@ -325,60 +312,6 @@ TEST_F(CorruptionTest, TableFile) {
 
   Corrupt(kTableFile, 100, 1);
   Check(99, 99);
-  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) {
@@ -394,11 +327,9 @@ TEST_F(CorruptionTest, TableFileIndexData) {
   // corrupt an index block of an entire file
   Corrupt(kTableFile, -2000, 500);
   Reopen();
-  dbi = reinterpret_cast<DBImpl*>(db_);
-  // one full file 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);
-  ASSERT_NOK(dbi->VerifyChecksum());
+  Check(5000, 5000);
 }
 
 TEST_F(CorruptionTest, MissingDescriptor) {
@@ -458,12 +389,10 @@ TEST_F(CorruptionTest, CompactionInputError) {
 
   Corrupt(kTableFile, 100, 1);
   Check(9, 9);
-  ASSERT_NOK(dbi->VerifyChecksum());
 
   // Force compactions by writing lots of values
   Build(10000);
   Check(10000, 10000);
-  ASSERT_NOK(dbi->VerifyChecksum());
 }
 
 TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
@@ -495,7 +424,6 @@ TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
 
   CorruptTableFileAtLevel(0, 100, 1);
   Check(9, 9);
-  ASSERT_NOK(dbi->VerifyChecksum());
 
   // Write must eventually fail because of corrupted table
   Status s;
@@ -517,7 +445,6 @@ TEST_F(CorruptionTest, UnrelatedKeys) {
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
   Corrupt(kTableFile, 100, 1);
-  ASSERT_NOK(dbi->VerifyChecksum());
 
   std::string tmp1, tmp2;
   ASSERT_OK(db_->Put(WriteOptions(), Key(1000, &tmp1), Value(1000, &tmp2)));
@@ -529,40 +456,6 @@ 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 +474,7 @@ 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 +499,7 @@ 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 +5,14 @@
 
 #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/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
-#include "util/string_util.h"
+#include "table/cuckoo_table_factory.h"
+#include "table/cuckoo_table_reader.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
@@ -25,13 +24,13 @@ 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()));
   }
@@ -241,7 +240,7 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
 
   // Write 28 values, each 10016 B ~ 10KB
   for (int idx = 0; idx < 28; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + char(idx))));
+    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
   }
   dbfull()->TEST_WaitForFlushMemTable();
   ASSERT_EQ("1", FilesPerLevel());
@@ -250,7 +249,7 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
                               true /* disallow trivial move */);
   ASSERT_EQ("0,2", FilesPerLevel());
   for (int idx = 0; idx < 28; ++idx) {
-    ASSERT_EQ(std::string(10000, 'a' + char(idx)), Get(Key(idx)));
+    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
   }
 }
 
@@ -271,23 +270,20 @@ TEST_F(CuckooTableDBTest, SameKeyInsertedInTwoDifferentFilesAndCompacted) {
 
   // Generate one more file in level-0, and should trigger level-0 compaction
   for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + char(idx))));
+    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
   }
   dbfull()->TEST_WaitForFlushMemTable();
   dbfull()->TEST_CompactRange(0, nullptr, nullptr);
 
   ASSERT_EQ("0,1", FilesPerLevel());
   for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_EQ(std::string(10000, 'a' + char(idx)), Get(Key(idx)));
+    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
   }
 }
 
 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);
@@ -323,20 +319,14 @@ TEST_F(CuckooTableDBTest, AdaptiveTable) {
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  if (rocksdb::port::kLittleEndian) {
-    ::testing::InitGoogleTest(&argc, argv);
-    return RUN_ALL_TESTS();
-  }
-  else {
-    fprintf(stderr, "SKIPPED as Cuckoo table doesn't support Big Endian\n");
-    return 0;
-  }
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
 }
 
 #else
 #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;
 }