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

.deprecated_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

@@ -31,8 +31,6 @@ build/
 ldb
 manifest_dump
 sst_dump
-blob_dump
-block_cache_trace_analyzer
 column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
@@ -40,15 +38,12 @@ 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
-.DS_Store
 
 java/out
 java/target
@@ -64,7 +59,7 @@ rocksdb.h
 unity.cc
 java/crossbuild/.vagrant
 .vagrant/
-java/**/*.asc
+java/**.asc
 java/javadoc
 
 scan_build_report/

.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
@@ -6,119 +7,55 @@ os:
 compiler:
   - clang
   - gcc
-osx_image: xcode8.3
 jdk:
-  - openjdk7
+  - oraclejdk7
 cache:
   - ccache
   - apt
 
 addons:
-  apt:
-    sources:
-      - ubuntu-toolchain-r-test
-    packages:
-      - curl
-      - g++-8
-      - libbz2-dev
-      - libgflags-dev
-      - libsnappy-dev
-      - mingw-w64
-      - zlib1g-dev
+   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
+  - JOB_NAME=lite_build
   # 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=examples
 
 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
-
-# https://docs.travis-ci.com/user/caching/#ccache-cache
-install:
-  - if [ "${TRAVIS_OS_NAME}" == osx ]; then
-      brew install ccache zstd lz4 snappy xz;
-      PATH=$PATH:/usr/local/opt/ccache/libexec;
-    fi
-  - if [ "${JOB_NAME}" == cmake-gcc8 ]; then
-      CC=gcc-8 && CXX=g++-8;
-    fi
-  - if [[ "${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=full_filter_block_test make -j4 check_some
-      ;;
-    2)
-      OPT=-DTRAVIS V=1 make -j4 tools && OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=full_filter_block_test ROCKSDBTESTS_END=write_batch_with_index_test make -j4 check_some
-      ;;
-    3)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_batch_with_index_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 $JOB_NAME in
-    java_test)
-      OPT=-DTRAVIS V=1 make rocksdbjava jtest
-      ;;
-    lite_build)
-      OPT='-DTRAVIS -DROCKSDB_LITE' V=1 make -j4 static_lib tools
-      ;;
-    examples)
-      OPT=-DTRAVIS V=1 make -j4 static_lib && cd examples && make -j4
-      ;;
-    cmake-mingw)
-      sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
-      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
-      ;;
-    cmake*)
-      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release && make -j4 rocksdb rocksdbjni
-      ;;
-    esac
+  - if [[ "${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
+  - if [[ "${JOB_NAME}" == 'examples' ]]; then OPT=-DTRAVIS V=1 make -j4 static_lib; cd examples; make -j4; fi
 notifications:
     email:
       - leveldb@fb.com

AUTHORS

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

CODE_OF_CONDUCT.md

@@ -1,3 +0,0 @@
-# Code of Conduct
-
-Facebook has adopted a Code of Conduct that we expect project participants to adhere to. Please [read the full text](https://code.facebook.com/codeofconduct) so that you can understand what actions will and will not be tolerated.

CONTRIBUTING.md

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

DEFAULT_OPTIONS_HISTORY.md

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

HISTORY.md

@@ -1,443 +1,64 @@
 # Rocksdb Change Log
-## Unreleased
-### 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 explictly 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
-* Now DB::Close() will return Aborted() error when there is unreleased snapshot. Users can retry after all snapshots are released.
-* Index and filter blocks are now handled similarly to data blocks with regards to the block cache: instead of storing reader objects in the cache, only the blocks themselves are cached. In addition, index and filter blocks (as well as filter partitions) no longer get evicted from the cache when a table is closed. Moreover, index blocks can now use the compressed block cache (if any).
-* Partitions of partitioned indexes no longer affect the read amplification statistics.
-* Due to the above refactoring, block cache eviction statistics for indexes and filters 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.
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-* Add C bindings for secondary instance, i.e. DBImplSecondary.
-* db_bench adds a "benchmark" stats_history, which prints out the whole stats history.
-* 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
-* 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
-
-### New Features
-* Add an option `snap_refresh_nanos` (default to 0.1s) 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 argument `--secondary_path` to ldb to open the database as the secondary instance. This would keep the original DB intact.
-
-### 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
-* Reduce iterator key comparision for upper/lower bound check.
-* 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.
+## 5.4.12 (08/21/2017)
+* Statistics::Reset() to reset user stats.
 
+## 5.4.11 (08/17/2017)
 ### 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 ingested file and directory not being fsync.
-* Return TryAgain status in place of Corruption when new tail is not visible to TransactionLogIterator.
-* 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.
+* Fix a bug in PosixWritableFile::Close()
 
+## 5.4.10 (08/12/2017)
 ### 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 destorying 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.
+## 5.4.9 (07/20/2017)
+* Change license to Apache + GPLv2
 
-### 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.
+## 5.4.8 (07/13/2017)
+No change from 5.4.7.
 
+## 5.4.7 (06/28/2017)
 ### Bug Fixes
 * Shouldn't ignore return value of fsync() in flush.
 
-## 5.5.0 (05/17/2017)
+## 5.4.6 (05/30/2017)
+### Bug Fixes
+* Fix db_bench with lite build.
+
+## 5.4.5 (05/19/2017)
+### Bug Fixes
+* Facility for cross-building RocksJava using Docker.
+* Build and link with ZStd when creating the static RocksJava build.
+* Fix snprintf's usage to be cross-platform.
+* Fix build error with blob DB.
+* Fix readamp test type inconsistency.
+
+## 5.4.4 (05/11/2017)
 ### 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
+* Fix a manual / auto compaction data race.
+* Fix CentOS 5 cross-building of RocksJava.
+
+## 5.4.3 (05/10/2017)
+### Bug Fixes
+* Fix memory alignment with logical sector size.
+* Fix alignment in ReadaheadRandomAccessFile.
+* Fix bias with read amplification stats (READ_AMP_ESTIMATE_USEFUL_BYTES and READ_AMP_TOTAL_READ_BYTES).
+
+## 5.4.2 (05/08/2017)
+### Bug Fixes
+* Fix huge fallocate calls fail and make XFS unhappy.
+
+## 5.4.1 (05/02/2017)
+### Bug Fxies
+* Fix WriteBatchWithIndex address use after scope error.
+* Fix WritableFile buffer size in direct IO.
+* Add prefetch to PosixRandomAccessFile in buffered io.
+* Fix PinnableSlice access invalid address when row cache is enabled.
 
 ## 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.
@@ -450,6 +71,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 * 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.
+* DB::ResetStats() to reset internal stats.
 
 ## 5.3.0 (03/08/2017)
 ### Public API Change
@@ -676,7 +298,7 @@ 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

@@ -21,18 +21,15 @@ 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`. If you want to build a binary that
+makes use of SSE4, add 'USE_SSE=1' before your make commands, like this: `USE_SSE=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 +40,6 @@ 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 +51,6 @@ 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**
@@ -69,29 +63,26 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
               git checkout v2.0
               ./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`.
+      **Notice**: Once installed, please add the include path for gflags to your CPATH env var and the
+      lib path to LIBRARY_PATH. If installed with default settings, the lib will be /usr/local/lib
+      and the include path will be /usr/local/include.
 
     * 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:
 
@@ -109,94 +100,9 @@ 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

@@ -1,11 +1,11 @@
 ## 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
@@ -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
 
@@ -83,16 +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.

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

@@ -1,67 +1,15 @@
 version: 1.0.{build}
-
-image: Visual Studio 2017
-
-environment:
-  JAVA_HOME: C:\Program Files\Java\jdk1.8.0
-  THIRDPARTY_HOME: $(APPVEYOR_BUILD_FOLDER)\thirdparty
-  SNAPPY_HOME: $(THIRDPARTY_HOME)\snappy-1.1.7
-  SNAPPY_INCLUDE: $(SNAPPY_HOME);$(SNAPPY_HOME)\build
-  SNAPPY_LIB_DEBUG: $(SNAPPY_HOME)\build\Debug\snappy.lib
-  SNAPPY_LIB_RELEASE: $(SNAPPY_HOME)\build\Release\snappy.lib
-  LZ4_HOME: $(THIRDPARTY_HOME)\lz4-1.8.3
-  LZ4_INCLUDE: $(LZ4_HOME)\lib
-  LZ4_LIB_DEBUG: $(LZ4_HOME)\visual\VS2010\bin\x64_Debug\liblz4_static.lib
-  LZ4_LIB_RELEASE: $(LZ4_HOME)\visual\VS2010\bin\x64_Release\liblz4_static.lib
-  ZSTD_HOME: $(THIRDPARTY_HOME)\zstd-1.4.0
-  ZSTD_INCLUDE: $(ZSTD_HOME)\lib;$(ZSTD_HOME)\lib\dictBuilder
-  ZSTD_LIB_DEBUG: $(ZSTD_HOME)\build\VS2010\bin\x64_Debug\libzstd_static.lib
-  ZSTD_LIB_RELEASE: $(ZSTD_HOME)\build\VS2010\bin\x64_Release\libzstd_static.lib
-
-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 -DCMAKE_GENERATOR_PLATFORM=x64 ..
-  - 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="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $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="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $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 "Visual Studio 15 Win64" -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 -Concurrency 8
-
-on_failure:
-  - cmd: 7z a build-failed.zip %APPVEYOR_BUILD_FOLDER%\build\ && appveyor PushArtifact build-failed.zip
+- ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test -Concurrency 8
 

buckifier/buckify_rocksdb.py

@@ -1,14 +1,16 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
 from targets_builder import TARGETSBuilder
+from optparse import OptionParser
 import os
 import fnmatch
 import sys
+import tempfile
 
 from util import ColorString
+import util
 
 # tests to export as libraries for inclusion in other projects
 _EXPORTED_TEST_LIBS = ["env_basic_test"]
@@ -34,7 +36,7 @@ def parse_src_mk(repo_path):
 # get all .cc / .c files
 def get_cc_files(repo_path):
     cc_files = []
-    for root, dirnames, filenames in os.walk(repo_path):  # noqa: B007 T25377293 Grandfathered in
+    for root, dirnames, filenames in os.walk(repo_path):
         root = root[(len(repo_path) + 1):]
         if "java" in root:
             # Skip java
@@ -110,19 +112,17 @@ def generate_targets(repo_path):
         "rocksdb_test_lib",
         src_mk.get("MOCK_LIB_SOURCES", []) +
         src_mk.get("TEST_LIB_SOURCES", []) +
-        src_mk.get("EXP_LIB_SOURCES", []) +
-        src_mk.get("ANALYZER_LIB_SOURCES", []),
+        src_mk.get("EXP_LIB_SOURCES", []),
         [":rocksdb_lib"])
     # rocksdb_tools_lib
     TARGETS.add_library(
         "rocksdb_tools_lib",
         src_mk.get("BENCH_LIB_SOURCES", []) +
-        src_mk.get("ANALYZER_LIB_SOURCES", []) +
-        ["test_util/testutil.cc"],
+        ["util/testutil.cc"],
         [":rocksdb_lib"])
 
     # test for every test we found in the Makefile
-    for test in sorted(tests):
+    for test in 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))

buckifier/rocks_test_runner.sh

@@ -1,6 +1,4 @@
-#!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#!/bin/bash
 # Create a tmp directory for the test to use
 TEST_DIR=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
-# shellcheck disable=SC2068
 TEST_TMPDIR="$TEST_DIR" $@ && rm -rf "$TEST_DIR"

buckifier/targets_builder.py

@@ -1,11 +1,12 @@
-# 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
 import targets_cfg
+import pprint
 
-def pretty_list(lst, indent=8):
+# TODO(tec): replace this with PrettyPrinter
+def pretty_list(lst, indent=6):
     if lst is None or len(lst) == 0:
         return ""
 
@@ -13,8 +14,8 @@ def pretty_list(lst, indent=8):
         return "\"%s\"" % lst[0]
 
     separator = "\",\n%s\"" % (" " * indent)
-    res = separator.join(sorted(lst))
-    res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 4))
+    res = separator.join(lst)
+    res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 2))
     return res
 
 
@@ -26,22 +27,19 @@ class TARGETSBuilder:
         self.total_lib = 0
         self.total_bin = 0
         self.total_test = 0
-        self.tests_cfg = ""
+        self.tests_cfg = []
 
     def __del__(self):
         self.targets_file.close()
 
     def add_library(self, name, srcs, deps=None, headers=None):
-        headers_attr_prefix = ""
         if headers is None:
-            headers_attr_prefix = "auto_"
             headers = "AutoHeaders.RECURSIVE_GLOB"
-        self.targets_file.write(targets_cfg.library_template.format(
-            name=name,
-            srcs=pretty_list(srcs),
-            headers_attr_prefix=headers_attr_prefix,
-            headers=headers,
-            deps=pretty_list(deps)))
+        self.targets_file.write(targets_cfg.library_template % (
+            name,
+            headers,
+            pretty_list(srcs),
+            pretty_list(deps)))
         self.total_lib = self.total_lib + 1
 
     def add_binary(self, name, srcs, deps=None):
@@ -55,13 +53,13 @@ class TARGETSBuilder:
         exec_mode = "serial"
         if is_parallel:
             exec_mode = "parallel"
-        self.tests_cfg += targets_cfg.test_cfg_template % (
-            test_name,
-            str(src),
-            str(exec_mode))
+        self.tests_cfg.append([test_name, str(src), str(exec_mode)])
 
         self.total_test = self.total_test + 1
 
     def flush_tests(self):
-        self.targets_file.write(targets_cfg.unittests_template % self.tests_cfg)
-        self.tests_cfg = ""
+        self.targets_file.write(targets_cfg.unittests_template % (
+            pprint.PrettyPrinter().pformat(self.tests_cfg)
+        ))
+
+        self.tests_cfg = []

buckifier/targets_cfg.py

@@ -1,137 +1,112 @@
-# 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 = """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",
-    "-DROCKSDB_PLATFORM_POSIX",
-    "-DROCKSDB_LIB_IO_POSIX",
-    "-DROCKSDB_FALLOCATE_PRESENT",
-    "-DROCKSDB_MALLOC_USABLE_SIZE",
-    "-DROCKSDB_RANGESYNC_PRESENT",
-    "-DROCKSDB_SCHED_GETCPU_PRESENT",
-    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
-    "-DOS_LINUX",
-    # Flags to enable libs we include
-    "-DSNAPPY",
-    "-DZLIB",
-    "-DBZIP2",
-    "-DLZ4",
-    "-DZSTD",
-    "-DZSTD_STATIC_LINKING_ONLY",
-    "-DGFLAGS=gflags",
-    "-DNUMA",
-    "-DTBB",
-    # Needed to compile in fbcode
-    "-Wno-expansion-to-defined",
-    # Added missing flags from output of build_detect_platform
-    "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
-    "-DROCKSDB_BACKTRACE",
-    "-Wnarrowing",
-    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
+rocksdb_target_header = """REPO_PATH = "internal_repo_rocksdb/repo/"
+BUCK_BINS = "buck-out/gen/" + REPO_PATH
+TEST_RUNNER = REPO_PATH + "buckifier/rocks_test_runner.sh"
+rocksdb_compiler_flags = [
+  "-msse",
+  "-msse4.2",
+  "-fno-builtin-memcmp",
+  "-DROCKSDB_PLATFORM_POSIX",
+  "-DROCKSDB_LIB_IO_POSIX",
+  "-DROCKSDB_FALLOCATE_PRESENT",
+  "-DROCKSDB_MALLOC_USABLE_SIZE",
+  "-DOS_LINUX",
+  # Flags to enable libs we include
+  "-DSNAPPY",
+  "-DZLIB",
+  "-DBZIP2",
+  "-DLZ4",
+  "-DZSTD",
+  "-DGFLAGS=gflags",
+  "-DNUMA",
+  "-DTBB",
+  # Needed to compile in fbcode
+  "-Wno-expansion-to-defined",
 ]
 
-ROCKSDB_EXTERNAL_DEPS = [
-    ("bzip2", None, "bz2"),
-    ("snappy", None, "snappy"),
-    ("zlib", None, "z"),
-    ("gflags", None, "gflags"),
-    ("lz4", None, "lz4"),
-    ("zstd", None),
-    ("tbb", None),
-    ("numa", None, "numa"),
-    ("googletest", None, "gtest"),
+rocksdb_external_deps = [
+  ('bzip2', None, 'bz2'),
+  ('snappy', None, "snappy"),
+  ('zlib', None, 'z'),
+  ('gflags', None, 'gflags'),
+  ('lz4', None, 'lz4'),
+  ('zstd', None),
+  ('tbb', None),
+  ("numa", "2.0.8", "numa"),
+  ("googletest", None, "gtest"),
 ]
 
-ROCKSDB_PREPROCESSOR_FLAGS = [
-    # Directories with files for #include
-    "-I" + REPO_PATH + "include/",
-    "-I" + REPO_PATH,
+rocksdb_preprocessor_flags = [
+  # Directories with files for #include
+  "-I" + REPO_PATH + "include/",
+  "-I" + REPO_PATH,
 ]
-
-ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
-    "x86_64": [
-        "-DHAVE_SSE42",
-        "-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_COMPILER_FLAGS += (["-DROCKSDB_JEMALLOC"] if sanitizer == "" else [])
-
-ROCKSDB_EXTERNAL_DEPS += ([("jemalloc", None, "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,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-    deps = [{deps}],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    name = "%s",
+    headers = %s,
+    srcs = [%s],
+    deps = [%s],
+    preprocessor_flags = rocksdb_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    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,
+  name = "%s",
+  srcs = [%s],
+  deps = [%s],
+  preprocessor_flags = rocksdb_preprocessor_flags,
+  compiler_flags = rocksdb_compiler_flags,
+  external_deps = rocksdb_external_deps,
 )
 """
 
-test_cfg_template = """    [
-        "%s",
-        "%s",
-        "%s",
-    ],
-"""
-
 unittests_template = """
 # [test_name, test_src, test_type]
-ROCKS_TESTS = [
-%s]
+ROCKS_TESTS = %s
+
 
 # Generate a test rule for each entry in ROCKS_TESTS
-# Do not build the tests in opt mode, since SyncPoint and other test code
-# will not be included.
-[
-    test_binary(
-        parallelism = parallelism,
-        rocksdb_arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-        rocksdb_compiler_flags = ROCKSDB_COMPILER_FLAGS,
-        rocksdb_external_deps = ROCKSDB_EXTERNAL_DEPS,
-        rocksdb_preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-        test_cc = test_cc,
-        test_name = test_name,
+for test_cfg in ROCKS_TESTS:
+    test_name = test_cfg[0]
+    test_cc = test_cfg[1]
+    ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
+    test_bin = test_name + "_bin"
+
+    cpp_binary (
+      name = test_bin,
+      srcs = [test_cc],
+      deps = [":rocksdb_test_lib"],
+      preprocessor_flags = rocksdb_preprocessor_flags,
+      compiler_flags = rocksdb_compiler_flags,
+      external_deps = rocksdb_external_deps,
     )
-    for test_name, test_cc, parallelism in ROCKS_TESTS
-    if not is_opt_mode
-]
+
+    custom_unittest(
+      name = test_name,
+      type = ttype,
+      deps = [":" + test_bin],
+      command = [TEST_RUNNER, BUCK_BINS + test_bin]
+    )
+
+custom_unittest(
+    name = "make_rocksdbjavastatic",
+    type = "simple",
+    command = ["internal_repo_rocksdb/make_rocksdbjavastatic.sh"],
+)
+
+custom_unittest(
+    name = "make_rocksdb_lite_release",
+    type = "simple",
+    command = ["internal_repo_rocksdb/make_rocksdb_lite_release.sh"],
+)
 """

buckifier/util.py

@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 """
 This module keeps commonly used components.
 """

build_tools/RocksDBCommonHelper.php

@@ -1,377 +0,0 @@
-<?php
-// Copyright 2004-present Facebook. All Rights Reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-// Name of the environment variables which need to be set by the entity which
-// triggers continuous runs so that code at the end of the file gets executed
-// and Sandcastle run starts.
-const ENV_POST_RECEIVE_HOOK = "POST_RECEIVE_HOOK";
-const ENV_HTTPS_APP_VALUE = "HTTPS_APP_VALUE";
-const ENV_HTTPS_TOKEN_VALUE = "HTTPS_TOKEN_VALUE";
-
-const PRIMARY_TOKEN_FILE = '/home/krad/.sandcastle';
-const CONT_RUN_ALIAS = "leveldb";
-
-//////////////////////////////////////////////////////////////////////
-/*  Run tests in sandcastle */
-function postURL($diffID, $url) {
-  assert(strlen($diffID) > 0);
-  assert(is_numeric($diffID));
-  assert(strlen($url) > 0);
-
-  $cmd_args = array(
-    'diff_id' => (int)$diffID,
-    'name' => sprintf(
-      'click here for sandcastle tests for D%d',
-      (int)$diffID
-    ),
-    'link' => $url
-  );
-  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
-         . ' | arc call-conduit differential.updateunitresults';
-
-  shell_exec($cmd);
-}
-
-function buildUpdateTestStatusCmd($diffID, $test, $status) {
-  assert(strlen($diffID) > 0);
-  assert(is_numeric($diffID));
-  assert(strlen($test) > 0);
-  assert(strlen($status) > 0);
-
-  $cmd_args = array(
-    'diff_id' => (int)$diffID,
-    'name' => $test,
-    'result' => $status
-  );
-
-  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
-         . ' | arc call-conduit differential.updateunitresults';
-
-  return $cmd;
-}
-
-function updateTestStatus($diffID, $test) {
-  assert(strlen($diffID) > 0);
-  assert(is_numeric($diffID));
-  assert(strlen($test) > 0);
-
-  shell_exec(buildUpdateTestStatusCmd($diffID, $test, "waiting"));
-}
-
-function getSteps($applyDiff, $diffID, $username, $test) {
-  assert(strlen($username) > 0);
-  assert(strlen($test) > 0);
-
-  if ($applyDiff) {
-    assert(strlen($diffID) > 0);
-    assert(is_numeric($diffID));
-
-    $arcrc_content = (PHP_OS == "Darwin" ?
-        exec("cat ~/.arcrc | gzip -f | base64") :
-            exec("cat ~/.arcrc | gzip -f | base64 -w0"));
-    assert(strlen($arcrc_content) > 0);
-
-    // Sandcastle machines don't have arc setup. We copy the user certificate
-    // and authenticate using that in Sandcastle.
-    $setup = array(
-      "name" => "Setup arcrc",
-      "shell" => "echo " . escapeshellarg($arcrc_content) . " | base64 --decode"
-                 . " | gzip -d > ~/.arcrc",
-      "user" => "root"
-    );
-
-    // arc demands certain permission on its config.
-    // also fix the sticky bit issue in sandcastle
-    $fix_permission = array(
-      "name" => "Fix environment",
-      "shell" => "chmod 600 ~/.arcrc && chmod +t /dev/shm",
-      "user" => "root"
-    );
-
-    // Construct the steps in the order of execution.
-    $steps[] = $setup;
-    $steps[] = $fix_permission;
-  }
-
-  // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
-  // Git thinks it is an uncommitted change.
-  $fix_git_ignore = array(
-    "name" => "Fix git ignore",
-    "shell" => "echo fbcode >> .git/info/exclude",
-    "user" => "root"
-  );
-
-  // This fixes "FATAL: ThreadSanitizer can not mmap the shadow memory"
-  // Source:
-  // https://github.com/google/sanitizers/wiki/ThreadSanitizerCppManual#FAQ
-  $fix_kernel_issue = array(
-    "name" => "Fix kernel issue with tsan",
-    "shell" => "echo 2 >/proc/sys/kernel/randomize_va_space",
-    "user" => "root"
-  );
-
-  $steps[] = $fix_git_ignore;
-  $steps[] = $fix_kernel_issue;
-
-  // This will be the command used to execute particular type of tests.
-  $cmd = "";
-
-  if ($applyDiff) {
-    // Patch the code (keep your fingures crossed).
-    $patch = array(
-      "name" => "Patch " . $diffID,
-      "shell" => "arc --arcrc-file ~/.arcrc "
-                  . "patch --nocommit --diff " . escapeshellarg($diffID),
-      "user" => "root"
-    );
-
-    $steps[] = $patch;
-
-    updateTestStatus($diffID, $test);
-    $cmd = buildUpdateTestStatusCmd($diffID, $test, "running") . "; ";
-  }
-
-  // Run the actual command.
-  $cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " .
-           escapeshellarg($test) . "; exit_code=$?; ";
-
-  if ($applyDiff) {
-    $cmd = $cmd . "([[ \$exit_code -eq 0 ]] &&"
-                . buildUpdateTestStatusCmd($diffID, $test, "pass") . ")"
-                . "||" . buildUpdateTestStatusCmd($diffID, $test, "fail")
-                . "; ";
-  }
-
-  // shell command to sort the tests based on exit code and print
-  // the output of the log files.
-  $cat_sorted_logs = "
-    while read code log_file;
-      do echo \"################ cat \$log_file [exit_code : \$code] ################\";
-      cat \$log_file;
-    done < <(tail -n +2 LOG | sort -k7,7n -k4,4gr | awk '{print \$7,\$NF}')";
-
-  // Shell command to cat all log files
-  $cat_all_logs = "for f in `ls t/!(run-*)`; do echo \$f;cat \$f; done";
-
-  // If LOG file exist use it to cat log files sorted by exit code, otherwise
-  // cat everything
-  $logs_cmd = "if [ -f LOG ]; then {$cat_sorted_logs}; else {$cat_all_logs}; fi";
-
-  $cmd = $cmd . " cat /tmp/precommit-check.log"
-              . "; shopt -s extglob; {$logs_cmd}"
-              . "; shopt -u extglob; [[ \$exit_code -eq 0 ]]";
-  assert(strlen($cmd) > 0);
-
-  $run_test = array(
-    "name" => "Run " . $test,
-    "shell" => $cmd,
-    "user" => "root",
-    "parser" => "python build_tools/error_filter.py " . escapeshellarg($test),
-  );
-
-  $steps[] = $run_test;
-
-  if ($applyDiff) {
-    // Clean up the user arc config we are using.
-    $cleanup = array(
-      "name" => "Arc cleanup",
-      "shell" => "rm -f ~/.arcrc",
-      "user" => "root"
-    );
-
-    $steps[] = $cleanup;
-  }
-
-  assert(count($steps) > 0);
-  return $steps;
-}
-
-function getSandcastleConfig() {
-  $sandcastle_config = array();
-
-  $cwd = getcwd();
-  $cwd_token_file = "{$cwd}/.sandcastle";
-  // This is a case when we're executed from a continuous run. Fetch the values
-  // from the environment.
-  if (getenv(ENV_POST_RECEIVE_HOOK)) {
-    $sandcastle_config[0] = getenv(ENV_HTTPS_APP_VALUE);
-    $sandcastle_config[1] = getenv(ENV_HTTPS_TOKEN_VALUE);
-  } else {
-    // This is a typical `[p]arc diff` case. Fetch the values from the specific
-    // configuration files.
-    for ($i = 0; $i < 50; $i++) {
-      if (file_exists(PRIMARY_TOKEN_FILE) ||
-          file_exists($cwd_token_file)) {
-        break;
-      }
-      // If we failed to fetch the tokens, sleep for 0.2 second and try again
-      usleep(200000);
-    }
-    assert(file_exists(PRIMARY_TOKEN_FILE) ||
-           file_exists($cwd_token_file));
-
-    // Try the primary location first, followed by a secondary.
-    if (file_exists(PRIMARY_TOKEN_FILE)) {
-      $cmd = 'cat ' . PRIMARY_TOKEN_FILE;
-    } else {
-      $cmd = 'cat ' . escapeshellarg($cwd_token_file);
-    }
-
-    assert(strlen($cmd) > 0);
-    $sandcastle_config = explode(':', rtrim(shell_exec($cmd)));
-  }
-
-  // In this case be very explicit about the implications.
-  if (count($sandcastle_config) != 2) {
-    echo "Sandcastle configuration files don't contain valid information " .
-         "or the necessary environment variables aren't defined. Unable " .
-         "to validate the code changes.";
-    exit(1);
-  }
-
-  assert(strlen($sandcastle_config[0]) > 0);
-  assert(strlen($sandcastle_config[1]) > 0);
-  assert(count($sandcastle_config) > 0);
-
-  return $sandcastle_config;
-}
-
-// This function can be called either from `[p]arc diff` command or during
-// the Git post-receive hook.
- function startTestsInSandcastle($applyDiff, $workflow, $diffID) {
-  // Default options don't terminate on failure, but that's what we want. In
-  // the current case we use assertions intentionally as "terminate on failure
-  // invariants".
-  assert_options(ASSERT_BAIL, true);
-
-  // In case of a diff we'll send notificatios to the author. Else it'll go to
-  // the entire team because failures indicate that build quality has regressed.
-  $username = $applyDiff ? exec("whoami") : CONT_RUN_ALIAS;
-  assert(strlen($username) > 0);
-
-  if ($applyDiff) {
-    assert($workflow);
-    assert(strlen($diffID) > 0);
-    assert(is_numeric($diffID));
-  }
-
-  // List of tests we want to run in Sandcastle.
-  $tests = array("unit", "unit_non_shm", "unit_481", "clang_unit", "tsan",
-                 "asan", "lite_test", "valgrind", "release", "release_481",
-                 "clang_release", "clang_analyze", "code_cov",
-                 "java_build", "no_compression", "unity", "ubsan");
-
-  $send_email_template = array(
-    'type' => 'email',
-    'triggers' => array('fail'),
-    'emails' => array($username . '@fb.com'),
-  );
-
-  // Construct a job definition for each test and add it to the master plan.
-  foreach ($tests as $test) {
-    $stepName = "RocksDB diff " . $diffID . " test " . $test;
-
-    if (!$applyDiff) {
-      $stepName = "RocksDB continuous integration test " . $test;
-    }
-
-    $arg[] = array(
-      "name" => $stepName,
-      "report" => array($send_email_template),
-      "steps" => getSteps($applyDiff, $diffID, $username, $test)
-    );
-  }
-
-  // We cannot submit the parallel execution master plan to Sandcastle and
-  // need supply the job plan as a determinator. So we construct a small job
-  // that will spit out the master job plan which Sandcastle will parse and
-  // execute. Why compress the job definitions? Otherwise we run over the max
-  // string size.
-  $cmd = "echo " . base64_encode(json_encode($arg))
-         . (PHP_OS == "Darwin" ?
-             " | gzip -f | base64" :
-                 " | gzip -f | base64 -w0");
-  assert(strlen($cmd) > 0);
-
-  $arg_encoded = shell_exec($cmd);
-  assert(strlen($arg_encoded) > 0);
-
-  $runName = "Run diff " . $diffID . "for user " . $username;
-
-  if (!$applyDiff) {
-    $runName = "RocksDB continuous integration build and test run";
-  }
-
-  $command = array(
-    "name" => $runName,
-    "steps" => array()
-  );
-
-  $command["steps"][] = array(
-    "name" => "Generate determinator",
-    "shell" => "echo " . $arg_encoded . " | base64 --decode | gzip -d"
-               . " | base64 --decode",
-    "determinator" => true,
-    "user" => "root"
-  );
-
-  // Submit to Sandcastle.
-  $url = 'https://interngraph.intern.facebook.com/sandcastle/create';
-
-  $job = array(
-    'command' => 'SandcastleUniversalCommand',
-    'args' => $command,
-    'capabilities' => array(
-      'vcs' => 'rocksdb-int-git',
-      'type' => 'lego',
-    ),
-    'hash' => 'origin/master',
-    'user' => $username,
-    'alias' => 'rocksdb-precommit',
-    'tags' => array('rocksdb'),
-    'description' => 'Rocksdb precommit job',
-  );
-
-  // Fetch the configuration necessary to submit a successful HTTPS request.
-  $sandcastle_config = getSandcastleConfig();
-
-  $app = $sandcastle_config[0];
-  $token = $sandcastle_config[1];
-
-  $cmd = 'curl -s -k '
-          . ' -F app=' . escapeshellarg($app)
-          . ' -F token=' . escapeshellarg($token)
-          . ' -F job=' . escapeshellarg(json_encode($job))
-          .' ' . escapeshellarg($url);
-
-  $output = shell_exec($cmd);
-  assert(strlen($output) > 0);
-
-  // Extract Sandcastle URL from the response.
-  preg_match('/url": "(.+)"/', $output, $sandcastle_url);
-
-  assert(count($sandcastle_url) > 0, "Unable to submit Sandcastle request.");
-  assert(strlen($sandcastle_url[1]) > 0, "Unable to extract Sandcastle URL.");
-
-  if ($applyDiff) {
-    echo "\nSandcastle URL: " . $sandcastle_url[1] . "\n";
-    // Ask Phabricator to display it on the diff UI.
-    postURL($diffID, $sandcastle_url[1]);
-  } else {
-    echo "Continuous integration started Sandcastle tests. You can look at ";
-    echo "the progress at:\n" . $sandcastle_url[1] . "\n";
-  }
-}
-
-// Continuous run cript will set the environment variable and based on that
-// we'll trigger the execution of tests in Sandcastle. In that case we don't
-// need to apply any diffs and there's no associated workflow either.
-if (getenv(ENV_POST_RECEIVE_HOOK)) {
-  startTestsInSandcastle(
-    false /* $applyDiff */,
-    NULL /* $workflow */,
-    NULL /* $diffID */);
-}

build_tools/amalgamate.py

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

build_tools/build_detect_platform

@@ -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 "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007" ]; then
-      source "$PWD/build_tools/fbcode_config_platform007.sh"
-    else
-      source "$PWD/build_tools/fbcode_config.sh"
-    fi
+    source "$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 ${CFLAGS}"
@@ -146,28 +117,18 @@ case "$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="$PLATFORM_LDFLAGS -lpthread -lrt"
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
         PLATFORM=OS_SOLARIS
-        COMMON_FLAGS="$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="$PLATFORM_LDFLAGS -lpthread"
         # PORT_FILES=port/freebsd/freebsd_specific.cc
@@ -180,12 +141,9 @@ case "$TARGET_OS" in
         ;;
     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
@@ -200,8 +158,6 @@ case "$TARGET_OS" in
         COMMON_FLAGS="$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
@@ -234,7 +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
@@ -242,147 +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
@@ -391,114 +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
 
@@ -518,11 +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 $HDFS_CCFLAGS"
@@ -530,90 +407,23 @@ if test "$USE_HDFS"; then
   JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi
 
-if test -z "$PORTABLE"; then
+if [ "$TARGET_OS" = FreeBSD -a "$TARGET_ARCHITECTURE" = i386 ]; then
+  # Intel SSE instructions breaks compilation on FreeBSD i386
+  unset USE_SSE
+fi
+
+if test "$USE_SSE"; then
+  # if Intel SSE instruction set is supported, set USE_SSE=1
+  COMMON_FLAGS="$COMMON_FLAGS -msse -msse4.2 "
+elif test -z "$PORTABLE"; then
   if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
     # Tune for this POWER processor, treating '+' models as base models
     POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
     COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
   elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
     COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep -e^arm -e^aarch64`"; then
-    # TODO: Handle this with approprite options.
-    COMMON_FLAGS="$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
+  else
     COMMON_FLAGS="$COMMON_FLAGS -march=native "
-  elif test "$USE_SSE"; then
-    COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
-  fi
-elif test "$USE_SSE"; then
-  COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <nmmintrin.h>
-  int main() {
-    volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_SSE42"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
-  exit 1
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <wmmintrin.h>
-  int main() {
-    const auto a = _mm_set_epi64x(0, 0);
-    const auto b = _mm_set_epi64x(0, 0);
-    const auto c = _mm_clmulepi64_si128(a, b, 0x00);
-    auto d = _mm_cvtsi128_si64(c);
-    (void)d;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_PCLMUL"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
-  exit 1
-fi
-
-# iOS doesn't support thread-local storage, but this check would erroneously
-# succeed because the cross-compiler flags are added by the Makefile, not this
-# script.
-if [ "$PLATFORM" != IOS ]; then
-  $CXX $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #if defined(_MSC_VER) && !defined(__thread)
-  #define __thread __declspec(thread)
-  #endif
-  int main() {
-    static __thread int tls;
-    (void)tls;
-  }
-EOF
-  if [ "$?" = 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
 
@@ -648,16 +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"

build_tools/cont_integration.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 #
 # Copyright (c) 2016, Facebook. All rights reserved.
 #
@@ -13,12 +13,10 @@ error=0
 
 function log {
   DATE=`date +%Y-%m-%d:%H:%M:%S`
-  # shellcheck disable=SC2068
   echo $DATE $@
 }
 
 function log_err {
-  # shellcheck disable=SC2145
   log "ERROR: $@ Error code: $error."
 }
 
@@ -69,7 +67,7 @@ function update_repo_status {
 #
 
 # Path to the determinator from the root of the RocksDB repo.
-CONTRUN_DETERMINATOR=./build_tools/RocksDBCommonHelper.php
+CONTRUN_DETERMINATOR=./arcanist_util/config/RocksDBCommonHelper.php
 
 # Value of the previous commit.
 PREV_COMMIT=

build_tools/dependencies.sh

@@ -1,19 +1,19 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/112ec378fec7002ad3e09afde022e656049f7191/5.x/centos7-native/c447969
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/04999bdb3ce81a11073535dcb00b5e13dc1cbaf5/stable/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/92b0c8e5c8eecc71eb042594ce1ab3413799b385/5.x/gcc-5-glibc-2.23/339d858
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/3d8698d5973ba94f41620a80a67e4457fdf01e90/2.23/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/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/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/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/gcc-5-glibc-2.23/9bc6787
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/af6628a46758f1a15484a1760cd7294164bc5ba1/1.3.5/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/b1a0e56c1e3e6929813a4331ade3a58ff083afbb/master/gcc-5-glibc-2.23/aa64d6b
-NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/gcc-5-glibc-2.23/9bc6787
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/gcc-5-glibc-2.23/b443de1
-TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/gcc-5-glibc-2.23/9bc6787
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/55031de95a2b46c82948743419a603b3d6aefe28/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/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

@@ -1,19 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/6e8e715624fd15256a7970073387793dfcf79b46/7.x/centos7-native/b2ef2b6
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/ef37e1faa1c29782abfac1ae65a291b9b7966f6d/stable/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/c67031f0f739ac61575a061518d6ef5038f99f90/7.x/platform007/5620abc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/60d6f124a78798b73944f5ba87c2306ae3460153/2.26/platform007/f259413
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/platform007/ca4da3d
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/platform007/ca4da3d
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/3ee276cbacfad3074e3f07bf826ac47f06970f4e/1.3.5/platform007/15a3614
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/9c910d36d6235cc40e8ff559358f1833452300ca/master/platform007/5b0f53e
-NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/platform007/ca4da3d
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/platform007/6f3e0a9
-TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/platform007/ca4da3d
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/fb/platform007/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/92ff90349e2f43ea0a8246d8b1cf17b6869013e3/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/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):
@@ -132,14 +128,11 @@ _TEST_NAME_TO_PARSERS = {
     'lite': [CompilerErrorParser],
     'lite_test': [CompilerErrorParser, GTestErrorParser],
     'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_atomic_flush': [CompilerErrorParser, DbCrashErrorParser],
     'write_stress': [CompilerErrorParser, WriteStressErrorParser],
     'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
     'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_atomic_flush': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
     'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
     'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_atomic_flush': [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/"
@@ -88,7 +87,6 @@ CFLAGS+=" -DTBB"
 
 # use Intel SSE support for checksum calculations
 export USE_SSE=1
-export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -110,8 +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 $GLIBC_INCLUDE"
   JEMALLOC=1
 else
   # clang
@@ -122,8 +120,8 @@ else
   KERNEL_HEADERS_INCLUDE="$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"
@@ -139,9 +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"
 
@@ -151,12 +149,4 @@ EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GF
 
 VALGRIND_VER="$VALGRIND_BASE/bin/"
 
-LUA_PATH="$LUA_BASE"
-
-if test -z $PIC_BUILD; then
-  LUA_LIB=" $LUA_PATH/lib/liblua.a"
-else
-  LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
-fi
-
-export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD 

build_tools/fbcode_config4.8.1.sh

@@ -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
@@ -55,7 +54,6 @@ TBB_LIBS="$TBB_BASE/lib/libtbb.a"
 
 # use Intel SSE support for checksum calculations
 export USE_SSE=1
-export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -95,7 +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

@@ -1,158 +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="$TBB_BASE/lib/libtbb_pic.a"
-fi
-CFLAGS+=" -DTBB"
-
-# use Intel SSE support for checksum calculations
-export USE_SSE=1
-export PORTABLE=1
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"
-
-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"
-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/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 $TBB_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-# lua not supported because it's on track for deprecation, I think
-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 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 ]

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/local/fbcode/gcc-4.9-glibc-2.20-fb/bin/python2.7
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 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
@@ -100,12 +85,9 @@ NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-# in gcc-5 there are known problems with TSAN like https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71090.
-# using platform007 gives us gcc-8 or higher which has that bug fixed.
-TSAN="ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007=1 COMPILE_WITH_TSAN=1"
+LITE="OPT=\"-DROCKSDB_LITE -g\""
+TSAN="COMPILE_WITH_TSAN=1"
 UBSAN="COMPILE_WITH_UBSAN=1"
-TSAN_CRASH='CRASH_TEST_EXT_ARGS="--compression_type=zstd --log2_keys_per_lock=22"'
-NON_TSAN_CRASH="CRASH_TEST_EXT_ARGS=--compression_type=zstd"
 DISABLE_JEMALLOC="DISABLE_JEMALLOC=1"
 HTTP_PROXY="https_proxy=http://fwdproxy.29.prn1:8080 http_proxy=http://fwdproxy.29.prn1:8080 ftp_proxy=http://fwdproxy.29.prn1:8080"
 SETUP_JAVA_ENV="export $HTTP_PROXY; export JAVA_HOME=/usr/local/jdk-8u60-64/; export PATH=\$JAVA_HOME/bin:\$PATH"
@@ -124,6 +106,13 @@ else
   TASK_CREATION_TOOL="false"
 fi
 
+ARTIFACTS=" 'artifacts': [
+    {
+        'name':'database',
+        'paths':[ '/dev/shm/rocksdb' ],
+    }
+]"
+
 #
 # A mechanism to disable tests temporarily
 #
@@ -141,6 +130,35 @@ 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
+            },
+        ],
+        $REPORT
+    }
+]"
+
 #
 # RocksDB unit test
 #
@@ -148,7 +166,6 @@ UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -169,7 +186,6 @@ UNIT_TEST_NON_SHM_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -192,7 +208,6 @@ RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -213,7 +228,6 @@ UNIT_TEST_COMMANDS_481="[
     {
         'name':'Rocksdb Unit Test on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -234,7 +248,6 @@ RELEASE_BUILD_COMMANDS_481="[
     {
         'name':'Rocksdb Release on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -255,7 +268,6 @@ CLANG_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -276,7 +288,6 @@ CLANG_RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb CLANG Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -297,7 +308,6 @@ CLANG_ANALYZE_COMMANDS="[
     {
         'name':'Rocksdb analyze',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -318,7 +328,6 @@ CODE_COV_COMMANDS="[
     {
         'name':'Rocksdb Unit Test Code Coverage',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -339,7 +348,6 @@ UNITY_COMMANDS="[
     {
         'name':'Rocksdb Unity',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -360,12 +368,11 @@ LITE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Lite build',
         'oncall':'$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 +382,23 @@ 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
+    }
 ]"
 
 #
@@ -396,56 +406,26 @@ 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,
-        ],
+        $ARTIFACTS,
         $REPORT
     }
 ]"
@@ -457,7 +437,6 @@ WRITE_STRESS_COMMANDS="[
     {
         'name':'Rocksdb Write Stress Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -480,7 +459,6 @@ ASAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under ASAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -501,14 +479,13 @@ ASAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under ASAN',
         'oncall':'$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
             },
@@ -517,30 +494,6 @@ 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB test under undefined behavior sanitizer
 #
@@ -548,7 +501,6 @@ UBSAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under UBSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -569,14 +521,13 @@ UBSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under UBSAN',
         'oncall':'$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 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
             },
@@ -585,30 +536,6 @@ 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 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB unit test under valgrind
 #
@@ -616,7 +543,6 @@ VALGRIND_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under valgrind',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -639,7 +565,6 @@ TSAN_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under TSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -662,14 +587,13 @@ TSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb Crash Test under TSAN',
         'oncall':'$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
             },
@@ -678,30 +602,6 @@ 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 format compatible
 #
@@ -712,14 +612,45 @@ 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': [
             $CLEANUP_ENV,
             {
@@ -742,7 +673,7 @@ run_no_compression()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
   make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzstd | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
+  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
   mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
   cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
   mv .tmp.Makefile Makefile
@@ -753,7 +684,6 @@ NO_COMPRESSION_COMMANDS="[
     {
         'name':'Rocksdb No Compression tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -796,12 +726,12 @@ 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 $(stat --printf="%s" `readlink -f librocksdb.so`)
@@ -831,7 +761,6 @@ JAVA_BUILD_TEST_COMMANDS="[
     {
         'name':'Rocksdb Java Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -847,6 +776,9 @@ JAVA_BUILD_TEST_COMMANDS="[
 
 
 case $1 in
+  punit)
+    echo $PARALLEL_UNIT_TEST_COMMANDS
+    ;;
   unit)
     echo $UNIT_TEST_COMMANDS
     ;;
@@ -880,15 +812,12 @@ 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
-    ;;
   write_stress)
     echo $WRITE_STRESS_COMMANDS
     ;;
@@ -898,18 +827,12 @@ case $1 in
   asan_crash)
     echo $ASAN_CRASH_TEST_COMMANDS
     ;;
-  asan_crash_with_atomic_flush)
-    echo $ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_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
-    ;;
   valgrind)
     echo $VALGRIND_TEST_COMMANDS
     ;;
@@ -919,9 +842,6 @@ case $1 in
   tsan_crash)
     echo $TSAN_CRASH_TEST_COMMANDS
     ;;
-  tsan_crash_with_atomic_flush)
-    echo $TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
   format_compatible)
     echo $FORMAT_COMPATIBLE_COMMANDS
     ;;

build_tools/run_ci_db_test.ps1

@@ -1,17 +1,13 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # This script enables you running RocksDB tests by running
 # All the tests concurrently and utilizing all the cores
 Param(
-  [switch]$EnableJE = $false,  # Look for and use test executable, append _je to listed exclusions
+  [switch]$EnableJE = $false,  # Look for and use _je executable, append _je to listed exclusions
   [switch]$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
@@ -43,18 +39,13 @@ $RunOnly.Add("compact_on_deletion_collector_test") | Out-Null
 $RunOnly.Add("merge_test") | Out-Null
 $RunOnly.Add("stringappend_test") | Out-Null # Apparently incorrectly written
 $RunOnly.Add("backupable_db_test") | Out-Null # Disabled
-$RunOnly.Add("timer_queue_test") | Out-Null # Not a gtest
+
 
 if($RunAll -and $SuiteRun -ne "") {
     Write-Error "$RunAll and $SuiteRun are not compatible"
     exit 1
 }
 
-if($RunAllExe -and $Run -ne "") {
-    Write-Error "$RunAllExe and $Run are not compatible"
-    exit 1
-}
-
 # If running under Appveyor assume that root
 [string]$Appveyor = $Env:APPVEYOR_BUILD_FOLDER
 if($Appveyor -ne "") {
@@ -140,8 +131,12 @@ function ExtractTestCases([string]$GTestExe, $HashTable) {
 
       # Leading whitespace is fine
       $l = $l -replace '^\s+',''
+      # but no whitespace any other place
+      if($l -match "\s+") {
+        continue
+      }
       # Trailing dot is a test group but no whitespace
-      if ($l -match "\.$" -and $l -notmatch "\s+") {
+      elseif ( $l -match "\.$" ) {
         $Group = $l
       }  else {
         # Otherwise it is a test name, remove leading space
@@ -228,11 +223,13 @@ $TestExes = [ordered]@{}
 if($Run -ne "") {
 
   $test_list = $Run -split ' '
+
   ForEach($t in $test_list) {
 
     if($EnableJE) {
       $t += "_je"
     }
+
     MakeAndAdd -token $t -HashTable $TestExes
   }
 
@@ -240,38 +237,6 @@ if($Run -ne "") {
      Write-Error "Failed to extract tests from $Run"
      exit 1
   }
-} elseif($RunAllExe) {
-  # Discover all the test binaries
-  if($EnableJE) {
-    $pattern = "*_test_je.exe"
-  } else {
-    $pattern = "*_test.exe"
-  }
-
-  $search_path = -join ($BinariesFolder, $pattern)
-  Write-Host "Binaries Search Path: $search_path"
-
-  $DiscoveredExe = @()
-  dir -Path $search_path | ForEach-Object {
-     $DiscoveredExe += ($_.Name)     
-  }
-
-  # Remove exclusions
-  ForEach($e in $DiscoveredExe) {
-    $e = $e -replace '.exe$', ''
-    $bare_name = $e -replace '_je$', ''
-
-    if($ExcludeExesSet.Contains($bare_name)) {
-      Write-Warning "Test $e is excluded"
-      continue
-    }
-    MakeAndAdd -token $e -HashTable $TestExes
-  }
-
-  if($TestExes.Count -lt 1) {
-     Write-Error "Failed to discover test executables"
-     exit 1
-  }
 }
 
 # Ordered by exe @{ Exe = @{ TestCase = LogName }}
@@ -280,7 +245,9 @@ $CasesToRun = [ordered]@{}
 if($SuiteRun -ne "") {
   $suite_list = $SuiteRun -split ' '
   ProcessSuites -ListOfSuites $suite_list -HashOfHashes $CasesToRun
-} elseif ($RunAll) {
+}
+
+if($RunAll) {
 # Discover all the test binaries
   if($EnableJE) {
     $pattern = "*_test_je.exe"
@@ -288,6 +255,7 @@ if($SuiteRun -ne "") {
     $pattern = "*_test.exe"
   }
 
+
   $search_path = -join ($BinariesFolder, $pattern)
   Write-Host "Binaries Search Path: $search_path"
 
@@ -308,7 +276,7 @@ if($SuiteRun -ne "") {
       continue
     }
 
-    if($RunOnly.Contains($bare_name)) {
+    if($RunOnly.Contains($e)) {
       MakeAndAdd -token $e -HashTable $TestExes
     } else {
       $ListOfSuites += $bare_name
@@ -319,6 +287,8 @@ if($SuiteRun -ne "") {
 }
 
 
+Write-Host "Attempting to start: $NumTestsToStart tests"
+
 # Invoke a test with a filter and redirect all output
 $InvokeTestCase = {
     param($exe, $test, $log);
@@ -337,7 +307,7 @@ $InvokeTestAsync = {
 # Test limiting factor here
 [int]$count = 0
 # Overall status
-[bool]$script:success = $true;
+[bool]$success = $true;
 
 function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
 {
@@ -363,7 +333,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
             $Cases = @{}
 
             if($Suites.Count -gt 0) {
-              # Will the first one
+              # Will teh first one
               ForEach($e in $Suites.Keys) {
                 $exe_name = $e
                 $Cases = $Suites[$e]
@@ -395,7 +365,6 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
                  break
                }
 
-              Write-Host "Starting $exe_name"
               [string]$Exe =  -Join ($BinariesFolder, $exe_name)
               $job = Start-Job -Name $exe_name -ScriptBlock $InvokeTestAsync -ArgumentList @($Exe,$log_path)
               $JobToLog.Add($job, $log_path)
@@ -426,7 +395,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
         $log_content = @(Get-Content $log)
 
         if($completed.State -ne "Completed") {
-            $script:success = $false
+            $success = $false
             Write-Warning $message
             $log_content | Write-Warning
         } else {
@@ -450,7 +419,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)
             }
 
             if(!$pass_found) {
-                $script:success = $false;
+                $success = $false;
                 Write-Warning $message
                 $log_content | Write-Warning
             } else {
@@ -474,7 +443,7 @@ New-TimeSpan -Start $StartDate -End $EndDate |
   }
 
 
-if(!$script:success) {
+if(!$success) {
 # This does not succeed killing off jobs quick
 # So we simply exit
 #    Remove-Job -Job $jobs -Force

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

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Update dependencies.sh file with the latest avaliable versions
 
@@ -39,7 +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
   
@@ -55,46 +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_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 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="$BASEDIR/dependencies.sh"
@@ -105,30 +64,30 @@ touch "$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_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
 

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

cache/cache_bench.cc

@@ -3,6 +3,9 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
 #ifndef GFLAGS
 #include <cstdio>
 int main() {
@@ -11,19 +14,19 @@ int main() {
 }
 #else
 
-#include <cinttypes>
+#include <inttypes.h>
 #include <sys/types.h>
 #include <stdio.h>
+#include <gflags/gflags.h>
 
-#include "port/port.h"
-#include "rocksdb/cache.h"
 #include "rocksdb/db.h"
+#include "rocksdb/cache.h"
 #include "rocksdb/env.h"
-#include "util/gflags_compat.h"
+#include "port/port.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
 
-using GFLAGS_NAMESPACE::ParseCommandLineFlags;
+using GFLAGS::ParseCommandLineFlags;
 
 static const uint32_t KB = 1024;
 
@@ -49,7 +52,7 @@ namespace rocksdb {
 
 class CacheBench;
 namespace {
-void deleter(const Slice& /*key*/, void* value) {
+void deleter(const Slice& key, void* value) {
     delete reinterpret_cast<char *>(value);
 }
 

cache/cache_test.cc

@@ -16,9 +16,9 @@
 #include <vector>
 #include "cache/clock_cache.h"
 #include "cache/lru_cache.h"
-#include "test_util/testharness.h"
 #include "util/coding.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
 
 namespace rocksdb {
 
@@ -40,9 +40,9 @@ static int DecodeValue(void* v) {
 const std::string kLRU = "lru";
 const std::string kClock = "clock";
 
-void dumbDeleter(const Slice& /*key*/, void* /*value*/) {}
+void dumbDeleter(const Slice& key, void* value) {}
 
-void eraseDeleter(const Slice& /*key*/, void* value) {
+void eraseDeleter(const Slice& key, void* value) {
   Cache* cache = reinterpret_cast<Cache*>(value);
   cache->Erase("foo");
 }
@@ -64,8 +64,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
 
   std::vector<int> deleted_keys_;
   std::vector<int> deleted_values_;
-  std::shared_ptr<Cache> cache_;
-  std::shared_ptr<Cache> cache2_;
+  shared_ptr<Cache> cache_;
+  shared_ptr<Cache> cache2_;
 
   CacheTest()
       : cache_(NewCache(kCacheSize, kNumShardBits, false)),
@@ -73,7 +73,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
     current_ = this;
   }
 
-  ~CacheTest() override {}
+  ~CacheTest() {
+  }
 
   std::shared_ptr<Cache> NewCache(size_t capacity) {
     auto type = GetParam();
@@ -90,7 +91,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
                                   bool strict_capacity_limit) {
     auto type = GetParam();
     if (type == kLRU) {
-      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit, 0.0);
+      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit);
     }
     if (type == kClock) {
       return NewClockCache(capacity, num_shard_bits, strict_capacity_limit);
@@ -98,7 +99,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return nullptr;
   }
 
-  int Lookup(std::shared_ptr<Cache> cache, int key) {
+  int Lookup(shared_ptr<Cache> cache, int key) {
     Cache::Handle* handle = cache->Lookup(EncodeKey(key));
     const int r = (handle == nullptr) ? -1 : DecodeValue(cache->Value(handle));
     if (handle != nullptr) {
@@ -107,16 +108,16 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return r;
   }
 
-  void Insert(std::shared_ptr<Cache> cache, int key, int value,
-              int charge = 1) {
+  void Insert(shared_ptr<Cache> cache, int key, int value, int charge = 1) {
     cache->Insert(EncodeKey(key), EncodeValue(value), charge,
                   &CacheTest::Deleter);
   }
 
-  void Erase(std::shared_ptr<Cache> cache, int key) {
+  void Erase(shared_ptr<Cache> cache, int key) {
     cache->Erase(EncodeKey(key));
   }
 
+
   int Lookup(int key) {
     return Lookup(cache_, key);
   }
@@ -144,7 +145,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
 CacheTest* CacheTest::current_;
 
 TEST_P(CacheTest, UsageTest) {
-  // cache is std::shared_ptr and will be automatically cleaned up.
+  // cache is shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
   auto cache = NewCache(kCapacity, 8, false);
 
@@ -172,7 +173,7 @@ TEST_P(CacheTest, UsageTest) {
 }
 
 TEST_P(CacheTest, PinnedUsageTest) {
-  // cache is std::shared_ptr and will be automatically cleaned up.
+  // cache is shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
   auto cache = NewCache(kCapacity, 8, false);
 
@@ -306,7 +307,7 @@ TEST_P(CacheTest, EvictionPolicy) {
   Insert(200, 201);
 
   // Frequently used entry must be kept around
-  for (int i = 0; i < kCacheSize + 200; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
     Insert(1000+i, 2000+i);
     ASSERT_EQ(101, Lookup(100));
   }
@@ -359,7 +360,7 @@ TEST_P(CacheTest, EvictionPolicyRef) {
   Insert(303, 104);
 
   // Insert entries much more than Cache capacity
-  for (int i = 0; i < kCacheSize + 200; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
     Insert(1000 + i, 2000 + i);
   }
 
@@ -469,42 +470,11 @@ class Value {
 };
 
 namespace {
-void deleter(const Slice& /*key*/, void* value) {
+void deleter(const Slice& key, void* value) {
   delete static_cast<Value *>(value);
 }
 }  // namespace
 
-TEST_P(CacheTest, ReleaseAndErase) {
-  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
-  Cache::Handle* handle;
-  Status s = cache->Insert(EncodeKey(100), EncodeValue(100), 1,
-                           &CacheTest::Deleter, &handle);
-  ASSERT_TRUE(s.ok());
-  ASSERT_EQ(5U, cache->GetCapacity());
-  ASSERT_EQ(1U, cache->GetUsage());
-  ASSERT_EQ(0U, deleted_keys_.size());
-  auto erased = cache->Release(handle, true);
-  ASSERT_TRUE(erased);
-  // This tests that deleter has been called
-  ASSERT_EQ(1U, deleted_keys_.size());
-}
-
-TEST_P(CacheTest, ReleaseWithoutErase) {
-  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
-  Cache::Handle* handle;
-  Status s = cache->Insert(EncodeKey(100), EncodeValue(100), 1,
-                           &CacheTest::Deleter, &handle);
-  ASSERT_TRUE(s.ok());
-  ASSERT_EQ(5U, cache->GetCapacity());
-  ASSERT_EQ(1U, cache->GetUsage());
-  ASSERT_EQ(0U, deleted_keys_.size());
-  auto erased = cache->Release(handle);
-  ASSERT_FALSE(erased);
-  // This tests that deleter is not called. When cache has free capacity it is
-  // not expected to immediately erase the released items.
-  ASSERT_EQ(0U, deleted_keys_.size());
-}
-
 TEST_P(CacheTest, SetCapacity) {
   // test1: increase capacity
   // lets create a cache with capacity 5,
@@ -562,7 +532,6 @@ TEST_P(CacheTest, SetStrictCapacityLimit) {
     ASSERT_OK(s);
     ASSERT_NE(nullptr, handles[i]);
   }
-  ASSERT_EQ(10, cache->GetUsage());
 
   // test2: set the flag to true. Insert and check if it fails.
   std::string extra_key = "extra";
@@ -572,7 +541,6 @@ TEST_P(CacheTest, SetStrictCapacityLimit) {
   s = cache->Insert(extra_key, extra_value, 1, &deleter, &handle);
   ASSERT_TRUE(s.IsIncomplete());
   ASSERT_EQ(nullptr, handle);
-  ASSERT_EQ(10, cache->GetUsage());
 
   for (size_t i = 0; i < 10; i++) {
     cache->Release(handles[i]);
@@ -593,7 +561,7 @@ TEST_P(CacheTest, SetStrictCapacityLimit) {
   s = cache2->Insert(extra_key, extra_value, 1, &deleter);
   // AS if the key have been inserted into cache but get evicted immediately.
   ASSERT_OK(s);
-  ASSERT_EQ(5, cache2->GetUsage());
+  ASSERT_EQ(5, cache->GetUsage());
   ASSERT_EQ(nullptr, cache2->Lookup(extra_key));
 
   for (size_t i = 0; i < 5; i++) {
@@ -688,17 +656,8 @@ TEST_P(CacheTest, DefaultShardBits) {
   ASSERT_EQ(6, sc->GetNumShardBits());
 }
 
-TEST_P(CacheTest, GetCharge) {
-  Insert(1, 2);
-  Cache::Handle* h1 = cache_->Lookup(EncodeKey(1));
-  ASSERT_EQ(2, DecodeValue(cache_->Value(h1)));
-  ASSERT_EQ(1, cache_->GetCharge(h1));
-  cache_->Release(h1);
-}
-
 #ifdef SUPPORT_CLOCK_CACHE
-std::shared_ptr<Cache> (*new_clock_cache_func)(size_t, int,
-                                               bool) = NewClockCache;
+shared_ptr<Cache> (*new_clock_cache_func)(size_t, int, bool) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                         testing::Values(kLRU, kClock));
 #else

cache/clock_cache.cc

@@ -13,8 +13,8 @@
 
 namespace rocksdb {
 
-std::shared_ptr<Cache> NewClockCache(size_t /*capacity*/, int /*num_shard_bits*/,
-                                     bool /*strict_capacity_limit*/) {
+std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
+                                     bool strict_capacity_limit) {
   // Clock cache not supported.
   return nullptr;
 }
@@ -26,12 +26,8 @@ std::shared_ptr<Cache> NewClockCache(size_t /*capacity*/, int /*num_shard_bits*/
 #include <assert.h>
 #include <atomic>
 #include <deque>
+#include <limits>
 
-// "tbb/concurrent_hash_map.h" requires RTTI if exception is enabled.
-// Disable it so users can chooose to disable RTTI.
-#ifndef ROCKSDB_USE_RTTI
-#define TBB_USE_EXCEPTIONS 0
-#endif
 #include "tbb/concurrent_hash_map.h"
 
 #include "cache/sharded_cache.h"
@@ -234,35 +230,35 @@ struct CleanupContext {
 };
 
 // A cache shard which maintains its own CLOCK cache.
-class ClockCacheShard final : public CacheShard {
+class ClockCacheShard : public CacheShard {
  public:
   // Hash map type.
   typedef tbb::concurrent_hash_map<CacheKey, CacheHandle*, CacheKey> HashTable;
 
   ClockCacheShard();
-  ~ClockCacheShard() override;
+  ~ClockCacheShard();
 
   // Interfaces
-  void SetCapacity(size_t capacity) override;
-  void SetStrictCapacityLimit(bool strict_capacity_limit) override;
-  Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value),
-                Cache::Handle** handle, Cache::Priority priority) override;
-  Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
+  virtual void SetCapacity(size_t capacity) override;
+  virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override;
+  virtual Status Insert(const Slice& key, uint32_t hash, void* value,
+                        size_t charge,
+                        void (*deleter)(const Slice& key, void* value),
+                        Cache::Handle** handle,
+                        Cache::Priority priority) override;
+  virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
   // If the entry in in cache, increase reference count and return true.
   // Return false otherwise.
   //
   // Not necessary to hold mutex_ before being called.
-  bool Ref(Cache::Handle* handle) override;
-  bool Release(Cache::Handle* handle, bool force_erase = false) override;
-  void Erase(const Slice& key, uint32_t hash) override;
-  bool EraseAndConfirm(const Slice& key, uint32_t hash,
-                       CleanupContext* context);
-  size_t GetUsage() const override;
-  size_t GetPinnedUsage() const override;
-  void EraseUnRefEntries() override;
-  void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
-                              bool thread_safe) override;
+  virtual bool Ref(Cache::Handle* handle) override;
+  virtual void Release(Cache::Handle* handle) override;
+  virtual void Erase(const Slice& key, uint32_t hash) override;
+  virtual size_t GetUsage() const override;
+  virtual size_t GetPinnedUsage() const override;
+  virtual void EraseUnRefEntries() override;
+  virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
+                                      bool thread_safe) override;
 
  private:
   static const uint32_t kInCacheBit = 1;
@@ -278,17 +274,13 @@ class ClockCacheShard final : public CacheShard {
   // Decrease reference count of the entry. If this decreases the count to 0,
   // recycle the entry. If set_usage is true, also set the usage bit.
   //
-  // returns true if a value is erased.
-  //
   // Not necessary to hold mutex_ before being called.
-  bool Unref(CacheHandle* handle, bool set_usage, CleanupContext* context);
+  void Unref(CacheHandle* handle, bool set_usage, CleanupContext* context);
 
   // Unset in-cache bit of the entry. Recycle the handle if necessary.
   //
-  // returns true if a value is erased.
-  //
   // Has to hold mutex_ before being called.
-  bool UnsetInCache(CacheHandle* handle, CleanupContext* context);
+  void UnsetInCache(CacheHandle* handle, CleanupContext* context);
 
   // Put the handle back to recycle_ list, and put the value associated with
   // it into to-be-deleted list. It doesn't cleanup the key as it might be
@@ -364,9 +356,7 @@ ClockCacheShard::~ClockCacheShard() {
   for (auto& handle : list_) {
     uint32_t flags = handle.flags.load(std::memory_order_relaxed);
     if (InCache(flags) || CountRefs(flags) > 0) {
-      if (handle.deleter != nullptr) {
-        (*handle.deleter)(handle.key, handle.value);
-      }
+      (*handle.deleter)(handle.key, handle.value);
       delete[] handle.key.data();
     }
   }
@@ -442,7 +432,7 @@ bool ClockCacheShard::Ref(Cache::Handle* h) {
   return false;
 }
 
-bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
+void ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
                             CleanupContext* context) {
   if (set_usage) {
     handle->flags.fetch_or(kUsageBit, std::memory_order_relaxed);
@@ -461,10 +451,9 @@ bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
       RecycleHandle(handle, context);
     }
   }
-  return context->to_delete_value.size();
 }
 
-bool ClockCacheShard::UnsetInCache(CacheHandle* handle,
+void ClockCacheShard::UnsetInCache(CacheHandle* handle,
                                    CleanupContext* context) {
   mutex_.AssertHeld();
   // Use acquire-release semantics as previous operations on the cache entry
@@ -476,7 +465,6 @@ bool ClockCacheShard::UnsetInCache(CacheHandle* handle,
   if (InCache(flags) && CountRefs(flags) == 0) {
     RecycleHandle(handle, context);
   }
-  return context->to_delete_value.size();
 }
 
 bool ClockCacheShard::TryEvict(CacheHandle* handle, CleanupContext* context) {
@@ -585,7 +573,7 @@ Status ClockCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
                                size_t charge,
                                void (*deleter)(const Slice& key, void* value),
                                Cache::Handle** out_handle,
-                               Cache::Priority /*priority*/) {
+                               Cache::Priority priority) {
   CleanupContext context;
   HashTable::accessor accessor;
   char* key_data = new char[key.size()];
@@ -630,34 +618,25 @@ Cache::Handle* ClockCacheShard::Lookup(const Slice& key, uint32_t hash) {
   return reinterpret_cast<Cache::Handle*>(handle);
 }
 
-bool ClockCacheShard::Release(Cache::Handle* h, bool force_erase) {
+void ClockCacheShard::Release(Cache::Handle* h) {
   CleanupContext context;
   CacheHandle* handle = reinterpret_cast<CacheHandle*>(h);
-  bool erased = Unref(handle, true, &context);
-  if (force_erase && !erased) {
-    erased = EraseAndConfirm(handle->key, handle->hash, &context);
-  }
+  Unref(handle, true, &context);
   Cleanup(context);
-  return erased;
 }
 
 void ClockCacheShard::Erase(const Slice& key, uint32_t hash) {
   CleanupContext context;
-  EraseAndConfirm(key, hash, &context);
-  Cleanup(context);
-}
-
-bool ClockCacheShard::EraseAndConfirm(const Slice& key, uint32_t hash,
-                                      CleanupContext* context) {
-  MutexLock l(&mutex_);
-  HashTable::accessor accessor;
-  bool erased = false;
-  if (table_.find(accessor, CacheKey(key, hash))) {
-    CacheHandle* handle = accessor->second;
-    table_.erase(accessor);
-    erased = UnsetInCache(handle, context);
+  {
+    MutexLock l(&mutex_);
+    HashTable::accessor accessor;
+    if (table_.find(accessor, CacheKey(key, hash))) {
+      CacheHandle* handle = accessor->second;
+      table_.erase(accessor);
+      UnsetInCache(handle, &context);
+    }
   }
-  return erased;
+  Cleanup(context);
 }
 
 void ClockCacheShard::EraseUnRefEntries() {
@@ -672,7 +651,7 @@ void ClockCacheShard::EraseUnRefEntries() {
   Cleanup(context);
 }
 
-class ClockCache final : public ShardedCache {
+class ClockCache : public ShardedCache {
  public:
   ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit)
       : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
@@ -682,31 +661,31 @@ class ClockCache final : public ShardedCache {
     SetStrictCapacityLimit(strict_capacity_limit);
   }
 
-  ~ClockCache() override { delete[] shards_; }
+  virtual ~ClockCache() { delete[] shards_; }
 
-  const char* Name() const override { return "ClockCache"; }
+  virtual const char* Name() const override { return "ClockCache"; }
 
-  CacheShard* GetShard(int shard) override {
+  virtual CacheShard* GetShard(int shard) override {
     return reinterpret_cast<CacheShard*>(&shards_[shard]);
   }
 
-  const CacheShard* GetShard(int shard) const override {
+  virtual const CacheShard* GetShard(int shard) const override {
     return reinterpret_cast<CacheShard*>(&shards_[shard]);
   }
 
-  void* Value(Handle* handle) override {
+  virtual void* Value(Handle* handle) override {
     return reinterpret_cast<const CacheHandle*>(handle)->value;
   }
 
-  size_t GetCharge(Handle* handle) const override {
+  virtual size_t GetCharge(Handle* handle) const override {
     return reinterpret_cast<const CacheHandle*>(handle)->charge;
   }
 
-  uint32_t GetHash(Handle* handle) const override {
+  virtual uint32_t GetHash(Handle* handle) const override {
     return reinterpret_cast<const CacheHandle*>(handle)->hash;
   }
 
-  void DisownData() override { shards_ = nullptr; }
+  virtual void DisownData() override { shards_ = nullptr; }
 
  private:
   ClockCacheShard* shards_;

cache/lru_cache.cc

@@ -7,6 +7,10 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/lru_cache.h"
 
 #include <assert.h>
@@ -18,13 +22,13 @@
 
 namespace rocksdb {
 
-LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {
+LRUHandleTable::LRUHandleTable() : length_(0), elems_(0), list_(nullptr) {
   Resize();
 }
 
 LRUHandleTable::~LRUHandleTable() {
   ApplyToAllCacheEntries([](LRUHandle* h) {
-    if (!h->HasRefs()) {
+    if (h->refs == 1) {
       h->Free();
     }
   });
@@ -95,35 +99,37 @@ void LRUHandleTable::Resize() {
   length_ = new_length;
 }
 
-LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                             double high_pri_pool_ratio,
-                             bool use_adaptive_mutex)
-    : capacity_(0),
-      high_pri_pool_usage_(0),
-      strict_capacity_limit_(strict_capacity_limit),
-      high_pri_pool_ratio_(high_pri_pool_ratio),
-      high_pri_pool_capacity_(0),
-      usage_(0),
-      lru_usage_(0),
-      mutex_(use_adaptive_mutex) {
+LRUCacheShard::LRUCacheShard()
+    : usage_(0), lru_usage_(0), high_pri_pool_usage_(0) {
   // Make empty circular linked list
   lru_.next = &lru_;
   lru_.prev = &lru_;
   lru_low_pri_ = &lru_;
-  SetCapacity(capacity);
 }
 
+LRUCacheShard::~LRUCacheShard() {}
+
+bool LRUCacheShard::Unref(LRUHandle* e) {
+  assert(e->refs > 0);
+  e->refs--;
+  return e->refs == 0;
+}
+
+// Call deleter and free
+
 void LRUCacheShard::EraseUnRefEntries() {
   autovector<LRUHandle*> last_reference_list;
   {
     MutexLock l(&mutex_);
     while (lru_.next != &lru_) {
       LRUHandle* old = lru_.next;
-      // LRU list contains only elements which can be evicted
-      assert(old->InCache() && !old->HasRefs());
+      assert(old->InCache());
+      assert(old->refs ==
+             1);  // LRU list contains elements which may be evicted
       LRU_Remove(old);
       table_.Remove(old->key(), old->hash);
       old->SetInCache(false);
+      Unref(old);
       usage_ -= old->charge;
       last_reference_list.push_back(old);
     }
@@ -136,41 +142,21 @@ void LRUCacheShard::EraseUnRefEntries() {
 
 void LRUCacheShard::ApplyToAllCacheEntries(void (*callback)(void*, size_t),
                                            bool thread_safe) {
-  const auto applyCallback = [&]() {
-    table_.ApplyToAllCacheEntries(
-        [callback](LRUHandle* h) { callback(h->value, h->charge); });
-  };
-
   if (thread_safe) {
-    MutexLock l(&mutex_);
-    applyCallback();
-  } else {
-    applyCallback();
+    mutex_.Lock();
+  }
+  table_.ApplyToAllCacheEntries(
+      [callback](LRUHandle* h) { callback(h->value, h->charge); });
+  if (thread_safe) {
+    mutex_.Unlock();
   }
 }
 
 void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
-  MutexLock l(&mutex_);
   *lru = &lru_;
   *lru_low_pri = lru_low_pri_;
 }
 
-size_t LRUCacheShard::TEST_GetLRUSize() {
-  MutexLock l(&mutex_);
-  LRUHandle* lru_handle = lru_.next;
-  size_t lru_size = 0;
-  while (lru_handle != &lru_) {
-    lru_size++;
-    lru_handle = lru_handle->next;
-  }
-  return lru_size;
-}
-
-double LRUCacheShard::GetHighPriPoolRatio() {
-  MutexLock l(&mutex_);
-  return high_pri_pool_ratio_;
-}
-
 void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   assert(e->next != nullptr);
   assert(e->prev != nullptr);
@@ -190,7 +176,7 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
   assert(e->next == nullptr);
   assert(e->prev == nullptr);
-  if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
+  if (high_pri_pool_ratio_ > 0 && e->IsHighPri()) {
     // Inset "e" to head of LRU list.
     e->next = &lru_;
     e->prev = lru_.prev;
@@ -224,13 +210,14 @@ void LRUCacheShard::MaintainPoolSize() {
 
 void LRUCacheShard::EvictFromLRU(size_t charge,
                                  autovector<LRUHandle*>* deleted) {
-  while ((usage_ + charge) > capacity_ && lru_.next != &lru_) {
+  while (usage_ + charge > capacity_ && lru_.next != &lru_) {
     LRUHandle* old = lru_.next;
-    // LRU list contains only elements which can be evicted
-    assert(old->InCache() && !old->HasRefs());
+    assert(old->InCache());
+    assert(old->refs == 1);  // LRU list contains elements which may be evicted
     LRU_Remove(old);
     table_.Remove(old->key(), old->hash);
     old->SetInCache(false);
+    Unref(old);
     usage_ -= old->charge;
     deleted->push_back(old);
   }
@@ -244,8 +231,8 @@ void LRUCacheShard::SetCapacity(size_t capacity) {
     high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
     EvictFromLRU(0, &last_reference_list);
   }
-
-  // Free the entries outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
   for (auto entry : last_reference_list) {
     entry->Free();
   }
@@ -261,22 +248,21 @@ Cache::Handle* LRUCacheShard::Lookup(const Slice& key, uint32_t hash) {
   LRUHandle* e = table_.Lookup(key, hash);
   if (e != nullptr) {
     assert(e->InCache());
-    if (!e->HasRefs()) {
-      // The entry is in LRU since it's in hash and has no external references
+    if (e->refs == 1) {
       LRU_Remove(e);
     }
-    e->Ref();
-    e->SetHit();
+    e->refs++;
   }
   return reinterpret_cast<Cache::Handle*>(e);
 }
 
 bool LRUCacheShard::Ref(Cache::Handle* h) {
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(h);
+  LRUHandle* handle = reinterpret_cast<LRUHandle*>(h);
   MutexLock l(&mutex_);
-  // To create another reference - entry must be already externally referenced
-  assert(e->HasRefs());
-  e->Ref();
+  if (handle->InCache() && handle->refs == 1) {
+    LRU_Remove(handle);
+  }
+  handle->refs++;
   return true;
 }
 
@@ -287,39 +273,41 @@ void LRUCacheShard::SetHighPriorityPoolRatio(double high_pri_pool_ratio) {
   MaintainPoolSize();
 }
 
-bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
+void LRUCacheShard::Release(Cache::Handle* handle) {
   if (handle == nullptr) {
-    return false;
+    return;
   }
   LRUHandle* e = reinterpret_cast<LRUHandle*>(handle);
   bool last_reference = false;
   {
     MutexLock l(&mutex_);
-    last_reference = e->Unref();
-    if (last_reference && e->InCache()) {
-      // The item is still in cache, and nobody else holds a reference to it
-      if (usage_ > capacity_ || force_erase) {
-        // The LRU list must be empty since the cache is full
-        assert(lru_.next == &lru_ || force_erase);
-        // Take this opportunity and remove the item
-        table_.Remove(e->key(), e->hash);
-        e->SetInCache(false);
-      } else {
-        // Put the item back on the LRU list, and don't free it
-        LRU_Insert(e);
-        last_reference = false;
-      }
-    }
+    last_reference = Unref(e);
     if (last_reference) {
       usage_ -= e->charge;
     }
+    if (e->refs == 1 && e->InCache()) {
+      // The item is still in cache, and nobody else holds a reference to it
+      if (usage_ > capacity_) {
+        // the cache is full
+        // The LRU list must be empty since the cache is full
+        assert(lru_.next == &lru_);
+        // take this opportunity and remove the item
+        table_.Remove(e->key(), e->hash);
+        e->SetInCache(false);
+        Unref(e);
+        usage_ -= e->charge;
+        last_reference = true;
+      } else {
+        // put the item on the list to be potentially freed
+        LRU_Insert(e);
+      }
+    }
   }
 
-  // Free the entry here outside of mutex for performance reasons
+  // free outside of mutex
   if (last_reference) {
     e->Free();
   }
-  return last_reference;
 }
 
 Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
@@ -331,16 +319,17 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   // It shouldn't happen very often though.
   LRUHandle* e = reinterpret_cast<LRUHandle*>(
       new char[sizeof(LRUHandle) - 1 + key.size()]);
-  Status s = Status::OK();
+  Status s;
   autovector<LRUHandle*> last_reference_list;
 
   e->value = value;
   e->deleter = deleter;
   e->charge = charge;
   e->key_length = key.size();
-  e->flags = 0;
   e->hash = hash;
-  e->refs = 0;
+  e->refs = (handle == nullptr
+                 ? 1
+                 : 2);  // One from LRUCache, one for the returned handle
   e->next = e->prev = nullptr;
   e->SetInCache(true);
   e->SetPriority(priority);
@@ -353,12 +342,11 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
     // is freed or the lru list is empty
     EvictFromLRU(charge, &last_reference_list);
 
-    if ((usage_ + charge) > capacity_ &&
+    if (usage_ - lru_usage_ + charge > capacity_ &&
         (strict_capacity_limit_ || handle == nullptr)) {
       if (handle == nullptr) {
         // Don't insert the entry but still return ok, as if the entry inserted
         // into cache and get evicted immediately.
-        e->SetInCache(false);
         last_reference_list.push_back(e);
       } else {
         delete[] reinterpret_cast<char*>(e);
@@ -366,30 +354,32 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
         s = Status::Incomplete("Insert failed due to LRU cache being full.");
       }
     } else {
-      // Insert into the cache. Note that the cache might get larger than its
-      // capacity if not enough space was freed up.
+      // insert into the cache
+      // note that the cache might get larger than its capacity if not enough
+      // space was freed
       LRUHandle* old = table_.Insert(e);
       usage_ += e->charge;
       if (old != nullptr) {
-        assert(old->InCache());
         old->SetInCache(false);
-        if (!old->HasRefs()) {
-          // old is on LRU because it's in cache and its reference count is 0
-          LRU_Remove(old);
+        if (Unref(old)) {
           usage_ -= old->charge;
+          // old is on LRU because it's in cache and its reference count
+          // was just 1 (Unref returned 0)
+          LRU_Remove(old);
           last_reference_list.push_back(old);
         }
       }
       if (handle == nullptr) {
         LRU_Insert(e);
       } else {
-        e->Ref();
         *handle = reinterpret_cast<Cache::Handle*>(e);
       }
+      s = Status::OK();
     }
   }
 
-  // Free the entries here outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
   for (auto entry : last_reference_list) {
     entry->Free();
   }
@@ -404,18 +394,18 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
     MutexLock l(&mutex_);
     e = table_.Remove(key, hash);
     if (e != nullptr) {
-      assert(e->InCache());
-      e->SetInCache(false);
-      if (!e->HasRefs()) {
-        // The entry is in LRU since it's in hash and has no external references
-        LRU_Remove(e);
+      last_reference = Unref(e);
+      if (last_reference) {
         usage_ -= e->charge;
-        last_reference = true;
       }
+      if (last_reference && e->InCache()) {
+        LRU_Remove(e);
+      }
+      e->SetInCache(false);
     }
   }
 
-  // Free the entry here outside of mutex for performance reasons
+  // mutex not held here
   // last_reference will only be true if e != nullptr
   if (last_reference) {
     e->Free();
@@ -445,31 +435,18 @@ std::string LRUCacheShard::GetPrintableOptions() const {
 }
 
 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit, double high_pri_pool_ratio,
-                   std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
-                   std::move(allocator)) {
-  num_shards_ = 1 << num_shard_bits;
-  shards_ = reinterpret_cast<LRUCacheShard*>(
-      port::cacheline_aligned_alloc(sizeof(LRUCacheShard) * num_shards_));
-  size_t per_shard = (capacity + (num_shards_ - 1)) / num_shards_;
-  for (int i = 0; i < num_shards_; i++) {
-    new (&shards_[i])
-        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio,
-            use_adaptive_mutex);
+                   bool strict_capacity_limit, double high_pri_pool_ratio)
+    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
+  int num_shards = 1 << num_shard_bits;
+  shards_ = new LRUCacheShard[num_shards];
+  SetCapacity(capacity);
+  SetStrictCapacityLimit(strict_capacity_limit);
+  for (int i = 0; i < num_shards; i++) {
+    shards_[i].SetHighPriorityPoolRatio(high_pri_pool_ratio);
   }
 }
 
-LRUCache::~LRUCache() {
-  if (shards_ != nullptr) {
-    assert(num_shards_ > 0);
-    for (int i = 0; i < num_shards_; i++) {
-      shards_[i].~LRUCacheShard();
-    }
-    port::cacheline_aligned_free(shards_);
-  }
-}
+LRUCache::~LRUCache() { delete[] shards_; }
 
 CacheShard* LRUCache::GetShard(int shard) {
   return reinterpret_cast<CacheShard*>(&shards_[shard]);
@@ -491,50 +468,11 @@ uint32_t LRUCache::GetHash(Handle* handle) const {
   return reinterpret_cast<const LRUHandle*>(handle)->hash;
 }
 
-void LRUCache::DisownData() {
-// Do not drop data if compile with ASAN to suppress leak warning.
-#if defined(__clang__)
-#if !defined(__has_feature) || !__has_feature(address_sanitizer)
-  shards_ = nullptr;
-  num_shards_ = 0;
-#endif
-#else  // __clang__
-#ifndef __SANITIZE_ADDRESS__
-  shards_ = nullptr;
-  num_shards_ = 0;
-#endif  // !__SANITIZE_ADDRESS__
-#endif  // __clang__
-}
+void LRUCache::DisownData() { shards_ = nullptr; }
 
-size_t LRUCache::TEST_GetLRUSize() {
-  size_t lru_size_of_all_shards = 0;
-  for (int i = 0; i < num_shards_; i++) {
-    lru_size_of_all_shards += shards_[i].TEST_GetLRUSize();
-  }
-  return lru_size_of_all_shards;
-}
-
-double LRUCache::GetHighPriPoolRatio() {
-  double result = 0.0;
-  if (num_shards_ > 0) {
-    result = shards_[0].GetHighPriPoolRatio();
-  }
-  return result;
-}
-
-std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
-  return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
-                     cache_opts.strict_capacity_limit,
-                     cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator,
-                     cache_opts.use_adaptive_mutex);
-}
-
-std::shared_ptr<Cache> NewLRUCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator,
-    bool use_adaptive_mutex) {
+std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
+                                   bool strict_capacity_limit,
+                                   double high_pri_pool_ratio) {
   if (num_shard_bits >= 20) {
     return nullptr;  // the cache cannot be sharded into too many fine pieces
   }
@@ -546,9 +484,7 @@ std::shared_ptr<Cache> NewLRUCache(
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
   return std::make_shared<LRUCache>(capacity, num_shard_bits,
-                                    strict_capacity_limit, high_pri_pool_ratio,
-                                    std::move(memory_allocator),
-                                    use_adaptive_mutex);
+                                    strict_capacity_limit, high_pri_pool_ratio);
 }
 
 }  // namespace rocksdb

cache/lru_cache.h

@@ -17,34 +17,31 @@
 
 namespace rocksdb {
 
-// LRU cache implementation. This class is not thread-safe.
+// LRU cache implementation
 
 // An entry is a variable length heap-allocated structure.
 // Entries are referenced by cache and/or by any external entity.
-// The cache keeps all its entries in a hash table. Some elements
+// The cache keeps all its entries in table. Some elements
 // are also stored on LRU list.
 //
 // LRUHandle can be in these states:
 // 1. Referenced externally AND in hash table.
-//    In that case the entry is *not* in the LRU list
-//    (refs >= 1 && in_cache == true)
-// 2. Not referenced externally AND in hash table.
-//    In that case the entry is in the LRU list and can be freed.
-//    (refs == 0 && in_cache == true)
-// 3. Referenced externally AND not in hash table.
-//    In that case the entry is not in the LRU list and not in hash table.
-//    The entry can be freed when refs becomes 0.
-//    (refs >= 1 && in_cache == false)
+//  In that case the entry is *not* in the LRU. (refs > 1 && in_cache == true)
+// 2. Not referenced externally and in hash table. In that case the entry is
+// in the LRU and can be freed. (refs == 1 && in_cache == true)
+// 3. Referenced externally and not in hash table. In that case the entry is
+// in not on LRU and not in table. (refs >= 1 && in_cache == false)
 //
 // All newly created LRUHandles are in state 1. If you call
-// LRUCacheShard::Release on entry in state 1, it will go into state 2.
-// To move from state 1 to state 3, either call LRUCacheShard::Erase or
-// LRUCacheShard::Insert with the same key (but possibly different value).
+// LRUCacheShard::Release
+// on entry in state 1, it will go into state 2. To move from state 1 to
+// state 3, either call LRUCacheShard::Erase or LRUCacheShard::Insert with the
+// same key.
 // To move from state 2 to state 1, use LRUCacheShard::Lookup.
 // Before destruction, make sure that no handles are in state 1. This means
 // that any successful LRUCacheShard::Lookup/LRUCacheShard::Insert have a
-// matching LRUCache::Release (to move into state 2) or LRUCacheShard::Erase
-// (to move into state 3).
+// matching
+// RUCache::Release (to move into state 2) or LRUCacheShard::Erase (for state 3)
 
 struct LRUHandle {
   void* value;
@@ -54,75 +51,59 @@ struct LRUHandle {
   LRUHandle* prev;
   size_t charge;  // TODO(opt): Only allow uint32_t?
   size_t key_length;
-  // The hash of key(). Used for fast sharding and comparisons.
-  uint32_t hash;
-  // The number of external refs to this entry. The cache itself is not counted.
-  uint32_t refs;
+  uint32_t refs;     // a number of refs to this entry
+                     // cache itself is counted as 1
 
-  enum Flags : uint8_t {
-    // Whether this entry is referenced by the hash table.
-    IN_CACHE = (1 << 0),
-    // Whether this entry is high priority entry.
-    IS_HIGH_PRI = (1 << 1),
-    // Whether this entry is in high-pri pool.
-    IN_HIGH_PRI_POOL = (1 << 2),
-    // Wwhether this entry has had any lookups (hits).
-    HAS_HIT = (1 << 3),
-  };
+  // Include the following flags:
+  //   in_cache:    whether this entry is referenced by the hash table.
+  //   is_high_pri: whether this entry is high priority entry.
+  //   in_high_pro_pool: whether this entry is in high-pri pool.
+  char flags;
 
-  uint8_t flags;
+  uint32_t hash;     // Hash of key(); used for fast sharding and comparisons
 
-  // Beginning of the key (MUST BE THE LAST FIELD IN THIS STRUCT!)
-  char key_data[1];
+  char key_data[1];  // Beginning of key
 
-  Slice key() const { return Slice(key_data, key_length); }
-
-  // Increase the reference count by 1.
-  void Ref() { refs++; }
-
-  // Just reduce the reference count by 1. Return true if it was last reference.
-  bool Unref() {
-    assert(refs > 0);
-    refs--;
-    return refs == 0;
+  Slice key() const {
+    // For cheaper lookups, we allow a temporary Handle object
+    // to store a pointer to a key in "value".
+    if (next == this) {
+      return *(reinterpret_cast<Slice*>(value));
+    } else {
+      return Slice(key_data, key_length);
+    }
   }
 
-  // Return true if there are external refs, false otherwise.
-  bool HasRefs() const { return refs > 0; }
-
-  bool InCache() const { return flags & IN_CACHE; }
-  bool IsHighPri() const { return flags & IS_HIGH_PRI; }
-  bool InHighPriPool() const { return flags & IN_HIGH_PRI_POOL; }
-  bool HasHit() const { return flags & HAS_HIT; }
+  bool InCache() { return flags & 1; }
+  bool IsHighPri() { return flags & 2; }
+  bool InHighPriPool() { return flags & 4; }
 
   void SetInCache(bool in_cache) {
     if (in_cache) {
-      flags |= IN_CACHE;
+      flags |= 1;
     } else {
-      flags &= ~IN_CACHE;
+      flags &= ~1;
     }
   }
 
   void SetPriority(Cache::Priority priority) {
     if (priority == Cache::Priority::HIGH) {
-      flags |= IS_HIGH_PRI;
+      flags |= 2;
     } else {
-      flags &= ~IS_HIGH_PRI;
+      flags &= ~2;
     }
   }
 
   void SetInHighPriPool(bool in_high_pri_pool) {
     if (in_high_pri_pool) {
-      flags |= IN_HIGH_PRI_POOL;
+      flags |= 4;
     } else {
-      flags &= ~IN_HIGH_PRI_POOL;
+      flags &= ~4;
     }
   }
 
-  void SetHit() { flags |= HAS_HIT; }
-
   void Free() {
-    assert(refs == 0);
+    assert((refs == 1 && InCache()) || (refs == 0 && !InCache()));
     if (deleter) {
       (*deleter)(key(), value);
     }
@@ -167,17 +148,16 @@ class LRUHandleTable {
 
   // The table consists of an array of buckets where each bucket is
   // a linked list of cache entries that hash into the bucket.
-  LRUHandle** list_;
   uint32_t length_;
   uint32_t elems_;
+  LRUHandle** list_;
 };
 
 // A single shard of sharded cache.
-class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
+class LRUCacheShard : public CacheShard {
  public:
-  LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                double high_pri_pool_ratio, bool use_adaptive_mutex);
-  virtual ~LRUCacheShard() override = default;
+  LRUCacheShard();
+  virtual ~LRUCacheShard();
 
   // Separate from constructor so caller can easily make an array of LRUCache
   // if current usage is more than new capacity, the function will attempt to
@@ -198,8 +178,7 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
                         Cache::Priority priority) override;
   virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
   virtual bool Ref(Cache::Handle* handle) override;
-  virtual bool Release(Cache::Handle* handle,
-                       bool force_erase = false) override;
+  virtual void Release(Cache::Handle* handle) override;
   virtual void Erase(const Slice& key, uint32_t hash) override;
 
   // Although in some platforms the update of size_t is atomic, to make sure
@@ -218,13 +197,6 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
 
   void TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri);
 
-  //  Retrieves number of elements in LRU, for unit test purpose only
-  //  not threadsafe
-  size_t TEST_GetLRUSize();
-
-  //  Retrives high pri pool ratio
-  double GetHighPriPoolRatio();
-
  private:
   void LRU_Remove(LRUHandle* e);
   void LRU_Insert(LRUHandle* e);
@@ -233,6 +205,10 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   // high-pri pool is no larger than the size specify by high_pri_pool_pct.
   void MaintainPoolSize();
 
+  // Just reduce the reference count by 1.
+  // Return true if last reference
+  bool Unref(LRUHandle* e);
+
   // Free some space following strict LRU policy until enough space
   // to hold (usage_ + charge) is freed or the lru list is empty
   // This function is not thread safe - it needs to be executed while
@@ -242,6 +218,12 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   // Initialized before use.
   size_t capacity_;
 
+  // Memory size for entries residing in the cache
+  size_t usage_;
+
+  // Memory size for entries residing only in the LRU list
+  size_t lru_usage_;
+
   // Memory size for entries in high-pri pool.
   size_t high_pri_pool_usage_;
 
@@ -255,6 +237,11 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   // Remember the value to avoid recomputing each time.
   double high_pri_pool_capacity_;
 
+  // mutex_ protects the following state.
+  // We don't count mutex_ as the cache's internal state so semantically we
+  // don't mind mutex_ invoking the non-const actions.
+  mutable port::Mutex mutex_;
+
   // Dummy head of LRU list.
   // lru.prev is newest entry, lru.next is oldest entry.
   // LRU contains items which can be evicted, ie reference only by cache
@@ -263,41 +250,13 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   // Pointer to head of low-pri pool in LRU list.
   LRUHandle* lru_low_pri_;
 
-  // ------------^^^^^^^^^^^^^-----------
-  // Not frequently modified data members
-  // ------------------------------------
-  //
-  // We separate data members that are updated frequently from the ones that
-  // are not frequently updated so that they don't share the same cache line
-  // which will lead into false cache sharing
-  //
-  // ------------------------------------
-  // Frequently modified data members
-  // ------------vvvvvvvvvvvvv-----------
   LRUHandleTable table_;
-
-  // Memory size for entries residing in the cache
-  size_t usage_;
-
-  // Memory size for entries residing only in the LRU list
-  size_t lru_usage_;
-
-  // mutex_ protects the following state.
-  // We don't count mutex_ as the cache's internal state so semantically we
-  // don't mind mutex_ invoking the non-const actions.
-  mutable port::Mutex mutex_;
 };
 
-class LRUCache
-#ifdef NDEBUG
-    final
-#endif
-    : public ShardedCache {
+class LRUCache : public ShardedCache {
  public:
   LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-           double high_pri_pool_ratio,
-           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex);
+           double high_pri_pool_ratio);
   virtual ~LRUCache();
   virtual const char* Name() const override { return "LRUCache"; }
   virtual CacheShard* GetShard(int shard) override;
@@ -307,14 +266,8 @@ class LRUCache
   virtual uint32_t GetHash(Handle* handle) const override;
   virtual void DisownData() override;
 
-  //  Retrieves number of elements in LRU, for unit test purpose only
-  size_t TEST_GetLRUSize();
-  //  Retrives high pri pool ratio
-  double GetHighPriPoolRatio();
-
  private:
-  LRUCacheShard* shards_ = nullptr;
-  int num_shards_ = 0;
+  LRUCacheShard* shards_;
 };
 
 }  // namespace rocksdb

cache/lru_cache_test.cc

@@ -7,31 +7,20 @@
 
 #include <string>
 #include <vector>
-#include "port/port.h"
-#include "test_util/testharness.h"
+#include "util/testharness.h"
 
 namespace rocksdb {
 
 class LRUCacheTest : public testing::Test {
  public:
   LRUCacheTest() {}
-  ~LRUCacheTest() override { DeleteCache(); }
+  ~LRUCacheTest() {}
 
-  void DeleteCache() {
-    if (cache_ != nullptr) {
-      cache_->~LRUCacheShard();
-      port::cacheline_aligned_free(cache_);
-      cache_ = nullptr;
-    }
-  }
-
-  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0,
-                bool use_adaptive_mutex = kDefaultToAdaptiveMutex) {
-    DeleteCache();
-    cache_ = reinterpret_cast<LRUCacheShard*>(
-        port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
-    new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
-                               high_pri_pool_ratio, use_adaptive_mutex);
+  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0) {
+    cache_.reset(new LRUCacheShard());
+    cache_->SetCapacity(capacity);
+    cache_->SetStrictCapacityLimit(false);
+    cache_->SetHighPriorityPoolRatio(high_pri_pool_ratio);
   }
 
   void Insert(const std::string& key,
@@ -87,7 +76,7 @@ class LRUCacheTest : public testing::Test {
   }
 
  private:
-  LRUCacheShard* cache_ = nullptr;
+  std::unique_ptr<LRUCacheShard> cache_;
 };
 
 TEST_F(LRUCacheTest, BasicLRU) {
@@ -116,30 +105,7 @@ TEST_F(LRUCacheTest, BasicLRU) {
   ValidateLRUList({"e", "z", "d", "u", "v"});
 }
 
-TEST_F(LRUCacheTest, MidpointInsertion) {
-  // Allocate 2 cache entries to high-pri pool.
-  NewCache(5, 0.45);
-
-  Insert("a", Cache::Priority::LOW);
-  Insert("b", Cache::Priority::LOW);
-  Insert("c", Cache::Priority::LOW);
-  Insert("x", Cache::Priority::HIGH);
-  Insert("y", Cache::Priority::HIGH);
-  ValidateLRUList({"a", "b", "c", "x", "y"}, 2);
-
-  // Low-pri entries inserted to the tail of low-pri list (the midpoint).
-  // After lookup, it will move to the tail of the full list.
-  Insert("d", Cache::Priority::LOW);
-  ValidateLRUList({"b", "c", "d", "x", "y"}, 2);
-  ASSERT_TRUE(Lookup("d"));
-  ValidateLRUList({"b", "c", "x", "y", "d"}, 2);
-
-  // High-pri entries will be inserted to the tail of full list.
-  Insert("z", Cache::Priority::HIGH);
-  ValidateLRUList({"c", "x", "y", "d", "z"}, 2);
-}
-
-TEST_F(LRUCacheTest, EntriesWithPriority) {
+TEST_F(LRUCacheTest, MidPointInsertion) {
   // Allocate 2 cache entries to high-pri pool.
   NewCache(5, 0.45);
 
@@ -165,15 +131,15 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   Insert("a", Cache::Priority::LOW);
   ValidateLRUList({"v", "X", "a", "Y", "Z"}, 2);
 
-  // Low-pri entries will be inserted to head of high-pri pool after lookup.
+  // Low-pri entries will be inserted to head of low-pri pool after lookup.
   ASSERT_TRUE(Lookup("v"));
-  ValidateLRUList({"X", "a", "Y", "Z", "v"}, 2);
+  ValidateLRUList({"X", "a", "v", "Y", "Z"}, 2);
 
   // High-pri entries will be inserted to the head of the list after lookup.
   ASSERT_TRUE(Lookup("X"));
-  ValidateLRUList({"a", "Y", "Z", "v", "X"}, 2);
+  ValidateLRUList({"a", "v", "Y", "Z", "X"}, 2);
   ASSERT_TRUE(Lookup("Z"));
-  ValidateLRUList({"a", "Y", "v", "X", "Z"}, 2);
+  ValidateLRUList({"a", "v", "Y", "X", "Z"}, 2);
 
   Erase("Y");
   ValidateLRUList({"a", "v", "X", "Z"}, 2);
@@ -186,7 +152,7 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   Insert("g", Cache::Priority::LOW);
   ValidateLRUList({"d", "e", "f", "g", "Z"}, 1);
   ASSERT_TRUE(Lookup("d"));
-  ValidateLRUList({"e", "f", "g", "Z", "d"}, 2);
+  ValidateLRUList({"e", "f", "g", "d", "Z"}, 1);
 }
 
 }  // namespace rocksdb

cache/sharded_cache.cc

@@ -7,6 +7,10 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/sharded_cache.h"
 
 #include <string>
@@ -16,10 +20,8 @@
 namespace rocksdb {
 
 ShardedCache::ShardedCache(size_t capacity, int num_shard_bits,
-                           bool strict_capacity_limit,
-                           std::shared_ptr<MemoryAllocator> allocator)
-    : Cache(std::move(allocator)),
-      num_shard_bits_(num_shard_bits),
+                           bool strict_capacity_limit)
+    : num_shard_bits_(num_shard_bits),
       capacity_(capacity),
       strict_capacity_limit_(strict_capacity_limit),
       last_id_(1) {}
@@ -51,7 +53,7 @@ Status ShardedCache::Insert(const Slice& key, void* value, size_t charge,
       ->Insert(key, hash, value, charge, deleter, handle, priority);
 }
 
-Cache::Handle* ShardedCache::Lookup(const Slice& key, Statistics* /*stats*/) {
+Cache::Handle* ShardedCache::Lookup(const Slice& key, Statistics* stats) {
   uint32_t hash = HashSlice(key);
   return GetShard(Shard(hash))->Lookup(key, hash);
 }
@@ -61,9 +63,9 @@ bool ShardedCache::Ref(Handle* handle) {
   return GetShard(Shard(hash))->Ref(handle);
 }
 
-bool ShardedCache::Release(Handle* handle, bool force_erase) {
+void ShardedCache::Release(Handle* handle) {
   uint32_t hash = GetHash(handle);
-  return GetShard(Shard(hash))->Release(handle, force_erase);
+  GetShard(Shard(hash))->Release(handle);
 }
 
 void ShardedCache::Erase(const Slice& key) {
@@ -140,9 +142,6 @@ std::string ShardedCache::GetPrintableOptions() const {
              strict_capacity_limit_);
     ret.append(buffer);
   }
-  snprintf(buffer, kBufferSize, "    memory_allocator : %s\n",
-           memory_allocator() ? memory_allocator()->Name() : "None");
-  ret.append(buffer);
   ret.append(GetShard(0)->GetPrintableOptions());
   return ret;
 }

cache/sharded_cache.h

@@ -30,7 +30,7 @@ class CacheShard {
                         Cache::Handle** handle, Cache::Priority priority) = 0;
   virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) = 0;
   virtual bool Ref(Cache::Handle* handle) = 0;
-  virtual bool Release(Cache::Handle* handle, bool force_erase = false) = 0;
+  virtual void Release(Cache::Handle* handle) = 0;
   virtual void Erase(const Slice& key, uint32_t hash) = 0;
   virtual void SetCapacity(size_t capacity) = 0;
   virtual void SetStrictCapacityLimit(bool strict_capacity_limit) = 0;
@@ -47,15 +47,13 @@ class CacheShard {
 // Keys are sharded by the highest num_shard_bits bits of hash value.
 class ShardedCache : public Cache {
  public:
-  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-               std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
+  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit);
   virtual ~ShardedCache() = default;
   virtual const char* Name() const override = 0;
   virtual CacheShard* GetShard(int shard) = 0;
   virtual const CacheShard* GetShard(int shard) const = 0;
   virtual void* Value(Handle* handle) override = 0;
-  virtual size_t GetCharge(Handle* handle) const override = 0;
-
+  virtual size_t GetCharge(Handle* handle) const = 0;
   virtual uint32_t GetHash(Handle* handle) const = 0;
   virtual void DisownData() override = 0;
 
@@ -67,7 +65,7 @@ class ShardedCache : public Cache {
                         Handle** handle, Priority priority) override;
   virtual Handle* Lookup(const Slice& key, Statistics* stats) override;
   virtual bool Ref(Handle* handle) override;
-  virtual bool Release(Handle* handle, bool force_erase = false) override;
+  virtual void Release(Handle* handle) override;
   virtual void Erase(const Slice& key) override;
   virtual uint64_t NewId() override;
   virtual size_t GetCapacity() const override;
@@ -84,7 +82,7 @@ class ShardedCache : public Cache {
 
  private:
   static inline uint32_t HashSlice(const Slice& s) {
-    return static_cast<uint32_t>(GetSliceNPHash64(s));
+    return Hash(s.data(), s.size(), 0);
   }
 
   uint32_t Shard(uint32_t hash) {

cmake/RocksDBConfig.cmake.in

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

cmake/modules/FindNUMA.cmake

@@ -1,21 +0,0 @@
-# - Find NUMA
-# Find the NUMA library and includes
-#
-# NUMA_INCLUDE_DIR - where to find numa.h, etc.
-# NUMA_LIBRARIES - List of libraries when using NUMA.
-# NUMA_FOUND - True if NUMA found.
-
-find_path(NUMA_INCLUDE_DIR
-  NAMES numa.h numaif.h
-  HINTS ${NUMA_ROOT_DIR}/include)
-
-find_library(NUMA_LIBRARIES
-  NAMES numa
-  HINTS ${NUMA_ROOT_DIR}/lib)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIR)
-
-mark_as_advanced(
-  NUMA_LIBRARIES
-  NUMA_INCLUDE_DIR)

cmake/modules/FindTBB.cmake

@@ -1,25 +0,0 @@
-# - Find TBB
-# Find the Thread Building Blocks library and includes
-#
-# TBB_INCLUDE_DIR - where to find tbb.h, etc.
-# TBB_LIBRARIES - List of libraries when using TBB.
-# TBB_FOUND - True if TBB found.
-
-if(NOT DEFINED TBB_ROOT_DIR)
-  set(TBB_ROOT_DIR "$ENV{TBBROOT}")
-endif()
-
-find_path(TBB_INCLUDE_DIR
-NAMES tbb/tbb.h
-HINTS ${TBB_ROOT_DIR}/include)
-
-find_library(TBB_LIBRARIES
-NAMES tbb
-HINTS ${TBB_ROOT_DIR}/lib ENV LIBRARY_PATH)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIR)
-
-mark_as_advanced(
-TBB_LIBRARIES
-TBB_INCLUDE_DIR)

cmake/modules/Findbzip2.cmake

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

cmake/modules/Findlz4.cmake

@@ -1,21 +0,0 @@
-# - Find Lz4
-# Find the lz4 compression library and includes
-#
-# LZ4_INCLUDE_DIR - where to find lz4.h, etc.
-# LZ4_LIBRARIES - List of libraries when using lz4.
-# LZ4_FOUND - True if lz4 found.
-
-find_path(LZ4_INCLUDE_DIR
-  NAMES lz4.h
-  HINTS ${LZ4_ROOT_DIR}/include)
-
-find_library(LZ4_LIBRARIES
-  NAMES lz4
-  HINTS ${LZ4_ROOT_DIR}/lib)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(lz4 DEFAULT_MSG LZ4_LIBRARIES LZ4_INCLUDE_DIR)
-
-mark_as_advanced(
-  LZ4_LIBRARIES
-  LZ4_INCLUDE_DIR)

cmake/modules/Findzstd.cmake

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

coverage/coverage_test.sh

@@ -1,5 +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/builder.cc

@@ -13,15 +13,13 @@
 #include <deque>
 #include <vector>
 
-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
-#include "db/range_del_aggregator.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
-#include "file/filename.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -29,38 +27,35 @@
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block_based_table_builder.h"
-#include "table/format.h"
+#include "table/block_based_table_builder.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
 #include "util/file_reader_writer.h"
+#include "util/filename.h"
 #include "util/stop_watch.h"
+#include "util/sync_point.h"
 
 namespace rocksdb {
 
 class TableFactory;
 
 TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
+    const ImmutableCFOptions& ioptions,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
     WritableFileWriter* file, const CompressionType compression_type,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    int level, const bool skip_filters, const uint64_t creation_time,
-    const uint64_t oldest_key_time, const uint64_t target_file_size,
-    const uint64_t file_creation_time) {
+    const CompressionOptions& compression_opts,
+    int level,
+    const std::string* compression_dict, const bool skip_filters) {
   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);
 }
 
@@ -68,21 +63,18 @@ Status BuildTable(
     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());
@@ -91,13 +83,15 @@ 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(
@@ -105,16 +99,11 @@ 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<WritableFile> file;
+      unique_ptr<WritableFile> file;
 #ifndef NDEBUG
       bool use_direct_writes = env_options.use_direct_writes;
       TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
@@ -127,30 +116,24 @@ Status BuildTable(
         return s;
       }
       file->SetIOPriority(io_priority);
-      file->SetWriteLifeTimeHint(write_hint);
 
-      file_writer.reset(
-          new WritableFileWriter(std::move(file), fname, env_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()) {
@@ -166,20 +149,12 @@ 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();
@@ -192,7 +167,7 @@ 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;
       }
@@ -216,14 +191,12 @@ Status BuildTable(
       // we will regrad this verification as user reads since the goal is
       // to cache it here for further user reads
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          ReadOptions(), env_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()) {

db/builder.h

@@ -9,9 +9,7 @@
 #include <string>
 #include <utility>
 #include <vector>
-#include "db/range_tombstone_fragmenter.h"
 #include "db/table_properties_collector.h"
-#include "logging/event_logger.h"
 #include "options/cf_options.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/env.h"
@@ -21,6 +19,7 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/event_logger.h"
 
 namespace rocksdb {
 
@@ -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
@@ -65,23 +65,18 @@ extern Status BuildTable(
     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/c_test.c

@@ -1,7 +1,6 @@
 /* Copyright (c) 2011 The LevelDB Authors. All rights reserved.
    Use of this source code is governed by a BSD-style license that can be
    found in the LICENSE file. See the AUTHORS file for names of contributors. */
-// Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 #include <stdio.h>
 
@@ -20,7 +19,10 @@
 
 // Can not use port/port.h macros as this is a c file
 #ifdef OS_WIN
-#include <windows.h>
+
+#include <Windows.h>
+
+#define snprintf _snprintf
 
 // Ok for uniqueness
 int geteuid() {
@@ -32,38 +34,23 @@ int geteuid() {
   return result;
 }
 
-// VS < 2015
-#if defined(_MSC_VER) && (_MSC_VER < 1900)
-#define snprintf _snprintf
-#endif
-
 #endif
 
 const char* phase = "";
 static char dbname[200];
 static char sstfilename[200];
 static char dbbackupname[200];
-static char dbcheckpointname[200];
-static char dbpathname[200];
-static char secondary_path[200];
 
 static void StartPhase(const char* name) {
   fprintf(stderr, "=== Test %s\n", name);
   phase = name;
 }
-#ifdef _MSC_VER
-#pragma warning(push)
-#pragma warning (disable: 4996) // getenv security warning
-#endif
 static const char* GetTempDir(void) {
     const char* ret = getenv("TEST_TMPDIR");
     if (ret == NULL || ret[0] == '\0')
         ret = "/tmp";
     return ret;
 }
-#ifdef _MSC_VER
-#pragma warning(pop)
-#endif
 
 #define CheckNoError(err)                                               \
   if ((err) != NULL) {                                                  \
@@ -139,32 +126,6 @@ static void CheckGetCF(
   Free(&val);
 }
 
-static void CheckPinGet(rocksdb_t* db, const rocksdb_readoptions_t* options,
-                        const char* key, const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  const char* val;
-  rocksdb_pinnableslice_t* p;
-  p = rocksdb_get_pinned(db, options, key, strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
-
-static void CheckPinGetCF(rocksdb_t* db, const rocksdb_readoptions_t* options,
-                          rocksdb_column_family_handle_t* handle,
-                          const char* key, const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  const char* val;
-  rocksdb_pinnableslice_t* p;
-  p = rocksdb_get_pinned_cf(db, options, handle, key, strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
 
 static void CheckIter(rocksdb_iterator_t* iter,
                       const char* key, const char* val) {
@@ -203,11 +164,10 @@ static void CheckDel(void* ptr, const char* k, size_t klen) {
   (*state)++;
 }
 
-static void CmpDestroy(void* arg) { (void)arg; }
+static void CmpDestroy(void* arg) { }
 
 static int CmpCompare(void* arg, const char* a, size_t alen,
                       const char* b, size_t blen) {
-  (void)arg;
   size_t n = (alen < blen) ? alen : blen;
   int r = memcmp(a, b, n);
   if (r == 0) {
@@ -218,15 +178,13 @@ static int CmpCompare(void* arg, const char* a, size_t alen,
 }
 
 static const char* CmpName(void* arg) {
-  (void)arg;
   return "foo";
 }
 
 // Custom filter policy
 static unsigned char fake_filter_result = 1;
-static void FilterDestroy(void* arg) { (void)arg; }
+static void FilterDestroy(void* arg) { }
 static const char* FilterName(void* arg) {
-  (void)arg;
   return "TestFilter";
 }
 static char* FilterCreate(
@@ -234,10 +192,6 @@ static char* FilterCreate(
     const char* const* key_array, const size_t* key_length_array,
     int num_keys,
     size_t* filter_length) {
-  (void)arg;
-  (void)key_array;
-  (void)key_length_array;
-  (void)num_keys;
   *filter_length = 4;
   char* result = malloc(4);
   memcpy(result, "fake", 4);
@@ -247,30 +201,20 @@ static unsigned char FilterKeyMatch(
     void* arg,
     const char* key, size_t length,
     const char* filter, size_t filter_length) {
-  (void)arg;
-  (void)key;
-  (void)length;
   CheckCondition(filter_length == 4);
   CheckCondition(memcmp(filter, "fake", 4) == 0);
   return fake_filter_result;
 }
 
 // Custom compaction filter
-static void CFilterDestroy(void* arg) { (void)arg; }
-static const char* CFilterName(void* arg) {
-  (void)arg;
-  return "foo";
-}
+static void CFilterDestroy(void* arg) {}
+static const char* CFilterName(void* arg) { return "foo"; }
 static unsigned char CFilterFilter(void* arg, int level, const char* key,
                                    size_t key_length,
                                    const char* existing_value,
                                    size_t value_length, char** new_value,
                                    size_t* new_value_length,
                                    unsigned char* value_changed) {
-  (void)arg;
-  (void)level;
-  (void)existing_value;
-  (void)value_length;
   if (key_length == 3) {
     if (memcmp(key, "bar", key_length) == 0) {
       return 1;
@@ -284,15 +228,10 @@ static unsigned char CFilterFilter(void* arg, int level, const char* key,
   return 0;
 }
 
-static void CFilterFactoryDestroy(void* arg) { (void)arg; }
-static const char* CFilterFactoryName(void* arg) {
-  (void)arg;
-  return "foo";
-}
+static void CFilterFactoryDestroy(void* arg) {}
+static const char* CFilterFactoryName(void* arg) { return "foo"; }
 static rocksdb_compactionfilter_t* CFilterCreate(
     void* arg, rocksdb_compactionfiltercontext_t* context) {
-  (void)arg;
-  (void)context;
   return rocksdb_compactionfilter_create(NULL, CFilterDestroy, CFilterFilter,
                                          CFilterName);
 }
@@ -323,9 +262,8 @@ static rocksdb_t* CheckCompaction(rocksdb_t* db, rocksdb_options_t* options,
 }
 
 // Custom merge operator
-static void MergeOperatorDestroy(void* arg) { (void)arg; }
+static void MergeOperatorDestroy(void* arg) { }
 static const char* MergeOperatorName(void* arg) {
-  (void)arg;
   return "TestMergeOperator";
 }
 static char* MergeOperatorFullMerge(
@@ -335,14 +273,6 @@ static char* MergeOperatorFullMerge(
     const char* const* operands_list, const size_t* operands_list_length,
     int num_operands,
     unsigned char* success, size_t* new_value_length) {
-  (void)arg;
-  (void)key;
-  (void)key_length;
-  (void)existing_value;
-  (void)existing_value_length;
-  (void)operands_list;
-  (void)operands_list_length;
-  (void)num_operands;
   *new_value_length = 4;
   *success = 1;
   char* result = malloc(4);
@@ -355,12 +285,6 @@ static char* MergeOperatorPartialMerge(
     const char* const* operands_list, const size_t* operands_list_length,
     int num_operands,
     unsigned char* success, size_t* new_value_length) {
-  (void)arg;
-  (void)key;
-  (void)key_length;
-  (void)operands_list;
-  (void)operands_list_length;
-  (void)num_operands;
   *new_value_length = 4;
   *success = 1;
   char* result = malloc(4);
@@ -368,69 +292,10 @@ static char* MergeOperatorPartialMerge(
   return result;
 }
 
-static void CheckTxnGet(
-        rocksdb_transaction_t* txn,
-        const rocksdb_readoptions_t* options,
-        const char* key,
-        const char* expected) {
-        char* err = NULL;
-        size_t val_len;
-        char* val;
-        val = rocksdb_transaction_get(txn, options, key, strlen(key), &val_len, &err);
-        CheckNoError(err);
-        CheckEqual(expected, val, val_len);
-        Free(&val);
-}
-
-static void CheckTxnGetCF(rocksdb_transaction_t* txn,
-                          const rocksdb_readoptions_t* options,
-                          rocksdb_column_family_handle_t* column_family,
-                          const char* key, const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  char* val;
-  val = rocksdb_transaction_get_cf(txn, options, column_family, key,
-                                   strlen(key), &val_len, &err);
-  CheckNoError(err);
-  CheckEqual(expected, val, val_len);
-  Free(&val);
-}
-
-static void CheckTxnDBGet(
-        rocksdb_transactiondb_t* txn_db,
-        const rocksdb_readoptions_t* options,
-        const char* key,
-        const char* expected) {
-        char* err = NULL;
-        size_t val_len;
-        char* val;
-        val = rocksdb_transactiondb_get(txn_db, options, key, strlen(key), &val_len, &err);
-        CheckNoError(err);
-        CheckEqual(expected, val, val_len);
-        Free(&val);
-}
-
-static void CheckTxnDBGetCF(rocksdb_transactiondb_t* txn_db,
-                            const rocksdb_readoptions_t* options,
-                            rocksdb_column_family_handle_t* column_family,
-                            const char* key, const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  char* val;
-  val = rocksdb_transactiondb_get_cf(txn_db, options, column_family, key,
-                                     strlen(key), &val_len, &err);
-  CheckNoError(err);
-  CheckEqual(expected, val, val_len);
-  Free(&val);
-}
-
 int main(int argc, char** argv) {
-  (void)argc;
-  (void)argv;
   rocksdb_t* db;
   rocksdb_comparator_t* cmp;
   rocksdb_cache_t* cache;
-  rocksdb_dbpath_t *dbpath;
   rocksdb_env_t* env;
   rocksdb_options_t* options;
   rocksdb_compactoptions_t* coptions;
@@ -438,12 +303,6 @@ int main(int argc, char** argv) {
   rocksdb_readoptions_t* roptions;
   rocksdb_writeoptions_t* woptions;
   rocksdb_ratelimiter_t* rate_limiter;
-  rocksdb_transactiondb_t* txn_db;
-  rocksdb_transactiondb_options_t* txn_db_options;
-  rocksdb_transaction_t* txn;
-  rocksdb_transaction_options_t* txn_options;
-  rocksdb_optimistictransactiondb_t* otxn_db;
-  rocksdb_optimistictransaction_options_t* otxn_options;
   char* err = NULL;
   int run = -1;
 
@@ -457,24 +316,13 @@ int main(int argc, char** argv) {
            GetTempDir(),
            ((int) geteuid()));
 
-  snprintf(dbcheckpointname, sizeof(dbcheckpointname),
-           "%s/rocksdb_c_test-%d-checkpoint",
-           GetTempDir(),
-           ((int) geteuid()));
-
   snprintf(sstfilename, sizeof(sstfilename),
            "%s/rocksdb_c_test-%d-sst",
            GetTempDir(),
            ((int)geteuid()));
 
-  snprintf(dbpathname, sizeof(dbpathname),
-           "%s/rocksdb_c_test-%d-dbpath",
-           GetTempDir(),
-           ((int) geteuid()));
-
   StartPhase("create_objects");
   cmp = rocksdb_comparator_create(NULL, CmpDestroy, CmpCompare, CmpName);
-  dbpath = rocksdb_dbpath_create(dbpathname, 1024 * 1024);
   env = rocksdb_create_default_env();
   cache = rocksdb_cache_create_lru(100000);
 
@@ -583,36 +431,6 @@ int main(int argc, char** argv) {
     rocksdb_backup_engine_close(be);
   }
 
-  StartPhase("checkpoint");
-  {
-    rocksdb_destroy_db(options, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_t* checkpoint = rocksdb_checkpoint_object_create(db, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_create(checkpoint, dbcheckpointname, 0, &err);
-    CheckNoError(err);
-
-    // start a new database from the checkpoint
-    rocksdb_close(db);
-    rocksdb_options_set_error_if_exists(options, 0);
-    db = rocksdb_open(options, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    CheckGet(db, roptions, "foo", "hello");
-
-    rocksdb_checkpoint_object_destroy(checkpoint);
-
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_options_set_error_if_exists(options, 1);
-  }
-
   StartPhase("compactall");
   rocksdb_compact_range(db, NULL, 0, NULL, 0);
   CheckGet(db, roptions, "foo", "hello");
@@ -654,14 +472,14 @@ int main(int argc, char** argv) {
     rocksdb_sstfilewriter_t* writer =
         rocksdb_sstfilewriter_create(env_opt, io_options);
 
-    remove(sstfilename);
+    unlink(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk1", 5, "v1", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk1", 5, "v1", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v2", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v2", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk3", 5, "v3", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v3", 2, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_finish(writer, &err);
     CheckNoError(err);
@@ -675,14 +493,14 @@ int main(int argc, char** argv) {
     CheckGet(db, roptions, "sstk2", "v2");
     CheckGet(db, roptions, "sstk3", "v3");
 
-    remove(sstfilename);
+    unlink(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v4", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v4", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk22", 6, "v5", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk22", 6, "v5", 2, &err);
     CheckNoError(err);
-    rocksdb_sstfilewriter_put(writer, "sstk3", 5, "v6", 2, &err);
+    rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v6", 2, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_finish(writer, &err);
     CheckNoError(err);
@@ -769,13 +587,10 @@ int main(int argc, char** argv) {
   {
     rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
     rocksdb_writebatch_set_save_point(wb);
-    rocksdb_writebatch_set_save_point(wb);
     const char* k_list[2] = {"z", "ap"};
     const size_t k_sizes[2] = {1, 2};
     const char* v_list[3] = {"x", "y", "z"};
     const size_t v_sizes[3] = {1, 1, 1};
-    rocksdb_writebatch_pop_save_point(wb, &err);
-    CheckNoError(err);
     rocksdb_writebatch_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
     rocksdb_writebatch_rollback_to_save_point(wb, &err);
     CheckNoError(err);
@@ -919,8 +734,7 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_wi_t* wbi = rocksdb_writebatch_wi_create(0, 1);
     rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
     rocksdb_writebatch_wi_delete(wbi, "foo", 3);
-    rocksdb_iterator_t* iter =
-        rocksdb_writebatch_wi_create_iterator_with_base(wbi, base_iter);
+    rocksdb_iterator_t* iter = rocksdb_writebatch_wi_create_iterator_with_base(wbi, base_iter);
     CheckCondition(!rocksdb_iter_valid(iter));
     rocksdb_iter_seek_to_first(iter);
     CheckCondition(rocksdb_iter_valid(iter));
@@ -972,13 +786,6 @@ int main(int argc, char** argv) {
     }
   }
 
-  StartPhase("pin_get");
-  {
-    CheckPinGet(db, roptions, "box", "c");
-    CheckPinGet(db, roptions, "foo", "hello");
-    CheckPinGet(db, roptions, "notfound", NULL);
-  }
-
   StartPhase("approximate_sizes");
   {
     int i;
@@ -1189,20 +996,12 @@ int main(int argc, char** argv) {
     rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &err);
     CheckNoError(err);
 
-    rocksdb_flushoptions_t *flush_options = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_options, 1);
-    rocksdb_flush_cf(db, flush_options, handles[1], &err);
-    CheckNoError(err)
-    rocksdb_flushoptions_destroy(flush_options);
-
     CheckGetCF(db, roptions, handles[1], "foo", "hello");
-    CheckPinGetCF(db, roptions, handles[1], "foo", "hello");
 
     rocksdb_delete_cf(db, woptions, handles[1], "foo", 3, &err);
     CheckNoError(err);
 
     CheckGetCF(db, roptions, handles[1], "foo", NULL);
-    CheckPinGetCF(db, roptions, handles[1], "foo", NULL);
 
     rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
     rocksdb_writebatch_put_cf(wb, handles[1], "baz", 3, "a", 1);
@@ -1215,9 +1014,6 @@ int main(int argc, char** argv) {
     CheckGetCF(db, roptions, handles[1], "baz", NULL);
     CheckGetCF(db, roptions, handles[1], "bar", NULL);
     CheckGetCF(db, roptions, handles[1], "box", "c");
-    CheckPinGetCF(db, roptions, handles[1], "baz", NULL);
-    CheckPinGetCF(db, roptions, handles[1], "bar", NULL);
-    CheckPinGetCF(db, roptions, handles[1], "box", "c");
     rocksdb_writebatch_destroy(wb);
 
     const char* keys[3] = { "box", "box", "barfooxx" };
@@ -1352,47 +1148,6 @@ int main(int argc, char** argv) {
     rocksdb_destroy_db(options, dbname, &err);
   }
 
-  // Check memory usage stats
-  StartPhase("approximate_memory_usage");
-  {
-    // Create database
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_memory_consumers_t* consumers;
-    consumers = rocksdb_memory_consumers_create();
-    rocksdb_memory_consumers_add_db(consumers, db);
-    rocksdb_memory_consumers_add_cache(consumers, cache);
-
-    // take memory usage report before write-read operation
-    rocksdb_memory_usage_t* mu1;
-    mu1 = rocksdb_approximate_memory_usage_create(consumers, &err);
-    CheckNoError(err);
-
-    // Put data (this should affect memtables)
-    rocksdb_put(db, woptions, "memory", 6, "test", 4, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "memory", "test");
-
-    // take memory usage report after write-read operation
-    rocksdb_memory_usage_t* mu2;
-    mu2 = rocksdb_approximate_memory_usage_create(consumers, &err);
-    CheckNoError(err);
-
-    // amount of memory used within memtables should grow
-    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_total(mu2) >=
-                   rocksdb_approximate_memory_usage_get_mem_table_total(mu1));
-    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu2) >=
-                   rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu1));
-
-    rocksdb_memory_consumers_destroy(consumers);
-    rocksdb_approximate_memory_usage_destroy(mu1);
-    rocksdb_approximate_memory_usage_destroy(mu2);
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-  }
-
   StartPhase("cuckoo_options");
   {
     rocksdb_cuckoo_table_options_t* cuckoo_options;
@@ -1470,245 +1225,14 @@ int main(int argc, char** argv) {
     }
   }
 
-  StartPhase("transactions");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    // open a TransactionDB
-    txn_db_options = rocksdb_transactiondb_options_create();
-    txn_options = rocksdb_transaction_options_create();
-    rocksdb_options_set_create_if_missing(options, 1);
-    txn_db = rocksdb_transactiondb_open(options, txn_db_options, dbname, &err);
-    CheckNoError(err);
-
-    // put outside a transaction
-    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-
-    // delete from outside transaction
-    rocksdb_transactiondb_delete(txn_db, woptions, "foo", 3, &err);
-    CheckNoError(err);
-    CheckTxnDBGet(txn_db, roptions, "foo", NULL);
-
-    // write batch into TransactionDB
-    rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
-    rocksdb_writebatch_put(wb, "foo", 3, "a", 1);
-    rocksdb_writebatch_clear(wb);
-    rocksdb_writebatch_put(wb, "bar", 3, "b", 1);
-    rocksdb_writebatch_put(wb, "box", 3, "c", 1);
-    rocksdb_writebatch_delete(wb, "bar", 3);
-    rocksdb_transactiondb_write(txn_db, woptions, wb, &err);
-    rocksdb_writebatch_destroy(wb);
-    CheckTxnDBGet(txn_db, roptions, "box", "c");
-    CheckNoError(err);
-
-    // begin a transaction
-    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
-    // put
-    rocksdb_transaction_put(txn, "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-    CheckTxnGet(txn, roptions, "foo", "hello");
-    // delete
-    rocksdb_transaction_delete(txn, "foo", 3, &err);
-    CheckNoError(err);
-    CheckTxnGet(txn, roptions, "foo", NULL);
-
-    rocksdb_transaction_put(txn, "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-
-    // read from outside transaction, before commit
-    CheckTxnDBGet(txn_db, roptions, "foo", NULL);
-
-    // commit
-    rocksdb_transaction_commit(txn, &err);
-    CheckNoError(err);
-
-    // read from outside transaction, after commit
-    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-
-    // reuse old transaction
-    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, txn);
-
-    // snapshot
-    const rocksdb_snapshot_t* snapshot;
-    snapshot = rocksdb_transactiondb_create_snapshot(txn_db);
-    rocksdb_readoptions_set_snapshot(roptions, snapshot);
-
-    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hey", 3,  &err);
-    CheckNoError(err);
-
-    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-    rocksdb_readoptions_set_snapshot(roptions, NULL);
-    rocksdb_transactiondb_release_snapshot(txn_db, snapshot);
-    CheckTxnDBGet(txn_db, roptions, "foo", "hey");
-
-    // iterate
-    rocksdb_transaction_put(txn, "bar", 3, "hi", 2, &err);
-    rocksdb_iterator_t* iter = rocksdb_transaction_create_iterator(txn, roptions);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-    CheckIter(iter, "bar", "hi");
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-
-    // rollback
-    rocksdb_transaction_rollback(txn, &err);
-    CheckNoError(err);
-    CheckTxnDBGet(txn_db, roptions, "bar", NULL);
-
-    // save point
-    rocksdb_transaction_put(txn, "foo1", 4, "hi1", 3, &err);
-    rocksdb_transaction_set_savepoint(txn);
-    CheckTxnGet(txn, roptions, "foo1", "hi1");
-    rocksdb_transaction_put(txn, "foo2", 4, "hi2", 3, &err);
-    CheckTxnGet(txn, roptions, "foo2", "hi2");
-
-    // rollback to savepoint
-    rocksdb_transaction_rollback_to_savepoint(txn, &err);
-    CheckNoError(err);
-    CheckTxnGet(txn, roptions, "foo2", NULL);
-    CheckTxnGet(txn, roptions, "foo1", "hi1");
-    CheckTxnDBGet(txn_db, roptions, "foo1", NULL);
-    CheckTxnDBGet(txn_db, roptions, "foo2", NULL);
-    rocksdb_transaction_commit(txn, &err);
-    CheckNoError(err);
-    CheckTxnDBGet(txn_db, roptions, "foo1", "hi1");
-    CheckTxnDBGet(txn_db, roptions, "foo2", NULL);
-
-    // Column families.
-    rocksdb_column_family_handle_t* cfh;
-    cfh = rocksdb_transactiondb_create_column_family(txn_db, options,
-                                                     "txn_db_cf", &err);
-    CheckNoError(err);
-
-    rocksdb_transactiondb_put_cf(txn_db, woptions, cfh, "cf_foo", 6, "cf_hello",
-                                 8, &err);
-    CheckNoError(err);
-    CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", "cf_hello");
-
-    rocksdb_transactiondb_delete_cf(txn_db, woptions, cfh, "cf_foo", 6, &err);
-    CheckNoError(err);
-    CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
-
-    rocksdb_column_family_handle_destroy(cfh);
-
-    // close and destroy
-    rocksdb_transaction_destroy(txn);
-    rocksdb_transactiondb_close(txn_db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_transaction_options_destroy(txn_options);
-    rocksdb_transactiondb_options_destroy(txn_db_options);
-  }
-
-  StartPhase("optimistic_transactions");
-  {
-    rocksdb_options_t* db_options = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(db_options, 1);
-    rocksdb_options_set_allow_concurrent_memtable_write(db_options, 1);
-    otxn_db = rocksdb_optimistictransactiondb_open(db_options, dbname, &err);
-    otxn_options = rocksdb_optimistictransaction_options_create();
-    rocksdb_transaction_t* txn1 = rocksdb_optimistictransaction_begin(
-        otxn_db, woptions, otxn_options, NULL);
-    rocksdb_transaction_t* txn2 = rocksdb_optimistictransaction_begin(
-        otxn_db, woptions, otxn_options, NULL);
-    rocksdb_transaction_put(txn1, "key", 3, "value", 5, &err);
-    CheckNoError(err);
-    rocksdb_transaction_put(txn2, "key1", 4, "value1", 6, &err);
-    CheckNoError(err);
-    CheckTxnGet(txn1, roptions, "key", "value");
-    rocksdb_transaction_commit(txn1, &err);
-    CheckNoError(err);
-    rocksdb_transaction_commit(txn2, &err);
-    CheckNoError(err);
-    rocksdb_transaction_destroy(txn1);
-    rocksdb_transaction_destroy(txn2);
-
-    // Check column family
-    db = rocksdb_optimistictransactiondb_get_base_db(otxn_db);
-    rocksdb_put(db, woptions, "key", 3, "value", 5, &err);
-    CheckNoError(err);
-    rocksdb_column_family_handle_t *cfh1, *cfh2;
-    cfh1 = rocksdb_create_column_family(db, db_options, "txn_db_cf1", &err);
-    cfh2 = rocksdb_create_column_family(db, db_options, "txn_db_cf2", &err);
-    txn = rocksdb_optimistictransaction_begin(otxn_db, woptions, otxn_options,
-                                              NULL);
-    rocksdb_transaction_put_cf(txn, cfh1, "key_cf1", 7, "val_cf1", 7, &err);
-    CheckNoError(err);
-    rocksdb_transaction_put_cf(txn, cfh2, "key_cf2", 7, "val_cf2", 7, &err);
-    CheckNoError(err);
-    rocksdb_transaction_commit(txn, &err);
-    CheckNoError(err);
-    txn = rocksdb_optimistictransaction_begin(otxn_db, woptions, otxn_options,
-                                              txn);
-    CheckGetCF(db, roptions, cfh1, "key_cf1", "val_cf1");
-    CheckTxnGetCF(txn, roptions, cfh1, "key_cf1", "val_cf1");
-
-    // Check iterator with column family
-    rocksdb_transaction_put_cf(txn, cfh1, "key1_cf", 7, "val1_cf", 7, &err);
-    CheckNoError(err);
-    rocksdb_iterator_t* iter =
-        rocksdb_transaction_create_iterator_cf(txn, roptions, cfh1);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-    CheckIter(iter, "key1_cf", "val1_cf");
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-
-    rocksdb_transaction_destroy(txn);
-    rocksdb_column_family_handle_destroy(cfh1);
-    rocksdb_column_family_handle_destroy(cfh2);
-    rocksdb_optimistictransactiondb_close_base_db(db);
-    rocksdb_optimistictransactiondb_close(otxn_db);
-
-    // Check open optimistic transaction db with column families
-    size_t cf_len;
-    char** column_fams =
-        rocksdb_list_column_families(db_options, dbname, &cf_len, &err);
-    CheckNoError(err);
-    CheckEqual("default", column_fams[0], 7);
-    CheckEqual("txn_db_cf1", column_fams[1], 10);
-    CheckEqual("txn_db_cf2", column_fams[2], 10);
-    CheckCondition(cf_len == 3);
-    rocksdb_list_column_families_destroy(column_fams, cf_len);
-
-    const char* cf_names[3] = {"default", "txn_db_cf1", "txn_db_cf2"};
-    rocksdb_options_t* cf_options = rocksdb_options_create();
-    const rocksdb_options_t* cf_opts[3] = {cf_options, cf_options, cf_options};
-
-    rocksdb_options_set_error_if_exists(cf_options, 0);
-    rocksdb_column_family_handle_t* cf_handles[3];
-    otxn_db = rocksdb_optimistictransactiondb_open_column_families(
-        db_options, dbname, 3, cf_names, cf_opts, cf_handles, &err);
-    CheckNoError(err);
-    rocksdb_transaction_t* txn_cf = rocksdb_optimistictransaction_begin(
-        otxn_db, woptions, otxn_options, NULL);
-    CheckTxnGetCF(txn_cf, roptions, cf_handles[0], "key", "value");
-    CheckTxnGetCF(txn_cf, roptions, cf_handles[1], "key_cf1", "val_cf1");
-    CheckTxnGetCF(txn_cf, roptions, cf_handles[2], "key_cf2", "val_cf2");
-    rocksdb_transaction_destroy(txn_cf);
-    rocksdb_options_destroy(cf_options);
-    rocksdb_column_family_handle_destroy(cf_handles[0]);
-    rocksdb_column_family_handle_destroy(cf_handles[1]);
-    rocksdb_column_family_handle_destroy(cf_handles[2]);
-    rocksdb_optimistictransactiondb_close(otxn_db);
-    rocksdb_destroy_db(db_options, dbname, &err);
-    rocksdb_options_destroy(db_options);
-    rocksdb_optimistictransaction_options_destroy(otxn_options);
-    CheckNoError(err);
-  }
-
   // Simple sanity check that setting memtable rep works.
   StartPhase("memtable_reps");
   {
     // Create database with vector memtable.
+    rocksdb_close(db);
+    rocksdb_destroy_db(options, dbname, &err);
+    CheckNoError(err);
+
     rocksdb_options_set_memtable_vector_rep(options);
     db = rocksdb_open(options, dbname, &err);
     CheckNoError(err);
@@ -1723,71 +1247,6 @@ int main(int argc, char** argv) {
     CheckNoError(err);
   }
 
-  // Check that secondary instance works.
-  StartPhase("open_as_secondary");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-
-    rocksdb_options_t* db_options = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(db_options, 1);
-    db = rocksdb_open(db_options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_t* db1;
-    rocksdb_options_t* opts = rocksdb_options_create();
-    rocksdb_options_set_max_open_files(opts, -1);
-    rocksdb_options_set_create_if_missing(opts, 1);
-    snprintf(secondary_path, sizeof(secondary_path),
-             "%s/rocksdb_c_test_secondary-%d", GetTempDir(), ((int)geteuid()));
-    db1 = rocksdb_open_as_secondary(opts, dbname, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_writeoptions_set_sync(woptions, 0);
-    rocksdb_writeoptions_disable_WAL(woptions, 1);
-    rocksdb_put(db, woptions, "key0", 4, "value0", 6, &err);
-    CheckNoError(err);
-    rocksdb_flushoptions_t* flush_opts = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_opts, 1);
-    rocksdb_flush(db, flush_opts, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    rocksdb_readoptions_t* ropts = rocksdb_readoptions_create();
-    rocksdb_readoptions_set_verify_checksums(ropts, 1);
-    rocksdb_readoptions_set_snapshot(ropts, NULL);
-    CheckGet(db, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key0", "value0");
-
-    rocksdb_writeoptions_disable_WAL(woptions, 0);
-    rocksdb_put(db, woptions, "key1", 4, "value1", 6, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    CheckGet(db1, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key1", "value1");
-
-    rocksdb_close(db1);
-    rocksdb_destroy_db(opts, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_options_destroy(db_options);
-    rocksdb_options_destroy(opts);
-    rocksdb_readoptions_destroy(ropts);
-    rocksdb_flushoptions_destroy(flush_opts);
-  }
-
-  // Simple sanity check that options setting db_paths work.
-  StartPhase("open_db_paths");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-
-    const rocksdb_dbpath_t* paths[1] = {dbpath};
-    rocksdb_options_set_db_paths(options, paths, 1);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-  }
-
   StartPhase("cleanup");
   rocksdb_close(db);
   rocksdb_options_destroy(options);
@@ -1797,7 +1256,6 @@ int main(int argc, char** argv) {
   rocksdb_compactoptions_destroy(coptions);
   rocksdb_cache_destroy(cache);
   rocksdb_comparator_destroy(cmp);
-  rocksdb_dbpath_destroy(dbpath);
   rocksdb_env_destroy(env);
 
   fprintf(stderr, "PASS\n");

db/column_family.cc

@@ -9,29 +9,28 @@
 
 #include "db/column_family.h"
 
-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <vector>
 #include <string>
 #include <algorithm>
 #include <limits>
 
-#include "db/compaction/compaction_picker.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
-#include "db/db_impl/db_impl.h"
+#include "db/compaction_picker.h"
+#include "db/compaction_picker_universal.h"
+#include "db/db_impl.h"
 #include "db/internal_stats.h"
 #include "db/job_context.h"
-#include "db/range_del_aggregator.h"
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
-#include "file/sst_file_manager_impl.h"
 #include "memtable/hash_skiplist_rep.h"
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
-#include "table/block_based/block_based_table_factory.h"
-#include "table/merging_iterator.h"
+#include "table/block_based_table_factory.h"
 #include "util/autovector.h"
 #include "util/compression.h"
 
@@ -54,30 +53,15 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
 #endif  // ROCKSDB_LITE
     // Job id == 0 means that this is not our background process, but rather
     // user thread
-    // Need to hold some shared pointers owned by the initial_cf_options
-    // before final cleaning up finishes.
-    ColumnFamilyOptions initial_cf_options_copy = cfd_->initial_cf_options();
     JobContext job_context(0);
     mutex_->Lock();
     if (cfd_->Unref()) {
-      bool dropped = cfd_->IsDropped();
-
       delete cfd_;
-
-      if (dropped) {
-        db_->FindObsoleteFiles(&job_context, false, true);
-      }
     }
+    db_->FindObsoleteFiles(&job_context, false, true);
     mutex_->Unlock();
     if (job_context.HaveSomethingToDelete()) {
-      bool defer_purge =
-          db_->immutable_db_options().avoid_unnecessary_blocking_io;
-      db_->PurgeObsoleteFiles(job_context, defer_purge);
-      if (defer_purge) {
-        mutex_->Lock();
-        db_->SchedulePurge();
-        mutex_->Unlock();
-      }
+      db_->PurgeObsoleteFiles(job_context);
     }
     job_context.Clean();
   }
@@ -96,7 +80,6 @@ Status ColumnFamilyHandleImpl::GetDescriptor(ColumnFamilyDescriptor* desc) {
   *desc = ColumnFamilyDescriptor(cfd()->GetName(), cfd()->GetLatestCFOptions());
   return Status::OK();
 #else
-  (void)desc;
   return Status::NotSupported();
 #endif  // !ROCKSDB_LITE
 }
@@ -116,6 +99,9 @@ void GetIntTblPropCollectorFactory(
     int_tbl_prop_collector_factories->emplace_back(
         new UserKeyTablePropertiesCollectorFactory(collector_factories[i]));
   }
+  // Add collector to collect internal key statistics
+  int_tbl_prop_collector_factories->emplace_back(
+      new InternalKeyPropertiesCollectorFactory);
 }
 
 Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
@@ -137,18 +123,6 @@ Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
           " is not linked with the binary.");
     }
   }
-  if (cf_options.compression_opts.zstd_max_train_bytes > 0) {
-    if (!ZSTD_TrainDictionarySupported()) {
-      return Status::InvalidArgument(
-          "zstd dictionary trainer cannot be used because ZSTD 1.1.3+ "
-          "is not linked with the binary.");
-    }
-    if (cf_options.compression_opts.max_dict_bytes == 0) {
-      return Status::InvalidArgument(
-          "The dictionary size limit (`CompressionOptions::max_dict_bytes`) "
-          "should be nonzero if we're using zstd's dictionary generator.");
-    }
-  }
   return Status::OK();
 }
 
@@ -165,28 +139,6 @@ Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options) {
   return Status::OK();
 }
 
-Status CheckCFPathsSupported(const DBOptions& db_options,
-                             const ColumnFamilyOptions& cf_options) {
-  // More than one cf_paths are supported only in universal
-  // and level compaction styles. This function also checks the case
-  // in which cf_paths is not specified, which results in db_paths
-  // being used.
-  if ((cf_options.compaction_style != kCompactionStyleUniversal) &&
-      (cf_options.compaction_style != kCompactionStyleLevel)) {
-    if (cf_options.cf_paths.size() > 1) {
-      return Status::NotSupported(
-          "More than one CF paths are only supported in "
-          "universal and level compaction styles. ");
-    } else if (cf_options.cf_paths.empty() &&
-               db_options.db_paths.size() > 1) {
-      return Status::NotSupported(
-          "More than one DB paths are only supported in "
-          "universal and level compaction styles. ");
-    }
-  }
-  return Status::OK();
-}
-
 ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                     const ColumnFamilyOptions& src) {
   ColumnFamilyOptions result = src;
@@ -218,12 +170,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
       result.num_levels < 2) {
     result.num_levels = 2;
   }
-
-  if (result.compaction_style == kCompactionStyleUniversal &&
-      db_options.allow_ingest_behind && result.num_levels < 3) {
-    result.num_levels = 3;
-  }
-
   if (result.max_write_buffer_number < 2) {
     result.max_write_buffer_number = 2;
   }
@@ -250,6 +196,7 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     result.num_levels = 1;
     // since we delete level0 files in FIFO compaction when there are too many
     // of them, these options don't really mean anything
+    result.level0_file_num_compaction_trigger = std::numeric_limits<int>::max();
     result.level0_slowdown_writes_trigger = std::numeric_limits<int>::max();
     result.level0_stop_writes_trigger = std::numeric_limits<int>::max();
   }
@@ -305,24 +252,9 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
         result.hard_pending_compaction_bytes_limit;
   }
 
-#ifndef ROCKSDB_LITE
-  // When the DB is stopped, it's possible that there are some .trash files that
-  // were not deleted yet, when we open the DB we will find these .trash files
-  // and schedule them to be deleted (or delete immediately if SstFileManager
-  // was not used)
-  auto sfm = static_cast<SstFileManagerImpl*>(db_options.sst_file_manager.get());
-  for (size_t i = 0; i < result.cf_paths.size(); i++) {
-    DeleteScheduler::CleanupDirectory(db_options.env, sfm, result.cf_paths[i].path);
-  }
-#endif
-
-  if (result.cf_paths.empty()) {
-    result.cf_paths = db_options.db_paths;
-  }
-
   if (result.level_compaction_dynamic_level_bytes) {
     if (result.compaction_style != kCompactionStyleLevel ||
-        result.cf_paths.size() > 1U) {
+        db_options.db_paths.size() > 1U) {
       // 1. level_compaction_dynamic_level_bytes only makes sense for
       //    level-based compaction.
       // 2. we don't yet know how to make both of this feature and multiple
@@ -391,13 +323,12 @@ void SuperVersionUnrefHandle(void* ptr) {
   // When latter happens, we are in ~ColumnFamilyData(), no get should happen as
   // well.
   SuperVersion* sv = static_cast<SuperVersion*>(ptr);
-  bool was_last_ref __attribute__((__unused__));
-  was_last_ref = sv->Unref();
-  // Thread-local SuperVersions can't outlive ColumnFamilyData::super_version_.
-  // This is important because we can't do SuperVersion cleanup here.
-  // That would require locking DB mutex, which would deadlock because
-  // SuperVersionUnrefHandle is called with locked ThreadLocalPtr mutex.
-  assert(!was_last_ref);
+  if (sv->Unref()) {
+    sv->db_mutex->Lock();
+    sv->Cleanup();
+    sv->db_mutex->Unlock();
+    delete sv;
+  }
 }
 }  // anonymous namespace
 
@@ -405,21 +336,19 @@ ColumnFamilyData::ColumnFamilyData(
     uint32_t id, const std::string& name, Version* _dummy_versions,
     Cache* _table_cache, WriteBufferManager* write_buffer_manager,
     const ColumnFamilyOptions& cf_options, const ImmutableDBOptions& db_options,
-    const EnvOptions& env_options, ColumnFamilySet* column_family_set,
-    BlockCacheTracer* const block_cache_tracer)
+    const EnvOptions& env_options, ColumnFamilySet* column_family_set)
     : id_(id),
       name_(name),
       dummy_versions_(_dummy_versions),
       current_(nullptr),
       refs_(0),
-      initialized_(false),
       dropped_(false),
       internal_comparator_(cf_options.comparator),
       initial_cf_options_(SanitizeOptions(db_options, cf_options)),
       ioptions_(db_options, initial_cf_options_),
       mutable_cf_options_(initial_cf_options_),
-      is_delete_range_supported_(
-          cf_options.table_factory->IsDeleteRangeSupported()),
+      is_delete_range_supported_(strcmp(cf_options.table_factory->Name(),
+                                        BlockBasedTableFactory().Name()) == 0),
       write_buffer_manager_(write_buffer_manager),
       mem_(nullptr),
       imm_(ioptions_.min_write_buffer_number_to_merge,
@@ -430,13 +359,11 @@ ColumnFamilyData::ColumnFamilyData(
       next_(nullptr),
       prev_(nullptr),
       log_number_(0),
-      flush_reason_(FlushReason::kOthers),
       column_family_set_(column_family_set),
-      queued_for_flush_(false),
-      queued_for_compaction_(false),
+      pending_flush_(false),
+      pending_compaction_(false),
       prev_compaction_needed_bytes_(0),
-      allow_2pc_(db_options.allow_2pc),
-      last_memtable_id_(0) {
+      allow_2pc_(db_options.allow_2pc) {
   Ref();
 
   // Convert user defined table properties collector factories to internal ones.
@@ -446,8 +373,7 @@ ColumnFamilyData::ColumnFamilyData(
   if (_dummy_versions != nullptr) {
     internal_stats_.reset(
         new InternalStats(ioptions_.num_levels, db_options.env, this));
-    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache,
-                                      block_cache_tracer));
+    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache));
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
           new LevelCompactionPicker(ioptions_, &internal_comparator_));
@@ -510,8 +436,8 @@ ColumnFamilyData::~ColumnFamilyData() {
 
   // It would be wrong if this ColumnFamilyData is in flush_queue_ or
   // compaction_queue_ and we destroyed it
-  assert(!queued_for_flush_);
-  assert(!queued_for_compaction_);
+  assert(!pending_flush_);
+  assert(!pending_compaction_);
 
   if (super_version_ != nullptr) {
     // Release SuperVersion reference kept in ThreadLocalPtr.
@@ -520,7 +446,7 @@ ColumnFamilyData::~ColumnFamilyData() {
     local_sv_.reset();
     super_version_->db_mutex->Lock();
 
-    bool is_last_reference __attribute__((__unused__));
+    bool is_last_reference __attribute__((unused));
     is_last_reference = super_version_->Unref();
     assert(is_last_reference);
     super_version_->Cleanup();
@@ -531,8 +457,7 @@ ColumnFamilyData::~ColumnFamilyData() {
   if (dummy_versions_ != nullptr) {
     // List must be empty
     assert(dummy_versions_->TEST_Next() == dummy_versions_);
-    bool deleted __attribute__((__unused__));
-    deleted = dummy_versions_->Unref();
+    bool deleted __attribute__((unused)) = dummy_versions_->Unref();
     assert(deleted);
   }
 
@@ -564,9 +489,7 @@ uint64_t ColumnFamilyData::OldestLogToKeep() {
   auto current_log = GetLogNumber();
 
   if (allow_2pc_) {
-    autovector<MemTable*> empty_list;
-    auto imm_prep_log =
-        imm()->PrecomputeMinLogContainingPrepSection(empty_list);
+    auto imm_prep_log = imm()->GetMinLogContainingPrepSection();
     auto mem_prep_log = mem()->GetMinLogContainingPrepSection();
 
     if (imm_prep_log > 0 && imm_prep_log < current_log) {
@@ -621,7 +544,7 @@ std::unique_ptr<WriteControllerToken> SetupDelay(
     // If DB just falled into the stop condition, we need to further reduce
     // the write rate to avoid the stop condition.
     if (penalize_stop) {
-      // Penalize the near stop or stop condition by more aggressive slowdown.
+      // Penalize the near stop or stop condition by more agressive slowdown.
       // This is to provide the long term slowdown increase signal.
       // The penalty is more than the reward of recovering to the normal
       // condition.
@@ -684,97 +607,58 @@ int GetL0ThresholdSpeedupCompaction(int level0_file_num_compaction_trigger,
 }
 }  // namespace
 
-std::pair<WriteStallCondition, ColumnFamilyData::WriteStallCause>
-ColumnFamilyData::GetWriteStallConditionAndCause(
-    int num_unflushed_memtables, int num_l0_files,
-    uint64_t num_compaction_needed_bytes,
-    const MutableCFOptions& mutable_cf_options) {
-  if (num_unflushed_memtables >= mutable_cf_options.max_write_buffer_number) {
-    return {WriteStallCondition::kStopped, WriteStallCause::kMemtableLimit};
-  } else if (!mutable_cf_options.disable_auto_compactions &&
-             num_l0_files >= mutable_cf_options.level0_stop_writes_trigger) {
-    return {WriteStallCondition::kStopped, WriteStallCause::kL0FileCountLimit};
-  } else if (!mutable_cf_options.disable_auto_compactions &&
-             mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
-             num_compaction_needed_bytes >=
-                 mutable_cf_options.hard_pending_compaction_bytes_limit) {
-    return {WriteStallCondition::kStopped,
-            WriteStallCause::kPendingCompactionBytes};
-  } else if (mutable_cf_options.max_write_buffer_number > 3 &&
-             num_unflushed_memtables >=
-                 mutable_cf_options.max_write_buffer_number - 1) {
-    return {WriteStallCondition::kDelayed, WriteStallCause::kMemtableLimit};
-  } else if (!mutable_cf_options.disable_auto_compactions &&
-             mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
-             num_l0_files >=
-                 mutable_cf_options.level0_slowdown_writes_trigger) {
-    return {WriteStallCondition::kDelayed, WriteStallCause::kL0FileCountLimit};
-  } else if (!mutable_cf_options.disable_auto_compactions &&
-             mutable_cf_options.soft_pending_compaction_bytes_limit > 0 &&
-             num_compaction_needed_bytes >=
-                 mutable_cf_options.soft_pending_compaction_bytes_limit) {
-    return {WriteStallCondition::kDelayed,
-            WriteStallCause::kPendingCompactionBytes};
-  }
-  return {WriteStallCondition::kNormal, WriteStallCause::kNone};
-}
-
-WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
+void ColumnFamilyData::RecalculateWriteStallConditions(
       const MutableCFOptions& mutable_cf_options) {
-  auto write_stall_condition = WriteStallCondition::kNormal;
   if (current_ != nullptr) {
     auto* vstorage = current_->storage_info();
     auto write_controller = column_family_set_->write_controller_;
     uint64_t compaction_needed_bytes =
         vstorage->estimated_compaction_needed_bytes();
 
-    auto write_stall_condition_and_cause = GetWriteStallConditionAndCause(
-        imm()->NumNotFlushed(), vstorage->l0_delay_trigger_count(),
-        vstorage->estimated_compaction_needed_bytes(), mutable_cf_options);
-    write_stall_condition = write_stall_condition_and_cause.first;
-    auto write_stall_cause = write_stall_condition_and_cause.second;
-
     bool was_stopped = write_controller->IsStopped();
     bool needed_delay = write_controller->NeedsDelay();
 
-    if (write_stall_condition == WriteStallCondition::kStopped &&
-        write_stall_cause == WriteStallCause::kMemtableLimit) {
+    if (imm()->NumNotFlushed() >= mutable_cf_options.max_write_buffer_number) {
       write_controller_token_ = write_controller->GetStopToken();
-      internal_stats_->AddCFStats(InternalStats::MEMTABLE_LIMIT_STOPS, 1);
+      internal_stats_->AddCFStats(InternalStats::MEMTABLE_COMPACTION, 1);
       ROCKS_LOG_WARN(
           ioptions_.info_log,
           "[%s] Stopping writes because we have %d immutable memtables "
           "(waiting for flush), max_write_buffer_number is set to %d",
           name_.c_str(), imm()->NumNotFlushed(),
           mutable_cf_options.max_write_buffer_number);
-    } else if (write_stall_condition == WriteStallCondition::kStopped &&
-               write_stall_cause == WriteStallCause::kL0FileCountLimit) {
+    } else if (!mutable_cf_options.disable_auto_compactions &&
+               vstorage->l0_delay_trigger_count() >=
+                   mutable_cf_options.level0_stop_writes_trigger) {
       write_controller_token_ = write_controller->GetStopToken();
-      internal_stats_->AddCFStats(InternalStats::L0_FILE_COUNT_LIMIT_STOPS, 1);
+      internal_stats_->AddCFStats(InternalStats::LEVEL0_NUM_FILES_TOTAL, 1);
       if (compaction_picker_->IsLevel0CompactionInProgress()) {
         internal_stats_->AddCFStats(
-            InternalStats::LOCKED_L0_FILE_COUNT_LIMIT_STOPS, 1);
+            InternalStats::LEVEL0_NUM_FILES_WITH_COMPACTION, 1);
       }
       ROCKS_LOG_WARN(ioptions_.info_log,
                      "[%s] Stopping writes because we have %d level-0 files",
                      name_.c_str(), vstorage->l0_delay_trigger_count());
-    } else if (write_stall_condition == WriteStallCondition::kStopped &&
-               write_stall_cause == WriteStallCause::kPendingCompactionBytes) {
+    } else if (!mutable_cf_options.disable_auto_compactions &&
+               mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
+               compaction_needed_bytes >=
+                   mutable_cf_options.hard_pending_compaction_bytes_limit) {
       write_controller_token_ = write_controller->GetStopToken();
       internal_stats_->AddCFStats(
-          InternalStats::PENDING_COMPACTION_BYTES_LIMIT_STOPS, 1);
+          InternalStats::HARD_PENDING_COMPACTION_BYTES_LIMIT, 1);
       ROCKS_LOG_WARN(
           ioptions_.info_log,
           "[%s] Stopping writes because of estimated pending compaction "
           "bytes %" PRIu64,
           name_.c_str(), compaction_needed_bytes);
-    } else if (write_stall_condition == WriteStallCondition::kDelayed &&
-               write_stall_cause == WriteStallCause::kMemtableLimit) {
+    } else if (mutable_cf_options.max_write_buffer_number > 3 &&
+               imm()->NumNotFlushed() >=
+                   mutable_cf_options.max_write_buffer_number - 1) {
       write_controller_token_ =
           SetupDelay(write_controller, compaction_needed_bytes,
                      prev_compaction_needed_bytes_, was_stopped,
                      mutable_cf_options.disable_auto_compactions);
-      internal_stats_->AddCFStats(InternalStats::MEMTABLE_LIMIT_SLOWDOWNS, 1);
+      internal_stats_->AddCFStats(InternalStats::MEMTABLE_SLOWDOWN, 1);
       ROCKS_LOG_WARN(
           ioptions_.info_log,
           "[%s] Stalling writes because we have %d immutable memtables "
@@ -783,8 +667,10 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
           name_.c_str(), imm()->NumNotFlushed(),
           mutable_cf_options.max_write_buffer_number,
           write_controller->delayed_write_rate());
-    } else if (write_stall_condition == WriteStallCondition::kDelayed &&
-               write_stall_cause == WriteStallCause::kL0FileCountLimit) {
+    } else if (!mutable_cf_options.disable_auto_compactions &&
+               mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
+               vstorage->l0_delay_trigger_count() >=
+                   mutable_cf_options.level0_slowdown_writes_trigger) {
       // L0 is the last two files from stopping.
       bool near_stop = vstorage->l0_delay_trigger_count() >=
                        mutable_cf_options.level0_stop_writes_trigger - 2;
@@ -792,19 +678,20 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
           SetupDelay(write_controller, compaction_needed_bytes,
                      prev_compaction_needed_bytes_, was_stopped || near_stop,
                      mutable_cf_options.disable_auto_compactions);
-      internal_stats_->AddCFStats(InternalStats::L0_FILE_COUNT_LIMIT_SLOWDOWNS,
-                                  1);
+      internal_stats_->AddCFStats(InternalStats::LEVEL0_SLOWDOWN_TOTAL, 1);
       if (compaction_picker_->IsLevel0CompactionInProgress()) {
         internal_stats_->AddCFStats(
-            InternalStats::LOCKED_L0_FILE_COUNT_LIMIT_SLOWDOWNS, 1);
+            InternalStats::LEVEL0_SLOWDOWN_WITH_COMPACTION, 1);
       }
       ROCKS_LOG_WARN(ioptions_.info_log,
                      "[%s] Stalling writes because we have %d level-0 files "
                      "rate %" PRIu64,
                      name_.c_str(), vstorage->l0_delay_trigger_count(),
                      write_controller->delayed_write_rate());
-    } else if (write_stall_condition == WriteStallCondition::kDelayed &&
-               write_stall_cause == WriteStallCause::kPendingCompactionBytes) {
+    } else if (!mutable_cf_options.disable_auto_compactions &&
+               mutable_cf_options.soft_pending_compaction_bytes_limit > 0 &&
+               vstorage->estimated_compaction_needed_bytes() >=
+                   mutable_cf_options.soft_pending_compaction_bytes_limit) {
       // If the distance to hard limit is less than 1/4 of the gap between soft
       // and
       // hard bytes limit, we think it is near stop and speed up the slowdown.
@@ -821,7 +708,7 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
                      prev_compaction_needed_bytes_, was_stopped || near_stop,
                      mutable_cf_options.disable_auto_compactions);
       internal_stats_->AddCFStats(
-          InternalStats::PENDING_COMPACTION_BYTES_LIMIT_SLOWDOWNS, 1);
+          InternalStats::SOFT_PENDING_COMPACTION_BYTES_LIMIT, 1);
       ROCKS_LOG_WARN(
           ioptions_.info_log,
           "[%s] Stalling writes because of estimated pending compaction "
@@ -829,14 +716,13 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
           name_.c_str(), vstorage->estimated_compaction_needed_bytes(),
           write_controller->delayed_write_rate());
     } else {
-      assert(write_stall_condition == WriteStallCondition::kNormal);
       if (vstorage->l0_delay_trigger_count() >=
           GetL0ThresholdSpeedupCompaction(
               mutable_cf_options.level0_file_num_compaction_trigger,
               mutable_cf_options.level0_slowdown_writes_trigger)) {
         write_controller_token_ =
             write_controller->GetCompactionPressureToken();
-        ROCKS_LOG_INFO(
+        ROCKS_LOG_WARN(
             ioptions_.info_log,
             "[%s] Increasing compaction threads because we have %d level-0 "
             "files ",
@@ -850,7 +736,7 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
         write_controller_token_ =
             write_controller->GetCompactionPressureToken();
         if (mutable_cf_options.soft_pending_compaction_bytes_limit > 0) {
-          ROCKS_LOG_INFO(
+          ROCKS_LOG_WARN(
               ioptions_.info_log,
               "[%s] Increasing compaction threads because of estimated pending "
               "compaction "
@@ -867,17 +753,10 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
         uint64_t write_rate = write_controller->delayed_write_rate();
         write_controller->set_delayed_write_rate(static_cast<uint64_t>(
             static_cast<double>(write_rate) * kDelayRecoverSlowdownRatio));
-        // Set the low pri limit to be 1/4 the delayed write rate.
-        // Note we don't reset this value even after delay condition is relased.
-        // Low-pri rate will continue to apply if there is a compaction
-        // pressure.
-        write_controller->low_pri_rate_limiter()->SetBytesPerSecond(write_rate /
-                                                                    4);
       }
     }
     prev_compaction_needed_bytes_ = compaction_needed_bytes;
   }
-  return write_stall_condition;
 }
 
 const EnvOptions* ColumnFamilyData::soptions() const {
@@ -896,14 +775,11 @@ uint64_t ColumnFamilyData::GetTotalSstFilesSize() const {
   return VersionSet::GetTotalSstFilesSize(dummy_versions_);
 }
 
-uint64_t ColumnFamilyData::GetLiveSstFilesSize() const {
-  return current_->GetSstFilesSize();
-}
-
 MemTable* ColumnFamilyData::ConstructNewMemtable(
     const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
+  assert(current_ != nullptr);
   return new MemTable(internal_comparator_, ioptions_, mutable_cf_options,
-                      write_buffer_manager_, earliest_seq, id_);
+                      write_buffer_manager_, earliest_seq);
 }
 
 void ColumnFamilyData::CreateNewMemtable(
@@ -936,71 +812,16 @@ bool ColumnFamilyData::RangeOverlapWithCompaction(
       smallest_user_key, largest_user_key, level);
 }
 
-Status ColumnFamilyData::RangesOverlapWithMemtables(
-    const autovector<Range>& ranges, SuperVersion* super_version,
-    bool* overlap) {
-  assert(overlap != nullptr);
-  *overlap = false;
-  // Create an InternalIterator over all unflushed memtables
-  Arena arena;
-  ReadOptions read_opts;
-  read_opts.total_order_seek = true;
-  MergeIteratorBuilder merge_iter_builder(&internal_comparator_, &arena);
-  merge_iter_builder.AddIterator(
-      super_version->mem->NewIterator(read_opts, &arena));
-  super_version->imm->AddIterators(read_opts, &merge_iter_builder);
-  ScopedArenaIterator memtable_iter(merge_iter_builder.Finish());
-
-  auto read_seq = super_version->current->version_set()->LastSequence();
-  ReadRangeDelAggregator range_del_agg(&internal_comparator_, read_seq);
-  auto* active_range_del_iter =
-      super_version->mem->NewRangeTombstoneIterator(read_opts, read_seq);
-  range_del_agg.AddTombstones(
-      std::unique_ptr<FragmentedRangeTombstoneIterator>(active_range_del_iter));
-  super_version->imm->AddRangeTombstoneIterators(read_opts, nullptr /* arena */,
-                                                 &range_del_agg);
-
-  Status status;
-  for (size_t i = 0; i < ranges.size() && status.ok() && !*overlap; ++i) {
-    auto* vstorage = super_version->current->storage_info();
-    auto* ucmp = vstorage->InternalComparator()->user_comparator();
-    InternalKey range_start(ranges[i].start, kMaxSequenceNumber,
-                            kValueTypeForSeek);
-    memtable_iter->Seek(range_start.Encode());
-    status = memtable_iter->status();
-    ParsedInternalKey seek_result;
-    if (status.ok()) {
-      if (memtable_iter->Valid() &&
-          !ParseInternalKey(memtable_iter->key(), &seek_result)) {
-        status = Status::Corruption("DB have corrupted keys");
-      }
-    }
-    if (status.ok()) {
-      if (memtable_iter->Valid() &&
-          ucmp->Compare(seek_result.user_key, ranges[i].limit) <= 0) {
-        *overlap = true;
-      } else if (range_del_agg.IsRangeOverlapped(ranges[i].start,
-                                                 ranges[i].limit)) {
-        *overlap = true;
-      }
-    }
-  }
-  return status;
-}
-
 const int ColumnFamilyData::kCompactAllLevels = -1;
 const int ColumnFamilyData::kCompactToBaseLevel = -2;
 
 Compaction* ColumnFamilyData::CompactRange(
     const MutableCFOptions& mutable_cf_options, int input_level,
-    int output_level, const CompactRangeOptions& compact_range_options,
-    const InternalKey* begin, const InternalKey* end,
-    InternalKey** compaction_end, bool* conflict,
-    uint64_t max_file_num_to_ignore) {
+    int output_level, uint32_t output_path_id, const InternalKey* begin,
+    const InternalKey* end, InternalKey** compaction_end, bool* conflict) {
   auto* result = compaction_picker_->CompactRange(
       GetName(), mutable_cf_options, current_->storage_info(), input_level,
-      output_level, compact_range_options, begin, end, compaction_end, conflict,
-      max_file_num_to_ignore);
+      output_level, output_path_id, begin, end, compaction_end, conflict);
   if (result != nullptr) {
     result->SetInputVersion(current_);
   }
@@ -1009,13 +830,10 @@ Compaction* ColumnFamilyData::CompactRange(
 
 SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
     InstrumentedMutex* db_mutex) {
-  SuperVersion* sv = GetThreadLocalSuperVersion(db_mutex);
+  SuperVersion* sv = nullptr;
+  sv = GetThreadLocalSuperVersion(db_mutex);
   sv->Ref();
   if (!ReturnThreadLocalSuperVersion(sv)) {
-    // This Unref() corresponds to the Ref() in GetThreadLocalSuperVersion()
-    // when the thread-local pointer was populated. So, the Ref() earlier in
-    // this function still prevents the returned SuperVersion* from being
-    // deleted out from under the caller.
     sv->Unref();
   }
   return sv;
@@ -1023,6 +841,7 @@ SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
 
 SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
     InstrumentedMutex* db_mutex) {
+  SuperVersion* sv = nullptr;
   // The SuperVersion is cached in thread local storage to avoid acquiring
   // mutex when SuperVersion does not change since the last use. When a new
   // SuperVersion is installed, the compaction or flush thread cleans up
@@ -1041,7 +860,7 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
   // should only keep kSVInUse before ReturnThreadLocalSuperVersion call
   // (if no Scrape happens).
   assert(ptr != SuperVersion::kSVInUse);
-  SuperVersion* sv = static_cast<SuperVersion*>(ptr);
+  sv = static_cast<SuperVersion*>(ptr);
   if (sv == SuperVersion::kSVObsolete ||
       sv->version_number != super_version_number_.load()) {
     RecordTick(ioptions_.statistics, NUMBER_SUPERVERSION_ACQUIRES);
@@ -1084,16 +903,15 @@ bool ColumnFamilyData::ReturnThreadLocalSuperVersion(SuperVersion* sv) {
   return false;
 }
 
-void ColumnFamilyData::InstallSuperVersion(
-    SuperVersionContext* sv_context, InstrumentedMutex* db_mutex) {
+SuperVersion* ColumnFamilyData::InstallSuperVersion(
+    SuperVersion* new_superversion, InstrumentedMutex* db_mutex) {
   db_mutex->AssertHeld();
-  return InstallSuperVersion(sv_context, db_mutex, mutable_cf_options_);
+  return InstallSuperVersion(new_superversion, db_mutex, mutable_cf_options_);
 }
 
-void ColumnFamilyData::InstallSuperVersion(
-    SuperVersionContext* sv_context, InstrumentedMutex* db_mutex,
+SuperVersion* ColumnFamilyData::InstallSuperVersion(
+    SuperVersion* new_superversion, InstrumentedMutex* db_mutex,
     const MutableCFOptions& mutable_cf_options) {
-  SuperVersion* new_superversion = sv_context->new_superversion.release();
   new_superversion->db_mutex = db_mutex;
   new_superversion->mutable_cf_options = mutable_cf_options;
   new_superversion->Init(mem_, imm_.current(), current_);
@@ -1101,31 +919,16 @@ void ColumnFamilyData::InstallSuperVersion(
   super_version_ = new_superversion;
   ++super_version_number_;
   super_version_->version_number = super_version_number_;
-  super_version_->write_stall_condition =
-      RecalculateWriteStallConditions(mutable_cf_options);
+  // Reset SuperVersions cached in thread local storage
+  ResetThreadLocalSuperVersions();
 
-  if (old_superversion != nullptr) {
-    // Reset SuperVersions cached in thread local storage.
-    // This should be done before old_superversion->Unref(). That's to ensure
-    // that local_sv_ never holds the last reference to SuperVersion, since
-    // it has no means to safely do SuperVersion cleanup.
-    ResetThreadLocalSuperVersions();
+  RecalculateWriteStallConditions(mutable_cf_options);
 
-    if (old_superversion->mutable_cf_options.write_buffer_size !=
-        mutable_cf_options.write_buffer_size) {
-      mem_->UpdateWriteBufferSize(mutable_cf_options.write_buffer_size);
-    }
-    if (old_superversion->write_stall_condition !=
-        new_superversion->write_stall_condition) {
-      sv_context->PushWriteStallNotification(
-          old_superversion->write_stall_condition,
-          new_superversion->write_stall_condition, GetName(), ioptions());
-    }
-    if (old_superversion->Unref()) {
-      old_superversion->Cleanup();
-      sv_context->superversions_to_free.push_back(old_superversion);
-    }
+  if (old_superversion != nullptr && old_superversion->Unref()) {
+    old_superversion->Cleanup();
+    return old_superversion;  // will let caller delete outside of mutex
   }
+  return nullptr;
 }
 
 void ColumnFamilyData::ResetThreadLocalSuperVersions() {
@@ -1137,69 +940,19 @@ void ColumnFamilyData::ResetThreadLocalSuperVersions() {
       continue;
     }
     auto sv = static_cast<SuperVersion*>(ptr);
-    bool was_last_ref __attribute__((__unused__));
-    was_last_ref = sv->Unref();
-    // sv couldn't have been the last reference because
-    // ResetThreadLocalSuperVersions() is called before
-    // unref'ing super_version_.
-    assert(!was_last_ref);
-  }
-}
-
-Status ColumnFamilyData::ValidateOptions(
-    const DBOptions& db_options, const ColumnFamilyOptions& cf_options) {
-  Status s;
-  s = CheckCompressionSupported(cf_options);
-  if (s.ok() && db_options.allow_concurrent_memtable_write) {
-    s = CheckConcurrentWritesSupported(cf_options);
-  }
-  if (s.ok()) {
-    s = CheckCFPathsSupported(db_options, cf_options);
-  }
-  if (!s.ok()) {
-    return s;
-  }
-
-  if (cf_options.ttl > 0) {
-    if (db_options.max_open_files != -1) {
-      return Status::NotSupported(
-          "TTL is only supported when files are always "
-          "kept open (set max_open_files = -1). ");
-    }
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "TTL is only supported in Block-Based Table format. ");
+    if (sv->Unref()) {
+      sv->Cleanup();
+      delete sv;
     }
   }
-
-  if (cf_options.periodic_compaction_seconds > 0) {
-    if (db_options.max_open_files != -1) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported when files are always "
-          "kept open (set max_open_files = -1). ");
-    }
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported in "
-          "Block-Based Table format. ");
-    }
-  }
-  return s;
 }
 
 #ifndef ROCKSDB_LITE
 Status ColumnFamilyData::SetOptions(
-    const DBOptions& db_options,
-    const std::unordered_map<std::string, std::string>& options_map) {
+      const std::unordered_map<std::string, std::string>& options_map) {
   MutableCFOptions new_mutable_cf_options;
-  Status s =
-      GetMutableOptionsFromStrings(mutable_cf_options_, options_map,
-                                   ioptions_.info_log, &new_mutable_cf_options);
-  if (s.ok()) {
-    ColumnFamilyOptions cf_options =
-        BuildColumnFamilyOptions(initial_cf_options_, new_mutable_cf_options);
-    s = ValidateOptions(db_options, cf_options);
-  }
+  Status s = GetMutableOptionsFromStrings(mutable_cf_options_, options_map,
+                                          &new_mutable_cf_options);
   if (s.ok()) {
     mutable_cf_options_ = new_mutable_cf_options;
     mutable_cf_options_.RefreshDerivedOptions(ioptions_);
@@ -1208,68 +961,23 @@ Status ColumnFamilyData::SetOptions(
 }
 #endif  // ROCKSDB_LITE
 
-// REQUIRES: DB mutex held
-Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
-  if (initial_cf_options_.compaction_style != kCompactionStyleLevel) {
-    return Env::WLTH_NOT_SET;
-  }
-  if (level == 0) {
-    return Env::WLTH_MEDIUM;
-  }
-  int base_level = current_->storage_info()->base_level();
-
-  // L1: medium, L2: long, ...
-  if (level - base_level >= 2) {
-    return Env::WLTH_EXTREME;
-  }
-  return static_cast<Env::WriteLifeTimeHint>(level - base_level +
-                            static_cast<int>(Env::WLTH_MEDIUM));
-}
-
-Status ColumnFamilyData::AddDirectories() {
-  Status s;
-  assert(data_dirs_.empty());
-  for (auto& p : ioptions_.cf_paths) {
-    std::unique_ptr<Directory> path_directory;
-    s = DBImpl::CreateAndNewDirectory(ioptions_.env, p.path, &path_directory);
-    if (!s.ok()) {
-      return s;
-    }
-    assert(path_directory != nullptr);
-    data_dirs_.emplace_back(path_directory.release());
-  }
-  assert(data_dirs_.size() == ioptions_.cf_paths.size());
-  return s;
-}
-
-Directory* ColumnFamilyData::GetDataDir(size_t path_id) const {
-  if (data_dirs_.empty()) {
-    return nullptr;
-  }
-
-  assert(path_id < data_dirs_.size());
-  return data_dirs_[path_id].get();
-}
-
 ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                  const ImmutableDBOptions* db_options,
                                  const EnvOptions& env_options,
                                  Cache* table_cache,
                                  WriteBufferManager* write_buffer_manager,
-                                 WriteController* write_controller,
-                                 BlockCacheTracer* const block_cache_tracer)
+                                 WriteController* write_controller)
     : max_column_family_(0),
-      dummy_cfd_(new ColumnFamilyData(
-          0, "", nullptr, nullptr, nullptr, ColumnFamilyOptions(), *db_options,
-          env_options, nullptr, block_cache_tracer)),
+      dummy_cfd_(new ColumnFamilyData(0, "", nullptr, nullptr, nullptr,
+                                      ColumnFamilyOptions(), *db_options,
+                                      env_options, nullptr)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
       env_options_(env_options),
       table_cache_(table_cache),
       write_buffer_manager_(write_buffer_manager),
-      write_controller_(write_controller),
-      block_cache_tracer_(block_cache_tracer) {
+      write_controller_(write_controller) {
   // initialize linked list
   dummy_cfd_->prev_ = dummy_cfd_;
   dummy_cfd_->next_ = dummy_cfd_;
@@ -1279,14 +987,10 @@ ColumnFamilySet::~ColumnFamilySet() {
   while (column_family_data_.size() > 0) {
     // cfd destructor will delete itself from column_family_data_
     auto cfd = column_family_data_.begin()->second;
-    bool last_ref __attribute__((__unused__));
-    last_ref = cfd->Unref();
-    assert(last_ref);
+    cfd->Unref();
     delete cfd;
   }
-  bool dummy_last_ref __attribute__((__unused__));
-  dummy_last_ref = dummy_cfd_->Unref();
-  assert(dummy_last_ref);
+  dummy_cfd_->Unref();
   delete dummy_cfd_;
 }
 
@@ -1337,7 +1041,7 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
   assert(column_families_.find(name) == column_families_.end());
   ColumnFamilyData* new_cfd = new ColumnFamilyData(
       id, name, dummy_versions, table_cache_, write_buffer_manager_, options,
-      *db_options_, env_options_, this, block_cache_tracer_);
+      *db_options_, env_options_, this);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   max_column_family_ = std::max(max_column_family_, id);

db/column_family.h

@@ -24,14 +24,12 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
-#include "trace_replay/block_cache_tracer.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
 
 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_; }
@@ -204,7 +95,6 @@ struct SuperVersion {
   MutableCFOptions mutable_cf_options;
   // Version number of the current SuperVersion
   uint64_t version_number;
-  WriteStallCondition write_stall_condition;
 
   InstrumentedMutex* db_mutex;
 
@@ -246,9 +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`
@@ -305,7 +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; }
@@ -313,10 +200,6 @@ class ColumnFamilyData {
   void SetLogNumber(uint64_t log_number) { log_number_ = log_number; }
   uint64_t GetLogNumber() const { return log_number_; }
 
-  void SetFlushReason(FlushReason flush_reason) {
-    flush_reason_ = flush_reason;
-  }
-  FlushReason GetFlushReason() const { return flush_reason_; }
   // thread-safe
   const EnvOptions* soptions() const;
   const ImmutableCFOptions* ioptions() const { return &ioptions_; }
@@ -339,13 +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
 
@@ -358,12 +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();
@@ -389,28 +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
@@ -448,55 +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,
@@ -505,8 +341,7 @@ class ColumnFamilyData {
                    const ColumnFamilyOptions& options,
                    const ImmutableDBOptions& db_options,
                    const EnvOptions& env_options,
-                   ColumnFamilySet* column_family_set,
-                   BlockCacheTracer* const block_cache_tracer);
+                   ColumnFamilySet* column_family_set);
 
   uint32_t id_;
   const std::string name_;
@@ -514,8 +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>>
@@ -557,8 +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_;
@@ -568,22 +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
@@ -634,8 +460,7 @@ class ColumnFamilySet {
                   const ImmutableDBOptions* db_options,
                   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;
@@ -694,7 +519,6 @@ class ColumnFamilySet {
   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"
 
@@ -17,20 +17,29 @@ 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*,
@@ -39,8 +48,8 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                          GetContext::kNotFound, key, value, 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();
   }
@@ -72,7 +81,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
                              GetContext::kNotFound, keys[idx], &pinnable_val,
                              nullptr, nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
-      r->Get(options, lkey.internal_key(), &get_context, nullptr);
+      r->Get(options, lkey.internal_key(), &get_context);
       value.assign(pinnable_val.data(), pinnable_val.size());
       if (get_context.State() == GetContext::kFound) {
         statuses[idx] = Status::OK();
@@ -84,7 +93,6 @@ 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 +100,9 @@ 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;
   }
@@ -147,7 +154,6 @@ Status CompactedDBImpl::Open(const Options& options,
   std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
   Status s = db->Init(options);
   if (s.ok()) {
-    db->StartTimedTasks();
     ROCKS_LOG_INFO(db->immutable_db_options_.info_log,
                    "Opened the db as fully compacted mode");
     LogFlush(db->immutable_db_options_.info_log);

db/compacted_db_impl.h

@@ -5,9 +5,9 @@
 
 #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 {
 
@@ -32,66 +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.");
   }
 

db/compaction.cc

@@ -7,54 +7,22 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#include <cinttypes>
+#include "db/compaction.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <vector>
 
 #include "db/column_family.h"
-#include "db/compaction/compaction.h"
 #include "rocksdb/compaction_filter.h"
-#include "test_util/sync_point.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
 namespace rocksdb {
 
-const uint64_t kRangeTombstoneSentinel =
-    PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b) {
-  auto c = user_cmp->Compare(a.user_key(), b.user_key());
-  if (c != 0) {
-    return c;
-  }
-  auto a_footer = ExtractInternalKeyFooter(a.Encode());
-  auto b_footer = ExtractInternalKeyFooter(b.Encode());
-  if (a_footer == kRangeTombstoneSentinel) {
-    if (b_footer != kRangeTombstoneSentinel) {
-      return -1;
-    }
-  } else if (b_footer == kRangeTombstoneSentinel) {
-    return 1;
-  }
-  return 0;
-}
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
-                      const InternalKey& b) {
-  if (a == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, *a, b);
-}
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey* b) {
-  if (b == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, a, *b);
-}
-
 uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
   uint64_t sum = 0;
   for (size_t i = 0; i < files.size() && files[i]; i++) {
@@ -113,71 +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) {
@@ -317,7 +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_;
   }
@@ -360,31 +283,32 @@ 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_;
+  }
+  if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel &&
+      output_level_ == 0) {
+    return false;
+  }
+  // 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
@@ -412,14 +336,12 @@ 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());
@@ -495,23 +417,20 @@ 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 (max_output_file_size_ != port::kMaxUint64 &&
+      (cfd_->ioptions()->compaction_style == kCompactionStyleLevel ||
+       output_level() > 0)) {
+    preallocation_size = max_output_file_size_;
+  } else {
+    for (const auto& level_files : inputs_) {
+      for (const auto& file : level_files.files) {
+        preallocation_size += file->fd.GetFileSize();
+      }
     }
   }
-
-  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 {
@@ -532,12 +451,11 @@ 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 && output_level_ > 0 && !IsOutputLevelEmpty();
   } else if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
     return number_levels_ > 1 && output_level_ > 0;
   } else {
@@ -545,21 +463,4 @@ bool Compaction::ShouldFormSubcompactions() const {
   }
 }
 
-uint64_t Compaction::MaxInputFileCreationTime() const {
-  uint64_t max_creation_time = 0;
-  for (const auto& file : inputs_[0].files) {
-    if (file->fd.table_reader != nullptr &&
-        file->fd.table_reader->GetTableProperties() != nullptr) {
-      uint64_t creation_time =
-          file->fd.table_reader->GetTableProperties()->creation_time;
-      max_creation_time = std::max(max_creation_time, creation_time);
-    }
-  }
-  return max_creation_time;
-}
-
-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"
 
 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 MaxInputFileCreationTime() 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

@@ -1,232 +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);
-
-  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) {
-  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) 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

@@ -1,553 +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,
-                         CompactionPicker* compaction_picker,
-                         LogBuffer* log_buffer,
-                         const MutableCFOptions& mutable_cf_options,
-                         const ImmutableCFOptions& ioptions)
-      : cf_name_(cf_name),
-        vstorage_(vstorage),
-        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_;
-  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_);
-}
-}  // namespace
-
-Compaction* LevelCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  LevelCompactionBuilder builder(cf_name, vstorage, 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) override;
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-
-}  // namespace rocksdb

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

@@ -3,92 +3,98 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#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 {
 
+#ifndef ROCKSDB_LITE
+CompactionEventListener::CompactionListenerValueType fromInternalValueType(
+    ValueType vt) {
+  switch (vt) {
+    case kTypeDeletion:
+      return CompactionEventListener::CompactionListenerValueType::kDelete;
+    case kTypeValue:
+      return CompactionEventListener::CompactionListenerValueType::kValue;
+    case kTypeMerge:
+      return CompactionEventListener::CompactionListenerValueType::
+          kMergeOperand;
+    case kTypeSingleDeletion:
+      return CompactionEventListener::CompactionListenerValueType::
+          kSingleDelete;
+    case kTypeRangeDeletion:
+      return CompactionEventListener::CompactionListenerValueType::kRangeDelete;
+    default:
+      assert(false);
+      return CompactionEventListener::CompactionListenerValueType::kInvalid;
+  }
+}
+#endif  // ROCKSDB_LITE
+
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_write_conflict_snapshot,
-    const SnapshotChecker* snapshot_checker, Env* env,
-    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,
-    SnapshotListFetchCallback* snap_list_callback)
+    SequenceNumber earliest_write_conflict_snapshot, Env* env,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
+    const Compaction* compaction, const CompactionFilter* compaction_filter,
+    CompactionEventListener* compaction_listener,
+    const std::atomic<bool>* shutting_down)
     : 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,
-          snap_list_callback) {}
+          compaction_filter, compaction_listener, 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,
-    SnapshotListFetchCallback* snap_list_callback)
+    CompactionEventListener* compaction_listener,
+    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),
+      compaction_listener_(compaction_listener),
       shutting_down_(shutting_down),
-      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),
-      snap_list_callback_(snap_list_callback) {
+      ignore_snapshots_(false),
+      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);
   }
-  ProcessSnapshotList();
+
+  if (snapshots_->size() == 0) {
+    // optimize for fast path if there are no snapshots
+    visible_at_tip_ = true;
+    earliest_snapshot_ = last_sequence;
+    latest_snapshot_ = 0;
+  } else {
+    visible_at_tip_ = false;
+    earliest_snapshot_ = snapshots_->at(0);
+    latest_snapshot_ = snapshots_->back();
+  }
+  if (compaction_filter_ != nullptr) {
+    if (compaction_filter_->IgnoreSnapshots()) {
+      ignore_snapshots_ = true;
+    }
+  } else {
+    ignore_snapshots_ = false;
+  }
   input_->SetPinnedItersMgr(&pinned_iters_mgr_);
-  TEST_SYNC_POINT_CALLBACK("CompactionIterator:AfterInit", compaction_.get());
 }
 
 CompactionIterator::~CompactionIterator() {
@@ -102,7 +108,6 @@ 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() {
@@ -120,8 +125,8 @@ 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);
@@ -155,81 +160,6 @@ 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::ProcessSnapshotList() {
-#ifndef NDEBUG
-  // findEarliestVisibleSnapshot assumes this ordering.
-  for (size_t i = 1; i < snapshots_->size(); ++i) {
-    assert(snapshots_->at(i - 1) < snapshots_->at(i));
-  }
-#endif
-  if (snapshots_->size() == 0) {
-    // optimize for fast path if there are no snapshots
-    visible_at_tip_ = true;
-    earliest_snapshot_iter_ = snapshots_->end();
-    earliest_snapshot_ = kMaxSequenceNumber;
-    latest_snapshot_ = 0;
-  } else {
-    visible_at_tip_ = false;
-    earliest_snapshot_iter_ = snapshots_->begin();
-    earliest_snapshot_ = snapshots_->at(0);
-    latest_snapshot_ = snapshots_->back();
-  }
-  released_snapshots_.clear();
-}
-
 void CompactionIterator::NextFromInput() {
   at_next_ = false;
   valid_ = false;
@@ -256,7 +186,6 @@ void CompactionIterator::NextFromInput() {
       valid_ = true;
       break;
     }
-    TEST_SYNC_POINT_CALLBACK("CompactionIterator:ProcessKV", &ikey_);
 
     // Update input statistics
     if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
@@ -277,13 +206,6 @@ void CompactionIterator::NextFromInput() {
     // compaction filter). ikey_.user_key is pointing to the copy.
     if (!has_current_user_key_ ||
         !cmp_->Equal(ikey_.user_key, current_user_key_)) {
-      num_keys_++;
-      // Use num_keys_ to reduce the overhead of reading current time
-      if (snap_list_callback_ && snapshots_->size() &&
-          snap_list_callback_->TimeToRefresh(num_keys_)) {
-        snap_list_callback_->Refresh(snapshots_, latest_snapshot_);
-        ProcessSnapshotList();
-      }
       // First occurrence of this user key
       // Copy key for output
       key_ = current_key_.SetInternalKey(key_, &ikey_);
@@ -292,14 +214,70 @@ void CompactionIterator::NextFromInput() {
       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);
+#ifndef ROCKSDB_LITE
+      if (compaction_listener_) {
+        compaction_listener_->OnCompaction(compaction_->level(), ikey_.user_key,
+                                           fromInternalValueType(ikey_.type),
+                                           value_, ikey_.sequence, true);
+      }
+#endif  // ROCKSDB_LITE
+
+      // apply the compaction filter to the first occurrence of the user key
+      if (compaction_filter_ != nullptr && ikey_.type == kTypeValue &&
+          (visible_at_tip_ || ikey_.sequence > latest_snapshot_ ||
+           ignore_snapshots_)) {
+        // If the user has specified a compaction filter and the sequence
+        // number is greater than any external snapshot, then invoke the
+        // filter. If the return value of the compaction filter is true,
+        // replace the entry with a deletion marker.
+        CompactionFilter::Decision filter;
+        compaction_filter_value_.clear();
+        compaction_filter_skip_until_.Clear();
+        {
+          StopWatchNano timer(env_, true);
+          filter = compaction_filter_->FilterV2(
+              compaction_->level(), ikey_.user_key,
+              CompactionFilter::ValueType::kValue, value_,
+              &compaction_filter_value_, compaction_filter_skip_until_.rep());
+          iter_stats_.total_filter_time +=
+              env_ != nullptr ? timer.ElapsedNanos() : 0;
+        }
+
+        if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
+            cmp_->Compare(*compaction_filter_skip_until_.rep(),
+                          ikey_.user_key) <= 0) {
+          // Can't skip to a key smaller than the current one.
+          // Keep the key as per FilterV2 documentation.
+          filter = CompactionFilter::Decision::kKeep;
+        }
+
+        if (filter == CompactionFilter::Decision::kRemove) {
+          // convert the current key to a delete; key_ is pointing into
+          // current_key_ at this point, so updating current_key_ updates key()
+          ikey_.type = kTypeDeletion;
+          current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
+          // no value associated with delete
+          value_.clear();
+          iter_stats_.num_record_drop_user++;
+        } else if (filter == CompactionFilter::Decision::kChangeValue) {
+          value_ = compaction_filter_value_;
+        } else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
+          need_skip = true;
+          compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
+                                                           kValueTypeForSeek);
+          skip_until = compaction_filter_skip_until_.Encode();
+        }
       }
     } else {
+#ifndef ROCKSDB_LITE
+      if (compaction_listener_) {
+        compaction_listener_->OnCompaction(compaction_->level(), ikey_.user_key,
+                                           fromInternalValueType(ikey_.type),
+                                           value_, ikey_.sequence, false);
+      }
+#endif  // ROCKSDB_LITE
+
       // Update the current key to reflect the new sequence number/type without
       // copying the user key.
       // TODO(rven): Compaction filter does not process keys in this path
@@ -308,32 +286,13 @@ void CompactionIterator::NextFromInput() {
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
       key_ = current_key_.GetInternalKey();
       ikey_.user_key = current_key_.GetUserKey();
-
-      // Note that newer version of a key is ordered before older versions. If a
-      // newer version of a key is committed, so as the older version. No need
-      // to query snapshot_checker_ in that case.
-      if (UNLIKELY(!current_key_committed_)) {
-        assert(snapshot_checker_ != nullptr);
-        current_key_committed_ = 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
@@ -398,8 +357,7 @@ 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.
@@ -410,9 +368,8 @@ 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
@@ -422,8 +379,7 @@ 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;
             }
 
@@ -460,16 +416,13 @@ 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;
@@ -479,24 +432,21 @@ 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(noetzli): why not > ?
       //
       // Note: Dropping this key will not affect TransactionDB write-conflict
       // checking since there has already been a record returned for this key
       // in this snapshot.
       assert(last_sequence >= current_user_key_sequence_);
-
       ++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_
@@ -513,38 +463,8 @@ 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(
@@ -569,8 +489,8 @@ void CompactionIterator::NextFromInput() {
         //       These will be correctly set below.
         key_ = merge_out_iter_.key();
         value_ = merge_out_iter_.value();
-        bool valid_key __attribute__((__unused__));
-        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);
@@ -594,7 +514,7 @@ 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;
@@ -620,15 +540,12 @@ void CompactionIterator::PrepareOutput() {
   // and the earliest snapshot is larger than this seqno
   // and the userkey differs from the last userkey in compaction
   // then we can squash the seqno to zero.
-  //
+
   // This is safe for TransactionDB write-conflict checking since transactions
   // only care about sequence number larger than any active snapshots.
-  //
-  // Can we do the same for levels above bottom level as long as
-  // KeyNotExistsBeyondOutputLevel() return true?
-  if ((compaction_ != nullptr && !compaction_->allow_ingest_behind()) &&
-      ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ && valid_ &&
-      IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
+  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);
@@ -638,68 +555,18 @@ void CompactionIterator::PrepareOutput() {
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  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 (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);
-    // 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);
-  assert(earliest_snapshot_ == kMaxSequenceNumber ||
-         (earliest_snapshot_iter_ != snapshots_->end() &&
-          *earliest_snapshot_iter_ == earliest_snapshot_));
-  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);
-  return in_snapshot == SnapshotCheckerResult::kInSnapshot;
-}
-
 }  // namespace rocksdb

db/compaction_iterator.h

@@ -7,66 +7,18 @@
 #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 {
 
-// This callback can be used to refresh the snapshot list from the db. It
-// includes logics to exponentially decrease the refresh rate to limit the
-// overhead of refresh.
-class SnapshotListFetchCallback {
- public:
-  SnapshotListFetchCallback(Env* env, uint64_t snap_refresh_nanos,
-                            size_t every_nth_key = 1024)
-      : timer_(env, /*auto restart*/ true),
-        snap_refresh_nanos_(snap_refresh_nanos),
-        every_nth_key_minus_one_(every_nth_key - 1) {
-    assert(every_nth_key > 0);
-    assert((ceil(log2(every_nth_key)) == floor(log2(every_nth_key))));
-  }
-  // Refresh the snapshot list. snapshots will bre replacted with the new list.
-  // max is the upper bound. Note: this function will acquire the db_mutex_.
-  virtual void Refresh(std::vector<SequenceNumber>* snapshots,
-                       SequenceNumber max) = 0;
-  inline bool TimeToRefresh(const size_t key_index) {
-    // skip the key if key_index % every_nth_key (which is of power 2) is not 0.
-    if ((key_index & every_nth_key_minus_one_) != 0) {
-      return false;
-    }
-    const uint64_t elapsed = timer_.ElapsedNanos();
-    auto ret = elapsed > snap_refresh_nanos_;
-    // pre-compute the next time threshold
-    if (ret) {
-      // inc next refresh period exponentially (by x4)
-      auto next_refresh_threshold = snap_refresh_nanos_ << 2;
-      // make sure the shift has not overflown the highest 1 bit
-      snap_refresh_nanos_ =
-          std::max(snap_refresh_nanos_, next_refresh_threshold);
-    }
-    return ret;
-  }
-  static constexpr SnapshotListFetchCallback* kDisabled = nullptr;
-
-  virtual ~SnapshotListFetchCallback() {}
-
- private:
-  // Time since the callback was created
-  StopWatchNano timer_;
-  // The delay before calling ::Refresh. To be increased exponentially.
-  uint64_t snap_refresh_nanos_;
-  // Skip evey nth key. Number n if of power 2. The math will require n-1.
-  const uint64_t every_nth_key_minus_one_;
-};
+class CompactionEventListener;
 
 class CompactionIterator {
  public:
@@ -78,7 +30,7 @@ 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(
@@ -92,12 +44,6 @@ 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;
@@ -109,29 +55,25 @@ class CompactionIterator {
   CompactionIterator(InternalIterator* input, const Comparator* cmp,
                      MergeHelper* merge_helper, SequenceNumber last_sequence,
                      std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
-                     bool report_detailed_time, bool expect_valid_internal_key,
-                     CompactionRangeDelAggregator* range_del_agg,
+                     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,
-                     const SequenceNumber preserve_deletes_seqnum = 0,
-                     SnapshotListFetchCallback* snap_list_callback = nullptr);
+                     CompactionEventListener* compaction_listener = 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,
+                     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,
-                     const SequenceNumber preserve_deletes_seqnum = 0,
-                     SnapshotListFetchCallback* snap_list_callback = nullptr);
+                     CompactionEventListener* compaction_listener = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr);
 
   ~CompactionIterator();
 
@@ -159,17 +101,12 @@ class CompactionIterator {
  private:
   // Processes the input stream to find the next output
   void NextFromInput();
-  // Process snapshots_ and assign related variables
-  void ProcessSnapshotList();
 
   // Do last preparations before presenting the output to the callee. At this
   // point this only zeroes out the sequence number if possible for better
   // 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
@@ -179,45 +116,24 @@ 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_;
-  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 std::vector<SequenceNumber>* snapshots_;
   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_;
+  CompactionEventListener* compaction_listener_;
   const std::atomic<bool>* shutting_down_;
-  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
   //
@@ -267,13 +183,6 @@ class CompactionIterator {
   std::vector<size_t> level_ptrs_;
   CompactionIterationStats iter_stats_;
 
-  // Used to avoid purging uncommitted values. The application can specify
-  // uncommitted values by providing a SnapshotChecker object.
-  bool current_key_committed_;
-  SnapshotListFetchCallback* snap_list_callback_;
-  // number of distinct keys processed
-  size_t num_keys_ = 0;
-
   bool IsShuttingDown() {
     // This is a best-effort facility, so memory_order_relaxed is sufficient.
     return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);

db/compaction_iterator_test.cc

@@ -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, nullptr, &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"
@@ -29,8 +29,6 @@
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
-#include "logging/event_logger.h"
-#include "options/cf_options.h"
 #include "options/db_options.h"
 #include "port/port.h"
 #include "rocksdb/compaction_filter.h"
@@ -41,41 +39,34 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
 
-class Arena;
-class ErrorHandler;
 class MemTable;
-class SnapshotChecker;
 class TableCache;
 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 EnvOptions env_options, VersionSet* versions,
-      const std::atomic<bool>* shutting_down,
-      const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
-      Directory* db_directory, Directory* output_directory, Statistics* stats,
-      InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
-      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, SnapshotListFetchCallback* snap_list_callback);
+  CompactionJob(int job_id, Compaction* compaction,
+                const ImmutableDBOptions& db_options,
+                const EnvOptions& env_options, VersionSet* versions,
+                const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
+                Directory* db_directory, Directory* output_directory,
+                Statistics* stats, InstrumentedMutex* db_mutex,
+                Status* db_bg_error,
+                std::vector<SequenceNumber> existing_snapshots,
+                SequenceNumber earliest_write_conflict_snapshot,
+                std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
+                bool paranoid_file_checks, bool measure_io_stats,
+                const std::string& dbname,
+                CompactionJobStats* compaction_job_stats);
 
   ~CompactionJob();
 
@@ -85,28 +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.
@@ -118,7 +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);
@@ -147,39 +127,32 @@ class CompactionJob {
   // DBImpl state
   const std::string& dbname_;
   const ImmutableDBOptions& db_options_;
-  const EnvOptions env_options_;
+  const EnvOptions& env_options_;
 
   Env* env_;
-  // env_option optimized for compaction table reads
-  EnvOptions env_options_for_read_;
   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_;
+  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
   // deleted because that version is not visible in any snapshot.
   std::vector<SequenceNumber> existing_snapshots_;
-  SnapshotListFetchCallback* snap_list_callback_;
 
   // This is the earliest snapshot that could be used for write-conflict
   // checking by a transaction.  For any user-key newer than this snapshot, we
   // 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_;
@@ -187,8 +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

@@ -7,7 +7,11 @@
 // 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>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
 #include <iostream>
 #include <mutex>
@@ -17,14 +21,12 @@
 #include <unordered_set>
 #include <utility>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/dbformat.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "db/write_batch_internal.h"
 #include "env/mock_env.h"
-#include "file/filename.h"
-#include "logging/logging.h"
 #include "memtable/hash_linklist_rep.h"
 #include "monitoring/statistics.h"
 #include "monitoring/thread_status_util.h"
@@ -45,18 +47,20 @@
 #include "rocksdb/thread_status.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/write_batch_with_index.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/mock_table.h"
-#include "table/plain/plain_table_factory.h"
+#include "table/plain_table_factory.h"
 #include "table/scoped_arena_iterator.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/compression.h"
+#include "util/filename.h"
 #include "util/hash.h"
+#include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/rate_limiter.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
 #if !defined(IOS_CROSS_COMPILE)
@@ -94,7 +98,7 @@ class CompactionJobStatsTest : public testing::Test,
   CompactionJobStatsTest() : env_(Env::Default()) {
     env_->SetBackgroundThreads(1, Env::LOW);
     env_->SetBackgroundThreads(1, Env::HIGH);
-    dbname_ = test::PerThreadDBPath("compaction_job_stats_test");
+    dbname_ = test::TmpDir(env_) + "/compaction_job_stats_test";
     alternative_wal_dir_ = dbname_ + "/wal";
     Options options;
     options.create_if_missing = true;
@@ -109,7 +113,7 @@ class CompactionJobStatsTest : public testing::Test,
     Reopen(options);
   }
 
-  ~CompactionJobStatsTest() override {
+  ~CompactionJobStatsTest() {
     rocksdb::SyncPoint::GetInstance()->DisableProcessing();
     rocksdb::SyncPoint::GetInstance()->LoadDependency({});
     rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -422,7 +426,7 @@ class CompactionJobStatsChecker : public EventListener {
   // Once a compaction completed, this function will verify the returned
   // CompactionJobInfo with the oldest CompactionJobInfo added earlier
   // in "expected_stats_" which has not yet being used for verification.
-  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
+  virtual void OnCompactionCompleted(DB *db, const CompactionJobInfo& ci) {
     if (verify_next_comp_io_stats_) {
       ASSERT_GT(ci.stats.file_write_nanos, 0);
       ASSERT_GT(ci.stats.file_range_sync_nanos, 0);
@@ -519,7 +523,7 @@ class CompactionJobDeletionStatsChecker : public CompactionJobStatsChecker {
  public:
   // Verifies whether two CompactionJobStats match.
   void Verify(const CompactionJobStats& current_stats,
-              const CompactionJobStats& stats) override {
+              const CompactionJobStats& stats) {
     ASSERT_EQ(
       current_stats.num_input_deletion_records,
       stats.num_input_deletion_records);
@@ -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

@@ -5,26 +5,23 @@
 
 #ifndef ROCKSDB_LITE
 
-#include <cinttypes>
 #include <algorithm>
-#include <array>
 #include <map>
 #include <string>
 #include <tuple>
 
 #include "db/column_family.h"
-#include "db/compaction/compaction_job.h"
-#include "db/error_handler.h"
+#include "db/compaction_job.h"
 #include "db/version_set.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 {
@@ -70,19 +67,16 @@ class CompactionJobTest : public testing::Test {
  public:
   CompactionJobTest()
       : env_(Env::Default()),
-        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_.db_paths.emplace_back(dbname_,
                                       std::numeric_limits<uint64_t>::max());
@@ -148,8 +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);
   }
 
@@ -175,7 +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);
@@ -197,26 +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();
-
     VersionEdit new_db;
     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(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;
@@ -241,10 +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,
-      SnapshotListFetchCallback* snapshot_fetcher =
-          SnapshotListFetchCallback::kDisabled) {
+      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
     auto cfd = versions_->GetColumnFamilySet()->GetDefault();
 
     size_t num_input_files = 0;
@@ -261,23 +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, snapshot_fetcher);
+        &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();
@@ -289,17 +266,15 @@ 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);
-        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);
-      }
+    if (expected_results.size() == 0) {
+      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, 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);
     }
   }
 
@@ -315,13 +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) {
@@ -363,24 +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();
 
@@ -396,7 +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);
@@ -449,7 +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);
@@ -473,7 +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);
@@ -500,7 +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);
@@ -763,7 +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);
@@ -947,112 +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 the snapshot fetcher in compaction
-TEST_F(CompactionJobTest, SnapshotRefresh) {
-  uint64_t time_seed = env_->NowMicros();
-  printf("time_seed is %" PRIu64 "\n", time_seed);  // would help to reproduce
-  Random64 rand(time_seed);
-  std::vector<SequenceNumber> db_snapshots;
-  class SnapshotListFetchCallbackTest : public SnapshotListFetchCallback {
-   public:
-    SnapshotListFetchCallbackTest(Env* env, Random64& rand,
-                                  std::vector<SequenceNumber>* snapshots)
-        : SnapshotListFetchCallback(env, 0 /*no time delay*/,
-                                    1 /*fetch after each key*/),
-          rand_(rand),
-          snapshots_(snapshots) {}
-    virtual void Refresh(std::vector<SequenceNumber>* snapshots,
-                         SequenceNumber) override {
-      assert(snapshots->size());
-      assert(snapshots_->size());
-      assert(snapshots_->size() == snapshots->size());
-      if (rand_.OneIn(2)) {
-        uint64_t release_index = rand_.Uniform(snapshots_->size());
-        snapshots_->erase(snapshots_->begin() + release_index);
-        *snapshots = *snapshots_;
-      }
-    }
-
-   private:
-    Random64 rand_;
-    std::vector<SequenceNumber>* snapshots_;
-  } snapshot_fetcher(env_, rand, &db_snapshots);
-
-  std::vector<std::pair<const std::string, std::string>> file1_kvs, file2_kvs;
-  std::array<ValueType, 4> types = {kTypeValue, kTypeDeletion,
-                                    kTypeSingleDeletion};
-  SequenceNumber last_seq = 0;
-  for (int i = 1; i < 100; i++) {
-    SequenceNumber seq = last_seq + 1;
-    last_seq = seq;
-    if (rand.OneIn(2)) {
-      auto type = types[rand.Uniform(types.size())];
-      file1_kvs.push_back(
-          {test::KeyStr("k" + ToString(i), seq, type), "v" + ToString(i)});
-    }
-  }
-  auto file1 = mock::MakeMockFile(file1_kvs);
-  for (int i = 1; i < 100; i++) {
-    SequenceNumber seq = last_seq + 1;
-    last_seq++;
-    if (rand.OneIn(2)) {
-      auto type = types[rand.Uniform(types.size())];
-      file2_kvs.push_back(
-          {test::KeyStr("k" + ToString(i), seq, type), "v" + ToString(i)});
-    }
-  }
-  auto file2 = mock::MakeMockFile(file2_kvs);
-  for (SequenceNumber i = 1; i < last_seq + 1; i++) {
-    if (rand.OneIn(5)) {
-      db_snapshots.push_back(i);
-    }
-  }
-
-  const bool kVerify = true;
-  const int output_level_0 = 0;
-  NewDB();
-  AddMockFile(file1);
-  AddMockFile(file2);
-  SetLastSequence(last_seq);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  // put the output on L0 since it is easier to feed them again to the 2nd
-  // compaction
-  RunCompaction({files}, file1, db_snapshots, kMaxSequenceNumber,
-                output_level_0, !kVerify, &snapshot_fetcher);
-
-  // Now db_snapshots are changed. Run the compaction again without snapshot
-  // fetcher but with the updated snapshot list.
-  compaction_job_stats_.Reset();
-  files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, file1, db_snapshots, kMaxSequenceNumber,
-                output_level_0 + 1, !kVerify);
-  // The result should be what we get if we run compaction without snapshot
-  // fetcher on the updated list of snapshots
-  auto expected = mock_table_factory_->output();
-
-  NewDB();
-  AddMockFile(file1);
-  AddMockFile(file2);
-  SetLastSequence(last_seq);
-  files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected, db_snapshots, kMaxSequenceNumber,
-                output_level_0, !kVerify);
-  // The 2nd compaction above would get rid of useless delete markers. To get
-  // the output here exactly as what we got above after two compactions, we also
-  // run the compaction for 2nd time.
-  compaction_job_stats_.Reset();
-  files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected, db_snapshots, kMaxSequenceNumber,
-                output_level_0 + 1, !kVerify);
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
@@ -1063,7 +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.cc

@@ -7,21 +7,24 @@
 // 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.h"
+#include "db/compaction_picker.h"
 
-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <limits>
 #include <queue>
 #include <string>
 #include <utility>
-#include <vector>
 #include "db/column_family.h"
-#include "file/filename.h"
-#include "logging/log_buffer.h"
 #include "monitoring/statistics.h"
-#include "test_util/sync_point.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
 #include "util/random.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
 namespace rocksdb {
 
@@ -35,43 +38,6 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
 }
 }  // anonymous namespace
 
-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) {
-  size_t compact_bytes = static_cast<size_t>(level_files[0]->fd.file_size);
-  uint64_t compensated_compact_bytes = level_files[0]->compensated_file_size;
-  size_t compact_bytes_per_del_file = port::kMaxSizet;
-  // Compaction range will be [0, span_len).
-  size_t span_len;
-  // Pull in files until the amount of compaction work per deleted file begins
-  // increasing or maximum total compaction size is reached.
-  size_t new_compact_bytes_per_del_file = 0;
-  for (span_len = 1; span_len < level_files.size(); ++span_len) {
-    compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
-    compensated_compact_bytes += level_files[span_len]->compensated_file_size;
-    new_compact_bytes_per_del_file = compact_bytes / span_len;
-    if (level_files[span_len]->being_compacted ||
-        new_compact_bytes_per_del_file > compact_bytes_per_del_file ||
-        compensated_compact_bytes > max_compaction_bytes) {
-      break;
-    }
-    compact_bytes_per_del_file = new_compact_bytes_per_del_file;
-  }
-
-  if (span_len >= min_files_to_compact &&
-      compact_bytes_per_del_file < max_compact_bytes_per_del_file) {
-    assert(comp_inputs != nullptr);
-    comp_inputs->level = 0;
-    for (size_t i = 0; i < span_len; ++i) {
-      comp_inputs->files.push_back(level_files[i]);
-    }
-    return true;
-  }
-  return false;
-}
-
 // Determine compression type, based on user options, level of the output
 // file and whether compression is disabled.
 // If enable_compression is false, then compression is always disabled no
@@ -90,7 +56,7 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
   // If bottommost_compression is set and we are compacting to the
   // bottommost level then we should use it.
   if (ioptions.bottommost_compression != kDisableCompressionOption &&
-      level >= (vstorage->num_non_empty_levels() - 1)) {
+      level > base_level && level >= (vstorage->num_non_empty_levels() - 1)) {
     return ioptions.bottommost_compression;
   }
   // If the user has specified a different compression level for each level,
@@ -111,24 +77,6 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
   }
 }
 
-CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
-                                         const VersionStorageInfo* vstorage,
-                                         int level,
-                                         const bool enable_compression) {
-  if (!enable_compression) {
-    return ioptions.compression_opts;
-  }
-  // If bottommost_compression is set and we are compacting to the
-  // bottommost level then we should use the specified compression options
-  // for the bottmomost_compression.
-  if (ioptions.bottommost_compression != kDisableCompressionOption &&
-      level >= (vstorage->num_non_empty_levels() - 1) &&
-      ioptions.bottommost_compression_opts.enabled) {
-    return ioptions.bottommost_compression_opts;
-  }
-  return ioptions.compression_opts;
-}
-
 CompactionPicker::CompactionPicker(const ImmutableCFOptions& ioptions,
                                    const InternalKeyComparator* icmp)
     : ioptions_(ioptions), icmp_(icmp) {}
@@ -218,10 +166,9 @@ void CompactionPicker::GetRange(const std::vector<CompactionInputFiles>& inputs,
   assert(initialized);
 }
 
-bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
+bool CompactionPicker::ExpandInputsToCleanCut(const std::string& cf_name,
                                               VersionStorageInfo* vstorage,
-                                              CompactionInputFiles* inputs,
-                                              InternalKey** next_smallest) {
+                                              CompactionInputFiles* inputs) {
   // This isn't good compaction
   assert(!inputs->empty());
 
@@ -244,8 +191,7 @@ bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
     GetRange(*inputs, &smallest, &largest);
     inputs->clear();
     vstorage->GetOverlappingInputs(level, &smallest, &largest, &inputs->files,
-                                   hint_index, &hint_index, true,
-                                   next_smallest);
+                                   hint_index, &hint_index);
   } while (inputs->size() > old_size);
 
   // we started off with inputs non-empty and the previous loop only grew
@@ -255,6 +201,11 @@ bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
   // If, after the expansion, there are files that are already under
   // compaction, then we must drop/cancel this compaction.
   if (AreFilesInCompaction(inputs->files)) {
+    ROCKS_LOG_WARN(
+        ioptions_.info_log,
+        "[%s] ExpandWhileOverlapping() failure because some of the necessary"
+        " compaction input files are currently being compacted.",
+        cf_name.c_str());
     return false;
   }
   return true;
@@ -313,34 +264,25 @@ Compaction* CompactionPicker::CompactFiles(
     VersionStorageInfo* vstorage, const MutableCFOptions& mutable_cf_options,
     uint32_t output_path_id) {
   assert(input_files.size());
-  // This compaction output should not overlap with a running compaction as
-  // `SanitizeCompactionInputFiles` should've checked earlier and db mutex
-  // shouldn't have been released since.
-  assert(!FilesRangeOverlapWithCompaction(input_files, output_level));
 
-  CompressionType compression_type;
-  if (compact_options.compression == kDisableCompressionOption) {
-    int base_level;
-    if (ioptions_.compaction_style == kCompactionStyleLevel) {
-      base_level = vstorage->base_level();
-    } else {
-      base_level = 1;
-    }
-    compression_type =
-        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
-                           output_level, base_level);
-  } else {
-    // TODO(ajkr): `CompactionOptions` offers configurable `CompressionType`
-    // without configurable `CompressionOptions`, which is inconsistent.
-    compression_type = compact_options.compression;
+  // TODO(rven ): we might be able to run concurrent level 0 compaction
+  // if the key ranges of the two compactions do not overlap, but for now
+  // we do not allow it.
+  if ((input_files[0].level == 0) && !level0_compactions_in_progress_.empty()) {
+    return nullptr;
   }
-  auto c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, input_files, output_level,
-      compact_options.output_file_size_limit,
-      mutable_cf_options.max_compaction_bytes, output_path_id, compression_type,
-      GetCompressionOptions(ioptions_, vstorage, output_level),
-      compact_options.max_subcompactions,
-      /* grandparents */ {}, true);
+  // This compaction output could overlap with a running compaction
+  if (FilesRangeOverlapWithCompaction(input_files, output_level)) {
+    return nullptr;
+  }
+  auto c =
+      new Compaction(vstorage, ioptions_, mutable_cf_options, input_files,
+                     output_level, compact_options.output_file_size_limit,
+                     mutable_cf_options.max_compaction_bytes, output_path_id,
+                     compact_options.compression, /* grandparents */ {}, true);
+
+  // If it's level 0 compaction, make sure we don't execute any other level 0
+  // compactions in parallel
   RegisterCompaction(c);
   return c;
 }
@@ -348,7 +290,7 @@ Compaction* CompactionPicker::CompactFiles(
 Status CompactionPicker::GetCompactionInputsFromFileNumbers(
     std::vector<CompactionInputFiles>* input_files,
     std::unordered_set<uint64_t>* input_set, const VersionStorageInfo* vstorage,
-    const CompactionOptions& /*compact_options*/) const {
+    const CompactionOptions& compact_options) const {
   if (input_set->size() == 0U) {
     return Status::InvalidArgument(
         "Compaction must include at least one file.");
@@ -403,7 +345,7 @@ bool CompactionPicker::IsRangeInCompaction(VersionStorageInfo* vstorage,
   assert(level < NumberLevels());
 
   vstorage->GetOverlappingInputs(level, smallest, largest, &inputs,
-                                 level_index ? *level_index : 0, level_index);
+                                 *level_index, level_index);
   return AreFilesInCompaction(inputs);
 }
 
@@ -426,10 +368,7 @@ bool CompactionPicker::SetupOtherInputs(
   assert(output_level_inputs->empty());
   const int input_level = inputs->level;
   const int output_level = output_level_inputs->level;
-  if (input_level == output_level) {
-    // no possibility of conflict
-    return true;
-  }
+  assert(input_level != output_level);
 
   // For now, we only support merging two levels, start level and output level.
   // We need to assert other levels are empty.
@@ -514,7 +453,7 @@ bool CompactionPicker::SetupOtherInputs(
       ROCKS_LOG_INFO(ioptions_.info_log,
                      "[%s] Expanding@%d %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt
                      "(%" PRIu64 "+%" PRIu64 " bytes) to %" ROCKSDB_PRIszt
-                     "+%" ROCKSDB_PRIszt " (%" PRIu64 "+%" PRIu64 " bytes)\n",
+                     "+%" ROCKSDB_PRIszt " (%" PRIu64 "+%" PRIu64 "bytes)\n",
                      cf_name.c_str(), input_level, inputs->size(),
                      output_level_inputs->size(), inputs_size,
                      output_level_inputs_size, expanded_inputs.size(),
@@ -543,9 +482,8 @@ void CompactionPicker::GetGrandparents(
 Compaction* CompactionPicker::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) {
   // CompactionPickerFIFO has its own implementation of compact range
   assert(ioptions_.compaction_style != kCompactionStyleFIFO);
 
@@ -556,11 +494,7 @@ Compaction* CompactionPicker::CompactRange(
     // files together to the last level.
     assert(vstorage->num_levels() > 1);
     // DBImpl::CompactRange() set output level to be the last level
-    if (ioptions_.allow_ingest_behind) {
-      assert(output_level == vstorage->num_levels() - 2);
-    } else {
-      assert(output_level == vstorage->num_levels() - 1);
-    }
+    assert(output_level == vstorage->num_levels() - 1);
     // DBImpl::RunManualCompaction will make full range for universal compaction
     assert(begin == nullptr);
     assert(end == nullptr);
@@ -606,16 +540,11 @@ Compaction* CompactionPicker::CompactRange(
 
     Compaction* c = new Compaction(
         vstorage, ioptions_, mutable_cf_options, std::move(inputs),
-        output_level,
-        MaxFileSizeForLevel(mutable_cf_options, output_level,
-                            ioptions_.compaction_style),
-        /* max_compaction_bytes */ LLONG_MAX,
-        compact_range_options.target_path_id,
+        output_level, mutable_cf_options.MaxFileSizeForLevel(output_level),
+        /* max_compaction_bytes */ LLONG_MAX, output_path_id,
         GetCompressionType(ioptions_, vstorage, mutable_cf_options,
                            output_level, 1),
-        GetCompressionOptions(ioptions_, vstorage, output_level),
-        compact_range_options.max_subcompactions, /* grandparents */ {},
-        /* is manual */ true);
+        /* grandparents */ {}, /* is manual */ true);
     RegisterCompaction(c);
     return c;
   }
@@ -654,54 +583,16 @@ Compaction* CompactionPicker::CompactRange(
       uint64_t s = inputs[i]->compensated_file_size;
       total += s;
       if (total >= limit) {
+        **compaction_end = inputs[i + 1]->smallest;
         covering_the_whole_range = false;
         inputs.files.resize(i + 1);
         break;
       }
     }
   }
-  assert(compact_range_options.target_path_id <
-         static_cast<uint32_t>(ioptions_.cf_paths.size()));
+  assert(output_path_id < static_cast<uint32_t>(ioptions_.db_paths.size()));
 
-  // for BOTTOM LEVEL compaction only, use max_file_num_to_ignore to filter out
-  // files that are created during the current compaction.
-  if (compact_range_options.bottommost_level_compaction ==
-          BottommostLevelCompaction::kForceOptimized &&
-      max_file_num_to_ignore != port::kMaxUint64) {
-    assert(input_level == output_level);
-    // inputs_shrunk holds a continuous subset of input files which were all
-    // created before the current manual compaction
-    std::vector<FileMetaData*> inputs_shrunk;
-    size_t skip_input_index = inputs.size();
-    for (size_t i = 0; i < inputs.size(); ++i) {
-      if (inputs[i]->fd.GetNumber() < max_file_num_to_ignore) {
-        inputs_shrunk.push_back(inputs[i]);
-      } else if (!inputs_shrunk.empty()) {
-        // inputs[i] was created during the current manual compaction and
-        // need to be skipped
-        skip_input_index = i;
-        break;
-      }
-    }
-    if (inputs_shrunk.empty()) {
-      return nullptr;
-    }
-    if (inputs.size() != inputs_shrunk.size()) {
-      inputs.files.swap(inputs_shrunk);
-    }
-    // set covering_the_whole_range to false if there is any file that need to
-    // be compacted in the range of inputs[skip_input_index+1, inputs.size())
-    for (size_t i = skip_input_index + 1; i < inputs.size(); ++i) {
-      if (inputs[i]->fd.GetNumber() < max_file_num_to_ignore) {
-        covering_the_whole_range = false;
-      }
-    }
-  }
-
-  InternalKey key_storage;
-  InternalKey* next_smallest = &key_storage;
-  if (ExpandInputsToCleanCut(cf_name, vstorage, &inputs, &next_smallest) ==
-      false) {
+  if (ExpandInputsToCleanCut(cf_name, vstorage, &inputs) == false) {
     // manual compaction is now multi-threaded, so it can
     // happen that ExpandWhileOverlapping fails
     // we handle it higher in RunManualCompaction
@@ -709,10 +600,8 @@ Compaction* CompactionPicker::CompactRange(
     return nullptr;
   }
 
-  if (covering_the_whole_range || !next_smallest) {
+  if (covering_the_whole_range) {
     *compaction_end = nullptr;
-  } else {
-    **compaction_end = *next_smallest;
   }
 
   CompactionInputFiles output_level_inputs;
@@ -758,17 +647,11 @@ Compaction* CompactionPicker::CompactRange(
   GetGrandparents(vstorage, inputs, output_level_inputs, &grandparents);
   Compaction* compaction = 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,
-      compact_range_options.target_path_id,
+      output_level, mutable_cf_options.MaxFileSizeForLevel(output_level),
+      mutable_cf_options.max_compaction_bytes, output_path_id,
       GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                          vstorage->base_level()),
-      GetCompressionOptions(ioptions_, vstorage, output_level),
-      compact_range_options.max_subcompactions, std::move(grandparents),
-      /* is manual compaction */ true);
+      std::move(grandparents), /* is manual compaction */ true);
 
   TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);
   RegisterCompaction(compaction);
@@ -815,6 +698,10 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
   auto& levels = cf_meta.levels;
   auto comparator = icmp_->user_comparator();
 
+  // TODO(yhchiang): If there is any input files of L1 or up and there
+  // is at least one L0 files. All L0 files older than the L0 file needs
+  // to be included. Otherwise, it is a false conditoin
+
   // TODO(yhchiang): add is_adjustable to CompactionOptions
 
   // the smallest and largest key of the current compaction input
@@ -875,8 +762,6 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
         }
         last_included++;
       }
-    } else if (output_level > 0) {
-      last_included = static_cast<int>(current_files.size() - 1);
     }
 
     // include all files between the first and the last compaction input files.
@@ -936,11 +821,6 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
       }
     }
   }
-  if (RangeOverlapWithCompaction(smallestkey, largestkey, output_level)) {
-    return Status::Aborted(
-        "A running compaction is writing to the same output level in an "
-        "overlapping key range");
-  }
   return Status::OK();
 }
 
@@ -983,8 +863,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
   // any currently-existing files.
   for (auto file_num : *input_files) {
     bool found = false;
-    for (const auto& level_meta : cf_meta.levels) {
-      for (const auto& file_meta : level_meta.files) {
+    for (auto level_meta : cf_meta.levels) {
+      for (auto file_meta : level_meta.files) {
         if (file_num == TableFileNameToNumber(file_meta.name)) {
           if (file_meta.being_compacted) {
             return Status::Aborted("Specified compaction input file " +
@@ -1035,76 +915,551 @@ void CompactionPicker::UnregisterCompaction(Compaction* c) {
   compactions_in_progress_.erase(c);
 }
 
-void CompactionPicker::PickFilesMarkedForCompaction(
-    const std::string& cf_name, VersionStorageInfo* vstorage, int* start_level,
-    int* output_level, CompactionInputFiles* start_level_inputs) {
-  if (vstorage->FilesMarkedForCompaction().empty()) {
+bool LevelCompactionPicker::NeedsCompaction(
+    const VersionStorageInfo* vstorage) const {
+  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,
+                         CompactionPicker* compaction_picker,
+                         LogBuffer* log_buffer,
+                         const MutableCFOptions& mutable_cf_options,
+                         const ImmutableCFOptions& ioptions)
+      : cf_name_(cf_name),
+        vstorage_(vstorage),
+        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();
+
+  // If there is any file marked for compaction, put put it into inputs.
+  void PickFilesMarkedForCompaction();
+
+  const std::string& cf_name_;
+  VersionStorageInfo* vstorage_;
+  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::PickFilesMarkedForCompaction() {
+  if (vstorage_->FilesMarkedForCompaction().empty()) {
     return;
   }
 
-  auto continuation = [&, cf_name](std::pair<int, FileMetaData*> level_file) {
+  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;
+    start_level_ = level_file.first;
+    output_level_ =
+        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
 
-    if (*start_level == 0 && !level0_compactions_in_progress()->empty()) {
+    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 ExpandInputsToCleanCut(cf_name, vstorage, start_level_inputs);
+    start_level_inputs_.files = {level_file.second};
+    start_level_inputs_.level = start_level_;
+    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                      &start_level_inputs_);
   };
 
   // take a chance on a random file first
-  Random64 rnd(/* seed */ reinterpret_cast<uint64_t>(vstorage));
+  Random64 rnd(/* seed */ reinterpret_cast<uint64_t>(vstorage_));
   size_t random_file_index = static_cast<size_t>(rnd.Uniform(
-      static_cast<uint64_t>(vstorage->FilesMarkedForCompaction().size())));
+      static_cast<uint64_t>(vstorage_->FilesMarkedForCompaction().size())));
 
-  if (continuation(vstorage->FilesMarkedForCompaction()[random_file_index])) {
+  if (continuation(vstorage_->FilesMarkedForCompaction()[random_file_index])) {
     // found the compaction!
     return;
   }
 
-  for (auto& level_file : vstorage->FilesMarkedForCompaction()) {
+  for (auto& level_file : vstorage_->FilesMarkedForCompaction()) {
     if (continuation(level_file)) {
       // found the compaction!
       return;
     }
   }
-  start_level_inputs->files.clear();
+  start_level_inputs_.files.clear();
 }
 
-bool CompactionPicker::GetOverlappingL0Files(
-    VersionStorageInfo* vstorage, CompactionInputFiles* start_level_inputs,
-    int output_level, int* parent_index) {
-  // Two level 0 compaction won't run at the same time, so don't need to worry
-  // about files on level 0 being compacted.
-  assert(level0_compactions_in_progress()->empty());
-  InternalKey smallest, largest;
-  GetRange(*start_level_inputs, &smallest, &largest);
-  // Note that the next call will discard the file we placed in
-  // c->inputs_[0] earlier and replace it with an overlapping set
-  // which will include the picked file.
-  start_level_inputs->files.clear();
-  vstorage->GetOverlappingInputs(0, &smallest, &largest,
-                                 &(start_level_inputs->files));
-
-  // If we include more L0 files in the same compaction run it can
-  // cause the 'smallest' and 'largest' key to get extended to a
-  // larger range. So, re-invoke GetRange to get the new key range
-  GetRange(*start_level_inputs, &smallest, &largest);
-  if (IsRangeInCompaction(vstorage, &smallest, &largest, output_level,
-                          parent_index)) {
-    return false;
+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() &&
+          compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                     &start_level_inputs_) &&
+          !compaction_picker_->FilesRangeOverlapWithCompaction(
+              {start_level_inputs_}, output_level_)) {
+        // 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;
+          }
+        }
+      }
+    }
   }
-  assert(!start_level_inputs->files.empty());
+
+  // if we didn't find a compaction, check if there are any files marked for
+  // compaction
+  if (start_level_inputs_.empty()) {
+    is_manual_ = true;
+    parent_index_ = base_index_ = -1;
+    PickFilesMarkedForCompaction();
+    if (!start_level_inputs_.empty()) {
+      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
+    }
+  }
+}
+
+bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
+  if (start_level_ == 0 && output_level_ != 0) {
+    // Two level 0 compaction won't run at the same time, so don't need to worry
+    // about files on level 0 being compacted.
+    assert(compaction_picker_->level0_compactions_in_progress()->empty());
+    InternalKey smallest, largest;
+    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
+    // Note that the next call will discard the file we placed in
+    // c->inputs_[0] earlier and replace it with an overlapping set
+    // which will include the picked file.
+    start_level_inputs_.files.clear();
+    vstorage_->GetOverlappingInputs(0, &smallest, &largest,
+                                    &start_level_inputs_.files);
+
+    // If we include more L0 files in the same compaction run it can
+    // cause the 'smallest' and 'largest' key to get extended to a
+    // larger range. So, re-invoke GetRange to get the new key range
+    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
+    if (compaction_picker_->IsRangeInCompaction(
+            vstorage_, &smallest, &largest, output_level_, &parent_index_)) {
+      return false;
+    }
+  }
+  assert(!start_level_inputs_.files.empty());
 
   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_, mutable_cf_options_.MaxFileSizeForLevel(output_level_),
+      mutable_cf_options_.max_compaction_bytes,
+      GetPathId(ioptions_, mutable_cf_options_, output_level_),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level_, vstorage_->base_level()),
+      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.db_paths.empty());
+
+  // size remaining in the most recent path
+  uint64_t current_path_size = ioptions.db_paths[0].target_size;
+
+  uint64_t level_size;
+  int cur_level = 0;
+
+  level_size = mutable_cf_options.max_bytes_for_level_base;
+
+  // Last path is the fallback
+  while (p < ioptions.db_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;
+        level_size = static_cast<uint64_t>(
+            level_size * mutable_cf_options.max_bytes_for_level_multiplier);
+        cur_level++;
+        continue;
+      }
+    }
+    p++;
+    current_path_size = ioptions.db_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_);
+
+  // record the first file that is not yet compacted
+  int nextIndex = -1;
+
+  for (unsigned int i = vstorage_->NextCompactionIndex(start_level_);
+       i < file_size.size(); i++) {
+    int index = file_size[i];
+    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;
+    }
+
+    // remember the startIndex for the next call to PickCompaction
+    if (nextIndex == -1) {
+      nextIndex = i;
+    }
+
+    // Do not pick this file if its parents at level+1 are being compacted.
+    // Maybe we can avoid redoing this work in SetupOtherInputs
+    parent_index_ = -1;
+    if (compaction_picker_->IsRangeInCompaction(vstorage_, &f->smallest,
+                                                &f->largest, output_level_,
+                                                &parent_index_)) {
+      continue;
+    }
+    start_level_inputs_.files.push_back(f);
+    start_level_inputs_.level = start_level_;
+    base_index_ = index;
+    break;
+  }
+
+  // store where to start the iteration in the next call to PickCompaction
+  vstorage_->SetNextCompactionIndex(start_level_, nextIndex);
+
+  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;
+  }
+
+  size_t compact_bytes = level_files[0]->fd.file_size;
+  size_t compact_bytes_per_del_file = port::kMaxSizet;
+  // compaction range will be [0, span_len).
+  size_t span_len;
+  // pull in files until the amount of compaction work per deleted file begins
+  // increasing.
+  for (span_len = 1; span_len < level_files.size(); ++span_len) {
+    compact_bytes += level_files[span_len]->fd.file_size;
+    size_t new_compact_bytes_per_del_file = compact_bytes / span_len;
+    if (level_files[span_len]->being_compacted ||
+        new_compact_bytes_per_del_file > compact_bytes_per_del_file) {
+      break;
+    }
+    compact_bytes_per_del_file = new_compact_bytes_per_del_file;
+  }
+
+  if (span_len >= kMinFilesForIntraL0Compaction) {
+    start_level_inputs_.level = 0;
+    for (size_t i = 0; i < span_len; ++i) {
+      start_level_inputs_.files.push_back(level_files[i]);
+    }
+    return true;
+  }
+  return false;
+}
+}  // namespace
+
+Compaction* LevelCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
+                                 mutable_cf_options, ioptions_);
+  return builder.PickCompaction();
+}
+
+#ifndef ROCKSDB_LITE
+bool FIFOCompactionPicker::NeedsCompaction(
+    const VersionStorageInfo* vstorage) const {
+  const int kLevel0 = 0;
+  return vstorage->CompactionScore(kLevel0) >= 1;
+}
+
+Compaction* FIFOCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  assert(vstorage->num_levels() == 1);
+  const int kLevel0 = 0;
+  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  uint64_t total_size = 0;
+  for (const auto& file : level_files) {
+    total_size += file->fd.file_size;
+  }
+
+  if (total_size <= ioptions_.compaction_options_fifo.max_table_files_size ||
+      level_files.size() == 0) {
+    // total size not exceeded
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: nothing to do. Total size %" PRIu64
+                     ", max size %" PRIu64 "\n",
+                     cf_name.c_str(), total_size,
+                     ioptions_.compaction_options_fifo.max_table_files_size);
+    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;
+  // delete old files (FIFO)
+  for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
+    auto f = *ritr;
+    total_size -= f->compensated_file_size;
+    inputs[0].files.push_back(f);
+    char tmp_fsize[16];
+    AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] FIFO compaction: picking file %" PRIu64
+                                 " with size %s for deletion",
+                     cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
+    if (total_size <= ioptions_.compaction_options_fifo.max_table_files_size) {
+      break;
+    }
+  }
+  Compaction* c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
+      kNoCompression, {}, /* is manual */ false, vstorage->CompactionScore(0),
+      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
+  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,
+    uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
+    InternalKey** compaction_end, bool* manual_conflict) {
+  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;
+}
+
+#endif  // !ROCKSDB_LITE
+
 }  // namespace rocksdb

db/compaction_picker.h

@@ -15,7 +15,7 @@
 #include <unordered_set>
 #include <vector>
 
-#include "db/compaction/compaction.h"
+#include "db/compaction.h"
 #include "db/version_set.h"
 #include "options/cf_options.h"
 #include "rocksdb/env.h"
@@ -24,26 +24,11 @@
 
 namespace rocksdb {
 
-// The file contains an abstract class CompactionPicker, and its two
-// sub-classes LevelCompactionPicker and NullCompactionPicker, as
-// well as some helper functions used by them.
-
 class LogBuffer;
 class Compaction;
 class VersionStorageInfo;
 struct CompactionInputFiles;
 
-// An abstract class to pick compactions from an existing LSM-tree.
-//
-// Each compaction style inherits the class and implement the
-// interface to form automatic compactions. If NeedCompaction() is true,
-// then call PickCompaction() to find what files need to be compacted
-// and where to put the output files.
-//
-// Non-virtual functions CompactRange() and CompactFiles() are used to
-// pick files to compact based on users' DB::CompactRange() and
-// DB::CompactFiles() requests, respectively. There is little
-// compaction style specific logic for them.
 class CompactionPicker {
  public:
   CompactionPicker(const ImmutableCFOptions& ioptions,
@@ -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; }
@@ -105,10 +88,6 @@ class CompactionPicker {
 
   // Takes a list of CompactionInputFiles and returns a (manual) Compaction
   // object.
-  //
-  // Caller must provide a set of input files that has been passed through
-  // `SanitizeCompactionInputFiles` earlier. The lock should not be released
-  // between that call and this one.
   Compaction* CompactFiles(const CompactionOptions& compact_options,
                            const std::vector<CompactionInputFiles>& input_files,
                            int output_level, VersionStorageInfo* vstorage,
@@ -167,8 +146,7 @@ class CompactionPicker {
   // Will return false if it is impossible to apply this compaction.
   bool ExpandInputsToCleanCut(const std::string& cf_name,
                               VersionStorageInfo* vstorage,
-                              CompactionInputFiles* inputs,
-                              InternalKey** next_smallest = nullptr);
+                              CompactionInputFiles* inputs);
 
   // Returns true if any one of the parent files are being compacted
   bool IsRangeInCompaction(VersionStorageInfo* vstorage,
@@ -192,15 +170,6 @@ class CompactionPicker {
                        const CompactionInputFiles& output_level_inputs,
                        std::vector<FileMetaData*>* grandparents);
 
-  void PickFilesMarkedForCompaction(const std::string& cf_name,
-                                    VersionStorageInfo* vstorage,
-                                    int* start_level, int* output_level,
-                                    CompactionInputFiles* start_level_inputs);
-
-  bool GetOverlappingL0Files(VersionStorageInfo* vstorage,
-                             CompactionInputFiles* start_level_inputs,
-                             int output_level, int* parent_index);
-
   // Register this compaction in the set of running compactions
   void RegisterCompaction(Compaction* c);
 
@@ -236,9 +205,45 @@ class CompactionPicker {
   const InternalKeyComparator* const icmp_;
 };
 
+class LevelCompactionPicker : public CompactionPicker {
+ public:
+  LevelCompactionPicker(const ImmutableCFOptions& ioptions,
+                        const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+};
+
 #ifndef ROCKSDB_LITE
-// A dummy compaction that never triggers any automatic
-// compaction.
+class FIFOCompactionPicker : public CompactionPicker {
+ public:
+  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
+                       const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* version,
+                                     LogBuffer* log_buffer) override;
+
+  virtual Compaction* CompactRange(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, int input_level, int output_level,
+      uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
+      InternalKey** compaction_end, bool* manual_conflict) override;
+
+  // The maximum allowed output level.  Always returns 0.
+  virtual int MaxOutputLevel() const override { return 0; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+};
+
 class NullCompactionPicker : public CompactionPicker {
  public:
   NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -247,66 +252,36 @@ 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*/) 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);
-
 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 +3,24 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-
+#include "db/compaction_picker.h"
 #include <limits>
 #include <string>
 #include <utility>
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
+#include "db/compaction.h"
+#include "db/compaction_picker_universal.h"
 
-#include "logging/logging.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/logging.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
 class CountingLogger : public Logger {
  public:
   using Logger::Logv;
-  void Logv(const char* /*format*/, va_list /*ap*/) override { log_count++; }
+  virtual void Logv(const char* format, va_list ap) override { log_count++; }
   size_t log_count;
 };
 
@@ -57,16 +55,14 @@ class CompactionPickerTest : public testing::Test {
         log_buffer_(InfoLogLevel::INFO_LEVEL, &logger_),
         file_num_(1),
         vstorage_(nullptr) {
-    // 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();
@@ -85,17 +81,16 @@ 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;
     f->fd = FileDescriptor(file_number, path_id, file_size);
     f->smallest = InternalKey(smallest, smallest_seq, kTypeValue);
     f->largest = InternalKey(largest, largest_seq, kTypeValue);
-    f->fd.smallest_seqno = smallest_seq;
-    f->fd.largest_seqno = largest_seq;
-    f->compensated_file_size =
-        (compensated_file_size != 0) ? compensated_file_size : file_size;
+    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);
@@ -180,8 +175,6 @@ 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);
@@ -198,14 +191,13 @@ TEST_F(CompactionPickerTest, Level1Trigger2) {
   ASSERT_EQ(66U, compaction->input(0, 0)->fd.GetNumber());
   ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
   ASSERT_EQ(7U, compaction->input(1, 1)->fd.GetNumber());
-  ASSERT_EQ(uint64_t{1073741824}, compaction->OutputFilePreallocationSize());
 }
 
 TEST_F(CompactionPickerTest, LevelMaxScore) {
   NewVersionStorage(6, kCompactionStyleLevel);
   mutable_cf_options_.target_file_size_base = 10000000;
+  mutable_cf_options_.target_file_size_multiplier = 10;
   mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
-  mutable_cf_options_.RefreshDerivedOptions(ioptions_);
   Add(0, 1U, "150", "200", 1000000U);
   // Level 1 score 1.2
   Add(1, 66U, "150", "200", 6000000U);
@@ -226,9 +218,6 @@ 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) {
@@ -394,10 +383,10 @@ 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;
@@ -411,36 +400,6 @@ 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
@@ -449,10 +408,9 @@ 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);
@@ -481,7 +439,7 @@ 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);
@@ -509,7 +467,7 @@ 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.
@@ -525,7 +483,7 @@ 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);
   }
 }
@@ -534,10 +492,9 @@ 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);
@@ -557,8 +514,6 @@ 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) {
@@ -618,35 +573,6 @@ 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) {
@@ -897,80 +823,6 @@ 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;
@@ -1069,7 +921,7 @@ 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);
@@ -1159,8 +1011,7 @@ 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);
@@ -1169,16 +1020,16 @@ 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());
 }
 
@@ -1435,108 +1286,6 @@ 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);
-  Add(0, 2U, "151", "200", 200000U);
-  Add(0, 3U, "201", "250", 200000U);
-  Add(0, 4U, "251", "300", 200000U);
-  Add(0, 5U, "301", "350", 200000U);
-  Add(1, 6U, "100", "350", 200000U);
-  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(0U, 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);
-  Add(0, 2U, "151", "200", 200000U);
-  Add(0, 3U, "201", "250", 200000U);
-  Add(0, 4U, "251", "300", 200000U);
-  Add(0, 5U, "301", "350", 200000U);
-  Add(1, 6U, "100", "350", 200000U);
-  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(0U, compaction->output_level());
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/compaction_picker_universal.cc

@@ -7,21 +7,25 @@
 // 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_universal.h"
+#include "db/compaction_picker_universal.h"
 #ifndef ROCKSDB_LITE
 
-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <limits>
 #include <queue>
 #include <string>
 #include <utility>
 #include "db/column_family.h"
-#include "file/filename.h"
-#include "logging/log_buffer.h"
 #include "monitoring/statistics.h"
-#include "test_util/sync_point.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
 #include "util/random.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
 namespace rocksdb {
 namespace {
@@ -31,7 +35,7 @@ namespace {
 // and the index of the file in that level
 
 struct InputFileInfo {
-  InputFileInfo() : f(nullptr), level(0), index(0) {}
+  InputFileInfo() : f(nullptr) {}
 
   FileMetaData* f;
   size_t level;
@@ -93,17 +97,17 @@ void GetSmallestLargestSeqno(const std::vector<FileMetaData*>& files,
                              SequenceNumber* largest_seqno) {
   bool is_first = true;
   for (FileMetaData* f : files) {
-    assert(f->fd.smallest_seqno <= f->fd.largest_seqno);
+    assert(f->smallest_seqno <= f->largest_seqno);
     if (is_first) {
       is_first = false;
-      *smallest_seqno = f->fd.smallest_seqno;
-      *largest_seqno = f->fd.largest_seqno;
+      *smallest_seqno = f->smallest_seqno;
+      *largest_seqno = f->largest_seqno;
     } else {
-      if (f->fd.smallest_seqno < *smallest_seqno) {
-        *smallest_seqno = f->fd.smallest_seqno;
+      if (f->smallest_seqno < *smallest_seqno) {
+        *smallest_seqno = f->smallest_seqno;
       }
-      if (f->fd.largest_seqno > *largest_seqno) {
-        *largest_seqno = f->fd.largest_seqno;
+      if (f->largest_seqno > *largest_seqno) {
+        *largest_seqno = f->largest_seqno;
       }
     }
   }
@@ -158,13 +162,7 @@ bool UniversalCompactionPicker::IsInputFilesNonOverlapping(Compaction* c) {
 bool UniversalCompactionPicker::NeedsCompaction(
     const VersionStorageInfo* vstorage) const {
   const int kLevel0 = 0;
-  if (vstorage->CompactionScore(kLevel0) >= 1) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  return false;
+  return vstorage->CompactionScore(kLevel0) >= 1;
 }
 
 void UniversalCompactionPicker::SortedRun::Dump(char* out_buf,
@@ -206,8 +204,7 @@ void UniversalCompactionPicker::SortedRun::DumpSizeInfo(
 
 std::vector<UniversalCompactionPicker::SortedRun>
 UniversalCompactionPicker::CalculateSortedRuns(
-    const VersionStorageInfo& vstorage, const ImmutableCFOptions& /*ioptions*/,
-    const MutableCFOptions& mutable_cf_options) {
+    const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions) {
   std::vector<UniversalCompactionPicker::SortedRun> ret;
   for (FileMetaData* f : vstorage.LevelFiles(0)) {
     ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
@@ -221,8 +218,7 @@ UniversalCompactionPicker::CalculateSortedRuns(
     for (FileMetaData* f : vstorage.LevelFiles(level)) {
       total_compensated_size += f->compensated_file_size;
       total_size += f->fd.GetFileSize();
-      if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
-          true) {
+      if (ioptions.compaction_options_universal.allow_trivial_move == true) {
         if (f->being_compacted) {
           being_compacted = f->being_compacted;
         }
@@ -231,8 +227,7 @@ UniversalCompactionPicker::CalculateSortedRuns(
         // non-zero level, all the files should share the same being_compacted
         // value.
         // This assumption is only valid when
-        // mutable_cf_options.compaction_options_universal.allow_trivial_move is
-        // false
+        // ioptions.compaction_options_universal.allow_trivial_move is false
         assert(is_first || f->being_compacted == being_compacted);
       }
       if (is_first) {
@@ -250,18 +245,18 @@ UniversalCompactionPicker::CalculateSortedRuns(
 
 // Universal style of compaction. Pick files that are contiguous in
 // time-range to compact.
+//
 Compaction* UniversalCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
   const int kLevel0 = 0;
   double score = vstorage->CompactionScore(kLevel0);
   std::vector<SortedRun> sorted_runs =
-      CalculateSortedRuns(*vstorage, ioptions_, mutable_cf_options);
+      CalculateSortedRuns(*vstorage, ioptions_);
 
   if (sorted_runs.size() == 0 ||
-      (vstorage->FilesMarkedForCompaction().empty() &&
-       sorted_runs.size() < (unsigned int)mutable_cf_options
-                                .level0_file_num_compaction_trigger)) {
+      sorted_runs.size() <
+          (unsigned int)mutable_cf_options.level0_file_num_compaction_trigger) {
     ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: nothing to do\n",
                      cf_name.c_str());
     TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
@@ -275,81 +270,64 @@ Compaction* UniversalCompactionPicker::PickCompaction(
       cf_name.c_str(), sorted_runs.size(), vstorage->LevelSummary(&tmp));
 
   // Check for size amplification first.
-  Compaction* c = nullptr;
-  if (sorted_runs.size() >=
-      static_cast<size_t>(
-          mutable_cf_options.level0_file_num_compaction_trigger)) {
-    if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options,
-                                           vstorage, score, sorted_runs,
-                                           log_buffer)) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
+  Compaction* c;
+  if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options, vstorage,
+                                         score, sorted_runs, log_buffer)) !=
+      nullptr) {
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
+                     cf_name.c_str());
+  } else {
+    // Size amplification is within limits. Try reducing read
+    // amplification while maintaining file size ratios.
+    unsigned int ratio = ioptions_.compaction_options_universal.size_ratio;
+
+    if ((c = PickCompactionToReduceSortedRuns(
+             cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
+             sorted_runs, log_buffer)) != nullptr) {
+      ROCKS_LOG_BUFFER(log_buffer,
+                       "[%s] Universal: compacting for size ratio\n",
                        cf_name.c_str());
     } else {
-      // Size amplification is within limits. Try reducing read
-      // amplification while maintaining file size ratios.
-      unsigned int ratio =
-          mutable_cf_options.compaction_options_universal.size_ratio;
-
-      if ((c = PickCompactionToReduceSortedRuns(
-               cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
-               sorted_runs, log_buffer)) != nullptr) {
-        ROCKS_LOG_BUFFER(log_buffer,
-                         "[%s] Universal: compacting for size ratio\n",
-                         cf_name.c_str());
-      } else {
-        // Size amplification and file size ratios are within configured limits.
-        // If max read amplification is exceeding configured limits, then force
-        // compaction without looking at filesize ratios and try to reduce
-        // the number of files to fewer than level0_file_num_compaction_trigger.
-        // This is guaranteed by NeedsCompaction()
-        assert(sorted_runs.size() >=
-               static_cast<size_t>(
-                   mutable_cf_options.level0_file_num_compaction_trigger));
-        // Get the total number of sorted runs that are not being compacted
-        int num_sr_not_compacted = 0;
-        for (size_t i = 0; i < sorted_runs.size(); i++) {
-          if (sorted_runs[i].being_compacted == false) {
-            num_sr_not_compacted++;
-          }
+      // Size amplification and file size ratios are within configured limits.
+      // If max read amplification is exceeding configured limits, then force
+      // compaction without looking at filesize ratios and try to reduce
+      // the number of files to fewer than level0_file_num_compaction_trigger.
+      // This is guaranteed by NeedsCompaction()
+      assert(sorted_runs.size() >=
+             static_cast<size_t>(
+                 mutable_cf_options.level0_file_num_compaction_trigger));
+      // Get the total number of sorted runs that are not being compacted
+      int num_sr_not_compacted = 0;
+      for (size_t i = 0; i < sorted_runs.size(); i++) {
+        if (sorted_runs[i].being_compacted == false) {
+          num_sr_not_compacted++;
         }
+      }
 
-        // The number of sorted runs that are not being compacted is greater
-        // than the maximum allowed number of sorted runs
-        if (num_sr_not_compacted >
-            mutable_cf_options.level0_file_num_compaction_trigger) {
-          unsigned int num_files =
-              num_sr_not_compacted -
-              mutable_cf_options.level0_file_num_compaction_trigger + 1;
-          if ((c = PickCompactionToReduceSortedRuns(
-                   cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
-                   num_files, sorted_runs, log_buffer)) != nullptr) {
-            ROCKS_LOG_BUFFER(log_buffer,
-                             "[%s] Universal: compacting for file num -- %u\n",
-                             cf_name.c_str(), num_files);
-          }
+      // The number of sorted runs that are not being compacted is greater than
+      // the maximum allowed number of sorted runs
+      if (num_sr_not_compacted >
+          mutable_cf_options.level0_file_num_compaction_trigger) {
+        unsigned int num_files =
+            num_sr_not_compacted -
+            mutable_cf_options.level0_file_num_compaction_trigger + 1;
+        if ((c = PickCompactionToReduceSortedRuns(
+                 cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
+                 num_files, sorted_runs, log_buffer)) != nullptr) {
+          ROCKS_LOG_BUFFER(log_buffer,
+                           "[%s] Universal: compacting for file num -- %u\n",
+                           cf_name.c_str(), num_files);
         }
       }
     }
   }
-
-  if (c == nullptr) {
-    if ((c = PickDeleteTriggeredCompaction(cf_name, mutable_cf_options,
-                                           vstorage, score, sorted_runs,
-                                           log_buffer)) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer,
-                       "[%s] Universal: delete triggered compaction\n",
-                       cf_name.c_str());
-    }
-  }
-
   if (c == nullptr) {
     TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
                              nullptr);
     return nullptr;
   }
 
-  if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
-      true) {
+  if (ioptions_.compaction_options_universal.allow_trivial_move == true) {
     c->set_is_trivial_move(IsInputFilesNonOverlapping(c));
   }
 
@@ -361,11 +339,13 @@ Compaction* UniversalCompactionPicker::PickCompaction(
   size_t level_index = 0U;
   if (c->start_level() == 0) {
     for (auto f : *c->inputs(0)) {
-      assert(f->fd.smallest_seqno <= f->fd.largest_seqno);
+      assert(f->smallest_seqno <= f->largest_seqno);
       if (is_first) {
         is_first = false;
+      } else {
+        assert(prev_smallest_seqno > f->largest_seqno);
       }
-      prev_smallest_seqno = f->fd.smallest_seqno;
+      prev_smallest_seqno = f->smallest_seqno;
     }
     level_index = 1U;
   }
@@ -391,11 +371,10 @@ Compaction* UniversalCompactionPicker::PickCompaction(
   }
 #endif
   // update statistics
-  RecordInHistogram(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
-                    c->inputs(0)->size());
+  MeasureTime(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
+              c->inputs(0)->size());
 
   RegisterCompaction(c);
-  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
 
   TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
                            c);
@@ -403,8 +382,7 @@ Compaction* UniversalCompactionPicker::PickCompaction(
 }
 
 uint32_t UniversalCompactionPicker::GetPathId(
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, uint64_t file_size) {
+    const ImmutableCFOptions& ioptions, uint64_t file_size) {
   // Two conditions need to be satisfied:
   // (1) the target path needs to be able to hold the file's size
   // (2) Total size left in this and previous paths need to be not
@@ -421,12 +399,12 @@ uint32_t UniversalCompactionPicker::GetPathId(
   // that case. We need to improve it.
   uint64_t accumulated_size = 0;
   uint64_t future_size =
-      file_size *
-      (100 - mutable_cf_options.compaction_options_universal.size_ratio) / 100;
+      file_size * (100 - ioptions.compaction_options_universal.size_ratio) /
+      100;
   uint32_t p = 0;
-  assert(!ioptions.cf_paths.empty());
-  for (; p < ioptions.cf_paths.size() - 1; p++) {
-    uint64_t target_size = ioptions.cf_paths[p].target_size;
+  assert(!ioptions.db_paths.empty());
+  for (; p < ioptions.db_paths.size() - 1; p++) {
+    uint64_t target_size = ioptions.db_paths[p].target_size;
     if (target_size > file_size &&
         accumulated_size + (target_size - file_size) > future_size) {
       return p;
@@ -446,9 +424,9 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
     unsigned int max_number_of_files_to_compact,
     const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
   unsigned int min_merge_width =
-      mutable_cf_options.compaction_options_universal.min_merge_width;
+      ioptions_.compaction_options_universal.min_merge_width;
   unsigned int max_merge_width =
-      mutable_cf_options.compaction_options_universal.max_merge_width;
+      ioptions_.compaction_options_universal.max_merge_width;
 
   const SortedRun* sr = nullptr;
   bool done = false;
@@ -515,7 +493,7 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
       if (sz < static_cast<double>(succeeding_sr->size)) {
         break;
       }
-      if (mutable_cf_options.compaction_options_universal.stop_style ==
+      if (ioptions_.compaction_options_universal.stop_style ==
           kCompactionStopStyleSimilarSize) {
         // Similar-size stopping rule: also check the last picked file isn't
         // far larger than the next candidate file.
@@ -558,7 +536,7 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
   // size ratio of compression.
   bool enable_compression = true;
   int ratio_to_compress =
-      mutable_cf_options.compaction_options_universal.compression_size_percent;
+      ioptions_.compaction_options_universal.compression_size_percent;
   if (ratio_to_compress >= 0) {
     uint64_t total_size = 0;
     for (auto& sorted_run : sorted_runs) {
@@ -579,8 +557,7 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
   for (unsigned int i = 0; i < first_index_after; i++) {
     estimated_total_size += sorted_runs[i].size;
   }
-  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
+  uint32_t path_id = GetPathId(ioptions_, estimated_total_size);
   int start_level = sorted_runs[start_index].level;
   int output_level;
   if (first_index_after == sorted_runs.size()) {
@@ -591,13 +568,6 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
     output_level = sorted_runs[first_index_after].level - 1;
   }
 
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind &&
-      (output_level == vstorage->num_levels() - 1)) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
   std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
   for (size_t i = 0; i < inputs.size(); ++i) {
     inputs[i].level = start_level + static_cast<int>(i);
@@ -621,21 +591,17 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
 
   CompactionReason compaction_reason;
   if (max_number_of_files_to_compact == UINT_MAX) {
-    compaction_reason = CompactionReason::kUniversalSizeRatio;
-  } else {
     compaction_reason = CompactionReason::kUniversalSortedRunNum;
+  } else {
+    compaction_reason = CompactionReason::kUniversalSizeRatio;
   }
   return new Compaction(
       vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
-      MaxFileSizeForLevel(mutable_cf_options, output_level,
-                          kCompactionStyleUniversal),
-      LLONG_MAX, path_id,
+      mutable_cf_options.MaxFileSizeForLevel(output_level), LLONG_MAX, path_id,
       GetCompressionType(ioptions_, vstorage, mutable_cf_options, start_level,
                          1, enable_compression),
-      GetCompressionOptions(ioptions_, vstorage, start_level,
-                            enable_compression),
-      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      score, false /* deletion_compaction */, compaction_reason);
+      /* grandparents */ {}, /* is manual */ false, score,
+      false /* deletion_compaction */, compaction_reason);
 }
 
 // Look at overall size amplification. If size amplification
@@ -648,19 +614,15 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     VersionStorageInfo* vstorage, double score,
     const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
-  // percentage flexibility while reducing size amplification
-  uint64_t ratio = mutable_cf_options.compaction_options_universal
-                       .max_size_amplification_percent;
+  // percentage flexibilty while reducing size amplification
+  uint64_t ratio =
+      ioptions_.compaction_options_universal.max_size_amplification_percent;
 
   unsigned int candidate_count = 0;
   uint64_t candidate_size = 0;
   size_t start_index = 0;
   const SortedRun* sr = nullptr;
 
-  if (sorted_runs.back().being_compacted) {
-    return nullptr;
-  }
-
   // Skip files that are already being compacted
   for (size_t loop = 0; loop < sorted_runs.size() - 1; loop++) {
     sr = &sorted_runs[loop];
@@ -732,8 +694,7 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
   for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
     estimated_total_size += sorted_runs[loop].size;
   }
-  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
+  uint32_t path_id = GetPathId(ioptions_, estimated_total_size);
   int start_level = sorted_runs[start_index].level;
 
   std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
@@ -758,146 +719,17 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
                      cf_name.c_str(), file_num_buf);
   }
 
-  // output files at the bottom most level, unless it's reserved
-  int output_level = vstorage->num_levels() - 1;
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
   return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
-      MaxFileSizeForLevel(mutable_cf_options, output_level,
-                          kCompactionStyleUniversal),
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs),
+      vstorage->num_levels() - 1,
+      mutable_cf_options.MaxFileSizeForLevel(vstorage->num_levels() - 1),
       /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
-                         1),
-      GetCompressionOptions(ioptions_, vstorage, output_level),
-      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      score, false /* deletion_compaction */,
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options,
+                         vstorage->num_levels() - 1, 1),
+      /* grandparents */ {}, /* is manual */ false, score,
+      false /* deletion_compaction */,
       CompactionReason::kUniversalSizeAmplification);
 }
-
-// Pick files marked for compaction. Typically, files are marked by
-// CompactOnDeleteCollector due to the presence of tombstones.
-Compaction* UniversalCompactionPicker::PickDeleteTriggeredCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, double score,
-    const std::vector<SortedRun>& /*sorted_runs*/, LogBuffer* /*log_buffer*/) {
-  CompactionInputFiles start_level_inputs;
-  int output_level;
-  std::vector<CompactionInputFiles> inputs;
-
-  if (vstorage->num_levels() == 1) {
-    // This is single level universal. Since we're basically trying to reclaim
-    // space by processing files marked for compaction due to high tombstone
-    // density, let's do the same thing as compaction to reduce size amp which
-    // has the same goals.
-    bool compact = false;
-
-    start_level_inputs.level = 0;
-    start_level_inputs.files.clear();
-    output_level = 0;
-    for (FileMetaData* f : vstorage->LevelFiles(0)) {
-      if (f->marked_for_compaction) {
-        compact = true;
-      }
-      if (compact) {
-        start_level_inputs.files.push_back(f);
-      }
-    }
-    if (start_level_inputs.size() <= 1) {
-      // If only the last file in L0 is marked for compaction, ignore it
-      return nullptr;
-    }
-    inputs.push_back(start_level_inputs);
-  } else {
-    int start_level;
-
-    // For multi-level universal, the strategy is to make this look more like
-    // leveled. We pick one of the files marked for compaction and compact with
-    // overlapping files in the adjacent level.
-    PickFilesMarkedForCompaction(cf_name, vstorage, &start_level, &output_level,
-                                 &start_level_inputs);
-    if (start_level_inputs.empty()) {
-      return nullptr;
-    }
-
-    // Pick the first non-empty level after the start_level
-    for (output_level = start_level + 1; output_level < vstorage->num_levels();
-         output_level++) {
-      if (vstorage->NumLevelFiles(output_level) != 0) {
-        break;
-      }
-    }
-
-    // If all higher levels are empty, pick the highest level as output level
-    if (output_level == vstorage->num_levels()) {
-      if (start_level == 0) {
-        output_level = vstorage->num_levels() - 1;
-      } else {
-        // If start level is non-zero and all higher levels are empty, this
-        // compaction will translate into a trivial move. Since the idea is
-        // to reclaim space and trivial move doesn't help with that, we
-        // skip compaction in this case and return nullptr
-        return nullptr;
-      }
-    }
-    if (ioptions_.allow_ingest_behind &&
-        output_level == vstorage->num_levels() - 1) {
-      assert(output_level > 1);
-      output_level--;
-    }
-
-    if (output_level != 0) {
-      if (start_level == 0) {
-        if (!GetOverlappingL0Files(vstorage, &start_level_inputs, output_level,
-                                   nullptr)) {
-          return nullptr;
-        }
-      }
-
-      CompactionInputFiles output_level_inputs;
-      int parent_index = -1;
-
-      output_level_inputs.level = output_level;
-      if (!SetupOtherInputs(cf_name, mutable_cf_options, vstorage,
-                            &start_level_inputs, &output_level_inputs,
-                            &parent_index, -1)) {
-        return nullptr;
-      }
-      inputs.push_back(start_level_inputs);
-      if (!output_level_inputs.empty()) {
-        inputs.push_back(output_level_inputs);
-      }
-      if (FilesRangeOverlapWithCompaction(inputs, output_level)) {
-        return nullptr;
-      }
-    } else {
-      inputs.push_back(start_level_inputs);
-    }
-  }
-
-  uint64_t estimated_total_size = 0;
-  // Use size of the output level as estimated file size
-  for (FileMetaData* f : vstorage->LevelFiles(output_level)) {
-    estimated_total_size += f->fd.GetFileSize();
-  }
-  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
-  return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
-      MaxFileSizeForLevel(mutable_cf_options, output_level,
-                          kCompactionStyleUniversal),
-      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
-                         1),
-      GetCompressionOptions(ioptions_, vstorage, output_level),
-      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ true,
-      score, false /* deletion_compaction */,
-      CompactionReason::kFilesMarkedForCompaction);
-}
 }  // namespace rocksdb
 
 #endif  // !ROCKSDB_LITE

db/compaction_picker_universal.h

@@ -10,7 +10,7 @@
 #pragma once
 #ifndef ROCKSDB_LITE
 
-#include "db/compaction/compaction_picker.h"
+#include "db/compaction_picker.h"
 
 namespace rocksdb {
 class UniversalCompactionPicker : public CompactionPicker {
@@ -73,11 +73,6 @@ class UniversalCompactionPicker : public CompactionPicker {
       VersionStorageInfo* vstorage, double score,
       const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
 
-  Compaction* PickDeleteTriggeredCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, double score,
-      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
-
   // Used in universal compaction when the enabled_trivial_move
   // option is set. Checks whether there are any overlapping files
   // in the input. Returns true if the input files are non
@@ -85,13 +80,11 @@ class UniversalCompactionPicker : public CompactionPicker {
   bool IsInputFilesNonOverlapping(Compaction* c);
 
   static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
-      const MutableCFOptions& mutable_cf_options);
+      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,
-                            const MutableCFOptions& mutable_cf_options,
                             uint64_t file_size);
 };
 }  // namespace rocksdb

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

@@ -8,59 +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) {
-  std::unique_ptr<RandomAccessFile> file;
-  uint64_t file_size;
-  InternalKeyComparator internal_comparator(options.comparator);
-  ImmutableCFOptions ioptions(options);
-
-  Status s = ioptions.env->NewRandomAccessFile(file_path, &file, env_options);
-  if (s.ok()) {
-    s = ioptions.env->GetFileSize(file_path, &file_size);
-  } else {
-    return s;
-  }
-  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(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

@@ -13,23 +13,20 @@
 
 #include <errno.h>
 #include <fcntl.h>
-#include <cinttypes>
+#include <inttypes.h>
 #include <sys/stat.h>
 #include <sys/types.h>
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "file/filename.h"
 #include "rocksdb/cache.h"
-#include "rocksdb/convenience.h"
 #include "rocksdb/env.h"
 #include "rocksdb/table.h"
 #include "rocksdb/write_batch.h"
-#include "table/block_based/block_based_table_builder.h"
-#include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/filename.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
@@ -39,7 +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_;
 
@@ -50,7 +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;
@@ -62,9 +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() {
@@ -155,7 +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) {
@@ -182,9 +179,6 @@ class CorruptionTest : public testing::Test {
     }
     s = WriteStringToFile(Env::Default(), contents, fname);
     ASSERT_TRUE(s.ok()) << s.ToString();
-    Options options;
-    EnvOptions env_options;
-    ASSERT_NOK(VerifySstFileChecksum(options, env_options, fname));
   }
 
   void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
@@ -219,7 +213,7 @@ class CorruptionTest : public testing::Test {
         return;
       }
     }
-    FAIL() << "no file found at level";
+    ASSERT_TRUE(false) << "no file found at level";
   }
 
 
@@ -318,7 +312,6 @@ TEST_F(CorruptionTest, TableFile) {
 
   Corrupt(kTableFile, 100, 1);
   Check(99, 99);
-  ASSERT_NOK(dbi->VerifyChecksum());
 }
 
 TEST_F(CorruptionTest, TableFileIndexData) {
@@ -334,11 +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) {
@@ -398,12 +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) {
@@ -435,7 +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;
@@ -457,7 +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)));
@@ -469,39 +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(std::move(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;
@@ -520,7 +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();
@@ -545,7 +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 +5,15 @@
 
 #ifndef ROCKSDB_LITE
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "table/cuckoo/cuckoo_table_factory.h"
-#include "table/cuckoo/cuckoo_table_reader.h"
+#include "table/cuckoo_table_factory.h"
+#include "table/cuckoo_table_reader.h"
 #include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 
@@ -25,13 +25,13 @@ class CuckooTableDBTest : public testing::Test {
 
  public:
   CuckooTableDBTest() : env_(Env::Default()) {
-    dbname_ = test::PerThreadDBPath("cuckoo_table_db_test");
+    dbname_ = test::TmpDir() + "/cuckoo_table_db_test";
     EXPECT_OK(DestroyDB(dbname_, Options()));
     db_ = nullptr;
     Reopen();
   }
 
-  ~CuckooTableDBTest() override {
+  ~CuckooTableDBTest() {
     delete db_;
     EXPECT_OK(DestroyDB(dbname_, Options()));
   }
@@ -241,7 +241,7 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
 
   // Write 28 values, each 10016 B ~ 10KB
   for (int idx = 0; idx < 28; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + char(idx))));
+    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
   }
   dbfull()->TEST_WaitForFlushMemTable();
   ASSERT_EQ("1", FilesPerLevel());
@@ -250,7 +250,7 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
                               true /* disallow trivial move */);
   ASSERT_EQ("0,2", FilesPerLevel());
   for (int idx = 0; idx < 28; ++idx) {
-    ASSERT_EQ(std::string(10000, 'a' + char(idx)), Get(Key(idx)));
+    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
   }
 }
 
@@ -271,14 +271,14 @@ TEST_F(CuckooTableDBTest, SameKeyInsertedInTwoDifferentFilesAndCompacted) {
 
   // Generate one more file in level-0, and should trigger level-0 compaction
   for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + char(idx))));
+    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
   }
   dbfull()->TEST_WaitForFlushMemTable();
   dbfull()->TEST_CompactRange(0, nullptr, nullptr);
 
   ASSERT_EQ("0,1", FilesPerLevel());
   for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_EQ(std::string(10000, 'a' + char(idx)), Get(Key(idx)));
+    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
   }
 }
 
@@ -320,20 +320,14 @@ 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;
 }

db/db_blob_index_test.cc

@@ -1,410 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include <functional>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "db/column_family.h"
-#include "db/db_iter.h"
-#include "db/db_test_util.h"
-#include "db/dbformat.h"
-#include "db/write_batch_internal.h"
-#include "port/port.h"
-#include "port/stack_trace.h"
-#include "util/string_util.h"
-#include "utilities/merge_operators.h"
-
-namespace rocksdb {
-
-// kTypeBlobIndex is a value type used by BlobDB only. The base rocksdb
-// should accept the value type on write, and report not supported value
-// for reads, unless caller request for it explicitly. The base rocksdb
-// doesn't understand format of actual blob index (the value).
-class DBBlobIndexTest : public DBTestBase {
- public:
-  enum Tier {
-    kMemtable = 0,
-    kImmutableMemtables = 1,
-    kL0SstFile = 2,
-    kLnSstFile = 3,
-  };
-  const std::vector<Tier> kAllTiers = {Tier::kMemtable,
-                                       Tier::kImmutableMemtables,
-                                       Tier::kL0SstFile, Tier::kLnSstFile};
-
-  DBBlobIndexTest() : DBTestBase("/db_blob_index_test") {}
-
-  ColumnFamilyHandle* cfh() { return dbfull()->DefaultColumnFamily(); }
-
-  ColumnFamilyData* cfd() {
-    return reinterpret_cast<ColumnFamilyHandleImpl*>(cfh())->cfd();
-  }
-
-  Status PutBlobIndex(WriteBatch* batch, const Slice& key,
-                      const Slice& blob_index) {
-    return WriteBatchInternal::PutBlobIndex(batch, cfd()->GetID(), key,
-                                            blob_index);
-  }
-
-  Status Write(WriteBatch* batch) {
-    return dbfull()->Write(WriteOptions(), batch);
-  }
-
-  std::string GetImpl(const Slice& key, bool* is_blob_index = nullptr,
-                      const Snapshot* snapshot = nullptr) {
-    ReadOptions read_options;
-    read_options.snapshot = snapshot;
-    PinnableSlice value;
-    auto s = dbfull()->GetImpl(read_options, cfh(), key, &value,
-                               nullptr /*value_found*/, nullptr /*callback*/,
-                               is_blob_index);
-    if (s.IsNotFound()) {
-      return "NOT_FOUND";
-    }
-    if (s.IsNotSupported()) {
-      return "NOT_SUPPORTED";
-    }
-    if (!s.ok()) {
-      return s.ToString();
-    }
-    return value.ToString();
-  }
-
-  std::string GetBlobIndex(const Slice& key,
-                           const Snapshot* snapshot = nullptr) {
-    bool is_blob_index = false;
-    std::string value = GetImpl(key, &is_blob_index, snapshot);
-    if (!is_blob_index) {
-      return "NOT_BLOB";
-    }
-    return value;
-  }
-
-  ArenaWrappedDBIter* GetBlobIterator() {
-    return dbfull()->NewIteratorImpl(
-        ReadOptions(), cfd(), dbfull()->GetLatestSequenceNumber(),
-        nullptr /*read_callback*/, true /*allow_blob*/);
-  }
-
-  Options GetTestOptions() {
-    Options options;
-    options.create_if_missing = true;
-    options.num_levels = 2;
-    options.disable_auto_compactions = true;
-    // Disable auto flushes.
-    options.max_write_buffer_number = 10;
-    options.min_write_buffer_number_to_merge = 10;
-    options.merge_operator = MergeOperators::CreateStringAppendOperator();
-    return options;
-  }
-
-  void MoveDataTo(Tier tier) {
-    switch (tier) {
-      case Tier::kMemtable:
-        break;
-      case Tier::kImmutableMemtables:
-        ASSERT_OK(dbfull()->TEST_SwitchMemtable());
-        break;
-      case Tier::kL0SstFile:
-        ASSERT_OK(Flush());
-        break;
-      case Tier::kLnSstFile:
-        ASSERT_OK(Flush());
-        ASSERT_OK(Put("a", "dummy"));
-        ASSERT_OK(Put("z", "dummy"));
-        ASSERT_OK(Flush());
-        ASSERT_OK(
-            dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-#ifndef ROCKSDB_LITE
-        ASSERT_EQ("0,1", FilesPerLevel());
-#endif  // !ROCKSDB_LITE
-        break;
-    }
-  }
-};
-
-// Should be able to write kTypeBlobIndex to memtables and SST files.
-TEST_F(DBBlobIndexTest, Write) {
-  for (auto tier : kAllTiers) {
-    DestroyAndReopen(GetTestOptions());
-    for (int i = 1; i <= 5; i++) {
-      std::string index = ToString(i);
-      WriteBatch batch;
-      ASSERT_OK(PutBlobIndex(&batch, "key" + index, "blob" + index));
-      ASSERT_OK(Write(&batch));
-    }
-    MoveDataTo(tier);
-    for (int i = 1; i <= 5; i++) {
-      std::string index = ToString(i);
-      ASSERT_EQ("blob" + index, GetBlobIndex("key" + index));
-    }
-  }
-}
-
-// Get should be able to return blob index if is_blob_index is provided,
-// otherwise return Status::NotSupported status.
-TEST_F(DBBlobIndexTest, Get) {
-  for (auto tier : kAllTiers) {
-    DestroyAndReopen(GetTestOptions());
-    WriteBatch batch;
-    ASSERT_OK(batch.Put("key", "value"));
-    ASSERT_OK(PutBlobIndex(&batch, "blob_key", "blob_index"));
-    ASSERT_OK(Write(&batch));
-    MoveDataTo(tier);
-    // Verify normal value
-    bool is_blob_index = false;
-    PinnableSlice value;
-    ASSERT_EQ("value", Get("key"));
-    ASSERT_EQ("value", GetImpl("key"));
-    ASSERT_EQ("value", GetImpl("key", &is_blob_index));
-    ASSERT_FALSE(is_blob_index);
-    // Verify blob index
-    ASSERT_TRUE(Get("blob_key", &value).IsNotSupported());
-    ASSERT_EQ("NOT_SUPPORTED", GetImpl("blob_key"));
-    ASSERT_EQ("blob_index", GetImpl("blob_key", &is_blob_index));
-    ASSERT_TRUE(is_blob_index);
-  }
-}
-
-// Get should NOT return Status::NotSupported if blob index is updated with
-// a normal value.
-TEST_F(DBBlobIndexTest, Updated) {
-  for (auto tier : kAllTiers) {
-    DestroyAndReopen(GetTestOptions());
-    WriteBatch batch;
-    for (int i = 0; i < 10; i++) {
-      ASSERT_OK(PutBlobIndex(&batch, "key" + ToString(i), "blob_index"));
-    }
-    ASSERT_OK(Write(&batch));
-    // Avoid blob values from being purged.
-    const Snapshot* snapshot = dbfull()->GetSnapshot();
-    ASSERT_OK(Put("key1", "new_value"));
-    ASSERT_OK(Merge("key2", "a"));
-    ASSERT_OK(Merge("key2", "b"));
-    ASSERT_OK(Merge("key2", "c"));
-    ASSERT_OK(Delete("key3"));
-    ASSERT_OK(SingleDelete("key4"));
-    ASSERT_OK(Delete("key5"));
-    ASSERT_OK(Merge("key5", "a"));
-    ASSERT_OK(Merge("key5", "b"));
-    ASSERT_OK(Merge("key5", "c"));
-    ASSERT_OK(dbfull()->DeleteRange(WriteOptions(), cfh(), "key6", "key9"));
-    MoveDataTo(tier);
-    for (int i = 0; i < 10; i++) {
-      ASSERT_EQ("blob_index", GetBlobIndex("key" + ToString(i), snapshot));
-    }
-    ASSERT_EQ("new_value", Get("key1"));
-    ASSERT_EQ("NOT_SUPPORTED", GetImpl("key2"));
-    ASSERT_EQ("NOT_FOUND", Get("key3"));
-    ASSERT_EQ("NOT_FOUND", Get("key4"));
-    ASSERT_EQ("a,b,c", GetImpl("key5"));
-    for (int i = 6; i < 9; i++) {
-      ASSERT_EQ("NOT_FOUND", Get("key" + ToString(i)));
-    }
-    ASSERT_EQ("blob_index", GetBlobIndex("key9"));
-    dbfull()->ReleaseSnapshot(snapshot);
-  }
-}
-
-// Iterator should get blob value if allow_blob flag is set,
-// otherwise return Status::NotSupported status.
-TEST_F(DBBlobIndexTest, Iterate) {
-  const std::vector<std::vector<ValueType>> data = {
-      /*00*/ {kTypeValue},
-      /*01*/ {kTypeBlobIndex},
-      /*02*/ {kTypeValue},
-      /*03*/ {kTypeBlobIndex, kTypeValue},
-      /*04*/ {kTypeValue},
-      /*05*/ {kTypeValue, kTypeBlobIndex},
-      /*06*/ {kTypeValue},
-      /*07*/ {kTypeDeletion, kTypeBlobIndex},
-      /*08*/ {kTypeValue},
-      /*09*/ {kTypeSingleDeletion, kTypeBlobIndex},
-      /*10*/ {kTypeValue},
-      /*11*/ {kTypeMerge, kTypeMerge, kTypeMerge, kTypeBlobIndex},
-      /*12*/ {kTypeValue},
-      /*13*/
-      {kTypeMerge, kTypeMerge, kTypeMerge, kTypeDeletion, kTypeBlobIndex},
-      /*14*/ {kTypeValue},
-      /*15*/ {kTypeBlobIndex},
-      /*16*/ {kTypeValue},
-  };
-
-  auto get_key = [](int index) {
-    char buf[20];
-    snprintf(buf, sizeof(buf), "%02d", index);
-    return "key" + std::string(buf);
-  };
-
-  auto get_value = [&](int index, int version) {
-    return get_key(index) + "_value" + ToString(version);
-  };
-
-  auto check_iterator = [&](Iterator* iterator, Status::Code expected_status,
-                            const Slice& expected_value) {
-    ASSERT_EQ(expected_status, iterator->status().code());
-    if (expected_status == Status::kOk) {
-      ASSERT_TRUE(iterator->Valid());
-      ASSERT_EQ(expected_value, iterator->value());
-    } else {
-      ASSERT_FALSE(iterator->Valid());
-    }
-  };
-
-  auto create_normal_iterator = [&]() -> Iterator* {
-    return dbfull()->NewIterator(ReadOptions());
-  };
-
-  auto create_blob_iterator = [&]() -> Iterator* { return GetBlobIterator(); };
-
-  auto check_is_blob = [&](bool is_blob) {
-    return [is_blob](Iterator* iterator) {
-      ASSERT_EQ(is_blob,
-                reinterpret_cast<ArenaWrappedDBIter*>(iterator)->IsBlob());
-    };
-  };
-
-  auto verify = [&](int index, Status::Code expected_status,
-                    const Slice& forward_value, const Slice& backward_value,
-                    std::function<Iterator*()> create_iterator,
-                    std::function<void(Iterator*)> extra_check = nullptr) {
-    // Seek
-    auto* iterator = create_iterator();
-    ASSERT_OK(iterator->Refresh());
-    iterator->Seek(get_key(index));
-    check_iterator(iterator, expected_status, forward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-
-    // Next
-    iterator = create_iterator();
-    ASSERT_OK(iterator->Refresh());
-    iterator->Seek(get_key(index - 1));
-    ASSERT_TRUE(iterator->Valid());
-    iterator->Next();
-    check_iterator(iterator, expected_status, forward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-
-    // SeekForPrev
-    iterator = create_iterator();
-    ASSERT_OK(iterator->Refresh());
-    iterator->SeekForPrev(get_key(index));
-    check_iterator(iterator, expected_status, backward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-
-    // Prev
-    iterator = create_iterator();
-    iterator->Seek(get_key(index + 1));
-    ASSERT_TRUE(iterator->Valid());
-    iterator->Prev();
-    check_iterator(iterator, expected_status, backward_value);
-    if (extra_check) {
-      extra_check(iterator);
-    }
-    delete iterator;
-  };
-
-  for (auto tier : {Tier::kMemtable} /*kAllTiers*/) {
-    // Avoid values from being purged.
-    std::vector<const Snapshot*> snapshots;
-    DestroyAndReopen(GetTestOptions());
-
-    // fill data
-    for (int i = 0; i < static_cast<int>(data.size()); i++) {
-      for (int j = static_cast<int>(data[i].size()) - 1; j >= 0; j--) {
-        std::string key = get_key(i);
-        std::string value = get_value(i, j);
-        WriteBatch batch;
-        switch (data[i][j]) {
-          case kTypeValue:
-            ASSERT_OK(Put(key, value));
-            break;
-          case kTypeDeletion:
-            ASSERT_OK(Delete(key));
-            break;
-          case kTypeSingleDeletion:
-            ASSERT_OK(SingleDelete(key));
-            break;
-          case kTypeMerge:
-            ASSERT_OK(Merge(key, value));
-            break;
-          case kTypeBlobIndex:
-            ASSERT_OK(PutBlobIndex(&batch, key, value));
-            ASSERT_OK(Write(&batch));
-            break;
-          default:
-            assert(false);
-        };
-      }
-      snapshots.push_back(dbfull()->GetSnapshot());
-    }
-    ASSERT_OK(
-        dbfull()->DeleteRange(WriteOptions(), cfh(), get_key(15), get_key(16)));
-    snapshots.push_back(dbfull()->GetSnapshot());
-    MoveDataTo(tier);
-
-    // Normal iterator
-    verify(1, Status::kNotSupported, "", "", create_normal_iterator);
-    verify(3, Status::kNotSupported, "", "", create_normal_iterator);
-    verify(5, Status::kOk, get_value(5, 0), get_value(5, 0),
-           create_normal_iterator);
-    verify(7, Status::kOk, get_value(8, 0), get_value(6, 0),
-           create_normal_iterator);
-    verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
-           create_normal_iterator);
-    verify(11, Status::kNotSupported, "", "", create_normal_iterator);
-    verify(13, Status::kOk,
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           create_normal_iterator);
-    verify(15, Status::kOk, get_value(16, 0), get_value(14, 0),
-           create_normal_iterator);
-
-    // Iterator with blob support
-    verify(1, Status::kOk, get_value(1, 0), get_value(1, 0),
-           create_blob_iterator, check_is_blob(true));
-    verify(3, Status::kOk, get_value(3, 0), get_value(3, 0),
-           create_blob_iterator, check_is_blob(true));
-    verify(5, Status::kOk, get_value(5, 0), get_value(5, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(7, Status::kOk, get_value(8, 0), get_value(6, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(11, Status::kNotSupported, "", "", create_blob_iterator);
-    verify(13, Status::kOk,
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(15, Status::kOk, get_value(16, 0), get_value(14, 0),
-           create_blob_iterator, check_is_blob(false));
-
-    for (auto* snapshot : snapshots) {
-      dbfull()->ReleaseSnapshot(snapshot);
-    }
-  }
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}