In HISTORY.md Switch unreleased notes to 3.13

Summary: Prepare release notes for 3.13.

Test Plan: Text only

Reviewers: yhchiang, IslamAbdelRahman, rven, anthony

Reviewed By: anthony

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D43665

.gitignore

@@ -21,6 +21,13 @@ make_config.mk
 *.o-*
 *.swp
 *~
+*.vcxproj
+*.vcxproj.filters
+*.sln
+*.cmake
+CMakeCache.txt
+CMakeFiles/
+build/
 
 ldb
 manifest_dump
@@ -33,6 +40,8 @@ package/
 .phutil_module_cache
 unity
 tags
+rocksdb_dump
+rocksdb_undump
 
 java/out
 java/target

.travis.yml

@@ -14,6 +14,6 @@ before_install:
  - sudo dpkg -i libgflags-dev_2.0-1_amd64.deb
 # Lousy hack to disable use and testing of fallocate, which doesn't behave quite
 # as EnvPosixTest::AllocateTest expects within the Travis OpenVZ environment.
-script: OPT=-DTRAVIS V=1 make unity && make clean && OPT=-DTRAVIS V=1 make db_test && ./db_test
+script: OPT=-DTRAVIS V=1 make unity && make clean && OPT=-DTRAVIS V=1 make db_test && ./db_test && OPT=-DTRAVIS V=1 make clean jclean rocksdbjava jtest
 notifications:
     email: false

CMakeLists.txt

@@ -0,0 +1,347 @@
+# This cmake build is for Windows 64-bit only.
+#
+# Prerequisites:
+#     You must have Visual Studio 2013 Update 4 installed. Start the Developer Command Prompt window that is a part of Visual Studio installation.
+#     Run the build commands from within the Developer Command Prompt window to have paths to the compiler and runtime libraries set.
+#     You must have git.exe in your %PATH% environment variable.
+#
+# To build Rocksdb for Windows is as easy as 1-2-3-4-5:
+#
+# 1. Update paths to third-party libraries in thirdparty.inc file
+# 2. Create a new directory for build artifacts
+#        mkdir build
+#        cd build
+# 3. Run cmake to generate project files for Windows, add more options to enable required third-party libraries.
+#    See thirdparty.inc for more information.
+#        cmake -G "Visual Studio 12 Win64" .. <more options>
+# 4. Then build the project in debug mode (you may want to add /m:<N> flag to run msbuild in <N> parallel threads)
+#        msbuild ALL_BUILD.vcxproj
+# 5. And release mode (/m:<N> is also supported)
+#        msbuild ALL_BUILD.vcxproj /p:Configuration=Release
+#
+
+cmake_minimum_required(VERSION 2.6)
+project(rocksdb)
+
+include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
+
+execute_process(COMMAND $ENV{COMSPEC} " /C date /T" OUTPUT_VARIABLE DATE)
+execute_process(COMMAND $ENV{COMSPEC} " /C time /T" OUTPUT_VARIABLE TIME)
+string(REGEX REPLACE "(..)/(..)/..(..).*" "\\1/\\2/\\3" DATE ${DATE})
+string(REGEX REPLACE "(..):(.....).*" " \\1:\\2" TIME ${TIME})
+string(CONCAT GIT_DATE_TIME ${DATE} ${TIME})
+
+execute_process(COMMAND $ENV{COMSPEC} " /C git rev-parse HEAD 2>nil" OUTPUT_VARIABLE GIT_SHA)
+string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA ${GIT_SHA})
+
+set(BUILD_VERSION_CC ${CMAKE_CURRENT_SOURCE_DIR}/util/build_version.cc)
+
+add_custom_command(OUTPUT ${BUILD_VERSION_CC}
+    COMMAND echo "#include \"build_version.h\"" > ${BUILD_VERSION_CC}
+    COMMAND echo "const char* rocksdb_build_git_sha = \"rocksdb_build_git_sha:${GIT_SHA}\";" >> ${BUILD_VERSION_CC}
+    COMMAND echo "const char* rocksdb_build_git_datetime = \"rocksdb_build_git_datetime:${GIT_DATE_TIME}\";" >> ${BUILD_VERSION_CC}
+    COMMAND echo const char* rocksdb_build_compile_date = __DATE__\; >> ${BUILD_VERSION_CC}
+)
+
+add_custom_target(GenerateBuildVersion DEPENDS ${BUILD_VERSION_CC})
+
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /W3 /WX /EHsc /GS /fp:precise /Zc:wchar_t /Zc:forScope /Gd /TP /errorReport:queue")
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /wd4018 /wd4100 /wd4101 /wd4127 /wd4189 /wd4200 /wd4244 /wd4267 /wd4296 /wd4305 /wd4307 /wd4309 /wd4512 /wd4701 /wd4702 /wd4800 /wd4804 /wd4996")
+
+set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm /MDd")
+set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /O2 /Oi /Gm- /Gy /MD")
+
+set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} /DEBUG")
+
+add_definitions(-DWIN32 -DOS_WIN -D_MBCS -DWIN64)
+
+include_directories(${PROJECT_SOURCE_DIR})
+include_directories(${PROJECT_SOURCE_DIR}/include)
+include_directories(${PROJECT_SOURCE_DIR}/port)
+include_directories(${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
+
+set(ROCKSDB_LIBS rocksdblib${ARTIFACT_SUFFIX})
+set(THIRDPARTY_LIBS ${THIRDPARTY_LIBS} gtest)
+set(SYSTEM_LIBS Shlwapi.lib Rpcrt4.lib)
+
+set(LIBS ${ROCKSDB_LIBS} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+
+add_subdirectory(third-party/gtest-1.7.0/fused-src/gtest)
+
+set(SOURCES
+        db/builder.cc
+        db/c.cc
+        db/column_family.cc
+        db/compacted_db_impl.cc
+        db/compaction.cc
+        db/compaction_job.cc
+        db/compaction_picker.cc
+        db/convenience.cc
+        db/dbformat.cc
+        db/db_filesnapshot.cc
+        db/db_impl.cc
+        db/db_impl_debug.cc
+        db/db_impl_experimental.cc
+        db/db_impl_readonly.cc
+        db/db_iter.cc
+        db/event_helpers.cc
+        db/experimental.cc
+        db/filename.cc
+        db/file_indexer.cc
+        db/flush_job.cc
+        db/flush_scheduler.cc
+        db/forward_iterator.cc
+        db/internal_stats.cc
+        db/log_reader.cc
+        db/log_writer.cc
+        db/managed_iterator.cc
+        db/memtable.cc
+        db/memtable_allocator.cc
+        db/memtable_list.cc
+        db/merge_helper.cc
+        db/merge_operator.cc
+        db/repair.cc
+        db/slice.cc
+        db/table_cache.cc
+        db/table_properties_collector.cc
+        db/transaction_log_impl.cc
+        db/version_builder.cc
+        db/version_edit.cc
+        db/version_set.cc
+        db/wal_manager.cc
+        db/write_batch.cc
+        db/write_batch_base.cc
+        db/write_controller.cc
+        db/write_thread.cc
+        port/stack_trace.cc
+        port/win/env_win.cc
+        port/win/port_win.cc
+        port/win/win_logger.cc
+        table/adaptive_table_factory.cc
+        table/block.cc
+        table/block_based_filter_block.cc
+        table/block_based_table_builder.cc
+        table/block_based_table_factory.cc
+        table/block_based_table_reader.cc
+        table/block_builder.cc
+        table/block_hash_index.cc
+        table/block_prefix_index.cc
+        table/bloom_block.cc
+        table/cuckoo_table_builder.cc
+        table/cuckoo_table_factory.cc
+        table/cuckoo_table_reader.cc
+        table/flush_block_policy.cc
+        table/format.cc
+        table/full_filter_block.cc
+        table/get_context.cc
+        table/iterator.cc
+        table/merger.cc
+        table/meta_blocks.cc
+        table/mock_table.cc
+        table/plain_table_builder.cc
+        table/plain_table_factory.cc
+        table/plain_table_index.cc
+        table/plain_table_key_coding.cc
+        table/plain_table_reader.cc
+        table/table_properties.cc
+        table/two_level_iterator.cc
+        util/arena.cc
+        util/auto_roll_logger.cc
+        util/bloom.cc
+        util/build_version.cc
+        util/cache.cc
+        util/coding.cc
+        util/compaction_job_stats_impl.cc
+        util/comparator.cc
+        util/crc32c.cc
+        util/db_info_dumper.cc
+        util/delete_scheduler_impl.cc
+        util/db_test_util.cc
+        util/dynamic_bloom.cc
+        util/env.cc
+        util/env_hdfs.cc
+        util/event_logger.cc
+        util/file_util.cc
+        util/file_reader_writer.cc
+        util/filter_policy.cc
+        util/hash.cc
+        util/hash_cuckoo_rep.cc
+        util/hash_linklist_rep.cc
+        util/hash_skiplist_rep.cc
+        util/histogram.cc
+        util/instrumented_mutex.cc
+        util/iostats_context.cc
+        util/ldb_cmd.cc
+        util/ldb_tool.cc
+        util/logging.cc
+        util/log_buffer.cc
+        util/memenv.cc
+        util/mock_env.cc
+        util/murmurhash.cc
+        util/mutable_cf_options.cc
+        util/options.cc
+        util/options_builder.cc
+        util/options_helper.cc
+        util/perf_context.cc
+        util/perf_level.cc
+        util/rate_limiter.cc
+        util/skiplistrep.cc
+        util/slice.cc
+        util/sst_dump_tool.cc
+        util/statistics.cc
+        util/status.cc
+        util/string_util.cc
+        util/sync_point.cc
+        util/testharness.cc
+        util/testutil.cc
+        util/thread_local.cc
+        util/thread_status_impl.cc
+        util/thread_status_updater.cc
+        util/thread_status_updater_debug.cc
+        util/thread_status_util.cc
+        util/thread_status_util_debug.cc
+        util/vectorrep.cc
+        util/xfunc.cc
+        util/xxhash.cc
+        utilities/backupable/backupable_db.cc
+        utilities/checkpoint/checkpoint.cc
+        utilities/document/document_db.cc
+        utilities/document/json_document.cc
+        utilities/document/json_document_builder.cc
+        utilities/flashcache/flashcache.cc
+        utilities/geodb/geodb_impl.cc
+        utilities/leveldb_options/leveldb_options.cc
+        utilities/merge_operators/string_append/stringappend.cc
+        utilities/merge_operators/string_append/stringappend2.cc
+        utilities/merge_operators/put.cc
+        utilities/merge_operators/uint64add.cc
+        utilities/redis/redis_lists.cc
+        utilities/spatialdb/spatial_db.cc
+        utilities/table_properties_collectors/compact_on_deletion_collector.cc
+        utilities/transactions/optimistic_transaction_impl.cc        
+        utilities/transactions/optimistic_transaction_db_impl.cc
+        utilities/ttl/db_ttl_impl.cc
+        utilities/write_batch_with_index/write_batch_with_index.cc
+        utilities/write_batch_with_index/write_batch_with_index_internal.cc
+)
+
+add_library(rocksdblib${ARTIFACT_SUFFIX} ${SOURCES})
+set_target_properties(rocksdblib${ARTIFACT_SUFFIX} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/rocksdblib${ARTIFACT_SUFFIX}.pdb")
+add_dependencies(rocksdblib${ARTIFACT_SUFFIX} GenerateBuildVersion)
+
+add_library(rocksdb${ARTIFACT_SUFFIX} SHARED ${SOURCES})
+set_target_properties(rocksdb${ARTIFACT_SUFFIX} PROPERTIES COMPILE_FLAGS "-DROCKSDB_DLL -DROCKSDB_LIBRARY_EXPORTS /Fd${CMAKE_CFG_INTDIR}/rocksdb${ARTIFACT_SUFFIX}.pdb")
+add_dependencies(rocksdb${ARTIFACT_SUFFIX} GenerateBuildVersion)
+target_link_libraries(rocksdb${ARTIFACT_SUFFIX} ${LIBS})
+
+set(APPS
+        db/db_bench.cc
+        db/memtablerep_bench.cc
+        table/table_reader_bench.cc
+        tools/db_stress.cc
+        tools/db_repl_stress.cc
+        tools/sst_dump.cc
+        tools/dump/rocksdb_dump.cc
+        tools/dump/rocksdb_undump.cc
+        util/cache_bench.cc
+)
+
+set(TESTS
+        db/c_test.c
+        db/column_family_test.cc
+        db/compact_files_test.cc
+        db/compaction_job_test.cc
+        db/compaction_job_stats_test.cc
+        db/compaction_picker_test.cc
+        db/comparator_db_test.cc
+        db/corruption_test.cc
+        db/cuckoo_table_db_test.cc
+        db/db_iter_test.cc
+        db/db_test.cc
+        db/db_compaction_filter_test.cc
+        db/db_compaction_test.cc
+        db/db_dynamic_level_test.cc
+        db/db_inplace_update_test.cc
+        db/db_log_iter_test.cc
+        db/db_universal_compaction_test.cc
+        db/db_wal_test.cc
+        db/db_tailing_iter_test.cc
+        db/dbformat_test.cc
+        db/deletefile_test.cc
+        db/fault_injection_test.cc
+        db/file_indexer_test.cc
+        db/filename_test.cc
+        db/flush_job_test.cc
+        db/listener_test.cc
+        db/log_test.cc
+        db/memtable_list_test.cc
+        db/merge_test.cc
+        db/merge_helper_test.cc
+        db/perf_context_test.cc
+        db/plain_table_db_test.cc
+        db/prefix_test.cc
+        db/skiplist_test.cc
+        db/table_properties_collector_test.cc
+        db/version_builder_test.cc
+        db/version_edit_test.cc
+        db/version_set_test.cc
+        db/wal_manager_test.cc
+        db/write_batch_test.cc
+        db/write_callback_test.cc
+        db/write_controller_test.cc
+        table/block_based_filter_block_test.cc
+        table/block_hash_index_test.cc
+        table/block_test.cc
+        table/cuckoo_table_builder_test.cc
+        table/cuckoo_table_reader_test.cc
+        table/full_filter_block_test.cc
+        table/merger_test.cc
+        table/table_test.cc
+        tools/db_sanity_test.cc
+        tools/reduce_levels_test.cc
+        util/arena_test.cc
+        util/autovector_test.cc
+        util/auto_roll_logger_test.cc
+        util/bloom_test.cc
+        util/cache_test.cc
+        util/coding_test.cc
+        util/crc32c_test.cc
+        util/dynamic_bloom_test.cc
+        util/env_test.cc
+        util/event_logger_test.cc
+        util/filelock_test.cc
+        util/file_reader_writer_test.cc
+        util/heap_test.cc
+        util/histogram_test.cc
+        util/manual_compaction_test.cc
+        util/memenv_test.cc
+        util/mock_env_test.cc
+        util/options_test.cc
+        util/rate_limiter_test.cc
+        util/slice_transform_test.cc
+        util/sst_dump_test.cc
+        util/thread_list_test.cc
+        util/thread_local_test.cc
+        utilities/backupable/backupable_db_test.cc
+        utilities/checkpoint/checkpoint_test.cc
+        utilities/document/document_db_test.cc
+        utilities/document/json_document_test.cc
+        utilities/geodb/geodb_test.cc
+        utilities/merge_operators/string_append/stringappend_test.cc
+        utilities/redis/redis_lists_test.cc
+        utilities/spatialdb/spatial_db_test.cc
+        utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
+        utilities/transactions/optimistic_transaction_test.cc
+        utilities/ttl/ttl_test.cc
+        utilities/write_batch_with_index/write_batch_with_index_test.cc
+)
+
+set(EXES ${APPS} ${TESTS})
+
+foreach(sourcefile ${EXES})
+    string(REPLACE ".cc" "" exename ${sourcefile})
+    string(REPLACE ".c" "" exename ${exename})
+    string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
+    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+    target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${LIBS})
+endforeach(sourcefile ${EXES})

DUMP_FORMAT.md

@@ -0,0 +1,16 @@
+## RocksDB dump format
+
+The version 1 RocksDB dump format is fairly simple:
+
+1) The dump starts with the magic 8 byte identifier "ROCKDUMP"
+
+2) The magic is followed by an 8 byte big-endian version which is 0x00000001.
+
+3) Next are arbitrarily sized chunks of bytes prepended by 4 byte little endian number indicating how large each chunk is.
+
+4) The first chunk is special and is a json string indicating some things about the creation of this dump.  It contains the following keys:
+* database-path: The path of the database this dump was created from.
+* hostname: The hostname of the machine where the dump was created.
+* creation-time: Unix seconds since epoc when this dump was created.
+
+5) Following the info dump the slices paired into are key/value pairs.

HISTORY.md

@@ -1,11 +1,53 @@
 # Rocksdb Change Log
 
-## 3.11.0 (5/19/2015)
+## 3.13.0 (8/6/2015)
+### New Features
+* RollbackToSavePoint() in WriteBatch/WriteBatchWithIndex
+* Add NewCompactOnDeletionCollectorFactory() in utilities/table_properties_collectors, which allows rocksdb to mark a SST file as need-compaction when it observes at least D deletion entries in any N consecutive entries in that SST file.  Note that this feature depends on an experimental NeedCompact() API --- the result of this API will not persist after DB restart.
+* Add DBOptions::delete_scheduler. Use NewDeleteScheduler() in include/rocksdb/delete_scheduler.h to create a DeleteScheduler that can be shared among multiple RocksDB instances to control the file deletion rate of SST files that exist in the first db_path.
 
+### Public API Changes
+* Deprecated WriteOptions::timeout_hint_us. We no longer support write timeout. If you really need this option, talk to us and we might consider returning it.
+* Deprecated purge_redundant_kvs_while_flush option.
+* Removed BackupEngine::NewBackupEngine() and NewReadOnlyBackupEngine() that were deprecated in RocksDB 3.8. Please use BackupEngine::Open() instead.
+* Deprecated Compaction Filter V2. We are not aware of any existing use-cases. If you use this filter, your compile will break with RocksDB 3.13. Please let us know if you use it and we'll put it back in RocksDB 3.14.
+* Env::FileExists now returns a Status instead of a boolean
+* Add statistics::getHistogramString() to print detailed distribution of a histogram metric.
+* Add DBOptions::skip_stats_update_on_db_open.  When it is on, DB::Open() will run faster as it skips the random reads required for loading necessary stats from SST files to optimize compaction.
+
+## 3.12.0 (7/2/2015)
+### New Features
+* Added experimental support for optimistic transactions.  See include/rocksdb/utilities/optimistic_transaction.h for more info.
+* 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-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.
+
+### Public API changes
+* EventListener::OnFlushCompleted() now passes FlushJobInfo instead of a list of parameters.
+* DB::GetDbIdentity() is now a const function.  If this function is overridden in your application, be sure to also make GetDbIdentity() const to avoid compile error.
+* Move listeners from ColumnFamilyOptions to DBOptions.
+* Add max_write_buffer_number_to_maintain option
+* DB::CompactRange()'s parameter reduce_level is changed to change_level, to allow users to move levels to lower levels if allowed. It can be used to migrate a DB from options.level_compaction_dynamic_level_bytes=false to options.level_compaction_dynamic_level_bytes.true.
+* Change default value for options.compaction_filter_factory and options.compaction_filter_factory_v2 to nullptr instead of DefaultCompactionFilterFactory and DefaultCompactionFilterFactoryV2.
+* If CancelAllBackgroundWork is called without doing a flush after doing loads with WAL disabled, the changes which haven't been flushed before the call to CancelAllBackgroundWork will be lost.
+* WBWIIterator::Entry() now returns WriteEntry instead of `const WriteEntry&`
+* options.hard_rate_limit is deprecated.
+* When options.soft_rate_limit or options.level0_slowdown_writes_trigger is triggered, the way to slow down writes is changed to: write rate to DB is limited to to options.delayed_write_rate.
+* DB::GetApproximateSizes() adds a parameter to allow the estimation to include data in mem table, with default to be not to include. It is now only supported in skip list mem table.
+* DB::CompactRange() now accept CompactRangeOptions instead of multiple paramters. CompactRangeOptions is defined in include/rocksdb/options.h.
+* CompactRange() will now skip bottommost level compaction for level based compaction if there is no compaction filter, bottommost_level_compaction is introduced in CompactRangeOptions to control when it's possbile to skip bottommost level compaction. This mean that if you want the compaction to produce a single file you need to set bottommost_level_compaction to BottommostLevelCompaction::kForce.
+* Add Cache.GetPinnedUsage() to get the size of memory occupied by entries that are in use by the system.
+* DB:Open() will fail if the compression specified in Options is not linked with the binary. If you see this failure, recompile RocksDB with compression libraries present on your system. Also, previously our default compression was snappy. This behavior is now changed. Now, the default compression is snappy only if it's available on the system. If it isn't we change the default to kNoCompression.
+* We changed how we account for memory used in block cache. Previously, we only counted the sum of block sizes currently present in block cache. Now, we count the actual memory usage of the blocks. For example, a block of size 4.5KB will use 8KB memory with jemalloc. This might decrease your memory usage and possibly decrease performance. Increase block cache size if you see this happening after an upgrade.
+* Add BackupEngineImpl.options_.max_background_operations to specify the maximum number of operations that may be performed in parallel. Add support for parallelized backup and restore.
+* Add DB::SyncWAL() that does a WAL sync without blocking writers.
+
+## 3.11.0 (5/19/2015)
 ### New Features
 * Added a new API Cache::SetCapacity(size_t capacity) to dynamically change the maximum configured capacity of the cache. If the new capacity is less than the existing cache usage, the implementation will try to lower the usage by evicting the necessary number of elements following a strict LRU policy.
-
-### New Features
 * Added an experimental API for handling flashcache devices (blacklists background threads from caching their reads) -- NewFlashcacheAwareEnv
 * If universal compaction is used and options.num_levels > 1, compact files are tried to be stored in none-L0 with smaller files based on options.target_file_size_base. The limitation of DB size when using universal compaction is greatly mitigated by using more levels. You can set num_levels = 1 to make universal compaction behave as before. If you set num_levels > 1 and want to roll back to a previous version, you need to compact all files to a big file in level 0 (by setting target_file_size_base to be large and CompactRange(<cf_handle>, nullptr, nullptr, true, 0) and reopen the DB with the same version to rewrite the manifest, and then you can open it using previous releases.
 * More information about rocksdb background threads are available in Env::GetThreadList(), including the number of bytes read / written by a compaction job, mem-table size and current number of bytes written by a flush job and many more.  Check include/rocksdb/thread_status.h for more detail.

INSTALL.md

@@ -28,7 +28,7 @@ your make commands, like this: `PORTABLE=1 make static_lib`
       data compression.
 
 * All our tools depend on:
-  - [gflags](https://code.google.com/p/gflags/) - a library that handles
+  - [gflags](https://gflags.github.io/gflags/) - a library that handles
       command line flags processing. You can compile rocksdb library even
       if you don't have gflags installed.
 
@@ -75,8 +75,11 @@ your make commands, like this: `PORTABLE=1 make static_lib`
         * Update XCode:  run `xcode-select --install` (or install it from XCode App's settting).
         * Install via [homebrew](http://brew.sh/).
             * If you're first time developer in MacOS, you still need to run: `xcode-select --install` in your command line.
-            * run `brew tap homebrew/dupes; brew install gcc47 --use-llvm` to install gcc 4.7 (or higher).
+            * run `brew tap homebrew/versions; brew install gcc47 --use-llvm` to install gcc 4.7 (or higher).
     * run `brew install rocksdb`
 
 * **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**:
+  * Read the follow the instructions at CMakeLists.txt

Makefile

@@ -30,7 +30,7 @@ quoted_perl_command = $(subst ','\'',$(perl_command))
 # We use this debug level when developing RocksDB.
 # * DEBUG_LEVEL=0; this is the debug level we use for release. If you're
 # running rocksdb in production you most definitely want to compile RocksDB
-# with debug level 0. To compile with level 0, run `make shared_lib`, 
+# with debug level 0. To compile with level 0, run `make shared_lib`,
 # `make install-shared`, `make static_lib`, `make install-static` or
 # `make install`
 DEBUG_LEVEL=1
@@ -220,6 +220,14 @@ VALGRIND_OPTS = --error-exitcode=$(VALGRIND_ERROR) --leak-check=full
 TESTS = \
 	db_test \
 	db_iter_test \
+	db_log_iter_test \
+	db_compaction_filter_test \
+	db_compaction_test \
+	db_dynamic_level_test \
+	db_inplace_update_test \
+	db_tailing_iter_test \
+	db_universal_compaction_test \
+	db_wal_test \
 	block_hash_index_test \
 	autovector_test \
 	column_family_test \
@@ -231,6 +239,7 @@ TESTS = \
 	dynamic_bloom_test \
 	c_test \
 	cache_test \
+	checkpoint_test \
 	coding_test \
 	corruption_test \
 	crc32c_test \
@@ -240,6 +249,7 @@ TESTS = \
 	fault_injection_test \
 	filelock_test \
 	filename_test \
+	file_reader_writer_test \
 	block_based_filter_block_test \
 	full_filter_block_test \
 	histogram_test \
@@ -248,6 +258,7 @@ TESTS = \
 	memenv_test \
 	mock_env_test \
 	memtable_list_test \
+	merge_helper_test \
 	merge_test \
 	merger_test \
 	redis_test \
@@ -275,6 +286,7 @@ TESTS = \
 	thread_local_test \
 	geodb_test \
 	rate_limiter_test \
+	delete_scheduler_test \
 	options_test \
 	event_logger_test \
 	cuckoo_table_builder_test \
@@ -287,7 +299,12 @@ TESTS = \
 	thread_list_test \
 	sst_dump_test \
 	compact_files_test \
-	perf_context_test
+	perf_context_test \
+	optimistic_transaction_test \
+	write_callback_test \
+	heap_test \
+	compact_on_deletion_collector_test \
+	compaction_job_stats_test
 
 SUBSET :=  $(shell echo $(TESTS) |sed s/^.*$(ROCKSDBTESTS_START)/$(ROCKSDBTESTS_START)/)
 
@@ -296,7 +313,9 @@ TOOLS = \
 	db_sanity_test \
 	db_stress \
 	ldb \
-	db_repl_stress
+	db_repl_stress \
+	rocksdb_dump \
+	rocksdb_undump
 
 BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench
 
@@ -329,9 +348,16 @@ SHARED_MAJOR = $(ROCKSDB_MAJOR)
 SHARED_MINOR = $(ROCKSDB_MINOR)
 SHARED_PATCH = $(ROCKSDB_PATCH)
 SHARED1 = ${LIBNAME}.$(PLATFORM_SHARED_EXT)
+ifeq ($(PLATFORM), OS_MACOSX)
+SHARED_OSX = $(LIBNAME).$(SHARED_MAJOR)
+SHARED2 = $(SHARED_OSX).$(PLATFORM_SHARED_EXT)
+SHARED3 = $(SHARED_OSX).$(SHARED_MINOR).$(PLATFORM_SHARED_EXT)
+SHARED4 = $(SHARED_OSX).$(SHARED_MINOR).$(SHARED_PATCH).$(PLATFORM_SHARED_EXT)
+else
 SHARED2 = $(SHARED1).$(SHARED_MAJOR)
 SHARED3 = $(SHARED1).$(SHARED_MAJOR).$(SHARED_MINOR)
 SHARED4 = $(SHARED1).$(SHARED_MAJOR).$(SHARED_MINOR).$(SHARED_PATCH)
+endif
 SHARED = $(SHARED1) $(SHARED2) $(SHARED3) $(SHARED4)
 $(SHARED1): $(SHARED4)
 	ln -fs $(SHARED4) $(SHARED1)
@@ -342,7 +368,8 @@ $(SHARED3): $(SHARED4)
 endif
 
 $(SHARED4):
-	$(CXX) $(PLATFORM_SHARED_LDFLAGS)$(SHARED3) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(LIB_SOURCES) $(LDFLAGS) -o $@
+	$(CXX) $(PLATFORM_SHARED_LDFLAGS)$(SHARED3) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(LIB_SOURCES) \
+		$(LDFLAGS) -o $@
 
 endif  # PLATFORM_SHARED_EXT
 
@@ -362,11 +389,11 @@ dbg: $(LIBRARY) $(BENCHMARKS) $(TOOLS) $(TESTS)
 # creates static library and programs
 release:
 	$(MAKE) clean
-	OPT="-DNDEBUG -O2" $(MAKE) static_lib $(TOOLS) db_bench -j32
+	OPT="-DNDEBUG -O2" $(MAKE) static_lib $(TOOLS) db_bench
 
 coverage:
 	$(MAKE) clean
-	COVERAGEFLAGS="-fprofile-arcs -ftest-coverage" LDFLAGS+="-lgcov" $(MAKE) all check -j32
+	COVERAGEFLAGS="-fprofile-arcs -ftest-coverage" LDFLAGS+="-lgcov" $(MAKE) J=1 all check
 	cd coverage && ./coverage_test.sh
         # Delete intermediate files
 	find . -type f -regex ".*\.\(\(gcda\)\|\(gcno\)\)" -exec rm {} \;
@@ -497,18 +524,22 @@ CLEAN_FILES += t LOG $(TMPD)
 watch-log:
 	watch --interval=0 'sort -k7,7nr -k4,4gr LOG|$(quoted_perl_command)'
 
-# If GNU parallel is installed, run the tests in parallel,
+# If J != 1 and GNU parallel is installed, run the tests in parallel,
 # via the check_0 rule above.  Otherwise, run them sequentially.
 check: all
-	$(AM_V_GEN)case $$(parallel --gnu --help 2>/dev/null) in	\
-	  *'GNU Parallel'*)						\
-	    t=$$($(test_names));					\
-	    $(MAKE) T="$$t" TMPD=$(TMPD) check_0;;			\
-	  *)								\
-	    for t in $(TESTS); do					\
-	      echo "===== Running $$t"; ./$$t || exit 1; done;;		\
-	esac
+	$(AM_V_GEN)if test "$(J)" != 1                                  \
+	    && (parallel --gnu --help 2>/dev/null) |                    \
+	        grep -q 'GNU Parallel';                                 \
+	then                                                            \
+	    t=$$($(test_names));                                        \
+	    $(MAKE) T="$$t" TMPD=$(TMPD) check_0;                       \
+	else                                                            \
+	    for t in $(TESTS); do                                       \
+	      echo "===== Running $$t"; ./$$t || exit 1; done;          \
+	fi
 	rm -rf $(TMPD)
+	python tools/ldb_test.py
+	sh tools/rocksdb_dump_test.sh
 
 check_some: $(SUBSET) ldb_tests
 	for t in $(SUBSET); do echo "===== Running $$t"; ./$$t || exit 1; done
@@ -520,9 +551,11 @@ ldb_tests: ldb
 crash_test: whitebox_crash_test blackbox_crash_test
 
 blackbox_crash_test: db_stress
+	python -u tools/db_crashtest.py -s
 	python -u tools/db_crashtest.py
 
 whitebox_crash_test: db_stress
+	python -u tools/db_crashtest2.py -s
 	python -u tools/db_crashtest2.py
 
 asan_check:
@@ -542,8 +575,11 @@ valgrind_check: $(TESTS)
 	for t in $(filter-out skiplist_test,$(TESTS)); do \
 		stime=`date '+%s'`; \
 		$(VALGRIND_VER) $(VALGRIND_OPTS) ./$$t; \
-		if [ $$? -eq $(VALGRIND_ERROR) ] ; then \
+		ret_code=$$?; \
+		if [ $$ret_code -eq $(VALGRIND_ERROR) ] ; then \
 			echo $$t >> $(VALGRIND_DIR)/valgrind_failed_tests; \
+		elif [ $$ret_code -ne 0 ]; then \
+			exit $$ret_code; \
 		fi; \
 		etime=`date '+%s'`; \
 		echo $$t $$((etime - stime)) >> $(VALGRIND_DIR)/valgrind_tests_times; \
@@ -661,13 +697,36 @@ crc32c_test: util/crc32c_test.o $(LIBOBJECTS) $(TESTHARNESS)
 slice_transform_test: util/slice_transform_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+db_test: db/db_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
 
-db_test: db/db_test.o $(LIBOBJECTS) $(TESTHARNESS)
+db_log_iter_test: db/db_log_iter_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_compaction_filter_test: db/db_compaction_filter_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_compaction_test: db/db_compaction_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_dynamic_level_test: db/db_dynamic_level_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_inplace_update_test: db/db_inplace_update_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_tailing_iter_test: db/db_tailing_iter_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 db_iter_test: db/db_iter_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+db_universal_compaction_test: db/db_universal_compaction_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_wal_test: db/db_wal_test.o util/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 log_write_bench: util/log_write_bench.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK) $(pg)
 
@@ -689,6 +748,9 @@ prefix_test: db/prefix_test.o $(LIBOBJECTS) $(TESTHARNESS)
 backupable_db_test: utilities/backupable/backupable_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+checkpoint_test: utilities/checkpoint/checkpoint_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 document_db_test: utilities/document/document_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -710,6 +772,12 @@ flush_job_test: db/flush_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
 compaction_job_test: db/compaction_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+compaction_job_stats_test: db/compaction_job_stats_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+compact_on_deletion_collector_test: utilities/table_properties_collectors/compact_on_deletion_collector_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 wal_manager_test: db/wal_manager_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -725,9 +793,15 @@ fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
 rate_limiter_test: util/rate_limiter_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+delete_scheduler_test: util/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+file_reader_writer_test: util/file_reader_writer_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 block_based_filter_block_test: table/block_based_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -770,6 +844,9 @@ write_batch_test: db/write_batch_test.o $(LIBOBJECTS) $(TESTHARNESS)
 write_controller_test: db/write_controller_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+merge_helper_test: db/merge_helper_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 merge_test: db/merge_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -782,6 +859,12 @@ deletefile_test: db/deletefile_test.o $(LIBOBJECTS) $(TESTHARNESS)
 geodb_test: utilities/geodb/geodb_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
+	$(AM_LINK)
+
+rocksdb_undump: tools/dump/rocksdb_undump.o $(LIBOBJECTS)
+	$(AM_LINK)
+
 cuckoo_table_builder_test: table/cuckoo_table_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -797,9 +880,6 @@ listener_test: db/listener_test.o $(LIBOBJECTS) $(TESTHARNESS)
 thread_list_test: util/thread_list_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-compactor_test: utilities/compaction/compactor_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 compact_files_test: db/compact_files_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -815,6 +895,9 @@ sst_dump_test: util/sst_dump_test.o $(LIBOBJECTS) $(TESTHARNESS)
 memenv_test : util/memenv_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+optimistic_transaction_test: utilities/transactions/optimistic_transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 mock_env_test : util/mock_env_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -830,6 +913,12 @@ auto_roll_logger_test: util/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 memtable_list_test: db/memtable_list_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+write_callback_test: db/write_callback_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+heap_test: util/heap_test.o $(GTEST)
+	$(AM_LINK)
+
 sst_dump: tools/sst_dump.o $(LIBOBJECTS)
 	$(AM_LINK)
 
@@ -939,7 +1028,7 @@ rocksdbjavastatic: $(java_libobjects) libz.a libbz2.a libsnappy.a liblz4.a
 	$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC \
 	  -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) \
 	  $(java_libobjects) $(COVERAGEFLAGS) \
-	  libz.a libbz2.a libsnappy.a liblz4.a
+	  libz.a libbz2.a libsnappy.a liblz4.a $(LDFLAGS)
 	cd java/target;strip -S -x $(ROCKSDBJNILIB)
 	cd java;jar -cf target/$(ROCKSDB_JAR) HISTORY*.md
 	cd java/target;jar -uf $(ROCKSDB_JAR) $(ROCKSDBJNILIB)
@@ -972,7 +1061,7 @@ rocksdbjava: $(java_libobjects)
 jclean:
 	cd java;$(MAKE) clean;
 
-jtest:
+jtest: rocksdbjava
 	cd java;$(MAKE) sample;$(MAKE) test;
 
 jdb_bench:
@@ -980,7 +1069,7 @@ jdb_bench:
 
 commit-prereq:
 	$(MAKE) clean && $(MAKE) all check;
-	$(MAKE) clean && $(MAKE) rocksdbjava;
+	$(MAKE) clean && $(MAKE) jclean && $(MAKE) rocksdbjava;
 	$(MAKE) clean && USE_CLANG=1 $(MAKE) all;
 	$(MAKE) clean && OPT=-DROCKSDB_LITE $(MAKE) static_lib;
 

ROCKSDB_LITE.md

@@ -8,6 +8,7 @@ Some examples of the features disabled by ROCKSDB_LITE:
 * 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
 
 When adding a new big feature to RocksDB, please add ROCKSDB_LITE compile guard if:
 * Nobody from mobile really needs your feature,

USERS.md

@@ -15,7 +15,7 @@ Two different use cases at Linkedin are using RocksDB as a storage engine:
 Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasundaram: http://www.youtube.com/watch?v=plqVp_OnSzg
 
 ## Yahoo
-Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa.
+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 (still in development). They are using RocksDB as their storage engine. Check out their github: https://github.com/cockroachdb/cockroach

WINDOWS_PORT.md

@@ -0,0 +1,228 @@
+# Microsoft Contribution Notes
+
+## Contributors
+* Alexander Zinoviev https://github.com/zinoale
+* Dmitri Smirnov https://github.com/yuslepukhin
+* Praveen Rao  https://github.com/PraveenSinghRao
+* Sherlock Huang  https://github.com/SherlockNoMad
+
+## Introduction
+RocksDB is a well proven open source key-value persistent store, optimized for fast storage. It provides scalability with number of CPUs and storage IOPS, to support IO-bound, in-memory and write-once workloads, most importantly, to be flexible to allow for innovation.
+
+As Microsoft Bing team we have been continuously pushing hard to improve the scalability, efficiency of platform and eventually benefit Bing end-user satisfaction.  We would like to explore the opportunity to embrace open source, RocksDB here, to use, enhance and customize for our usage, and also contribute back to the RocksDB community. Herein, we are pleased to offer this RocksDB port for Windows platform.
+
+These notes describe some decisions and changes we had to make with regards to porting RocksDB on Windows. We hope this will help both reviewers and users of the Windows port.
+We are open for comments and improvements.
+
+## OS specifics
+All of the porting, testing and benchmarking was done on Windows Server 2012 R2 Datacenter 64-bit but to the best of our knowledge there is not a specific API we used during porting that is unsupported on other Windows OS after Vista.
+
+## Porting goals
+We strive to achieve the following goals:
+* make use of the existing porting interface of RocksDB
+* make minimum [WY2]modifications within platform independent code.
+* make all unit test pass both in debug and release builds. 
+  * Note: latest introduction of SyncPoint seems to disable running db_test in Release.
+* make performance on par with published benchmarks accounting for HW differences
+* we would like to keep the port code inline with the master branch with no forking
+
+## Build system
+We have chosen CMake as a widely accepted build system to build the Windows port. It is very fast and convenient. 
+
+At the same time it generates Visual Studio projects that are both usable from a command line and IDE.
+
+The top-level CMakeLists.txt file contains description of all targets and build rules. It also provides brief instructions on how to build the software for Windows. One more build related file is thirdparty.inc that also resides on the top level. This file must be edited to point to actual third party libraries location.
+We think that it would be beneficial to merge the existing make-based build system and the new cmake-based build system into a single one to use on all platforms.
+
+All building and testing was done for 64-bit. We have not conducted any testing for 32-bit and early reports indicate that it will not run on 32-bit.
+
+## C++ and STL notes
+We had to make some minimum changes within the portable files that either account for OS differences or the shortcomings of C++11 support in the current version of the MS compiler. Most or all of them are expected to be fixed in the upcoming compiler releases.
+
+We plan to use this port for our business purposes here at Bing and this provided business justification for this port. This also means, we do not have at present to choose the compiler version at will.
+
+* 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/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 `%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)
+* Union members that have non-trivial constructors were replaced to `char[]` in one place along with bug fixes (spatial experimental feature)
+* Zero-sized arrays are deemed a non-standard extension which we converted to 1 size array and that should work well for the purposes of these classes.
+* `std::chrono` lacks nanoseconds support (fixed in the upcoming release of the STL) and we had to use `QueryPerfCounter()` within env_win.cc
+* Function local statics initialization is still not safe. Used `std::once` to mitigate within WinEnv.
+
+## Windows Environments notes
+We endeavored to make it functionally on par with posix_env. This means we replicated the functionality of the thread pool and other things as precise as possible, including:
+* Replicate posix logic using std:thread primitives.
+* Implement all posix_env disk access functionality.
+* Set `use_os_buffer=false` to disable OS disk buffering for WinWritableFile and WinRandomAccessFile.
+* Replace `pread/pwrite` with `WriteFile/ReadFile` with `OVERLAPPED` structure.
+* Use `SetFileInformationByHandle` to compensate absence of `fallocate`.
+
+### In detail
+Even though Windows provides its own efficient thread-pool implementation we chose to replicate posix logic using `std::thread` primitives. This allows anyone to quickly detect any changes within the posix source code and replicate them within windows env. This has proven to work very well. At the same time for anyone who wishes to replace the built-in thread-pool can do so using RocksDB stackable environments.
+
+For disk access we implemented all of the functionality present within the posix_env which includes memory mapped files, random access, rate-limiter support etc.
+The `use_os_buffer` flag on Posix platforms currently denotes disabling read-ahead log via `fadvise` mechanism. Windows does not have `fadvise` system call. What is more, it implements disk cache in a way that differs from Linux greatly. It’s not an uncommon practice on Windows to perform un-buffered disk access to gain control of the memory consumption. We think that in our use case this may also be a good configuration option at the expense of disk throughput. To compensate one may increase the configured in-memory cache size instead. Thus we have chosen  `use_os_buffer=false` to disable OS disk buffering for `WinWritableFile` and `WinRandomAccessFile`. The OS imposes restrictions on the alignment of the disk offsets, buffers used and the amount of data that is read/written when accessing files in un-buffered mode. When the option is true, the classes behave in a standard way. This allows to perform writes and reads in cases when un-buffered access does not make sense such as WAL and MANIFEST.
+
+We have replaced `pread/pwrite` with `WriteFile/ReadFile` with `OVERLAPPED` structure so we can atomically seek to the position of the disk operation but still perform the operation synchronously. Thus we able to emulate that functionality of `pread/pwrite` reasonably well. The only difference is that the file pointer is not returned to its original position but that hardly matters given the random nature of access.
+
+We used `SetFileInformationByHandle` both to truncate files after writing a full final page to disk and to pre-allocate disk space for faster I/O thus compensating for the absence of `fallocate` although some differences remain. For example, the pre-allocated space is not filled with zeros like on Linux, however, on a positive note, the end of file position is also not modified after pre-allocation.
+
+RocksDB renames, copies and deletes files at will even though they may be opened with another handle at the same time. We had to relax and allow nearly all the concurrent access permissions possible.
+
+## Thread-Local Storage
+Thread-Local storage plays a significant role for RocksDB performance. Rather than creating a separate implementation we chose to create inline wrappers that forward `pthread_specific` calls to Windows `Tls` interfaces within `rocksdb::port` namespace. This leaves the existing meat of the logic in tact and unchanged and just as maintainable.
+
+To mitigate the lack of thread local storage cleanup on thread-exit we added a limited amount of windows specific code within the same thread_local.cc file that injects a cleanup callback into a `"__tls"` structure within `".CRT$XLB"` data segment. This approach guarantees that the callback is invoked regardless of whether RocksDB used within an executable, standalone DLL or within another DLL.
+
+## Jemalloc usage
+
+When RocksDB is used with Jemalloc the latter needs to be initialized before any of the C++ globals or statics. To accomplish that we injected an initialization routine into `".CRT$XCT"` that is automatically invoked by the runtime before initializing static objects. je-uninit is queued to `atexit()`. 
+
+The jemalloc redirecting `new/delete` global operators are used by the linker providing certain conditions are met. See build section in these notes.
+
+## Stack Trace and Unhandled Exception Handler
+
+We decided not to implement these two features because the hosting program as a rule has these two things in it.
+We experienced no inconveniences debugging issues in the debugger or analyzing process dumps if need be and thus we did not
+see this as a priority.
+
+## Performance results
+### Setup
+All of the benchmarks are run on the same set of machines. Here are the details of the test setup:
+* 2 Intel(R) Xeon(R) E5 2450 0 @ 2.10 GHz (total 16 cores)
+* 2 XK0480GDQPH SSD Device, total 894GB free disk
+* Machine has 128 GB of RAM
+* Operating System: Windows Server 2012 R2 Datacenter
+* 100 Million keys; each key is of size 10 bytes, each value is of size 800 bytes
+* total database size is ~76GB
+* The performance result is based on RocksDB 3.11.
+* The parameters used, unless specified, were exactly the same as published in the GitHub Wiki page. 
+
+### RocksDB on flash storage
+
+#### Test 1. Bulk Load of keys in Random Order
+
+Version 3.11 
+
+* Total Run Time: 17.6 min
+* Fillrandom: 5.480 micros/op 182465 ops/sec;  142.0 MB/s
+* Compact: 486056544.000 micros/op 0 ops/sec
+
+Version 3.10 
+
+* Total Run Time: 16.2 min 
+* Fillrandom: 5.018 micros/op 199269 ops/sec;  155.1 MB/s 
+* Compact: 441313173.000 micros/op 0 ops/sec; 
+
+
+#### Test 2. Bulk Load of keys in Sequential Order
+
+Version 3.11 
+
+* Fillseq: 4.944 micros/op 202k ops/sec;  157.4 MB/s
+
+Version 3.10
+
+* Fillseq: 4.105 micros/op 243.6k ops/sec;  189.6 MB/s 
+
+
+#### Test 3. Random Write
+
+Version 3.11 
+
+* Unbuffered I/O enabled
+* Overwrite: 52.661 micros/op 18.9k ops/sec;   14.8 MB/s
+
+Version 3.10
+
+* Unbuffered I/O enabled 
+* Overwrite: 52.661 micros/op 18.9k ops/sec; 
+
+
+#### Test 4. Random Read
+
+Version 3.11 
+
+* Unbuffered I/O enabled
+* Readrandom: 15.716 micros/op 63.6k ops/sec; 49.5 MB/s 
+
+Version 3.10
+
+* Unbuffered I/O enabled 
+* Readrandom: 15.548 micros/op 64.3k ops/sec; 
+
+
+#### Test 5. Multi-threaded read and single-threaded write
+
+Version 3.11
+
+* Unbuffered I/O enabled
+* Readwhilewriting: 25.128 micros/op 39.7k ops/sec; 
+
+Version 3.10
+
+* Unbuffered I/O enabled 
+* Readwhilewriting: 24.854 micros/op 40.2k ops/sec; 
+
+
+### RocksDB In Memory 
+
+#### Test 1. Point Lookup
+
+Version 3.11
+
+80K writes/sec
+* Write Rate Achieved: 40.5k write/sec;
+* Readwhilewriting: 0.314 micros/op 3187455 ops/sec;  364.8 MB/s (715454999 of 715454999 found)
+
+Version 3.10
+
+* Write Rate Achieved:  50.6k write/sec 
+* Readwhilewriting: 0.316 micros/op 3162028 ops/sec; (719576999 of 719576999 found) 
+
+
+*10K writes/sec*
+
+Version 3.11
+
+* Write Rate Achieved: 5.8k/s write/sec
+* Readwhilewriting: 0.246 micros/op 4062669 ops/sec;  464.9 MB/s (915481999 of 915481999 found)
+
+Version 3.10
+
+* Write Rate Achieved: 5.8k/s write/sec 
+* Readwhilewriting: 0.244 micros/op 4106253 ops/sec; (927986999 of 927986999 found) 
+
+
+#### Test 2. Prefix Range Query
+
+Version 3.11
+
+80K writes/sec
+* Write Rate Achieved:  46.3k/s write/sec
+* Readwhilewriting: 0.362 micros/op 2765052 ops/sec;  316.4 MB/s (611549999 of 611549999 found)
+
+Version 3.10
+
+* Write Rate Achieved: 45.8k/s write/sec 
+* Readwhilewriting: 0.317 micros/op 3154941 ops/sec; (708158999 of 708158999 found) 
+
+Version 3.11
+
+10K writes/sec
+* Write Rate Achieved: 5.78k write/sec
+* Readwhilewriting: 0.269 micros/op 3716692 ops/sec;  425.3 MB/s (837401999 of 837401999 found)
+
+Version 3.10
+
+* Write Rate Achieved: 5.7k write/sec 
+* Readwhilewriting: 0.261 micros/op 3830152 ops/sec; (863482999 of 863482999 found) 
+
+
+We think that there is still big room to improve the performance, which will be an ongoing effort for us.
+

build_tools/build_detect_platform

@@ -92,7 +92,7 @@ CROSS_COMPILE=
 PLATFORM_CCFLAGS=
 PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS"
 PLATFORM_SHARED_EXT="so"
-PLATFORM_SHARED_LDFLAGS="-shared -Wl,-soname -Wl,"
+PLATFORM_SHARED_LDFLAGS="-Wl,--no-as-needed -shared -Wl,-soname -Wl,"
 PLATFORM_SHARED_CFLAGS="-fPIC"
 PLATFORM_SHARED_VERSIONED=true
 
@@ -157,6 +157,7 @@ case "$TARGET_OS" in
         ;;
     Cygwin)
         PLATFORM=CYGWIN
+        PLATFORM_SHARED_CFLAGS=""
         PLATFORM_CXXFLAGS="-std=gnu++11"
         COMMON_FLAGS="$COMMON_FLAGS -DCYGWIN"
         if [ -z "$USE_CLANG" ]; then
@@ -293,6 +294,18 @@ EOF
             JAVA_LDFLAGS="$JAVA_LDFLAGS -ltcmalloc"
         fi
     fi
+
+    # Test whether malloc_usable_size is available
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <malloc.h>
+      int main() {
+        size_t res = malloc_usable_size(0);
+        return 0;
+      }
+EOF
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
+    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.

build_tools/dockerbuild.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+docker run -v $PWD:/rocks -w /rocks buildpack-deps make

build_tools/fb_compile_mongo.sh

@@ -0,0 +1,55 @@
+#!/bin/sh
+
+# fail early
+set -e
+
+if test -z $ROCKSDB_PATH; then
+  ROCKSDB_PATH=~/rocksdb
+fi
+source $ROCKSDB_PATH/build_tools/fbcode_config4.8.1.sh
+
+EXTRA_LDFLAGS=""
+
+if test -z $ALLOC; then
+  # default
+  ALLOC=tcmalloc
+elif [[ $ALLOC == "jemalloc" ]]; then
+  ALLOC=system
+  EXTRA_LDFLAGS+=" -Wl,--whole-archive $JEMALLOC_LIB -Wl,--no-whole-archive"
+fi
+
+# we need to force mongo to use static library, not shared
+STATIC_LIB_DEP_DIR='build/static_library_dependencies'
+test -d $STATIC_LIB_DEP_DIR || mkdir $STATIC_LIB_DEP_DIR
+test -h $STATIC_LIB_DEP_DIR/`basename $SNAPPY_LIBS` || ln -s $SNAPPY_LIBS $STATIC_LIB_DEP_DIR
+test -h $STATIC_LIB_DEP_DIR/`basename $LZ4_LIBS` || ln -s $LZ4_LIBS $STATIC_LIB_DEP_DIR
+
+EXTRA_LDFLAGS+=" -L $STATIC_LIB_DEP_DIR"
+
+set -x
+
+EXTRA_CMD=""
+if ! test -e version.json; then
+  # this is Mongo 3.0
+  EXTRA_CMD="--rocksdb \
+    --variant-dir=linux2/norm
+    --cxx=${CXX} \
+    --cc=${CC} \
+    --use-system-zlib"  # add this line back to normal code path
+                        # when https://jira.mongodb.org/browse/SERVER-19123 is resolved
+fi
+
+scons \
+  LINKFLAGS="$EXTRA_LDFLAGS $EXEC_LDFLAGS $PLATFORM_LDFLAGS" \
+  CCFLAGS="$CXXFLAGS -L $STATIC_LIB_DEP_DIR" \
+  LIBS="lz4 gcc stdc++" \
+  LIBPATH="$ROCKSDB_PATH" \
+  CPPPATH="$ROCKSDB_PATH/include" \
+  -j32 \
+  --allocator=$ALLOC \
+  --nostrip \
+  --opt=on \
+  --disable-minimum-compiler-version-enforcement \
+  --use-system-snappy \
+  --disable-warnings-as-errors \
+  $EXTRA_CMD $*

build_tools/fbcode_config.sh

@@ -18,19 +18,6 @@ GLIBC_REV=7397bed99280af5d9543439cdb7d018af7542720
 GLIBC_INCLUDE="/mnt/gvfs/third-party2/glibc/$GLIBC_REV/2.20/gcc-4.9-glibc-2.20/99df8fc/include"
 GLIBC_LIBS=" -L /mnt/gvfs/third-party2/glibc/$GLIBC_REV/2.20/gcc-4.9-glibc-2.20/99df8fc/lib"
 
-# snappy and zlib depend are bundled with MongoDB so we wan't to pick up the bundled headers when
-# building for it and disable block compressors supported by RocksDB but not used by MongoDB.
-
-if [[ -n $ROCKSDB_FOR_MONGO ]]; then
-
-MONGO_SRC="$ROCKSDB_FOR_MONGO/src/third_party"
-SNAPPY_INCLUDE=" -I $MONGO_SRC/snappy-1.1.2"
-CFLAGS+=" -DSNAPPY"
-ZLIB_INCLUDE=" -I $MONGO_SRC/zlib-1.2.8"
-CFLAGS+=" -DZLIB"
-
-else
-
 SNAPPY_INCLUDE=" -I /mnt/gvfs/third-party2/snappy/b0f269b3ca47770121aa159b99e1d8d2ab260e1f/1.0.3/gcc-4.9-glibc-2.20/c32916f/include/"
 
 if test -z $PIC_BUILD; then
@@ -56,7 +43,6 @@ if test -z $PIC_BUILD; then
   LZ4_LIBS=" /mnt/gvfs/third-party2/lz4/79d2943e2dd7208a3e0b06cf95e9f85f05fe9e1b/r124/gcc-4.9-glibc-2.20/4230243/lib/liblz4.a"
   CFLAGS+=" -DLZ4"
 fi
-fi
 
 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I /mnt/gvfs/third-party2/gflags/0fa60e2b88de3e469db6c482d6e6dac72f5d65f9/1.6/gcc-4.9-glibc-2.20/4230243/include/"
@@ -125,7 +111,7 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_FALLOCATE_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $GFLAGS_LIBS $NUMA_LIB"

build_tools/fbcode_config4.8.1.sh

@@ -35,8 +35,8 @@ GFLAGS_INCLUDE=" -I /mnt/gvfs/third-party2/gflags/1ad047a6e6f6673991918ecadc6708
 GFLAGS_LIBS=" /mnt/gvfs/third-party2/gflags/1ad047a6e6f6673991918ecadc670868205a243a/1.6/gcc-4.8.1-glibc-2.17/c3f970a/lib/libgflags.a"
 
 # location of jemalloc
-JEMALLOC_INCLUDE=" -I /mnt/gvfs/third-party2/jemalloc/c60d854f7824f334195fe7fd34b2bc9057e3c1f9/3.6.0/gcc-4.8.1-glibc-2.17/4d53c6f/include"
-JEMALLOC_LIB=" /mnt/gvfs/third-party2/jemalloc/c60d854f7824f334195fe7fd34b2bc9057e3c1f9/3.6.0/gcc-4.8.1-glibc-2.17/4d53c6f/lib/libjemalloc.a"
+JEMALLOC_INCLUDE=" -I /mnt/gvfs/third-party2/jemalloc/3691c776ac26dd8781e84f8888b6a0fbdbc0a9ed/dev/gcc-4.8.1-glibc-2.17/4d53c6f/include"
+JEMALLOC_LIB="/mnt/gvfs/third-party2/jemalloc/3691c776ac26dd8781e84f8888b6a0fbdbc0a9ed/dev/gcc-4.8.1-glibc-2.17/4d53c6f/lib/libjemalloc.a"
 
 # location of numa
 NUMA_REV=829d10dac0230f99cd7e1778869d2adf3da24b65
@@ -87,13 +87,14 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_FALLOCATE_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
 CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DNUMA"
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $GFLAGS_LIBS $NUMA_LIB"
 EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
+EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib"
 
 PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
 

db/builder.cc

@@ -21,6 +21,7 @@
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
 #include "table/block_based_table_builder.h"
+#include "util/file_reader_writer.h"
 #include "util/iostats_context_imp.h"
 #include "util/thread_status_util.h"
 #include "util/stop_watch.h"
@@ -34,7 +35,7 @@ TableBuilder* NewTableBuilder(
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
-    WritableFile* file, const CompressionType compression_type,
+    WritableFileWriter* file, const CompressionType compression_type,
     const CompressionOptions& compression_opts, const bool skip_filters) {
   return ioptions.table_factory->NewTableBuilder(
       TableBuilderOptions(ioptions, internal_comparator,
@@ -64,7 +65,7 @@ Status BuildTable(
   // If the sequence number of the smallest entry in the memtable is
   // smaller than the most recent snapshot, then we do not trigger
   // removal of duplicate/deleted keys as part of this builder.
-  bool purge = ioptions.purge_redundant_kvs_while_flush;
+  bool purge = true;
   if (earliest_seqno_in_memtable <= newest_snapshot) {
     purge = false;
   }
@@ -72,16 +73,22 @@ Status BuildTable(
   std::string fname = TableFileName(ioptions.db_paths, meta->fd.GetNumber(),
                                     meta->fd.GetPathId());
   if (iter->Valid()) {
-    unique_ptr<WritableFile> file;
-    s = env->NewWritableFile(fname, &file, env_options);
-    if (!s.ok()) {
-      return s;
-    }
-    file->SetIOPriority(io_priority);
+    TableBuilder* builder;
+    unique_ptr<WritableFileWriter> file_writer;
+    {
+      unique_ptr<WritableFile> file;
+      s = env->NewWritableFile(fname, &file, env_options);
+      if (!s.ok()) {
+        return s;
+      }
+      file->SetIOPriority(io_priority);
 
-    TableBuilder* builder = NewTableBuilder(
-        ioptions, internal_comparator, int_tbl_prop_collector_factories,
-        file.get(), compression, compression_opts);
+      file_writer.reset(new WritableFileWriter(std::move(file), env_options));
+
+      builder = NewTableBuilder(
+          ioptions, internal_comparator, int_tbl_prop_collector_factories,
+          file_writer.get(), compression, compression_opts);
+    }
 
     {
       // the first key is the smallest key
@@ -222,6 +229,7 @@ Status BuildTable(
     }
     if (s.ok()) {
       meta->fd.file_size = builder->FileSize();
+      meta->marked_for_compaction = builder->NeedCompact();
       assert(meta->fd.GetFileSize() > 0);
       if (table_properties) {
         *table_properties = builder->GetTableProperties();
@@ -231,16 +239,11 @@ Status BuildTable(
 
     // Finish and check for file errors
     if (s.ok() && !ioptions.disable_data_sync) {
-      if (ioptions.use_fsync) {
-        StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
-        s = file->Fsync();
-      } else {
-        StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
-        s = file->Sync();
-      }
+      StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
+      file_writer->Sync(ioptions.use_fsync);
     }
     if (s.ok()) {
-      s = file->Close();
+      s = file_writer->Close();
     }
 
     if (s.ok()) {

db/builder.h

@@ -29,14 +29,14 @@ class Iterator;
 class TableCache;
 class VersionEdit;
 class TableBuilder;
-class WritableFile;
+class WritableFileWriter;
 
 TableBuilder* NewTableBuilder(
     const ImmutableCFOptions& options,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
-    WritableFile* file, const CompressionType compression_type,
+    WritableFileWriter* file, const CompressionType compression_type,
     const CompressionOptions& compression_opts,
     const bool skip_filters = false);
 

db/c.cc

@@ -12,10 +12,11 @@
 #include "rocksdb/c.h"
 
 #include <stdlib.h>
-#include <unistd.h>
+#include "port/port.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/comparator.h"
+#include "rocksdb/convenience.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/filter_policy.h"
@@ -30,6 +31,7 @@
 #include "rocksdb/slice_transform.h"
 #include "rocksdb/table.h"
 #include "rocksdb/utilities/backupable_db.h"
+#include "utilities/merge_operators.h"
 
 using rocksdb::Cache;
 using rocksdb::ColumnFamilyDescriptor;
@@ -37,8 +39,6 @@ using rocksdb::ColumnFamilyHandle;
 using rocksdb::ColumnFamilyOptions;
 using rocksdb::CompactionFilter;
 using rocksdb::CompactionFilterFactory;
-using rocksdb::CompactionFilterV2;
-using rocksdb::CompactionFilterFactoryV2;
 using rocksdb::CompactionFilterContext;
 using rocksdb::CompactionOptionsFIFO;
 using rocksdb::Comparator;
@@ -53,6 +53,7 @@ using rocksdb::FlushOptions;
 using rocksdb::Iterator;
 using rocksdb::Logger;
 using rocksdb::MergeOperator;
+using rocksdb::MergeOperators;
 using rocksdb::NewBloomFilterPolicy;
 using rocksdb::NewLRUCache;
 using rocksdb::Options;
@@ -63,6 +64,7 @@ using rocksdb::Range;
 using rocksdb::ReadOptions;
 using rocksdb::SequentialFile;
 using rocksdb::Slice;
+using rocksdb::SliceParts;
 using rocksdb::SliceTransform;
 using rocksdb::Snapshot;
 using rocksdb::Status;
@@ -74,6 +76,7 @@ using rocksdb::BackupEngine;
 using rocksdb::BackupableDBOptions;
 using rocksdb::BackupInfo;
 using rocksdb::RestoreOptions;
+using rocksdb::CompactRangeOptions;
 
 using std::shared_ptr;
 
@@ -167,99 +170,6 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
   virtual const char* Name() const override { return (*name_)(state_); }
 };
 
-struct rocksdb_compactionfilterv2_t : public CompactionFilterV2 {
-  void* state_;
-  void (*destructor_)(void*);
-  const char* (*name_)(void*);
-  void (*filter_)(void*, int level, size_t num_keys,
-                  const char* const* keys_list, const size_t* keys_list_sizes,
-                  const char* const* existing_values_list, const size_t* existing_values_list_sizes,
-                  char** new_values_list, size_t* new_values_list_sizes,
-                  unsigned char* to_delete_list);
-
-  virtual ~rocksdb_compactionfilterv2_t() {
-    (*destructor_)(state_);
-  }
-
-  virtual const char* Name() const override { return (*name_)(state_); }
-
-  virtual std::vector<bool> Filter(
-      int level, const SliceVector& keys, const SliceVector& existing_values,
-      std::vector<std::string>* new_values,
-      std::vector<bool>* values_changed) const override {
-    // Make a vector pointing to the underlying key data.
-    size_t num_keys = keys.size();
-    std::vector<const char*> keys_list(num_keys);
-    std::vector<size_t> keys_list_sizes(num_keys);
-    for (size_t i = 0; i < num_keys; ++i) {
-      keys_list[i] = keys[i].data();
-      keys_list_sizes[i] = keys[i].size();
-    }
-    // Make a vector pointing to the underlying value data.
-    std::vector<const char*> existing_values_list(num_keys);
-    std::vector<size_t> existing_values_list_sizes(num_keys);
-    for (size_t i = 0; i < num_keys; ++i) {
-      existing_values_list[i] = existing_values[i].data();
-      existing_values_list_sizes[i] = existing_values[i].size();
-    }
-    // Make a vector which will accept newly-allocated char* arrays
-    // which we will take ownership of and assign to strings in new_values.
-    new_values->clear();
-    std::vector<char*> new_values_list(num_keys);
-    std::vector<size_t> new_values_list_sizes(num_keys);
-    // Resize values_changed to hold all keys.
-    values_changed->resize(num_keys);
-    // Make a vector for bools indicating a value should be deleted
-    // on compaction (true) or maintained (false).
-    std::vector<unsigned char> to_delete_list(num_keys);
-
-    (*filter_)(
-        state_, level, num_keys, &keys_list[0], &keys_list_sizes[0],
-        &existing_values_list[0], &existing_values_list_sizes[0],
-        &new_values_list[0], &new_values_list_sizes[0], &to_delete_list[0]);
-
-    // Now, we transfer any changed values, setting values_changed and
-    // initializing new_values in the event a value changed.
-    std::vector<bool> to_delete(num_keys);
-    for (size_t i = 0; i < num_keys; ++i) {
-      to_delete[i] = to_delete_list[i];
-      (*values_changed)[i] = new_values_list[i] != nullptr;
-      if ((*values_changed)[i]) {
-        new_values->push_back(std::string(new_values_list[i], new_values_list_sizes[i]));
-        free(new_values_list[i]);
-      }
-    }
-    return to_delete;
-  }
-};
-
-struct rocksdb_compactionfilterfactoryv2_t : public CompactionFilterFactoryV2 {
-  void* state_;
-  void (*destructor_)(void*);
-  const char* (*name_)(void*);
-  rocksdb_compactionfilterv2_t* (*create_compaction_filter_v2_)(
-      void* state, const rocksdb_compactionfiltercontext_t* context);
-
-  rocksdb_compactionfilterfactoryv2_t(const SliceTransform* prefix_extractor)
-      : CompactionFilterFactoryV2(prefix_extractor) {
-  }
-
-  virtual ~rocksdb_compactionfilterfactoryv2_t() {
-    (*destructor_)(state_);
-  }
-
-  virtual const char* Name() const override { return (*name_)(state_); }
-
-  virtual std::unique_ptr<CompactionFilterV2> CreateCompactionFilterV2(
-      const CompactionFilterContext& context) override {
-    struct rocksdb_compactionfiltercontext_t c_context;
-    c_context.rep.is_full_compaction = context.is_full_compaction;
-    c_context.rep.is_manual_compaction = context.is_manual_compaction;
-    return std::unique_ptr<CompactionFilterV2>(
-        (*create_compaction_filter_v2_)(state_, &c_context));
-  }
-};
-
 struct rocksdb_comparator_t : public Comparator {
   void* state_;
   void (*destructor_)(void*);
@@ -479,6 +389,7 @@ static bool SaveError(char** errptr, const Status& s) {
     *errptr = strdup(s.ToString().c_str());
   } else {
     // TODO(sanjay): Merge with existing error?
+    // This is a bug if *errptr is not created by malloc()
     free(*errptr);
     *errptr = strdup(s.ToString().c_str());
   }
@@ -602,6 +513,10 @@ void rocksdb_close(rocksdb_t* db) {
   delete db;
 }
 
+void rocksdb_options_set_uint64add_merge_operator(rocksdb_options_t* opt) {
+  opt->rep.merge_operator = rocksdb::MergeOperators::CreateUInt64AddOperator();
+}
+
 rocksdb_t* rocksdb_open_column_families(
     const rocksdb_options_t* db_options,
     const char* name,
@@ -830,6 +745,69 @@ char* rocksdb_get_cf(
   return result;
 }
 
+void rocksdb_multi_get(
+    rocksdb_t* db,
+    const rocksdb_readoptions_t* options,
+    size_t num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes,
+    char** values_list, size_t* values_list_sizes,
+    char** errs) {
+  std::vector<Slice> keys(num_keys);
+  for (size_t i = 0; i < num_keys; i++) {
+    keys[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  std::vector<std::string> values(num_keys);
+  std::vector<Status> statuses = db->rep->MultiGet(options->rep, keys, &values);
+  for (size_t i = 0; i < num_keys; i++) {
+    if (statuses[i].ok()) {
+      values_list[i] = CopyString(values[i]);
+      values_list_sizes[i] = values[i].size();
+      errs[i] = nullptr;
+    } else {
+      values_list[i] = nullptr;
+      values_list_sizes[i] = 0;
+      if (!statuses[i].IsNotFound()) {
+        errs[i] = strdup(statuses[i].ToString().c_str());
+      } else {
+        errs[i] = nullptr;
+      }
+    }
+  }
+}
+
+void rocksdb_multi_get_cf(
+    rocksdb_t* db,
+    const rocksdb_readoptions_t* options,
+    const rocksdb_column_family_handle_t* const* column_families,
+    size_t num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes,
+    char** values_list, size_t* values_list_sizes,
+    char** errs) {
+  std::vector<Slice> keys(num_keys);
+  std::vector<ColumnFamilyHandle*> cfs(num_keys);
+  for (size_t i = 0; i < num_keys; i++) {
+    keys[i] = Slice(keys_list[i], keys_list_sizes[i]);
+    cfs[i] = column_families[i]->rep;
+  }
+  std::vector<std::string> values(num_keys);
+  std::vector<Status> statuses = db->rep->MultiGet(options->rep, cfs, keys, &values);
+  for (size_t i = 0; i < num_keys; i++) {
+    if (statuses[i].ok()) {
+      values_list[i] = CopyString(values[i]);
+      values_list_sizes[i] = values[i].size();
+      errs[i] = nullptr;
+    } else {
+      values_list[i] = nullptr;
+      values_list_sizes[i] = 0;
+      if (!statuses[i].IsNotFound()) {
+        errs[i] = strdup(statuses[i].ToString().c_str());
+      } else {
+        errs[i] = nullptr;
+      }
+    }
+  }
+}
+
 rocksdb_iterator_t* rocksdb_create_iterator(
     rocksdb_t* db,
     const rocksdb_readoptions_t* options) {
@@ -936,6 +914,7 @@ void rocksdb_compact_range(
     const char* limit_key, size_t limit_key_len) {
   Slice a, b;
   db->rep->CompactRange(
+      CompactRangeOptions(),
       // Pass nullptr Slice if corresponding "const char*" is nullptr
       (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
       (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr));
@@ -948,7 +927,7 @@ void rocksdb_compact_range_cf(
     const char* limit_key, size_t limit_key_len) {
   Slice a, b;
   db->rep->CompactRange(
-      column_family->rep,
+      CompactRangeOptions(), column_family->rep,
       // Pass nullptr Slice if corresponding "const char*" is nullptr
       (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
       (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr));
@@ -1071,6 +1050,43 @@ void rocksdb_writebatch_put_cf(
   b->rep.Put(column_family->rep, Slice(key, klen), Slice(val, vlen));
 }
 
+void rocksdb_writebatch_putv(
+    rocksdb_writebatch_t* b,
+    int num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes,
+    int num_values, const char* const* values_list,
+    const size_t* values_list_sizes) {
+  std::vector<Slice> key_slices(num_keys);
+  for (int i = 0; i < num_keys; i++) {
+    key_slices[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  std::vector<Slice> value_slices(num_values);
+  for (int i = 0; i < num_values; i++) {
+    value_slices[i] = Slice(values_list[i], values_list_sizes[i]);
+  }
+  b->rep.Put(SliceParts(key_slices.data(), num_keys),
+             SliceParts(value_slices.data(), num_values));
+}
+
+void rocksdb_writebatch_putv_cf(
+    rocksdb_writebatch_t* b,
+    rocksdb_column_family_handle_t* column_family,
+    int num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes,
+    int num_values, const char* const* values_list,
+    const size_t* values_list_sizes) {
+  std::vector<Slice> key_slices(num_keys);
+  for (int i = 0; i < num_keys; i++) {
+    key_slices[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  std::vector<Slice> value_slices(num_values);
+  for (int i = 0; i < num_values; i++) {
+    value_slices[i] = Slice(values_list[i], values_list_sizes[i]);
+  }
+  b->rep.Put(column_family->rep, SliceParts(key_slices.data(), num_keys),
+             SliceParts(value_slices.data(), num_values));
+}
+
 void rocksdb_writebatch_merge(
     rocksdb_writebatch_t* b,
     const char* key, size_t klen,
@@ -1086,6 +1102,43 @@ void rocksdb_writebatch_merge_cf(
   b->rep.Merge(column_family->rep, Slice(key, klen), Slice(val, vlen));
 }
 
+void rocksdb_writebatch_mergev(
+    rocksdb_writebatch_t* b,
+    int num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes,
+    int num_values, const char* const* values_list,
+    const size_t* values_list_sizes) {
+  std::vector<Slice> key_slices(num_keys);
+  for (int i = 0; i < num_keys; i++) {
+    key_slices[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  std::vector<Slice> value_slices(num_values);
+  for (int i = 0; i < num_values; i++) {
+    value_slices[i] = Slice(values_list[i], values_list_sizes[i]);
+  }
+  b->rep.Merge(SliceParts(key_slices.data(), num_keys),
+               SliceParts(value_slices.data(), num_values));
+}
+
+void rocksdb_writebatch_mergev_cf(
+    rocksdb_writebatch_t* b,
+    rocksdb_column_family_handle_t* column_family,
+    int num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes,
+    int num_values, const char* const* values_list,
+    const size_t* values_list_sizes) {
+  std::vector<Slice> key_slices(num_keys);
+  for (int i = 0; i < num_keys; i++) {
+    key_slices[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  std::vector<Slice> value_slices(num_values);
+  for (int i = 0; i < num_values; i++) {
+    value_slices[i] = Slice(values_list[i], values_list_sizes[i]);
+  }
+  b->rep.Merge(column_family->rep, SliceParts(key_slices.data(), num_keys),
+               SliceParts(value_slices.data(), num_values));
+}
+
 void rocksdb_writebatch_delete(
     rocksdb_writebatch_t* b,
     const char* key, size_t klen) {
@@ -1099,6 +1152,35 @@ void rocksdb_writebatch_delete_cf(
   b->rep.Delete(column_family->rep, Slice(key, klen));
 }
 
+void rocksdb_writebatch_deletev(
+    rocksdb_writebatch_t* b,
+    int num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes) {
+  std::vector<Slice> key_slices(num_keys);
+  for (int i = 0; i < num_keys; i++) {
+    key_slices[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  b->rep.Delete(SliceParts(key_slices.data(), num_keys));
+}
+
+void rocksdb_writebatch_deletev_cf(
+    rocksdb_writebatch_t* b,
+    rocksdb_column_family_handle_t* column_family,
+    int num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes) {
+  std::vector<Slice> key_slices(num_keys);
+  for (int i = 0; i < num_keys; i++) {
+    key_slices[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  b->rep.Delete(column_family->rep, SliceParts(key_slices.data(), num_keys));
+}
+
+void rocksdb_writebatch_put_log_data(
+    rocksdb_writebatch_t* b,
+    const char* blob, size_t len) {
+  b->rep.PutLogData(Slice(blob, len));
+}
+
 void rocksdb_writebatch_iterate(
     rocksdb_writebatch_t* b,
     void* state,
@@ -1186,6 +1268,26 @@ void rocksdb_block_based_options_set_whole_key_filtering(
   options->rep.whole_key_filtering = v;
 }
 
+void rocksdb_block_based_options_set_format_version(
+    rocksdb_block_based_table_options_t* options, int v) {
+  options->rep.format_version = v;
+}
+
+void rocksdb_block_based_options_set_index_type(
+    rocksdb_block_based_table_options_t* options, int v) {
+  options->rep.index_type = static_cast<BlockBasedTableOptions::IndexType>(v);
+}
+
+void rocksdb_block_based_options_set_hash_index_allow_collision(
+    rocksdb_block_based_table_options_t* options, unsigned char v) {
+  options->rep.hash_index_allow_collision = v;
+}
+
+void rocksdb_block_based_options_set_cache_index_and_filter_blocks(
+    rocksdb_block_based_table_options_t* options, unsigned char v) {
+  options->rep.cache_index_and_filter_blocks = v;
+}
+
 void rocksdb_options_set_block_based_table_factory(
     rocksdb_options_t *opt,
     rocksdb_block_based_table_options_t* table_options) {
@@ -1293,11 +1395,6 @@ void rocksdb_options_set_merge_operator(
   opt->rep.merge_operator = std::shared_ptr<MergeOperator>(merge_operator);
 }
 
-void rocksdb_options_set_compaction_filter_factory_v2(
-    rocksdb_options_t* opt,
-    rocksdb_compactionfilterfactoryv2_t* compaction_filter_factory_v2) {
-  opt->rep.compaction_filter_factory_v2 = std::shared_ptr<CompactionFilterFactoryV2>(compaction_filter_factory_v2);
-}
 
 void rocksdb_options_set_create_if_missing(
     rocksdb_options_t* opt, unsigned char v) {
@@ -1412,10 +1509,8 @@ void rocksdb_options_set_level0_stop_writes_trigger(
   opt->rep.level0_stop_writes_trigger = n;
 }
 
-void rocksdb_options_set_max_mem_compaction_level(
-    rocksdb_options_t* opt, int n) {
-  opt->rep.max_mem_compaction_level = n;
-}
+void rocksdb_options_set_max_mem_compaction_level(rocksdb_options_t* opt,
+                                                  int n) {}
 
 void rocksdb_options_set_compression(rocksdb_options_t* opt, int t) {
   opt->rep.compression = static_cast<CompressionType>(t);
@@ -1477,10 +1572,9 @@ void rocksdb_options_set_manifest_preallocation_size(
   opt->rep.manifest_preallocation_size = v;
 }
 
-void rocksdb_options_set_purge_redundant_kvs_while_flush(
-    rocksdb_options_t* opt, unsigned char v) {
-  opt->rep.purge_redundant_kvs_while_flush = v;
-}
+// noop
+void rocksdb_options_set_purge_redundant_kvs_while_flush(rocksdb_options_t* opt,
+                                                         unsigned char v) {}
 
 void rocksdb_options_set_allow_os_buffer(rocksdb_options_t* opt,
                                          unsigned char v) {
@@ -1568,6 +1662,11 @@ void rocksdb_options_set_min_write_buffer_number_to_merge(rocksdb_options_t* opt
   opt->rep.min_write_buffer_number_to_merge = n;
 }
 
+void rocksdb_options_set_max_write_buffer_number_to_maintain(
+    rocksdb_options_t* opt, int n) {
+  opt->rep.max_write_buffer_number_to_maintain = n;
+}
+
 void rocksdb_options_set_max_background_compactions(rocksdb_options_t* opt, int n) {
   opt->rep.max_background_compactions = n;
 }
@@ -1732,10 +1831,17 @@ void rocksdb_options_set_fifo_compaction_options(
   opt->rep.compaction_options_fifo = fifo->rep;
 }
 
+char *rocksdb_options_statistics_get_string(rocksdb_options_t *opt) {
+  rocksdb::Statistics *statistics = opt->rep.statistics.get();
+  if (statistics) {
+    return strdup(statistics->ToString().c_str());
+  }
+  return nullptr;
+}
+
 /*
 TODO:
 DB::OpenForReadOnly
-DB::MultiGet
 DB::KeyMayExist
 DB::GetOptions
 DB::GetSortedWalFiles
@@ -1799,46 +1905,6 @@ void rocksdb_compactionfilterfactory_destroy(
   delete factory;
 }
 
-rocksdb_compactionfilterv2_t* rocksdb_compactionfilterv2_create(
-    void* state,
-    void (*destructor)(void*),
-    void (*filter)(void*, int level, size_t num_keys,
-                   const char* const* keys_list, const size_t* keys_list_sizes,
-                   const char* const* existing_values_list, const size_t* existing_values_list_sizes,
-                   char** new_values_list, size_t* new_values_list_sizes,
-                   unsigned char* to_delete_list),
-    const char* (*name)(void*)) {
-  rocksdb_compactionfilterv2_t* result = new rocksdb_compactionfilterv2_t;
-  result->state_ = state;
-  result->destructor_ = destructor;
-  result->filter_ = filter;
-  result->name_ = name;
-  return result;
-}
-
-void rocksdb_compactionfilterv2_destroy(rocksdb_compactionfilterv2_t* filter) {
-  delete filter;
-}
-
-rocksdb_compactionfilterfactoryv2_t* rocksdb_compactionfilterfactoryv2_create(
-    void* state,
-    rocksdb_slicetransform_t* prefix_extractor,
-    void (*destructor)(void*),
-    rocksdb_compactionfilterv2_t* (*create_compaction_filter_v2)(
-        void* state, const rocksdb_compactionfiltercontext_t* context),
-    const char* (*name)(void*)) {
-  rocksdb_compactionfilterfactoryv2_t* result = new rocksdb_compactionfilterfactoryv2_t(prefix_extractor);
-  result->state_ = state;
-  result->destructor_ = destructor;
-  result->create_compaction_filter_v2_ = create_compaction_filter_v2;
-  result->name_ = name;
-  return result;
-}
-
-void rocksdb_compactionfilterfactoryv2_destroy(rocksdb_compactionfilterfactoryv2_t* factory) {
-  delete factory;
-}
-
 rocksdb_comparator_t* rocksdb_comparator_create(
     void* state,
     void (*destructor)(void*),
@@ -2046,6 +2112,10 @@ void rocksdb_env_set_high_priority_background_threads(rocksdb_env_t* env, int n)
   env->rep->SetBackgroundThreads(n, Env::HIGH);
 }
 
+void rocksdb_env_join_all_threads(rocksdb_env_t* env) {
+  env->rep->WaitForJoin();
+}
+
 void rocksdb_env_destroy(rocksdb_env_t* env) {
   if (!env->is_default) delete env->rep;
   delete env;
@@ -2100,6 +2170,27 @@ rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t pref
   return wrapper;
 }
 
+rocksdb_slicetransform_t* rocksdb_slicetransform_create_noop() {
+  struct Wrapper : public rocksdb_slicetransform_t {
+    const SliceTransform* rep_;
+    ~Wrapper() { delete rep_; }
+    const char* Name() const override { return rep_->Name(); }
+    Slice Transform(const Slice& src) const override {
+      return rep_->Transform(src);
+    }
+    bool InDomain(const Slice& src) const override {
+      return rep_->InDomain(src);
+    }
+    bool InRange(const Slice& src) const override { return rep_->InRange(src); }
+    static void DoNothing(void*) { }
+  };
+  Wrapper* wrapper = new Wrapper;
+  wrapper->rep_ = rocksdb::NewNoopTransform();
+  wrapper->state_ = nullptr;
+  wrapper->destructor_ = &Wrapper::DoNothing;
+  return wrapper;
+}
+
 rocksdb_universal_compaction_options_t* rocksdb_universal_compaction_options_create() {
   rocksdb_universal_compaction_options_t* result = new rocksdb_universal_compaction_options_t;
   result->rep = new rocksdb::CompactionOptionsUniversal;
@@ -2215,6 +2306,17 @@ extern void rocksdb_livefiles_destroy(
   delete lf;
 }
 
+void rocksdb_get_options_from_string(const rocksdb_options_t* base_options,
+                                     const char* opts_str,
+                                     rocksdb_options_t* new_options,
+                                     char** errptr) {
+  SaveError(errptr,
+            GetOptionsFromString(base_options->rep, std::string(opts_str),
+                                 &new_options->rep));
+}
+
+void rocksdb_free(void* ptr) { free(ptr); }
+
 }  // end extern "C"
 
-#endif  // ROCKSDB_LITE
+#endif  // !ROCKSDB_LITE

db/c_test.c

@@ -2,6 +2,8 @@
    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 ROCKSDB_LITE  // Lite does not support C API
+
 #include "rocksdb/c.h"
 
 #include <stddef.h>
@@ -9,9 +11,31 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
-#include <unistd.h>
+#ifndef OS_WIN
+#  include <unistd.h>
+#endif
 #include <inttypes.h>
 
+// Can not use port/port.h macros as this is a c file
+#ifdef OS_WIN
+
+#include <Windows.h>
+
+# define snprintf _snprintf
+
+// Ok for uniqueness
+int geteuid() {
+
+  int result = 0;
+
+  result = ((int)GetCurrentProcessId() << 16);
+  result |= (int)GetCurrentThreadId();
+
+  return result;
+}
+
+#endif
+
 const char* phase = "";
 static char dbname[200];
 static char dbbackupname[200];
@@ -227,79 +251,6 @@ static rocksdb_t* CheckCompaction(rocksdb_t* db, rocksdb_options_t* options,
   return db;
 }
 
-// Custom compaction filter V2.
-static void CompactionFilterV2Destroy(void* arg) { }
-static const char* CompactionFilterV2Name(void* arg) {
-  return "TestCompactionFilterV2";
-}
-static void CompactionFilterV2Filter(
-    void* arg, int level, size_t num_keys,
-    const char* const* keys_list, const size_t* keys_list_sizes,
-    const char* const* existing_values_list, const size_t* existing_values_list_sizes,
-    char** new_values_list, size_t* new_values_list_sizes,
-    unsigned char* to_delete_list) {
-  size_t i;
-  for (i = 0; i < num_keys; i++) {
-    // If any value is "gc", it's removed.
-    if (existing_values_list_sizes[i] == 2 && memcmp(existing_values_list[i], "gc", 2) == 0) {
-      to_delete_list[i] = 1;
-    } else if (existing_values_list_sizes[i] == 6 && memcmp(existing_values_list[i], "gc all", 6) == 0) {
-      // If any value is "gc all", all keys are removed.
-      size_t j;
-      for (j = 0; j < num_keys; j++) {
-        to_delete_list[j] = 1;
-      }
-      return;
-    } else if (existing_values_list_sizes[i] == 6 && memcmp(existing_values_list[i], "change", 6) == 0) {
-      // If value is "change", set changed value to "changed".
-      size_t len;
-      len = strlen("changed");
-      new_values_list[i] = malloc(len);
-      memcpy(new_values_list[i], "changed", len);
-      new_values_list_sizes[i] = len;
-    } else {
-      // Otherwise, no keys are removed.
-    }
-  }
-}
-
-// Custom prefix extractor for compaction filter V2 which extracts first 3 characters.
-static void CFV2PrefixExtractorDestroy(void* arg) { }
-static char* CFV2PrefixExtractorTransform(void* arg, const char* key, size_t length, size_t* dst_length) {
-  // Verify keys are maximum length 4; this verifies fix for a
-  // prior bug which was passing the RocksDB-encoded key with
-  // logical timestamp suffix instead of parsed user key.
-  if (length > 4) {
-    fprintf(stderr, "%s:%d: %s: key %s is not user key\n", __FILE__, __LINE__, phase, key);
-    abort();
-  }
-  *dst_length = length < 3 ? length : 3;
-  return (char*)key;
-}
-static unsigned char CFV2PrefixExtractorInDomain(void* state, const char* key, size_t length) {
-  return 1;
-}
-static unsigned char CFV2PrefixExtractorInRange(void* state, const char* key, size_t length) {
-  return 1;
-}
-static const char* CFV2PrefixExtractorName(void* state) {
-  return "TestCFV2PrefixExtractor";
-}
-
-// Custom compaction filter factory V2.
-static void CompactionFilterFactoryV2Destroy(void* arg) {
-  rocksdb_slicetransform_destroy((rocksdb_slicetransform_t*)arg);
-}
-static const char* CompactionFilterFactoryV2Name(void* arg) {
-  return "TestCompactionFilterFactoryV2";
-}
-static rocksdb_compactionfilterv2_t* CompactionFilterFactoryV2Create(
-    void* state, const rocksdb_compactionfiltercontext_t* context) {
-  return rocksdb_compactionfilterv2_create(state, CompactionFilterV2Destroy,
-                                           CompactionFilterV2Filter,
-                                           CompactionFilterV2Name);
-}
-
 // Custom merge operator
 static void MergeOperatorDestroy(void* arg) { }
 static const char* MergeOperatorName(void* arg) {
@@ -465,6 +416,24 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_destroy(wb);
   }
 
+  StartPhase("writebatch_vectors");
+  {
+    rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
+    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_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
+    rocksdb_write(db, woptions, wb, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "zap", "xyz");
+    rocksdb_writebatch_delete(wb, "zap", 3);
+    rocksdb_write(db, woptions, wb, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "zap", NULL);
+    rocksdb_writebatch_destroy(wb);
+  }
+
   StartPhase("writebatch_rep");
   {
     rocksdb_writebatch_t* wb1 = rocksdb_writebatch_create();
@@ -505,6 +474,33 @@ int main(int argc, char** argv) {
     rocksdb_iter_destroy(iter);
   }
 
+  StartPhase("multiget");
+  {
+    const char* keys[3] = { "box", "foo", "notfound" };
+    const size_t keys_sizes[3] = { 3, 3, 8 };
+    char* vals[3];
+    size_t vals_sizes[3];
+    char* errs[3];
+    rocksdb_multi_get(db, roptions, 3, keys, keys_sizes, vals, vals_sizes, errs);
+
+    int i;
+    for (i = 0; i < 3; i++) {
+      CheckEqual(NULL, errs[i], 0);
+      switch (i) {
+      case 0:
+        CheckEqual("c", vals[i], vals_sizes[i]);
+        break;
+      case 1:
+        CheckEqual("hello", vals[i], vals_sizes[i]);
+        break;
+      case 2:
+        CheckEqual(NULL, vals[i], vals_sizes[i]);
+        break;
+      }
+      Free(&vals[i]);
+    }
+  }
+
   StartPhase("approximate_sizes");
   {
     int i;
@@ -653,50 +649,6 @@ int main(int argc, char** argv) {
     rocksdb_options_destroy(options_with_filter_factory);
   }
 
-  StartPhase("compaction_filter_v2");
-  {
-    rocksdb_compactionfilterfactoryv2_t* factory;
-    rocksdb_slicetransform_t* prefix_extractor;
-    prefix_extractor = rocksdb_slicetransform_create(
-        NULL, CFV2PrefixExtractorDestroy, CFV2PrefixExtractorTransform,
-        CFV2PrefixExtractorInDomain, CFV2PrefixExtractorInRange,
-        CFV2PrefixExtractorName);
-    factory = rocksdb_compactionfilterfactoryv2_create(
-        prefix_extractor, prefix_extractor, CompactionFilterFactoryV2Destroy,
-        CompactionFilterFactoryV2Create, CompactionFilterFactoryV2Name);
-    // Create new database
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    rocksdb_options_set_compaction_filter_factory_v2(options, factory);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-    // Only foo2 is GC'd, foo3 is changed.
-    rocksdb_put(db, woptions, "foo1", 4, "no gc", 5, &err);
-    CheckNoError(err);
-    rocksdb_put(db, woptions, "foo2", 4, "gc", 2, &err);
-    CheckNoError(err);
-    rocksdb_put(db, woptions, "foo3", 4, "change", 6, &err);
-    CheckNoError(err);
-    // All bars are GC'd.
-    rocksdb_put(db, woptions, "bar1", 4, "no gc", 5, &err);
-    CheckNoError(err);
-    rocksdb_put(db, woptions, "bar2", 4, "gc all", 6, &err);
-    CheckNoError(err);
-    rocksdb_put(db, woptions, "bar3", 4, "no gc", 5, &err);
-    CheckNoError(err);
-    // Compact the DB to garbage collect.
-    rocksdb_compact_range(db, NULL, 0, NULL, 0);
-
-    // Verify foo entries.
-    CheckGet(db, roptions, "foo1", "no gc");
-    CheckGet(db, roptions, "foo2", NULL);
-    CheckGet(db, roptions, "foo3", "changed");
-    // Verify bar entries were all deleted.
-    CheckGet(db, roptions, "bar1", NULL);
-    CheckGet(db, roptions, "bar2", NULL);
-    CheckGet(db, roptions, "bar3", NULL);
-  }
-
   StartPhase("merge_operator");
   {
     rocksdb_mergeoperator_t* merge_operator;
@@ -778,12 +730,36 @@ int main(int argc, char** argv) {
     CheckGetCF(db, roptions, handles[1], "box", "c");
     rocksdb_writebatch_destroy(wb);
 
+    const char* keys[3] = { "box", "box", "barfooxx" };
+    const rocksdb_column_family_handle_t* get_handles[3] = { handles[0], handles[1], handles[1] };
+    const size_t keys_sizes[3] = { 3, 3, 8 };
+    char* vals[3];
+    size_t vals_sizes[3];
+    char* errs[3];
+    rocksdb_multi_get_cf(db, roptions, get_handles, 3, keys, keys_sizes, vals, vals_sizes, errs);
+
+    int i;
+    for (i = 0; i < 3; i++) {
+      CheckEqual(NULL, errs[i], 0);
+      switch (i) {
+      case 0:
+        CheckEqual(NULL, vals[i], vals_sizes[i]); // wrong cf
+        break;
+      case 1:
+        CheckEqual("c", vals[i], vals_sizes[i]); // bingo
+        break;
+      case 2:
+        CheckEqual(NULL, vals[i], vals_sizes[i]); // normal not found
+        break;
+      }
+      Free(&vals[i]);
+    }
+
     rocksdb_iterator_t* iter = rocksdb_create_iterator_cf(db, roptions, handles[1]);
     CheckCondition(!rocksdb_iter_valid(iter));
     rocksdb_iter_seek_to_first(iter);
     CheckCondition(rocksdb_iter_valid(iter));
 
-    int i;
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
@@ -938,3 +914,13 @@ int main(int argc, char** argv) {
   fprintf(stderr, "PASS\n");
   return 0;
 }
+
+#else
+#include <stdio.h>
+
+int main() {
+  fprintf(stderr, "SKIPPED\n");
+  return 0;
+}
+
+#endif  // !ROCKSDB_LITE

db/column_family.cc

@@ -25,46 +25,18 @@
 #include "db/version_set.h"
 #include "db/writebuffer.h"
 #include "db/internal_stats.h"
-#include "db/job_context.h"
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
 #include "util/autovector.h"
+#include "util/compression.h"
 #include "util/hash_skiplist_rep.h"
 #include "util/options_helper.h"
+#include "util/thread_status_util.h"
+#include "util/xfunc.h"
 
 namespace rocksdb {
 
-namespace {
-// This function computes the amount of time in microseconds by which a write
-// should be delayed based on the number of level-0 files according to the
-// following formula:
-// if n < bottom, return 0;
-// if n >= top, return 1000;
-// otherwise, let r = (n - bottom) /
-//                    (top - bottom)
-//  and return r^2 * 1000.
-// The goal of this formula is to gradually increase the rate at which writes
-// are slowed. We also tried linear delay (r * 1000), but it seemed to do
-// slightly worse. There is no other particular reason for choosing quadratic.
-uint64_t SlowdownAmount(int n, double bottom, double top) {
-  uint64_t delay;
-  if (n >= top) {
-    delay = 1000;
-  } else if (n < bottom) {
-    delay = 0;
-  } else {
-    // If we are here, we know that:
-    //   level0_start_slowdown <= n < level0_slowdown
-    // since the previous two conditions are false.
-    double how_much = static_cast<double>(n - bottom) / (top - bottom);
-    delay = std::max(how_much * how_much * 1000, 100.0);
-  }
-  assert(delay <= 1000);
-  return delay;
-}
-}  // namespace
-
 ColumnFamilyHandleImpl::ColumnFamilyHandleImpl(
     ColumnFamilyData* column_family_data, DBImpl* db, InstrumentedMutex* mutex)
     : cfd_(column_family_data), db_(db), mutex_(mutex) {
@@ -87,6 +59,7 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
     if (job_context.HaveSomethingToDelete()) {
       db_->PurgeObsoleteFiles(job_context);
     }
+    job_context.Clean();
   }
 }
 
@@ -116,6 +89,28 @@ void GetIntTblPropCollectorFactory(
       new InternalKeyPropertiesCollectorFactory);
 }
 
+Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
+  if (!cf_options.compression_per_level.empty()) {
+    for (size_t level = 0; level < cf_options.compression_per_level.size();
+         ++level) {
+      if (!CompressionTypeSupported(cf_options.compression_per_level[level])) {
+        return Status::InvalidArgument(
+            "Compression type " +
+            CompressionTypeToString(cf_options.compression_per_level[level]) +
+            " is not linked with the binary.");
+      }
+    }
+  } else {
+    if (!CompressionTypeSupported(cf_options.compression)) {
+      return Status::InvalidArgument(
+          "Compression type " +
+          CompressionTypeToString(cf_options.compression) +
+          " is not linked with the binary.");
+    }
+  }
+  return Status::OK();
+}
+
 ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
                                     const InternalKeyComparator* icmp,
                                     const ColumnFamilyOptions& src) {
@@ -136,15 +131,28 @@ ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
   result.min_write_buffer_number_to_merge =
       std::min(result.min_write_buffer_number_to_merge,
                result.max_write_buffer_number - 1);
-  if (result.max_mem_compaction_level >= result.num_levels) {
-    result.max_mem_compaction_level = result.num_levels - 1;
+  if (result.num_levels < 1) {
+    result.num_levels = 1;
   }
-  if (result.soft_rate_limit > result.hard_rate_limit) {
-    result.soft_rate_limit = result.hard_rate_limit;
+  if (result.compaction_style == kCompactionStyleLevel &&
+      result.num_levels < 2) {
+    result.num_levels = 2;
   }
   if (result.max_write_buffer_number < 2) {
     result.max_write_buffer_number = 2;
   }
+  if (result.max_write_buffer_number_to_maintain < 0) {
+    result.max_write_buffer_number_to_maintain = result.max_write_buffer_number;
+  }
+  XFUNC_TEST("memtablelist_history", "transaction_xftest_SanitizeOptions",
+             xf_transaction_set_memtable_history1,
+             xf_transaction_set_memtable_history,
+             &result.max_write_buffer_number_to_maintain);
+  XFUNC_TEST("memtablelist_history_clear", "transaction_xftest_SanitizeOptions",
+             xf_transaction_clear_memtable_history1,
+             xf_transaction_clear_memtable_history,
+             &result.max_write_buffer_number_to_maintain);
+
   if (!result.prefix_extractor) {
     assert(result.memtable_factory);
     Slice name = result.memtable_factory->Name();
@@ -154,24 +162,6 @@ ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
     }
   }
 
-  if (!src.compression_per_level.empty()) {
-    for (size_t level = 0; level < src.compression_per_level.size(); ++level) {
-      if (!CompressionTypeSupported(src.compression_per_level[level])) {
-        Log(InfoLogLevel::WARN_LEVEL, db_options.info_log,
-            "Compression type chosen for level %zu is not supported: %s. "
-            "RocksDB "
-            "will not compress data on level %zu.",
-            level, CompressionTypeToString(src.compression_per_level[level]),
-            level);
-      }
-    }
-  } else if (!CompressionTypeSupported(src.compression)) {
-    Log(InfoLogLevel::WARN_LEVEL, db_options.info_log,
-        "Compression type chosen is not supported: %s. RocksDB will not "
-        "compress data.",
-        CompressionTypeToString(src.compression));
-  }
-
   if (result.compaction_style == kCompactionStyleFIFO) {
     result.num_levels = 1;
     // since we delete level0 files in FIFO compaction when there are too many
@@ -302,7 +292,8 @@ ColumnFamilyData::ColumnFamilyData(
       mutable_cf_options_(options_, ioptions_),
       write_buffer_(write_buffer),
       mem_(nullptr),
-      imm_(options_.min_write_buffer_number_to_merge),
+      imm_(options_.min_write_buffer_number_to_merge,
+           options_.max_write_buffer_number_to_maintain),
       super_version_(nullptr),
       super_version_number_(0),
       local_sv_(new ThreadLocalPtr(&SuperVersionUnrefHandle)),
@@ -352,7 +343,7 @@ ColumnFamilyData::ColumnFamilyData(
     if (column_family_set_->NumberOfColumnFamilies() < 10) {
       Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
           "--------------- Options for column family [%s]:\n", name.c_str());
-      options_.Dump(ioptions_.info_log);
+      options_.DumpCFOptions(ioptions_.info_log);
     } else {
       Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
           "\t(skipping printing options)\n");
@@ -435,16 +426,15 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
     auto* vstorage = current_->storage_info();
     const double score = vstorage->max_compaction_score();
     const int max_level = vstorage->max_compaction_score_level();
-
     auto write_controller = column_family_set_->write_controller_;
 
-    if (imm()->size() >= mutable_cf_options.max_write_buffer_number) {
+    if (imm()->NumNotFlushed() >= mutable_cf_options.max_write_buffer_number) {
       write_controller_token_ = write_controller->GetStopToken();
       internal_stats_->AddCFStats(InternalStats::MEMTABLE_COMPACTION, 1);
       Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
           "[%s] Stopping writes because we have %d immutable memtables "
           "(waiting for flush), max_write_buffer_number is set to %d",
-          name_.c_str(), imm()->size(),
+          name_.c_str(), imm()->NumNotFlushed(),
           mutable_cf_options.max_write_buffer_number);
     } else if (vstorage->l0_delay_trigger_count() >=
                mutable_cf_options.level0_stop_writes_trigger) {
@@ -456,37 +446,18 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
     } else if (mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
                vstorage->l0_delay_trigger_count() >=
                    mutable_cf_options.level0_slowdown_writes_trigger) {
-      uint64_t slowdown =
-          SlowdownAmount(vstorage->l0_delay_trigger_count(),
-                         mutable_cf_options.level0_slowdown_writes_trigger,
-                         mutable_cf_options.level0_stop_writes_trigger);
-      write_controller_token_ = write_controller->GetDelayToken(slowdown);
-      internal_stats_->AddCFStats(InternalStats::LEVEL0_SLOWDOWN, slowdown);
+      write_controller_token_ = write_controller->GetDelayToken();
+      internal_stats_->AddCFStats(InternalStats::LEVEL0_SLOWDOWN, 1);
       Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-          "[%s] Stalling writes because we have %d level-0 files (%" PRIu64
-          "us)",
-          name_.c_str(), vstorage->l0_delay_trigger_count(), slowdown);
-    } else if (mutable_cf_options.hard_rate_limit > 1.0 &&
-               score > mutable_cf_options.hard_rate_limit) {
-      uint64_t kHardLimitSlowdown = 1000;
-      write_controller_token_ =
-          write_controller->GetDelayToken(kHardLimitSlowdown);
-      internal_stats_->RecordLevelNSlowdown(max_level, false);
-      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-          "[%s] Stalling writes because we hit hard limit on level %d. "
-          "(%" PRIu64 "us)",
-          name_.c_str(), max_level, kHardLimitSlowdown);
+          "[%s] Stalling writes because we have %d level-0 files",
+          name_.c_str(), vstorage->l0_delay_trigger_count());
     } else if (mutable_cf_options.soft_rate_limit > 0.0 &&
                score > mutable_cf_options.soft_rate_limit) {
-      uint64_t slowdown = SlowdownAmount(score,
-          mutable_cf_options.soft_rate_limit,
-          mutable_cf_options.hard_rate_limit);
-      write_controller_token_ = write_controller->GetDelayToken(slowdown);
+      write_controller_token_ = write_controller->GetDelayToken();
       internal_stats_->RecordLevelNSlowdown(max_level, true);
       Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-          "[%s] Stalling writes because we hit soft limit on level %d (%" PRIu64
-          "us)",
-          name_.c_str(), max_level, slowdown);
+          "[%s] Stalling writes because we hit soft limit on level %d",
+          name_.c_str(), max_level);
     } else {
       write_controller_token_.reset();
     }
@@ -506,18 +477,18 @@ uint64_t ColumnFamilyData::GetNumLiveVersions() const {
 }
 
 MemTable* ColumnFamilyData::ConstructNewMemtable(
-    const MutableCFOptions& mutable_cf_options) {
+    const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
   assert(current_ != nullptr);
-  return new MemTable(internal_comparator_, ioptions_,
-                      mutable_cf_options, write_buffer_);
+  return new MemTable(internal_comparator_, ioptions_, mutable_cf_options,
+                      write_buffer_, earliest_seq);
 }
 
 void ColumnFamilyData::CreateNewMemtable(
-    const MutableCFOptions& mutable_cf_options) {
+    const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
   if (mem_ != nullptr) {
     delete mem_->Unref();
   }
-  SetMemtable(ConstructNewMemtable(mutable_cf_options));
+  SetMemtable(ConstructNewMemtable(mutable_cf_options, earliest_seq));
   mem_->Ref();
 }
 
@@ -627,51 +598,6 @@ bool ColumnFamilyData::ReturnThreadLocalSuperVersion(SuperVersion* sv) {
   return false;
 }
 
-void ColumnFamilyData::NotifyOnCompactionCompleted(
-    DB* db, Compaction* c, const Status& status) {
-#ifndef ROCKSDB_LITE
-  auto listeners = ioptions()->listeners;
-  assert(listeners.size() > 0U);
-  CompactionJobInfo info;
-  info.cf_name = c->column_family_data()->GetName();
-  info.status = status;
-  info.output_level = c->output_level();
-  for (size_t i = 0; i < c->num_input_levels(); ++i) {
-    for (const auto fmd : *c->inputs(i)) {
-      info.input_files.push_back(
-          TableFileName(options_.db_paths,
-                        fmd->fd.GetNumber(),
-                        fmd->fd.GetPathId()));
-    }
-  }
-  for (const auto newf : c->edit()->GetNewFiles()) {
-    info.output_files.push_back(
-        TableFileName(options_.db_paths,
-                      newf.second.fd.GetNumber(),
-                      newf.second.fd.GetPathId()));
-  }
-  for (auto listener : listeners) {
-    listener->OnCompactionCompleted(db, info);
-  }
-#endif  // ROCKSDB_LITE
-}
-
-void ColumnFamilyData::NotifyOnFlushCompleted(
-    DB* db, const std::string& file_path,
-    bool triggered_flush_slowdown,
-    bool triggered_flush_stop) {
-
-#ifndef ROCKSDB_LITE
-  auto listeners = ioptions()->listeners;
-  for (auto listener : listeners) {
-    listener->OnFlushCompleted(
-        db, GetName(), file_path,
-        // Use path 0 as fulled memtables are first flushed into path 0.
-        triggered_flush_slowdown, triggered_flush_stop);
-  }
-#endif  // ROCKSDB_LITE
-}
-
 SuperVersion* ColumnFamilyData::InstallSuperVersion(
     SuperVersion* new_superversion, InstrumentedMutex* db_mutex) {
   db_mutex->AssertHeld();

db/column_family.h

@@ -14,15 +14,16 @@
 #include <vector>
 #include <atomic>
 
-#include "rocksdb/options.h"
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
 #include "db/memtable_list.h"
 #include "db/write_batch_internal.h"
 #include "db/write_controller.h"
 #include "db/table_cache.h"
 #include "db/table_properties_collector.h"
 #include "db/flush_scheduler.h"
+#include "rocksdb/compaction_job_stats.h"
+#include "rocksdb/db.h"
+#include "rocksdb/env.h"
+#include "rocksdb/options.h"
 #include "util/instrumented_mutex.h"
 #include "util/mutable_cf_options.h"
 #include "util/thread_local.h"
@@ -129,6 +130,8 @@ struct SuperVersion {
   autovector<MemTable*> to_delete;
 };
 
+extern Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options);
+
 extern ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
                                            const InternalKeyComparator* icmp,
                                            const ColumnFamilyOptions& src);
@@ -223,10 +226,13 @@ class ColumnFamilyData {
   Version* dummy_versions() { return dummy_versions_; }
   void SetCurrent(Version* current);
   uint64_t GetNumLiveVersions() const;  // REQUIRE: DB mutex held
-
-  MemTable* ConstructNewMemtable(const MutableCFOptions& mutable_cf_options);
   void SetMemtable(MemTable* new_mem) { mem_ = new_mem; }
-  void CreateNewMemtable(const MutableCFOptions& mutable_cf_options);
+
+  // See Memtable constructor for explanation of earliest_seq param.
+  MemTable* ConstructNewMemtable(const MutableCFOptions& mutable_cf_options,
+                                 SequenceNumber earliest_seq);
+  void CreateNewMemtable(const MutableCFOptions& mutable_cf_options,
+                         SequenceNumber earliest_seq);
 
   TableCache* table_cache() const { return table_cache_.get(); }
 
@@ -292,13 +298,6 @@ class ColumnFamilyData {
 
   void ResetThreadLocalSuperVersions();
 
-  void NotifyOnCompactionCompleted(DB* db, Compaction* c, const Status& status);
-
-  void NotifyOnFlushCompleted(
-      DB* db, const std::string& file_path,
-      bool triggered_flush_slowdown,
-      bool triggered_flush_stop);
-
   // Protected by DB mutex
   void set_pending_flush(bool value) { pending_flush_ = value; }
   void set_pending_compaction(bool value) { pending_compaction_ = value; }

db/column_family_test.cc

@@ -98,10 +98,12 @@ class ColumnFamilyTest : public testing::Test {
                                &db_);
   }
 
+#ifndef ROCKSDB_LITE  // ReadOnlyDB is not supported
   void AssertOpenReadOnly(std::vector<std::string> cf,
                     std::vector<ColumnFamilyOptions> options = {}) {
     ASSERT_OK(OpenReadOnly(cf, options));
   }
+#endif  // !ROCKSDB_LITE
 
 
   void Open(std::vector<std::string> cf,
@@ -121,7 +123,7 @@ class ColumnFamilyTest : public testing::Test {
 #ifndef CYGWIN
     return std::stoi(value);
 #else
-    return std::strtol(value.c_str(), 0);
+    return std::strtol(value.c_str(), 0 /* off */, 10 /* base */);
 #endif
   }
 
@@ -186,10 +188,28 @@ class ColumnFamilyTest : public testing::Test {
   }
 
   void WaitForFlush(int cf) {
+#ifndef ROCKSDB_LITE  // TEST functions are not supported in lite
     ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable(handles_[cf]));
+#endif  // !ROCKSDB_LITE
   }
 
-  void WaitForCompaction() { ASSERT_OK(dbfull()->TEST_WaitForCompact()); }
+  void WaitForCompaction() {
+#ifndef ROCKSDB_LITE  // TEST functions are not supported in lite
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+#endif  // !ROCKSDB_LITE
+  }
+
+  uint64_t MaxTotalInMemoryState() {
+#ifndef ROCKSDB_LITE
+    return dbfull()->TEST_MaxTotalInMemoryState();
+#else
+    return 0;
+#endif  // !ROCKSDB_LITE
+  }
+
+  void AssertMaxTotalInMemoryState(uint64_t value) {
+    ASSERT_EQ(value, MaxTotalInMemoryState());
+  }
 
   Status Put(int cf, const std::string& key, const std::string& value) {
     return db_->Put(WriteOptions(), handles_[cf], Slice(key), Slice(value));
@@ -215,11 +235,13 @@ class ColumnFamilyTest : public testing::Test {
   }
 
   void CompactAll(int cf) {
-    ASSERT_OK(db_->CompactRange(handles_[cf], nullptr, nullptr));
+    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), handles_[cf], nullptr,
+                                nullptr));
   }
 
   void Compact(int cf, const Slice& start, const Slice& limit) {
-    ASSERT_OK(db_->CompactRange(handles_[cf], &start, &limit));
+    ASSERT_OK(
+        db_->CompactRange(CompactRangeOptions(), handles_[cf], &start, &limit));
   }
 
   int NumTableFilesAtLevel(int level, int cf) {
@@ -227,6 +249,7 @@ class ColumnFamilyTest : public testing::Test {
                        "rocksdb.num-files-at-level" + ToString(level));
   }
 
+#ifndef ROCKSDB_LITE
   // Return spread of files per level
   std::string FilesPerLevel(int cf) {
     std::string result;
@@ -243,12 +266,27 @@ class ColumnFamilyTest : public testing::Test {
     result.resize(last_non_zero_offset);
     return result;
   }
+#endif
 
+  void AssertFilesPerLevel(const std::string& value, int cf) {
+#ifndef ROCKSDB_LITE
+    ASSERT_EQ(value, FilesPerLevel(cf));
+#endif
+  }
+
+#ifndef ROCKSDB_LITE  // GetLiveFilesMetaData is not supported
   int CountLiveFiles() {
     std::vector<LiveFileMetaData> metadata;
     db_->GetLiveFilesMetaData(&metadata);
     return static_cast<int>(metadata.size());
   }
+#endif  // !ROCKSDB_LITE
+
+  void AssertCountLiveFiles(int expected_value) {
+#ifndef ROCKSDB_LITE
+    ASSERT_EQ(expected_value, CountLiveFiles());
+#endif
+  }
 
   // Do n memtable flushes, each of which produces an sstable
   // covering the range [small,large].
@@ -261,6 +299,7 @@ class ColumnFamilyTest : public testing::Test {
     }
   }
 
+#ifndef ROCKSDB_LITE  // GetSortedWalFiles is not supported
   int CountLiveLogFiles() {
     int micros_wait_for_log_deletion = 20000;
     env_->SleepForMicroseconds(micros_wait_for_log_deletion);
@@ -287,15 +326,25 @@ class ColumnFamilyTest : public testing::Test {
       }
     }
     return ret;
+    return 0;
+  }
+#endif  // !ROCKSDB_LITE
+
+  void AssertCountLiveLogFiles(int value) {
+#ifndef ROCKSDB_LITE  // GetSortedWalFiles is not supported
+    ASSERT_EQ(value, CountLiveLogFiles());
+#endif  // !ROCKSDB_LITE
   }
 
   void AssertNumberOfImmutableMemtables(std::vector<int> num_per_cf) {
     assert(num_per_cf.size() == handles_.size());
 
+#ifndef ROCKSDB_LITE  // GetProperty is not supported in lite
     for (size_t i = 0; i < num_per_cf.size(); ++i) {
       ASSERT_EQ(num_per_cf[i], GetProperty(static_cast<int>(i),
                                            "rocksdb.num-immutable-mem-table"));
     }
+#endif  // !ROCKSDB_LITE
   }
 
   void CopyFile(const std::string& source, const std::string& destination,
@@ -332,13 +381,6 @@ class ColumnFamilyTest : public testing::Test {
   Random rnd_;
 };
 
-class DumbLogger : public Logger {
- public:
-  using Logger::Logv;
-  virtual void Logv(const char* format, va_list ap) override {}
-  virtual size_t GetLogFileSize() const override { return 0; }
-};
-
 TEST_F(ColumnFamilyTest, DontReuseColumnFamilyID) {
   for (int iter = 0; iter < 3; ++iter) {
     Open();
@@ -408,10 +450,10 @@ TEST_F(ColumnFamilyTest, DropTest) {
     }
     ASSERT_EQ("bar1", Get(1, "1"));
 
-    ASSERT_EQ(CountLiveFiles(), 1);
+    AssertCountLiveFiles(1);
     DropColumnFamilies({1});
     // make sure that all files are deleted when we drop the column family
-    ASSERT_EQ(CountLiveFiles(), 0);
+    AssertCountLiveFiles(0);
     Destroy();
   }
 }
@@ -552,10 +594,9 @@ TEST_F(ColumnFamilyTest, FlushTest) {
 
     for (int i = 0; i < 3; ++i) {
       uint64_t max_total_in_memory_state =
-          dbfull()->TEST_MaxTotalInMemoryState();
+          MaxTotalInMemoryState();
       Flush(i);
-      ASSERT_EQ(dbfull()->TEST_MaxTotalInMemoryState(),
-                max_total_in_memory_state);
+      AssertMaxTotalInMemoryState(max_total_in_memory_state);
     }
     ASSERT_OK(Put(1, "foofoo", "bar"));
     ASSERT_OK(Put(0, "foofoo", "bar"));
@@ -590,7 +631,7 @@ TEST_F(ColumnFamilyTest, LogDeletionTest) {
   // Each bracket is one log file. if number is in (), it means
   // we don't need it anymore (it's been flushed)
   // []
-  ASSERT_EQ(CountLiveLogFiles(), 0);
+  AssertCountLiveLogFiles(0);
   PutRandomData(0, 1, 100);
   // [0]
   PutRandomData(1, 1, 100);
@@ -598,53 +639,53 @@ TEST_F(ColumnFamilyTest, LogDeletionTest) {
   PutRandomData(1, 1000, 100);
   WaitForFlush(1);
   // [0, (1)] [1]
-  ASSERT_EQ(CountLiveLogFiles(), 2);
+  AssertCountLiveLogFiles(2);
   PutRandomData(0, 1, 100);
   // [0, (1)] [0, 1]
-  ASSERT_EQ(CountLiveLogFiles(), 2);
+  AssertCountLiveLogFiles(2);
   PutRandomData(2, 1, 100);
   // [0, (1)] [0, 1, 2]
   PutRandomData(2, 1000, 100);
   WaitForFlush(2);
   // [0, (1)] [0, 1, (2)] [2]
-  ASSERT_EQ(CountLiveLogFiles(), 3);
+  AssertCountLiveLogFiles(3);
   PutRandomData(2, 1000, 100);
   WaitForFlush(2);
   // [0, (1)] [0, 1, (2)] [(2)] [2]
-  ASSERT_EQ(CountLiveLogFiles(), 4);
+  AssertCountLiveLogFiles(4);
   PutRandomData(3, 1, 100);
   // [0, (1)] [0, 1, (2)] [(2)] [2, 3]
   PutRandomData(1, 1, 100);
   // [0, (1)] [0, 1, (2)] [(2)] [1, 2, 3]
-  ASSERT_EQ(CountLiveLogFiles(), 4);
+  AssertCountLiveLogFiles(4);
   PutRandomData(1, 1000, 100);
   WaitForFlush(1);
   // [0, (1)] [0, (1), (2)] [(2)] [(1), 2, 3] [1]
-  ASSERT_EQ(CountLiveLogFiles(), 5);
+  AssertCountLiveLogFiles(5);
   PutRandomData(0, 1000, 100);
   WaitForFlush(0);
   // [(0), (1)] [(0), (1), (2)] [(2)] [(1), 2, 3] [1, (0)] [0]
   // delete obsolete logs -->
   // [(1), 2, 3] [1, (0)] [0]
-  ASSERT_EQ(CountLiveLogFiles(), 3);
+  AssertCountLiveLogFiles(3);
   PutRandomData(0, 1000, 100);
   WaitForFlush(0);
   // [(1), 2, 3] [1, (0)], [(0)] [0]
-  ASSERT_EQ(CountLiveLogFiles(), 4);
+  AssertCountLiveLogFiles(4);
   PutRandomData(1, 1000, 100);
   WaitForFlush(1);
   // [(1), 2, 3] [(1), (0)] [(0)] [0, (1)] [1]
-  ASSERT_EQ(CountLiveLogFiles(), 5);
+  AssertCountLiveLogFiles(5);
   PutRandomData(2, 1000, 100);
   WaitForFlush(2);
   // [(1), (2), 3] [(1), (0)] [(0)] [0, (1)] [1, (2)], [2]
-  ASSERT_EQ(CountLiveLogFiles(), 6);
+  AssertCountLiveLogFiles(6);
   PutRandomData(3, 1000, 100);
   WaitForFlush(3);
   // [(1), (2), (3)] [(1), (0)] [(0)] [0, (1)] [1, (2)], [2, (3)] [3]
   // delete obsolete logs -->
   // [0, (1)] [1, (2)], [2, (3)] [3]
-  ASSERT_EQ(CountLiveLogFiles(), 4);
+  AssertCountLiveLogFiles(4);
   Close();
 }
 
@@ -663,15 +704,19 @@ TEST_F(ColumnFamilyTest, DifferentWriteBufferSizes) {
   default_cf.write_buffer_size = 100000;
   default_cf.max_write_buffer_number = 10;
   default_cf.min_write_buffer_number_to_merge = 1;
+  default_cf.max_write_buffer_number_to_maintain = 0;
   one.write_buffer_size = 200000;
   one.max_write_buffer_number = 10;
   one.min_write_buffer_number_to_merge = 2;
+  one.max_write_buffer_number_to_maintain = 1;
   two.write_buffer_size = 1000000;
   two.max_write_buffer_number = 10;
   two.min_write_buffer_number_to_merge = 3;
+  two.max_write_buffer_number_to_maintain = 2;
   three.write_buffer_size = 90000;
   three.max_write_buffer_number = 10;
   three.min_write_buffer_number_to_merge = 4;
+  three.max_write_buffer_number_to_maintain = -1;
 
   Reopen({default_cf, one, two, three});
 
@@ -679,72 +724,73 @@ TEST_F(ColumnFamilyTest, DifferentWriteBufferSizes) {
   PutRandomData(0, 100, 1000);
   WaitForFlush(0);
   AssertNumberOfImmutableMemtables({0, 0, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 1);
+  AssertCountLiveLogFiles(1);
   PutRandomData(1, 200, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 2);
+  AssertCountLiveLogFiles(2);
   PutRandomData(2, 1000, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 1, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 3);
+  AssertCountLiveLogFiles(3);
   PutRandomData(2, 1000, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 2, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 4);
+  AssertCountLiveLogFiles(4);
   PutRandomData(3, 90, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 2, 1});
-  ASSERT_EQ(CountLiveLogFiles(), 5);
+  AssertCountLiveLogFiles(5);
   PutRandomData(3, 90, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 2, 2});
-  ASSERT_EQ(CountLiveLogFiles(), 6);
+  AssertCountLiveLogFiles(6);
   PutRandomData(3, 90, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 2, 3});
-  ASSERT_EQ(CountLiveLogFiles(), 7);
+  AssertCountLiveLogFiles(7);
   PutRandomData(0, 100, 1000);
   WaitForFlush(0);
   AssertNumberOfImmutableMemtables({0, 1, 2, 3});
-  ASSERT_EQ(CountLiveLogFiles(), 8);
+  AssertCountLiveLogFiles(8);
   PutRandomData(2, 100, 10000);
   WaitForFlush(2);
   AssertNumberOfImmutableMemtables({0, 1, 0, 3});
-  ASSERT_EQ(CountLiveLogFiles(), 9);
+  AssertCountLiveLogFiles(9);
   PutRandomData(3, 90, 1000);
   WaitForFlush(3);
   AssertNumberOfImmutableMemtables({0, 1, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 10);
+  AssertCountLiveLogFiles(10);
   PutRandomData(3, 90, 1000);
   env_->SleepForMicroseconds(micros_wait_for_flush);
   AssertNumberOfImmutableMemtables({0, 1, 0, 1});
-  ASSERT_EQ(CountLiveLogFiles(), 11);
+  AssertCountLiveLogFiles(11);
   PutRandomData(1, 200, 1000);
   WaitForFlush(1);
   AssertNumberOfImmutableMemtables({0, 0, 0, 1});
-  ASSERT_EQ(CountLiveLogFiles(), 5);
+  AssertCountLiveLogFiles(5);
   PutRandomData(3, 240, 1000);
   WaitForFlush(3);
   PutRandomData(3, 300, 1000);
   WaitForFlush(3);
   AssertNumberOfImmutableMemtables({0, 0, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 12);
+  AssertCountLiveLogFiles(12);
   PutRandomData(0, 100, 1000);
   WaitForFlush(0);
   AssertNumberOfImmutableMemtables({0, 0, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 12);
+  AssertCountLiveLogFiles(12);
   PutRandomData(2, 3*100, 10000);
   WaitForFlush(2);
   AssertNumberOfImmutableMemtables({0, 0, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 12);
+  AssertCountLiveLogFiles(12);
   PutRandomData(1, 2*200, 1000);
   WaitForFlush(1);
   AssertNumberOfImmutableMemtables({0, 0, 0, 0});
-  ASSERT_EQ(CountLiveLogFiles(), 7);
+  AssertCountLiveLogFiles(7);
   Close();
 }
 
+#ifndef ROCKSDB_LITE  // Cuckoo is not supported in lite
 TEST_F(ColumnFamilyTest, MemtableNotSupportSnapshot) {
   Open();
   auto* s1 = dbfull()->GetSnapshot();
@@ -765,6 +811,7 @@ TEST_F(ColumnFamilyTest, MemtableNotSupportSnapshot) {
   ASSERT_TRUE(s3 == nullptr);
   Close();
 }
+#endif  // !ROCKSDB_LITE
 
 TEST_F(ColumnFamilyTest, DifferentMergeOperators) {
   Open();
@@ -813,6 +860,7 @@ TEST_F(ColumnFamilyTest, DifferentCompactionStyles) {
   default_cf.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   one.compaction_style = kCompactionStyleUniversal;
+
   one.num_levels = 1;
   // trigger compaction if there are >= 4 files
   one.level0_file_num_compaction_trigger = 4;
@@ -820,7 +868,6 @@ TEST_F(ColumnFamilyTest, DifferentCompactionStyles) {
 
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
-  two.max_mem_compaction_level = 0;
   two.level0_file_num_compaction_trigger = 3;
   two.write_buffer_size = 100000;
 
@@ -830,14 +877,14 @@ TEST_F(ColumnFamilyTest, DifferentCompactionStyles) {
   for (int i = 0; i < one.level0_file_num_compaction_trigger - 1; ++i) {
     PutRandomData(1, 11, 10000);
     WaitForFlush(1);
-    ASSERT_EQ(ToString(i + 1), FilesPerLevel(1));
+    AssertFilesPerLevel(ToString(i + 1), 1);
   }
 
   // SETUP column family "two" -- level style with 4 levels
   for (int i = 0; i < two.level0_file_num_compaction_trigger - 1; ++i) {
     PutRandomData(2, 15, 10000);
     WaitForFlush(2);
-    ASSERT_EQ(ToString(i + 1), FilesPerLevel(2));
+    AssertFilesPerLevel(ToString(i + 1), 2);
   }
 
   // TRIGGER compaction "one"
@@ -850,16 +897,17 @@ TEST_F(ColumnFamilyTest, DifferentCompactionStyles) {
   WaitForCompaction();
 
   // VERIFY compaction "one"
-  ASSERT_EQ("1", FilesPerLevel(1));
+  AssertFilesPerLevel("1", 1);
 
   // VERIFY compaction "two"
-  ASSERT_EQ("0,1", FilesPerLevel(2));
+  AssertFilesPerLevel("0,1", 2);
   CompactAll(2);
-  ASSERT_EQ("0,1", FilesPerLevel(2));
+  AssertFilesPerLevel("0,1", 2);
 
   Close();
 }
 
+#ifndef ROCKSDB_LITE  // Tailing interator not supported
 namespace {
 std::string IterStatus(Iterator* iter) {
   std::string result;
@@ -916,7 +964,9 @@ TEST_F(ColumnFamilyTest, NewIteratorsTest) {
     Destroy();
   }
 }
+#endif  // !ROCKSDB_LITE
 
+#ifndef ROCKSDB_LITE  // ReadOnlyDB is not supported
 TEST_F(ColumnFamilyTest, ReadOnlyDBTest) {
   Open();
   CreateColumnFamiliesAndReopen({"one", "two", "three", "four"});
@@ -966,6 +1016,7 @@ TEST_F(ColumnFamilyTest, ReadOnlyDBTest) {
   s = OpenReadOnly({"one", "four"});
   ASSERT_TRUE(!s.ok());
 }
+#endif  // !ROCKSDB_LITE
 
 TEST_F(ColumnFamilyTest, DontRollEmptyLogs) {
   Open();
@@ -981,7 +1032,7 @@ TEST_F(ColumnFamilyTest, DontRollEmptyLogs) {
   }
 
   for (int i = 0; i < 4; ++i) {
-    dbfull()->TEST_WaitForFlushMemTable(handles_[i]);
+    WaitForFlush(i);
   }
   int total_new_writable_files =
       env_->GetNumberOfNewWritableFileCalls() - num_writable_file_start;
@@ -1005,7 +1056,8 @@ TEST_F(ColumnFamilyTest, FlushStaleColumnFamilies) {
   for (int i = 0; i < 2; ++i) {
     PutRandomData(0, 100, 1000);  // flush
     WaitForFlush(0);
-    ASSERT_EQ(i + 1, CountLiveFiles());
+
+    AssertCountLiveFiles(i + 1);
   }
   // third flush. now, CF [two] should be detected as stale and flushed
   // column family 1 should not be flushed since it's empty
@@ -1014,7 +1066,7 @@ TEST_F(ColumnFamilyTest, FlushStaleColumnFamilies) {
   WaitForFlush(2);
   // 3 files for default column families, 1 file for column family [two], zero
   // files for column family [one], because it's empty
-  ASSERT_EQ(4, CountLiveFiles());
+  AssertCountLiveFiles(4);
   Close();
 }
 
@@ -1029,21 +1081,35 @@ TEST_F(ColumnFamilyTest, CreateMissingColumnFamilies) {
 
 TEST_F(ColumnFamilyTest, SanitizeOptions) {
   DBOptions db_options;
-  for (int i = 1; i <= 3; i++) {
-    for (int j = 1; j <= 3; j++) {
-      for (int k = 1; k <= 3; k++) {
-        ColumnFamilyOptions original;
-        original.level0_stop_writes_trigger = i;
-        original.level0_slowdown_writes_trigger = j;
-        original.level0_file_num_compaction_trigger = k;
-        ColumnFamilyOptions result =
-            SanitizeOptions(db_options, nullptr, original);
-        ASSERT_TRUE(result.level0_stop_writes_trigger >=
-                    result.level0_slowdown_writes_trigger);
-        ASSERT_TRUE(result.level0_slowdown_writes_trigger >=
-                    result.level0_file_num_compaction_trigger);
-        ASSERT_TRUE(result.level0_file_num_compaction_trigger ==
-                    original.level0_file_num_compaction_trigger);
+  for (int s = kCompactionStyleLevel; s <= kCompactionStyleUniversal; ++s) {
+    for (int l = 0; l <= 2; l++) {
+      for (int i = 1; i <= 3; i++) {
+        for (int j = 1; j <= 3; j++) {
+          for (int k = 1; k <= 3; k++) {
+            ColumnFamilyOptions original;
+            original.compaction_style = static_cast<CompactionStyle>(s);
+            original.num_levels = l;
+            original.level0_stop_writes_trigger = i;
+            original.level0_slowdown_writes_trigger = j;
+            original.level0_file_num_compaction_trigger = k;
+            ColumnFamilyOptions result =
+                SanitizeOptions(db_options, nullptr, original);
+            ASSERT_TRUE(result.level0_stop_writes_trigger >=
+                        result.level0_slowdown_writes_trigger);
+            ASSERT_TRUE(result.level0_slowdown_writes_trigger >=
+                        result.level0_file_num_compaction_trigger);
+            ASSERT_TRUE(result.level0_file_num_compaction_trigger ==
+                        original.level0_file_num_compaction_trigger);
+            if (s == kCompactionStyleLevel) {
+              ASSERT_GE(result.num_levels, 2);
+            } else {
+              ASSERT_GE(result.num_levels, 1);
+              if (original.num_levels >= 1) {
+                ASSERT_EQ(result.num_levels, original.num_levels);
+              }
+            }
+          }
+        }
       }
     }
   }

db/compact_files_test.cc

@@ -3,12 +3,15 @@
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
 
+#ifndef ROCKSDB_LITE
+
 #include <mutex>
 #include <string>
 #include <vector>
 
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
+#include "util/string_util.h"
 #include "util/testharness.h"
 
 namespace rocksdb {
@@ -31,12 +34,9 @@ class FlushedFileCollector : public EventListener {
   ~FlushedFileCollector() {}
 
   virtual void OnFlushCompleted(
-      DB* db, const std::string& column_family_name,
-      const std::string& file_path,
-      bool triggered_writes_slowdown,
-      bool triggered_writes_stop) {
+      DB* db, const FlushJobInfo& info) override {
     std::lock_guard<std::mutex> lock(mutex_);
-    flushed_files_.push_back(file_path);
+    flushed_files_.push_back(info.file_path);
   }
 
   std::vector<std::string> GetFlushedFiles() {
@@ -79,9 +79,8 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
 
   // create couple files
   for (int i = 1000; i < 2000; ++i) {
-    db->Put(WriteOptions(),
-        std::to_string(i),
-        std::string(kWriteBufferSize / 10, 'a' + (i % 26)));
+    db->Put(WriteOptions(), ToString(i),
+            std::string(kWriteBufferSize / 10, 'a' + (i % 26)));
   }
 
   auto l0_files = collector->GetFlushedFiles();
@@ -92,7 +91,7 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
 
   // verify all compaction input files are deleted
   for (auto fname : l0_files) {
-    ASSERT_TRUE(!env_->FileExists(fname));
+    ASSERT_EQ(Status::NotFound(), env_->FileExists(fname));
   }
   delete db;
 }
@@ -103,3 +102,14 @@ int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }
+
+#else
+#include <stdio.h>
+
+int main(int argc, char** argv) {
+  fprintf(stderr,
+          "SKIPPED as DBImpl::CompactFiles is not supported in ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // !ROCKSDB_LITE

db/compacted_db_impl.cc

@@ -4,7 +4,7 @@
 //  of patent rights can be found in the PATENTS file in the same directory.
 
 #ifndef ROCKSDB_LITE
-#include "utilities/compacted_db/compacted_db_impl.h"
+#include "db/compacted_db_impl.h"
 #include "db/db_impl.h"
 #include "db/version_set.h"
 #include "table/get_context.h"

db/compacted_db_impl.h

@@ -54,10 +54,9 @@ class CompactedDBImpl : public DBImpl {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
   using DBImpl::CompactRange;
-  virtual Status CompactRange(ColumnFamilyHandle* column_family,
-                              const Slice* begin, const Slice* end,
-                              bool reduce_level = false, int target_level = -1,
-                              uint32_t target_path_id = 0) 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.");
   }
 

db/compaction.cc

@@ -16,6 +16,7 @@
 #include <inttypes.h>
 #include <vector>
 
+#include "rocksdb/compaction_filter.h"
 #include "db/column_family.h"
 #include "util/logging.h"
 #include "util/sync_point.h"
@@ -148,10 +149,32 @@ bool Compaction::IsTrivialMove() const {
   // Otherwise, the move could create a parent file that will require
   // a very expensive merge later on.
   // If start_level_== output_level_, the purpose is to force compaction
-  // filter to be applied to that level, and thus cannot be a trivia move.
+  // filter to be applied to that level, and thus cannot be a trivial move.
+
+  // Check if start level have files with overlapping ranges
+  if (start_level_ == 0 &&
+      input_version_->storage_info()->level0_non_overlapping() == false) {
+    // We cannot move files from L0 to L1 if the files are overlapping
+    return false;
+  }
+
+  if (is_manual_compaction_ &&
+      (cfd_->ioptions()->compaction_filter != nullptr ||
+       cfd_->ioptions()->compaction_filter_factory != nullptr)) {
+    // This is a manual compaction and we have a compaction filter that should
+    // be executed, we cannot do a trivial move
+    return false;
+  }
+
+  // Used in universal compaction, where trivial move can be done if the
+  // input files are non overlapping
+  if ((cfd_->ioptions()->compaction_options_universal.allow_trivial_move) &&
+      (output_level_ != 0)) {
+    return is_trivial_move_;
+  }
+
   return (start_level_ != output_level_ && num_input_levels() == 1 &&
-          num_input_files(0) == 1 &&
-          input(0, 0)->fd.GetPathId() == GetOutputPathId() &&
+          input(0, 0)->fd.GetPathId() == output_path_id() &&
           InputCompressionMatchesOutput() &&
           TotalFileSize(grandparents_) <= max_grandparent_overlap_bytes_);
 }
@@ -247,7 +270,8 @@ const char* Compaction::InputLevelSummary(
       is_first = false;
     }
     len += snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
-                    "%zu@%d", input_level.size(), input_level.level);
+                    "%" ROCKSDB_PRIszt "@%d", input_level.size(),
+                    input_level.level);
   }
   snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
            " files to L%d", output_level());
@@ -340,4 +364,16 @@ uint64_t Compaction::OutputFilePreallocationSize() {
   return preallocation_size * 1.1;
 }
 
+std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
+  if (!cfd_->ioptions()->compaction_filter_factory) {
+    return nullptr;
+  }
+
+  CompactionFilter::Context context;
+  context.is_full_compaction = is_full_compaction_;
+  context.is_manual_compaction = is_manual_compaction_;
+  return cfd_->ioptions()->compaction_filter_factory->CreateCompactionFilter(
+      context);
+}
+
 }  // namespace rocksdb

db/compaction.h

@@ -29,6 +29,7 @@ struct CompactionInputFiles {
 class Version;
 class ColumnFamilyData;
 class VersionStorageInfo;
+class CompactionFilter;
 
 // A Compaction encapsulates information about a compaction.
 class Compaction {
@@ -107,22 +108,20 @@ class Compaction {
   }
 
   // Maximum size of files to build during this compaction.
-  uint64_t MaxOutputFileSize() const { return max_output_file_size_; }
+  uint64_t max_output_file_size() const { return max_output_file_size_; }
 
   // What compression for output
-  CompressionType OutputCompressionType() const { return output_compression_; }
+  CompressionType output_compression() const { return output_compression_; }
 
   // Whether need to write output file to second DB path.
-  uint32_t GetOutputPathId() const { return output_path_id_; }
+  uint32_t output_path_id() const { return output_path_id_; }
 
   // Is this a trivial compaction that can be implemented by just
   // moving a single input file to the next level (no merging or splitting)
   bool IsTrivialMove() const;
 
   // If true, then the compaction can be done by simply deleting input files.
-  bool IsDeletionCompaction() const {
-    return deletion_compaction_;
-  }
+  bool deletion_compaction() const { return deletion_compaction_; }
 
   // Add all inputs to this compaction as delete operations to *edit.
   void AddInputDeletions(VersionEdit* edit);
@@ -148,13 +147,26 @@ class Compaction {
   double score() const { return score_; }
 
   // Is this compaction creating a file in the bottom most level?
-  bool BottomMostLevel() { return bottommost_level_; }
+  bool bottommost_level() { return bottommost_level_; }
 
   // Does this compaction include all sst files?
-  bool IsFullCompaction() { return is_full_compaction_; }
+  bool is_full_compaction() { return is_full_compaction_; }
 
   // Was this compaction triggered manually by the client?
-  bool IsManualCompaction() { return is_manual_compaction_; }
+  bool is_manual_compaction() { return is_manual_compaction_; }
+
+  // Used when allow_trivial_move option is set in
+  // Universal compaction. If all the input files are
+  // non overlapping, then is_trivial_move_ variable
+  // will be set true, else false
+  void set_is_trivial_move(bool trivial_move) {
+    is_trivial_move_ = trivial_move;
+  }
+
+  // Used when allow_trivial_move option is set in
+  // Universal compaction. Returns true, if the input files
+  // are non-overlapping and can be trivially moved.
+  bool is_trivial_move() { return is_trivial_move_; }
 
   // Return the MutableCFOptions that should be used throughout the compaction
   // procedure
@@ -179,6 +191,20 @@ class Compaction {
   // to pick up the next file to be compacted from files_by_size_
   void ResetNextCompactionIndex();
 
+  // Create a CompactionFilter from compaction_filter_factory
+  std::unique_ptr<CompactionFilter> CreateCompactionFilter() const;
+
+  // Should this compaction be broken up into smaller ones run in parallel?
+  bool IsSubCompaction() const {
+    return start_level_ == 0 && output_level_ == 1
+        && mutable_cf_options_.num_subcompactions > 1;
+  }
+
+  // If is_sub_compaction == true, how many smaller compactions should execute
+  int NumSubCompactions() const {
+    return mutable_cf_options_.num_subcompactions;
+  }
+
  private:
   // mark (or clear) all files that are being compacted
   void MarkFilesBeingCompacted(bool mark_as_compacted);
@@ -230,6 +256,11 @@ class Compaction {
   // Is this compaction requested by the client?
   const bool is_manual_compaction_;
 
+  // True if we can do trivial move in Universal multi level
+  // compaction
+
+  bool is_trivial_move_;
+
   // "level_ptrs_" holds indices into "input_version_->levels_", where each
   // index remembers which file of an associated level we are currently used
   // to check KeyNotExistsBeyondOutputLevel() for deletion operation.

db/compaction_job.h

@@ -27,6 +27,7 @@
 #include "rocksdb/env.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/compaction_filter.h"
+#include "rocksdb/compaction_job_stats.h"
 #include "rocksdb/transaction_log.h"
 #include "util/autovector.h"
 #include "util/event_logger.h"
@@ -57,8 +58,9 @@ class CompactionJob {
                 Statistics* stats,
                 std::vector<SequenceNumber> existing_snapshots,
                 std::shared_ptr<Cache> table_cache,
-                std::function<uint64_t()> yield_callback,
-                EventLogger* event_logger, bool paranoid_file_checks);
+                EventLogger* event_logger, bool paranoid_file_checks,
+                const std::string& dbname,
+                CompactionJobStats* compaction_job_stats);
 
   ~CompactionJob();
 
@@ -71,23 +73,31 @@ class CompactionJob {
   void Prepare();
   // REQUIRED mutex not held
   Status Run();
+
   // REQUIRED: mutex held
   // status is the return of Run()
   void Install(Status* status, const MutableCFOptions& mutable_cf_options,
                InstrumentedMutex* db_mutex);
 
  private:
+  // REQUIRED: mutex not held
+  Status SubCompactionRun(Slice* start, Slice* end);
+
+  void GetSubCompactionBoundaries();
   // update the thread status for starting a compaction.
   void ReportStartedCompaction(Compaction* compaction);
   void AllocateCompactionOutputFileNumbers();
-  // Call compaction filter if is_compaction_v2 is not true. Then iterate
-  // through input and compact the kv-pairs
+  // Call compaction filter. Then iterate through input and compact the
+  // kv-pairs
   Status ProcessKeyValueCompaction(int64_t* imm_micros, Iterator* input,
-                                   bool is_compaction_v2);
-  // Call compaction_filter_v2->Filter() on kv-pairs in compact
-  void CallCompactionFilterV2(CompactionFilterV2* compaction_filter_v2,
-                              uint64_t* time);
-  Status FinishCompactionOutputFile(Iterator* input);
+                                    Slice* start = nullptr,
+                                    Slice* end = nullptr);
+
+  Status WriteKeyValue(const Slice& key, const Slice& value,
+                       const ParsedInternalKey& ikey,
+                       const Status& input_status);
+
+  Status FinishCompactionOutputFile(const Status& input_status);
   Status InstallCompactionResults(InstrumentedMutex* db_mutex,
                                   const MutableCFOptions& mutable_cf_options);
   SequenceNumber findEarliestVisibleSnapshot(
@@ -96,12 +106,24 @@ class CompactionJob {
   void RecordCompactionIOStats();
   Status OpenCompactionOutputFile();
   void CleanupCompaction(const Status& status);
+  void UpdateCompactionJobStats(
+    const InternalStats::CompactionStats& stats) const;
+  void RecordDroppedKeys(int64_t* key_drop_user,
+                         int64_t* key_drop_newer_entry,
+                         int64_t* key_drop_obsolete);
+
+  void UpdateCompactionStats();
+  void UpdateCompactionInputStatsHelper(
+      int* num_files, uint64_t* bytes_read, int input_level);
+
+  void LogCompaction(ColumnFamilyData* cfd, Compaction* compaction);
 
   int job_id_;
 
   // CompactionJob state
   struct CompactionState;
   CompactionState* compact_;
+  CompactionJobStats* compaction_job_stats_;
 
   bool bottommost_level_;
   SequenceNumber earliest_snapshot_;
@@ -111,6 +133,7 @@ class CompactionJob {
   InternalStats::CompactionStats compaction_stats_;
 
   // DBImpl state
+  const std::string& dbname_;
   const DBOptions& db_options_;
   const EnvOptions& env_options_;
   Env* env_;
@@ -127,12 +150,10 @@ class CompactionJob {
   std::vector<SequenceNumber> existing_snapshots_;
   std::shared_ptr<Cache> table_cache_;
 
-  // yield callback
-  std::function<uint64_t()> yield_callback_;
-
   EventLogger* event_logger_;
 
   bool paranoid_file_checks_;
+  std::vector<Slice> sub_compaction_boundaries_;
 };
 
 }  // namespace rocksdb

db/compaction_job_stats_test.cc

@@ -0,0 +1,967 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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.
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
+#include <algorithm>
+#include <iostream>
+#include <mutex>
+#include <queue>
+#include <set>
+#include <thread>
+#include <unordered_set>
+#include <utility>
+
+#include "db/db_impl.h"
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/job_context.h"
+#include "db/version_set.h"
+#include "db/write_batch_internal.h"
+#include "port/stack_trace.h"
+#include "rocksdb/cache.h"
+#include "rocksdb/compaction_filter.h"
+#include "rocksdb/convenience.h"
+#include "rocksdb/db.h"
+#include "rocksdb/env.h"
+#include "rocksdb/experimental.h"
+#include "rocksdb/filter_policy.h"
+#include "rocksdb/options.h"
+#include "rocksdb/perf_context.h"
+#include "rocksdb/slice.h"
+#include "rocksdb/slice_transform.h"
+#include "rocksdb/table.h"
+#include "rocksdb/table_properties.h"
+#include "rocksdb/thread_status.h"
+#include "rocksdb/utilities/checkpoint.h"
+#include "rocksdb/utilities/write_batch_with_index.h"
+#include "table/block_based_table_factory.h"
+#include "table/mock_table.h"
+#include "table/plain_table_factory.h"
+#include "util/compression.h"
+#include "util/hash.h"
+#include "util/hash_linklist_rep.h"
+#include "util/logging.h"
+#include "util/mock_env.h"
+#include "util/mutexlock.h"
+#include "util/rate_limiter.h"
+#include "util/scoped_arena_iterator.h"
+#include "util/statistics.h"
+#include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+#include "util/thread_status_util.h"
+#include "util/xfunc.h"
+#include "utilities/merge_operators.h"
+
+#if !defined(IOS_CROSS_COMPILE) && (!defined(NDEBUG) || !defined(OS_WIN))
+#ifndef ROCKSDB_LITE
+namespace rocksdb {
+
+static std::string RandomString(Random* rnd, int len, double ratio) {
+  std::string r;
+  test::CompressibleString(rnd, ratio, len, &r);
+  return r;
+}
+
+std::string Key(uint64_t key, int length) {
+  const int kBufSize = 1000;
+  char buf[kBufSize];
+  if (length > kBufSize) {
+    length = kBufSize;
+  }
+  snprintf(buf, kBufSize, "%0*" PRIu64, length, key);
+  return std::string(buf);
+}
+
+class CompactionJobStatsTest : public testing::Test,
+                               public testing::WithParamInterface<bool> {
+ public:
+  std::string dbname_;
+  std::string alternative_wal_dir_;
+  Env* env_;
+  DB* db_;
+  std::vector<ColumnFamilyHandle*> handles_;
+  uint32_t num_subcompactions_;
+
+  Options last_options_;
+
+  CompactionJobStatsTest() : env_(Env::Default()) {
+    env_->SetBackgroundThreads(1, Env::LOW);
+    env_->SetBackgroundThreads(1, Env::HIGH);
+    dbname_ = test::TmpDir(env_) + "/compaction_job_stats_test";
+    alternative_wal_dir_ = dbname_ + "/wal";
+    Options options;
+    options.create_if_missing = true;
+    num_subcompactions_ = GetParam();
+    options.num_subcompactions = num_subcompactions_;
+    auto delete_options = options;
+    delete_options.wal_dir = alternative_wal_dir_;
+    EXPECT_OK(DestroyDB(dbname_, delete_options));
+    // Destroy it for not alternative WAL dir is used.
+    EXPECT_OK(DestroyDB(dbname_, options));
+    db_ = nullptr;
+    Reopen(options);
+  }
+
+  ~CompactionJobStatsTest() {
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->LoadDependency({});
+    rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+    Close();
+    Options options;
+    options.db_paths.emplace_back(dbname_, 0);
+    options.db_paths.emplace_back(dbname_ + "_2", 0);
+    options.db_paths.emplace_back(dbname_ + "_3", 0);
+    options.db_paths.emplace_back(dbname_ + "_4", 0);
+    EXPECT_OK(DestroyDB(dbname_, options));
+  }
+
+  // Required if inheriting from testing::WithParamInterface<>
+  static void SetUpTestCase() {}
+  static void TearDownTestCase() {}
+
+  DBImpl* dbfull() {
+    return reinterpret_cast<DBImpl*>(db_);
+  }
+
+  void CreateColumnFamilies(const std::vector<std::string>& cfs,
+                            const Options& options) {
+    ColumnFamilyOptions cf_opts(options);
+    size_t cfi = handles_.size();
+    handles_.resize(cfi + cfs.size());
+    for (auto cf : cfs) {
+      ASSERT_OK(db_->CreateColumnFamily(cf_opts, cf, &handles_[cfi++]));
+    }
+  }
+
+  void CreateAndReopenWithCF(const std::vector<std::string>& cfs,
+                             const Options& options) {
+    CreateColumnFamilies(cfs, options);
+    std::vector<std::string> cfs_plus_default = cfs;
+    cfs_plus_default.insert(cfs_plus_default.begin(), kDefaultColumnFamilyName);
+    ReopenWithColumnFamilies(cfs_plus_default, options);
+  }
+
+  void ReopenWithColumnFamilies(const std::vector<std::string>& cfs,
+                                const std::vector<Options>& options) {
+    ASSERT_OK(TryReopenWithColumnFamilies(cfs, options));
+  }
+
+  void ReopenWithColumnFamilies(const std::vector<std::string>& cfs,
+                                const Options& options) {
+    ASSERT_OK(TryReopenWithColumnFamilies(cfs, options));
+  }
+
+  Status TryReopenWithColumnFamilies(
+      const std::vector<std::string>& cfs,
+      const std::vector<Options>& options) {
+    Close();
+    EXPECT_EQ(cfs.size(), options.size());
+    std::vector<ColumnFamilyDescriptor> column_families;
+    for (size_t i = 0; i < cfs.size(); ++i) {
+      column_families.push_back(ColumnFamilyDescriptor(cfs[i], options[i]));
+    }
+    DBOptions db_opts = DBOptions(options[0]);
+    return DB::Open(db_opts, dbname_, column_families, &handles_, &db_);
+  }
+
+  Status TryReopenWithColumnFamilies(const std::vector<std::string>& cfs,
+                                     const Options& options) {
+    Close();
+    std::vector<Options> v_opts(cfs.size(), options);
+    return TryReopenWithColumnFamilies(cfs, v_opts);
+  }
+
+  void Reopen(const Options& options) {
+    ASSERT_OK(TryReopen(options));
+  }
+
+  void Close() {
+    for (auto h : handles_) {
+      delete h;
+    }
+    handles_.clear();
+    delete db_;
+    db_ = nullptr;
+  }
+
+  void DestroyAndReopen(const Options& options) {
+    // Destroy using last options
+    Destroy(last_options_);
+    ASSERT_OK(TryReopen(options));
+  }
+
+  void Destroy(const Options& options) {
+    Close();
+    ASSERT_OK(DestroyDB(dbname_, options));
+  }
+
+  Status ReadOnlyReopen(const Options& options) {
+    return DB::OpenForReadOnly(options, dbname_, &db_);
+  }
+
+  Status TryReopen(const Options& options) {
+    Close();
+    last_options_ = options;
+    return DB::Open(options, dbname_, &db_);
+  }
+
+  Status Flush(int cf = 0) {
+    if (cf == 0) {
+      return db_->Flush(FlushOptions());
+    } else {
+      return db_->Flush(FlushOptions(), handles_[cf]);
+    }
+  }
+
+  Status Put(const Slice& k, const Slice& v, WriteOptions wo = WriteOptions()) {
+    return db_->Put(wo, k, v);
+  }
+
+  Status Put(int cf, const Slice& k, const Slice& v,
+             WriteOptions wo = WriteOptions()) {
+    return db_->Put(wo, handles_[cf], k, v);
+  }
+
+  Status Delete(const std::string& k) {
+    return db_->Delete(WriteOptions(), k);
+  }
+
+  Status Delete(int cf, const std::string& k) {
+    return db_->Delete(WriteOptions(), handles_[cf], k);
+  }
+
+  std::string Get(const std::string& k, const Snapshot* snapshot = nullptr) {
+    ReadOptions options;
+    options.verify_checksums = true;
+    options.snapshot = snapshot;
+    std::string result;
+    Status s = db_->Get(options, k, &result);
+    if (s.IsNotFound()) {
+      result = "NOT_FOUND";
+    } else if (!s.ok()) {
+      result = s.ToString();
+    }
+    return result;
+  }
+
+  std::string Get(int cf, const std::string& k,
+                  const Snapshot* snapshot = nullptr) {
+    ReadOptions options;
+    options.verify_checksums = true;
+    options.snapshot = snapshot;
+    std::string result;
+    Status s = db_->Get(options, handles_[cf], k, &result);
+    if (s.IsNotFound()) {
+      result = "NOT_FOUND";
+    } else if (!s.ok()) {
+      result = s.ToString();
+    }
+    return result;
+  }
+
+  int NumTableFilesAtLevel(int level, int cf = 0) {
+    std::string property;
+    if (cf == 0) {
+      // default cfd
+      EXPECT_TRUE(db_->GetProperty(
+          "rocksdb.num-files-at-level" + NumberToString(level), &property));
+    } else {
+      EXPECT_TRUE(db_->GetProperty(
+          handles_[cf], "rocksdb.num-files-at-level" + NumberToString(level),
+          &property));
+    }
+    return atoi(property.c_str());
+  }
+
+  // Return spread of files per level
+  std::string FilesPerLevel(int cf = 0) {
+    int num_levels =
+        (cf == 0) ? db_->NumberLevels() : db_->NumberLevels(handles_[1]);
+    std::string result;
+    size_t last_non_zero_offset = 0;
+    for (int level = 0; level < num_levels; level++) {
+      int f = NumTableFilesAtLevel(level, cf);
+      char buf[100];
+      snprintf(buf, sizeof(buf), "%s%d", (level ? "," : ""), f);
+      result += buf;
+      if (f > 0) {
+        last_non_zero_offset = result.size();
+      }
+    }
+    result.resize(last_non_zero_offset);
+    return result;
+  }
+
+  uint64_t Size(const Slice& start, const Slice& limit, int cf = 0) {
+    Range r(start, limit);
+    uint64_t size;
+    if (cf == 0) {
+      db_->GetApproximateSizes(&r, 1, &size);
+    } else {
+      db_->GetApproximateSizes(handles_[1], &r, 1, &size);
+    }
+    return size;
+  }
+
+  void Compact(int cf, const Slice& start, const Slice& limit,
+               uint32_t target_path_id) {
+    CompactRangeOptions compact_options;
+    compact_options.target_path_id = target_path_id;
+    ASSERT_OK(db_->CompactRange(compact_options, handles_[cf], &start, &limit));
+  }
+
+  void Compact(int cf, const Slice& start, const Slice& limit) {
+    ASSERT_OK(
+        db_->CompactRange(CompactRangeOptions(), handles_[cf], &start, &limit));
+  }
+
+  void Compact(const Slice& start, const Slice& limit) {
+    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), &start, &limit));
+  }
+
+  void TEST_Compact(int level, int cf, const Slice& start, const Slice& limit) {
+    ASSERT_OK(dbfull()->TEST_CompactRange(level, &start, &limit, handles_[cf],
+                                          true /* disallow trivial move */));
+  }
+
+  // Do n memtable compactions, each of which produces an sstable
+  // covering the range [small,large].
+  void MakeTables(int n, const std::string& small, const std::string& large,
+                  int cf = 0) {
+    for (int i = 0; i < n; i++) {
+      ASSERT_OK(Put(cf, small, "begin"));
+      ASSERT_OK(Put(cf, large, "end"));
+      ASSERT_OK(Flush(cf));
+    }
+  }
+
+  static void SetDeletionCompactionStats(
+      CompactionJobStats *stats, uint64_t input_deletions,
+      uint64_t expired_deletions, uint64_t records_replaced) {
+    stats->num_input_deletion_records = input_deletions;
+    stats->num_expired_deletion_records = expired_deletions;
+    stats->num_records_replaced = records_replaced;
+  }
+
+  void MakeTableWithKeyValues(
+    Random* rnd, uint64_t smallest, uint64_t largest,
+    int key_size, int value_size, uint64_t interval,
+    double ratio, int cf = 0) {
+    for (auto key = smallest; key < largest; key += interval) {
+      ASSERT_OK(Put(cf, Slice(Key(key, key_size)),
+                        Slice(RandomString(rnd, value_size, ratio))));
+    }
+    ASSERT_OK(Flush(cf));
+  }
+
+  // This function behaves with the implicit understanding that two
+  // rounds of keys are inserted into the database, as per the behavior
+  // of the DeletionStatsTest.
+  void SelectivelyDeleteKeys(uint64_t smallest, uint64_t largest,
+    uint64_t interval, int deletion_interval, int key_size,
+    uint64_t cutoff_key_num, CompactionJobStats* stats, int cf = 0) {
+
+    // interval needs to be >= 2 so that deletion entries can be inserted
+    // that are intended to not result in an actual key deletion by using
+    // an offset of 1 from another existing key
+    ASSERT_GE(interval, 2);
+
+    uint64_t ctr = 1;
+    uint32_t deletions_made = 0;
+    uint32_t num_deleted = 0;
+    uint32_t num_expired = 0;
+    for (auto key = smallest; key <= largest; key += interval, ctr++) {
+      if (ctr % deletion_interval == 0) {
+        ASSERT_OK(Delete(cf, Key(key, key_size)));
+        deletions_made++;
+        num_deleted++;
+
+        if (key > cutoff_key_num) {
+          num_expired++;
+        }
+      }
+    }
+
+    // Insert some deletions for keys that don't exist that
+    // are both in and out of the key range
+    ASSERT_OK(Delete(cf, Key(smallest+1, key_size)));
+    deletions_made++;
+
+    ASSERT_OK(Delete(cf, Key(smallest-1, key_size)));
+    deletions_made++;
+    num_expired++;
+
+    ASSERT_OK(Delete(cf, Key(smallest-9, key_size)));
+    deletions_made++;
+    num_expired++;
+
+    ASSERT_OK(Flush(cf));
+    SetDeletionCompactionStats(stats, deletions_made, num_expired,
+      num_deleted);
+  }
+};
+
+// An EventListener which helps verify the compaction results in
+// test CompactionJobStatsTest.
+class CompactionJobStatsChecker : public EventListener {
+ public:
+  CompactionJobStatsChecker() : compression_enabled_(false) {}
+
+  size_t NumberOfUnverifiedStats() { return expected_stats_.size(); }
+
+  // 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.
+  virtual void OnCompactionCompleted(DB *db, const CompactionJobInfo& ci) {
+    std::lock_guard<std::mutex> lock(mutex_);
+    if (expected_stats_.size()) {
+      Verify(ci.stats, expected_stats_.front());
+      expected_stats_.pop();
+    }
+  }
+
+  // A helper function which verifies whether two CompactionJobStats
+  // match.  The verification of all compaction stats are done by
+  // ASSERT_EQ except for the total input / output bytes, which we
+  // use ASSERT_GE and ASSERT_LE with a reasonable bias ---
+  // 10% in uncompressed case and 20% when compression is used.
+  virtual void Verify(const CompactionJobStats& current_stats,
+              const CompactionJobStats& stats) {
+    // time
+    ASSERT_GT(current_stats.elapsed_micros, 0U);
+
+    ASSERT_EQ(current_stats.num_input_records,
+        stats.num_input_records);
+    ASSERT_EQ(current_stats.num_input_files,
+        stats.num_input_files);
+    ASSERT_EQ(current_stats.num_input_files_at_output_level,
+        stats.num_input_files_at_output_level);
+
+    ASSERT_EQ(current_stats.num_output_records,
+        stats.num_output_records);
+    ASSERT_EQ(current_stats.num_output_files,
+        stats.num_output_files);
+
+    ASSERT_EQ(current_stats.is_manual_compaction,
+        stats.is_manual_compaction);
+
+    // file size
+    double kFileSizeBias = compression_enabled_ ? 0.20 : 0.10;
+    ASSERT_GE(current_stats.total_input_bytes * (1.00 + kFileSizeBias),
+              stats.total_input_bytes);
+    ASSERT_LE(current_stats.total_input_bytes,
+              stats.total_input_bytes * (1.00 + kFileSizeBias));
+    ASSERT_GE(current_stats.total_output_bytes * (1.00 + kFileSizeBias),
+              stats.total_output_bytes);
+    ASSERT_LE(current_stats.total_output_bytes,
+              stats.total_output_bytes * (1.00 + kFileSizeBias));
+    ASSERT_EQ(current_stats.total_input_raw_key_bytes,
+              stats.total_input_raw_key_bytes);
+    ASSERT_EQ(current_stats.total_input_raw_value_bytes,
+              stats.total_input_raw_value_bytes);
+
+    ASSERT_EQ(current_stats.num_records_replaced,
+        stats.num_records_replaced);
+
+    ASSERT_EQ(current_stats.num_corrupt_keys,
+        stats.num_corrupt_keys);
+
+    ASSERT_EQ(
+        std::string(current_stats.smallest_output_key_prefix),
+        std::string(stats.smallest_output_key_prefix));
+    ASSERT_EQ(
+        std::string(current_stats.largest_output_key_prefix),
+        std::string(stats.largest_output_key_prefix));
+  }
+
+  // Add an expected compaction stats, which will be used to
+  // verify the CompactionJobStats returned by the OnCompactionCompleted()
+  // callback.
+  void AddExpectedStats(const CompactionJobStats& stats) {
+    std::lock_guard<std::mutex> lock(mutex_);
+    expected_stats_.push(stats);
+  }
+
+  void EnableCompression(bool flag) {
+    compression_enabled_ = flag;
+  }
+
+ private:
+  std::mutex mutex_;
+  std::queue<CompactionJobStats> expected_stats_;
+  bool compression_enabled_;
+};
+
+// An EventListener which helps verify the compaction statistics in
+// the test DeletionStatsTest.
+class CompactionJobDeletionStatsChecker : public CompactionJobStatsChecker {
+ public:
+  // Verifies whether two CompactionJobStats match.
+  void Verify(const CompactionJobStats& current_stats,
+              const CompactionJobStats& stats) {
+    ASSERT_EQ(
+      current_stats.num_input_deletion_records,
+      stats.num_input_deletion_records);
+    ASSERT_EQ(
+        current_stats.num_expired_deletion_records,
+        stats.num_expired_deletion_records);
+    ASSERT_EQ(
+        current_stats.num_records_replaced,
+        stats.num_records_replaced);
+
+    ASSERT_EQ(current_stats.num_corrupt_keys,
+        stats.num_corrupt_keys);
+  }
+};
+
+namespace {
+
+uint64_t EstimatedFileSize(
+    uint64_t num_records, size_t key_size, size_t value_size,
+    double compression_ratio = 1.0,
+    size_t block_size = 4096,
+    int bloom_bits_per_key = 10) {
+  const size_t kPerKeyOverhead = 8;
+  const size_t kFooterSize = 512;
+
+  uint64_t data_size =
+      num_records * (key_size + value_size * compression_ratio +
+                     kPerKeyOverhead);
+
+  return data_size + kFooterSize
+         + num_records * bloom_bits_per_key / 8      // filter block
+         + data_size * (key_size + 8) / block_size;  // index block
+}
+
+namespace {
+
+void CopyPrefix(
+    const Slice& src, size_t prefix_length, std::string* dst) {
+  assert(prefix_length > 0);
+  size_t length = src.size() > prefix_length ? prefix_length : src.size();
+  dst->assign(src.data(), length);
+}
+
+}  // namespace
+
+CompactionJobStats NewManualCompactionJobStats(
+    const std::string& smallest_key, const std::string& largest_key,
+    size_t num_input_files, size_t num_input_files_at_output_level,
+    uint64_t num_input_records, size_t key_size, size_t value_size,
+    size_t num_output_files, uint64_t num_output_records,
+    double compression_ratio, uint64_t num_records_replaced,
+    bool is_manual = true) {
+  CompactionJobStats stats;
+  stats.Reset();
+
+  stats.num_input_records = num_input_records;
+  stats.num_input_files = num_input_files;
+  stats.num_input_files_at_output_level = num_input_files_at_output_level;
+
+  stats.num_output_records = num_output_records;
+  stats.num_output_files = num_output_files;
+
+  stats.total_input_bytes =
+      EstimatedFileSize(
+          num_input_records / num_input_files,
+          key_size, value_size, compression_ratio) * num_input_files;
+  stats.total_output_bytes =
+      EstimatedFileSize(
+          num_output_records / num_output_files,
+          key_size, value_size, compression_ratio) * num_output_files;
+  stats.total_input_raw_key_bytes =
+      num_input_records * (key_size + 8);
+  stats.total_input_raw_value_bytes =
+      num_input_records * value_size;
+
+  stats.is_manual_compaction = is_manual;
+
+  stats.num_records_replaced = num_records_replaced;
+
+  CopyPrefix(smallest_key,
+             CompactionJobStats::kMaxPrefixLength,
+             &stats.smallest_output_key_prefix);
+  CopyPrefix(largest_key,
+             CompactionJobStats::kMaxPrefixLength,
+             &stats.largest_output_key_prefix);
+
+  return stats;
+}
+
+CompressionType GetAnyCompression() {
+  if (Snappy_Supported()) {
+    return kSnappyCompression;
+  } else if (Zlib_Supported()) {
+    return kZlibCompression;
+  } else if (BZip2_Supported()) {
+    return kBZip2Compression;
+  } else if (LZ4_Supported()) {
+    return kLZ4Compression;
+  }
+  return kNoCompression;
+}
+
+}  // namespace
+
+TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
+  Random rnd(301);
+  const int kBufSize = 100;
+  char buf[kBufSize];
+  uint64_t key_base = 100000000l;
+  // Note: key_base must be multiple of num_keys_per_L0_file
+  int num_keys_per_L0_file = 100;
+  const int kTestScale = 8;
+  const int kKeySize = 10;
+  const int kValueSize = 1000;
+  const double kCompressionRatio = 0.5;
+  double compression_ratio = 1.0;
+  uint64_t key_interval = key_base / num_keys_per_L0_file;
+
+  // Whenever a compaction completes, this listener will try to
+  // verify whether the returned CompactionJobStats matches
+  // what we expect.  The expected CompactionJobStats is added
+  // via AddExpectedStats().
+  auto* stats_checker = new CompactionJobStatsChecker();
+  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;
+  options.compression = kNoCompression;
+  options.num_subcompactions = num_subcompactions_;
+
+  for (int test = 0; test < 2; ++test) {
+    DestroyAndReopen(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // 1st Phase: generate "num_L0_files" L0 files.
+    int num_L0_files = 0;
+    for (uint64_t start_key = key_base;
+                  start_key <= key_base * kTestScale;
+                  start_key += key_base) {
+      MakeTableWithKeyValues(
+          &rnd, start_key, start_key + key_base - 1,
+          kKeySize, kValueSize, key_interval,
+          compression_ratio, 1);
+      snprintf(buf, kBufSize, "%d", ++num_L0_files);
+      ASSERT_EQ(std::string(buf), FilesPerLevel(1));
+    }
+    ASSERT_EQ(ToString(num_L0_files), FilesPerLevel(1));
+
+    // 2nd Phase: perform L0 -> L1 compaction.
+    int L0_compaction_count = 6;
+    int count = 1;
+    std::string smallest_key;
+    std::string largest_key;
+    for (uint64_t start_key = key_base;
+         start_key <= key_base * L0_compaction_count;
+         start_key += key_base, count++) {
+      smallest_key = Key(start_key, 10);
+      largest_key = Key(start_key + key_base - key_interval, 10);
+      stats_checker->AddExpectedStats(
+          NewManualCompactionJobStats(
+              smallest_key, largest_key,
+              1, 0, num_keys_per_L0_file,
+              kKeySize, kValueSize,
+              1, num_keys_per_L0_file,
+              compression_ratio, 0));
+      ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 1U);
+      TEST_Compact(0, 1, smallest_key, largest_key);
+      snprintf(buf, kBufSize, "%d,%d", num_L0_files - count, count);
+      ASSERT_EQ(std::string(buf), FilesPerLevel(1));
+    }
+
+    // compact two files into one in the last L0 -> L1 compaction
+    int num_remaining_L0 = num_L0_files - L0_compaction_count;
+    smallest_key = Key(key_base * (L0_compaction_count + 1), 10);
+    largest_key = Key(key_base * (kTestScale + 1) - key_interval, 10);
+    stats_checker->AddExpectedStats(
+        NewManualCompactionJobStats(
+            smallest_key, largest_key,
+            num_remaining_L0,
+            0, num_keys_per_L0_file * num_remaining_L0,
+            kKeySize, kValueSize,
+            1, num_keys_per_L0_file * num_remaining_L0,
+            compression_ratio, 0));
+    ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 1U);
+    TEST_Compact(0, 1, smallest_key, largest_key);
+
+    int num_L1_files = num_L0_files - num_remaining_L0 + 1;
+    num_L0_files = 0;
+    snprintf(buf, kBufSize, "%d,%d", num_L0_files, num_L1_files);
+    ASSERT_EQ(std::string(buf), FilesPerLevel(1));
+
+    // 3rd Phase: generate sparse L0 files (wider key-range, same num of keys)
+    int sparseness = 2;
+    for (uint64_t start_key = key_base;
+                  start_key <= key_base * kTestScale;
+                  start_key += key_base * sparseness) {
+      MakeTableWithKeyValues(
+          &rnd, start_key, start_key + key_base * sparseness - 1,
+          kKeySize, kValueSize,
+          key_base * sparseness / num_keys_per_L0_file,
+          compression_ratio, 1);
+      snprintf(buf, kBufSize, "%d,%d", ++num_L0_files, num_L1_files);
+      ASSERT_EQ(std::string(buf), FilesPerLevel(1));
+    }
+
+    // 4th Phase: perform L0 -> L1 compaction again, expect higher write amp
+    // When subcompactions are enabled, the number of output files increases
+    // by 1 because multiple threads are consuming the input and generating
+    // output files without coordinating to see if the output could fit into
+    // a smaller number of files like it does when it runs sequentially
+    int num_output_files = options.num_subcompactions > 1 ? 2 : 1;
+    for (uint64_t start_key = key_base;
+         num_L0_files > 1;
+         start_key += key_base * sparseness) {
+      smallest_key = Key(start_key, 10);
+      largest_key =
+          Key(start_key + key_base * sparseness - key_interval, 10);
+      stats_checker->AddExpectedStats(
+          NewManualCompactionJobStats(
+              smallest_key, largest_key,
+              3, 2, num_keys_per_L0_file * 3,
+              kKeySize, kValueSize,
+              num_output_files,
+              num_keys_per_L0_file * 2,  // 1/3 of the data will be updated.
+              compression_ratio,
+              num_keys_per_L0_file));
+      ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 1U);
+      Compact(1, smallest_key, largest_key);
+      // TODO(aekmekji): account for whether parallel L0-L1 compaction is
+      // enabled or not. If so then num_L1_files will increase by 1
+      if (options.num_subcompactions == 1) {
+        --num_L1_files;
+      }
+      snprintf(buf, kBufSize, "%d,%d", --num_L0_files, num_L1_files);
+      ASSERT_EQ(std::string(buf), FilesPerLevel(1));
+    }
+
+    // 5th Phase: Do a full compaction, which involves in two sub-compactions.
+    // Here we expect to have 1 L0 files and 4 L1 files
+    // In the first sub-compaction, we expect L0 compaction.
+    smallest_key = Key(key_base, 10);
+    largest_key = Key(key_base * (kTestScale + 1) - key_interval, 10);
+    stats_checker->AddExpectedStats(
+        NewManualCompactionJobStats(
+            Key(key_base * (kTestScale + 1 - sparseness), 10), largest_key,
+            2, 1, num_keys_per_L0_file * 3,
+            kKeySize, kValueSize,
+            1, num_keys_per_L0_file * 2,
+            compression_ratio,
+            num_keys_per_L0_file));
+    ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 1U);
+    Compact(1, smallest_key, largest_key);
+    num_L1_files = options.num_subcompactions > 1 ? 7 : 4;
+    char L1_buf[4];
+    snprintf(L1_buf, sizeof(L1_buf), "0,%d", num_L1_files);
+    std::string L1_files(L1_buf);
+    ASSERT_EQ(L1_files, FilesPerLevel(1));
+    options.compression = GetAnyCompression();
+    if (options.compression == kNoCompression) {
+      break;
+    }
+    stats_checker->EnableCompression(true);
+    compression_ratio = kCompressionRatio;
+  }
+  ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 0U);
+}
+
+TEST_P(CompactionJobStatsTest, DeletionStatsTest) {
+  Random rnd(301);
+  uint64_t key_base = 100000l;
+  // Note: key_base must be multiple of num_keys_per_L0_file
+  int num_keys_per_L0_file = 20;
+  const int kTestScale = 8;  // make sure this is even
+  const int kKeySize = 10;
+  const int kValueSize = 100;
+  double compression_ratio = 1.0;
+  uint64_t key_interval = key_base / num_keys_per_L0_file;
+  uint64_t largest_key_num = key_base * (kTestScale + 1) - key_interval;
+  uint64_t cutoff_key_num = key_base * (kTestScale / 2 + 1) - key_interval;
+  const std::string smallest_key = Key(key_base - 10, kKeySize);
+  const std::string largest_key = Key(largest_key_num + 10, kKeySize);
+
+  // Whenever a compaction completes, this listener will try to
+  // verify whether the returned CompactionJobStats matches
+  // what we expect.
+  auto* stats_checker = new CompactionJobDeletionStatsChecker();
+  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;
+  options.max_bytes_for_level_multiplier = 2;
+  options.num_subcompactions = num_subcompactions_;
+
+  DestroyAndReopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  // Stage 1: Generate several L0 files and then send them to L2 by
+  // using CompactRangeOptions and CompactRange(). These files will
+  // have a strict subset of the keys from the full key-range
+  for (uint64_t start_key = key_base;
+                start_key <= key_base * kTestScale / 2;
+                start_key += key_base) {
+    MakeTableWithKeyValues(
+        &rnd, start_key, start_key + key_base - 1,
+        kKeySize, kValueSize, key_interval,
+        compression_ratio, 1);
+  }
+
+  CompactRangeOptions cr_options;
+  cr_options.change_level = true;
+  cr_options.target_level = 2;
+  db_->CompactRange(cr_options, handles_[1], nullptr, nullptr);
+  ASSERT_GT(NumTableFilesAtLevel(2, 1), 0);
+
+  // Stage 2: Generate files including keys from the entire key range
+  for (uint64_t start_key = key_base;
+                start_key <= key_base * kTestScale;
+                start_key += key_base) {
+    MakeTableWithKeyValues(
+        &rnd, start_key, start_key + key_base - 1,
+        kKeySize, kValueSize, key_interval,
+        compression_ratio, 1);
+  }
+
+  // Send these L0 files to L1
+  TEST_Compact(0, 1, smallest_key, largest_key);
+  ASSERT_GT(NumTableFilesAtLevel(1, 1), 0);
+
+  // Add a new record and flush so now there is a L0 file
+  // with a value too (not just deletions from the next step)
+  ASSERT_OK(Put(1, Key(key_base-6, kKeySize), "test"));
+  ASSERT_OK(Flush(1));
+
+  // Stage 3: Generate L0 files with some deletions so now
+  // there are files with the same key range in L0, L1, and L2
+  int deletion_interval = 3;
+  CompactionJobStats first_compaction_stats;
+  SelectivelyDeleteKeys(key_base, largest_key_num,
+      key_interval, deletion_interval, kKeySize, cutoff_key_num,
+      &first_compaction_stats, 1);
+
+  stats_checker->AddExpectedStats(first_compaction_stats);
+
+  // Stage 4: Trigger compaction and verify the stats
+  TEST_Compact(0, 1, smallest_key, largest_key);
+}
+
+namespace {
+int GetUniversalCompactionInputUnits(uint32_t num_flushes) {
+  uint32_t compaction_input_units;
+  for (compaction_input_units = 1;
+       num_flushes >= compaction_input_units;
+       compaction_input_units *= 2) {
+    if ((num_flushes & compaction_input_units) != 0) {
+      return compaction_input_units > 1 ? compaction_input_units : 0;
+    }
+  }
+  return 0;
+}
+}  // namespace
+
+TEST_P(CompactionJobStatsTest, UniversalCompactionTest) {
+  Random rnd(301);
+  uint64_t key_base = 100000000l;
+  // Note: key_base must be multiple of num_keys_per_L0_file
+  int num_keys_per_table = 100;
+  const uint32_t kTestScale = 8;
+  const int kKeySize = 10;
+  const int kValueSize = 900;
+  double compression_ratio = 1.0;
+  uint64_t key_interval = key_base / num_keys_per_table;
+
+  auto* stats_checker = new CompactionJobStatsChecker();
+  Options options;
+  options.listeners.emplace_back(stats_checker);
+  options.create_if_missing = true;
+  options.num_levels = 3;
+  options.compression = kNoCompression;
+  options.level0_file_num_compaction_trigger = 2;
+  options.target_file_size_base = num_keys_per_table * 1000;
+  options.compaction_style = kCompactionStyleUniversal;
+  options.compaction_options_universal.size_ratio = 1;
+  options.compaction_options_universal.max_size_amplification_percent = 1000;
+  options.num_subcompactions = num_subcompactions_;
+
+  DestroyAndReopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  // Generates the expected CompactionJobStats for each compaction
+  for (uint32_t num_flushes = 2; num_flushes <= kTestScale; num_flushes++) {
+    // Here we treat one newly flushed file as an unit.
+    //
+    // For example, if a newly flushed file is 100k, and a compaction has
+    // 4 input units, then this compaction inputs 400k.
+    uint32_t num_input_units = GetUniversalCompactionInputUnits(num_flushes);
+    if (num_input_units == 0) {
+      continue;
+    }
+    // The following statement determines the expected smallest key
+    // based on whether it is a full compaction.  A full compaction only
+    // happens when the number of flushes equals to the number of compaction
+    // input runs.
+    uint64_t smallest_key =
+        (num_flushes == num_input_units) ?
+            key_base : key_base * (num_flushes - 1);
+
+    stats_checker->AddExpectedStats(
+        NewManualCompactionJobStats(
+            Key(smallest_key, 10),
+            Key(smallest_key + key_base * num_input_units - key_interval, 10),
+            num_input_units,
+            num_input_units > 2 ? num_input_units / 2 : 0,
+            num_keys_per_table * num_input_units,
+            kKeySize, kValueSize,
+            num_input_units,
+            num_keys_per_table * num_input_units,
+            1.0, 0, false));
+  }
+  ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 4U);
+
+  for (uint64_t start_key = key_base;
+                start_key <= key_base * kTestScale;
+                start_key += key_base) {
+    MakeTableWithKeyValues(
+        &rnd, start_key, start_key + key_base - 1,
+        kKeySize, kValueSize, key_interval,
+        compression_ratio, 1);
+  }
+  reinterpret_cast<DBImpl*>(db_)->TEST_WaitForCompact();
+  ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 0U);
+}
+
+INSTANTIATE_TEST_CASE_P(CompactionJobStatsTest, CompactionJobStatsTest,
+                        ::testing::Values(1, 4));
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
+
+#endif  // !ROCKSDB_LITE
+
+#else
+
+int main(int argc, char** argv) { return 0; }
+#endif  // !defined(IOS_CROSS_COMPILE)

db/compaction_job_test.cc

@@ -13,6 +13,7 @@
 #include "rocksdb/cache.h"
 #include "rocksdb/options.h"
 #include "rocksdb/db.h"
+#include "util/file_reader_writer.h"
 #include "util/string_util.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
@@ -20,6 +21,41 @@
 
 namespace rocksdb {
 
+namespace {
+void VerifyInitializationOfCompactionJobStats(
+      const CompactionJobStats& compaction_job_stats) {
+#if !defined(IOS_CROSS_COMPILE)
+  ASSERT_EQ(compaction_job_stats.elapsed_micros, 0U);
+
+  ASSERT_EQ(compaction_job_stats.num_input_records, 0U);
+  ASSERT_EQ(compaction_job_stats.num_input_files, 0U);
+  ASSERT_EQ(compaction_job_stats.num_input_files_at_output_level, 0U);
+
+  ASSERT_EQ(compaction_job_stats.num_output_records, 0U);
+  ASSERT_EQ(compaction_job_stats.num_output_files, 0U);
+
+  ASSERT_EQ(compaction_job_stats.is_manual_compaction, false);
+
+  ASSERT_EQ(compaction_job_stats.total_input_bytes, 0U);
+  ASSERT_EQ(compaction_job_stats.total_output_bytes, 0U);
+
+  ASSERT_EQ(compaction_job_stats.total_input_raw_key_bytes, 0U);
+  ASSERT_EQ(compaction_job_stats.total_input_raw_value_bytes, 0U);
+
+  ASSERT_EQ(compaction_job_stats.smallest_output_key_prefix[0], 0);
+  ASSERT_EQ(compaction_job_stats.largest_output_key_prefix[0], 0);
+
+  ASSERT_EQ(compaction_job_stats.num_records_replaced, 0U);
+
+  ASSERT_EQ(compaction_job_stats.num_input_deletion_records, 0U);
+  ASSERT_EQ(compaction_job_stats.num_expired_deletion_records, 0U);
+
+  ASSERT_EQ(compaction_job_stats.num_corrupt_keys, 0U);
+#endif  // !defined(IOS_CROSS_COMPILE)
+}
+
+}  // namespace
+
 // TODO(icanadi) Make it simpler once we mock out VersionSet
 class CompactionJobTest : public testing::Test {
  public:
@@ -53,22 +89,40 @@ class CompactionJobTest : public testing::Test {
     return TableFileName(db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());
   }
 
+  // Corrupts key by changing the type
+  void CorruptKey(InternalKey* ikey) {
+    std::string keystr = ikey->Encode().ToString();
+    keystr[keystr.size() - 8] = kTypeLogData;
+    ikey->DecodeFrom(Slice(keystr.data(), keystr.size()));
+  }
+
   // returns expected result after compaction
-  mock::MockFileContents CreateTwoFiles() {
+  mock::MockFileContents CreateTwoFiles(bool gen_corrupted_keys) {
     mock::MockFileContents expected_results;
     const int kKeysPerFile = 10000;
+    const int kCorruptKeysPerFile = 200;
+    const int kMatchingKeys = kKeysPerFile / 2;
     SequenceNumber sequence_number = 0;
+
+    auto corrupt_id = [&](int id) {
+      return gen_corrupted_keys && id > 0 && id <= kCorruptKeysPerFile;
+    };
+
     for (int i = 0; i < 2; ++i) {
       mock::MockFileContents contents;
       SequenceNumber smallest_seqno = 0, largest_seqno = 0;
       InternalKey smallest, largest;
       for (int k = 0; k < kKeysPerFile; ++k) {
-        auto key = ToString(i * (kKeysPerFile / 2) + k);
+        auto key = ToString(i * kMatchingKeys + k);
         auto value = ToString(i * kKeysPerFile + k);
         InternalKey internal_key(key, ++sequence_number, kTypeValue);
         // This is how the key will look like once it's written in bottommost
         // file
         InternalKey bottommost_internal_key(key, 0, kTypeValue);
+        if (corrupt_id(k)) {
+          CorruptKey(&internal_key);
+          CorruptKey(&bottommost_internal_key);
+        }
         if (k == 0) {
           smallest = internal_key;
           smallest_seqno = sequence_number;
@@ -76,11 +130,10 @@ class CompactionJobTest : public testing::Test {
           largest = internal_key;
           largest_seqno = sequence_number;
         }
-        std::pair<std::string, std::string> key_value(
-            {bottommost_internal_key.Encode().ToString(), value});
-        contents.insert(key_value);
-        if (i == 1 || k < kKeysPerFile / 2) {
-          expected_results.insert(key_value);
+        contents.insert({internal_key.Encode().ToString(), value});
+        if (i == 1 || k < kMatchingKeys || corrupt_id(k - kMatchingKeys)) {
+          expected_results.insert(
+              {bottommost_internal_key.Encode().ToString(), value});
         }
       }
 
@@ -90,14 +143,14 @@ class CompactionJobTest : public testing::Test {
 
       VersionEdit edit;
       edit.AddFile(0, file_number, 0, 10, smallest, largest, smallest_seqno,
-                   largest_seqno);
+                   largest_seqno, false);
 
       mutex_.Lock();
       versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
                              mutable_cf_options_, &edit, &mutex_);
       mutex_.Unlock();
     }
-    versions_->SetLastSequence(sequence_number);
+    versions_->SetLastSequence(sequence_number + 1);
     return expected_results;
   }
 
@@ -112,8 +165,10 @@ class CompactionJobTest : public testing::Test {
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
+    unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), EnvOptions()));
     {
-      log::Writer log(std::move(file));
+      log::Writer log(std::move(file_writer));
       std::string record;
       new_db.EncodeTo(&record);
       s = log.AddRecord(record);
@@ -123,6 +178,44 @@ class CompactionJobTest : public testing::Test {
     s = SetCurrentFile(env_, dbname_, 1, nullptr);
   }
 
+  void RunCompaction(const std::vector<FileMetaData*>& files) {
+    auto cfd = versions_->GetColumnFamilySet()->GetDefault();
+
+    CompactionInputFiles compaction_input_files;
+    compaction_input_files.level = 0;
+    for (auto file : files) {
+      compaction_input_files.files.push_back(file);
+    }
+    Compaction compaction(cfd->current()->storage_info(),
+                          *cfd->GetLatestMutableCFOptions(),
+                          {compaction_input_files}, 1, 1024 * 1024, 10, 0,
+                          kNoCompression, {});
+    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());
+    CompactionJob compaction_job(
+        0, &compaction, db_options_, env_options_, versions_.get(),
+        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, {},
+        table_cache_, &event_logger, false, dbname_, &compaction_job_stats_);
+
+    VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
+
+    compaction_job.Prepare();
+    mutex_.Unlock();
+    ASSERT_OK(compaction_job.Run());
+    mutex_.Lock();
+    Status s;
+    compaction_job.Install(&s, *cfd->GetLatestMutableCFOptions(), &mutex_);
+    ASSERT_OK(s);
+    mutex_.Unlock();
+
+    ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+    ASSERT_EQ(compaction_job_stats_.num_input_files, files.size());
+    ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
+  }
+
   Env* env_;
   std::string dbname_;
   EnvOptions env_options_;
@@ -136,49 +229,27 @@ class CompactionJobTest : public testing::Test {
   InstrumentedMutex mutex_;
   std::atomic<bool> shutting_down_;
   std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
+  CompactionJobStats compaction_job_stats_;
 };
 
 TEST_F(CompactionJobTest, Simple) {
+  auto expected_results = CreateTwoFiles(false);
   auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-
-  auto expected_results = CreateTwoFiles();
-
   auto files = cfd->current()->storage_info()->LevelFiles(0);
   ASSERT_EQ(2U, files.size());
 
-  CompactionInputFiles compaction_input_files;
-  compaction_input_files.level = 0;
-  compaction_input_files.files.push_back(files[0]);
-  compaction_input_files.files.push_back(files[1]);
-  std::unique_ptr<Compaction> compaction(new Compaction(
-      cfd->current()->storage_info(), *cfd->GetLatestMutableCFOptions(),
-      {compaction_input_files}, 1, 1024 * 1024, 10, 0, kNoCompression, {}));
-  compaction->SetInputVersion(cfd->current());
-
-  int yield_callback_called = 0;
-  std::function<uint64_t()> yield_callback = [&]() {
-    yield_callback_called++;
-    return 0;
-  };
-  LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
-  mutex_.Lock();
-  EventLogger event_logger(db_options_.info_log.get());
-  CompactionJob compaction_job(0, compaction.get(), db_options_, env_options_,
-                               versions_.get(), &shutting_down_, &log_buffer,
-                               nullptr, nullptr, nullptr, {}, table_cache_,
-                               std::move(yield_callback), &event_logger, false);
-
-  compaction_job.Prepare();
-  mutex_.Unlock();
-  ASSERT_OK(compaction_job.Run());
-  mutex_.Lock();
-  Status s;
-  compaction_job.Install(&s, *cfd->GetLatestMutableCFOptions(), &mutex_);
-  ASSERT_OK(s);
-  mutex_.Unlock();
-
+  RunCompaction(files);
+  mock_table_factory_->AssertLatestFile(expected_results);
+}
+
+TEST_F(CompactionJobTest, SimpleCorrupted) {
+  auto expected_results = CreateTwoFiles(true);
+  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
+  auto files = cfd->current()->storage_info()->LevelFiles(0);
+
+  RunCompaction(files);
+  ASSERT_EQ(compaction_job_stats_.num_corrupt_keys, 400U);
   mock_table_factory_->AssertLatestFile(expected_results);
-  ASSERT_EQ(yield_callback_called, 20000);
 }
 
 }  // namespace rocksdb

db/compaction_picker.cc

@@ -15,6 +15,7 @@
 
 #include <inttypes.h>
 #include <limits>
+#include <queue>
 #include <string>
 #include <utility>
 
@@ -37,6 +38,69 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
   return sum;
 }
 
+// Universal compaction is not supported in ROCKSDB_LITE
+#ifndef ROCKSDB_LITE
+
+// Used in universal compaction when trivial move is enabled.
+// This structure is used for the construction of min heap
+// that contains the file meta data, the level of the file
+// and the index of the file in that level
+
+struct InputFileInfo {
+  InputFileInfo() : f(nullptr) {}
+
+  FileMetaData* f;
+  size_t level;
+  size_t index;
+};
+
+// Used in universal compaction when trivial move is enabled.
+// This comparator is used for the construction of min heap
+// based on the smallest key of the file.
+struct UserKeyComparator {
+  explicit UserKeyComparator(const Comparator* ucmp) { ucmp_ = ucmp; }
+
+  bool operator()(InputFileInfo i1, InputFileInfo i2) const {
+    return (ucmp_->Compare(i1.f->smallest.user_key(),
+                           i2.f->smallest.user_key()) > 0);
+  }
+
+ private:
+  const Comparator* ucmp_;
+};
+
+typedef std::priority_queue<InputFileInfo, std::vector<InputFileInfo>,
+                            UserKeyComparator> SmallestKeyHeap;
+
+// This function creates the heap that is used to find if the files are
+// overlapping during universal compaction when the allow_trivial_move
+// is set.
+SmallestKeyHeap create_level_heap(Compaction* c, const Comparator* ucmp) {
+  SmallestKeyHeap smallest_key_priority_q =
+      SmallestKeyHeap(UserKeyComparator(ucmp));
+
+  InputFileInfo input_file;
+
+  for (size_t l = 0; l < c->num_input_levels(); l++) {
+    if (c->num_input_files(l) != 0) {
+      if (l == 0 && c->start_level() == 0) {
+        for (size_t i = 0; i < c->num_input_files(0); i++) {
+          input_file.f = c->input(0, i);
+          input_file.level = 0;
+          input_file.index = i;
+          smallest_key_priority_q.push(std::move(input_file));
+        }
+      } else {
+        input_file.f = c->input(l, 0);
+        input_file.level = l;
+        input_file.index = 0;
+        smallest_key_priority_q.push(std::move(input_file));
+      }
+    }
+  }
+  return smallest_key_priority_q;
+}
+#endif  // !ROCKSDB_LITE
 }  // anonymous namespace
 
 // Determine compression type, based on user options, level of the output
@@ -342,8 +406,9 @@ bool CompactionPicker::SetupOtherInputs(
       if (expanded1.size() == output_level_inputs->size() &&
           !FilesInCompaction(expanded1)) {
         Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
-            "[%s] Expanding@%d %zu+%zu (%" PRIu64 "+%" PRIu64
-            " bytes) to %zu+%zu (%" PRIu64 "+%" PRIu64 "bytes)\n",
+            "[%s] Expanding@%d %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt "(%" PRIu64
+            "+%" PRIu64 " bytes) to %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt
+            " (%" PRIu64 "+%" PRIu64 "bytes)\n",
             cf_name.c_str(), input_level, inputs->size(),
             output_level_inputs->size(), inputs0_size, inputs1_size,
             expanded0.size(), expanded1.size(), expanded0_size, inputs1_size);
@@ -645,7 +710,12 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
     aggregated_file_meta.largestkey = largestkey;
 
     // For all lower levels, include all overlapping files.
-    for (int m = l + 1; m <= output_level; ++m) {
+    // We need to add overlapping files from the current level too because even
+    // if there no input_files in level l, we would still need to add files
+    // which overlap with the range containing the input_files in levels 0 to l
+    // Level 0 doesn't need to be handled this way because files are sorted by
+    // time and not by key
+    for (int m = std::max(l, 1); m <= output_level; ++m) {
       for (auto& next_lv_file : levels[m].files) {
         if (HaveOverlappingKeyRanges(
             comparator, aggregated_file_meta, next_lv_file)) {
@@ -763,6 +833,10 @@ void LevelCompactionPicker::PickFilesMarkedForCompactionExperimental(
     *level = level_file.first;
     *output_level = (*level == 0) ? vstorage->base_level() : *level + 1;
 
+    if (*level == 0 && !level0_compactions_in_progress_.empty()) {
+      return false;
+    }
+
     inputs->files = {level_file.second};
     inputs->level = *level;
     return ExpandWhileOverlapping(cf_name, vstorage, inputs);
@@ -1045,7 +1119,7 @@ void UniversalCompactionPicker::SortedRun::DumpSizeInfo(
 
 std::vector<UniversalCompactionPicker::SortedRun>
 UniversalCompactionPicker::CalculateSortedRuns(
-    const VersionStorageInfo& vstorage) {
+    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,
@@ -1059,10 +1133,18 @@ UniversalCompactionPicker::CalculateSortedRuns(
     for (FileMetaData* f : vstorage.LevelFiles(level)) {
       total_compensated_size += f->compensated_file_size;
       total_size += f->fd.GetFileSize();
-      // Compaction always includes all files for a non-zero level, so for a
-      // non-zero level, all the files should share the same being_compacted
-      // value.
-      assert(is_first || f->being_compacted == being_compacted);
+      if (ioptions.compaction_options_universal.allow_trivial_move == true) {
+        if (f->being_compacted) {
+          being_compacted = f->being_compacted;
+        }
+      } else {
+        // Compaction always includes all files for a non-zero level, so for a
+        // non-zero level, all the files should share the same being_compacted
+        // value.
+        // This assumption is only valid when
+        // ioptions.compaction_options_universal.allow_trivial_move is false
+        assert(is_first || f->being_compacted == being_compacted);
+      }
       if (is_first) {
         being_compacted = f->being_compacted;
         is_first = false;
@@ -1102,6 +1184,50 @@ void GetSmallestLargestSeqno(const std::vector<FileMetaData*>& files,
 }  // namespace
 #endif
 
+// Algorithm that checks to see if there are any overlapping
+// files in the input
+bool CompactionPicker::IsInputNonOverlapping(Compaction* c) {
+  auto comparator = icmp_->user_comparator();
+  int first_iter = 1;
+
+  InputFileInfo prev, curr, next;
+
+  SmallestKeyHeap smallest_key_priority_q =
+      create_level_heap(c, icmp_->user_comparator());
+
+  while (!smallest_key_priority_q.empty()) {
+    curr = smallest_key_priority_q.top();
+    smallest_key_priority_q.pop();
+
+    if (first_iter) {
+      prev = curr;
+      first_iter = 0;
+    } else {
+      if (comparator->Compare(prev.f->largest.user_key(),
+                              curr.f->smallest.user_key()) >= 0) {
+        // found overlapping files, return false
+        return false;
+      }
+      assert(comparator->Compare(curr.f->largest.user_key(),
+                                 prev.f->largest.user_key()) > 0);
+      prev = curr;
+    }
+
+    next.f = nullptr;
+
+    if (curr.level != 0 && curr.index < c->num_input_files(curr.level) - 1) {
+      next.f = c->input(curr.level, curr.index + 1);
+      next.level = curr.level;
+      next.index = curr.index + 1;
+    }
+
+    if (next.f) {
+      smallest_key_priority_q.push(std::move(next));
+    }
+  }
+  return true;
+}
+
 // Universal style of compaction. Pick files that are contiguous in
 // time-range to compact.
 //
@@ -1110,7 +1236,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
     VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
   const int kLevel0 = 0;
   double score = vstorage->CompactionScore(kLevel0);
-  std::vector<SortedRun> sorted_runs = CalculateSortedRuns(*vstorage);
+  std::vector<SortedRun> sorted_runs =
+      CalculateSortedRuns(*vstorage, ioptions_);
 
   if (sorted_runs.size() <
       (unsigned int)mutable_cf_options.level0_file_num_compaction_trigger) {
@@ -1118,7 +1245,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
     return nullptr;
   }
   VersionStorageInfo::LevelSummaryStorage tmp;
-  LogToBuffer(log_buffer, 3072, "[%s] Universal: sorted runs files(%zu): %s\n",
+  LogToBuffer(log_buffer, 3072,
+              "[%s] Universal: sorted runs files(%" ROCKSDB_PRIszt "): %s\n",
               cf_name.c_str(), sorted_runs.size(),
               vstorage->LevelSummary(&tmp));
 
@@ -1164,6 +1292,10 @@ Compaction* UniversalCompactionPicker::PickCompaction(
     return nullptr;
   }
 
+  if (ioptions_.compaction_options_universal.allow_trivial_move == true) {
+    c->set_is_trivial_move(IsInputNonOverlapping(c));
+  }
+
 // validate that all the chosen files of L0 are non overlapping in time
 #ifndef NDEBUG
   SequenceNumber prev_smallest_seqno = 0U;

db/compaction_picker.h

@@ -105,6 +105,12 @@ class CompactionPicker {
       const VersionStorageInfo* vstorage,
       const CompactionOptions& compact_options) const;
 
+  // Used in universal compaction when the enabled_trivial_move
+  // option is set. Checks whether there are any overlapping files
+  // in the input. Returns true if the input files are non
+  // overlapping.
+  bool IsInputNonOverlapping(Compaction* c);
+
  protected:
   int NumberLevels() const { return ioptions_.num_levels; }
 
@@ -269,7 +275,7 @@ class UniversalCompactionPicker : public CompactionPicker {
       const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
 
   static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage);
+      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions);
 
   // Pick a path ID to place a newly generated file, with its estimated file
   // size.

db/compaction_picker_test.cc

@@ -77,6 +77,8 @@ class CompactionPickerTest : public testing::Test {
     f->fd = FileDescriptor(file_number, path_id, file_size);
     f->smallest = InternalKey(smallest, smallest_seq, kTypeValue);
     f->largest = InternalKey(largest, largest_seq, kTypeValue);
+    f->smallest_seqno = smallest_seq;
+    f->largest_seqno = largest_seq;
     f->compensated_file_size = file_size;
     f->refs = 0;
     vstorage_->AddFile(level, f);
@@ -90,6 +92,7 @@ class CompactionPickerTest : public testing::Test {
     vstorage_->GenerateFileIndexer();
     vstorage_->GenerateLevelFilesBrief();
     vstorage_->ComputeCompactionScore(mutable_cf_options_, fifo_options_);
+    vstorage_->GenerateLevel0NonOverlapping();
     vstorage_->SetFinalized();
   }
 };
@@ -343,6 +346,8 @@ TEST_F(CompactionPickerTest, LevelTriggerDynamic4) {
   ASSERT_EQ(num_levels - 1, compaction->output_level());
 }
 
+// Universal and FIFO Compactions are not supported in ROCKSDB_LITE
+#ifndef ROCKSDB_LITE
 TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(
@@ -364,6 +369,64 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
               vstorage_->CompactionScore(0) >= 1);
   }
 }
+// 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
+// be trivially moved.
+
+TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
+  const uint64_t kFileSize = 100000;
+
+  ioptions_.compaction_options_universal.allow_trivial_move = true;
+  NewVersionStorage(1, kCompactionStyleUniversal);
+  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
+  // must return false when there's no files.
+  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_));
+
+  ASSERT_TRUE(!compaction->is_trivial_move());
+}
+// 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 doesn't overlaps, they should
+// be trivially moved.
+TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
+  const uint64_t kFileSize = 100000;
+
+  ioptions_.compaction_options_universal.allow_trivial_move = true;
+  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
+
+  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, "010", "080", kFileSize, 0, 200, 251);
+  Add(2, 3U, "301", "350", kFileSize, 0, 101, 150);
+
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(
+      universal_compaction_picker.PickCompaction(
+          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
+
+  ASSERT_TRUE(compaction->is_trivial_move());
+}
 
 TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   NewVersionStorage(1, kCompactionStyleFIFO);
@@ -394,6 +457,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
               vstorage_->CompactionScore(0) >= 1);
   }
 }
+#endif  // ROCKSDB_LITE
 
 // This test exhibits the bug where we don't properly reset parent_index in
 // PickCompaction()
@@ -418,6 +482,76 @@ TEST_F(CompactionPickerTest, ParentIndexResetBug) {
       cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
 }
 
+// This test checks ExpandWhileOverlapping() by having overlapping user keys
+// ranges (with different sequence numbers) in the input files.
+TEST_F(CompactionPickerTest, OverlappingUserKeys) {
+  NewVersionStorage(6, kCompactionStyleLevel);
+  Add(1, 1U, "100", "150", 1U);
+  // Overlapping user keys
+  Add(1, 2U, "200", "400", 1U);
+  Add(1, 3U, "400", "500", 1000000000U, 0, 0);
+  Add(2, 4U, "600", "700", 1U);
+  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(2U, compaction->num_input_files(0));
+  ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, OverlappingUserKeys2) {
+  NewVersionStorage(6, kCompactionStyleLevel);
+  // Overlapping user keys on same level and output level
+  Add(1, 1U, "200", "400", 1000000000U);
+  Add(1, 2U, "400", "500", 1U, 0, 0);
+  Add(2, 3U, "400", "600", 1U);
+  // The following file is not in the compaction despite overlapping user keys
+  Add(2, 4U, "600", "700", 1U, 0, 0);
+  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(2U, compaction->num_input_files(0));
+  ASSERT_EQ(1U, compaction->num_input_files(1));
+  ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
+  ASSERT_EQ(3U, compaction->input(1, 0)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, OverlappingUserKeys3) {
+  NewVersionStorage(6, kCompactionStyleLevel);
+  // Chain of overlapping user key ranges (forces ExpandWhileOverlapping() to
+  // expand multiple times)
+  Add(1, 1U, "100", "150", 1U);
+  Add(1, 2U, "150", "200", 1U, 0, 0);
+  Add(1, 3U, "200", "250", 1000000000U, 0, 0);
+  Add(1, 4U, "250", "300", 1U, 0, 0);
+  Add(1, 5U, "300", "350", 1U, 0, 0);
+  // Output level overlaps with the beginning and the end of the chain
+  Add(2, 6U, "050", "100", 1U);
+  Add(2, 7U, "350", "400", 1U);
+  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(5U, compaction->num_input_files(0));
+  ASSERT_EQ(2U, compaction->num_input_files(1));
+  ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
+  ASSERT_EQ(3U, compaction->input(0, 2)->fd.GetNumber());
+  ASSERT_EQ(4U, compaction->input(0, 3)->fd.GetNumber());
+  ASSERT_EQ(5U, compaction->input(0, 4)->fd.GetNumber());
+  ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
+  ASSERT_EQ(7U, compaction->input(1, 1)->fd.GetNumber());
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/comparator_db_test.cc

@@ -177,8 +177,13 @@ class DoubleComparator : public Comparator {
   virtual const char* Name() const override { return "DoubleComparator"; }
 
   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());
+#else
+    double da = std::strtod(a.ToString().c_str(), 0 /* endptr */);
+    double db = std::strtod(a.ToString().c_str(), 0 /* endptr */);
+#endif
     if (da == db) {
       return a.compare(b);
     } else if (da > db) {

db/convenience.cc

@@ -9,7 +9,7 @@
 
 #ifndef ROCKSDB_LITE
 
-#include "rocksdb/utilities/convenience.h"
+#include "rocksdb/convenience.h"
 
 #include "db/db_impl.h"
 

db/corruption_test.cc

@@ -57,6 +57,11 @@ class CorruptionTest : public testing::Test {
      DestroyDB(dbname_, Options());
   }
 
+  void CloseDb() {
+    delete db_;
+    db_ = nullptr;
+  }
+
   Status TryReopen(Options* options = nullptr) {
     delete db_;
     db_ = nullptr;
@@ -229,6 +234,16 @@ class CorruptionTest : public testing::Test {
 TEST_F(CorruptionTest, Recovery) {
   Build(100);
   Check(100, 100);
+#ifdef OS_WIN
+  // On Wndows OS Disk cache does not behave properly
+  // We do not call FlushBuffers on every Flush. If we do not close
+  // the log file prior to the corruption we end up with the first
+  // block not corrupted but only the second. However, under the debugger
+  // things work just fine but never pass when running normally
+  // For that reason people may want to run with unbuffered I/O. That option
+  // is not available for WAL though.
+  CloseDb();
+#endif
   Corrupt(kLogFile, 19, 1);      // WriteBatch tag for first record
   Corrupt(kLogFile, log::kBlockSize + 1000, 1);  // Somewhere in second block
   ASSERT_TRUE(!TryReopen().ok());
@@ -336,13 +351,13 @@ TEST_F(CorruptionTest, CorruptedDescriptor) {
 
 TEST_F(CorruptionTest, CompactionInputError) {
   Options options;
-  options.max_background_flushes = 0;
   Reopen(&options);
   Build(10);
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
-  const int last = dbi->MaxMemCompactionLevel();
-  ASSERT_EQ(1, Property("rocksdb.num-files-at-level" + NumberToString(last)));
+  dbi->TEST_CompactRange(0, nullptr, nullptr);
+  dbi->TEST_CompactRange(1, nullptr, nullptr);
+  ASSERT_EQ(1, Property("rocksdb.num-files-at-level2"));
 
   Corrupt(kTableFile, 100, 1);
   Check(9, 9);
@@ -357,18 +372,20 @@ TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
   options.paranoid_checks = true;
   options.write_buffer_size = 131072;
   options.max_write_buffer_number = 2;
-  options.max_background_flushes = 0;
   Reopen(&options);
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
 
-  // Fill levels >= 1 so memtable flush outputs to level 0
+  // Fill levels >= 1
   for (int level = 1; level < dbi->NumberLevels(); level++) {
     dbi->Put(WriteOptions(), "", "begin");
     dbi->Put(WriteOptions(), "~", "end");
     dbi->TEST_FlushMemTable();
+    for (int comp_level = 0; comp_level < dbi->NumberLevels() - level;
+         ++comp_level) {
+      dbi->TEST_CompactRange(comp_level, nullptr, nullptr);
+    }
   }
 
-  options.max_mem_compaction_level = 0;
   Reopen(&options);
 
   dbi = reinterpret_cast<DBImpl*>(db_);

db/cuckoo_table_db_test.cc

@@ -3,6 +3,8 @@
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
 
+#ifndef ROCKSDB_LITE
+
 #include "db/db_impl.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
@@ -39,7 +41,6 @@ class CuckooTableDBTest : public testing::Test {
     options.memtable_factory.reset(NewHashLinkListRepFactory(4, 0, 3, true));
     options.allow_mmap_reads = true;
     options.create_if_missing = true;
-    options.max_mem_compaction_level = 0;
     return options;
   }
 
@@ -243,7 +244,8 @@ TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
   dbfull()->TEST_WaitForFlushMemTable();
   ASSERT_EQ("1", FilesPerLevel());
 
-  dbfull()->TEST_CompactRange(0, nullptr, nullptr);
+  dbfull()->TEST_CompactRange(0, nullptr, nullptr, nullptr,
+                              true /* disallow trivial move */);
   ASSERT_EQ("0,2", FilesPerLevel());
   for (int idx = 0; idx < 28; ++idx) {
     ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
@@ -319,3 +321,13 @@ int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }
+
+#else
+#include <stdio.h>
+
+int main(int argc, char** argv) {
+  fprintf(stderr, "SKIPPED as Cuckoo table is not supported in ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // ROCKSDB_LITE

db/db_bench.cc

@@ -24,7 +24,9 @@ int main() {
 #include <numaif.h>
 #endif
 
+#ifndef OS_WIN
 #include <unistd.h>
+#endif
 #include <fcntl.h>
 #include <inttypes.h>
 #include <cstddef>
@@ -32,6 +34,12 @@ int main() {
 #include <stdio.h>
 #include <stdlib.h>
 #include <gflags/gflags.h>
+
+#include <atomic>
+#include <condition_variable>
+#include <mutex>
+#include <thread>
+
 #include "db/db_impl.h"
 #include "db/version_set.h"
 #include "rocksdb/options.h"
@@ -46,6 +54,8 @@ int main() {
 #include "rocksdb/slice_transform.h"
 #include "rocksdb/perf_context.h"
 #include "rocksdb/utilities/flashcache.h"
+#include "rocksdb/utilities/optimistic_transaction.h"
+#include "rocksdb/utilities/optimistic_transaction_db.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
 #include "util/crc32c.h"
@@ -60,6 +70,10 @@ int main() {
 #include "hdfs/env_hdfs.h"
 #include "utilities/merge_operators.h"
 
+#ifdef OS_WIN
+#include <io.h>  // open/close
+#endif
+
 using GFLAGS::ParseCommandLineFlags;
 using GFLAGS::RegisterFlagValidator;
 using GFLAGS::SetUsageMessage;
@@ -94,7 +108,8 @@ DEFINE_string(benchmarks,
               "compress,"
               "uncompress,"
               "acquireload,"
-              "fillseekseq,",
+              "fillseekseq,"
+              "randomtransaction",
 
               "Comma-separated list of operations to run in the specified order"
               "Actual benchmarks:\n"
@@ -115,8 +130,6 @@ DEFINE_string(benchmarks,
               "\treadreverse   -- read N times in reverse order\n"
               "\treadrandom    -- read N times in random order\n"
               "\treadmissing   -- read N missing keys in random order\n"
-              "\treadhot       -- read N times in random order from 1% section "
-              "of DB\n"
               "\treadwhilewriting      -- 1 writer, N threads doing random "
               "reads\n"
               "\treadwhilemerging      -- 1 merger, N threads doing random "
@@ -145,6 +158,8 @@ DEFINE_string(benchmarks,
               "\tacquireload   -- load N*1000 times\n"
               "\tfillseekseq   -- write N values in sequential key, then read "
               "them by seeking to each key\n"
+              "\trandomtransaction     -- execute N random transactions and "
+              "verify correctness\n"
               "Meta operations:\n"
               "\tcompact     -- Compact the entire DB\n"
               "\tstats       -- Print DB stats\n"
@@ -215,7 +230,7 @@ DEFINE_double(compression_ratio, 0.5, "Arrange to generate values that shrink"
 
 DEFINE_double(read_random_exp_range, 0.0,
               "Read random's key will be generated using distribution of "
-              "num * exp(r) where r is uniform number from 0 to this value. "
+              "num * exp(-r) where r is uniform number from 0 to this value. "
               "The larger the number is, the more skewed the reads are. "
               "Only used in readrandom and multireadrandom benchmarks.");
 
@@ -251,6 +266,20 @@ DEFINE_int32(min_write_buffer_number_to_merge,
              " writing less data to storage if there are duplicate records "
              " in each of these individual write buffers.");
 
+DEFINE_int32(max_write_buffer_number_to_maintain,
+             rocksdb::Options().max_write_buffer_number_to_maintain,
+             "The total maximum number of write buffers to maintain in memory "
+             "including copies of buffers that have already been flushed. "
+             "Unlike max_write_buffer_number, this parameter does not affect "
+             "flushing. This controls the minimum amount of write history "
+             "that will be available in memory for conflict checking when "
+             "Transactions are used. If this value is too low, some "
+             "transactions may fail at commit time due to not being able to "
+             "determine whether there were any write conflicts. Setting this "
+             "value to 0 will cause write buffers to be freed immediately "
+             "after they are flushed.  If this value is set to -1, "
+             "'max_write_buffer_number' will be used.");
+
 DEFINE_int32(max_background_compactions,
              rocksdb::Options().max_background_compactions,
              "The maximum number of concurrent background compactions"
@@ -282,9 +311,15 @@ DEFINE_int32(universal_compression_size_percent, -1,
              "The percentage of the database to compress for universal "
              "compaction. -1 means compress everything.");
 
+DEFINE_bool(universal_allow_trivial_move, false,
+            "Sllow trivial move in universal compaction.");
+
 DEFINE_int64(cache_size, -1, "Number of bytes to use as a cache of uncompressed"
              "data. Negative means use default settings.");
 
+DEFINE_bool(cache_index_and_filter_blocks, false,
+            "Cache index/filter blocks in block cache.");
+
 DEFINE_int32(block_size,
              static_cast<int32_t>(rocksdb::BlockBasedTableOptions().block_size),
              "Number of bytes in a block.");
@@ -297,6 +332,10 @@ DEFINE_int32(block_restart_interval,
 DEFINE_int64(compressed_cache_size, -1,
              "Number of bytes to use as a cache of compressed data.");
 
+DEFINE_int64(row_cache_size, 0,
+             "Number of bytes to use as a cache of individual rows"
+             " (0 = disabled).");
+
 DEFINE_int32(open_files, rocksdb::Options().max_open_files,
              "Maximum number of files to keep open at the same time"
              " (use default if == 0)");
@@ -367,13 +406,19 @@ static std::vector<int> FLAGS_max_bytes_for_level_multiplier_additional_v;
 DEFINE_string(max_bytes_for_level_multiplier_additional, "",
               "A vector that specifies additional fanout per level");
 
-DEFINE_int32(level0_stop_writes_trigger, 12, "Number of files in level-0"
+DEFINE_int32(level0_stop_writes_trigger,
+             rocksdb::Options().level0_stop_writes_trigger,
+             "Number of files in level-0"
              " that will trigger put stop.");
 
-DEFINE_int32(level0_slowdown_writes_trigger, 8, "Number of files in level-0"
+DEFINE_int32(level0_slowdown_writes_trigger,
+             rocksdb::Options().level0_slowdown_writes_trigger,
+             "Number of files in level-0"
              " that will slow down writes.");
 
-DEFINE_int32(level0_file_num_compaction_trigger, 4, "Number of files in level-0"
+DEFINE_int32(level0_file_num_compaction_trigger,
+             rocksdb::Options().level0_file_num_compaction_trigger,
+             "Number of files in level-0"
              " when compactions start");
 
 static bool ValidateInt32Percent(const char* flagname, int32_t value) {
@@ -403,6 +448,18 @@ DEFINE_int32(deletepercent, 2, "Percentage of deletes out of reads/writes/"
 DEFINE_uint64(delete_obsolete_files_period_micros, 0,
               "Ignored. Left here for backward compatibility");
 
+DEFINE_bool(transaction_db, false,
+            "Open a OptimisticTransactionDB instance. "
+            "Required for randomtransaction benchmark.");
+
+DEFINE_uint64(transaction_sets, 2,
+              "Number of keys each transaction will "
+              "modify (use in RandomTransaction only).  Max: 9999");
+
+DEFINE_int32(transaction_sleep, 0,
+             "Max microseconds to sleep in between "
+             "reading and writing a value (used in RandomTransaction only). ");
+
 namespace {
 enum rocksdb::CompressionType StringToCompressionType(const char* ctype) {
   assert(ctype);
@@ -485,6 +542,14 @@ DEFINE_int64(stats_interval_seconds, 0, "Report stats every N seconds. This "
 DEFINE_int32(stats_per_interval, 0, "Reports additional stats per interval when"
              " this is greater than 0.");
 
+DEFINE_int64(report_interval_seconds, 0,
+             "If greater than zero, it will write simple stats in CVS format "
+             "to --report_file every N seconds");
+
+DEFINE_string(report_file, "report.csv",
+              "Filename where some simple stats are reported to (if "
+              "--report_interval_seconds is bigger than 0)");
+
 DEFINE_int32(thread_status_per_interval, 0,
              "Takes and report a snapshot of the current status of each thread"
              " when this is greater than 0.");
@@ -492,7 +557,7 @@ DEFINE_int32(thread_status_per_interval, 0,
 DEFINE_int32(perf_level, 0, "Level of perf collection");
 
 static bool ValidateRateLimit(const char* flagname, double value) {
-  static constexpr double EPSILON = 1e-10;
+  const double EPSILON = 1e-10;
   if ( value < -EPSILON ) {
     fprintf(stderr, "Invalid value for --%s: %12.6f, must be >= 0.0\n",
             flagname, value);
@@ -506,12 +571,20 @@ DEFINE_double(hard_rate_limit, 0.0, "When not equal to 0 this make threads "
               "sleep at each stats reporting interval until the compaction"
               " score for all levels is less than or equal to this value.");
 
+DEFINE_uint64(delayed_write_rate, 2097152u,
+              "Limited bytes allowed to DB when soft_rate_limit or "
+              "level0_slowdown_writes_trigger triggers");
+
 DEFINE_int32(rate_limit_delay_max_milliseconds, 1000,
              "When hard_rate_limit is set then this is the max time a put will"
              " be stalled.");
 
 DEFINE_uint64(rate_limiter_bytes_per_sec, 0, "Set options.rate_limiter value.");
 
+DEFINE_uint64(
+    benchmark_write_rate_limit, 0,
+    "If non-zero, db_bench will rate-limit the writes going into RocksDB");
+
 DEFINE_int32(max_grandparent_overlap_factor, 10, "Control maximum bytes of "
              "overlaps in grandparent (i.e., level+2) before we stop building a"
              " single file in a level->level+1 compaction.");
@@ -846,6 +919,7 @@ static void AppendWithSpace(std::string* str, Slice msg) {
 struct DBWithColumnFamilies {
   std::vector<ColumnFamilyHandle*> cfh;
   DB* db;
+  OptimisticTransactionDB* txn_db;
   std::atomic<size_t> num_created;  // Need to be updated after all the
                                     // new entries in cfh are set.
   size_t num_hot;  // Number of column families to be queried at each moment.
@@ -853,7 +927,7 @@ struct DBWithColumnFamilies {
                    // Column families will be created and used to be queried.
   port::Mutex create_cf_mutex;  // Only one thread can execute CreateNewCf()
 
-  DBWithColumnFamilies() : db(nullptr) {
+  DBWithColumnFamilies() : db(nullptr), txn_db(nullptr) {
     cfh.clear();
     num_created = 0;
     num_hot = 0;
@@ -862,9 +936,23 @@ struct DBWithColumnFamilies {
   DBWithColumnFamilies(const DBWithColumnFamilies& other)
       : cfh(other.cfh),
         db(other.db),
+        txn_db(other.txn_db),
         num_created(other.num_created.load()),
         num_hot(other.num_hot) {}
 
+  void DeleteDBs() {
+    std::for_each(cfh.begin(), cfh.end(),
+                  [](ColumnFamilyHandle* cfhi) { delete cfhi; });
+    cfh.clear();
+    if (txn_db) {
+      delete txn_db;
+      txn_db = nullptr;
+    } else {
+      delete db;
+    }
+    db = nullptr;
+  }
+
   ColumnFamilyHandle* GetCfh(int64_t rand_num) {
     assert(num_hot > 0);
     return cfh[num_created.load(std::memory_order_acquire) - num_hot +
@@ -894,6 +982,96 @@ struct DBWithColumnFamilies {
   }
 };
 
+// a class that reports stats to CSV file
+class ReporterAgent {
+ public:
+  ReporterAgent(Env* env, const std::string& fname,
+                uint64_t report_interval_secs)
+      : env_(env),
+        total_ops_done_(0),
+        last_report_(0),
+        report_interval_secs_(report_interval_secs),
+        stop_(false) {
+    auto s = env_->NewWritableFile(fname, &report_file_, EnvOptions());
+    if (s.ok()) {
+      s = report_file_->Append(Header() + "\n");
+    }
+    if (s.ok()) {
+      s = report_file_->Flush();
+    }
+    if (!s.ok()) {
+      fprintf(stderr, "Can't open %s: %s\n", fname.c_str(),
+              s.ToString().c_str());
+      abort();
+    }
+
+    reporting_thread_ = std::thread([&]() { SleepAndReport(); });
+  }
+
+  ~ReporterAgent() {
+    {
+      std::unique_lock<std::mutex> lk(mutex_);
+      stop_ = true;
+      stop_cv_.notify_all();
+    }
+    reporting_thread_.join();
+  }
+
+  // thread safe
+  void ReportFinishedOps(int64_t num_ops) {
+    total_ops_done_.fetch_add(num_ops);
+  }
+
+ private:
+  std::string Header() const { return "secs_elapsed,interval_qps"; }
+  void SleepAndReport() {
+    uint64_t kMicrosInSecond = 1000 * 1000;
+    auto time_started = env_->NowMicros();
+    while (true) {
+      {
+        std::unique_lock<std::mutex> lk(mutex_);
+        if (stop_ ||
+            stop_cv_.wait_for(lk, std::chrono::seconds(report_interval_secs_),
+                              [&]() { return stop_; })) {
+          // stopping
+          break;
+        }
+        // else -> timeout, which means time for a report!
+      }
+      auto total_ops_done_snapshot = total_ops_done_.load();
+      // round the seconds elapsed
+      auto secs_elapsed =
+          (env_->NowMicros() - time_started + kMicrosInSecond / 2) /
+          kMicrosInSecond;
+      std::string report = ToString(secs_elapsed) + "," +
+                           ToString(total_ops_done_snapshot - last_report_) +
+                           "\n";
+      auto s = report_file_->Append(report);
+      if (s.ok()) {
+        s = report_file_->Flush();
+      }
+      if (!s.ok()) {
+        fprintf(stderr,
+                "Can't write to report file (%s), stopping the reporting\n",
+                s.ToString().c_str());
+        break;
+      }
+      last_report_ = total_ops_done_snapshot;
+    }
+  }
+
+  Env* env_;
+  std::unique_ptr<WritableFile> report_file_;
+  std::atomic<int64_t> total_ops_done_;
+  int64_t last_report_;
+  const uint64_t report_interval_secs_;
+  std::thread reporting_thread_;
+  std::mutex mutex_;
+  // will notify on stop
+  std::condition_variable stop_cv_;
+  bool stop_;
+};
+
 class Stats {
  private:
   int id_;
@@ -909,10 +1087,15 @@ class Stats {
   HistogramImpl hist_;
   std::string message_;
   bool exclude_from_merge_;
+  ReporterAgent* reporter_agent_;  // does not own
 
  public:
   Stats() { Start(-1); }
 
+  void SetReporterAgent(ReporterAgent* reporter_agent) {
+    reporter_agent_ = reporter_agent;
+  }
+
   void Start(int id) {
     id_ = id;
     next_report_ = FLAGS_stats_interval ? FLAGS_stats_interval : 100;
@@ -988,6 +1171,9 @@ class Stats {
   }
 
   void FinishedOps(DBWithColumnFamilies* db_with_cfh, DB* db, int64_t num_ops) {
+    if (reporter_agent_) {
+      reporter_agent_->ReportFinishedOps(num_ops);
+    }
     if (FLAGS_histogram) {
       double now = FLAGS_env->NowMicros();
       double micros = now - last_op_finish_;
@@ -1120,6 +1306,7 @@ struct SharedState {
   port::CondVar cv;
   int total;
   int perf_level;
+  std::shared_ptr<RateLimiter> write_rate_limiter;
 
   // Each thread goes through the following states:
   //    (1) initializing
@@ -1232,7 +1419,7 @@ class Benchmark {
             (((FLAGS_key_size + FLAGS_value_size * FLAGS_compression_ratio)
               * num_)
              / 1048576.0));
-    fprintf(stdout, "Write rate limit: %d\n", FLAGS_writes_per_second);
+    fprintf(stdout, "Writes per second: %d\n", FLAGS_writes_per_second);
     if (FLAGS_enable_numa) {
       fprintf(stderr, "Running in NUMA enabled mode.\n");
 #ifndef NUMA
@@ -1467,9 +1654,7 @@ class Benchmark {
   }
 
   ~Benchmark() {
-    std::for_each(db_.cfh.begin(), db_.cfh.end(),
-                  [](ColumnFamilyHandle* cfh) { delete cfh; });
-    delete db_.db;
+    db_.DeleteDBs();
     delete prefix_extractor_;
     if (cache_.get() != nullptr) {
       // this will leak, but we're shutting down so nobody cares
@@ -1573,6 +1758,8 @@ class Benchmark {
       write_options_.disableWAL = FLAGS_disable_wal;
 
       void (Benchmark::*method)(ThreadState*) = nullptr;
+      void (Benchmark::*post_process_method)() = nullptr;
+
       bool fresh_db = false;
       int num_threads = FLAGS_threads;
 
@@ -1688,6 +1875,9 @@ class Benchmark {
         method = &Benchmark::Compress;
       } else if (name == Slice("uncompress")) {
         method = &Benchmark::Uncompress;
+      } else if (name == Slice("randomtransaction")) {
+        method = &Benchmark::RandomTransaction;
+        post_process_method = &Benchmark::RandomTransactionVerify;
       } else if (name == Slice("stats")) {
         PrintStats("rocksdb.stats");
       } else if (name == Slice("levelstats")) {
@@ -1708,11 +1898,7 @@ class Benchmark {
           method = nullptr;
         } else {
           if (db_.db != nullptr) {
-            std::for_each(db_.cfh.begin(), db_.cfh.end(),
-                          [](ColumnFamilyHandle* cfh) { delete cfh; });
-            delete db_.db;
-            db_.db = nullptr;
-            db_.cfh.clear();
+            db_.DeleteDBs();
             DestroyDB(FLAGS_db, open_options_);
           }
           for (size_t i = 0; i < multi_dbs_.size(); i++) {
@@ -1728,6 +1914,9 @@ class Benchmark {
         fprintf(stdout, "DB path: [%s]\n", FLAGS_db.c_str());
         RunBenchmark(num_threads, name, method);
       }
+      if (post_process_method != nullptr) {
+        (this->*post_process_method)();
+      }
     }
     if (FLAGS_statistics) {
      fprintf(stdout, "STATISTICS:\n%s\n", dbstats->ToString().c_str());
@@ -1780,6 +1969,16 @@ class Benchmark {
     shared.num_initialized = 0;
     shared.num_done = 0;
     shared.start = false;
+    if (FLAGS_benchmark_write_rate_limit > 0) {
+      shared.write_rate_limiter.reset(
+          NewGenericRateLimiter(FLAGS_benchmark_write_rate_limit));
+    }
+
+    std::unique_ptr<ReporterAgent> reporter_agent;
+    if (FLAGS_report_interval_seconds > 0) {
+      reporter_agent.reset(new ReporterAgent(FLAGS_env, FLAGS_report_file,
+                                             FLAGS_report_interval_seconds));
+    }
 
     ThreadArg* arg = new ThreadArg[n];
 
@@ -1805,6 +2004,7 @@ class Benchmark {
       arg[i].method = method;
       arg[i].shared = &shared;
       arg[i].thread = new ThreadState(i);
+      arg[i].thread->stats.SetReporterAgent(reporter_agent.get());
       arg[i].thread->shared = &shared;
       FLAGS_env->StartThread(ThreadBody, &arg[i]);
     }
@@ -2027,6 +2227,8 @@ class Benchmark {
     options.max_write_buffer_number = FLAGS_max_write_buffer_number;
     options.min_write_buffer_number_to_merge =
       FLAGS_min_write_buffer_number_to_merge;
+    options.max_write_buffer_number_to_maintain =
+        FLAGS_max_write_buffer_number_to_maintain;
     options.max_background_compactions = FLAGS_max_background_compactions;
     options.max_background_flushes = FLAGS_max_background_flushes;
     options.compaction_style = FLAGS_compaction_style_e;
@@ -2080,6 +2282,14 @@ class Benchmark {
     options.max_bytes_for_level_multiplier =
         FLAGS_max_bytes_for_level_multiplier;
     options.filter_deletes = FLAGS_filter_deletes;
+    if (FLAGS_row_cache_size) {
+      if (FLAGS_cache_numshardbits >= 1) {
+        options.row_cache =
+            NewLRUCache(FLAGS_row_cache_size, FLAGS_cache_numshardbits);
+      } else {
+        options.row_cache = NewLRUCache(FLAGS_row_cache_size);
+      }
+    }
     if ((FLAGS_prefix_size == 0) && (FLAGS_rep_factory == kPrefixHash ||
                                      FLAGS_rep_factory == kHashLinkedList)) {
       fprintf(stderr, "prefix_size should be non-zero if PrefixHash or "
@@ -2171,6 +2381,8 @@ class Benchmark {
       if (cache_ == nullptr) {
         block_based_options.no_block_cache = true;
       }
+      block_based_options.cache_index_and_filter_blocks =
+          FLAGS_cache_index_and_filter_blocks;
       block_based_options.block_cache = cache_;
       block_based_options.block_cache_compressed = compressed_cache_;
       block_based_options.block_size = FLAGS_block_size;
@@ -2214,6 +2426,7 @@ class Benchmark {
     }
     options.soft_rate_limit = FLAGS_soft_rate_limit;
     options.hard_rate_limit = FLAGS_hard_rate_limit;
+    options.delayed_write_rate = FLAGS_delayed_write_rate;
     options.rate_limit_delay_max_milliseconds =
       FLAGS_rate_limit_delay_max_milliseconds;
     options.table_cache_numshardbits = FLAGS_table_cache_numshardbits;
@@ -2263,6 +2476,8 @@ class Benchmark {
       options.compaction_options_universal.compression_size_percent =
         FLAGS_universal_compression_size_percent;
     }
+    options.compaction_options_universal.allow_trivial_move =
+        FLAGS_universal_allow_trivial_move;
     if (FLAGS_thread_status_per_interval > 0) {
       options.enable_thread_tracking = true;
     }
@@ -2271,6 +2486,11 @@ class Benchmark {
           NewGenericRateLimiter(FLAGS_rate_limiter_bytes_per_sec));
     }
 
+    if (FLAGS_readonly && FLAGS_transaction_db) {
+      fprintf(stderr, "Cannot use readonly flag with transaction_db\n");
+      exit(1);
+    }
+
     if (FLAGS_num_multi_db <= 1) {
       OpenDb(options, FLAGS_db, &db_);
     } else {
@@ -2305,15 +2525,25 @@ class Benchmark {
       if (FLAGS_readonly) {
         s = DB::OpenForReadOnly(options, db_name, column_families,
             &db->cfh, &db->db);
+      } else if (FLAGS_transaction_db) {
+        s = OptimisticTransactionDB::Open(options, db_name, column_families,
+                                          &db->cfh, &db->txn_db);
+        if (s.ok()) {
+          db->db = db->txn_db->GetBaseDB();
+        }
       } else {
         s = DB::Open(options, db_name, column_families, &db->cfh, &db->db);
       }
       db->cfh.resize(FLAGS_num_column_families);
       db->num_created = num_hot;
       db->num_hot = num_hot;
-
     } else if (FLAGS_readonly) {
       s = DB::OpenForReadOnly(options, db_name, &db->db);
+    } else if (FLAGS_transaction_db) {
+      s = OptimisticTransactionDB::Open(options, db_name, &db->txn_db);
+      if (s.ok()) {
+        db->db = db->txn_db->GetBaseDB();
+      }
     } else {
       s = DB::Open(options, db_name, &db->db);
     }
@@ -2451,6 +2681,10 @@ class Benchmark {
       DBWithColumnFamilies* db_with_cfh = SelectDBWithCfh(id);
       batch.Clear();
       for (int64_t j = 0; j < entries_per_batch_; j++) {
+        if (thread->shared->write_rate_limiter.get() != nullptr) {
+          thread->shared->write_rate_limiter->Request(value_size_ + key_size_,
+                                                      Env::IO_HIGH);
+        }
         int64_t rand_num = key_gens[id]->Next();
         GenerateKeyFromInt(rand_num, FLAGS_num, &key);
         if (FLAGS_num_column_families <= 1) {
@@ -3313,8 +3547,8 @@ class Benchmark {
 
     char msg[100];
     snprintf(msg, sizeof(msg),
-             "(reads:%" PRIu64 " merges:%" PRIu64 " total:%" PRIu64 " hits:%" \
-             PRIu64 " maxlength:%zu)",
+             "(reads:%" PRIu64 " merges:%" PRIu64 " total:%" PRIu64
+             " hits:%" PRIu64 " maxlength:%" ROCKSDB_PRIszt ")",
              num_gets, num_merges, readwrites_, num_hits, max_length);
     thread->stats.AddMessage(msg);
   }
@@ -3354,9 +3588,206 @@ class Benchmark {
     }
   }
 
+  // This benchmark stress tests Transactions.  For a given --duration (or
+  // total number of --writes, a Transaction will perform a read-modify-write
+  // to increment the value of a key in each of N(--transaction-sets) sets of
+  // keys (where each set has --num keys).  If --threads is set, this will be
+  // done in parallel.
+  //
+  // To test transactions, use --transaction_db=true.  Not setting this
+  // parameter
+  // will run the same benchmark without transactions.
+  //
+  // RandomTransactionVerify() will then validate the correctness of the results
+  // by checking if the sum of all keys in each set is the same.
+  void RandomTransaction(ThreadState* thread) {
+    ReadOptions options(FLAGS_verify_checksum, true);
+    Duration duration(FLAGS_duration, readwrites_);
+    ReadOptions read_options(FLAGS_verify_checksum, true);
+    std::string value;
+    DB* db = db_.db;
+    uint64_t transactions_done = 0;
+    uint64_t transactions_aborted = 0;
+    Status s;
+    uint64_t num_prefix_ranges = FLAGS_transaction_sets;
+    bool use_txn = FLAGS_transaction_db;
+
+    if (num_prefix_ranges == 0 || num_prefix_ranges > 9999) {
+      fprintf(stderr, "invalid value for transaction_sets\n");
+      abort();
+    }
+
+    if (FLAGS_num_multi_db > 1) {
+      fprintf(stderr,
+              "Cannot run RandomTransaction benchmark with "
+              "FLAGS_multi_db > 1.");
+      abort();
+    }
+
+    while (!duration.Done(1)) {
+      OptimisticTransaction* txn = nullptr;
+      WriteBatch* batch = nullptr;
+
+      if (use_txn) {
+        txn = db_.txn_db->BeginTransaction(write_options_);
+        assert(txn);
+      } else {
+        batch = new WriteBatch();
+      }
+
+      // pick a random number to use to increment a key in each set
+      uint64_t incr = (thread->rand.Next() % 100) + 1;
+
+      // For each set, pick a key at random and increment it
+      for (uint8_t i = 0; i < num_prefix_ranges; i++) {
+        uint64_t int_value;
+        char prefix_buf[5];
+
+        // key format:  [SET#][random#]
+        std::string rand_key = ToString(thread->rand.Next() % FLAGS_num);
+        Slice base_key(rand_key);
+
+        // Pad prefix appropriately so we can iterate over each set
+        snprintf(prefix_buf, sizeof(prefix_buf), "%04d", i + 1);
+        std::string full_key = std::string(prefix_buf) + base_key.ToString();
+        Slice key(full_key);
+
+        if (use_txn) {
+          s = txn->Get(read_options, key, &value);
+        } else {
+          s = db->Get(read_options, key, &value);
+        }
+
+        if (s.ok()) {
+          int_value = std::stoull(value);
+
+          if (int_value == 0 || int_value == ULONG_MAX) {
+            fprintf(stderr, "Get returned unexpected value: %s\n",
+                    value.c_str());
+            abort();
+          }
+        } else if (s.IsNotFound()) {
+          int_value = 0;
+        } else {
+          fprintf(stderr, "Get returned an error: %s\n", s.ToString().c_str());
+          abort();
+        }
+
+        if (FLAGS_transaction_sleep > 0) {
+          FLAGS_env->SleepForMicroseconds(thread->rand.Next() %
+                                          FLAGS_transaction_sleep);
+        }
+
+        std::string sum = ToString(int_value + incr);
+        if (use_txn) {
+          txn->Put(key, sum);
+        } else {
+          batch->Put(key, sum);
+        }
+      }
+
+      if (use_txn) {
+        s = txn->Commit();
+      } else {
+        s = db->Write(write_options_, batch);
+      }
+
+      if (!s.ok()) {
+        // Ideally, we'd want to run this stress test with enough concurrency
+        // on a small enough set of keys that we get some failed transactions
+        // due to conflicts.
+        if (use_txn && s.IsBusy()) {
+          transactions_aborted++;
+        } else {
+          fprintf(stderr, "Unexpected write error: %s\n", s.ToString().c_str());
+          abort();
+        }
+      }
+
+      if (txn) {
+        delete txn;
+      }
+      if (batch) {
+        delete batch;
+      }
+
+      transactions_done++;
+    }
+
+    char msg[100];
+    if (use_txn) {
+      snprintf(msg, sizeof(msg),
+               "( transactions:%" PRIu64 " aborts:%" PRIu64 ")",
+               transactions_done, transactions_aborted);
+    } else {
+      snprintf(msg, sizeof(msg), "( batches:%" PRIu64 " )", transactions_done);
+    }
+    thread->stats.AddMessage(msg);
+
+    if (FLAGS_perf_level > 0) {
+      thread->stats.AddMessage(perf_context.ToString());
+    }
+  }
+
+  // Verifies consistency of data after RandomTransaction() has been run.
+  // Since each iteration of RandomTransaction() incremented a key in each set
+  // by the same value, the sum of the keys in each set should be the same.
+  void RandomTransactionVerify() {
+    if (!FLAGS_transaction_db) {
+      // transactions not used, nothing to verify.
+      return;
+    }
+
+    uint64_t prev_total = 0;
+
+    // For each set of keys with the same prefix, sum all the values
+    for (uint32_t i = 0; i < FLAGS_transaction_sets; i++) {
+      char prefix_buf[5];
+      snprintf(prefix_buf, sizeof(prefix_buf), "%04u", i + 1);
+      uint64_t total = 0;
+
+      Iterator* iter = db_.db->NewIterator(ReadOptions());
+
+      for (iter->Seek(Slice(prefix_buf, 4)); iter->Valid(); iter->Next()) {
+        Slice key = iter->key();
+
+        // stop when we reach a different prefix
+        if (key.ToString().compare(0, 4, prefix_buf) != 0) {
+          break;
+        }
+
+        Slice value = iter->value();
+        uint64_t int_value = std::stoull(value.ToString());
+        if (int_value == 0 || int_value == ULONG_MAX) {
+          fprintf(stderr, "Iter returned unexpected value: %s\n",
+                  value.ToString().c_str());
+          abort();
+        }
+
+        total += int_value;
+      }
+      delete iter;
+
+      if (i > 0) {
+        if (total != prev_total) {
+          fprintf(stderr,
+                  "RandomTransactionVerify found inconsistent totals. "
+                  "Set[%" PRIu32 "]: %" PRIu64 ", Set[%" PRIu32 "]: %" PRIu64
+                  " \n",
+                  i - 1, prev_total, i, total);
+          abort();
+        }
+      }
+      prev_total = total;
+    }
+
+    fprintf(stdout, "RandomTransactionVerify Success! Total:%" PRIu64 "\n",
+            prev_total);
+  }
+
   void Compact(ThreadState* thread) {
     DB* db = SelectDB(thread);
-    db->CompactRange(nullptr, nullptr);
+    db->CompactRange(CompactRangeOptions(), nullptr, nullptr);
   }
 
   void PrintStats(const char* key) {
@@ -3397,7 +3828,11 @@ int main(int argc, char** argv) {
       FLAGS_max_bytes_for_level_multiplier_additional, ',');
   for (unsigned int j= 0; j < fanout.size(); j++) {
     FLAGS_max_bytes_for_level_multiplier_additional_v.push_back(
-      std::stoi(fanout[j]));
+#ifndef CYGWIN
+        std::stoi(fanout[j]));
+#else
+        stoi(fanout[j]));
+#endif
   }
 
   FLAGS_compression_type_e =

db/db_compaction_filter_test.cc

@@ -0,0 +1,548 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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 "port/stack_trace.h"
+#include "util/db_test_util.h"
+
+namespace rocksdb {
+
+static int cfilter_count = 0;
+
+// This is a static filter used for filtering
+// kvs during the compaction process.
+static std::string NEW_VALUE = "NewValue";
+
+class DBTestCompactionFilter : public DBTestBase {
+ public:
+  DBTestCompactionFilter() : DBTestBase("/db_compaction_filter_test") {}
+};
+
+class KeepFilter : public CompactionFilter {
+ public:
+  virtual bool Filter(int level, const Slice& key, const Slice& value,
+                      std::string* new_value, bool* value_changed) const
+      override {
+    cfilter_count++;
+    return false;
+  }
+
+  virtual const char* Name() const override { return "KeepFilter"; }
+};
+
+class DeleteFilter : public CompactionFilter {
+ public:
+  virtual bool Filter(int level, const Slice& key, const Slice& value,
+                      std::string* new_value, bool* value_changed) const
+      override {
+    cfilter_count++;
+    return true;
+  }
+
+  virtual const char* Name() const override { return "DeleteFilter"; }
+};
+
+class DelayFilter : public CompactionFilter {
+ public:
+  explicit DelayFilter(DBTestBase* d) : db_test(d) {}
+  virtual bool Filter(int level, const Slice& key, const Slice& value,
+                      std::string* new_value,
+                      bool* value_changed) const override {
+    db_test->env_->addon_time_.fetch_add(1000);
+    return true;
+  }
+
+  virtual const char* Name() const override { return "DelayFilter"; }
+
+ private:
+  DBTestBase* db_test;
+};
+
+class ConditionalFilter : public CompactionFilter {
+ public:
+  explicit ConditionalFilter(const std::string* filtered_value)
+      : filtered_value_(filtered_value) {}
+  virtual bool Filter(int level, const Slice& key, const Slice& value,
+                      std::string* new_value,
+                      bool* value_changed) const override {
+    return value.ToString() == *filtered_value_;
+  }
+
+  virtual const char* Name() const override { return "ConditionalFilter"; }
+
+ private:
+  const std::string* filtered_value_;
+};
+
+class ChangeFilter : public CompactionFilter {
+ public:
+  explicit ChangeFilter() {}
+
+  virtual bool Filter(int level, const Slice& key, const Slice& value,
+                      std::string* new_value, bool* value_changed) const
+      override {
+    assert(new_value != nullptr);
+    *new_value = NEW_VALUE;
+    *value_changed = true;
+    return false;
+  }
+
+  virtual const char* Name() const override { return "ChangeFilter"; }
+};
+
+class KeepFilterFactory : public CompactionFilterFactory {
+ public:
+  explicit KeepFilterFactory(bool check_context = false)
+      : check_context_(check_context) {}
+
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+      const CompactionFilter::Context& context) override {
+    if (check_context_) {
+      EXPECT_EQ(expect_full_compaction_.load(), context.is_full_compaction);
+      EXPECT_EQ(expect_manual_compaction_.load(), context.is_manual_compaction);
+    }
+    return std::unique_ptr<CompactionFilter>(new KeepFilter());
+  }
+
+  virtual const char* Name() const override { return "KeepFilterFactory"; }
+  bool check_context_;
+  std::atomic_bool expect_full_compaction_;
+  std::atomic_bool expect_manual_compaction_;
+};
+
+class DeleteFilterFactory : public CompactionFilterFactory {
+ public:
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+      const CompactionFilter::Context& context) override {
+    if (context.is_manual_compaction) {
+      return std::unique_ptr<CompactionFilter>(new DeleteFilter());
+    } else {
+      return std::unique_ptr<CompactionFilter>(nullptr);
+    }
+  }
+
+  virtual const char* Name() const override { return "DeleteFilterFactory"; }
+};
+
+class DelayFilterFactory : public CompactionFilterFactory {
+ public:
+  explicit DelayFilterFactory(DBTestBase* d) : db_test(d) {}
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+      const CompactionFilter::Context& context) override {
+    return std::unique_ptr<CompactionFilter>(new DelayFilter(db_test));
+  }
+
+  virtual const char* Name() const override { return "DelayFilterFactory"; }
+
+ private:
+  DBTestBase* db_test;
+};
+
+class ConditionalFilterFactory : public CompactionFilterFactory {
+ public:
+  explicit ConditionalFilterFactory(const Slice& filtered_value)
+      : filtered_value_(filtered_value.ToString()) {}
+
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+      const CompactionFilter::Context& context) override {
+    return std::unique_ptr<CompactionFilter>(
+        new ConditionalFilter(&filtered_value_));
+  }
+
+  virtual const char* Name() const override {
+    return "ConditionalFilterFactory";
+  }
+
+ private:
+  std::string filtered_value_;
+};
+
+class ChangeFilterFactory : public CompactionFilterFactory {
+ public:
+  explicit ChangeFilterFactory() {}
+
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+      const CompactionFilter::Context& context) override {
+    return std::unique_ptr<CompactionFilter>(new ChangeFilter());
+  }
+
+  virtual const char* Name() const override { return "ChangeFilterFactory"; }
+};
+
+TEST_F(DBTestCompactionFilter, CompactionFilter) {
+  Options options = CurrentOptions();
+  options.max_open_files = -1;
+  options.num_levels = 3;
+  options.compaction_filter_factory = std::make_shared<KeepFilterFactory>();
+  options = CurrentOptions(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  // Write 100K keys, these are written to a few files in L0.
+  const std::string value(10, 'x');
+  for (int i = 0; i < 100000; i++) {
+    char key[100];
+    snprintf(key, sizeof(key), "B%010d", i);
+    Put(1, key, value);
+  }
+  ASSERT_OK(Flush(1));
+
+  // Push all files to the highest level L2. Verify that
+  // the compaction is each level invokes the filter for
+  // all the keys in that level.
+  cfilter_count = 0;
+  dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+  ASSERT_EQ(cfilter_count, 100000);
+  cfilter_count = 0;
+  dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+  ASSERT_EQ(cfilter_count, 100000);
+
+  ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
+  ASSERT_NE(NumTableFilesAtLevel(2, 1), 0);
+  cfilter_count = 0;
+
+  // All the files are in the lowest level.
+  // Verify that all but the 100001st record
+  // has sequence number zero. The 100001st record
+  // is at the tip of this snapshot and cannot
+  // be zeroed out.
+  int count = 0;
+  int total = 0;
+  Arena arena;
+  {
+    ScopedArenaIterator iter(
+        dbfull()->TEST_NewInternalIterator(&arena, handles_[1]));
+    iter->SeekToFirst();
+    ASSERT_OK(iter->status());
+    while (iter->Valid()) {
+      ParsedInternalKey ikey(Slice(), 0, kTypeValue);
+      ikey.sequence = -1;
+      ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
+      total++;
+      if (ikey.sequence != 0) {
+        count++;
+      }
+      iter->Next();
+    }
+  }
+  ASSERT_EQ(total, 100000);
+  ASSERT_EQ(count, 1);
+
+  // overwrite all the 100K keys once again.
+  for (int i = 0; i < 100000; i++) {
+    char key[100];
+    snprintf(key, sizeof(key), "B%010d", i);
+    ASSERT_OK(Put(1, key, value));
+  }
+  ASSERT_OK(Flush(1));
+
+  // push all files to the highest level L2. This
+  // means that all keys should pass at least once
+  // via the compaction filter
+  cfilter_count = 0;
+  dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+  ASSERT_EQ(cfilter_count, 100000);
+  cfilter_count = 0;
+  dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+  ASSERT_EQ(cfilter_count, 100000);
+  ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
+  ASSERT_NE(NumTableFilesAtLevel(2, 1), 0);
+
+  // create a new database with the compaction
+  // filter in such a way that it deletes all keys
+  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
+  options.create_if_missing = true;
+  DestroyAndReopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  // write all the keys once again.
+  for (int i = 0; i < 100000; i++) {
+    char key[100];
+    snprintf(key, sizeof(key), "B%010d", i);
+    ASSERT_OK(Put(1, key, value));
+  }
+  ASSERT_OK(Flush(1));
+  ASSERT_NE(NumTableFilesAtLevel(0, 1), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(2, 1), 0);
+
+  // Push all files to the highest level L2. This
+  // triggers the compaction filter to delete all keys,
+  // verify that at the end of the compaction process,
+  // nothing is left.
+  cfilter_count = 0;
+  dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+  ASSERT_EQ(cfilter_count, 100000);
+  cfilter_count = 0;
+  dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+  ASSERT_EQ(cfilter_count, 0);
+  ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
+
+  {
+    // Scan the entire database to ensure that nothing is left
+    std::unique_ptr<Iterator> iter(
+        db_->NewIterator(ReadOptions(), handles_[1]));
+    iter->SeekToFirst();
+    count = 0;
+    while (iter->Valid()) {
+      count++;
+      iter->Next();
+    }
+    ASSERT_EQ(count, 0);
+  }
+
+  // The sequence number of the remaining record
+  // is not zeroed out even though it is at the
+  // level Lmax because this record is at the tip
+  count = 0;
+  {
+    ScopedArenaIterator iter(
+        dbfull()->TEST_NewInternalIterator(&arena, handles_[1]));
+    iter->SeekToFirst();
+    ASSERT_OK(iter->status());
+    while (iter->Valid()) {
+      ParsedInternalKey ikey(Slice(), 0, kTypeValue);
+      ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
+      ASSERT_NE(ikey.sequence, (unsigned)0);
+      count++;
+      iter->Next();
+    }
+    ASSERT_EQ(count, 0);
+  }
+}
+
+// Tests the edge case where compaction does not produce any output -- all
+// entries are deleted. The compaction should create bunch of 'DeleteFile'
+// entries in VersionEdit, but none of the 'AddFile's.
+TEST_F(DBTestCompactionFilter, CompactionFilterDeletesAll) {
+  Options options;
+  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
+  options.disable_auto_compactions = true;
+  options.create_if_missing = true;
+  options = CurrentOptions(options);
+  DestroyAndReopen(options);
+
+  // put some data
+  for (int table = 0; table < 4; ++table) {
+    for (int i = 0; i < 10 + table; ++i) {
+      Put(ToString(table * 100 + i), "val");
+    }
+    Flush();
+  }
+
+  // this will produce empty file (delete compaction filter)
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  ASSERT_EQ(0U, CountLiveFiles());
+
+  Reopen(options);
+
+  Iterator* itr = db_->NewIterator(ReadOptions());
+  itr->SeekToFirst();
+  // empty db
+  ASSERT_TRUE(!itr->Valid());
+
+  delete itr;
+}
+
+TEST_F(DBTestCompactionFilter, CompactionFilterWithValueChange) {
+  do {
+    Options options;
+    options.num_levels = 3;
+    options.compaction_filter_factory =
+      std::make_shared<ChangeFilterFactory>();
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Write 100K+1 keys, these are written to a few files
+    // in L0. We do this so that the current snapshot points
+    // to the 100001 key.The compaction filter is  not invoked
+    // on keys that are visible via a snapshot because we
+    // anyways cannot delete it.
+    const std::string value(10, 'x');
+    for (int i = 0; i < 100001; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%010d", i);
+      Put(1, key, value);
+    }
+
+    // push all files to  lower levels
+    ASSERT_OK(Flush(1));
+    if (option_config_ != kUniversalCompactionMultiLevel) {
+      dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+      dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+    } else {
+      dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
+                             nullptr);
+    }
+
+    // re-write all data again
+    for (int i = 0; i < 100001; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%010d", i);
+      Put(1, key, value);
+    }
+
+    // push all files to  lower levels. This should
+    // invoke the compaction filter for all 100000 keys.
+    ASSERT_OK(Flush(1));
+    if (option_config_ != kUniversalCompactionMultiLevel) {
+      dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
+      dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
+    } else {
+      dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
+                             nullptr);
+    }
+
+    // verify that all keys now have the new value that
+    // was set by the compaction process.
+    for (int i = 0; i < 100001; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%010d", i);
+      std::string newvalue = Get(1, key);
+      ASSERT_EQ(newvalue.compare(NEW_VALUE), 0);
+    }
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestCompactionFilter, CompactionFilterWithMergeOperator) {
+  std::string one, two, three, four;
+  PutFixed64(&one, 1);
+  PutFixed64(&two, 2);
+  PutFixed64(&three, 3);
+  PutFixed64(&four, 4);
+
+  Options options;
+  options = CurrentOptions(options);
+  options.create_if_missing = true;
+  options.merge_operator = MergeOperators::CreateUInt64AddOperator();
+  options.num_levels = 3;
+  // Filter out keys with value is 2.
+  options.compaction_filter_factory =
+      std::make_shared<ConditionalFilterFactory>(two);
+  DestroyAndReopen(options);
+
+  // In the same compaction, a value type needs to be deleted based on
+  // compaction filter, and there is a merge type for the key. compaction
+  // filter result is ignored.
+  ASSERT_OK(db_->Put(WriteOptions(), "foo", two));
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->Merge(WriteOptions(), "foo", one));
+  ASSERT_OK(Flush());
+  std::string newvalue = Get("foo");
+  ASSERT_EQ(newvalue, three);
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  newvalue = Get("foo");
+  ASSERT_EQ(newvalue, three);
+
+  // value key can be deleted based on compaction filter, leaving only
+  // merge keys.
+  ASSERT_OK(db_->Put(WriteOptions(), "bar", two));
+  ASSERT_OK(Flush());
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  newvalue = Get("bar");
+  ASSERT_EQ("NOT_FOUND", newvalue);
+  ASSERT_OK(db_->Merge(WriteOptions(), "bar", two));
+  ASSERT_OK(Flush());
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  newvalue = Get("bar");
+  ASSERT_EQ(two, two);
+
+  // Compaction filter never applies to merge keys.
+  ASSERT_OK(db_->Put(WriteOptions(), "foobar", one));
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->Merge(WriteOptions(), "foobar", two));
+  ASSERT_OK(Flush());
+  newvalue = Get("foobar");
+  ASSERT_EQ(newvalue, three);
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  newvalue = Get("foobar");
+  ASSERT_EQ(newvalue, three);
+
+  // In the same compaction, both of value type and merge type keys need to be
+  // deleted based on compaction filter, and there is a merge type for the key.
+  // For both keys, compaction filter results are ignored.
+  ASSERT_OK(db_->Put(WriteOptions(), "barfoo", two));
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->Merge(WriteOptions(), "barfoo", two));
+  ASSERT_OK(Flush());
+  newvalue = Get("barfoo");
+  ASSERT_EQ(newvalue, four);
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  newvalue = Get("barfoo");
+  ASSERT_EQ(newvalue, four);
+}
+
+TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
+  KeepFilterFactory* filter = new KeepFilterFactory();
+
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleUniversal;
+  options.compaction_filter_factory.reset(filter);
+  options.compression = kNoCompression;
+  options.level0_file_num_compaction_trigger = 8;
+  Reopen(options);
+  int num_keys_per_file = 400;
+  for (int j = 0; j < 3; j++) {
+    // Write several keys.
+    const std::string value(10, 'x');
+    for (int i = 0; i < num_keys_per_file; i++) {
+      char key[100];
+      snprintf(key, sizeof(key), "B%08d%02d", i, j);
+      Put(key, value);
+    }
+    dbfull()->TEST_FlushMemTable();
+    // Make sure next file is much smaller so automatic compaction will not
+    // be triggered.
+    num_keys_per_file /= 2;
+  }
+
+  // Force a manual compaction
+  cfilter_count = 0;
+  filter->expect_manual_compaction_.store(true);
+  filter->expect_full_compaction_.store(false);  // Manual compaction always
+                                                 // set this flag.
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  ASSERT_EQ(cfilter_count, 700);
+  ASSERT_EQ(NumSortedRuns(0), 1);
+
+  // Verify total number of keys is correct after manual compaction.
+  {
+    int count = 0;
+    int total = 0;
+    Arena arena;
+    ScopedArenaIterator iter(dbfull()->TEST_NewInternalIterator(&arena));
+    iter->SeekToFirst();
+    ASSERT_OK(iter->status());
+    while (iter->Valid()) {
+      ParsedInternalKey ikey(Slice(), 0, kTypeValue);
+      ikey.sequence = -1;
+      ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
+      total++;
+      if (ikey.sequence != 0) {
+        count++;
+      }
+      iter->Next();
+    }
+    ASSERT_EQ(total, 700);
+    ASSERT_EQ(count, 1);
+  }
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+#if !(defined NDEBUG) || !defined(OS_WIN)
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+#else
+  return 0;
+#endif
+}

db/db_dynamic_level_test.cc

@@ -0,0 +1,497 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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.
+
+// Introduction of SyncPoint effectively disabled building and running this test
+// in Release build.
+// which is a pity, it is a good test
+#if !(defined NDEBUG) || !defined(OS_WIN)
+
+#include "port/stack_trace.h"
+#include "util/db_test_util.h"
+
+namespace rocksdb {
+class DBTestDynamicLevel : public DBTestBase {
+ public:
+  DBTestDynamicLevel() : DBTestBase("/db_dynamic_level_test") {}
+};
+
+TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
+  if (!Snappy_Supported() || !LZ4_Supported()) {
+    return;
+  }
+  // Use InMemoryEnv, or it would be too slow.
+  unique_ptr<Env> env(new MockEnv(env_));
+
+  const int kNKeys = 1000;
+  int keys[kNKeys];
+
+  auto verify_func = [&]() {
+    for (int i = 0; i < kNKeys; i++) {
+      ASSERT_NE("NOT_FOUND", Get(Key(i)));
+      ASSERT_NE("NOT_FOUND", Get(Key(kNKeys * 2 + i)));
+      if (i < kNKeys / 10) {
+        ASSERT_EQ("NOT_FOUND", Get(Key(kNKeys + keys[i])));
+      } else {
+        ASSERT_NE("NOT_FOUND", Get(Key(kNKeys + keys[i])));
+      }
+    }
+  };
+
+  Random rnd(301);
+  for (int ordered_insert = 0; ordered_insert <= 1; ordered_insert++) {
+    for (int i = 0; i < kNKeys; i++) {
+      keys[i] = i;
+    }
+    if (ordered_insert == 0) {
+      std::random_shuffle(std::begin(keys), std::end(keys));
+    }
+    for (int max_background_compactions = 1; max_background_compactions < 4;
+         max_background_compactions += 2) {
+      Options options;
+      options.env = env.get();
+      options.create_if_missing = true;
+      options.db_write_buffer_size = 2048;
+      options.write_buffer_size = 2048;
+      options.max_write_buffer_number = 2;
+      options.level0_file_num_compaction_trigger = 2;
+      options.level0_slowdown_writes_trigger = 2;
+      options.level0_stop_writes_trigger = 2;
+      options.target_file_size_base = 2048;
+      options.level_compaction_dynamic_level_bytes = true;
+      options.max_bytes_for_level_base = 10240;
+      options.max_bytes_for_level_multiplier = 4;
+      options.soft_rate_limit = 1.1;
+      options.max_background_compactions = max_background_compactions;
+      options.num_levels = 5;
+
+      options.compression_per_level.resize(3);
+      options.compression_per_level[0] = kNoCompression;
+      options.compression_per_level[1] = kLZ4Compression;
+      options.compression_per_level[2] = kSnappyCompression;
+
+      DestroyAndReopen(options);
+
+      for (int i = 0; i < kNKeys; i++) {
+        int key = keys[i];
+        ASSERT_OK(Put(Key(kNKeys + key), RandomString(&rnd, 102)));
+        ASSERT_OK(Put(Key(key), RandomString(&rnd, 102)));
+        ASSERT_OK(Put(Key(kNKeys * 2 + key), RandomString(&rnd, 102)));
+        ASSERT_OK(Delete(Key(kNKeys + keys[i / 10])));
+        env_->SleepForMicroseconds(5000);
+      }
+
+      uint64_t int_prop;
+      ASSERT_TRUE(db_->GetIntProperty("rocksdb.background-errors", &int_prop));
+      ASSERT_EQ(0U, int_prop);
+
+      // Verify DB
+      for (int j = 0; j < 2; j++) {
+        verify_func();
+        if (j == 0) {
+          Reopen(options);
+        }
+      }
+
+      // Test compact range works
+      dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+      // All data should be in the last level.
+      ColumnFamilyMetaData cf_meta;
+      db_->GetColumnFamilyMetaData(&cf_meta);
+      ASSERT_EQ(5U, cf_meta.levels.size());
+      for (int i = 0; i < 4; i++) {
+        ASSERT_EQ(0U, cf_meta.levels[i].files.size());
+      }
+      ASSERT_GT(cf_meta.levels[4U].files.size(), 0U);
+      verify_func();
+
+      Close();
+    }
+  }
+
+  env_->SetBackgroundThreads(1, Env::LOW);
+  env_->SetBackgroundThreads(1, Env::HIGH);
+}
+
+// Test specific cases in dynamic max bytes
+TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
+  Random rnd(301);
+  int kMaxKey = 1000000;
+
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
+  options.write_buffer_size = 2048;
+  options.max_write_buffer_number = 2;
+  options.level0_file_num_compaction_trigger = 2;
+  options.level0_slowdown_writes_trigger = 9999;
+  options.level0_stop_writes_trigger = 9999;
+  options.target_file_size_base = 2048;
+  options.level_compaction_dynamic_level_bytes = true;
+  options.max_bytes_for_level_base = 10240;
+  options.max_bytes_for_level_multiplier = 4;
+  options.max_background_compactions = 2;
+  options.num_levels = 5;
+  options.expanded_compaction_factor = 0;  // Force not expanding in compactions
+  BlockBasedTableOptions table_options;
+  table_options.block_size = 1024;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+
+  DestroyAndReopen(options);
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "true"},
+  }));
+
+  uint64_t int_prop;
+  std::string str_prop;
+
+  // Initial base level is the last level
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(4U, int_prop);
+
+  // Put about 7K to L0
+  for (int i = 0; i < 70; i++) {
+    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                  RandomString(&rnd, 80)));
+  }
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "false"},
+  }));
+  Flush();
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(4U, int_prop);
+
+  // Insert extra about 3.5K to L0. After they are compacted to L4, base level
+  // should be changed to L3.
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "true"},
+  }));
+  for (int i = 0; i < 70; i++) {
+    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                  RandomString(&rnd, 80)));
+  }
+
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "false"},
+  }));
+  Flush();
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(3U, int_prop);
+  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level1", &str_prop));
+  ASSERT_EQ("0", str_prop);
+  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
+  ASSERT_EQ("0", str_prop);
+
+  // Trigger parallel compaction, and the first one would change the base
+  // level.
+  // Hold compaction jobs to make sure
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "CompactionJob::Run():Start",
+      [&](void* arg) { env_->SleepForMicroseconds(100000); });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "true"},
+  }));
+  // Write about 10K more
+  for (int i = 0; i < 100; i++) {
+    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                  RandomString(&rnd, 80)));
+  }
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "false"},
+  }));
+  Flush();
+  // Wait for 200 milliseconds before proceeding compactions to make sure two
+  // parallel ones are executed.
+  env_->SleepForMicroseconds(200000);
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(3U, int_prop);
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+
+  // Trigger a condition that the compaction changes base level and L0->Lbase
+  // happens at the same time.
+  // We try to make last levels' targets to be 10K, 40K, 160K, add triggers
+  // another compaction from 40K->160K.
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "true"},
+  }));
+  // Write about 150K more
+  for (int i = 0; i < 1350; i++) {
+    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                  RandomString(&rnd, 80)));
+  }
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "false"},
+  }));
+  Flush();
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(2U, int_prop);
+
+  // Keep Writing data until base level changed 2->1. There will be L0->L2
+  // compaction going on at the same time.
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  for (int attempt = 0; attempt <= 20; attempt++) {
+    // Write about 5K more data with two flushes. It should be flush to level 2
+    // but when it is applied, base level is already 1.
+    for (int i = 0; i < 50; i++) {
+      ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                    RandomString(&rnd, 80)));
+    }
+    Flush();
+
+    ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+    if (int_prop == 2U) {
+      env_->SleepForMicroseconds(50000);
+    } else {
+      break;
+    }
+  }
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  env_->SleepForMicroseconds(200000);
+
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(1U, int_prop);
+}
+
+// Test specific cases in dynamic max bytes
+TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesCompactRange) {
+  Random rnd(301);
+  int kMaxKey = 1000000;
+
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
+  options.write_buffer_size = 2048;
+  options.max_write_buffer_number = 2;
+  options.level0_file_num_compaction_trigger = 2;
+  options.level0_slowdown_writes_trigger = 9999;
+  options.level0_stop_writes_trigger = 9999;
+  options.target_file_size_base = 2;
+  options.level_compaction_dynamic_level_bytes = true;
+  options.max_bytes_for_level_base = 10240;
+  options.max_bytes_for_level_multiplier = 4;
+  options.max_background_compactions = 1;
+  const int kNumLevels = 5;
+  options.num_levels = kNumLevels;
+  options.expanded_compaction_factor = 0;  // Force not expanding in compactions
+  BlockBasedTableOptions table_options;
+  table_options.block_size = 1024;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+
+  DestroyAndReopen(options);
+
+  // Compact against empty DB
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+
+  uint64_t int_prop;
+  std::string str_prop;
+
+  // Initial base level is the last level
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(4U, int_prop);
+
+  // Put about 7K to L0
+  for (int i = 0; i < 140; i++) {
+    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                  RandomString(&rnd, 80)));
+  }
+  Flush();
+  dbfull()->TEST_WaitForCompact();
+  if (NumTableFilesAtLevel(0) == 0) {
+    // Make sure level 0 is not empty
+    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                  RandomString(&rnd, 80)));
+    Flush();
+  }
+
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(3U, int_prop);
+  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level1", &str_prop));
+  ASSERT_EQ("0", str_prop);
+  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
+  ASSERT_EQ("0", str_prop);
+
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  std::set<int> output_levels;
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "CompactionPicker::CompactRange:Return", [&](void* arg) {
+        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
+        output_levels.insert(compaction->output_level());
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  ASSERT_EQ(output_levels.size(), 2);
+  ASSERT_TRUE(output_levels.find(3) != output_levels.end());
+  ASSERT_TRUE(output_levels.find(4) != output_levels.end());
+  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level0", &str_prop));
+  ASSERT_EQ("0", str_prop);
+  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level3", &str_prop));
+  ASSERT_EQ("0", str_prop);
+  // Base level is still level 3.
+  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+  ASSERT_EQ(3U, int_prop);
+}
+
+TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
+  options.write_buffer_size = 2048;
+  options.max_write_buffer_number = 2;
+  options.level0_file_num_compaction_trigger = 2;
+  options.level0_slowdown_writes_trigger = 2;
+  options.level0_stop_writes_trigger = 2;
+  options.target_file_size_base = 2048;
+  options.level_compaction_dynamic_level_bytes = true;
+  options.max_bytes_for_level_base = 10240;
+  options.max_bytes_for_level_multiplier = 4;
+  options.soft_rate_limit = 1.1;
+  options.max_background_compactions = 2;
+  options.num_levels = 5;
+
+  DestroyAndReopen(options);
+
+  int non_trivial = 0;
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundCompaction:NonTrivial",
+      [&](void* arg) { non_trivial++; });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  Random rnd(301);
+  const int total_keys = 3000;
+  const int random_part_size = 100;
+  for (int i = 0; i < total_keys; i++) {
+    std::string value = RandomString(&rnd, random_part_size);
+    PutFixed32(&value, static_cast<uint32_t>(i));
+    ASSERT_OK(Put(Key(i), value));
+  }
+  Flush();
+  dbfull()->TEST_WaitForCompact();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+
+  ASSERT_EQ(non_trivial, 0);
+
+  for (int i = 0; i < total_keys; i++) {
+    std::string value = Get(Key(i));
+    ASSERT_EQ(DecodeFixed32(value.c_str() + random_part_size),
+              static_cast<uint32_t>(i));
+  }
+
+  env_->SetBackgroundThreads(1, Env::LOW);
+  env_->SetBackgroundThreads(1, Env::HIGH);
+}
+
+TEST_F(DBTestDynamicLevel, MigrateToDynamicLevelMaxBytesBase) {
+  Random rnd(301);
+  const int kMaxKey = 2000;
+
+  Options options;
+  options.create_if_missing = true;
+  options.db_write_buffer_size = 2048;
+  options.write_buffer_size = 2048;
+  options.max_write_buffer_number = 8;
+  options.level0_file_num_compaction_trigger = 4;
+  options.level0_slowdown_writes_trigger = 4;
+  options.level0_stop_writes_trigger = 8;
+  options.target_file_size_base = 2048;
+  options.level_compaction_dynamic_level_bytes = false;
+  options.max_bytes_for_level_base = 10240;
+  options.max_bytes_for_level_multiplier = 4;
+  options.soft_rate_limit = 1.1;
+  options.num_levels = 8;
+
+  DestroyAndReopen(options);
+
+  auto verify_func = [&](int num_keys, bool if_sleep) {
+    for (int i = 0; i < num_keys; i++) {
+      ASSERT_NE("NOT_FOUND", Get(Key(kMaxKey + i)));
+      if (i < num_keys / 10) {
+        ASSERT_EQ("NOT_FOUND", Get(Key(i)));
+      } else {
+        ASSERT_NE("NOT_FOUND", Get(Key(i)));
+      }
+      if (if_sleep && i % 1000 == 0) {
+        // Without it, valgrind may choose not to give another
+        // thread a chance to run before finishing the function,
+        // causing the test to be extremely slow.
+        env_->SleepForMicroseconds(1);
+      }
+    }
+  };
+
+  int total_keys = 1000;
+  for (int i = 0; i < total_keys; i++) {
+    ASSERT_OK(Put(Key(i), RandomString(&rnd, 102)));
+    ASSERT_OK(Put(Key(kMaxKey + i), RandomString(&rnd, 102)));
+    ASSERT_OK(Delete(Key(i / 10)));
+  }
+  verify_func(total_keys, false);
+  dbfull()->TEST_WaitForCompact();
+
+  options.level_compaction_dynamic_level_bytes = true;
+  options.disable_auto_compactions = true;
+  Reopen(options);
+  verify_func(total_keys, false);
+
+  std::atomic_bool compaction_finished;
+  compaction_finished = false;
+  // Issue manual compaction in one thread and still verify DB state
+  // in main thread.
+  std::thread t([&]() {
+    CompactRangeOptions compact_options;
+    compact_options.change_level = true;
+    compact_options.target_level = options.num_levels - 1;
+    dbfull()->CompactRange(compact_options, nullptr, nullptr);
+    compaction_finished.store(true);
+  });
+  do {
+    verify_func(total_keys, true);
+  } while (!compaction_finished.load());
+  t.join();
+
+  ASSERT_OK(dbfull()->SetOptions({
+      {"disable_auto_compactions", "false"},
+  }));
+
+  int total_keys2 = 2000;
+  for (int i = total_keys; i < total_keys2; i++) {
+    ASSERT_OK(Put(Key(i), RandomString(&rnd, 102)));
+    ASSERT_OK(Put(Key(kMaxKey + i), RandomString(&rnd, 102)));
+    ASSERT_OK(Delete(Key(i / 10)));
+  }
+
+  verify_func(total_keys2, false);
+  dbfull()->TEST_WaitForCompact();
+  verify_func(total_keys2, false);
+
+  // Base level is not level 1
+  ASSERT_EQ(NumTableFilesAtLevel(1), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(2), 0);
+}
+}  // namespace rocksdb
+
+#endif  // !(defined NDEBUG) || !defined(OS_WIN)
+
+int main(int argc, char** argv) {
+#if !(defined NDEBUG) || !defined(OS_WIN)
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+#else
+  return 0;
+#endif
+}

db/db_filesnapshot.cc

@@ -98,6 +98,8 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
       cfd->Ref();
       mutex_.Unlock();
       status = FlushMemTable(cfd, FlushOptions());
+      TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
+      TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
       mutex_.Lock();
       cfd->Unref();
       if (!status.ok()) {

db/db_impl.h

@@ -22,6 +22,8 @@
 #include "db/log_writer.h"
 #include "db/snapshot.h"
 #include "db/column_family.h"
+#include "db/compaction_job.h"
+#include "db/flush_job.h"
 #include "db/version_edit.h"
 #include "db/wal_manager.h"
 #include "db/writebuffer.h"
@@ -53,6 +55,7 @@ class VersionEdit;
 class VersionSet;
 class CompactionFilterV2;
 class Arena;
+class WriteCallback;
 struct JobContext;
 
 class DBImpl : public DB {
@@ -76,6 +79,7 @@ class DBImpl : public DB {
   using DB::Write;
   virtual Status Write(const WriteOptions& options,
                        WriteBatch* updates) override;
+
   using DB::Get;
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
@@ -118,13 +122,12 @@ class DBImpl : public DB {
                               const Slice& property, uint64_t* value) override;
   using DB::GetApproximateSizes;
   virtual void GetApproximateSizes(ColumnFamilyHandle* column_family,
-                                   const Range* range, int n,
-                                   uint64_t* sizes) override;
+                                   const Range* range, int n, uint64_t* sizes,
+                                   bool include_memtable = false) override;
   using DB::CompactRange;
-  virtual Status CompactRange(ColumnFamilyHandle* column_family,
-                              const Slice* begin, const Slice* end,
-                              bool reduce_level = false, int target_level = -1,
-                              uint32_t target_path_id = 0) override;
+  virtual Status CompactRange(const CompactRangeOptions& options,
+                              ColumnFamilyHandle* column_family,
+                              const Slice* begin, const Slice* end) override;
 
   using DB::CompactFiles;
   virtual Status CompactFiles(const CompactionOptions& compact_options,
@@ -155,6 +158,7 @@ class DBImpl : public DB {
   using DB::Flush;
   virtual Status Flush(const FlushOptions& options,
                        ColumnFamilyHandle* column_family) override;
+  virtual Status SyncWAL() override;
 
   virtual SequenceNumber GetLatestSequenceNumber() const override;
 
@@ -191,17 +195,46 @@ class DBImpl : public DB {
 
   Status PromoteL0(ColumnFamilyHandle* column_family, int target_level);
 
+  // Similar to Write() but will call the callback once on the single write
+  // thread to determine whether it is safe to perform the write.
+  virtual Status WriteWithCallback(const WriteOptions& write_options,
+                                   WriteBatch* my_batch,
+                                   WriteCallback* callback);
+
+  // Returns the sequence number that is guaranteed to be smaller than or equal
+  // to the sequence number of any key that could be inserted into the current
+  // memtables. It can then be assumed that any write with a larger(or equal)
+  // sequence number will be present in this memtable or a later memtable.
+  //
+  // If the earliest sequence number could not be determined,
+  // kMaxSequenceNumber will be returned.
+  //
+  // If include_history=true, will also search Memtables in MemTableList
+  // History.
+  SequenceNumber GetEarliestMemTableSequenceNumber(SuperVersion* sv,
+                                                   bool include_history);
+
+  // For a given key, check to see if there are any records for this key
+  // in the memtables, including memtable history.
+
+  // On success, *seq will contain the sequence number for the
+  // latest such change or kMaxSequenceNumber if no records were present.
+  // Returns OK on success, other status on error reading memtables.
+  Status GetLatestSequenceForKeyFromMemtable(SuperVersion* sv, const Slice& key,
+                                             SequenceNumber* seq);
+
 #endif  // ROCKSDB_LITE
 
   // checks if all live files exist on file system and that their file sizes
   // match to our in-memory records
   virtual Status CheckConsistency();
 
-  virtual Status GetDbIdentity(std::string& identity) override;
+  virtual Status GetDbIdentity(std::string& identity) const override;
 
   Status RunManualCompaction(ColumnFamilyData* cfd, int input_level,
                              int output_level, uint32_t output_path_id,
-                             const Slice* begin, const Slice* end);
+                             const Slice* begin, const Slice* end,
+                             bool disallow_trivial_move = false);
 
 #ifndef ROCKSDB_LITE
   // Extra methods (for testing) that are not in the public DB interface
@@ -209,7 +242,8 @@ class DBImpl : public DB {
 
   // Compact any files in the named level that overlap [*begin, *end]
   Status TEST_CompactRange(int level, const Slice* begin, const Slice* end,
-                           ColumnFamilyHandle* column_family = nullptr);
+                           ColumnFamilyHandle* column_family = nullptr,
+                           bool disallow_trivial_move = false);
 
   // Force current memtable contents to be flushed.
   Status TEST_FlushMemTable(bool wait = true);
@@ -257,6 +291,8 @@ class DBImpl : public DB {
 
   size_t TEST_LogsToFreeSize();
 
+  uint64_t TEST_LogfileNumber();
+
 #endif  // ROCKSDB_LITE
 
   // Returns the list of live files in 'live' and the list
@@ -279,6 +315,32 @@ class DBImpl : public DB {
 
   void CancelAllBackgroundWork(bool wait);
 
+  // Find Super version and reference it. Based on options, it might return
+  // the thread local cached one.
+  // Call ReturnAndCleanupSuperVersion() when it is no longer needed.
+  SuperVersion* GetAndRefSuperVersion(ColumnFamilyData* cfd);
+
+  // Similar to the previous function but looks up based on a column family id.
+  // nullptr will be returned if this column family no longer exists.
+  // REQUIRED: this function should only be called on the write thread or if the
+  // mutex is held.
+  SuperVersion* GetAndRefSuperVersion(uint32_t column_family_id);
+
+  // Un-reference the super version and return it to thread local cache if
+  // needed. If it is the last reference of the super version. Clean it up
+  // after un-referencing it.
+  void ReturnAndCleanupSuperVersion(ColumnFamilyData* cfd, SuperVersion* sv);
+
+  // Similar to the previous function but looks up based on a column family id.
+  // nullptr will be returned if this column family no longer exists.
+  // REQUIRED: this function should only be called on the write thread.
+  void ReturnAndCleanupSuperVersion(uint32_t colun_family_id, SuperVersion* sv);
+
+  // REQUIRED: this function should only be called on the write thread or if the
+  // mutex is held.  Return value only valid until next call to this function or
+  // mutex is released.
+  ColumnFamilyHandle* GetColumnFamilyHandle(uint32_t column_family_id);
+
  protected:
   Env* const env_;
   const std::string dbname_;
@@ -289,11 +351,14 @@ class DBImpl : public DB {
   Iterator* NewInternalIterator(const ReadOptions&, ColumnFamilyData* cfd,
                                 SuperVersion* super_version, Arena* arena);
 
-  void NotifyOnFlushCompleted(ColumnFamilyData* cfd, uint64_t file_number,
-                              const MutableCFOptions& mutable_cf_options);
+  void NotifyOnFlushCompleted(ColumnFamilyData* cfd, FileMetaData* file_meta,
+                              const MutableCFOptions& mutable_cf_options,
+                              int job_id);
 
   void NotifyOnCompactionCompleted(ColumnFamilyData* cfd,
-                                   Compaction *c, const Status &st);
+                                   Compaction *c, const Status &st,
+                                   const CompactionJobStats& job_stats,
+                                   int job_id);
 
   void NewThreadStatusCfInfo(ColumnFamilyData* cfd) const;
 
@@ -301,6 +366,9 @@ class DBImpl : public DB {
 
   void EraseThreadStatusDbInfo() const;
 
+  Status WriteImpl(const WriteOptions& options, WriteBatch* updates,
+                   WriteCallback* callback);
+
  private:
   friend class DB;
   friend class InternalStats;
@@ -309,6 +377,9 @@ class DBImpl : public DB {
 #endif
   friend struct SuperVersion;
   friend class CompactedDBImpl;
+#ifndef NDEBUG
+  friend class XFTransactionWriteHandler;
+#endif
   struct CompactionState;
 
   struct WriteContext;
@@ -364,12 +435,14 @@ class DBImpl : public DB {
   // concurrent flush memtables to storage.
   Status WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                                      MemTable* mem, VersionEdit* edit);
-  Status DelayWrite(uint64_t expiration_time);
+
+  // num_bytes: for slowdown case, delay time is calculated based on
+  //            `num_bytes` going through.
+  Status DelayWrite(uint64_t num_bytes);
 
   Status ScheduleFlushes(WriteContext* context);
 
-  Status SetNewMemtableAndNewLogFile(ColumnFamilyData* cfd,
-                                     WriteContext* context);
+  Status SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context);
 
   // Force current memtable contents to be flushed.
   Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options);
@@ -402,13 +475,6 @@ class DBImpl : public DB {
   Status BackgroundFlush(bool* madeProgress, JobContext* job_context,
                          LogBuffer* log_buffer);
 
-  // This function is called as part of compaction. It enables Flush process to
-  // preempt compaction, since it's higher prioirty
-  uint64_t CallFlushDuringCompaction(ColumnFamilyData* cfd,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     JobContext* job_context,
-                                     LogBuffer* log_buffer);
-
   void PrintStatistics();
 
   // dump rocksdb.stats to LOG
@@ -430,6 +496,9 @@ class DBImpl : public DB {
   void AddToFlushQueue(ColumnFamilyData* cfd);
   ColumnFamilyData* PopFirstFromFlushQueue();
 
+  // helper function to call after some of the logs_ were synced
+  void MarkLogsSynced(uint64_t up_to, bool synced_dir, const Status& status);
+
   // table_cache_ provides its own synchronization
   std::shared_ptr<Cache> table_cache_;
 
@@ -449,7 +518,6 @@ class DBImpl : public DB {
   // * whenever there is an error in background flush or compaction
   InstrumentedCondVar bg_cv_;
   uint64_t logfile_number_;
-  unique_ptr<log::Writer> log_;
   bool log_dir_synced_;
   bool log_empty_;
   ColumnFamilyHandleImpl* default_cf_handle_;
@@ -457,13 +525,45 @@ class DBImpl : public DB {
   unique_ptr<ColumnFamilyMemTablesImpl> column_family_memtables_;
   struct LogFileNumberSize {
     explicit LogFileNumberSize(uint64_t _number)
-        : number(_number), size(0), getting_flushed(false) {}
+        : number(_number) {}
     void AddSize(uint64_t new_size) { size += new_size; }
     uint64_t number;
-    uint64_t size;
-    bool getting_flushed;
+    uint64_t size = 0;
+    bool getting_flushed = false;
+  };
+  struct LogWriterNumber {
+    // pass ownership of _writer
+    LogWriterNumber(uint64_t _number, log::Writer* _writer)
+        : number(_number), writer(_writer) {}
+
+    log::Writer* ReleaseWriter() {
+      auto* w = writer;
+      writer = nullptr;
+      return w;
+    }
+    void ClearWriter() {
+      delete writer;
+      writer = nullptr;
+    }
+
+    uint64_t number;
+    // Visual Studio doesn't support deque's member to be noncopyable because
+    // of a unique_ptr as a member.
+    log::Writer* writer;  // own
+    // true for some prefix of logs_
+    bool getting_synced = false;
   };
   std::deque<LogFileNumberSize> alive_log_files_;
+  // Log files that aren't fully synced, and the current log file.
+  // Synchronization:
+  //  - push_back() is done from write thread with locked mutex_,
+  //  - pop_front() is done from any thread with locked mutex_,
+  //  - back() and items with getting_synced=true are not popped,
+  //  - it follows that write thread with unlocked mutex_ can safely access
+  //    back() and items with getting_synced=true.
+  std::deque<LogWriterNumber> logs_;
+  // Signaled when getting_synced becomes false for some of the logs_.
+  InstrumentedCondVar log_sync_cv_;
   uint64_t total_log_size_;
   // only used for dynamically adjusting max_total_wal_size. it is a sum of
   // [write_buffer_size * max_write_buffer_number] over all column families
@@ -513,6 +613,11 @@ class DBImpl : public DB {
   WriteBatch tmp_batch_;
 
   WriteController write_controller_;
+
+  // Size of the last batch group. In slowdown mode, next write needs to
+  // sleep if it uses up the quota.
+  uint64_t last_batch_group_size_;
+
   FlushScheduler flush_scheduler_;
 
   SnapshotList snapshots_;
@@ -574,10 +679,11 @@ class DBImpl : public DB {
     uint32_t output_path_id;
     bool done;
     Status status;
-    bool in_progress;           // compaction request being processed?
-    const InternalKey* begin;   // nullptr means beginning of key range
-    const InternalKey* end;     // nullptr means end of key range
-    InternalKey tmp_storage;    // Used to keep track of compaction progress
+    bool in_progress;             // compaction request being processed?
+    const InternalKey* begin;     // nullptr means beginning of key range
+    const InternalKey* end;       // nullptr means end of key range
+    InternalKey tmp_storage;      // Used to keep track of compaction progress
+    bool disallow_trivial_move;   // Force actual compaction to run
   };
   ManualCompaction* manual_compaction_;
 
@@ -605,6 +711,9 @@ class DBImpl : public DB {
   bool flush_on_destroy_; // Used when disableWAL is true.
 
   static const int KEEP_LOG_FILE_NUM = 1000;
+  // MSVC version 1800 still does not have constexpr for ::max()
+  static const uint64_t kNoTimeOut = port::kMaxUint64;
+
   std::string db_absolute_path_;
 
   // The options to access storage files
@@ -626,12 +735,6 @@ class DBImpl : public DB {
   // Indicate DB was opened successfully
   bool opened_successfully_;
 
-  // The list of registered event listeners.
-  std::list<EventListener*> listeners_;
-
-  // count how many events are currently being notified.
-  int notifying_events_;
-
   // No copying allowed
   DBImpl(const DBImpl&);
   void operator=(const DBImpl&);
@@ -647,31 +750,16 @@ class DBImpl : public DB {
   // the InstallSuperVersion() function. Background threads carry
   // job_context which can have new_superversion already
   // allocated.
-  void InstallSuperVersionBackground(
+  void InstallSuperVersionAndScheduleWorkWrapper(
       ColumnFamilyData* cfd, JobContext* job_context,
       const MutableCFOptions& mutable_cf_options);
 
   // All ColumnFamily state changes go through this function. Here we analyze
   // the new state and we schedule background work if we detect that the new
   // state needs flush or compaction.
-  // If dont_schedule_bg_work == true, then caller asks us to not schedule flush
-  // or compaction here, but it also promises to schedule needed background
-  // work. We use this to  scheduling background compactions when we are in the
-  // write thread, which is very performance critical. Caller schedules
-  // background work as soon as it exits the write thread
-  SuperVersion* InstallSuperVersion(ColumnFamilyData* cfd, SuperVersion* new_sv,
-                                    const MutableCFOptions& mutable_cf_options,
-                                    bool dont_schedule_bg_work = false);
-
-  // Find Super version and reference it. Based on options, it might return
-  // the thread local cached one.
-  inline SuperVersion* GetAndRefSuperVersion(ColumnFamilyData* cfd);
-
-  // Un-reference the super version and return it to thread local cache if
-  // needed. If it is the last reference of the super version. Clean it up
-  // after un-referencing it.
-  inline void ReturnAndCleanupSuperVersion(ColumnFamilyData* cfd,
-                                           SuperVersion* sv);
+  SuperVersion* InstallSuperVersionAndScheduleWork(
+      ColumnFamilyData* cfd, SuperVersion* new_sv,
+      const MutableCFOptions& mutable_cf_options);
 
 #ifndef ROCKSDB_LITE
   using DB::GetPropertiesOfAllTables;

db/db_impl_debug.cc

@@ -73,7 +73,8 @@ uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
 
 Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
                                  const Slice* end,
-                                 ColumnFamilyHandle* column_family) {
+                                 ColumnFamilyHandle* column_family,
+                                 bool disallow_trivial_move) {
   ColumnFamilyData* cfd;
   if (column_family == nullptr) {
     cfd = default_cf_handle_->cfd();
@@ -86,7 +87,8 @@ Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
        cfd->ioptions()->compaction_style == kCompactionStyleFIFO)
           ? level
           : level + 1;
-  return RunManualCompaction(cfd, level, output_level, 0, begin, end);
+  return RunManualCompaction(cfd, level, output_level, 0, begin, end,
+                             disallow_trivial_move);
 }
 
 Status DBImpl::TEST_FlushMemTable(bool wait) {
@@ -130,8 +132,8 @@ void DBImpl::TEST_UnlockMutex() {
 
 void* DBImpl::TEST_BeginWrite() {
   auto w = new WriteThread::Writer(&mutex_);
-  Status s = write_thread_.EnterWriteThread(w, 0);
-  assert(s.ok() && !w->done);  // No timeout and nobody should do our job
+  write_thread_.EnterWriteThread(w);
+  assert(!w->done);  // Nobody should do our job
   return reinterpret_cast<void*>(w);
 }
 
@@ -146,5 +148,10 @@ size_t DBImpl::TEST_LogsToFreeSize() {
   return logs_to_free_.size();
 }
 
+uint64_t DBImpl::TEST_LogfileNumber() {
+  InstrumentedMutexLock l(&mutex_);
+  return logfile_number_;
+}
+
 }  // namespace rocksdb
 #endif  // ROCKSDB_LITE

db/db_impl_experimental.cc

@@ -130,14 +130,15 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
       edit.DeleteFile(0, f->fd.GetNumber());
       edit.AddFile(target_level, f->fd.GetNumber(), f->fd.GetPathId(),
                    f->fd.GetFileSize(), f->smallest, f->largest,
-                   f->smallest_seqno, f->largest_seqno);
+                   f->smallest_seqno, f->largest_seqno,
+                   f->marked_for_compaction);
     }
 
     status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
                                     &edit, &mutex_, directories_.GetDbDir());
     if (status.ok()) {
-      InstallSuperVersionBackground(cfd, &job_context,
-                                    *cfd->GetLatestMutableCFOptions());
+      InstallSuperVersionAndScheduleWorkWrapper(
+          cfd, &job_context, *cfd->GetLatestMutableCFOptions());
     }
   }  // lock released here
   LogFlush(db_options_.info_log);

db/db_impl_readonly.cc

@@ -5,7 +5,8 @@
 
 
 #include "db/db_impl_readonly.h"
-#include "utilities/compacted_db/compacted_db_impl.h"
+
+#include "db/compacted_db_impl.h"
 #include "db/db_impl.h"
 #include "db/merge_context.h"
 #include "db/db_iter.h"

db/db_impl_readonly.h

@@ -58,10 +58,9 @@ class DBImplReadOnly : public DBImpl {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
   using DBImpl::CompactRange;
-  virtual Status CompactRange(ColumnFamilyHandle* column_family,
-                              const Slice* begin, const Slice* end,
-                              bool reduce_level = false, int target_level = -1,
-                              uint32_t target_path_id = 0) override {
+  virtual Status CompactRange(const CompactRangeOptions& options,
+                              ColumnFamilyHandle* column_family,
+                              const Slice* begin, const Slice* end) override {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
 

db/db_inplace_update_test.cc

@@ -0,0 +1,171 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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 "port/stack_trace.h"
+#include "util/db_test_util.h"
+
+namespace rocksdb {
+
+class DBTestInPlaceUpdate : public DBTestBase {
+ public:
+  DBTestInPlaceUpdate() : DBTestBase("/db_inplace_update_test") {}
+};
+
+TEST_F(DBTestInPlaceUpdate, InPlaceUpdate) {
+  do {
+    Options options;
+    options.create_if_missing = true;
+    options.inplace_update_support = true;
+    options.env = env_;
+    options.write_buffer_size = 100000;
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Update key with values of smaller size
+    int numValues = 10;
+    for (int i = numValues; i > 0; i--) {
+      std::string value = DummyString(i, 'a');
+      ASSERT_OK(Put(1, "key", value));
+      ASSERT_EQ(value, Get(1, "key"));
+    }
+
+    // Only 1 instance for that key.
+    validateNumberOfEntries(1, 1);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestInPlaceUpdate, InPlaceUpdateLargeNewValue) {
+  do {
+    Options options;
+    options.create_if_missing = true;
+    options.inplace_update_support = true;
+    options.env = env_;
+    options.write_buffer_size = 100000;
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Update key with values of larger size
+    int numValues = 10;
+    for (int i = 0; i < numValues; i++) {
+      std::string value = DummyString(i, 'a');
+      ASSERT_OK(Put(1, "key", value));
+      ASSERT_EQ(value, Get(1, "key"));
+    }
+
+    // All 10 updates exist in the internal iterator
+    validateNumberOfEntries(numValues, 1);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerSize) {
+  do {
+    Options options;
+    options.create_if_missing = true;
+    options.inplace_update_support = true;
+
+    options.env = env_;
+    options.write_buffer_size = 100000;
+    options.inplace_callback =
+      rocksdb::DBTestInPlaceUpdate::updateInPlaceSmallerSize;
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Update key with values of smaller size
+    int numValues = 10;
+    ASSERT_OK(Put(1, "key", DummyString(numValues, 'a')));
+    ASSERT_EQ(DummyString(numValues, 'c'), Get(1, "key"));
+
+    for (int i = numValues; i > 0; i--) {
+      ASSERT_OK(Put(1, "key", DummyString(i, 'a')));
+      ASSERT_EQ(DummyString(i - 1, 'b'), Get(1, "key"));
+    }
+
+    // Only 1 instance for that key.
+    validateNumberOfEntries(1, 1);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerVarintSize) {
+  do {
+    Options options;
+    options.create_if_missing = true;
+    options.inplace_update_support = true;
+
+    options.env = env_;
+    options.write_buffer_size = 100000;
+    options.inplace_callback =
+      rocksdb::DBTestInPlaceUpdate::updateInPlaceSmallerVarintSize;
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Update key with values of smaller varint size
+    int numValues = 265;
+    ASSERT_OK(Put(1, "key", DummyString(numValues, 'a')));
+    ASSERT_EQ(DummyString(numValues, 'c'), Get(1, "key"));
+
+    for (int i = numValues; i > 0; i--) {
+      ASSERT_OK(Put(1, "key", DummyString(i, 'a')));
+      ASSERT_EQ(DummyString(1, 'b'), Get(1, "key"));
+    }
+
+    // Only 1 instance for that key.
+    validateNumberOfEntries(1, 1);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackLargeNewValue) {
+  do {
+    Options options;
+    options.create_if_missing = true;
+    options.inplace_update_support = true;
+
+    options.env = env_;
+    options.write_buffer_size = 100000;
+    options.inplace_callback =
+      rocksdb::DBTestInPlaceUpdate::updateInPlaceLargerSize;
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Update key with values of larger size
+    int numValues = 10;
+    for (int i = 0; i < numValues; i++) {
+      ASSERT_OK(Put(1, "key", DummyString(i, 'a')));
+      ASSERT_EQ(DummyString(i, 'c'), Get(1, "key"));
+    }
+
+    // No inplace updates. All updates are puts with new seq number
+    // All 10 updates exist in the internal iterator
+    validateNumberOfEntries(numValues, 1);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackNoAction) {
+  do {
+    Options options;
+    options.create_if_missing = true;
+    options.inplace_update_support = true;
+
+    options.env = env_;
+    options.write_buffer_size = 100000;
+    options.inplace_callback =
+      rocksdb::DBTestInPlaceUpdate::updateInPlaceNoAction;
+    options = CurrentOptions(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+
+    // Callback function requests no actions from db
+    ASSERT_OK(Put(1, "key", DummyString(1, 'a')));
+    ASSERT_EQ(Get(1, "key"), "NOT_FOUND");
+  } while (ChangeCompactOptions());
+}
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/db_iter.cc

@@ -115,6 +115,7 @@ class DBIter: public Iterator {
   virtual void SeekToLast() override;
 
  private:
+  void ReverseToBackward();
   void PrevInternal();
   void FindParseableKey(ParsedInternalKey* ikey, Direction direction);
   bool FindValueForCurrentKey();
@@ -255,12 +256,13 @@ void DBIter::FindNextUserEntryInternal(bool skipping) {
     // If we have sequentially iterated via numerous keys and still not
     // found the next user-key, then it is better to seek so that we can
     // avoid too many key comparisons. We seek to the last occurrence of
-    // our current key by looking for sequence number 0.
+    // our current key by looking for sequence number 0 and type deletion
+    // (the smallest type).
     if (skipping && num_skipped > max_skip_) {
       num_skipped = 0;
       std::string last_key;
       AppendInternalKey(&last_key, ParsedInternalKey(saved_key_.GetKey(), 0,
-                                                     kValueTypeForSeek));
+                                                     kTypeDeletion));
       iter_->Seek(last_key);
       RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
     } else {
@@ -350,12 +352,38 @@ void DBIter::MergeValuesNewToOld() {
 void DBIter::Prev() {
   assert(valid_);
   if (direction_ == kForward) {
-    FindPrevUserKey();
-    direction_ = kReverse;
+    ReverseToBackward();
   }
   PrevInternal();
 }
 
+void DBIter::ReverseToBackward() {
+  if (current_entry_is_merged_) {
+    // Not placed in the same key. Need to call Prev() until finding the
+    // previous key.
+    if (!iter_->Valid()) {
+      iter_->SeekToLast();
+    }
+    ParsedInternalKey ikey;
+    FindParseableKey(&ikey, kReverse);
+    while (iter_->Valid() &&
+           user_comparator_->Compare(ikey.user_key, saved_key_.GetKey()) > 0) {
+      iter_->Prev();
+      FindParseableKey(&ikey, kReverse);
+    }
+  }
+#ifndef NDEBUG
+  if (iter_->Valid()) {
+    ParsedInternalKey ikey;
+    assert(ParseKey(&ikey));
+    assert(user_comparator_->Compare(ikey.user_key, saved_key_.GetKey()) <= 0);
+  }
+#endif
+
+  FindPrevUserKey();
+  direction_ = kReverse;
+}
+
 void DBIter::PrevInternal() {
   if (!iter_->Valid()) {
     valid_ = false;
@@ -664,7 +692,28 @@ void DBIter::SeekToLast() {
     PERF_TIMER_GUARD(seek_internal_seek_time);
     iter_->SeekToLast();
   }
+  // When the iterate_upper_bound is set to a value,
+  // it will seek to the last key before the
+  // ReadOptions.iterate_upper_bound
+  if (iter_->Valid() && iterate_upper_bound_ != nullptr) {
+    saved_key_.SetKey(*iterate_upper_bound_);
+    std::string last_key;
+    AppendInternalKey(&last_key,
+                      ParsedInternalKey(saved_key_.GetKey(), kMaxSequenceNumber,
+                                        kValueTypeForSeek));
 
+    iter_->Seek(last_key);
+
+    if (!iter_->Valid()) {
+      iter_->SeekToLast();
+    } else {
+      iter_->Prev();
+      if (!iter_->Valid()) {
+        valid_ = false;
+        return;
+      }
+    }
+  }
   PrevInternal();
 }
 

db/db_iter_test.cc

@@ -11,6 +11,7 @@
 #include "db/dbformat.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/options.h"
+#include "rocksdb/perf_context.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/statistics.h"
 #include "db/db_iter.h"
@@ -184,6 +185,272 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     db_iter->Next();
     ASSERT_TRUE(!db_iter->Valid());
   }
+  // Test to check the SeekToLast() with iterate_upper_bound not set
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->Finish();
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "c");
+  }
+
+  // Test to check the SeekToLast() with iterate_upper_bound set
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("d", "val_d");
+    internal_iter->AddPut("e", "val_e");
+    internal_iter->AddPut("f", "val_f");
+    internal_iter->Finish();
+
+    Slice prefix("d");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "c");
+
+    db_iter->Next();
+    ASSERT_TRUE(!db_iter->Valid());
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "c");
+  }
+  // Test to check the SeekToLast() iterate_upper_bound set to a key that
+  // is not Put yet
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("d", "val_d");
+    internal_iter->Finish();
+
+    Slice prefix("z");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "d");
+
+    db_iter->Next();
+    ASSERT_TRUE(!db_iter->Valid());
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "d");
+
+    db_iter->Prev();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "c");
+  }
+  // Test to check the SeekToLast() with iterate_upper_bound set to the
+  // first key
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->Finish();
+
+    Slice prefix("a");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(!db_iter->Valid());
+  }
+  // Test case to check SeekToLast with iterate_upper_bound set
+  // (same key put may times - SeekToLast should start with the
+  // maximum sequence id of the upper bound)
+
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->Finish();
+
+    Slice prefix("c");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        7, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    SetPerfLevel(kEnableCount);
+    ASSERT_TRUE(GetPerfLevel() == kEnableCount);
+
+    perf_context.Reset();
+    db_iter->SeekToLast();
+
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(static_cast<int>(perf_context.internal_key_skipped_count), 1);
+    ASSERT_EQ(db_iter->key().ToString(), "b");
+
+    SetPerfLevel(kDisable);
+  }
+  // Test to check the SeekToLast() with the iterate_upper_bound set
+  // (Checking the value of the key which has sequence ids greater than
+  // and less that the iterator's sequence id)
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+
+    internal_iter->AddPut("a", "val_a1");
+    internal_iter->AddPut("a", "val_a2");
+    internal_iter->AddPut("b", "val_b1");
+    internal_iter->AddPut("c", "val_c1");
+    internal_iter->AddPut("c", "val_c2");
+    internal_iter->AddPut("c", "val_c3");
+    internal_iter->AddPut("b", "val_b2");
+    internal_iter->AddPut("d", "val_d1");
+    internal_iter->Finish();
+
+    Slice prefix("c");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        4, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "b");
+    ASSERT_EQ(db_iter->value().ToString(), "val_b1");
+  }
+
+  // Test to check the SeekToLast() with the iterate_upper_bound set to the
+  // key that is deleted
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddDeletion("a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->Finish();
+
+    Slice prefix("a");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(!db_iter->Valid());
+  }
+  // Test to check the SeekToLast() with the iterate_upper_bound set
+  // (Deletion cases)
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddDeletion("b");
+    internal_iter->AddPut("c", "val_c");
+    internal_iter->Finish();
+
+    Slice prefix("c");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "a");
+
+    db_iter->Next();
+    ASSERT_TRUE(!db_iter->Valid());
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "a");
+  }
+  // Test to check the SeekToLast() with iterate_upper_bound set
+  // (Deletion cases - Lot of internal keys after the upper_bound
+  // is deleted)
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddPut("a", "val_a");
+    internal_iter->AddPut("b", "val_b");
+    internal_iter->AddDeletion("c");
+    internal_iter->AddDeletion("d");
+    internal_iter->AddDeletion("e");
+    internal_iter->AddDeletion("f");
+    internal_iter->AddDeletion("g");
+    internal_iter->AddDeletion("h");
+    internal_iter->Finish();
+
+    Slice prefix("c");
+
+    ReadOptions ro;
+    ro.iterate_upper_bound = &prefix;
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        7, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+
+    SetPerfLevel(kEnableCount);
+    ASSERT_TRUE(GetPerfLevel() == kEnableCount);
+
+    perf_context.Reset();
+    db_iter->SeekToLast();
+
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(static_cast<int>(perf_context.internal_delete_skipped_count), 0);
+    ASSERT_EQ(db_iter->key().ToString(), "b");
+
+    SetPerfLevel(kDisable);
+  }
 
   {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
@@ -1377,6 +1644,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_TRUE(!db_iter->Valid());
   }
 }
+
 TEST_F(DBIteratorTest, DBIterator8) {
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
@@ -1401,6 +1669,109 @@ TEST_F(DBIteratorTest, DBIterator8) {
   ASSERT_EQ(db_iter->value().ToString(), "0");
 }
 
+// TODO(3.13): fix the issue of Seek() then Prev() which might not necessary
+//             return the biggest element smaller than the seek key.
+TEST_F(DBIteratorTest, DBIterator9) {
+  Options options;
+  options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
+  {
+    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+    internal_iter->AddMerge("a", "merge_1");
+    internal_iter->AddMerge("a", "merge_2");
+    internal_iter->AddMerge("b", "merge_3");
+    internal_iter->AddMerge("b", "merge_4");
+    internal_iter->AddMerge("d", "merge_5");
+    internal_iter->AddMerge("d", "merge_6");
+    internal_iter->Finish();
+
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations));
+
+    db_iter->SeekToLast();
+    ASSERT_TRUE(db_iter->Valid());
+    db_iter->Prev();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "b");
+    ASSERT_EQ(db_iter->value().ToString(), "merge_3,merge_4");
+    db_iter->Next();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "d");
+    ASSERT_EQ(db_iter->value().ToString(), "merge_5,merge_6");
+
+    db_iter->Seek("b");
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "b");
+    ASSERT_EQ(db_iter->value().ToString(), "merge_3,merge_4");
+    db_iter->Prev();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "a");
+    ASSERT_EQ(db_iter->value().ToString(), "merge_1,merge_2");
+
+    db_iter->Seek("c");
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "d");
+    ASSERT_EQ(db_iter->value().ToString(), "merge_5,merge_6");
+    db_iter->Prev();
+    ASSERT_TRUE(db_iter->Valid());
+    ASSERT_EQ(db_iter->key().ToString(), "b");
+    ASSERT_EQ(db_iter->value().ToString(), "merge_3,merge_4");
+  }
+}
+
+// TODO(3.13): fix the issue of Seek() then Prev() which might not necessary
+//             return the biggest element smaller than the seek key.
+TEST_F(DBIteratorTest, DBIterator10) {
+  Options options;
+
+  TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+  internal_iter->AddPut("a", "1");
+  internal_iter->AddPut("b", "2");
+  internal_iter->AddPut("c", "3");
+  internal_iter->AddPut("d", "4");
+  internal_iter->Finish();
+
+  std::unique_ptr<Iterator> db_iter(NewDBIterator(
+      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+      10, options.max_sequential_skip_in_iterations));
+
+  db_iter->Seek("c");
+  ASSERT_TRUE(db_iter->Valid());
+  db_iter->Prev();
+  ASSERT_TRUE(db_iter->Valid());
+  ASSERT_EQ(db_iter->key().ToString(), "b");
+  ASSERT_EQ(db_iter->value().ToString(), "2");
+
+  db_iter->Next();
+  ASSERT_TRUE(db_iter->Valid());
+  ASSERT_EQ(db_iter->key().ToString(), "c");
+  ASSERT_EQ(db_iter->value().ToString(), "3");
+}
+
+TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
+  Options options;
+  options.merge_operator = nullptr;
+
+  TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+  internal_iter->AddPut("a", "1");
+  internal_iter->AddPut("b", "2");
+  internal_iter->Finish();
+
+  std::unique_ptr<Iterator> db_iter(NewDBIterator(
+      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+      10, 0 /* force seek */));
+  db_iter->SeekToFirst();
+  ASSERT_TRUE(db_iter->Valid());
+  ASSERT_EQ(db_iter->key().ToString(), "a");
+  ASSERT_EQ(db_iter->value().ToString(), "1");
+  db_iter->Next();
+  ASSERT_TRUE(db_iter->Valid());
+  ASSERT_EQ(db_iter->key().ToString(), "b");
+  ASSERT_EQ(db_iter->value().ToString(), "2");
+  db_iter->Next();
+  ASSERT_FALSE(db_iter->Valid());
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/db_log_iter_test.cc

@@ -0,0 +1,290 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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.
+
+// Introduction of SyncPoint effectively disabled building and running this test
+// in Release build.
+// which is a pity, it is a good test
+#if !(defined NDEBUG) || !defined(OS_WIN)
+
+#include "port/stack_trace.h"
+#include "util/db_test_util.h"
+
+namespace rocksdb {
+
+class DBTestXactLogIterator : public DBTestBase {
+ public:
+  DBTestXactLogIterator() : DBTestBase("/db_log_iter_test") {}
+
+  std::unique_ptr<TransactionLogIterator> OpenTransactionLogIter(
+      const SequenceNumber seq) {
+    unique_ptr<TransactionLogIterator> iter;
+    Status status = dbfull()->GetUpdatesSince(seq, &iter);
+    EXPECT_OK(status);
+    EXPECT_TRUE(iter->Valid());
+    return std::move(iter);
+  }
+};
+
+namespace {
+SequenceNumber ReadRecords(
+    std::unique_ptr<TransactionLogIterator>& iter,
+    int& count) {
+  count = 0;
+  SequenceNumber lastSequence = 0;
+  BatchResult res;
+  while (iter->Valid()) {
+    res = iter->GetBatch();
+    EXPECT_TRUE(res.sequence > lastSequence);
+    ++count;
+    lastSequence = res.sequence;
+    EXPECT_OK(iter->status());
+    iter->Next();
+  }
+  return res.sequence;
+}
+
+void ExpectRecords(
+    const int expected_no_records,
+    std::unique_ptr<TransactionLogIterator>& iter) {
+  int num_records;
+  ReadRecords(iter, num_records);
+  ASSERT_EQ(num_records, expected_no_records);
+}
+}  // namespace
+
+TEST_F(DBTestXactLogIterator, TransactionLogIterator) {
+  do {
+    Options options = OptionsForLogIterTest();
+    DestroyAndReopen(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+    Put(0, "key1", DummyString(1024));
+    Put(1, "key2", DummyString(1024));
+    Put(1, "key2", DummyString(1024));
+    ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 3U);
+    {
+      auto iter = OpenTransactionLogIter(0);
+      ExpectRecords(3, iter);
+    }
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    env_->SleepForMicroseconds(2 * 1000 * 1000);
+    {
+      Put(0, "key4", DummyString(1024));
+      Put(1, "key5", DummyString(1024));
+      Put(0, "key6", DummyString(1024));
+    }
+    {
+      auto iter = OpenTransactionLogIter(0);
+      ExpectRecords(6, iter);
+    }
+  } while (ChangeCompactOptions());
+}
+
+#ifndef NDEBUG  // sync point is not included with DNDEBUG build
+TEST_F(DBTestXactLogIterator, TransactionLogIteratorRace) {
+  static const int LOG_ITERATOR_RACE_TEST_COUNT = 2;
+  static const char* sync_points[LOG_ITERATOR_RACE_TEST_COUNT][4] = {
+      {"WalManager::GetSortedWalFiles:1",  "WalManager::PurgeObsoleteFiles:1",
+       "WalManager::PurgeObsoleteFiles:2", "WalManager::GetSortedWalFiles:2"},
+      {"WalManager::GetSortedWalsOfType:1",
+       "WalManager::PurgeObsoleteFiles:1",
+       "WalManager::PurgeObsoleteFiles:2",
+       "WalManager::GetSortedWalsOfType:2"}};
+  for (int test = 0; test < LOG_ITERATOR_RACE_TEST_COUNT; ++test) {
+    // Setup sync point dependency to reproduce the race condition of
+    // a log file moved to archived dir, in the middle of GetSortedWalFiles
+    rocksdb::SyncPoint::GetInstance()->LoadDependency(
+      { { sync_points[test][0], sync_points[test][1] },
+        { sync_points[test][2], sync_points[test][3] },
+      });
+
+    do {
+      rocksdb::SyncPoint::GetInstance()->ClearTrace();
+      rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+      Options options = OptionsForLogIterTest();
+      DestroyAndReopen(options);
+      Put("key1", DummyString(1024));
+      dbfull()->Flush(FlushOptions());
+      Put("key2", DummyString(1024));
+      dbfull()->Flush(FlushOptions());
+      Put("key3", DummyString(1024));
+      dbfull()->Flush(FlushOptions());
+      Put("key4", DummyString(1024));
+      ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 4U);
+
+      {
+        auto iter = OpenTransactionLogIter(0);
+        ExpectRecords(4, iter);
+      }
+
+      rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+      // trigger async flush, and log move. Well, log move will
+      // wait until the GetSortedWalFiles:1 to reproduce the race
+      // condition
+      FlushOptions flush_options;
+      flush_options.wait = false;
+      dbfull()->Flush(flush_options);
+
+      // "key5" would be written in a new memtable and log
+      Put("key5", DummyString(1024));
+      {
+        // this iter would miss "key4" if not fixed
+        auto iter = OpenTransactionLogIter(0);
+        ExpectRecords(5, iter);
+      }
+    } while (ChangeCompactOptions());
+  }
+}
+#endif
+
+TEST_F(DBTestXactLogIterator, TransactionLogIteratorStallAtLastRecord) {
+  do {
+    Options options = OptionsForLogIterTest();
+    DestroyAndReopen(options);
+    Put("key1", DummyString(1024));
+    auto iter = OpenTransactionLogIter(0);
+    ASSERT_OK(iter->status());
+    ASSERT_TRUE(iter->Valid());
+    iter->Next();
+    ASSERT_TRUE(!iter->Valid());
+    ASSERT_OK(iter->status());
+    Put("key2", DummyString(1024));
+    iter->Next();
+    ASSERT_OK(iter->status());
+    ASSERT_TRUE(iter->Valid());
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestXactLogIterator, TransactionLogIteratorCheckAfterRestart) {
+  do {
+    Options options = OptionsForLogIterTest();
+    DestroyAndReopen(options);
+    Put("key1", DummyString(1024));
+    Put("key2", DummyString(1023));
+    dbfull()->Flush(FlushOptions());
+    Reopen(options);
+    auto iter = OpenTransactionLogIter(0);
+    ExpectRecords(2, iter);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestXactLogIterator, TransactionLogIteratorCorruptedLog) {
+  do {
+    Options options = OptionsForLogIterTest();
+    DestroyAndReopen(options);
+    for (int i = 0; i < 1024; i++) {
+      Put("key"+ToString(i), DummyString(10));
+    }
+    dbfull()->Flush(FlushOptions());
+    // Corrupt this log to create a gap
+    rocksdb::VectorLogPtr wal_files;
+    ASSERT_OK(dbfull()->GetSortedWalFiles(wal_files));
+    const auto logfile_path = dbname_ + "/" + wal_files.front()->PathName();
+    if (mem_env_) {
+      mem_env_->Truncate(logfile_path, wal_files.front()->SizeFileBytes() / 2);
+    } else {
+      ASSERT_EQ(0, truncate(logfile_path.c_str(),
+                   wal_files.front()->SizeFileBytes() / 2));
+    }
+
+    // Insert a new entry to a new log file
+    Put("key1025", DummyString(10));
+    // Try to read from the beginning. Should stop before the gap and read less
+    // than 1025 entries
+    auto iter = OpenTransactionLogIter(0);
+    int count;
+    SequenceNumber last_sequence_read = ReadRecords(iter, count);
+    ASSERT_LT(last_sequence_read, 1025U);
+    // Try to read past the gap, should be able to seek to key1025
+    auto iter2 = OpenTransactionLogIter(last_sequence_read + 1);
+    ExpectRecords(1, iter2);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestXactLogIterator, TransactionLogIteratorBatchOperations) {
+  do {
+    Options options = OptionsForLogIterTest();
+    DestroyAndReopen(options);
+    CreateAndReopenWithCF({"pikachu"}, options);
+    WriteBatch batch;
+    batch.Put(handles_[1], "key1", DummyString(1024));
+    batch.Put(handles_[0], "key2", DummyString(1024));
+    batch.Put(handles_[1], "key3", DummyString(1024));
+    batch.Delete(handles_[0], "key2");
+    dbfull()->Write(WriteOptions(), &batch);
+    Flush(1);
+    Flush(0);
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    Put(1, "key4", DummyString(1024));
+    auto iter = OpenTransactionLogIter(3);
+    ExpectRecords(2, iter);
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBTestXactLogIterator, TransactionLogIteratorBlobs) {
+  Options options = OptionsForLogIterTest();
+  DestroyAndReopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+  {
+    WriteBatch batch;
+    batch.Put(handles_[1], "key1", DummyString(1024));
+    batch.Put(handles_[0], "key2", DummyString(1024));
+    batch.PutLogData(Slice("blob1"));
+    batch.Put(handles_[1], "key3", DummyString(1024));
+    batch.PutLogData(Slice("blob2"));
+    batch.Delete(handles_[0], "key2");
+    dbfull()->Write(WriteOptions(), &batch);
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+  }
+
+  auto res = OpenTransactionLogIter(0)->GetBatch();
+  struct Handler : public WriteBatch::Handler {
+    std::string seen;
+    virtual Status PutCF(uint32_t cf, const Slice& key,
+                         const Slice& value) override {
+      seen += "Put(" + ToString(cf) + ", " + key.ToString() + ", " +
+              ToString(value.size()) + ")";
+      return Status::OK();
+    }
+    virtual Status MergeCF(uint32_t cf, const Slice& key,
+                           const Slice& value) override {
+      seen += "Merge(" + ToString(cf) + ", " + key.ToString() + ", " +
+              ToString(value.size()) + ")";
+      return Status::OK();
+    }
+    virtual void LogData(const Slice& blob) override {
+      seen += "LogData(" + blob.ToString() + ")";
+    }
+    virtual Status DeleteCF(uint32_t cf, const Slice& key) override {
+      seen += "Delete(" + ToString(cf) + ", " + key.ToString() + ")";
+      return Status::OK();
+    }
+  } handler;
+  res.writeBatchPtr->Iterate(&handler);
+  ASSERT_EQ(
+      "Put(1, key1, 1024)"
+      "Put(0, key2, 1024)"
+      "LogData(blob1)"
+      "Put(1, key3, 1024)"
+      "LogData(blob2)"
+      "Delete(0, key2)",
+      handler.seen);
+}
+}  // namespace rocksdb
+
+#endif  // !(defined NDEBUG) || !defined(OS_WIN)
+
+int main(int argc, char** argv) {
+#if !(defined NDEBUG) || !defined(OS_WIN)
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+#else
+  return 0;
+#endif
+}

db/db_tailing_iter_test.cc

@@ -0,0 +1,481 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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.
+
+// Introduction of SyncPoint effectively disabled building and running this test
+// in Release build.
+// which is a pity, it is a good test
+#if !(defined NDEBUG) || !defined(OS_WIN)
+
+#include "port/stack_trace.h"
+#include "util/db_test_util.h"
+
+namespace rocksdb {
+
+class DBTestTailingIterator : public DBTestBase {
+ public:
+  DBTestTailingIterator() : DBTestBase("/db_tailing_iterator_test") {}
+};
+
+TEST_F(DBTestTailingIterator, TailingIteratorSingle) {
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+  iter->SeekToFirst();
+  ASSERT_TRUE(!iter->Valid());
+
+  // add a record and check that iter can see it
+  ASSERT_OK(db_->Put(WriteOptions(), "mirko", "fodor"));
+  iter->SeekToFirst();
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(iter->key().ToString(), "mirko");
+
+  iter->Next();
+  ASSERT_TRUE(!iter->Valid());
+}
+
+TEST_F(DBTestTailingIterator, TailingIteratorKeepAdding) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+  std::string value(1024, 'a');
+
+  const int num_records = 10000;
+  for (int i = 0; i < num_records; ++i) {
+    char buf[32];
+    snprintf(buf, sizeof(buf), "%016d", i);
+
+    Slice key(buf, 16);
+    ASSERT_OK(Put(1, key, value));
+
+    iter->Seek(key);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->key().compare(key), 0);
+  }
+}
+
+TEST_F(DBTestTailingIterator, TailingIteratorSeekToNext) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+  std::string value(1024, 'a');
+
+  const int num_records = 1000;
+  for (int i = 1; i < num_records; ++i) {
+    char buf1[32];
+    char buf2[32];
+    snprintf(buf1, sizeof(buf1), "00a0%016d", i * 5);
+
+    Slice key(buf1, 20);
+    ASSERT_OK(Put(1, key, value));
+
+    if (i % 100 == 99) {
+      ASSERT_OK(Flush(1));
+    }
+
+    snprintf(buf2, sizeof(buf2), "00a0%016d", i * 5 - 2);
+    Slice target(buf2, 20);
+    iter->Seek(target);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->key().compare(key), 0);
+  }
+  for (int i = 2 * num_records; i > 0; --i) {
+    char buf1[32];
+    char buf2[32];
+    snprintf(buf1, sizeof(buf1), "00a0%016d", i * 5);
+
+    Slice key(buf1, 20);
+    ASSERT_OK(Put(1, key, value));
+
+    if (i % 100 == 99) {
+      ASSERT_OK(Flush(1));
+    }
+
+    snprintf(buf2, sizeof(buf2), "00a0%016d", i * 5 - 2);
+    Slice target(buf2, 20);
+    iter->Seek(target);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->key().compare(key), 0);
+  }
+}
+
+TEST_F(DBTestTailingIterator, TailingIteratorDeletes) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+
+  // write a single record, read it using the iterator, then delete it
+  ASSERT_OK(Put(1, "0test", "test"));
+  iter->SeekToFirst();
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(iter->key().ToString(), "0test");
+  ASSERT_OK(Delete(1, "0test"));
+
+  // write many more records
+  const int num_records = 10000;
+  std::string value(1024, 'A');
+
+  for (int i = 0; i < num_records; ++i) {
+    char buf[32];
+    snprintf(buf, sizeof(buf), "1%015d", i);
+
+    Slice key(buf, 16);
+    ASSERT_OK(Put(1, key, value));
+  }
+
+  // force a flush to make sure that no records are read from memtable
+  ASSERT_OK(Flush(1));
+
+  // skip "0test"
+  iter->Next();
+
+  // make sure we can read all new records using the existing iterator
+  int count = 0;
+  for (; iter->Valid(); iter->Next(), ++count) ;
+
+  ASSERT_EQ(count, num_records);
+}
+
+TEST_F(DBTestTailingIterator, TailingIteratorPrefixSeek) {
+  XFUNC_TEST("", "dbtest_prefix", prefix_skip1, XFuncPoint::SetSkip,
+             kSkipNoPrefix);
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.create_if_missing = true;
+  options.disable_auto_compactions = true;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(2));
+  options.memtable_factory.reset(NewHashSkipListRepFactory(16));
+  DestroyAndReopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+  ASSERT_OK(Put(1, "0101", "test"));
+
+  ASSERT_OK(Flush(1));
+
+  ASSERT_OK(Put(1, "0202", "test"));
+
+  // Seek(0102) shouldn't find any records since 0202 has a different prefix
+  iter->Seek("0102");
+  ASSERT_TRUE(!iter->Valid());
+
+  iter->Seek("0202");
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(iter->key().ToString(), "0202");
+
+  iter->Next();
+  ASSERT_TRUE(!iter->Valid());
+  XFUNC_TEST("", "dbtest_prefix", prefix_skip1, XFuncPoint::SetSkip, 0);
+}
+
+TEST_F(DBTestTailingIterator, TailingIteratorIncomplete) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.read_tier = kBlockCacheTier;
+
+  std::string key("key");
+  std::string value("value");
+
+  ASSERT_OK(db_->Put(WriteOptions(), key, value));
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+  iter->SeekToFirst();
+  // we either see the entry or it's not in cache
+  ASSERT_TRUE(iter->Valid() || iter->status().IsIncomplete());
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  iter->SeekToFirst();
+  // should still be true after compaction
+  ASSERT_TRUE(iter->Valid() || iter->status().IsIncomplete());
+}
+
+TEST_F(DBTestTailingIterator, TailingIteratorSeekToSame) {
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleUniversal;
+  options.write_buffer_size = 1000;
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  const int NROWS = 10000;
+  // Write rows with keys 00000, 00002, 00004 etc.
+  for (int i = 0; i < NROWS; ++i) {
+    char buf[100];
+    snprintf(buf, sizeof(buf), "%05d", 2*i);
+    std::string key(buf);
+    std::string value("value");
+    ASSERT_OK(db_->Put(WriteOptions(), key, value));
+  }
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+  // Seek to 00001.  We expect to find 00002.
+  std::string start_key = "00001";
+  iter->Seek(start_key);
+  ASSERT_TRUE(iter->Valid());
+
+  std::string found = iter->key().ToString();
+  ASSERT_EQ("00002", found);
+
+  // Now seek to the same key.  The iterator should remain in the same
+  // position.
+  iter->Seek(found);
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(found, iter->key().ToString());
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorSingle) {
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+  iter->SeekToFirst();
+  ASSERT_TRUE(!iter->Valid());
+
+  // add a record and check that iter can see it
+  ASSERT_OK(db_->Put(WriteOptions(), "mirko", "fodor"));
+  iter->SeekToFirst();
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(iter->key().ToString(), "mirko");
+
+  iter->Next();
+  ASSERT_TRUE(!iter->Valid());
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorKeepAdding) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+  std::string value(1024, 'a');
+
+  const int num_records = 10000;
+  for (int i = 0; i < num_records; ++i) {
+    char buf[32];
+    snprintf(buf, sizeof(buf), "%016d", i);
+
+    Slice key(buf, 16);
+    ASSERT_OK(Put(1, key, value));
+
+    iter->Seek(key);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->key().compare(key), 0);
+  }
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorSeekToNext) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+  std::string value(1024, 'a');
+
+  const int num_records = 1000;
+  for (int i = 1; i < num_records; ++i) {
+    char buf1[32];
+    char buf2[32];
+    snprintf(buf1, sizeof(buf1), "00a0%016d", i * 5);
+
+    Slice key(buf1, 20);
+    ASSERT_OK(Put(1, key, value));
+
+    if (i % 100 == 99) {
+      ASSERT_OK(Flush(1));
+    }
+
+    snprintf(buf2, sizeof(buf2), "00a0%016d", i * 5 - 2);
+    Slice target(buf2, 20);
+    iter->Seek(target);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->key().compare(key), 0);
+  }
+  for (int i = 2 * num_records; i > 0; --i) {
+    char buf1[32];
+    char buf2[32];
+    snprintf(buf1, sizeof(buf1), "00a0%016d", i * 5);
+
+    Slice key(buf1, 20);
+    ASSERT_OK(Put(1, key, value));
+
+    if (i % 100 == 99) {
+      ASSERT_OK(Flush(1));
+    }
+
+    snprintf(buf2, sizeof(buf2), "00a0%016d", i * 5 - 2);
+    Slice target(buf2, 20);
+    iter->Seek(target);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->key().compare(key), 0);
+  }
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorDeletes) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+
+  // write a single record, read it using the iterator, then delete it
+  ASSERT_OK(Put(1, "0test", "test"));
+  iter->SeekToFirst();
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(iter->key().ToString(), "0test");
+  ASSERT_OK(Delete(1, "0test"));
+
+  // write many more records
+  const int num_records = 10000;
+  std::string value(1024, 'A');
+
+  for (int i = 0; i < num_records; ++i) {
+    char buf[32];
+    snprintf(buf, sizeof(buf), "1%015d", i);
+
+    Slice key(buf, 16);
+    ASSERT_OK(Put(1, key, value));
+  }
+
+  // force a flush to make sure that no records are read from memtable
+  ASSERT_OK(Flush(1));
+
+  // skip "0test"
+  iter->Next();
+
+  // make sure we can read all new records using the existing iterator
+  int count = 0;
+  for (; iter->Valid(); iter->Next(), ++count) {
+  }
+
+  ASSERT_EQ(count, num_records);
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorPrefixSeek) {
+  XFUNC_TEST("", "dbtest_prefix", prefix_skip1, XFuncPoint::SetSkip,
+             kSkipNoPrefix);
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.create_if_missing = true;
+  options.disable_auto_compactions = true;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(2));
+  options.memtable_factory.reset(NewHashSkipListRepFactory(16));
+  DestroyAndReopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options, handles_[1]));
+  ASSERT_OK(Put(1, "0101", "test"));
+
+  ASSERT_OK(Flush(1));
+
+  ASSERT_OK(Put(1, "0202", "test"));
+
+  // Seek(0102) shouldn't find any records since 0202 has a different prefix
+  iter->Seek("0102");
+  ASSERT_TRUE(!iter->Valid());
+
+  iter->Seek("0202");
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(iter->key().ToString(), "0202");
+
+  iter->Next();
+  ASSERT_TRUE(!iter->Valid());
+  XFUNC_TEST("", "dbtest_prefix", prefix_skip1, XFuncPoint::SetSkip, 0);
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorIncomplete) {
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+  read_options.read_tier = kBlockCacheTier;
+
+  std::string key = "key";
+  std::string value = "value";
+
+  ASSERT_OK(db_->Put(WriteOptions(), key, value));
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+  iter->SeekToFirst();
+  // we either see the entry or it's not in cache
+  ASSERT_TRUE(iter->Valid() || iter->status().IsIncomplete());
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  iter->SeekToFirst();
+  // should still be true after compaction
+  ASSERT_TRUE(iter->Valid() || iter->status().IsIncomplete());
+}
+
+TEST_F(DBTestTailingIterator, ManagedTailingIteratorSeekToSame) {
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleUniversal;
+  options.write_buffer_size = 1000;
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  ReadOptions read_options;
+  read_options.tailing = true;
+  read_options.managed = true;
+
+  const int NROWS = 10000;
+  // Write rows with keys 00000, 00002, 00004 etc.
+  for (int i = 0; i < NROWS; ++i) {
+    char buf[100];
+    snprintf(buf, sizeof(buf), "%05d", 2 * i);
+    std::string key(buf);
+    std::string value("value");
+    ASSERT_OK(db_->Put(WriteOptions(), key, value));
+  }
+
+  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+  // Seek to 00001.  We expect to find 00002.
+  std::string start_key = "00001";
+  iter->Seek(start_key);
+  ASSERT_TRUE(iter->Valid());
+
+  std::string found = iter->key().ToString();
+  ASSERT_EQ("00002", found);
+
+  // Now seek to the same key.  The iterator should remain in the same
+  // position.
+  iter->Seek(found);
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(found, iter->key().ToString());
+}
+
+}  // namespace rocksdb
+
+#endif  // !(defined NDEBUG) || !defined(OS_WIN)
+
+int main(int argc, char** argv) {
+#if !(defined NDEBUG) || !defined(OS_WIN)
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+#else
+  return 0;
+#endif
+}

db/db_wal_test.cc

@@ -0,0 +1,144 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 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 "port/stack_trace.h"
+#include "util/db_test_util.h"
+#if !(defined NDEBUG) || !defined(OS_WIN)
+#include "util/sync_point.h"
+#endif
+
+namespace rocksdb {
+class DBWALTest : public DBTestBase {
+ public:
+  DBWALTest() : DBTestBase("/db_wal_test") {}
+};
+
+TEST_F(DBWALTest, WAL) {
+  do {
+    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+    WriteOptions writeOpt = WriteOptions();
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v1"));
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v1"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
+    ASSERT_EQ("v1", Get(1, "foo"));
+    ASSERT_EQ("v1", Get(1, "bar"));
+
+    writeOpt.disableWAL = false;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v2"));
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v2"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
+    // Both value's should be present.
+    ASSERT_EQ("v2", Get(1, "bar"));
+    ASSERT_EQ("v2", Get(1, "foo"));
+
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v3"));
+    writeOpt.disableWAL = false;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v3"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
+    // again both values should be present.
+    ASSERT_EQ("v3", Get(1, "foo"));
+    ASSERT_EQ("v3", Get(1, "bar"));
+  } while (ChangeCompactOptions());
+}
+
+TEST_F(DBWALTest, RollLog) {
+  do {
+    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+    ASSERT_OK(Put(1, "foo", "v1"));
+    ASSERT_OK(Put(1, "baz", "v5"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
+    for (int i = 0; i < 10; i++) {
+      ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
+    }
+    ASSERT_OK(Put(1, "foo", "v4"));
+    for (int i = 0; i < 10; i++) {
+      ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
+    }
+  } while (ChangeOptions());
+}
+
+#if !(defined NDEBUG) || !defined(OS_WIN)
+TEST_F(DBWALTest, SyncWALNotBlockWrite) {
+  Options options = CurrentOptions();
+  options.max_write_buffer_number = 4;
+  DestroyAndReopen(options);
+
+  ASSERT_OK(Put("foo1", "bar1"));
+  ASSERT_OK(Put("foo5", "bar5"));
+
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
+      {"WritableFileWriter::SyncWithoutFlush:1",
+       "DBWALTest::SyncWALNotBlockWrite:1"},
+      {"DBWALTest::SyncWALNotBlockWrite:2",
+       "WritableFileWriter::SyncWithoutFlush:2"},
+  });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  std::thread thread([&]() { ASSERT_OK(db_->SyncWAL()); });
+
+  TEST_SYNC_POINT("DBWALTest::SyncWALNotBlockWrite:1");
+  ASSERT_OK(Put("foo2", "bar2"));
+  ASSERT_OK(Put("foo3", "bar3"));
+  FlushOptions fo;
+  fo.wait = false;
+  ASSERT_OK(db_->Flush(fo));
+  ASSERT_OK(Put("foo4", "bar4"));
+
+  TEST_SYNC_POINT("DBWALTest::SyncWALNotBlockWrite:2");
+
+  thread.join();
+
+  ASSERT_EQ(Get("foo1"), "bar1");
+  ASSERT_EQ(Get("foo2"), "bar2");
+  ASSERT_EQ(Get("foo3"), "bar3");
+  ASSERT_EQ(Get("foo4"), "bar4");
+  ASSERT_EQ(Get("foo5"), "bar5");
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_F(DBWALTest, SyncWALNotWaitWrite) {
+  ASSERT_OK(Put("foo1", "bar1"));
+  ASSERT_OK(Put("foo3", "bar3"));
+
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
+      {"SpecialEnv::WalFile::Append:1", "DBWALTest::SyncWALNotWaitWrite:1"},
+      {"DBWALTest::SyncWALNotWaitWrite:2", "SpecialEnv::WalFile::Append:2"},
+  });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  std::thread thread([&]() { ASSERT_OK(Put("foo2", "bar2")); });
+  TEST_SYNC_POINT("DBWALTest::SyncWALNotWaitWrite:1");
+  ASSERT_OK(db_->SyncWAL());
+  TEST_SYNC_POINT("DBWALTest::SyncWALNotWaitWrite:2");
+
+  thread.join();
+
+  ASSERT_EQ(Get("foo1"), "bar1");
+  ASSERT_EQ(Get("foo2"), "bar2");
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+}
+#endif
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+#if !(defined NDEBUG) || !defined(OS_WIN)
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+#else
+  return 0;
+#endif
+}

db/dbformat.cc

@@ -8,6 +8,11 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 #include "db/dbformat.h"
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <stdio.h>
 #include "port/port.h"
 #include "util/coding.h"
@@ -21,6 +26,14 @@ uint64_t PackSequenceAndType(uint64_t seq, ValueType t) {
   return (seq << 8) | t;
 }
 
+void UnPackSequenceAndType(uint64_t packed, uint64_t* seq, ValueType* t) {
+  *seq = packed >> 8;
+  *t = static_cast<ValueType>(packed & 0xff);
+
+  assert(*seq <= kMaxSequenceNumber);
+  assert(*t <= kValueTypeForSeek);
+}
+
 void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
   result->append(key.user_key.data(), key.user_key.size());
   PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
@@ -28,9 +41,8 @@ void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
 
 std::string ParsedInternalKey::DebugString(bool hex) const {
   char buf[50];
-  snprintf(buf, sizeof(buf), "' @ %llu : %d",
-           (unsigned long long) sequence,
-           int(type));
+  snprintf(buf, sizeof(buf), "' @ %" PRIu64 ": %d", sequence,
+           static_cast<int>(type));
   std::string result = "'";
   result += user_key.ToString(hex);
   result += buf;

db/dbformat.h

@@ -71,8 +71,13 @@ inline size_t InternalKeyEncodingLength(const ParsedInternalKey& key) {
   return key.user_key.size() + 8;
 }
 
+// Pack a sequence number and a ValueType into a uint64_t
 extern uint64_t PackSequenceAndType(uint64_t seq, ValueType t);
 
+// Given the result of PackSequenceAndType, store the sequence number in *seq
+// and the ValueType in *t.
+extern void UnPackSequenceAndType(uint64_t packed, uint64_t* seq, ValueType* t);
+
 // Append the serialization of "key" to *result.
 extern void AppendInternalKey(std::string* result,
                               const ParsedInternalKey& key);
@@ -190,14 +195,17 @@ inline bool ParseInternalKey(const Slice& internal_key,
   return (c <= static_cast<unsigned char>(kValueTypeForSeek));
 }
 
-// Update the sequence number in the internal key
-inline void UpdateInternalKey(char* internal_key,
-                              const size_t internal_key_size,
+// Update the sequence number in the internal key.
+// Guarantees not to invalidate ikey.data().
+inline void UpdateInternalKey(std::string* ikey,
                               uint64_t seq, ValueType t) {
-  assert(internal_key_size >= 8);
-  char* seqtype = internal_key + internal_key_size - 8;
+  size_t ikey_sz = ikey->size();
+  assert(ikey_sz >= 8);
   uint64_t newval = (seq << 8) | t;
-  EncodeFixed64(seqtype, newval);
+
+  // Note: Since C++11, strings are guaranteed to be stored contiguously and
+  // string::operator[]() is guaranteed not to change ikey.data().
+  EncodeFixed64(&(*ikey)[ikey_sz - 8], newval);
 }
 
 // Get the sequence number from the internal key

db/dbformat_test.cc

@@ -149,6 +149,25 @@ TEST_F(FormatTest, IterKeyOperation) {
               "abcdefghijklmnopqrstuvwxyz"));
 }
 
+TEST_F(FormatTest, UpdateInternalKey) {
+  std::string user_key("abcdefghijklmnopqrstuvwxyz");
+  uint64_t new_seq = 0x123456;
+  ValueType new_val_type = kTypeDeletion;
+
+  std::string ikey;
+  AppendInternalKey(&ikey, ParsedInternalKey(user_key, 100U, kTypeValue));
+  size_t ikey_size = ikey.size();
+  UpdateInternalKey(&ikey, new_seq, new_val_type);
+  ASSERT_EQ(ikey_size, ikey.size());
+
+  Slice in(ikey);
+  ParsedInternalKey decoded;
+  ASSERT_TRUE(ParseInternalKey(in, &decoded));
+  ASSERT_EQ(user_key, decoded.user_key.ToString());
+  ASSERT_EQ(new_seq, decoded.sequence);
+  ASSERT_EQ(new_val_type, decoded.type);
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/deletefile_test.cc

@@ -7,6 +7,8 @@
 // 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 ROCKSDB_LITE
+
 #include "rocksdb/db.h"
 #include "db/db_impl.h"
 #include "db/filename.h"
@@ -36,7 +38,6 @@ class DeleteFileTest : public testing::Test {
     db_ = nullptr;
     env_ = Env::Default();
     options_.enable_thread_tracking = true;
-    options_.max_background_flushes = 0;
     options_.write_buffer_size = 1024*1024*1000;
     options_.target_file_size_base = 1024*1024*1000;
     options_.max_bytes_for_level_base = 1024*1024*1000;
@@ -117,10 +118,14 @@ class DeleteFileTest : public testing::Test {
     DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
     ASSERT_OK(dbi->TEST_FlushMemTable());
     ASSERT_OK(dbi->TEST_WaitForFlushMemTable());
+    for (int i = 0; i < 2; ++i) {
+      ASSERT_OK(dbi->TEST_CompactRange(i, nullptr, nullptr));
+    }
 
     AddKeys(50000, 10000);
     ASSERT_OK(dbi->TEST_FlushMemTable());
     ASSERT_OK(dbi->TEST_WaitForFlushMemTable());
+    ASSERT_OK(dbi->TEST_CompactRange(0, nullptr, nullptr));
   }
 
   void CheckFileTypeCounts(std::string& dir,
@@ -201,8 +206,11 @@ TEST_F(DeleteFileTest, PurgeObsoleteFilesTest) {
   // 2 ssts, 1 manifest
   CheckFileTypeCounts(dbname_, 0, 2, 1);
   std::string first("0"), last("999999");
+  CompactRangeOptions compact_options;
+  compact_options.change_level = true;
+  compact_options.target_level = 2;
   Slice first_slice(first), last_slice(last);
-  db_->CompactRange(&first_slice, &last_slice, true, 2);
+  db_->CompactRange(compact_options, &first_slice, &last_slice);
   // 1 sst after compaction
   CheckFileTypeCounts(dbname_, 0, 1, 1);
 
@@ -211,7 +219,7 @@ TEST_F(DeleteFileTest, PurgeObsoleteFilesTest) {
   Iterator *itr = 0;
   CreateTwoLevels();
   itr = db_->NewIterator(ReadOptions());
-  db_->CompactRange(&first_slice, &last_slice, true, 2);
+  db_->CompactRange(compact_options, &first_slice, &last_slice);
   // 3 sst after compaction with live iterator
   CheckFileTypeCounts(dbname_, 0, 3, 1);
   delete itr;
@@ -261,11 +269,11 @@ TEST_F(DeleteFileTest, DeleteLogFiles) {
   // Should not succeed because live logs are not allowed to be deleted
   std::unique_ptr<LogFile> alive_log = std::move(logfiles.back());
   ASSERT_EQ(alive_log->Type(), kAliveLogFile);
-  ASSERT_TRUE(env_->FileExists(options_.wal_dir + "/" + alive_log->PathName()));
+  ASSERT_OK(env_->FileExists(options_.wal_dir + "/" + alive_log->PathName()));
   fprintf(stdout, "Deleting alive log file %s\n",
           alive_log->PathName().c_str());
   ASSERT_TRUE(!db_->DeleteFile(alive_log->PathName()).ok());
-  ASSERT_TRUE(env_->FileExists(options_.wal_dir + "/" + alive_log->PathName()));
+  ASSERT_OK(env_->FileExists(options_.wal_dir + "/" + alive_log->PathName()));
   logfiles.clear();
 
   // Call Flush to bring about a new working log file and add more keys
@@ -279,13 +287,13 @@ TEST_F(DeleteFileTest, DeleteLogFiles) {
   ASSERT_GT(logfiles.size(), 0UL);
   std::unique_ptr<LogFile> archived_log = std::move(logfiles.front());
   ASSERT_EQ(archived_log->Type(), kArchivedLogFile);
-  ASSERT_TRUE(env_->FileExists(options_.wal_dir + "/" +
-        archived_log->PathName()));
+  ASSERT_OK(
+      env_->FileExists(options_.wal_dir + "/" + archived_log->PathName()));
   fprintf(stdout, "Deleting archived log file %s\n",
           archived_log->PathName().c_str());
   ASSERT_OK(db_->DeleteFile(archived_log->PathName()));
-  ASSERT_TRUE(!env_->FileExists(options_.wal_dir + "/" +
-        archived_log->PathName()));
+  ASSERT_EQ(Status::NotFound(), env_->FileExists(options_.wal_dir + "/" +
+                                                 archived_log->PathName()));
   CloseDB();
 }
 
@@ -365,3 +373,13 @@ int main(int argc, char** argv) {
   return RUN_ALL_TESTS();
 }
 
+#else
+#include <stdio.h>
+
+int main(int argc, char** argv) {
+  fprintf(stderr,
+          "SKIPPED as DBImpl::DeleteFile is not supported in ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // !ROCKSDB_LITE

db/event_helpers.cc

@@ -0,0 +1,108 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+
+#include "db/event_helpers.h"
+
+namespace rocksdb {
+
+namespace {
+inline double SafeDivide(double a, double b) { return b == 0.0 ? 0 : a / b; }
+}  // namespace
+
+void EventHelpers::AppendCurrentTime(JSONWriter* jwriter) {
+  *jwriter << "time_micros"
+           << std::chrono::duration_cast<std::chrono::microseconds>(
+                  std::chrono::system_clock::now().time_since_epoch()).count();
+}
+
+void EventHelpers::LogAndNotifyTableFileCreation(
+    EventLogger* event_logger,
+    const std::vector<std::shared_ptr<EventListener>>& listeners,
+    const FileDescriptor& fd, const TableFileCreationInfo& info) {
+  assert(event_logger);
+  JSONWriter jwriter;
+  AppendCurrentTime(&jwriter);
+  jwriter << "cf_name" << info.cf_name
+          << "job" << info.job_id
+          << "event" << "table_file_creation"
+          << "file_number" << fd.GetNumber()
+          << "file_size" << fd.GetFileSize();
+
+  // table_properties
+  {
+    jwriter << "table_properties";
+    jwriter.StartObject();
+
+    // basic properties:
+    jwriter << "data_size" << info.table_properties.data_size
+            << "index_size" << info.table_properties.index_size
+            << "filter_size" << info.table_properties.filter_size
+            << "raw_key_size" << info.table_properties.raw_key_size
+            << "raw_average_key_size" << SafeDivide(
+                info.table_properties.raw_key_size,
+                info.table_properties.num_entries)
+            << "raw_value_size" << info.table_properties.raw_value_size
+            << "raw_average_value_size" << SafeDivide(
+               info.table_properties.raw_value_size,
+               info.table_properties.num_entries)
+            << "num_data_blocks" << info.table_properties.num_data_blocks
+            << "num_entries" << info.table_properties.num_entries
+            << "filter_policy_name" <<
+                info.table_properties.filter_policy_name;
+
+    // user collected properties
+    for (const auto& prop : info.table_properties.user_collected_properties) {
+      jwriter << prop.first << prop.second;
+    }
+    jwriter.EndObject();
+  }
+  jwriter.EndObject();
+
+  event_logger->Log(jwriter);
+
+#ifndef ROCKSDB_LITE
+  if (listeners.size() == 0) {
+    return;
+  }
+
+  for (auto listener : listeners) {
+    listener->OnTableFileCreated(info);
+  }
+#endif  // !ROCKSDB_LITE
+}
+
+void EventHelpers::LogAndNotifyTableFileDeletion(
+    EventLogger* event_logger, int job_id,
+    uint64_t file_number, const std::string& file_path,
+    const Status& status, const std::string& dbname,
+    const std::vector<std::shared_ptr<EventListener>>& listeners) {
+
+  JSONWriter jwriter;
+  AppendCurrentTime(&jwriter);
+
+  jwriter << "job" << job_id
+          << "event" << "table_file_deletion"
+          << "file_number" << file_number;
+  if (!status.ok()) {
+    jwriter << "status" << status.ToString();
+  }
+
+  jwriter.EndObject();
+
+  event_logger->Log(jwriter);
+
+#ifndef ROCKSDB_LITE
+  TableFileDeletionInfo info;
+  info.db_name = dbname;
+  info.job_id = job_id;
+  info.file_path = file_path;
+  info.status = status;
+  for (auto listener : listeners) {
+    listener->OnTableFileDeleted(info);
+  }
+#endif  // !ROCKSDB_LITE
+}
+
+}  // namespace rocksdb

db/event_helpers.h

@@ -0,0 +1,33 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+#pragma once
+
+#include <memory>
+#include <string>
+#include <vector>
+
+#include "db/column_family.h"
+#include "db/version_edit.h"
+#include "rocksdb/listener.h"
+#include "rocksdb/table_properties.h"
+#include "util/event_logger.h"
+
+namespace rocksdb {
+
+class EventHelpers {
+ public:
+  static void AppendCurrentTime(JSONWriter* json_writer);
+  static void LogAndNotifyTableFileCreation(
+      EventLogger* event_logger,
+      const std::vector<std::shared_ptr<EventListener>>& listeners,
+      const FileDescriptor& fd, const TableFileCreationInfo& info);
+  static void LogAndNotifyTableFileDeletion(
+      EventLogger* event_logger, int job_id,
+      uint64_t file_number, const std::string& file_path,
+      const Status& status, const std::string& db_name,
+      const std::vector<std::shared_ptr<EventListener>>& listeners);
+};
+
+}  // namespace rocksdb

db/event_logger_helpers.cc

@@ -1,46 +0,0 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#include "db/event_logger_helpers.h"
-
-namespace rocksdb {
-
-namespace {
-inline double SafeDivide(double a, double b) { return b == 0.0 ? 0 : a / b; }
-}  // namespace
-
-void EventLoggerHelpers::LogTableFileCreation(
-    EventLogger* event_logger, int job_id, uint64_t file_number,
-    uint64_t file_size, const TableProperties& table_properties) {
-  auto stream = event_logger->Log();
-  stream << "job" << job_id << "event"
-         << "table_file_creation"
-         << "file_number" << file_number << "file_size" << file_size
-         << "table_properties";
-  stream.StartObject();
-
-  // basic properties:
-  stream << "data_size" << table_properties.data_size
-         << "index_size" << table_properties.index_size
-         << "filter_size" << table_properties.filter_size
-         << "raw_key_size" << table_properties.raw_key_size
-         << "raw_average_key_size" << SafeDivide(table_properties.raw_key_size,
-             table_properties.num_entries)
-         << "raw_value_size" << table_properties.raw_value_size
-         << "raw_average_value_size" << SafeDivide(
-             table_properties.raw_value_size, table_properties.num_entries)
-         << "num_data_blocks" << table_properties.num_data_blocks
-         << "num_entries" << table_properties.num_entries
-         << "filter_policy_name" << table_properties.filter_policy_name;
-
-  // user collected properties
-  for (const auto& prop : table_properties.user_collected_properties) {
-    stream << prop.first << prop.second;
-  }
-
-  stream.EndObject();
-}
-
-}  // namespace rocksdb

db/event_logger_helpers.h

@@ -1,18 +0,0 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-#pragma once
-
-#include "util/event_logger.h"
-#include "rocksdb/table_properties.h"
-
-namespace rocksdb {
-
-class EventLoggerHelpers {
- public:
-  static void LogTableFileCreation(EventLogger* event_logger, int job_id,
-                                   uint64_t file_number, uint64_t file_size,
-                                   const TableProperties& table_properties);
-};
-}  // namespace rocksdb

db/fault_injection_test.cc

@@ -25,6 +25,7 @@
 #include "util/logging.h"
 #include "util/mock_env.h"
 #include "util/mutexlock.h"
+#include "util/sync_point.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
 
@@ -77,9 +78,12 @@ Status Truncate(Env* env, const std::string& filename, uint64_t length) {
     return s;
   }
 
-  char* scratch = new char[length];
+  std::unique_ptr<char[]> scratch(new char[length]);
   rocksdb::Slice result;
-  s = orig_file->Read(length, &result, scratch);
+  s = orig_file->Read(length, &result, scratch.get());
+#ifdef OS_WIN
+  orig_file.reset();
+#endif
   if (s.ok()) {
     std::string tmp_name = GetDirName(filename) + "/truncate.tmp";
     unique_ptr<WritableFile> tmp_file;
@@ -100,8 +104,6 @@ Status Truncate(Env* env, const std::string& filename, uint64_t length) {
             s.ToString().c_str());
   }
 
-  delete[] scratch;
-
   return s;
 }
 
@@ -128,7 +130,7 @@ struct FileState {
 
 }  // anonymous namespace
 
-// A wrapper around WritableFile which informs another Env whenever this file
+// A wrapper around WritableFileWriter* file
 // is written to or sync'ed.
 class TestWritableFile : public WritableFile {
  public:
@@ -140,6 +142,7 @@ class TestWritableFile : public WritableFile {
   virtual Status Close() override;
   virtual Status Flush() override;
   virtual Status Sync() override;
+  virtual bool IsSyncThreadSafe() const override { return true; }
 
  private:
   FileState state_;
@@ -185,10 +188,21 @@ class FaultInjectionTestEnv : public EnvWrapper {
   Status NewWritableFile(const std::string& fname,
                          unique_ptr<WritableFile>* result,
                          const EnvOptions& soptions) override {
-    Status s = target()->NewWritableFile(fname, result, soptions);
+    if (!IsFilesystemActive()) {
+      return Status::Corruption("Not Active");
+    }
+    // Not allow overwriting files
+    Status s = target()->FileExists(fname);
+    if (s.ok()) {
+      return Status::Corruption("File already exists.");
+    } else if (!s.IsNotFound()) {
+      assert(s.IsIOError());
+      return s;
+    }
+    s = target()->NewWritableFile(fname, result, soptions);
     if (s.ok()) {
       result->reset(new TestWritableFile(fname, std::move(*result), this));
-      // WritableFile doesn't append to files, so if the same file is opened
+      // WritableFileWriter* file is opened
       // again then it will be truncated - so forget our saved state.
       UntrackFile(fname);
       MutexLock l(&mutex_);
@@ -201,6 +215,9 @@ class FaultInjectionTestEnv : public EnvWrapper {
   }
 
   virtual Status DeleteFile(const std::string& f) override {
+    if (!IsFilesystemActive()) {
+      return Status::Corruption("Not Active");
+    }
     Status s = EnvWrapper::DeleteFile(f);
     if (!s.ok()) {
       fprintf(stderr, "Cannot delete file %s: %s\n", f.c_str(),
@@ -215,6 +232,9 @@ class FaultInjectionTestEnv : public EnvWrapper {
 
   virtual Status RenameFile(const std::string& s,
                             const std::string& t) override {
+    if (!IsFilesystemActive()) {
+      return Status::Corruption("Not Active");
+    }
     Status ret = EnvWrapper::RenameFile(s, t);
 
     if (ret.ok()) {
@@ -373,8 +393,11 @@ TestWritableFile::~TestWritableFile() {
 }
 
 Status TestWritableFile::Append(const Slice& data) {
+  if (!env_->IsFilesystemActive()) {
+    return Status::Corruption("Not Active");
+  }
   Status s = target_->Append(data);
-  if (s.ok() && env_->IsFilesystemActive()) {
+  if (s.ok()) {
     state_.pos_ += data.size();
   }
   return s;
@@ -406,7 +429,8 @@ Status TestWritableFile::Sync() {
   return Status::OK();
 }
 
-class FaultInjectionTest : public testing::Test {
+class FaultInjectionTest : public testing::Test,
+                           public testing::WithParamInterface<bool> {
  protected:
   enum OptionConfig {
     kDefault,
@@ -423,6 +447,8 @@ class FaultInjectionTest : public testing::Test {
   // When need to make sure data is persistent, call DB::CompactRange()
   bool sync_use_compact_;
 
+  bool sequential_order_;
+
  protected:
  public:
   enum ExpectedVerifResult { kValExpectFound, kValExpectNoError };
@@ -449,6 +475,11 @@ class FaultInjectionTest : public testing::Test {
         db_(NULL) {
   }
 
+  ~FaultInjectionTest() {
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+  }
+
   bool ChangeOptions() {
     option_config_++;
     if (option_config_ >= kEnd) {
@@ -529,7 +560,10 @@ class FaultInjectionTest : public testing::Test {
     return s;
   }
 
-  void SetUp() override { ASSERT_OK(NewDB()); }
+  void SetUp() override {
+    sequential_order_ = GetParam();
+    ASSERT_OK(NewDB());
+  }
 
   void TearDown() override {
     CloseDB();
@@ -591,8 +625,15 @@ class FaultInjectionTest : public testing::Test {
 
   // Return the ith key
   Slice Key(int i, std::string* storage) const {
+    int num = i;
+    if (!sequential_order_) {
+      // random transfer
+      const int m = 0x5bd1e995;
+      num *= m;
+      num ^= num << 24;
+    }
     char buf[100];
-    snprintf(buf, sizeof(buf), "%016d", i);
+    snprintf(buf, sizeof(buf), "%016d", num);
     storage->assign(buf, strlen(buf));
     return Slice(*storage);
   }
@@ -659,7 +700,7 @@ class FaultInjectionTest : public testing::Test {
 
     Build(write_options, 0, num_pre_sync);
     if (sync_use_compact_) {
-      db_->CompactRange(nullptr, nullptr);
+      db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
     }
     write_options.sync = false;
     Build(write_options, num_pre_sync, num_post_sync);
@@ -675,6 +716,10 @@ class FaultInjectionTest : public testing::Test {
     ASSERT_OK(Verify(0, num_pre_sync, FaultInjectionTest::kValExpectFound));
     ASSERT_OK(Verify(num_pre_sync, num_post_sync,
                      FaultInjectionTest::kValExpectNoError));
+    WaitCompactionFinish();
+    ASSERT_OK(Verify(0, num_pre_sync, FaultInjectionTest::kValExpectFound));
+    ASSERT_OK(Verify(num_pre_sync, num_post_sync,
+                     FaultInjectionTest::kValExpectNoError));
   }
 
   void NoWriteTestPreFault() {
@@ -685,9 +730,14 @@ class FaultInjectionTest : public testing::Test {
     ResetDBState(reset_method);
     ASSERT_OK(OpenDB());
   }
+
+  void WaitCompactionFinish() {
+    static_cast<DBImpl*>(db_)->TEST_WaitForCompact();
+    ASSERT_OK(db_->Put(WriteOptions(), "", ""));
+  }
 };
 
-TEST_F(FaultInjectionTest, FaultTest) {
+TEST_P(FaultInjectionTest, FaultTest) {
   do {
     Random rnd(301);
 
@@ -758,10 +808,8 @@ class SleepingBackgroundTask {
   bool done_with_sleep_;
 };
 
-// Disable the test because it is not passing.
 // Previous log file is not fsynced if sync is forced after log rolling.
-// TODO(FB internal task#6730880) Fix the bug
-TEST_F(FaultInjectionTest, DISABLED_WriteOptionSyncTest) {
+TEST_P(FaultInjectionTest, WriteOptionSyncTest) {
   SleepingBackgroundTask sleeping_task_low;
   env_->SetBackgroundThreads(1, Env::HIGH);
   // Block the job queue to prevent flush job from running.
@@ -796,6 +844,91 @@ TEST_F(FaultInjectionTest, DISABLED_WriteOptionSyncTest) {
   ASSERT_EQ(value_space, val);
 }
 
+TEST_P(FaultInjectionTest, UninstalledCompaction) {
+  options_.target_file_size_base = 32 * 1024;
+  options_.write_buffer_size = 100 << 10;  // 100KB
+  options_.level0_file_num_compaction_trigger = 6;
+  options_.level0_stop_writes_trigger = 1 << 10;
+  options_.level0_slowdown_writes_trigger = 1 << 10;
+  options_.max_background_compactions = 1;
+  OpenDB();
+
+  if (!sequential_order_) {
+    rocksdb::SyncPoint::GetInstance()->LoadDependency({
+        {"FaultInjectionTest::FaultTest:0", "DBImpl::BGWorkCompaction"},
+        {"CompactionJob::Run():End", "FaultInjectionTest::FaultTest:1"},
+        {"FaultInjectionTest::FaultTest:2",
+         "DBImpl::BackgroundCompaction:NonTrivial:AfterRun"},
+    });
+  }
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  int kNumKeys = 1000;
+  Build(WriteOptions(), 0, kNumKeys);
+  FlushOptions flush_options;
+  flush_options.wait = true;
+  db_->Flush(flush_options);
+  ASSERT_OK(db_->Put(WriteOptions(), "", ""));
+  TEST_SYNC_POINT("FaultInjectionTest::FaultTest:0");
+  TEST_SYNC_POINT("FaultInjectionTest::FaultTest:1");
+  env_->SetFilesystemActive(false);
+  TEST_SYNC_POINT("FaultInjectionTest::FaultTest:2");
+  CloseDB();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  ResetDBState(kResetDropUnsyncedData);
+
+  std::atomic<bool> opened(false);
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::Open:Opened", [&](void* arg) { opened.store(true); });
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BGWorkCompaction",
+      [&](void* arg) { ASSERT_TRUE(opened.load()); });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(OpenDB());
+  ASSERT_OK(Verify(0, kNumKeys, FaultInjectionTest::kValExpectFound));
+  WaitCompactionFinish();
+  ASSERT_OK(Verify(0, kNumKeys, FaultInjectionTest::kValExpectFound));
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_P(FaultInjectionTest, ManualLogSyncTest) {
+  SleepingBackgroundTask sleeping_task_low;
+  env_->SetBackgroundThreads(1, Env::HIGH);
+  // Block the job queue to prevent flush job from running.
+  env_->Schedule(&SleepingBackgroundTask::DoSleepTask, &sleeping_task_low,
+                 Env::Priority::HIGH);
+
+  WriteOptions write_options;
+  write_options.sync = false;
+
+  std::string key_space, value_space;
+  ASSERT_OK(
+      db_->Put(write_options, Key(1, &key_space), Value(1, &value_space)));
+  FlushOptions flush_options;
+  flush_options.wait = false;
+  ASSERT_OK(db_->Flush(flush_options));
+  ASSERT_OK(
+      db_->Put(write_options, Key(2, &key_space), Value(2, &value_space)));
+  ASSERT_OK(db_->SyncWAL());
+
+  env_->SetFilesystemActive(false);
+  NoWriteTestReopenWithFault(kResetDropAndDeleteUnsynced);
+  sleeping_task_low.WakeUp();
+
+  ASSERT_OK(OpenDB());
+  std::string val;
+  Value(2, &value_space);
+  ASSERT_OK(ReadValue(2, &val));
+  ASSERT_EQ(value_space, val);
+
+  Value(1, &value_space);
+  ASSERT_OK(ReadValue(1, &val));
+  ASSERT_EQ(value_space, val);
+}
+
+INSTANTIATE_TEST_CASE_P(FaultTest, FaultInjectionTest, ::testing::Bool());
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/file_indexer.h

@@ -12,6 +12,7 @@
 #include <functional>
 #include <limits>
 #include <vector>
+#include "port/port.h"
 #include "util/arena.h"
 #include "util/autovector.h"
 
@@ -58,7 +59,8 @@ class FileIndexer {
                    std::vector<FileMetaData*>* const files);
 
   enum {
-    kLevelMaxIndex = std::numeric_limits<int32_t>::max()
+    // MSVC version 1800 still does not have constexpr for ::max()
+    kLevelMaxIndex = rocksdb::port::kMaxInt32
   };
 
  private:

db/filename.cc

@@ -18,6 +18,7 @@
 #include <vector>
 #include "db/dbformat.h"
 #include "rocksdb/env.h"
+#include "util/file_reader_writer.h"
 #include "util/logging.h"
 #include "util/stop_watch.h"
 
@@ -103,8 +104,6 @@ std::string TableFileName(const std::vector<DbPath>& db_paths, uint64_t number,
   return MakeTableFileName(path, number);
 }
 
-const size_t kFormatFileNumberBufSize = 38;
-
 void FormatFileNumber(uint64_t number, uint32_t path_id, char* out_buf,
                       size_t out_buf_size) {
   if (path_id == 0) {
@@ -330,15 +329,13 @@ Status SetIdentityFile(Env* env, const std::string& dbname) {
   return s;
 }
 
-Status SyncManifest(Env* env, const DBOptions* db_options, WritableFile* file) {
+Status SyncManifest(Env* env, const DBOptions* db_options,
+                    WritableFileWriter* file) {
   if (db_options->disableDataSync) {
     return Status::OK();
-  } else if (db_options->use_fsync) {
-    StopWatch sw(env, db_options->statistics.get(), MANIFEST_FILE_SYNC_MICROS);
-    return file->Fsync();
   } else {
     StopWatch sw(env, db_options->statistics.get(), MANIFEST_FILE_SYNC_MICROS);
-    return file->Sync();
+    return file->Sync(db_options->use_fsync);
   }
 }
 

db/filename.h

@@ -25,7 +25,7 @@ namespace rocksdb {
 
 class Env;
 class Directory;
-class WritableFile;
+class WritableFileWriter;
 
 enum FileType {
   kLogFile,
@@ -66,7 +66,7 @@ extern std::string TableFileName(const std::vector<DbPath>& db_paths,
                                  uint64_t number, uint32_t path_id);
 
 // Sufficient buffer size for FormatFileNumber.
-extern const size_t kFormatFileNumberBufSize;
+const size_t kFormatFileNumberBufSize = 38;
 
 extern void FormatFileNumber(uint64_t number, uint32_t path_id, char* out_buf,
                              size_t out_buf_size);
@@ -140,6 +140,6 @@ extern Status SetIdentityFile(Env* env, const std::string& dbname);
 
 // Sync manifest file `file`.
 extern Status SyncManifest(Env* env, const DBOptions* db_options,
-                           WritableFile* file);
+                           WritableFileWriter* file);
 
 }  // namespace rocksdb

db/flush_job.cc

@@ -20,7 +20,7 @@
 #include "db/builder.h"
 #include "db/db_iter.h"
 #include "db/dbformat.h"
-#include "db/event_logger_helpers.h"
+#include "db/event_helpers.h"
 #include "db/filename.h"
 #include "db/log_reader.h"
 #include "db/log_writer.h"
@@ -116,11 +116,11 @@ void FlushJob::RecordFlushIOStats() {
   IOSTATS_RESET(bytes_written);
 }
 
-Status FlushJob::Run(uint64_t* file_number) {
+Status FlushJob::Run(FileMetaData* file_meta) {
   AutoThreadOperationStageUpdater stage_run(
       ThreadStatus::STAGE_FLUSH_RUN);
   // Save the contents of the earliest memtable as a new Table
-  uint64_t fn;
+  FileMetaData meta;
   autovector<MemTable*> mems;
   cfd_->imm()->PickMemtablesToFlush(&mems);
   if (mems.empty()) {
@@ -143,7 +143,7 @@ Status FlushJob::Run(uint64_t* file_number) {
   edit->SetColumnFamily(cfd_->GetID());
 
   // This will release and re-acquire the mutex.
-  Status s = WriteLevel0Table(mems, edit, &fn);
+  Status s = WriteLevel0Table(mems, edit, &meta);
 
   if (s.ok() &&
       (shutting_down_->load(std::memory_order_acquire) || cfd_->IsDropped())) {
@@ -152,16 +152,17 @@ Status FlushJob::Run(uint64_t* file_number) {
   }
 
   if (!s.ok()) {
-    cfd_->imm()->RollbackMemtableFlush(mems, fn);
+    cfd_->imm()->RollbackMemtableFlush(mems, meta.fd.GetNumber());
   } else {
     // Replace immutable memtable with the generated Table
     s = cfd_->imm()->InstallMemtableFlushResults(
-        cfd_, mutable_cf_options_, mems, versions_, db_mutex_, fn,
-        &job_context_->memtables_to_free, db_directory_, log_buffer_);
+        cfd_, mutable_cf_options_, mems, versions_, db_mutex_,
+        meta.fd.GetNumber(), &job_context_->memtables_to_free, db_directory_,
+        log_buffer_);
   }
 
-  if (s.ok() && file_number != nullptr) {
-    *file_number = fn;
+  if (s.ok() && file_meta != nullptr) {
+    *file_meta = meta;
   }
   RecordFlushIOStats();
 
@@ -180,15 +181,13 @@ Status FlushJob::Run(uint64_t* file_number) {
 }
 
 Status FlushJob::WriteLevel0Table(const autovector<MemTable*>& mems,
-                                  VersionEdit* edit, uint64_t* filenumber) {
+                                  VersionEdit* edit, FileMetaData* meta) {
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_FLUSH_WRITE_L0);
   db_mutex_->AssertHeld();
   const uint64_t start_micros = db_options_.env->NowMicros();
-  FileMetaData meta;
   // path 0 for level 0 file.
-  meta.fd = FileDescriptor(versions_->NewFileNumber(), 0, 0);
-  *filenumber = meta.fd.GetNumber();
+  meta->fd = FileDescriptor(versions_->NewFileNumber(), 0, 0);
 
   const SequenceNumber earliest_seqno_in_memtable =
       mems[0]->GetFirstSequenceNumber();
@@ -222,37 +221,47 @@ Status FlushJob::WriteLevel0Table(const autovector<MemTable*>& mems,
                          << total_num_entries << "num_deletes"
                          << total_num_deletes << "memory_usage"
                          << total_memory_usage;
-    TableProperties table_properties;
+    TableFileCreationInfo info;
     {
       ScopedArenaIterator iter(
           NewMergingIterator(&cfd_->internal_comparator(), &memtables[0],
                              static_cast<int>(memtables.size()), &arena));
       Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
           "[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": started",
-          cfd_->GetName().c_str(), job_context_->job_id, meta.fd.GetNumber());
+          cfd_->GetName().c_str(), job_context_->job_id, meta->fd.GetNumber());
 
       TEST_SYNC_POINT_CALLBACK("FlushJob::WriteLevel0Table:output_compression",
                                &output_compression_);
       s = BuildTable(dbname_, db_options_.env, *cfd_->ioptions(), env_options_,
-                     cfd_->table_cache(), iter.get(), &meta,
+                     cfd_->table_cache(), iter.get(), meta,
                      cfd_->internal_comparator(),
                      cfd_->int_tbl_prop_collector_factories(), newest_snapshot_,
                      earliest_seqno_in_memtable, output_compression_,
                      cfd_->ioptions()->compression_opts,
                      mutable_cf_options_.paranoid_file_checks, Env::IO_HIGH,
-                     &table_properties);
+                     &info.table_properties);
       LogFlush(db_options_.info_log);
     }
     Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-        "[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": %" PRIu64 " bytes %s",
-        cfd_->GetName().c_str(), job_context_->job_id, meta.fd.GetNumber(),
-        meta.fd.GetFileSize(), s.ToString().c_str());
+        "[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": %" PRIu64
+        " bytes %s"
+        "%s",
+        cfd_->GetName().c_str(), job_context_->job_id, meta->fd.GetNumber(),
+        meta->fd.GetFileSize(), s.ToString().c_str(),
+        meta->marked_for_compaction ? " (needs compaction)" : "");
 
     // output to event logger
     if (s.ok()) {
-      EventLoggerHelpers::LogTableFileCreation(
-          event_logger_, job_context_->job_id, meta.fd.GetNumber(),
-          meta.fd.GetFileSize(), table_properties);
+      info.db_name = dbname_;
+      info.cf_name = cfd_->GetName();
+      info.file_path = TableFileName(db_options_.db_paths,
+                                     meta->fd.GetNumber(),
+                                     meta->fd.GetPathId());
+      info.file_size = meta->fd.GetFileSize();
+      info.job_id = job_context_->job_id;
+      EventHelpers::LogAndNotifyTableFileCreation(
+          event_logger_, db_options_.listeners,
+          meta->fd, info);
     }
 
     if (!db_options_.disableDataSync && output_file_directory_ != nullptr) {
@@ -267,38 +276,25 @@ Status FlushJob::WriteLevel0Table(const autovector<MemTable*>& mems,
 
   // Note that if file_size is zero, the file has been deleted and
   // should not be added to the manifest.
-  int level = 0;
-  if (s.ok() && meta.fd.GetFileSize() > 0) {
-    const Slice min_user_key = meta.smallest.user_key();
-    const Slice max_user_key = meta.largest.user_key();
+  if (s.ok() && meta->fd.GetFileSize() > 0) {
     // if we have more than 1 background thread, then we cannot
     // insert files directly into higher levels because some other
     // threads could be concurrently producing compacted files for
     // that key range.
-    if (base != nullptr && db_options_.max_background_compactions <= 1 &&
-        db_options_.max_background_flushes == 0 &&
-        cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
-      level = base->storage_info()->PickLevelForMemTableOutput(
-          mutable_cf_options_, min_user_key, max_user_key);
-      // If level does not match path id, reset level back to 0
-      uint32_t fdpath = LevelCompactionPicker::GetPathId(
-          *cfd_->ioptions(), mutable_cf_options_, level);
-      if (fdpath != 0) {
-        level = 0;
-      }
-    }
-    edit->AddFile(level, meta.fd.GetNumber(), meta.fd.GetPathId(),
-                  meta.fd.GetFileSize(), meta.smallest, meta.largest,
-                  meta.smallest_seqno, meta.largest_seqno);
+    // Add file to L0
+    edit->AddFile(0 /* level */, meta->fd.GetNumber(), meta->fd.GetPathId(),
+                  meta->fd.GetFileSize(), meta->smallest, meta->largest,
+                  meta->smallest_seqno, meta->largest_seqno,
+                  meta->marked_for_compaction);
   }
 
   InternalStats::CompactionStats stats(1);
   stats.micros = db_options_.env->NowMicros() - start_micros;
-  stats.bytes_written = meta.fd.GetFileSize();
-  cfd_->internal_stats()->AddCompactionStats(level, stats);
+  stats.bytes_written = meta->fd.GetFileSize();
+  cfd_->internal_stats()->AddCompactionStats(0 /* level */, stats);
   cfd_->internal_stats()->AddCFStats(InternalStats::BYTES_FLUSHED,
-                                     meta.fd.GetFileSize());
-  RecordTick(stats_, COMPACT_WRITE_BYTES, meta.fd.GetFileSize());
+                                     meta->fd.GetFileSize());
+  RecordTick(stats_, COMPACT_WRITE_BYTES, meta->fd.GetFileSize());
   return s;
 }
 

db/flush_job.h

@@ -64,14 +64,14 @@ class FlushJob {
 
   ~FlushJob();
 
-  Status Run(uint64_t* file_number = nullptr);
+  Status Run(FileMetaData* file_meta = nullptr);
 
  private:
   void ReportStartedFlush();
   void ReportFlushInputSize(const autovector<MemTable*>& mems);
   void RecordFlushIOStats();
   Status WriteLevel0Table(const autovector<MemTable*>& mems, VersionEdit* edit,
-                          uint64_t* filenumber);
+                          FileMetaData* meta);
   const std::string& dbname_;
   ColumnFamilyData* cfd_;
   const DBOptions& db_options_;

db/flush_job_test.cc

@@ -11,6 +11,7 @@
 #include "db/version_set.h"
 #include "db/writebuffer.h"
 #include "rocksdb/cache.h"
+#include "util/file_reader_writer.h"
 #include "util/string_util.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
@@ -56,8 +57,10 @@ class FlushJobTest : public testing::Test {
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
+    unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), EnvOptions()));
     {
-      log::Writer log(std::move(file));
+      log::Writer log(std::move(file_writer));
       std::string record;
       new_db.EncodeTo(&record);
       s = log.AddRecord(record);
@@ -97,7 +100,8 @@ TEST_F(FlushJobTest, Empty) {
 TEST_F(FlushJobTest, NonEmpty) {
   JobContext job_context(0);
   auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions());
+  auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
+                                           kMaxSequenceNumber);
   new_mem->Ref();
   std::map<std::string, std::string> inserted_keys;
   for (int i = 1; i < 10000; ++i) {
@@ -107,7 +111,12 @@ TEST_F(FlushJobTest, NonEmpty) {
     InternalKey internal_key(key, SequenceNumber(i), kTypeValue);
     inserted_keys.insert({internal_key.Encode().ToString(), value});
   }
-  cfd->imm()->Add(new_mem);
+
+  autovector<MemTable*> to_delete;
+  cfd->imm()->Add(new_mem, &to_delete);
+  for (auto& m : to_delete) {
+    delete m;
+  }
 
   EventLogger event_logger(db_options_.info_log.get());
   FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),

db/forward_iterator.cc

@@ -169,6 +169,7 @@ void ForwardIterator::Cleanup(bool release_sv) {
       if (job_context.HaveSomethingToDelete()) {
         db_->PurgeObsoleteFiles(job_context);
       }
+      job_context.Clean();
     }
   }
 }

db/internal_stats.cc

@@ -45,8 +45,10 @@ void PrintLevelStats(char* buf, size_t len, const std::string& name,
     int num_files, int being_compacted, double total_file_size, double score,
     double w_amp, uint64_t stalls,
     const InternalStats::CompactionStats& stats) {
-  uint64_t bytes_read = stats.bytes_readn + stats.bytes_readnp1;
-  int64_t bytes_new = stats.bytes_written - stats.bytes_readnp1;
+  uint64_t bytes_read =
+      stats.bytes_read_non_output_levels + stats.bytes_read_output_level;
+  int64_t bytes_new =
+      stats.bytes_written - stats.bytes_read_output_level;
   double elapsed = (stats.micros + 1) / 1000000.0;
   std::string num_input_records = NumberToHumanString(stats.num_input_records);
   std::string num_dropped_records =
@@ -71,8 +73,8 @@ void PrintLevelStats(char* buf, size_t len, const std::string& name,
            "%7s "   /* KeyIn */
            "%6s\n", /* KeyDrop */
            name.c_str(), num_files, being_compacted, total_file_size / kMB,
-           score, bytes_read / kGB, stats.bytes_readn / kGB,
-           stats.bytes_readnp1 / kGB, stats.bytes_written / kGB,
+           score, bytes_read / kGB, stats.bytes_read_non_output_levels / kGB,
+           stats.bytes_read_output_level / kGB, stats.bytes_written / kGB,
            bytes_new / kGB, stats.bytes_moved / kGB,
            w_amp, bytes_read / kMB / elapsed,
            stats.bytes_written / kMB / elapsed, stats.micros / 1000000.0,
@@ -92,6 +94,8 @@ static const std::string cfstats = "cfstats";
 static const std::string dbstats = "dbstats";
 static const std::string levelstats = "levelstats";
 static const std::string num_immutable_mem_table = "num-immutable-mem-table";
+static const std::string num_immutable_mem_table_flushed =
+    "num-immutable-mem-table-flushed";
 static const std::string mem_table_flush_pending = "mem-table-flush-pending";
 static const std::string compaction_pending = "compaction-pending";
 static const std::string background_errors = "background-errors";
@@ -114,6 +118,7 @@ static const std::string is_file_deletions_enabled =
 static const std::string num_snapshots = "num-snapshots";
 static const std::string oldest_snapshot_time = "oldest-snapshot-time";
 static const std::string num_live_versions = "num-live-versions";
+static const std::string estimate_live_data_size = "estimate-live-data-size";
 static const std::string base_level = "base-level";
 
 const std::string DB::Properties::kNumFilesAtLevelPrefix =
@@ -154,6 +159,8 @@ const std::string DB::Properties::kOldestSnapshotTime =
                       rocksdb_prefix + oldest_snapshot_time;
 const std::string DB::Properties::kNumLiveVersions =
                       rocksdb_prefix + num_live_versions;
+const std::string DB::Properties::kEstimateLiveDataSize =
+                      rocksdb_prefix + estimate_live_data_size;
 
 DBPropertyType GetPropertyType(const Slice& property, bool* is_int_property,
                                bool* need_out_of_mutex) {
@@ -185,6 +192,8 @@ DBPropertyType GetPropertyType(const Slice& property, bool* is_int_property,
   *is_int_property = true;
   if (in == num_immutable_mem_table) {
     return kNumImmutableMemTable;
+  } else if (in == num_immutable_mem_table_flushed) {
+    return kNumImmutableMemTableFlushed;
   } else if (in == mem_table_flush_pending) {
     return kMemtableFlushPending;
   } else if (in == compaction_pending) {
@@ -216,6 +225,9 @@ DBPropertyType GetPropertyType(const Slice& property, bool* is_int_property,
     return kOldestSnapshotTime;
   } else if (in == num_live_versions) {
     return kNumLiveVersions;
+  } else if (in == estimate_live_data_size) {
+    *need_out_of_mutex = true;
+    return kEstimateLiveDataSize;
   } else if (in == base_level) {
     return kBaseLevel;
   }
@@ -226,15 +238,19 @@ bool InternalStats::GetIntPropertyOutOfMutex(DBPropertyType property_type,
                                              Version* version,
                                              uint64_t* value) const {
   assert(value != nullptr);
-  if (property_type != kEstimatedUsageByTableReaders) {
-    return false;
+  const auto* vstorage = cfd_->current()->storage_info();
+
+  switch (property_type) {
+    case kEstimatedUsageByTableReaders:
+      *value = (version == nullptr) ?
+        0 : version->GetMemoryUsageByTableReaders();
+      return true;
+    case kEstimateLiveDataSize:
+      *value = vstorage->EstimateLiveDataSize();
+      return true;
+    default:
+      return false;
   }
-  if (version == nullptr) {
-    *value = 0;
-  } else {
-    *value = version->GetMemoryUsageByTableReaders();
-  }
-  return true;
 }
 
 bool InternalStats::GetStringProperty(DBPropertyType property_type,
@@ -307,7 +323,10 @@ bool InternalStats::GetIntProperty(DBPropertyType property_type,
 
   switch (property_type) {
     case kNumImmutableMemTable:
-      *value = cfd_->imm()->size();
+      *value = cfd_->imm()->NumNotFlushed();
+      return true;
+    case kNumImmutableMemTableFlushed:
+      *value = cfd_->imm()->NumFlushed();
       return true;
     case kMemtableFlushPending:
       // Return number of mem tables that are ready to flush (made immutable)
@@ -433,8 +452,8 @@ void InternalStats::DumpDBStats(std::string* value) {
   value->append(buf);
   // Compact
   for (int level = 0; level < number_levels_; level++) {
-    compact_bytes_read += comp_stats_[level].bytes_readnp1 +
-                          comp_stats_[level].bytes_readn;
+    compact_bytes_read += comp_stats_[level].bytes_read_output_level +
+                          comp_stats_[level].bytes_read_non_output_levels;
     compact_bytes_write += comp_stats_[level].bytes_written;
     compact_micros += comp_stats_[level].micros;
   }
@@ -541,8 +560,7 @@ void InternalStats::DumpCFStats(std::string* value) {
   const VersionStorageInfo* vstorage = cfd_->current()->storage_info();
 
   int num_levels_to_check =
-      (cfd_->ioptions()->compaction_style != kCompactionStyleUniversal &&
-       cfd_->ioptions()->compaction_style != kCompactionStyleFIFO)
+      (cfd_->ioptions()->compaction_style != kCompactionStyleFIFO)
           ? vstorage->num_levels() - 1
           : 1;
 
@@ -555,7 +573,7 @@ void InternalStats::DumpCFStats(std::string* value) {
   }
   // Count # of files being compacted for each level
   std::vector<int> files_being_compacted(number_levels_, 0);
-  for (int level = 0; level < num_levels_to_check; ++level) {
+  for (int level = 0; level < number_levels_; ++level) {
     for (auto* f : vstorage->LevelFiles(level)) {
       if (f->being_compacted) {
         ++files_being_compacted[level];
@@ -592,9 +610,10 @@ void InternalStats::DumpCFStats(std::string* value) {
       total_stall_count += stalls;
       total_slowdown_count_soft += stall_leveln_slowdown_count_soft_[level];
       total_slowdown_count_hard += stall_leveln_slowdown_count_hard_[level];
-      double w_amp = (comp_stats_[level].bytes_readn == 0) ? 0.0
-          : comp_stats_[level].bytes_written /
-            static_cast<double>(comp_stats_[level].bytes_readn);
+      double w_amp =
+          (comp_stats_[level].bytes_read_non_output_levels == 0) ? 0.0
+          : static_cast<double>(comp_stats_[level].bytes_written) /
+            comp_stats_[level].bytes_read_non_output_levels;
       PrintLevelStats(buf, sizeof(buf), "L" + ToString(level), files,
                       files_being_compacted[level],
                       vstorage->NumLevelBytes(level), compaction_score[level],

db/internal_stats.h

@@ -32,9 +32,12 @@ enum DBPropertyType : uint32_t {
   kStats,            // Return general statitistics of both DB and CF
   kSsTables,         // Return a human readable string of current SST files
   kStartIntTypes,    // ---- Dummy value to indicate the start of integer values
-  kNumImmutableMemTable,   // Return number of immutable mem tables
-  kMemtableFlushPending,   // Return 1 if mem table flushing is pending,
-                           // otherwise 0.
+  kNumImmutableMemTable,         // Return number of immutable mem tables that
+                                 // have not been flushed.
+  kNumImmutableMemTableFlushed,  // Return number of immutable mem tables
+                                 // in memory that have already been flushed
+  kMemtableFlushPending,         // Return 1 if mem table flushing is pending,
+                                 // otherwise 0.
   kCompactionPending,      // Return 1 if a compaction is pending. Otherwise 0.
   kBackgroundErrors,       // Return accumulated background errors encountered.
   kCurSizeActiveMemTable,  // Return current size of the active memtable
@@ -55,6 +58,7 @@ enum DBPropertyType : uint32_t {
   kNumSnapshots,                  // Number of snapshots in the system
   kOldestSnapshotTime,            // Unix timestamp of the first snapshot
   kNumLiveVersions,
+  kEstimateLiveDataSize,          // Estimated amount of live data in bytes
   kBaseLevel,  // The level that L0 data is compacted to
 };
 
@@ -117,26 +121,26 @@ class InternalStats {
   struct CompactionStats {
     uint64_t micros;
 
-    // Bytes read from level N during compaction between levels N and N+1
-    uint64_t bytes_readn;
+    // The number of bytes read from all non-output levels
+    uint64_t bytes_read_non_output_levels;
 
-    // Bytes read from level N+1 during compaction between levels N and N+1
-    uint64_t bytes_readnp1;
+    // The number of bytes read from the compaction output level.
+    uint64_t bytes_read_output_level;
 
-    // Total bytes written during compaction between levels N and N+1
+    // Total number of bytes written during compaction
     uint64_t bytes_written;
 
-    // Total bytes moved to this level
+    // Total number of bytes moved to the output level
     uint64_t bytes_moved;
 
-    // Files read from level N during compaction between levels N and N+1
-    int files_in_leveln;
+    // The number of compaction input files in all non-output levels.
+    int num_input_files_in_non_output_levels;
 
-    // Files read from level N+1 during compaction between levels N and N+1
-    int files_in_levelnp1;
+    // The number of compaction input files in the output level.
+    int num_input_files_in_output_level;
 
-    // Files written during compaction between levels N and N+1
-    int files_out_levelnp1;
+    // The number of compaction output files.
+    int num_output_files;
 
     // Total incoming entries during compaction between levels N and N+1
     uint64_t num_input_records;
@@ -150,39 +154,43 @@ class InternalStats {
 
     explicit CompactionStats(int _count = 0)
         : micros(0),
-          bytes_readn(0),
-          bytes_readnp1(0),
+          bytes_read_non_output_levels(0),
+          bytes_read_output_level(0),
           bytes_written(0),
           bytes_moved(0),
-          files_in_leveln(0),
-          files_in_levelnp1(0),
-          files_out_levelnp1(0),
+          num_input_files_in_non_output_levels(0),
+          num_input_files_in_output_level(0),
+          num_output_files(0),
           num_input_records(0),
           num_dropped_records(0),
           count(_count) {}
 
     explicit CompactionStats(const CompactionStats& c)
         : micros(c.micros),
-          bytes_readn(c.bytes_readn),
-          bytes_readnp1(c.bytes_readnp1),
+          bytes_read_non_output_levels(c.bytes_read_non_output_levels),
+          bytes_read_output_level(c.bytes_read_output_level),
           bytes_written(c.bytes_written),
           bytes_moved(c.bytes_moved),
-          files_in_leveln(c.files_in_leveln),
-          files_in_levelnp1(c.files_in_levelnp1),
-          files_out_levelnp1(c.files_out_levelnp1),
+          num_input_files_in_non_output_levels(
+              c.num_input_files_in_non_output_levels),
+          num_input_files_in_output_level(
+              c.num_input_files_in_output_level),
+          num_output_files(c.num_output_files),
           num_input_records(c.num_input_records),
           num_dropped_records(c.num_dropped_records),
           count(c.count) {}
 
     void Add(const CompactionStats& c) {
       this->micros += c.micros;
-      this->bytes_readn += c.bytes_readn;
-      this->bytes_readnp1 += c.bytes_readnp1;
+      this->bytes_read_non_output_levels += c.bytes_read_non_output_levels;
+      this->bytes_read_output_level += c.bytes_read_output_level;
       this->bytes_written += c.bytes_written;
       this->bytes_moved += c.bytes_moved;
-      this->files_in_leveln += c.files_in_leveln;
-      this->files_in_levelnp1 += c.files_in_levelnp1;
-      this->files_out_levelnp1 += c.files_out_levelnp1;
+      this->num_input_files_in_non_output_levels +=
+          c.num_input_files_in_non_output_levels;
+      this->num_input_files_in_output_level +=
+          c.num_input_files_in_output_level;
+      this->num_output_files += c.num_output_files;
       this->num_input_records += c.num_input_records;
       this->num_dropped_records += c.num_dropped_records;
       this->count += c.count;
@@ -190,13 +198,15 @@ class InternalStats {
 
     void Subtract(const CompactionStats& c) {
       this->micros -= c.micros;
-      this->bytes_readn -= c.bytes_readn;
-      this->bytes_readnp1 -= c.bytes_readnp1;
+      this->bytes_read_non_output_levels -= c.bytes_read_non_output_levels;
+      this->bytes_read_output_level -= c.bytes_read_output_level;
       this->bytes_written -= c.bytes_written;
       this->bytes_moved -= c.bytes_moved;
-      this->files_in_leveln -= c.files_in_leveln;
-      this->files_in_levelnp1 -= c.files_in_levelnp1;
-      this->files_out_levelnp1 -= c.files_out_levelnp1;
+      this->num_input_files_in_non_output_levels -=
+          c.num_input_files_in_non_output_levels;
+      this->num_input_files_in_output_level -=
+          c.num_input_files_in_output_level;
+      this->num_output_files -= c.num_output_files;
       this->num_input_records -= c.num_input_records;
       this->num_dropped_records -= c.num_dropped_records;
       this->count -= c.count;
@@ -349,13 +359,13 @@ class InternalStats {
 
   struct CompactionStats {
     uint64_t micros;
-    uint64_t bytes_readn;
-    uint64_t bytes_readnp1;
+    uint64_t bytes_read_non_output_levels;
+    uint64_t bytes_read_output_level;
     uint64_t bytes_written;
     uint64_t bytes_moved;
-    int files_in_leveln;
-    int files_in_levelnp1;
-    int files_out_levelnp1;
+    int num_input_files_in_non_output_levels;
+    int num_input_files_in_output_level;
+    int num_output_files;
     uint64_t num_input_records;
     uint64_t num_dropped_records;
     int count;

db/job_context.h

@@ -83,6 +83,10 @@ struct JobContext {
     new_superversion = create_superversion ? new SuperVersion() : nullptr;
   }
 
+  // For non-empty JobContext Clean() has to be called at least once before
+  // before destruction (see asserts in ~JobContext()). Should be called with
+  // unlocked DB mutex. Destructor doesn't call Clean() to avoid accidentally
+  // doing potentially slow Clean() with locked DB mutex.
   void Clean() {
     // free pending memtables
     for (auto m : memtables_to_free) {
@@ -109,6 +113,7 @@ struct JobContext {
     assert(memtables_to_free.size() == 0);
     assert(superversions_to_free.size() == 0);
     assert(new_superversion == nullptr);
+    assert(logs_to_free.size() == 0);
   }
 };
 

db/listener_test.cc

@@ -156,6 +156,8 @@ class TestCompactionListener : public EventListener {
     compacted_dbs_.push_back(db);
     ASSERT_GT(ci.input_files.size(), 0U);
     ASSERT_GT(ci.output_files.size(), 0U);
+    ASSERT_EQ(db->GetEnv()->GetThreadID(), ci.thread_id);
+    ASSERT_GT(ci.thread_id, 0U);
   }
 
   std::vector<DB*> compacted_dbs_;
@@ -177,7 +179,9 @@ TEST_F(EventListenerTest, OnSingleDBCompactionTest) {
   options.max_bytes_for_level_base = options.target_file_size_base * 2;
   options.max_bytes_for_level_multiplier = 2;
   options.compression = kNoCompression;
+#if ROCKSDB_USING_THREAD_STATUS
   options.enable_thread_tracking = true;
+#endif  // ROCKSDB_USING_THREAD_STATUS
   options.level0_file_num_compaction_trigger = kNumL0Files;
 
   TestCompactionListener* listener = new TestCompactionListener();
@@ -197,7 +201,8 @@ TEST_F(EventListenerTest, OnSingleDBCompactionTest) {
     ASSERT_OK(Flush(static_cast<int>(i)));
     const Slice kStart = "a";
     const Slice kEnd = "z";
-    ASSERT_OK(dbfull()->CompactRange(handles_[i], &kStart, &kEnd));
+    ASSERT_OK(dbfull()->CompactRange(CompactRangeOptions(), handles_[i],
+                                     &kStart, &kEnd));
     dbfull()->TEST_WaitForFlushMemTable();
     dbfull()->TEST_WaitForCompact();
   }
@@ -208,33 +213,85 @@ TEST_F(EventListenerTest, OnSingleDBCompactionTest) {
   }
 }
 
+// This simple Listener can only handle one flush at a time.
 class TestFlushListener : public EventListener {
  public:
+  explicit TestFlushListener(Env* env)
+      : slowdown_count(0), stop_count(0), db_closed(), env_(env) {
+    db_closed = false;
+  }
+  void OnTableFileCreated(
+      const TableFileCreationInfo& info) override {
+    // remember the info for later checking the FlushJobInfo.
+    prev_fc_info_ = info;
+    ASSERT_GT(info.db_name.size(), 0U);
+    ASSERT_GT(info.cf_name.size(), 0U);
+    ASSERT_GT(info.file_path.size(), 0U);
+    ASSERT_GT(info.job_id, 0);
+    ASSERT_GT(info.table_properties.data_size, 0U);
+    ASSERT_GT(info.table_properties.raw_key_size, 0U);
+    ASSERT_GT(info.table_properties.raw_value_size, 0U);
+    ASSERT_GT(info.table_properties.num_data_blocks, 0U);
+    ASSERT_GT(info.table_properties.num_entries, 0U);
+
+#if ROCKSDB_USING_THREAD_STATUS
+    // Verify the id of the current thread that created this table
+    // file matches the id of any active flush or compaction thread.
+    uint64_t thread_id = env_->GetThreadID();
+    std::vector<ThreadStatus> thread_list;
+    ASSERT_OK(env_->GetThreadList(&thread_list));
+    bool found_match = false;
+    for (auto thread_status : thread_list) {
+      if (thread_status.operation_type == ThreadStatus::OP_FLUSH ||
+          thread_status.operation_type == ThreadStatus::OP_COMPACTION) {
+        if (thread_id == thread_status.thread_id) {
+          found_match = true;
+          break;
+        }
+      }
+    }
+    ASSERT_TRUE(found_match);
+#endif  // ROCKSDB_USING_THREAD_STATUS
+  }
+
   void OnFlushCompleted(
-      DB* db, const std::string& name,
-      const std::string& file_path,
-      bool triggered_writes_slowdown,
-      bool triggered_writes_stop) override {
+      DB* db, const FlushJobInfo& info) override {
     flushed_dbs_.push_back(db);
-    flushed_column_family_names_.push_back(name);
-    if (triggered_writes_slowdown) {
+    flushed_column_family_names_.push_back(info.cf_name);
+    if (info.triggered_writes_slowdown) {
       slowdown_count++;
     }
-    if (triggered_writes_stop) {
+    if (info.triggered_writes_stop) {
       stop_count++;
     }
+    // verify whether the previously created file matches the flushed file.
+    ASSERT_EQ(prev_fc_info_.db_name, db->GetName());
+    ASSERT_EQ(prev_fc_info_.cf_name, info.cf_name);
+    ASSERT_EQ(prev_fc_info_.job_id, info.job_id);
+    ASSERT_EQ(prev_fc_info_.file_path, info.file_path);
+    ASSERT_EQ(db->GetEnv()->GetThreadID(), info.thread_id);
+    ASSERT_GT(info.thread_id, 0U);
   }
 
   std::vector<std::string> flushed_column_family_names_;
   std::vector<DB*> flushed_dbs_;
   int slowdown_count;
   int stop_count;
+  bool db_closing;
+  std::atomic_bool db_closed;
+  TableFileCreationInfo prev_fc_info_;
+
+ protected:
+  Env* env_;
 };
 
 TEST_F(EventListenerTest, OnSingleDBFlushTest) {
   Options options;
   options.write_buffer_size = 100000;
-  TestFlushListener* listener = new TestFlushListener();
+#if ROCKSDB_USING_THREAD_STATUS
+  options.enable_thread_tracking = true;
+#endif  // ROCKSDB_USING_THREAD_STATUS
+  TestFlushListener* listener = new TestFlushListener(options.env);
   options.listeners.emplace_back(listener);
   std::vector<std::string> cf_names = {
       "pikachu", "ilya", "muromec", "dobrynia",
@@ -265,7 +322,10 @@ TEST_F(EventListenerTest, OnSingleDBFlushTest) {
 TEST_F(EventListenerTest, MultiCF) {
   Options options;
   options.write_buffer_size = 100000;
-  TestFlushListener* listener = new TestFlushListener();
+#if ROCKSDB_USING_THREAD_STATUS
+  options.enable_thread_tracking = true;
+#endif  // ROCKSDB_USING_THREAD_STATUS
+  TestFlushListener* listener = new TestFlushListener(options.env);
   options.listeners.emplace_back(listener);
   std::vector<std::string> cf_names = {
       "pikachu", "ilya", "muromec", "dobrynia",
@@ -293,18 +353,21 @@ TEST_F(EventListenerTest, MultiCF) {
 }
 
 TEST_F(EventListenerTest, MultiDBMultiListeners) {
+  Options options;
+#if ROCKSDB_USING_THREAD_STATUS
+  options.enable_thread_tracking = true;
+#endif  // ROCKSDB_USING_THREAD_STATUS
   std::vector<TestFlushListener*> listeners;
   const int kNumDBs = 5;
   const int kNumListeners = 10;
   for (int i = 0; i < kNumListeners; ++i) {
-    listeners.emplace_back(new TestFlushListener());
+    listeners.emplace_back(new TestFlushListener(options.env));
   }
 
   std::vector<std::string> cf_names = {
       "pikachu", "ilya", "muromec", "dobrynia",
       "nikitich", "alyosha", "popovich"};
 
-  Options options;
   options.create_if_missing = true;
   for (int i = 0; i < kNumListeners; ++i) {
     options.listeners.emplace_back(listeners[i]);
@@ -355,6 +418,7 @@ TEST_F(EventListenerTest, MultiDBMultiListeners) {
     }
   }
 
+
   for (auto handles : vec_handles) {
     for (auto h : handles) {
       delete h;
@@ -370,11 +434,17 @@ TEST_F(EventListenerTest, MultiDBMultiListeners) {
 
 TEST_F(EventListenerTest, DisableBGCompaction) {
   Options options;
-  TestFlushListener* listener = new TestFlushListener();
+#if ROCKSDB_USING_THREAD_STATUS
+  options.enable_thread_tracking = true;
+#endif  // ROCKSDB_USING_THREAD_STATUS
+  TestFlushListener* listener = new TestFlushListener(options.env);
+  const int kCompactionTrigger = 1;
   const int kSlowdownTrigger = 5;
-  const int kStopTrigger = 10;
+  const int kStopTrigger = 100;
+  options.level0_file_num_compaction_trigger = kCompactionTrigger;
   options.level0_slowdown_writes_trigger = kSlowdownTrigger;
   options.level0_stop_writes_trigger = kStopTrigger;
+  options.max_write_buffer_number = 10;
   options.listeners.emplace_back(listener);
   // BG compaction is disabled.  Number of L0 files will simply keeps
   // increasing in this test.
@@ -383,17 +453,17 @@ TEST_F(EventListenerTest, DisableBGCompaction) {
   options.write_buffer_size = 100000;  // Small write buffer
 
   CreateAndReopenWithCF({"pikachu"}, &options);
-  WriteOptions wopts;
-  wopts.timeout_hint_us = 100000;
   ColumnFamilyMetaData cf_meta;
   db_->GetColumnFamilyMetaData(handles_[1], &cf_meta);
+
   // keep writing until writes are forced to stop.
-  for (int i = 0; static_cast<int>(cf_meta.file_count) < kStopTrigger; ++i) {
-    Put(1, ToString(i), std::string(100000, 'x'), wopts);
+  for (int i = 0; static_cast<int>(cf_meta.file_count) < kSlowdownTrigger * 10;
+       ++i) {
+    Put(1, ToString(i), std::string(10000, 'x'), WriteOptions());
+    db_->Flush(FlushOptions(), handles_[1]);
     db_->GetColumnFamilyMetaData(handles_[1], &cf_meta);
   }
-  ASSERT_GE(listener->slowdown_count, kStopTrigger - kSlowdownTrigger);
-  ASSERT_GE(listener->stop_count, 1);
+  ASSERT_GE(listener->slowdown_count, kSlowdownTrigger * 9);
 }
 
 }  // namespace rocksdb

db/log_reader.cc

@@ -13,6 +13,7 @@
 #include "rocksdb/env.h"
 #include "util/coding.h"
 #include "util/crc32c.h"
+#include "util/file_reader_writer.h"
 
 namespace rocksdb {
 namespace log {
@@ -20,7 +21,7 @@ namespace log {
 Reader::Reporter::~Reporter() {
 }
 
-Reader::Reader(unique_ptr<SequentialFile>&& _file, Reporter* reporter,
+Reader::Reader(unique_ptr<SequentialFileReader>&& _file, Reporter* reporter,
                bool checksum, uint64_t initial_offset)
     : file_(std::move(_file)),
       reporter_(reporter),
@@ -61,7 +62,8 @@ bool Reader::SkipToInitialBlock() {
   return true;
 }
 
-bool Reader::ReadRecord(Slice* record, std::string* scratch) {
+bool Reader::ReadRecord(Slice* record, std::string* scratch,
+                        const bool report_eof_inconsistency) {
   if (last_record_offset_ < initial_offset_) {
     if (!SkipToInitialBlock()) {
       return false;
@@ -78,7 +80,8 @@ bool Reader::ReadRecord(Slice* record, std::string* scratch) {
   Slice fragment;
   while (true) {
     uint64_t physical_record_offset = end_of_buffer_offset_ - buffer_.size();
-    const unsigned int record_type = ReadPhysicalRecord(&fragment);
+    const unsigned int record_type =
+        ReadPhysicalRecord(&fragment, report_eof_inconsistency);
     switch (record_type) {
       case kFullType:
         if (in_fragmented_record && !scratch->empty()) {
@@ -130,6 +133,9 @@ bool Reader::ReadRecord(Slice* record, std::string* scratch) {
 
       case kEof:
         if (in_fragmented_record) {
+          if (report_eof_inconsistency) {
+            ReportCorruption(scratch->size(), "error reading trailing data");
+          }
           // This can be caused by the writer dying immediately after
           //  writing a physical record but before completing the next; don't
           //  treat it as a corruption, just ignore the entire logical record.
@@ -238,7 +244,8 @@ void Reader::ReportDrop(size_t bytes, const Status& reason) {
   }
 }
 
-unsigned int Reader::ReadPhysicalRecord(Slice* result) {
+unsigned int Reader::ReadPhysicalRecord(Slice* result,
+                                        const bool report_eof_inconsistency) {
   while (true) {
     if (buffer_.size() < (size_t)kHeaderSize) {
       if (!eof_ && !read_error_) {
@@ -259,8 +266,11 @@ unsigned int Reader::ReadPhysicalRecord(Slice* result) {
       } else {
         // Note that if buffer_ is non-empty, we have a truncated header at the
         //  end of the file, which can be caused by the writer crashing in the
-        //  middle of writing the header. Instead of considering this an error,
-        //  just report EOF.
+        //  middle of writing the header. Unless explicitly requested we don't
+        //  considering this an error, just report EOF.
+        if (buffer_.size() && report_eof_inconsistency) {
+          ReportCorruption(buffer_.size(), "truncated header");
+        }
         buffer_.clear();
         return kEof;
       }
@@ -281,7 +291,10 @@ unsigned int Reader::ReadPhysicalRecord(Slice* result) {
       }
       // If the end of the file has been reached without reading |length| bytes
       // of payload, assume the writer died in the middle of writing the record.
-      // Don't report a corruption.
+      // Don't report a corruption unless requested.
+      if (drop_size && report_eof_inconsistency) {
+        ReportCorruption(drop_size, "truncated header");
+      }
       return kEof;
     }
 

db/log_reader.h

@@ -17,7 +17,7 @@
 
 namespace rocksdb {
 
-class SequentialFile;
+class SequentialFileReader;
 using std::unique_ptr;
 
 namespace log {
@@ -51,7 +51,7 @@ class Reader {
   //
   // The Reader will start reading at the first record located at physical
   // position >= initial_offset within the file.
-  Reader(unique_ptr<SequentialFile>&& file, Reporter* reporter,
+  Reader(unique_ptr<SequentialFileReader>&& file, Reporter* reporter,
          bool checksum, uint64_t initial_offset);
 
   ~Reader();
@@ -61,7 +61,8 @@ class Reader {
   // "*scratch" as temporary storage.  The contents filled in *record
   // will only be valid until the next mutating operation on this
   // reader or the next mutation to *scratch.
-  bool ReadRecord(Slice* record, std::string* scratch);
+  bool ReadRecord(Slice* record, std::string* scratch,
+                  bool report_eof_inconsistency = false);
 
   // Returns the physical offset of the last record returned by ReadRecord.
   //
@@ -80,10 +81,10 @@ class Reader {
   // block that was partially read.
   void UnmarkEOF();
 
-  SequentialFile* file() { return file_.get(); }
+  SequentialFileReader* file() { return file_.get(); }
 
  private:
-  const unique_ptr<SequentialFile> file_;
+  const unique_ptr<SequentialFileReader> file_;
   Reporter* const reporter_;
   bool const checksum_;
   char* const backing_store_;
@@ -120,7 +121,8 @@ class Reader {
   bool SkipToInitialBlock();
 
   // Return type, or one of the preceding special values
-  unsigned int ReadPhysicalRecord(Slice* result);
+  unsigned int ReadPhysicalRecord(Slice* result,
+                                  bool report_eof_inconsistency = false);
 
   // Reports dropped bytes to the reporter.
   // buffer_ must be updated to remove the dropped bytes prior to invocation.

db/log_test.cc

@@ -12,8 +12,10 @@
 #include "rocksdb/env.h"
 #include "util/coding.h"
 #include "util/crc32c.h"
+#include "util/file_reader_writer.h"
 #include "util/random.h"
 #include "util/testharness.h"
+#include "util/testutil.h"
 
 namespace rocksdb {
 namespace log {
@@ -43,46 +45,6 @@ static std::string RandomSkewedString(int i, Random* rnd) {
 
 class LogTest : public testing::Test {
  private:
-  class StringDest : public WritableFile {
-   public:
-    std::string contents_;
-
-    explicit StringDest(Slice& reader_contents) :
-      WritableFile(),
-      contents_(""),
-      reader_contents_(reader_contents),
-      last_flush_(0) {
-      reader_contents_ = Slice(contents_.data(), 0);
-    };
-
-    virtual Status Close() override { return Status::OK(); }
-    virtual Status Flush() override {
-      EXPECT_TRUE(reader_contents_.size() <= last_flush_);
-      size_t offset = last_flush_ - reader_contents_.size();
-      reader_contents_ = Slice(
-          contents_.data() + offset,
-          contents_.size() - offset);
-      last_flush_ = contents_.size();
-
-      return Status::OK();
-    }
-    virtual Status Sync() override { return Status::OK(); }
-    virtual Status Append(const Slice& slice) override {
-      contents_.append(slice.data(), slice.size());
-      return Status::OK();
-    }
-    void Drop(size_t bytes) {
-      contents_.resize(contents_.size() - bytes);
-      reader_contents_ = Slice(
-          reader_contents_.data(), reader_contents_.size() - bytes);
-      last_flush_ = contents_.size();
-    }
-
-   private:
-    Slice& reader_contents_;
-    size_t last_flush_;
-  };
-
   class StringSource : public SequentialFile {
    public:
     Slice& contents_;
@@ -163,26 +125,28 @@ class LogTest : public testing::Test {
   };
 
   std::string& dest_contents() {
-    auto dest = dynamic_cast<StringDest*>(writer_.file());
+    auto dest =
+      dynamic_cast<test::StringSink*>(writer_.file()->writable_file());
     assert(dest);
     return dest->contents_;
   }
 
   const std::string& dest_contents() const {
-    auto dest = dynamic_cast<const StringDest*>(writer_.file());
+    auto dest =
+      dynamic_cast<const test::StringSink*>(writer_.file()->writable_file());
     assert(dest);
     return dest->contents_;
   }
 
   void reset_source_contents() {
-    auto src = dynamic_cast<StringSource*>(reader_.file());
+    auto src = dynamic_cast<StringSource*>(reader_.file()->file());
     assert(src);
     src->contents_ = dest_contents();
   }
 
   Slice reader_contents_;
-  unique_ptr<StringDest> dest_holder_;
-  unique_ptr<StringSource> source_holder_;
+  unique_ptr<WritableFileWriter> dest_holder_;
+  unique_ptr<SequentialFileReader> source_holder_;
   ReportCollector report_;
   Writer writer_;
   Reader reader_;
@@ -192,13 +156,16 @@ class LogTest : public testing::Test {
   static uint64_t initial_offset_last_record_offsets_[];
 
  public:
-  LogTest() : reader_contents_(),
-              dest_holder_(new StringDest(reader_contents_)),
-              source_holder_(new StringSource(reader_contents_)),
-              writer_(std::move(dest_holder_)),
-              reader_(std::move(source_holder_), &report_, true/*checksum*/,
-                      0/*initial_offset*/) {
-  }
+  LogTest()
+      : reader_contents_(),
+        dest_holder_(
+            test::GetWritableFileWriter(
+              new test::StringSink(&reader_contents_))),
+        source_holder_(
+            test::GetSequentialFileReader(new StringSource(reader_contents_))),
+        writer_(std::move(dest_holder_)),
+        reader_(std::move(source_holder_), &report_, true /*checksum*/,
+                0 /*initial_offset*/) {}
 
   void Write(const std::string& msg) {
     writer_.AddRecord(Slice(msg));
@@ -208,10 +175,10 @@ class LogTest : public testing::Test {
     return dest_contents().size();
   }
 
-  std::string Read() {
+  std::string Read(const bool report_eof_inconsistency = false) {
     std::string scratch;
     Slice record;
-    if (reader_.ReadRecord(&record, &scratch)) {
+    if (reader_.ReadRecord(&record, &scratch, report_eof_inconsistency)) {
       return record.ToString();
     } else {
       return "EOF";
@@ -227,7 +194,8 @@ class LogTest : public testing::Test {
   }
 
   void ShrinkSize(int bytes) {
-    auto dest = dynamic_cast<StringDest*>(writer_.file());
+    auto dest =
+      dynamic_cast<test::StringSink*>(writer_.file()->writable_file());
     assert(dest);
     dest->Drop(bytes);
   }
@@ -240,7 +208,7 @@ class LogTest : public testing::Test {
   }
 
   void ForceError(size_t position = 0) {
-    auto src = dynamic_cast<StringSource*>(reader_.file());
+    auto src = dynamic_cast<StringSource*>(reader_.file()->file());
     src->force_error_ = true;
     src->force_error_position_ = position;
   }
@@ -254,13 +222,13 @@ class LogTest : public testing::Test {
   }
 
   void ForceEOF(size_t position = 0) {
-    auto src = dynamic_cast<StringSource*>(reader_.file());
+    auto src = dynamic_cast<StringSource*>(reader_.file()->file());
     src->force_eof_ = true;
     src->force_eof_position_ = position;
   }
 
   void UnmarkEOF() {
-    auto src = dynamic_cast<StringSource*>(reader_.file());
+    auto src = dynamic_cast<StringSource*>(reader_.file()->file());
     src->returned_partial_ = false;
     reader_.UnmarkEOF();
   }
@@ -288,10 +256,11 @@ class LogTest : public testing::Test {
 
   void CheckOffsetPastEndReturnsNoRecords(uint64_t offset_past_end) {
     WriteInitialOffsetLog();
-    unique_ptr<StringSource> source(new StringSource(reader_contents_));
+    unique_ptr<SequentialFileReader> file_reader(
+        test::GetSequentialFileReader(new StringSource(reader_contents_)));
     unique_ptr<Reader> offset_reader(
-      new Reader(std::move(source), &report_, true/*checksum*/,
-                 WrittenBytes() + offset_past_end));
+        new Reader(std::move(file_reader), &report_, true /*checksum*/,
+                   WrittenBytes() + offset_past_end));
     Slice record;
     std::string scratch;
     ASSERT_TRUE(!offset_reader->ReadRecord(&record, &scratch));
@@ -300,10 +269,10 @@ class LogTest : public testing::Test {
   void CheckInitialOffsetRecord(uint64_t initial_offset,
                                 int expected_record_offset) {
     WriteInitialOffsetLog();
-    unique_ptr<StringSource> source(new StringSource(reader_contents_));
-    unique_ptr<Reader> offset_reader(
-      new Reader(std::move(source), &report_, true/*checksum*/,
-                 initial_offset));
+    unique_ptr<SequentialFileReader> file_reader(
+        test::GetSequentialFileReader(new StringSource(reader_contents_)));
+    unique_ptr<Reader> offset_reader(new Reader(
+        std::move(file_reader), &report_, true /*checksum*/, initial_offset));
     Slice record;
     std::string scratch;
     ASSERT_TRUE(offset_reader->ReadRecord(&record, &scratch));
@@ -452,6 +421,15 @@ TEST_F(LogTest, TruncatedTrailingRecordIsIgnored) {
   ASSERT_EQ("", ReportMessage());
 }
 
+TEST_F(LogTest, TruncatedTrailingRecordIsNotIgnored) {
+  Write("foo");
+  ShrinkSize(4);  // Drop all payload as well as a header byte
+  ASSERT_EQ("EOF", Read(/*report_eof_inconsistency*/ true));
+  // Truncated last record is ignored, not treated as an error
+  ASSERT_GT(DroppedBytes(), 0U);
+  ASSERT_EQ("OK", MatchError("Corruption: truncated header"));
+}
+
 TEST_F(LogTest, BadLength) {
   const int kPayloadSize = kBlockSize - kHeaderSize;
   Write(BigString("bar", kPayloadSize));
@@ -471,6 +449,14 @@ TEST_F(LogTest, BadLengthAtEndIsIgnored) {
   ASSERT_EQ("", ReportMessage());
 }
 
+TEST_F(LogTest, BadLengthAtEndIsNotIgnored) {
+  Write("foo");
+  ShrinkSize(1);
+  ASSERT_EQ("EOF", Read(/*report_eof_inconsistency=*/true));
+  ASSERT_GT(DroppedBytes(), 0U);
+  ASSERT_EQ("OK", MatchError("Corruption: truncated header"));
+}
+
 TEST_F(LogTest, ChecksumMismatch) {
   Write("foo");
   IncrementByte(0, 10);
@@ -528,6 +514,15 @@ TEST_F(LogTest, MissingLastIsIgnored) {
   ASSERT_EQ(0U, DroppedBytes());
 }
 
+TEST_F(LogTest, MissingLastIsNotIgnored) {
+  Write(BigString("bar", kBlockSize));
+  // Remove the LAST block, including header.
+  ShrinkSize(14);
+  ASSERT_EQ("EOF", Read(/*report_eof_inconsistency=*/true));
+  ASSERT_GT(DroppedBytes(), 0U);
+  ASSERT_EQ("OK", MatchError("Corruption: error reading trailing data"));
+}
+
 TEST_F(LogTest, PartialLastIsIgnored) {
   Write(BigString("bar", kBlockSize));
   // Cause a bad record length in the LAST block.
@@ -537,6 +532,17 @@ TEST_F(LogTest, PartialLastIsIgnored) {
   ASSERT_EQ(0U, DroppedBytes());
 }
 
+TEST_F(LogTest, PartialLastIsNotIgnored) {
+  Write(BigString("bar", kBlockSize));
+  // Cause a bad record length in the LAST block.
+  ShrinkSize(1);
+  ASSERT_EQ("EOF", Read(/*report_eof_inconsistency=*/true));
+  ASSERT_GT(DroppedBytes(), 0U);
+  ASSERT_EQ("OK", MatchError(
+                      "Corruption: truncated headerCorruption: "
+                      "error reading trailing data"));
+}
+
 TEST_F(LogTest, ErrorJoinsRecords) {
   // Consider two fragmented records:
   //    first(R1) last(R1) first(R2) last(R2)

db/log_writer.cc

@@ -13,13 +13,13 @@
 #include "rocksdb/env.h"
 #include "util/coding.h"
 #include "util/crc32c.h"
+#include "util/file_reader_writer.h"
 
 namespace rocksdb {
 namespace log {
 
-Writer::Writer(unique_ptr<WritableFile>&& dest)
-    : dest_(std::move(dest)),
-      block_offset_(0) {
+Writer::Writer(unique_ptr<WritableFileWriter>&& dest)
+    : dest_(std::move(dest)), block_offset_(0) {
   for (int i = 0; i <= kMaxRecordType; i++) {
     char t = static_cast<char>(i);
     type_crc_[i] = crc32c::Value(&t, 1);

db/log_writer.h

@@ -16,7 +16,7 @@
 
 namespace rocksdb {
 
-class WritableFile;
+class WritableFileWriter;
 
 using std::unique_ptr;
 
@@ -61,16 +61,16 @@ class Writer {
   // Create a writer that will append data to "*dest".
   // "*dest" must be initially empty.
   // "*dest" must remain live while this Writer is in use.
-  explicit Writer(unique_ptr<WritableFile>&& dest);
+  explicit Writer(unique_ptr<WritableFileWriter>&& dest);
   ~Writer();
 
   Status AddRecord(const Slice& slice);
 
-  WritableFile* file() { return dest_.get(); }
-  const WritableFile* file() const { return dest_.get(); }
+  WritableFileWriter* file() { return dest_.get(); }
+  const WritableFileWriter* file() const { return dest_.get(); }
 
  private:
-  unique_ptr<WritableFile> dest_;
+  unique_ptr<WritableFileWriter> dest_;
   int block_offset_;       // Current offset in block
 
   // crc32c values for all supported record types.  These are

db/managed_iterator.cc

@@ -93,6 +93,7 @@ ManagedIterator::~ManagedIterator() {
     snapshot_created_ = false;
     read_options_.snapshot = nullptr;
   }
+  UnLock();
 }
 
 bool ManagedIterator::Valid() const { return valid_; }

db/memtable.cc

@@ -54,7 +54,7 @@ MemTableOptions::MemTableOptions(
 MemTable::MemTable(const InternalKeyComparator& cmp,
                    const ImmutableCFOptions& ioptions,
                    const MutableCFOptions& mutable_cf_options,
-                   WriteBuffer* write_buffer)
+                   WriteBuffer* write_buffer, SequenceNumber earliest_seq)
     : comparator_(cmp),
       moptions_(ioptions, mutable_cf_options),
       refs_(0),
@@ -64,12 +64,14 @@ MemTable::MemTable(const InternalKeyComparator& cmp,
       table_(ioptions.memtable_factory->CreateMemTableRep(
           comparator_, &allocator_, ioptions.prefix_extractor,
           ioptions.info_log)),
+      data_size_(0),
       num_entries_(0),
       num_deletes_(0),
       flush_in_progress_(false),
       flush_completed_(false),
       file_number_(0),
       first_seqno_(0),
+      earliest_seqno_(earliest_seq),
       mem_next_logfile_number_(0),
       locks_(moptions_.inplace_update_support
                  ? moptions_.inplace_update_num_locks
@@ -289,6 +291,26 @@ port::RWMutex* MemTable::GetLock(const Slice& key) {
   return &locks_[hash(key) % locks_.size()];
 }
 
+uint64_t MemTable::ApproximateSize(const Slice& start_ikey,
+                                   const Slice& end_ikey) {
+  uint64_t entry_count = table_->ApproximateNumEntries(start_ikey, end_ikey);
+  if (entry_count == 0) {
+    return 0;
+  }
+  uint64_t n = num_entries_.load(std::memory_order_relaxed);
+  if (n == 0) {
+    return 0;
+  }
+  if (entry_count > n) {
+    // table_->ApproximateNumEntries() is just an estimate so it can be larger
+    // than actual entries we have. Cap it to entries we have to limit the
+    // inaccuracy.
+    entry_count = n;
+  }
+  uint64_t data_size = data_size_.load(std::memory_order_relaxed);
+  return entry_count * (data_size / n);
+}
+
 void MemTable::Add(SequenceNumber s, ValueType type,
                    const Slice& key, /* user key */
                    const Slice& value) {
@@ -309,13 +331,17 @@ void MemTable::Add(SequenceNumber s, ValueType type,
   char* p = EncodeVarint32(buf, internal_key_size);
   memcpy(p, key.data(), key_size);
   p += key_size;
-  EncodeFixed64(p, (s << 8) | type);
+  uint64_t packed = PackSequenceAndType(s, type);
+  EncodeFixed64(p, packed);
   p += 8;
   p = EncodeVarint32(p, val_size);
   memcpy(p, value.data(), val_size);
   assert((unsigned)(p + val_size - buf) == (unsigned)encoded_len);
   table_->Insert(handle);
-  num_entries_++;
+  num_entries_.store(num_entries_.load(std::memory_order_relaxed) + 1,
+                     std::memory_order_relaxed);
+  data_size_.store(data_size_.load(std::memory_order_relaxed) + encoded_len,
+                   std::memory_order_relaxed);
   if (type == kTypeDeletion) {
     num_deletes_++;
   }
@@ -329,6 +355,11 @@ void MemTable::Add(SequenceNumber s, ValueType type,
   assert(first_seqno_ == 0 || s > first_seqno_);
   if (first_seqno_ == 0) {
     first_seqno_ = s;
+
+    if (earliest_seqno_ == kMaxSequenceNumber) {
+      earliest_seqno_ = first_seqno_;
+    }
+    assert(first_seqno_ >= earliest_seqno_);
   }
 
   should_flush_ = ShouldFlushNow();
@@ -343,6 +374,7 @@ struct Saver {
   bool* found_final_value;  // Is value set correctly? Used by KeyMayExist
   bool* merge_in_progress;
   std::string* value;
+  SequenceNumber seq;
   const MergeOperator* merge_operator;
   // the merge operations encountered;
   MergeContext* merge_context;
@@ -376,7 +408,10 @@ static bool SaveValue(void* arg, const char* entry) {
           Slice(key_ptr, key_length - 8), s->key->user_key()) == 0) {
     // Correct user key
     const uint64_t tag = DecodeFixed64(key_ptr + key_length - 8);
-    switch (static_cast<ValueType>(tag & 0xff)) {
+    ValueType type;
+    UnPackSequenceAndType(tag, &s->seq, &type);
+
+    switch (type) {
       case kTypeValue: {
         if (s->inplace_update_support) {
           s->mem->GetLock(s->key->user_key())->ReadLock();
@@ -461,7 +496,7 @@ static bool SaveValue(void* arg, const char* entry) {
 }
 
 bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
-                   MergeContext* merge_context) {
+                   MergeContext* merge_context, SequenceNumber* seq) {
   // The sequence number is updated synchronously in version_set.h
   if (IsEmpty()) {
     // Avoiding recording stats for speed.
@@ -476,6 +511,7 @@ bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
   if (prefix_bloom_ &&
       !prefix_bloom_->MayContain(prefix_extractor_->Transform(user_key))) {
     // iter is null if prefix bloom says the key does not exist
+    *seq = kMaxSequenceNumber;
   } else {
     Saver saver;
     saver.status = s;
@@ -483,7 +519,7 @@ bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
     saver.merge_in_progress = &merge_in_progress;
     saver.key = &key;
     saver.value = value;
-    saver.status = s;
+    saver.seq = kMaxSequenceNumber;
     saver.mem = this;
     saver.merge_context = merge_context;
     saver.merge_operator = moptions_.merge_operator;
@@ -492,6 +528,8 @@ bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
     saver.statistics = moptions_.statistics;
     saver.env_ = env_;
     table_->Get(key, &saver, SaveValue);
+
+    *seq = saver.seq;
   }
 
   // No change to value, since we have not yet found a Put/Delete
@@ -529,7 +567,10 @@ void MemTable::Update(SequenceNumber seq,
         Slice(key_ptr, key_length - 8), lkey.user_key()) == 0) {
       // Correct user key
       const uint64_t tag = DecodeFixed64(key_ptr + key_length - 8);
-      switch (static_cast<ValueType>(tag & 0xff)) {
+      ValueType type;
+      SequenceNumber unused;
+      UnPackSequenceAndType(tag, &unused, &type);
+      switch (type) {
         case kTypeValue: {
           Slice prev_value = GetLengthPrefixedSlice(key_ptr + key_length);
           uint32_t prev_size = static_cast<uint32_t>(prev_value.size());
@@ -587,7 +628,10 @@ bool MemTable::UpdateCallback(SequenceNumber seq,
         Slice(key_ptr, key_length - 8), lkey.user_key()) == 0) {
       // Correct user key
       const uint64_t tag = DecodeFixed64(key_ptr + key_length - 8);
-      switch (static_cast<ValueType>(tag & 0xff)) {
+      ValueType type;
+      uint64_t unused;
+      UnPackSequenceAndType(tag, &unused, &type);
+      switch (type) {
         case kTypeValue: {
           Slice prev_value = GetLengthPrefixedSlice(key_ptr + key_length);
           uint32_t prev_size = static_cast<uint32_t>(prev_value.size());
@@ -657,7 +701,10 @@ size_t MemTable::CountSuccessiveMergeEntries(const LookupKey& key) {
     }
 
     const uint64_t tag = DecodeFixed64(iter_key_ptr + key_length - 8);
-    if (static_cast<ValueType>(tag & 0xff) != kTypeMerge) {
+    ValueType type;
+    uint64_t unused;
+    UnPackSequenceAndType(tag, &unused, &type);
+    if (type != kTypeMerge) {
       break;
     }
 

db/memtable.h

@@ -80,10 +80,17 @@ class MemTable {
 
   // MemTables are reference counted.  The initial reference count
   // is zero and the caller must call Ref() at least once.
+  //
+  // earliest_seq should be the current SequenceNumber in the db such that any
+  // key inserted into this memtable will have an equal or larger seq number.
+  // (When a db is first created, the earliest sequence number will be 0).
+  // If the earliest sequence number is not known, kMaxSequenceNumber may be
+  // used, but this may prevent some transactions from succeeding until the
+  // first key is inserted into the memtable.
   explicit MemTable(const InternalKeyComparator& comparator,
                     const ImmutableCFOptions& ioptions,
                     const MutableCFOptions& mutable_cf_options,
-                    WriteBuffer* write_buffer);
+                    WriteBuffer* write_buffer, SequenceNumber earliest_seq);
 
   // Do not delete this MemTable unless Unref() indicates it not in use.
   ~MemTable();
@@ -153,8 +160,19 @@ class MemTable {
   //   prepend the current merge operand to *operands.
   //   store MergeInProgress in s, and return false.
   // Else, return false.
+  // If any operation was found, its most recent sequence number
+  // will be stored in *seq on success (regardless of whether true/false is
+  // returned).  Otherwise, *seq will be set to kMaxSequenceNumber.
+  // On success, *s may be set to OK, NotFound, or MergeInProgress.  Any other
+  // status returned indicates a corruption or other unexpected error.
   bool Get(const LookupKey& key, std::string* value, Status* s,
-           MergeContext* merge_context);
+           MergeContext* merge_context, SequenceNumber* seq);
+
+  bool Get(const LookupKey& key, std::string* value, Status* s,
+           MergeContext* merge_context) {
+    SequenceNumber seq;
+    return Get(key, value, s, merge_context, &seq);
+  }
 
   // Attempts to update the new_value inplace, else does normal Add
   // Pseudocode
@@ -194,7 +212,9 @@ class MemTable {
   // Get total number of entries in the mem table.
   // REQUIRES: external synchronization to prevent simultaneous
   // operations on the same MemTable (unless this Memtable is immutable).
-  uint64_t num_entries() const { return num_entries_; }
+  uint64_t num_entries() const {
+    return num_entries_.load(std::memory_order_relaxed);
+  }
 
   // Get total number of deletes in the mem table.
   // REQUIRES: external synchronization to prevent simultaneous
@@ -215,6 +235,15 @@ class MemTable {
   // operations on the same MemTable (unless this Memtable is immutable).
   SequenceNumber GetFirstSequenceNumber() { return first_seqno_; }
 
+  // Returns the sequence number that is guaranteed to be smaller than or equal
+  // to the sequence number of any key that could be inserted into this
+  // memtable. It can then be assumed that any write with a larger(or equal)
+  // sequence number will be present in this memtable or a later memtable.
+  //
+  // If the earliest sequence number could not be determined,
+  // kMaxSequenceNumber will be returned.
+  SequenceNumber GetEarliestSequenceNumber() { return earliest_seqno_; }
+
   // Returns the next active logfile number when this memtable is about to
   // be flushed to storage
   // REQUIRES: external synchronization to prevent simultaneous
@@ -248,6 +277,8 @@ class MemTable {
     return table_->IsSnapshotSupported() && !moptions_.inplace_update_support;
   }
 
+  uint64_t ApproximateSize(const Slice& start_ikey, const Slice& end_ikey);
+
   // Get the lock associated for the key
   port::RWMutex* GetLock(const Slice& key);
 
@@ -273,7 +304,9 @@ class MemTable {
   MemTableAllocator allocator_;
   unique_ptr<MemTableRep> table_;
 
-  uint64_t num_entries_;
+  // Total data size of all data inserted
+  std::atomic<uint64_t> data_size_;
+  std::atomic<uint64_t> num_entries_;
   uint64_t num_deletes_;
 
   // These are used to manage memtable flushes to storage
@@ -288,6 +321,10 @@ class MemTable {
   // The sequence number of the kv that was inserted first
   SequenceNumber first_seqno_;
 
+  // The db sequence number at the time of creation or kMaxSequenceNumber
+  // if not set.
+  SequenceNumber earliest_seqno_;
+
   // The log files earlier than this number can be deleted.
   uint64_t mem_next_logfile_number_;
 

db/memtable_list.cc

@@ -27,16 +27,27 @@ class InternalKeyComparator;
 class Mutex;
 class VersionSet;
 
-MemTableListVersion::MemTableListVersion(MemTableListVersion* old) {
+MemTableListVersion::MemTableListVersion(MemTableListVersion* old)
+    : max_write_buffer_number_to_maintain_(
+          old->max_write_buffer_number_to_maintain_) {
   if (old != nullptr) {
     memlist_ = old->memlist_;
-    size_ = old->size_;
     for (auto& m : memlist_) {
       m->Ref();
     }
+
+    memlist_history_ = old->memlist_history_;
+    for (auto& m : memlist_history_) {
+      m->Ref();
+    }
   }
 }
 
+MemTableListVersion::MemTableListVersion(
+    int max_write_buffer_number_to_maintain)
+    : max_write_buffer_number_to_maintain_(
+          max_write_buffer_number_to_maintain) {}
+
 void MemTableListVersion::Ref() { ++refs_; }
 
 void MemTableListVersion::Unref(autovector<MemTable*>* to_delete) {
@@ -52,25 +63,62 @@ void MemTableListVersion::Unref(autovector<MemTable*>* to_delete) {
         to_delete->push_back(x);
       }
     }
+    for (const auto& m : memlist_history_) {
+      MemTable* x = m->Unref();
+      if (x != nullptr) {
+        to_delete->push_back(x);
+      }
+    }
     delete this;
   }
 }
 
-int MemTableListVersion::size() const { return size_; }
+int MemTableList::NumNotFlushed() const {
+  int size = static_cast<int>(current_->memlist_.size());
+  assert(num_flush_not_started_ <= size);
+  return size;
+}
 
-// Returns the total number of memtables in the list
-int MemTableList::size() const {
-  assert(num_flush_not_started_ <= current_->size_);
-  return current_->size_;
+int MemTableList::NumFlushed() const {
+  return static_cast<int>(current_->memlist_history_.size());
 }
 
 // Search all the memtables starting from the most recent one.
 // Return the most recent value found, if any.
 // Operands stores the list of merge operations to apply, so far.
 bool MemTableListVersion::Get(const LookupKey& key, std::string* value,
-                              Status* s, MergeContext* merge_context) {
-  for (auto& memtable : memlist_) {
-    if (memtable->Get(key, value, s, merge_context)) {
+                              Status* s, MergeContext* merge_context,
+                              SequenceNumber* seq) {
+  return GetFromList(&memlist_, key, value, s, merge_context, seq);
+}
+
+bool MemTableListVersion::GetFromHistory(const LookupKey& key,
+                                         std::string* value, Status* s,
+                                         MergeContext* merge_context,
+                                         SequenceNumber* seq) {
+  return GetFromList(&memlist_history_, key, value, s, merge_context, seq);
+}
+
+bool MemTableListVersion::GetFromList(std::list<MemTable*>* list,
+                                      const LookupKey& key, std::string* value,
+                                      Status* s, MergeContext* merge_context,
+                                      SequenceNumber* seq) {
+  *seq = kMaxSequenceNumber;
+
+  for (auto& memtable : *list) {
+    SequenceNumber current_seq = kMaxSequenceNumber;
+
+    bool done = memtable->Get(key, value, s, merge_context, &current_seq);
+    if (*seq == kMaxSequenceNumber) {
+      // Store the most recent sequence number of any operation on this key.
+      // Since we only care about the most recent change, we only need to
+      // return the first operation found when searching memtables in
+      // reverse-chronological order.
+      *seq = current_seq;
+    }
+
+    if (done) {
+      assert(*seq != kMaxSequenceNumber);
       return true;
     }
   }
@@ -101,6 +149,15 @@ uint64_t MemTableListVersion::GetTotalNumEntries() const {
   return total_num;
 }
 
+uint64_t MemTableListVersion::ApproximateSize(const Slice& start_ikey,
+                                              const Slice& end_ikey) {
+  uint64_t total_size = 0;
+  for (auto& m : memlist_) {
+    total_size += m->ApproximateSize(start_ikey, end_ikey);
+  }
+  return total_size;
+}
+
 uint64_t MemTableListVersion::GetTotalNumDeletes() const {
   uint64_t total_num = 0;
   for (auto& m : memlist_) {
@@ -109,18 +166,53 @@ uint64_t MemTableListVersion::GetTotalNumDeletes() const {
   return total_num;
 }
 
-// caller is responsible for referencing m
-void MemTableListVersion::Add(MemTable* m) {
-  assert(refs_ == 1);  // only when refs_ == 1 is MemTableListVersion mutable
-  memlist_.push_front(m);
-  ++size_;
+SequenceNumber MemTableListVersion::GetEarliestSequenceNumber(
+    bool include_history) const {
+  if (include_history && !memlist_history_.empty()) {
+    return memlist_history_.back()->GetEarliestSequenceNumber();
+  } else if (!memlist_.empty()) {
+    return memlist_.back()->GetEarliestSequenceNumber();
+  } else {
+    return kMaxSequenceNumber;
+  }
 }
 
-// caller is responsible for unreferencing m
-void MemTableListVersion::Remove(MemTable* m) {
+// caller is responsible for referencing m
+void MemTableListVersion::Add(MemTable* m, autovector<MemTable*>* to_delete) {
+  assert(refs_ == 1);  // only when refs_ == 1 is MemTableListVersion mutable
+  memlist_.push_front(m);
+
+  TrimHistory(to_delete);
+}
+
+// Removes m from list of memtables not flushed.  Caller should NOT Unref m.
+void MemTableListVersion::Remove(MemTable* m,
+                                 autovector<MemTable*>* to_delete) {
   assert(refs_ == 1);  // only when refs_ == 1 is MemTableListVersion mutable
   memlist_.remove(m);
-  --size_;
+
+  if (max_write_buffer_number_to_maintain_ > 0) {
+    memlist_history_.push_front(m);
+    TrimHistory(to_delete);
+  } else {
+    if (m->Unref()) {
+      to_delete->push_back(m);
+    }
+  }
+}
+
+// Make sure we don't use up too much space in history
+void MemTableListVersion::TrimHistory(autovector<MemTable*>* to_delete) {
+  while (memlist_.size() + memlist_history_.size() >
+             static_cast<size_t>(max_write_buffer_number_to_maintain_) &&
+         !memlist_history_.empty()) {
+    MemTable* x = memlist_history_.back();
+    memlist_history_.pop_back();
+
+    if (x->Unref()) {
+      to_delete->push_back(x);
+    }
+  }
 }
 
 // Returns true if there is at least one memtable on which flush has
@@ -229,12 +321,8 @@ Status MemTableList::InstallMemtableFlushResults(
         LogToBuffer(log_buffer, "[%s] Level-0 commit table #%" PRIu64
                                 ": memtable #%" PRIu64 " done",
                     cfd->GetName().c_str(), m->file_number_, mem_id);
-        current_->Remove(m);
         assert(m->file_number_ > 0);
-
-        if (m->Unref() != nullptr) {
-          to_delete->push_back(m);
-        }
+        current_->Remove(m, to_delete);
       } else {
         //commit failed. setup state so that we can flush again.
         LogToBuffer(log_buffer, "Level-0 commit table #%" PRIu64
@@ -256,15 +344,15 @@ Status MemTableList::InstallMemtableFlushResults(
 }
 
 // New memtables are inserted at the front of the list.
-void MemTableList::Add(MemTable* m) {
-  assert(current_->size_ >= num_flush_not_started_);
+void MemTableList::Add(MemTable* m, autovector<MemTable*>* to_delete) {
+  assert(static_cast<int>(current_->memlist_.size()) >= num_flush_not_started_);
   InstallNewVersion();
   // this method is used to move mutable memtable into an immutable list.
   // since mutable memtable is already refcounted by the DBImpl,
   // and when moving to the imutable list we don't unref it,
   // we don't have to ref the memtable here. we just take over the
   // reference from the DBImpl.
-  current_->Add(m);
+  current_->Add(m, to_delete);
   m->MarkImmutable();
   num_flush_not_started_++;
   if (num_flush_not_started_ == 1) {

db/memtable_list.h

@@ -21,6 +21,7 @@
 #include "rocksdb/db.h"
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
+#include "rocksdb/types.h"
 #include "util/autovector.h"
 #include "util/instrumented_mutex.h"
 #include "util/log_buffer.h"
@@ -41,16 +42,37 @@ class MergeIteratorBuilder;
 class MemTableListVersion {
  public:
   explicit MemTableListVersion(MemTableListVersion* old = nullptr);
+  explicit MemTableListVersion(int max_write_buffer_number_to_maintain);
 
   void Ref();
   void Unref(autovector<MemTable*>* to_delete = nullptr);
 
-  int size() const;
-
   // Search all the memtables starting from the most recent one.
   // Return the most recent value found, if any.
+  //
+  // If any operation was found for this key, its most recent sequence number
+  // will be stored in *seq on success (regardless of whether true/false is
+  // returned).  Otherwise, *seq will be set to kMaxSequenceNumber.
   bool Get(const LookupKey& key, std::string* value, Status* s,
-           MergeContext* merge_context);
+           MergeContext* merge_context, SequenceNumber* seq);
+
+  bool Get(const LookupKey& key, std::string* value, Status* s,
+           MergeContext* merge_context) {
+    SequenceNumber seq;
+    return Get(key, value, s, merge_context, &seq);
+  }
+
+  // Similar to Get(), but searches the Memtable history of memtables that
+  // have already been flushed.  Should only be used from in-memory only
+  // queries (such as Transaction validation) as the history may contain
+  // writes that are also present in the SST files.
+  bool GetFromHistory(const LookupKey& key, std::string* value, Status* s,
+                      MergeContext* merge_context, SequenceNumber* seq);
+  bool GetFromHistory(const LookupKey& key, std::string* value, Status* s,
+                      MergeContext* merge_context) {
+    SequenceNumber seq;
+    return GetFromHistory(key, value, s, merge_context, &seq);
+  }
 
   void AddIterators(const ReadOptions& options,
                     std::vector<Iterator*>* iterator_list, Arena* arena);
@@ -62,15 +84,39 @@ class MemTableListVersion {
 
   uint64_t GetTotalNumDeletes() const;
 
+  uint64_t ApproximateSize(const Slice& start_ikey, const Slice& end_ikey);
+
+  // Returns the value of MemTable::GetEarliestSequenceNumber() on the most
+  // recent MemTable in this list or kMaxSequenceNumber if the list is empty.
+  // If include_history=true, will also search Memtables in MemTableList
+  // History.
+  SequenceNumber GetEarliestSequenceNumber(bool include_history = false) const;
+
  private:
-  // REQUIRE: m is mutable memtable
-  void Add(MemTable* m);
-  // REQUIRE: m is mutable memtable
-  void Remove(MemTable* m);
+  // REQUIRE: m is an immutable memtable
+  void Add(MemTable* m, autovector<MemTable*>* to_delete);
+  // REQUIRE: m is an immutable memtable
+  void Remove(MemTable* m, autovector<MemTable*>* to_delete);
+
+  void TrimHistory(autovector<MemTable*>* to_delete);
+
+  bool GetFromList(std::list<MemTable*>* list, const LookupKey& key,
+                   std::string* value, Status* s, MergeContext* merge_context,
+                   SequenceNumber* seq);
 
   friend class MemTableList;
+
+  // Immutable MemTables that have not yet been flushed.
   std::list<MemTable*> memlist_;
-  int size_ = 0;
+
+  // MemTables that have already been flushed
+  // (used during Transaction validation)
+  std::list<MemTable*> memlist_history_;
+
+  // Maximum number of MemTables to keep in memory (including both flushed
+  // and not-yet-flushed tables).
+  const int max_write_buffer_number_to_maintain_;
+
   int refs_ = 0;
 };
 
@@ -88,10 +134,11 @@ class MemTableListVersion {
 class MemTableList {
  public:
   // A list of memtables.
-  explicit MemTableList(int min_write_buffer_number_to_merge)
+  explicit MemTableList(int min_write_buffer_number_to_merge,
+                        int max_write_buffer_number_to_maintain)
       : imm_flush_needed(false),
         min_write_buffer_number_to_merge_(min_write_buffer_number_to_merge),
-        current_(new MemTableListVersion()),
+        current_(new MemTableListVersion(max_write_buffer_number_to_maintain)),
         num_flush_not_started_(0),
         commit_in_progress_(false),
         flush_requested_(false) {
@@ -108,8 +155,13 @@ class MemTableList {
   // determine whether there is anything more to start flushing.
   std::atomic<bool> imm_flush_needed;
 
-  // Returns the total number of memtables in the list
-  int size() const;
+  // Returns the total number of memtables in the list that haven't yet
+  // been flushed and logged.
+  int NumNotFlushed() const;
+
+  // Returns total number of memtables in the list that have been
+  // completely flushed and logged.
+  int NumFlushed() const;
 
   // Returns true if there is at least one memtable on which flush has
   // not yet started.
@@ -133,7 +185,7 @@ class MemTableList {
 
   // New memtables are inserted at the front of the list.
   // Takes ownership of the referenced held on *m by the caller of Add().
-  void Add(MemTable* m);
+  void Add(MemTable* m, autovector<MemTable*>* to_delete);
 
   // Returns an estimate of the number of bytes of data in use.
   size_t ApproximateMemoryUsage();
@@ -153,7 +205,7 @@ class MemTableList {
   // DB mutex held
   void InstallNewVersion();
 
-  int min_write_buffer_number_to_merge_;
+  const int min_write_buffer_number_to_merge_;
 
   MemTableListVersion* current_;
 

db/memtable_list_test.cc

@@ -3,6 +3,7 @@
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
 
+#include <algorithm>
 #include <string>
 #include <vector>
 #include "db/memtable_list.h"
@@ -12,17 +13,12 @@
 #include "db/writebuffer.h"
 #include "rocksdb/db.h"
 #include "rocksdb/status.h"
+#include "util/testutil.h"
+#include "util/string_util.h"
 #include "util/testharness.h"
 
 namespace rocksdb {
 
-class DumbLogger : public Logger {
- public:
-  using Logger::Logv;
-  virtual void Logv(const char* format, va_list ap) override {}
-  virtual size_t GetLogFileSize() const override { return 0; }
-};
-
 class MemTableListTest : public testing::Test {
  public:
   std::string dbname;
@@ -56,7 +52,7 @@ class MemTableListTest : public testing::Test {
       MemTableList* list, const MutableCFOptions& mutable_cf_options,
       const autovector<MemTable*>& m, autovector<MemTable*>* to_delete) {
     // Create a mock Logger
-    DumbLogger logger;
+    test::NullLogger logger;
     LogBuffer log_buffer(DEBUG_LEVEL, &logger);
 
     // Create a mock VersionSet
@@ -64,7 +60,7 @@ class MemTableListTest : public testing::Test {
     EnvOptions env_options;
     shared_ptr<Cache> table_cache(NewLRUCache(50000, 16));
     WriteBuffer write_buffer(db_options.db_write_buffer_size);
-    WriteController write_controller;
+    WriteController write_controller(10000000u);
 
     CreateDB();
     VersionSet versions(dbname, &db_options, env_options, table_cache.get(),
@@ -92,9 +88,9 @@ class MemTableListTest : public testing::Test {
 
 TEST_F(MemTableListTest, Empty) {
   // Create an empty MemTableList and validate basic functions.
-  MemTableList list(1);
+  MemTableList list(1, 0);
 
-  ASSERT_EQ(0, list.size());
+  ASSERT_EQ(0, list.NumNotFlushed());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
   ASSERT_FALSE(list.IsFlushPending());
 
@@ -110,12 +106,15 @@ TEST_F(MemTableListTest, Empty) {
 TEST_F(MemTableListTest, GetTest) {
   // Create MemTableList
   int min_write_buffer_number_to_merge = 2;
-  MemTableList list(min_write_buffer_number_to_merge);
+  int max_write_buffer_number_to_maintain = 0;
+  MemTableList list(min_write_buffer_number_to_merge,
+                    max_write_buffer_number_to_maintain);
 
   SequenceNumber seq = 1;
   std::string value;
   Status s;
   MergeContext merge_context;
+  autovector<MemTable*> to_delete;
 
   LookupKey lkey("key1", seq);
   bool found = list.current()->Get(lkey, &value, &s, &merge_context);
@@ -129,7 +128,8 @@ TEST_F(MemTableListTest, GetTest) {
 
   WriteBuffer wb(options.db_write_buffer_size);
   MemTable* mem =
-      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb);
+      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb,
+                   kMaxSequenceNumber);
   mem->Ref();
 
   // Write some keys to this memtable.
@@ -158,21 +158,22 @@ TEST_F(MemTableListTest, GetTest) {
   ASSERT_EQ(1, mem->num_deletes());
 
   // Add memtable to list
-  list.Add(mem);
+  list.Add(mem, &to_delete);
 
   SequenceNumber saved_seq = seq;
 
   // Create another memtable and write some keys to it
   WriteBuffer wb2(options.db_write_buffer_size);
   MemTable* mem2 =
-      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb2);
+      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb2,
+                   kMaxSequenceNumber);
   mem2->Ref();
 
   mem2->Add(++seq, kTypeDeletion, "key1", "");
   mem2->Add(++seq, kTypeValue, "key2", "value2.3");
 
   // Add second memtable to list
-  list.Add(mem2);
+  list.Add(mem2, &to_delete);
 
   // Fetch keys via MemTableList
   merge_context.Clear();
@@ -196,15 +197,190 @@ TEST_F(MemTableListTest, GetTest) {
   found = list.current()->Get(LookupKey("key2", 1), &value, &s, &merge_context);
   ASSERT_FALSE(found);
 
-  ASSERT_EQ(2, list.size());
+  ASSERT_EQ(2, list.NumNotFlushed());
 
-  autovector<MemTable*> to_delete;
   list.current()->Unref(&to_delete);
   for (MemTable* m : to_delete) {
     delete m;
   }
 }
 
+TEST_F(MemTableListTest, GetFromHistoryTest) {
+  // Create MemTableList
+  int min_write_buffer_number_to_merge = 2;
+  int max_write_buffer_number_to_maintain = 2;
+  MemTableList list(min_write_buffer_number_to_merge,
+                    max_write_buffer_number_to_maintain);
+
+  SequenceNumber seq = 1;
+  std::string value;
+  Status s;
+  MergeContext merge_context;
+  autovector<MemTable*> to_delete;
+
+  LookupKey lkey("key1", seq);
+  bool found = list.current()->Get(lkey, &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  // Create a MemTable
+  InternalKeyComparator cmp(BytewiseComparator());
+  auto factory = std::make_shared<SkipListFactory>();
+  options.memtable_factory = factory;
+  ImmutableCFOptions ioptions(options);
+
+  WriteBuffer wb(options.db_write_buffer_size);
+  MemTable* mem =
+      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb,
+                   kMaxSequenceNumber);
+  mem->Ref();
+
+  // Write some keys to this memtable.
+  mem->Add(++seq, kTypeDeletion, "key1", "");
+  mem->Add(++seq, kTypeValue, "key2", "value2");
+  mem->Add(++seq, kTypeValue, "key2", "value2.2");
+
+  // Fetch the newly written keys
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key1", seq), &value, &s, &merge_context);
+  // MemTable found out that this key is *not* found (at this sequence#)
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key2", seq), &value, &s, &merge_context);
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ(value, "value2.2");
+
+  // Add memtable to list
+  list.Add(mem, &to_delete);
+  ASSERT_EQ(0, to_delete.size());
+
+  // Fetch keys via MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context);
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context);
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ("value2.2", value);
+
+  // Flush this memtable from the list.
+  // (It will then be a part of the memtable history).
+  autovector<MemTable*> to_flush;
+  list.PickMemtablesToFlush(&to_flush);
+  ASSERT_EQ(1, to_flush.size());
+
+  s = Mock_InstallMemtableFlushResults(
+      &list, MutableCFOptions(options, ioptions), to_flush, &to_delete);
+  ASSERT_OK(s);
+  ASSERT_EQ(0, list.NumNotFlushed());
+  ASSERT_EQ(1, list.NumFlushed());
+  ASSERT_EQ(0, to_delete.size());
+
+  // Verify keys are no longer in MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  // Verify keys are present in history
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(LookupKey("key1", seq), &value, &s,
+                                         &merge_context);
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(LookupKey("key2", seq), &value, &s,
+                                         &merge_context);
+  ASSERT_TRUE(found);
+  ASSERT_EQ("value2.2", value);
+
+  // Create another memtable and write some keys to it
+  WriteBuffer wb2(options.db_write_buffer_size);
+  MemTable* mem2 =
+      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb2,
+                   kMaxSequenceNumber);
+  mem2->Ref();
+
+  mem2->Add(++seq, kTypeDeletion, "key1", "");
+  mem2->Add(++seq, kTypeValue, "key3", "value3");
+
+  // Add second memtable to list
+  list.Add(mem2, &to_delete);
+  ASSERT_EQ(0, to_delete.size());
+
+  to_flush.clear();
+  list.PickMemtablesToFlush(&to_flush);
+  ASSERT_EQ(1, to_flush.size());
+
+  // Flush second memtable
+  s = Mock_InstallMemtableFlushResults(
+      &list, MutableCFOptions(options, ioptions), to_flush, &to_delete);
+  ASSERT_OK(s);
+  ASSERT_EQ(0, list.NumNotFlushed());
+  ASSERT_EQ(2, list.NumFlushed());
+  ASSERT_EQ(0, to_delete.size());
+
+  // Add a third memtable to push the first memtable out of the history
+  WriteBuffer wb3(options.db_write_buffer_size);
+  MemTable* mem3 =
+      new MemTable(cmp, ioptions, MutableCFOptions(options, ioptions), &wb3,
+                   kMaxSequenceNumber);
+  mem3->Ref();
+  list.Add(mem3, &to_delete);
+  ASSERT_EQ(1, list.NumNotFlushed());
+  ASSERT_EQ(1, list.NumFlushed());
+  ASSERT_EQ(1, to_delete.size());
+
+  // Verify keys are no longer in MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key3", seq), &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  // Verify that the second memtable's keys are in the history
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(LookupKey("key1", seq), &value, &s,
+                                         &merge_context);
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(LookupKey("key3", seq), &value, &s,
+                                         &merge_context);
+  ASSERT_TRUE(found);
+  ASSERT_EQ("value3", value);
+
+  // Verify that key2 from the first memtable is no longer in the history
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context);
+  ASSERT_FALSE(found);
+
+  // Cleanup
+  list.current()->Unref(&to_delete);
+  ASSERT_EQ(3, to_delete.size());
+  for (MemTable* m : to_delete) {
+    delete m;
+  }
+}
+
 TEST_F(MemTableListTest, FlushPendingTest) {
   const int num_tables = 5;
   SequenceNumber seq = 1;
@@ -215,26 +391,30 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   ImmutableCFOptions ioptions(options);
   InternalKeyComparator cmp(BytewiseComparator());
   WriteBuffer wb(options.db_write_buffer_size);
+  autovector<MemTable*> to_delete;
 
   // Create MemTableList
   int min_write_buffer_number_to_merge = 3;
-  MemTableList list(min_write_buffer_number_to_merge);
+  int max_write_buffer_number_to_maintain = 7;
+  MemTableList list(min_write_buffer_number_to_merge,
+                    max_write_buffer_number_to_maintain);
 
   // Create some MemTables
   std::vector<MemTable*> tables;
   MutableCFOptions mutable_cf_options(options, ioptions);
   for (int i = 0; i < num_tables; i++) {
-    MemTable* mem = new MemTable(cmp, ioptions, mutable_cf_options, &wb);
+    MemTable* mem = new MemTable(cmp, ioptions, mutable_cf_options, &wb,
+                                 kMaxSequenceNumber);
     mem->Ref();
 
     std::string value;
     MergeContext merge_context;
 
-    mem->Add(++seq, kTypeValue, "key1", std::to_string(i));
-    mem->Add(++seq, kTypeValue, "keyN" + std::to_string(i), "valueN");
-    mem->Add(++seq, kTypeValue, "keyX" + std::to_string(i), "value");
-    mem->Add(++seq, kTypeValue, "keyM" + std::to_string(i), "valueM");
-    mem->Add(++seq, kTypeDeletion, "keyX" + std::to_string(i), "");
+    mem->Add(++seq, kTypeValue, "key1", ToString(i));
+    mem->Add(++seq, kTypeValue, "keyN" + ToString(i), "valueN");
+    mem->Add(++seq, kTypeValue, "keyX" + ToString(i), "value");
+    mem->Add(++seq, kTypeValue, "keyM" + ToString(i), "valueM");
+    mem->Add(++seq, kTypeDeletion, "keyX" + ToString(i), "");
 
     tables.push_back(mem);
   }
@@ -264,9 +444,10 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
   // Add 2 tables
-  list.Add(tables[0]);
-  list.Add(tables[1]);
-  ASSERT_EQ(2, list.size());
+  list.Add(tables[0], &to_delete);
+  list.Add(tables[1], &to_delete);
+  ASSERT_EQ(2, list.NumNotFlushed());
+  ASSERT_EQ(0, to_delete.size());
 
   // Even though we have less than the minimum to flush, a flush is
   // pending since we had previously requested a flush and never called
@@ -277,7 +458,7 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   // Pick tables to flush
   list.PickMemtablesToFlush(&to_flush);
   ASSERT_EQ(2, to_flush.size());
-  ASSERT_EQ(2, list.size());
+  ASSERT_EQ(2, list.NumNotFlushed());
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
@@ -288,16 +469,17 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   to_flush.clear();
 
   // Add another table
-  list.Add(tables[2]);
+  list.Add(tables[2], &to_delete);
   // We now have the minimum to flush regardles of whether FlushRequested()
   // was called.
   ASSERT_TRUE(list.IsFlushPending());
   ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_EQ(0, to_delete.size());
 
   // Pick tables to flush
   list.PickMemtablesToFlush(&to_flush);
   ASSERT_EQ(3, to_flush.size());
-  ASSERT_EQ(3, list.size());
+  ASSERT_EQ(3, list.NumNotFlushed());
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
@@ -305,14 +487,15 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   autovector<MemTable*> to_flush2;
   list.PickMemtablesToFlush(&to_flush2);
   ASSERT_EQ(0, to_flush2.size());
-  ASSERT_EQ(3, list.size());
+  ASSERT_EQ(3, list.NumNotFlushed());
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
   // Add another table
-  list.Add(tables[3]);
+  list.Add(tables[3], &to_delete);
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_EQ(0, to_delete.size());
 
   // Request a flush again
   list.FlushRequested();
@@ -322,7 +505,7 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   // Pick tables to flush again
   list.PickMemtablesToFlush(&to_flush2);
   ASSERT_EQ(1, to_flush2.size());
-  ASSERT_EQ(4, list.size());
+  ASSERT_EQ(4, list.NumNotFlushed());
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
@@ -333,29 +516,28 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   to_flush.clear();
 
   // Add another tables
-  list.Add(tables[4]);
-  ASSERT_EQ(5, list.size());
+  list.Add(tables[4], &to_delete);
+  ASSERT_EQ(5, list.NumNotFlushed());
   // We now have the minimum to flush regardles of whether FlushRequested()
   ASSERT_TRUE(list.IsFlushPending());
   ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_EQ(0, to_delete.size());
 
   // Pick tables to flush
   list.PickMemtablesToFlush(&to_flush);
   // Should pick 4 of 5 since 1 table has been picked in to_flush2
   ASSERT_EQ(4, to_flush.size());
-  ASSERT_EQ(5, list.size());
+  ASSERT_EQ(5, list.NumNotFlushed());
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
   // Pick tables to flush again
   autovector<MemTable*> to_flush3;
   ASSERT_EQ(0, to_flush3.size());  // nothing not in progress of being flushed
-  ASSERT_EQ(5, list.size());
+  ASSERT_EQ(5, list.NumNotFlushed());
   ASSERT_FALSE(list.IsFlushPending());
   ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
 
-  autovector<MemTable*> to_delete;
-
   // Flush the 4 memtables that were picked in to_flush
   s = Mock_InstallMemtableFlushResults(
       &list, MutableCFOptions(options, ioptions), to_flush, &to_delete);
@@ -366,17 +548,10 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   // Current implementation will only commit memtables in the order they were
   // created.  So InstallMemtableFlushResults will install the first 3 tables
   // in to_flush and stop when it encounters a table not yet flushed.
-  ASSERT_EQ(3, to_delete.size());
-  ASSERT_EQ(2, list.size());
-
-  for (const auto& m : to_delete) {
-    // Refcount should be 0 after calling InstallMemtableFlushResults.
-    // Verify this, by Ref'ing then UnRef'ing:
-    m->Ref();
-    ASSERT_EQ(m, m->Unref());
-    delete m;
-  }
-  to_delete.clear();
+  ASSERT_EQ(2, list.NumNotFlushed());
+  int num_in_history = std::min(3, max_write_buffer_number_to_maintain);
+  ASSERT_EQ(num_in_history, list.NumFlushed());
+  ASSERT_EQ(5 - list.NumNotFlushed() - num_in_history, to_delete.size());
 
   // Request a flush again. Should be nothing to flush
   list.FlushRequested();
@@ -388,10 +563,12 @@ TEST_F(MemTableListTest, FlushPendingTest) {
       &list, MutableCFOptions(options, ioptions), to_flush2, &to_delete);
   ASSERT_OK(s);
 
-  // This will actually intall 2 tables.  The 1 we told it to flush, and also
+  // This will actually install 2 tables.  The 1 we told it to flush, and also
   // tables[4] which has been waiting for tables[3] to commit.
-  ASSERT_EQ(2, to_delete.size());
-  ASSERT_EQ(0, list.size());
+  ASSERT_EQ(0, list.NumNotFlushed());
+  num_in_history = std::min(5, max_write_buffer_number_to_maintain);
+  ASSERT_EQ(num_in_history, list.NumFlushed());
+  ASSERT_EQ(5 - list.NumNotFlushed() - num_in_history, to_delete.size());
 
   for (const auto& m : to_delete) {
     // Refcount should be 0 after calling InstallMemtableFlushResults.
@@ -403,7 +580,17 @@ TEST_F(MemTableListTest, FlushPendingTest) {
   to_delete.clear();
 
   list.current()->Unref(&to_delete);
-  ASSERT_EQ(0, to_delete.size());
+  int to_delete_size = std::min(5, max_write_buffer_number_to_maintain);
+  ASSERT_EQ(to_delete_size, to_delete.size());
+
+  for (const auto& m : to_delete) {
+    // Refcount should be 0 after calling InstallMemtableFlushResults.
+    // Verify this, by Ref'ing then UnRef'ing:
+    m->Ref();
+    ASSERT_EQ(m, m->Unref());
+    delete m;
+  }
+  to_delete.clear();
 }
 
 }  // namespace rocksdb

db/memtablerep_bench.cc

@@ -132,6 +132,8 @@ DEFINE_int64(seed, 0,
              "Seed base for random number generators. "
              "When 0 it is deterministic.");
 
+static rocksdb::Env* FLAGS_env = rocksdb::Env::Default();
+
 namespace rocksdb {
 
 namespace {

db/merge_helper.cc

@@ -3,14 +3,16 @@
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
 //
+
+#include <stdio.h>
+#include <string>
+
 #include "merge_helper.h"
 #include "db/dbformat.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/db.h"
 #include "rocksdb/merge_operator.h"
 #include "util/statistics.h"
-#include <string>
-#include <stdio.h>
 #include "util/perf_context_imp.h"
 #include "util/stop_watch.h"
 
@@ -56,8 +58,8 @@ Status MergeHelper::TimedFullMerge(const Slice& key, const Slice* value,
 //       keys_ stores the list of keys encountered while merging.
 //       operands_ stores the list of merge operands encountered while merging.
 //       keys_[i] corresponds to operands_[i] for each i.
-void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
-                             bool at_bottom, Statistics* stats, int* steps,
+void MergeHelper::MergeUntil(Iterator* iter, const SequenceNumber stop_before,
+                             const bool at_bottom, Statistics* stats,
                              Env* env_) {
   // Get a copy of the internal key, before it's invalidated by iter->Next()
   // Also maintain the list of merge operands seen.
@@ -79,10 +81,6 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
   ParseInternalKey(keys_.back(), &orig_ikey);
 
   bool hit_the_next_user_key = false;
-  std::string merge_result;  // Temporary value for merge results
-  if (steps) {
-    ++(*steps);
-  }
   for (iter->Next(); iter->Valid(); iter->Next()) {
     ParsedInternalKey ikey;
     assert(operands_.size() >= 1);        // Should be invariants!
@@ -109,46 +107,20 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
 
     // At this point we are guaranteed that we need to process this key.
 
-    if (kTypeDeletion == ikey.type) {
-      // hit a delete
-      //   => merge nullptr with operands_
-      //   => store result in operands_.back() (and update keys_.back())
-      //   => change the entry type to kTypeValue for keys_.back()
-      // We are done! Return a success if the merge passes.
-
-      Status s = TimedFullMerge(ikey.user_key, nullptr, operands_,
-                                user_merge_operator_, stats, env_, logger_,
-                                &merge_result);
-
-      // We store the result in keys_.back() and operands_.back()
-      // if nothing went wrong (i.e.: no operand corruption on disk)
-      if (s.ok()) {
-        std::string& original_key =
-            keys_.back();  // The original key encountered
-        orig_ikey.type = kTypeValue;
-        UpdateInternalKey(&original_key[0], original_key.size(),
-                          orig_ikey.sequence, orig_ikey.type);
-        swap(operands_.back(), merge_result);
-      }
-
-      // move iter to the next entry (before doing anything else)
-      iter->Next();
-      if (steps) {
-        ++(*steps);
-      }
-      return;
-    }
-
-    if (kTypeValue == ikey.type) {
-      // hit a put
-      //   => merge the put value with operands_
+    assert(ikey.type <= kValueTypeForSeek);
+    if (ikey.type != kTypeMerge) {
+      // hit a put/delete
+      //   => merge the put value or a nullptr with operands_
       //   => store result in operands_.back() (and update keys_.back())
       //   => change the entry type to kTypeValue for keys_.back()
       // We are done! Success!
       const Slice val = iter->value();
+      const Slice* val_ptr = (kTypeValue == ikey.type) ? &val : nullptr;
+      std::string merge_result;
       Status s =
-          TimedFullMerge(ikey.user_key, &val, operands_, user_merge_operator_,
-                         stats, env_, logger_, &merge_result);
+          TimedFullMerge(ikey.user_key, val_ptr, operands_,
+                         user_merge_operator_, stats, env_, logger_,
+                         &merge_result);
 
       // We store the result in keys_.back() and operands_.back()
       // if nothing went wrong (i.e.: no operand corruption on disk)
@@ -156,20 +128,15 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
         std::string& original_key =
             keys_.back();  // The original key encountered
         orig_ikey.type = kTypeValue;
-        UpdateInternalKey(&original_key[0], original_key.size(),
-                          orig_ikey.sequence, orig_ikey.type);
-        swap(operands_.back(), merge_result);
+        UpdateInternalKey(&original_key, orig_ikey.sequence, orig_ikey.type);
+        operands_.back() = std::move(merge_result);
+        success_ = true;
       }
 
       // move iter to the next entry
       iter->Next();
-      if (steps) {
-        ++(*steps);
-      }
       return;
-    }
-
-    if (kTypeMerge == ikey.type) {
+    } else {
       // hit a merge
       //   => merge the operand into the front of the operands_ list
       //   => use the user's associative merge function to determine how.
@@ -180,9 +147,6 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
       // request or later did a partial merge.
       keys_.push_front(iter->key().ToString());
       operands_.push_front(iter->value().ToString());
-      if (steps) {
-        ++(*steps);
-      }
     }
   }
 
@@ -208,6 +172,7 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
     assert(kTypeMerge == orig_ikey.type);
     assert(operands_.size() >= 1);
     assert(operands_.size() == keys_.size());
+    std::string merge_result;
     {
       StopWatchNano timer(env_, stats != nullptr);
       PERF_TIMER_GUARD(merge_operator_time_nanos);
@@ -219,11 +184,8 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
     if (success_) {
       std::string& original_key = keys_.back();  // The original key encountered
       orig_ikey.type = kTypeValue;
-      UpdateInternalKey(&original_key[0], original_key.size(),
-                        orig_ikey.sequence, orig_ikey.type);
-
-      // The final value() is always stored in operands_.back()
-      swap(operands_.back(),merge_result);
+      UpdateInternalKey(&original_key, orig_ikey.sequence, orig_ikey.type);
+      operands_.back() = std::move(merge_result);
     } else {
       RecordTick(stats, NUMBER_MERGE_FAILURES);
       // Do nothing if not success_. Leave keys() and operands() as they are.
@@ -236,6 +198,7 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
     if (operands_.size() >= 2 &&
         operands_.size() >= min_partial_merge_operands_) {
       bool merge_success = false;
+      std::string merge_result;
       {
         StopWatchNano timer(env_, stats != nullptr);
         PERF_TIMER_GUARD(merge_operator_time_nanos);
@@ -250,7 +213,7 @@ void MergeHelper::MergeUntil(Iterator* iter, SequenceNumber stop_before,
         // Merging of operands (associative merge) was successful.
         // Replace operands with the merge result
         operands_.clear();
-        operands_.push_front(std::move(merge_result));
+        operands_.emplace_front(std::move(merge_result));
         keys_.erase(keys_.begin(), keys_.end() - 1);
       }
     }

db/merge_helper.h

@@ -6,11 +6,12 @@
 #ifndef MERGE_HELPER_H
 #define MERGE_HELPER_H
 
-#include "db/dbformat.h"
-#include "rocksdb/slice.h"
-#include <string>
 #include <deque>
+#include <string>
+
+#include "db/dbformat.h"
 #include "rocksdb/env.h"
+#include "rocksdb/slice.h"
 
 namespace rocksdb {
 
@@ -56,9 +57,9 @@ class MergeHelper {
   //                   0 means no restriction
   // at_bottom:   (IN) true if the iterator covers the bottem level, which means
   //                   we could reach the start of the history of this user key.
-  void MergeUntil(Iterator* iter, SequenceNumber stop_before = 0,
-                  bool at_bottom = false, Statistics* stats = nullptr,
-                  int* steps = nullptr, Env* env_ = nullptr);
+  void MergeUntil(Iterator* iter, const SequenceNumber stop_before = 0,
+                  const bool at_bottom = false, Statistics* stats = nullptr,
+                  Env* env_ = nullptr);
 
   // Query the merge result
   // These are valid until the next MergeUntil call

db/merge_helper_test.cc

@@ -0,0 +1,153 @@
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+
+#include <algorithm>
+#include <string>
+#include <vector>
+
+#include "db/merge_helper.h"
+#include "rocksdb/comparator.h"
+#include "util/coding.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+#include "utilities/merge_operators.h"
+
+namespace rocksdb {
+
+class MergeHelperTest : public testing::Test {
+ public:
+  MergeHelperTest() = default;
+  ~MergeHelperTest() = default;
+
+  void RunUInt64MergeHelper(SequenceNumber stop_before, bool at_bottom) {
+    InitIterator();
+    merge_op_ = MergeOperators::CreateUInt64AddOperator();
+    merge_helper_.reset(new MergeHelper(BytewiseComparator(), merge_op_.get(),
+          nullptr, 2U, true));
+    merge_helper_->MergeUntil(iter_.get(), stop_before, at_bottom, nullptr,
+                              Env::Default());
+  }
+
+  void RunStringAppendMergeHelper(SequenceNumber stop_before, bool at_bottom) {
+    InitIterator();
+    merge_op_ = MergeOperators::CreateStringAppendTESTOperator();
+    merge_helper_.reset(new MergeHelper(BytewiseComparator(), merge_op_.get(),
+          nullptr, 2U, true));
+    merge_helper_->MergeUntil(iter_.get(), stop_before, at_bottom, nullptr,
+                              Env::Default());
+  }
+
+  std::string Key(const std::string& user_key, const SequenceNumber& seq,
+      const ValueType& t) {
+    std::string ikey;
+    AppendInternalKey(&ikey, ParsedInternalKey(Slice(user_key), seq, t));
+    return ikey;
+  }
+
+  void AddKeyVal(const std::string& user_key, const SequenceNumber& seq,
+      const ValueType& t, const std::string& val) {
+    ks_.push_back(Key(user_key, seq, t));
+    vs_.push_back(val);
+  }
+
+  void InitIterator() {
+    iter_.reset(new test::VectorIterator(ks_, vs_));
+    iter_->SeekToFirst();
+  }
+
+  std::string EncodeInt(uint64_t x) {
+    std::string result;
+    PutFixed64(&result, x);
+    return result;
+  }
+
+  void CheckState(bool success, int iter_pos) {
+    ASSERT_EQ(success, merge_helper_->IsSuccess());
+    if (iter_pos == -1) {
+      ASSERT_FALSE(iter_->Valid());
+    } else {
+      ASSERT_EQ(ks_[iter_pos], iter_->key());
+    }
+  }
+
+  std::unique_ptr<test::VectorIterator> iter_;
+  std::shared_ptr<MergeOperator> merge_op_;
+  std::unique_ptr<MergeHelper> merge_helper_;
+  std::vector<std::string> ks_;
+  std::vector<std::string> vs_;
+};
+
+// If MergeHelper encounters a new key on the last level, we know that
+// the key has no more history and it can merge keys.
+TEST_F(MergeHelperTest, MergeAtBottomSuccess) {
+  AddKeyVal("a", 20, kTypeMerge, EncodeInt(1U));
+  AddKeyVal("a", 10, kTypeMerge, EncodeInt(3U));
+  AddKeyVal("b", 10, kTypeMerge, EncodeInt(4U));  // <- Iterator after merge
+
+  RunUInt64MergeHelper(0, true);
+  CheckState(true, 2);
+  ASSERT_EQ(Key("a", 20, kTypeValue), merge_helper_->key());
+  ASSERT_EQ(EncodeInt(4U), merge_helper_->value());
+}
+
+// Merging with a value results in a successful merge.
+TEST_F(MergeHelperTest, MergeValue) {
+  AddKeyVal("a", 40, kTypeMerge, EncodeInt(1U));
+  AddKeyVal("a", 30, kTypeMerge, EncodeInt(3U));
+  AddKeyVal("a", 20, kTypeValue, EncodeInt(4U));  // <- Iterator after merge
+  AddKeyVal("a", 10, kTypeMerge, EncodeInt(1U));
+
+  RunUInt64MergeHelper(0, false);
+  CheckState(true, 3);
+  ASSERT_EQ(Key("a", 40, kTypeValue), merge_helper_->key());
+  ASSERT_EQ(EncodeInt(8U), merge_helper_->value());
+}
+
+// Merging stops before a snapshot.
+TEST_F(MergeHelperTest, SnapshotBeforeValue) {
+  AddKeyVal("a", 50, kTypeMerge, EncodeInt(1U));
+  AddKeyVal("a", 40, kTypeMerge, EncodeInt(3U));  // <- Iterator after merge
+  AddKeyVal("a", 30, kTypeMerge, EncodeInt(1U));
+  AddKeyVal("a", 20, kTypeValue, EncodeInt(4U));
+  AddKeyVal("a", 10, kTypeMerge, EncodeInt(1U));
+
+  RunUInt64MergeHelper(31, true);
+  CheckState(false, 2);
+  ASSERT_EQ(Key("a", 50, kTypeMerge), merge_helper_->keys()[0]);
+  ASSERT_EQ(EncodeInt(4U), merge_helper_->values()[0]);
+}
+
+// MergeHelper preserves the operand stack for merge operators that
+// cannot do a partial merge.
+TEST_F(MergeHelperTest, NoPartialMerge) {
+  AddKeyVal("a", 50, kTypeMerge, "v2");
+  AddKeyVal("a", 40, kTypeMerge, "v");  // <- Iterator after merge
+  AddKeyVal("a", 30, kTypeMerge, "v");
+
+  RunStringAppendMergeHelper(31, true);
+  CheckState(false, 2);
+  ASSERT_EQ(Key("a", 40, kTypeMerge), merge_helper_->keys()[0]);
+  ASSERT_EQ("v", merge_helper_->values()[0]);
+  ASSERT_EQ(Key("a", 50, kTypeMerge), merge_helper_->keys()[1]);
+  ASSERT_EQ("v2", merge_helper_->values()[1]);
+}
+
+// Merging with a deletion turns the deletion into a value
+TEST_F(MergeHelperTest, MergeDeletion) {
+  AddKeyVal("a", 30, kTypeMerge, EncodeInt(3U));
+  AddKeyVal("a", 20, kTypeDeletion, "");
+
+  RunUInt64MergeHelper(15, false);
+  CheckState(true, -1);
+  ASSERT_EQ(Key("a", 30, kTypeValue), merge_helper_->key());
+  ASSERT_EQ(EncodeInt(3U), merge_helper_->value());
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/merge_operator.cc

@@ -20,11 +20,11 @@ bool MergeOperator::PartialMergeMulti(const Slice& key,
                                       Logger* logger) const {
   assert(operand_list.size() >= 2);
   // Simply loop through the operands
-  std::string temp_value;
   Slice temp_slice(operand_list[0]);
 
   for (size_t i = 1; i < operand_list.size(); ++i) {
     auto& operand = operand_list[i];
+    std::string temp_value;
     if (!PartialMerge(key, temp_slice, operand, &temp_value, logger)) {
       return false;
     }
@@ -48,9 +48,9 @@ bool AssociativeMergeOperator::FullMerge(
 
   // Simply loop through the operands
   Slice temp_existing;
-  std::string temp_value;
   for (const auto& operand : operand_list) {
     Slice value(operand);
+    std::string temp_value;
     if (!Merge(key, existing_value, value, &temp_value, logger)) {
       return false;
     }

db/merge_test.cc

@@ -7,6 +7,7 @@
 #include <memory>
 #include <iostream>
 
+#include "port/stack_trace.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/db.h"
@@ -41,6 +42,7 @@ class CountMergeOperator : public AssociativeMergeOperator {
                      const Slice& value,
                      std::string* new_value,
                      Logger* logger) const override {
+    assert(new_value->empty());
     ++num_merge_operator_calls;
     if (existing_value == nullptr) {
       new_value->assign(value.data(), value.size());
@@ -59,6 +61,7 @@ class CountMergeOperator : public AssociativeMergeOperator {
                                  const std::deque<Slice>& operand_list,
                                  std::string* new_value,
                                  Logger* logger) const override {
+    assert(new_value->empty());
     ++num_partial_merge_calls;
     return mergeOperator_->PartialMergeMulti(key, operand_list, new_value,
                                              logger);
@@ -84,6 +87,8 @@ std::shared_ptr<DB> OpenDb(const string& dbname, const bool ttl = false,
   options.min_partial_merge_operands = min_partial_merge_operands;
   Status s;
   DestroyDB(dbname, Options());
+// DBWithTTL is not supported in ROCKSDB_LITE
+#ifndef ROCKSDB_LITE
   if (ttl) {
     cout << "Opening database with TTL\n";
     DBWithTTL* db_with_ttl;
@@ -92,6 +97,10 @@ std::shared_ptr<DB> OpenDb(const string& dbname, const bool ttl = false,
   } else {
     s = DB::Open(options, dbname, &db);
   }
+#else
+  assert(!ttl);
+  s = DB::Open(options, dbname, &db);
+#endif  // !ROCKSDB_LITE
   if (!s.ok()) {
     cerr << s.ToString() << endl;
     assert(false);
@@ -294,7 +303,7 @@ void testCounters(Counters& counters, DB* db, bool test_compaction) {
     db->Flush(o);
 
     cout << "Compaction started ...\n";
-    db->CompactRange(nullptr, nullptr);
+    db->CompactRange(CompactRangeOptions(), nullptr, nullptr);
     cout << "Compaction ended\n";
 
     dumpDb(db);
@@ -341,7 +350,7 @@ void testPartialMerge(Counters* counters, DB* db, size_t max_merge,
     tmp_sum += i;
   }
   db->Flush(o);
-  db->CompactRange(nullptr, nullptr);
+  db->CompactRange(CompactRangeOptions(), nullptr, nullptr);
   ASSERT_EQ(tmp_sum, counters->assert_get("b"));
   if (count > max_merge) {
     // in this case, FullMerge should be called instead.
@@ -360,7 +369,7 @@ void testPartialMerge(Counters* counters, DB* db, size_t max_merge,
     tmp_sum += i;
   }
   db->Flush(o);
-  db->CompactRange(nullptr, nullptr);
+  db->CompactRange(CompactRangeOptions(), nullptr, nullptr);
   ASSERT_EQ(tmp_sum, counters->assert_get("c"));
   ASSERT_EQ(num_partial_merge_calls, 0U);
 }
@@ -467,7 +476,7 @@ void runTest(int argc, const string& dbname, const bool use_ttl = false) {
       counters.add("test-key", 1);
       counters.add("test-key", 1);
       counters.add("test-key", 1);
-      db->CompactRange(nullptr, nullptr);
+      db->CompactRange(CompactRangeOptions(), nullptr, nullptr);
     }
 
     DB* reopen_db;
@@ -498,8 +507,12 @@ void runTest(int argc, const string& dbname, const bool use_ttl = false) {
 
 int main(int argc, char *argv[]) {
   //TODO: Make this test like a general rocksdb unit-test
+  rocksdb::port::InstallStackTraceHandler();
   runTest(argc, test::TmpDir() + "/merge_testdb");
+// DBWithTTL is not supported in ROCKSDB_LITE
+#ifndef ROCKSDB_LITE
   runTest(argc, test::TmpDir() + "/merge_testdbttl", true); // Run test on TTL database
+#endif  // !ROCKSDB_LITE
   printf("Passed all tests!\n");
   return 0;
 }

db/plain_table_db_test.cc

@@ -8,6 +8,9 @@
 // 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.
+
+#ifndef ROCKSDB_LITE
+
 #include <algorithm>
 #include <set>
 
@@ -198,10 +201,9 @@ class TestPlainTableReader : public PlainTableReader {
                        int bloom_bits_per_key, double hash_table_ratio,
                        size_t index_sparseness,
                        const TableProperties* table_properties,
-                       unique_ptr<RandomAccessFile>&& file,
+                       unique_ptr<RandomAccessFileReader>&& file,
                        const ImmutableCFOptions& ioptions,
-                       bool* expect_bloom_not_match,
-                       bool store_index_in_file)
+                       bool* expect_bloom_not_match, bool store_index_in_file)
       : PlainTableReader(ioptions, std::move(file), env_options, icomparator,
                          encoding_type, file_size, table_properties),
         expect_bloom_not_match_(expect_bloom_not_match) {
@@ -257,7 +259,8 @@ class TestPlainTableFactory : public PlainTableFactory {
   Status NewTableReader(const ImmutableCFOptions& ioptions,
                         const EnvOptions& env_options,
                         const InternalKeyComparator& internal_comparator,
-                        unique_ptr<RandomAccessFile>&& file, uint64_t file_size,
+                        unique_ptr<RandomAccessFileReader>&& file,
+                        uint64_t file_size,
                         unique_ptr<TableReader>* table) const override {
     TableProperties* props = nullptr;
     auto s = ReadTableProperties(file.get(), file_size, kPlainTableMagicNumber,
@@ -1011,7 +1014,6 @@ TEST_F(PlainTableDBTest, CompactionTrigger) {
   Options options = CurrentOptions();
   options.write_buffer_size = 100 << 10; //100KB
   options.num_levels = 3;
-  options.max_mem_compaction_level = 0;
   options.level0_file_num_compaction_trigger = 3;
   Reopen(&options);
 
@@ -1090,3 +1092,13 @@ int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }
+
+#else
+#include <stdio.h>
+
+int main(int argc, char** argv) {
+  fprintf(stderr, "SKIPPED as plain table is not supported in ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // !ROCKSDB_LITE

db/prefix_test.cc

@@ -3,6 +3,8 @@
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
 
+#ifndef ROCKSDB_LITE
+
 #ifndef GFLAGS
 #include <cstdio>
 int main() {
@@ -501,3 +503,15 @@ int main(int argc, char** argv) {
 }
 
 #endif  // GFLAGS
+
+#else
+#include <stdio.h>
+
+int main(int argc, char** argv) {
+  fprintf(stderr,
+          "SKIPPED as HashSkipList and HashLinkList are not supported in "
+          "ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // !ROCKSDB_LITE

db/repair.cc

@@ -81,6 +81,7 @@
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "rocksdb/immutable_options.h"
+#include "util/file_reader_writer.h"
 #include "util/scoped_arena_iterator.h"
 
 namespace rocksdb {
@@ -127,7 +128,7 @@ class Repairer {
       }
       Log(InfoLogLevel::WARN_LEVEL, options_.info_log,
           "**** Repaired rocksdb %s; "
-          "recovered %zu files; %" PRIu64
+          "recovered %" ROCKSDB_PRIszt " files; %" PRIu64
           "bytes. "
           "Some data may have been lost. "
           "****",
@@ -236,6 +237,8 @@ class Repairer {
     if (!status.ok()) {
       return status;
     }
+    unique_ptr<SequentialFileReader> lfile_reader(
+        new SequentialFileReader(std::move(lfile)));
 
     // Create the log reader.
     LogReporter reporter;
@@ -246,16 +249,17 @@ class Repairer {
     // corruptions cause entire commits to be skipped instead of
     // propagating bad information (like overly large sequence
     // numbers).
-    log::Reader reader(std::move(lfile), &reporter, true /*enable checksum*/,
-                       0/*initial_offset*/);
+    log::Reader reader(std::move(lfile_reader), &reporter,
+                       true /*enable checksum*/, 0 /*initial_offset*/);
 
     // Read all the records and add to a memtable
     std::string scratch;
     Slice record;
     WriteBatch batch;
     WriteBuffer wb(options_.db_write_buffer_size);
-    MemTable* mem = new MemTable(icmp_, ioptions_,
-                                 MutableCFOptions(options_, ioptions_), &wb);
+    MemTable* mem =
+        new MemTable(icmp_, ioptions_, MutableCFOptions(options_, ioptions_),
+                     &wb, kMaxSequenceNumber);
     auto cf_mems_default = new ColumnFamilyMemTablesDefault(mem);
     mem->Ref();
     int counter = 0;
@@ -377,8 +381,8 @@ class Repairer {
   Status WriteDescriptor() {
     std::string tmp = TempFileName(dbname_, 1);
     unique_ptr<WritableFile> file;
-    Status status = env_->NewWritableFile(
-        tmp, &file, env_->OptimizeForManifestWrite(env_options_));
+    EnvOptions env_options = env_->OptimizeForManifestWrite(env_options_);
+    Status status = env_->NewWritableFile(tmp, &file, env_options);
     if (!status.ok()) {
       return status;
     }
@@ -400,12 +404,15 @@ class Repairer {
       const TableInfo& t = tables_[i];
       edit_->AddFile(0, t.meta.fd.GetNumber(), t.meta.fd.GetPathId(),
                      t.meta.fd.GetFileSize(), t.meta.smallest, t.meta.largest,
-                     t.min_sequence, t.max_sequence);
+                     t.min_sequence, t.max_sequence,
+                     t.meta.marked_for_compaction);
     }
 
     //fprintf(stderr, "NewDescriptor:\n%s\n", edit_.DebugString().c_str());
     {
-      log::Writer log(std::move(file));
+      unique_ptr<WritableFileWriter> file_writer(
+          new WritableFileWriter(std::move(file), env_options));
+      log::Writer log(std::move(file_writer));
       std::string record;
       edit_->EncodeTo(&record);
       status = log.AddRecord(record);

db/skiplist.h

@@ -59,6 +59,9 @@ class SkipList {
   // Returns true iff an entry that compares equal to key is in the list.
   bool Contains(const Key& key) const;
 
+  // Return estimated number of entries smaller than `key`.
+  uint64_t EstimateCount(const Key& key) const;
+
   // Iteration over the contents of a skip list
   class Iterator {
    public:
@@ -354,10 +357,34 @@ typename SkipList<Key, Comparator>::Node* SkipList<Key, Comparator>::FindLast()
   }
 }
 
-template<typename Key, class Comparator>
+template <typename Key, class Comparator>
+uint64_t SkipList<Key, Comparator>::EstimateCount(const Key& key) const {
+  uint64_t count = 0;
+
+  Node* x = head_;
+  int level = GetMaxHeight() - 1;
+  while (true) {
+    assert(x == head_ || compare_(x->key, key) < 0);
+    Node* next = x->Next(level);
+    if (next == nullptr || compare_(next->key, key) >= 0) {
+      if (level == 0) {
+        return count;
+      } else {
+        // Switch to next list
+        count *= kBranching_;
+        level--;
+      }
+    } else {
+      x = next;
+      count++;
+    }
+  }
+}
+
+template <typename Key, class Comparator>
 SkipList<Key, Comparator>::SkipList(const Comparator cmp, Allocator* allocator,
-                                   int32_t max_height,
-                                   int32_t branching_factor)
+                                    int32_t max_height,
+                                    int32_t branching_factor)
     : kMaxHeight_(max_height),
       kBranching_(branching_factor),
       compare_(cmp),

db/snapshot.h

@@ -49,8 +49,8 @@ class SnapshotList {
   SnapshotImpl* oldest() const { assert(!empty()); return list_.next_; }
   SnapshotImpl* newest() const { assert(!empty()); return list_.prev_; }
 
-  const SnapshotImpl* New(SequenceNumber seq, uint64_t unix_time) {
-    SnapshotImpl* s = new SnapshotImpl;
+  const SnapshotImpl* New(SnapshotImpl* s, SequenceNumber seq,
+                          uint64_t unix_time) {
     s->number_ = seq;
     s->unix_time_ = unix_time;
     s->list_ = this;
@@ -62,12 +62,12 @@ class SnapshotList {
     return s;
   }
 
+  // Do not responsible to free the object.
   void Delete(const SnapshotImpl* s) {
     assert(s->list_ == this);
     s->prev_->next_ = s->next_;
     s->next_->prev_ = s->prev_;
     count_--;
-    delete s;
   }
 
   // retrieve all snapshot numbers. They are sorted in ascending order.

db/table_cache.cc

@@ -9,6 +9,7 @@
 
 #include "db/table_cache.h"
 
+#include "db/dbformat.h"
 #include "db/filename.h"
 #include "db/version_edit.h"
 
@@ -17,13 +18,18 @@
 #include "table/table_reader.h"
 #include "table/get_context.h"
 #include "util/coding.h"
+#include "util/file_reader_writer.h"
+#include "util/perf_context_imp.h"
 #include "util/stop_watch.h"
 
 namespace rocksdb {
 
+namespace {
+
+template <class T>
 static void DeleteEntry(const Slice& key, void* value) {
-  TableReader* table_reader = reinterpret_cast<TableReader*>(value);
-  delete table_reader;
+  T* typed_value = reinterpret_cast<T*>(value);
+  delete typed_value;
 }
 
 static void UnrefEntry(void* arg1, void* arg2) {
@@ -37,11 +43,27 @@ static Slice GetSliceForFileNumber(const uint64_t* file_number) {
                sizeof(*file_number));
 }
 
+#ifndef ROCKSDB_LITE
+
+void AppendVarint64(IterKey* key, uint64_t v) {
+  char buf[10];
+  auto ptr = EncodeVarint64(buf, v);
+  key->TrimAppend(key->Size(), buf, ptr - buf);
+}
+
+#endif  // ROCKSDB_LITE
+
+}  // namespace
+
 TableCache::TableCache(const ImmutableCFOptions& ioptions,
                        const EnvOptions& env_options, Cache* const cache)
-    : ioptions_(ioptions),
-      env_options_(env_options),
-      cache_(cache) {}
+    : ioptions_(ioptions), env_options_(env_options), cache_(cache) {
+  if (ioptions_.row_cache) {
+    // If the same cache is shared by multiple instances, we need to
+    // disambiguate its entries.
+    PutVarint64(&row_cache_id_, ioptions_.row_cache->NewId());
+  }
+}
 
 TableCache::~TableCache() {
 }
@@ -57,7 +79,8 @@ void TableCache::ReleaseHandle(Cache::Handle* handle) {
 Status TableCache::FindTable(const EnvOptions& env_options,
                              const InternalKeyComparator& internal_comparator,
                              const FileDescriptor& fd, Cache::Handle** handle,
-                             const bool no_io) {
+                             const bool no_io, bool record_read_stats) {
+  PERF_TIMER_GUARD(find_table_nanos);
   Status s;
   uint64_t number = fd.GetNumber();
   Slice key = GetSliceForFileNumber(&number);
@@ -77,8 +100,13 @@ Status TableCache::FindTable(const EnvOptions& env_options,
         file->Hint(RandomAccessFile::RANDOM);
       }
       StopWatch sw(ioptions_.env, ioptions_.statistics, TABLE_OPEN_IO_MICROS);
+      std::unique_ptr<RandomAccessFileReader> file_reader(
+          new RandomAccessFileReader(
+              std::move(file), ioptions_.env,
+              record_read_stats ? ioptions_.statistics : nullptr,
+              SST_READ_MICROS));
       s = ioptions_.table_factory->NewTableReader(
-          ioptions_, env_options, internal_comparator, std::move(file),
+          ioptions_, env_options, internal_comparator, std::move(file_reader),
           fd.GetFileSize(), &table_reader);
     }
 
@@ -88,7 +116,8 @@ Status TableCache::FindTable(const EnvOptions& env_options,
       // We do not cache error results so that if the error is transient,
       // or somebody repairs the file, we recover automatically.
     } else {
-      *handle = cache_->Insert(key, table_reader.release(), 1, &DeleteEntry);
+      *handle = cache_->Insert(key, table_reader.release(), 1,
+                               &DeleteEntry<TableReader>);
     }
   }
   return s;
@@ -100,6 +129,8 @@ Iterator* TableCache::NewIterator(const ReadOptions& options,
                                   const FileDescriptor& fd,
                                   TableReader** table_reader_ptr,
                                   bool for_compaction, Arena* arena) {
+  PERF_TIMER_GUARD(new_table_iterator_nanos);
+
   if (table_reader_ptr != nullptr) {
     *table_reader_ptr = nullptr;
   }
@@ -108,7 +139,7 @@ Iterator* TableCache::NewIterator(const ReadOptions& options,
   Status s;
   if (table_reader == nullptr) {
     s = FindTable(env_options, icomparator, fd, &handle,
-                  options.read_tier == kBlockCacheTier);
+                  options.read_tier == kBlockCacheTier, !for_compaction);
     if (!s.ok()) {
       return NewErrorIterator(s, arena);
     }
@@ -137,6 +168,46 @@ Status TableCache::Get(const ReadOptions& options,
   TableReader* t = fd.table_reader;
   Status s;
   Cache::Handle* handle = nullptr;
+  std::string* row_cache_entry = nullptr;
+
+#ifndef ROCKSDB_LITE
+  IterKey row_cache_key;
+  std::string row_cache_entry_buffer;
+
+  if (ioptions_.row_cache) {
+    uint64_t fd_number = fd.GetNumber();
+    auto user_key = ExtractUserKey(k);
+    // We use the user key as cache key instead of the internal key,
+    // otherwise the whole cache would be invalidated every time the
+    // sequence key increases. However, to support caching snapshot
+    // reads, we append the sequence number (incremented by 1 to
+    // distinguish from 0) only in this case.
+    uint64_t seq_no =
+        options.snapshot == nullptr ? 0 : 1 + GetInternalKeySeqno(k);
+
+    // Compute row cache key.
+    row_cache_key.TrimAppend(row_cache_key.Size(), row_cache_id_.data(),
+                             row_cache_id_.size());
+    AppendVarint64(&row_cache_key, fd_number);
+    AppendVarint64(&row_cache_key, seq_no);
+    row_cache_key.TrimAppend(row_cache_key.Size(), user_key.data(),
+                             user_key.size());
+
+    if (auto row_handle = ioptions_.row_cache->Lookup(row_cache_key.GetKey())) {
+      auto found_row_cache_entry = static_cast<const std::string*>(
+          ioptions_.row_cache->Value(row_handle));
+      replayGetContextLog(*found_row_cache_entry, user_key, get_context);
+      ioptions_.row_cache->Release(row_handle);
+      RecordTick(ioptions_.statistics, ROW_CACHE_HIT);
+      return Status::OK();
+    }
+
+    // Not found, setting up the replay log.
+    RecordTick(ioptions_.statistics, ROW_CACHE_MISS);
+    row_cache_entry = &row_cache_entry_buffer;
+  }
+#endif  // ROCKSDB_LITE
+
   if (!t) {
     s = FindTable(env_options_, internal_comparator, fd, &handle,
                   options.read_tier == kBlockCacheTier);
@@ -145,15 +216,30 @@ Status TableCache::Get(const ReadOptions& options,
     }
   }
   if (s.ok()) {
+    get_context->SetReplayLog(row_cache_entry);  // nullptr if no cache.
     s = t->Get(options, k, get_context);
+    get_context->SetReplayLog(nullptr);
     if (handle != nullptr) {
       ReleaseHandle(handle);
     }
   } else if (options.read_tier && s.IsIncomplete()) {
-    // Couldnt find Table in cache but treat as kFound if no_io set
+    // Couldn't find Table in cache but treat as kFound if no_io set
     get_context->MarkKeyMayExist();
     return Status::OK();
   }
+
+#ifndef ROCKSDB_LITE
+  // Put the replay log in row cache only if something was found.
+  if (s.ok() && row_cache_entry && !row_cache_entry->empty()) {
+    size_t charge =
+        row_cache_key.Size() + row_cache_entry->size() + sizeof(std::string);
+    void* row_ptr = new std::string(std::move(*row_cache_entry));
+    auto row_handle = ioptions_.row_cache->Insert(
+        row_cache_key.GetKey(), row_ptr, charge, &DeleteEntry<std::string>);
+    ioptions_.row_cache->Release(row_handle);
+  }
+#endif  // ROCKSDB_LITE
+
   return s;
 }