Fix WriteBatchBase::DeleteRange API comment

The `DeleteRange` end key is exclusive, not inclusive. Updated API comment accordingly.
2026-11-06 11:02:36 -05:00 · 2019-01-31 13:42:22 -08:00
957 changed files with 35841 additions and 94878 deletions
@@ -24,7 +24,6 @@ make_config.mk
 *.vcxproj.filters
 *.sln
 *.cmake
-.watchmanconfig
 CMakeCache.txt
 CMakeFiles/
 build/
@@ -33,8 +32,6 @@ ldb
 manifest_dump
 sst_dump
 blob_dump
-block_cache_trace_analyzer
-tools/block_cache_analyzer/*.pyc
 column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
@@ -50,8 +47,6 @@ rocksdb_undump
 db_test2
 trace_analyzer
 trace_analyzer_test
-block_cache_trace_analyzer
-.DS_Store

 java/out
 java/target
@@ -1,4 +1,5 @@
-dist: xenial
+sudo: false
+dist: trusty
 language: cpp
 os:
  - linux
@@ -8,7 +9,7 @@ compiler:
  - gcc
 osx_image: xcode8.3
 jdk:
-  - openjdk7
+  - oraclejdk7
 cache:
  - ccache
  - apt
@@ -70,10 +71,7 @@ install:
      CC=gcc-8 && CXX=g++-8;
    fi
  - if [[ "${JOB_NAME}" == cmake* ]] && [ "${TRAVIS_OS_NAME}" == linux ]; then
-      mkdir cmake-dist && curl -sfSL https://github.com/Kitware/CMake/releases/download/v3.14.5/cmake-3.14.5-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
-    fi
-  - if [[ "${JOB_NAME}" == java_test ]]; then
-      java -version && echo "JAVA_HOME=${JAVA_HOME}";
+      mkdir cmake-dist && curl -sfSL https://cmake.org/files/v3.8/cmake-3.8.1-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
    fi

 before_script:
@@ -103,7 +101,7 @@ script:
    esac
  - case $JOB_NAME in
    java_test)
-      OPT=-DTRAVIS V=1 make rocksdbjava jtest
+      OPT=-DTRAVIS V=1 make clean jclean && make rocksdbjava jtest
      ;;
    lite_build)
      OPT='-DTRAVIS -DROCKSDB_LITE' V=1 make -j4 static_lib tools
@@ -112,7 +110,6 @@ script:
      OPT=-DTRAVIS V=1 make -j4 static_lib && cd examples && make -j4
      ;;
    cmake-mingw)
-      sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
      ;;
    cmake*)
@@ -1,6 +0,0 @@
-{
-  "content_hash_warming": true,
-  "content_hash_max_items": 333333,
-  "hint_num_files_per_dir": 8,
-  "fsevents_latency": 0.05
-}
@@ -32,24 +32,17 @@
 # 3. cmake ..
 # 4. make -j

-cmake_minimum_required(VERSION 3.5.1)
-
-list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
-include(ReadVersion)
-get_rocksdb_version(rocksdb_VERSION)
-project(rocksdb
-  VERSION ${rocksdb_VERSION}
-  LANGUAGES CXX C ASM)
+cmake_minimum_required(VERSION 2.8.12)
+project(rocksdb)
+enable_language(CXX)
+enable_language(C)
+enable_language(ASM)

 if(POLICY CMP0042)
  cmake_policy(SET CMP0042 NEW)
 endif()

-find_program(CCACHE_FOUND ccache)
-if(CCACHE_FOUND)
-  set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
-  set_property(GLOBAL PROPERTY RULE_LAUNCH_LINK ccache)
-endif(CCACHE_FOUND)
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")

 option(WITH_JEMALLOC "build with JeMalloc" OFF)
 option(WITH_SNAPPY "build with SNAPPY" OFF)
@@ -60,13 +53,6 @@ option(WITH_WINDOWS_UTF8_FILENAMES "use UTF8 as characterset for opening files,
 if (WITH_WINDOWS_UTF8_FILENAMES)
  add_definitions(-DROCKSDB_WINDOWS_UTF8_FILENAMES)
 endif()
-# third-party/folly is only validated to work on Linux and Windows for now.
-# So only turn it on there by default.
-if(CMAKE_SYSTEM_NAME MATCHES "Linux" OR CMAKE_SYSTEM_NAME MATCHES "Windows")
-  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
-else()
-  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
-endif()
 if(MSVC)
  # Defaults currently different for GFLAGS.
  #  We will address find_package work a little later
@@ -82,7 +68,8 @@ else()
    if(WITH_JEMALLOC)
      find_package(JeMalloc REQUIRED)
      add_definitions(-DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE)
-      list(APPEND THIRDPARTY_LIBS JeMalloc::JeMalloc)
+      include_directories(${JEMALLOC_INCLUDE_DIR})
+      list(APPEND THIRDPARTY_LIBS ${JEMALLOC_LIBRARIES})
    endif()
  endif()

@@ -100,43 +87,47 @@ else()
  if(WITH_SNAPPY)
    find_package(snappy REQUIRED)
    add_definitions(-DSNAPPY)
-    list(APPEND THIRDPARTY_LIBS snappy::snappy)
+    include_directories(${SNAPPY_INCLUDE_DIR})
+    list(APPEND THIRDPARTY_LIBS ${SNAPPY_LIBRARIES})
  endif()

  if(WITH_ZLIB)
-    find_package(ZLIB REQUIRED)
+    find_package(zlib REQUIRED)
    add_definitions(-DZLIB)
-    list(APPEND THIRDPARTY_LIBS ZLIB::ZLIB)
+    if(ZLIB_INCLUDE_DIRS)
+      # CMake 3
+      include_directories(${ZLIB_INCLUDE_DIRS})
+    else()
+      # CMake 2
+      include_directories(${ZLIB_INCLUDE_DIR})
+    endif()
+    list(APPEND THIRDPARTY_LIBS ${ZLIB_LIBRARIES})
  endif()

  option(WITH_BZ2 "build with bzip2" OFF)
  if(WITH_BZ2)
-    find_package(BZip2 REQUIRED)
+    find_package(bzip2 REQUIRED)
    add_definitions(-DBZIP2)
-    if(BZIP2_INCLUDE_DIRS)
-      include_directories(${BZIP2_INCLUDE_DIRS})
-    else()
-      include_directories(${BZIP2_INCLUDE_DIR})
-    endif()
+    include_directories(${BZIP2_INCLUDE_DIR})
    list(APPEND THIRDPARTY_LIBS ${BZIP2_LIBRARIES})
  endif()

  if(WITH_LZ4)
    find_package(lz4 REQUIRED)
    add_definitions(-DLZ4)
-    list(APPEND THIRDPARTY_LIBS lz4::lz4)
+    include_directories(${LZ4_INCLUDE_DIR})
+    list(APPEND THIRDPARTY_LIBS ${LZ4_LIBRARIES})
  endif()

  if(WITH_ZSTD)
    find_package(zstd REQUIRED)
    add_definitions(-DZSTD)
    include_directories(${ZSTD_INCLUDE_DIR})
-    list(APPEND THIRDPARTY_LIBS zstd::zstd)
+    list(APPEND THIRDPARTY_LIBS ${ZSTD_LIBRARIES})
  endif()
 endif()

-string(TIMESTAMP TS "%Y/%m/%d %H:%M:%S" UTC)
-set(GIT_DATE_TIME "${TS}" CACHE STRING "the time we first built rocksdb")
+string(TIMESTAMP GIT_DATE_TIME "%Y/%m/%d %H:%M:%S" UTC)

 find_package(Git)

@@ -153,6 +144,17 @@ endif()
 string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA "${GIT_SHA}")


+# Read rocksdb version from version.h header file.
+file(READ include/rocksdb/version.h version_header_file)
+string(REGEX MATCH "#define ROCKSDB_MAJOR ([0-9]+)" _ ${version_header_file})
+set(ROCKSDB_VERSION_MAJOR ${CMAKE_MATCH_1})
+string(REGEX MATCH "#define ROCKSDB_MINOR ([0-9]+)" _ ${version_header_file})
+set(ROCKSDB_VERSION_MINOR ${CMAKE_MATCH_1})
+string(REGEX MATCH "#define ROCKSDB_PATCH ([0-9]+)" _ ${version_header_file})
+set(ROCKSDB_VERSION_PATCH ${CMAKE_MATCH_1})
+set(ROCKSDB_VERSION ${ROCKSDB_VERSION_MAJOR}.${ROCKSDB_VERSION_MINOR}.${ROCKSDB_VERSION_PATCH})
+
+
 option(WITH_MD_LIBRARY "build with MD" ON)
 if(WIN32 AND MSVC)
  if(WITH_MD_LIBRARY)
@@ -175,7 +177,6 @@ else()
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
  if(MINGW)
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
-    add_definitions(-D_POSIX_C_SOURCE=1)
  endif()
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
  if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
@@ -200,15 +201,6 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
  endif(HAS_ALTIVEC)
 endif(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")

-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
-        CHECK_C_COMPILER_FLAG("-march=armv8-a+crc+crypto" HAS_ARMV8_CRC)
-  if(HAS_ARMV8_CRC)
-    message(STATUS " HAS_ARMV8_CRC yes")
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
-  endif(HAS_ARMV8_CRC)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
-
 option(PORTABLE "build a portable binary" OFF)
 option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
 if(PORTABLE)
@@ -221,7 +213,7 @@ else()
  if(MSVC)
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
  else()
-    if(NOT HAVE_POWER8 AND NOT HAS_ARMV8_CRC)
+    if(NOT HAVE_POWER8)
      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
    endif()
  endif()
@@ -308,14 +300,15 @@ if(WITH_NUMA)
  find_package(NUMA REQUIRED)
  add_definitions(-DNUMA)
  include_directories(${NUMA_INCLUDE_DIR})
-  list(APPEND THIRDPARTY_LIBS NUMA::NUMA)
+  list(APPEND THIRDPARTY_LIBS ${NUMA_LIBRARIES})
 endif()

 option(WITH_TBB "build with Threading Building Blocks (TBB)" OFF)
 if(WITH_TBB)
  find_package(TBB REQUIRED)
  add_definitions(-DTBB)
-  list(APPEND THIRDPARTY_LIBS TBB::TBB)
+  include_directories(${TBB_INCLUDE_DIR})
+  list(APPEND THIRDPARTY_LIBS ${TBB_LIBRARIES})
 endif()

 # Stall notifications eat some performance from inserts
@@ -324,10 +317,6 @@ if(DISABLE_STALL_NOTIF)
  add_definitions(-DROCKSDB_DISABLE_STALL_NOTIFICATION)
 endif()

-option(WITH_DYNAMIC_EXTENSION "build with dynamic extension support" OFF)
-if(NOT WITH_DYNAMIC_EXTENSION)
-  add_definitions(-DROCKSDB_NO_DYNAMIC_EXTENSION)
-endif()

 if(DEFINED USE_RTTI)
  if(USE_RTTI)
@@ -427,7 +416,7 @@ if(WITH_FALLOCATE)
 #include <linux/falloc.h>
 int main() {
 int fd = open(\"/dev/null\", 0);
- fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, 1024);
+ fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
 }
 " HAVE_FALLOCATE)
  if(HAVE_FALLOCATE)
@@ -469,41 +458,37 @@ endif()

 include_directories(${PROJECT_SOURCE_DIR})
 include_directories(${PROJECT_SOURCE_DIR}/include)
-include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.8.1/fused-src)
-if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-  include_directories(${PROJECT_SOURCE_DIR}/third-party/folly)
-endif()
+include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
 find_package(Threads REQUIRED)

+add_subdirectory(third-party/gtest-1.7.0/fused-src/gtest)
+
 # Main library source code

 set(SOURCES
        cache/clock_cache.cc
        cache/lru_cache.cc
        cache/sharded_cache.cc
-        db/arena_wrapped_db_iter.cc
        db/builder.cc
        db/c.cc
        db/column_family.cc
        db/compacted_db_impl.cc
-        db/compaction/compaction.cc
-        db/compaction/compaction_iterator.cc
-        db/compaction/compaction_picker.cc
-        db/compaction/compaction_job.cc
-        db/compaction/compaction_picker_fifo.cc
-        db/compaction/compaction_picker_level.cc
-        db/compaction/compaction_picker_universal.cc
+        db/compaction.cc
+        db/compaction_iterator.cc
+        db/compaction_job.cc
+        db/compaction_picker.cc
+        db/compaction_picker_fifo.cc
+        db/compaction_picker_universal.cc
        db/convenience.cc
        db/db_filesnapshot.cc
-        db/db_impl/db_impl.cc
-        db/db_impl/db_impl_write.cc
-        db/db_impl/db_impl_compaction_flush.cc
-        db/db_impl/db_impl_files.cc
-        db/db_impl/db_impl_open.cc
-        db/db_impl/db_impl_debug.cc
-        db/db_impl/db_impl_experimental.cc
-        db/db_impl/db_impl_readonly.cc
-        db/db_impl/db_impl_secondary.cc
+        db/db_impl.cc
+        db/db_impl_write.cc
+        db/db_impl_compaction_flush.cc
+        db/db_impl_files.cc
+        db/db_impl_open.cc
+        db/db_impl_debug.cc
+        db/db_impl_experimental.cc
+        db/db_impl_readonly.cc
        db/db_info_dumper.cc
        db/db_iter.cc
        db/dbformat.cc
@@ -515,7 +500,6 @@ set(SOURCES
        db/flush_job.cc
        db/flush_scheduler.cc
        db/forward_iterator.cc
-        db/import_column_family_job.cc
        db/internal_stats.cc
        db/logs_with_prep_tracker.cc
        db/log_reader.cc
@@ -532,7 +516,6 @@ set(SOURCES
        db/table_cache.cc
        db/table_properties_collector.cc
        db/transaction_log_impl.cc
-        db/trim_history_scheduler.cc
        db/version_builder.cc
        db/version_edit.cc
        db/version_set.cc
@@ -546,23 +529,8 @@ set(SOURCES
        env/env_encryption.cc
        env/env_hdfs.cc
        env/mock_env.cc
-        file/delete_scheduler.cc
-        file/file_prefetch_buffer.cc
-        file/file_util.cc
-        file/filename.cc
-        file/random_access_file_reader.cc
-        file/read_write_util.cc
-        file/readahead_raf.cc
-        file/sequence_file_reader.cc
-        file/sst_file_manager_impl.cc
-        file/writable_file_writer.cc
-        logging/auto_roll_logger.cc
-        logging/event_logger.cc
-        logging/log_buffer.cc
-        memory/arena.cc
-        memory/concurrent_arena.cc
-        memory/jemalloc_nodump_allocator.cc
        memtable/alloc_tracker.cc
+        memtable/hash_cuckoo_rep.cc
        memtable/hash_linklist_rep.cc
        memtable/hash_skiplist_rep.cc
        memtable/skiplistrep.cc
@@ -570,12 +538,10 @@ set(SOURCES
        memtable/write_buffer_manager.cc
        monitoring/histogram.cc
        monitoring/histogram_windowing.cc
-        monitoring/in_memory_stats_history.cc
        monitoring/instrumented_mutex.cc
        monitoring/iostats_context.cc
        monitoring/perf_context.cc
        monitoring/perf_level.cc
-        monitoring/persistent_stats_history.cc
        monitoring/statistics.cc
        monitoring/thread_status_impl.cc
        monitoring/thread_status_updater.cc
@@ -588,73 +554,80 @@ set(SOURCES
        options/options_parser.cc
        options/options_sanity_check.cc
        port/stack_trace.cc
-        table/adaptive/adaptive_table_factory.cc
-        table/block_based/block.cc
-        table/block_based/block_based_filter_block.cc
-        table/block_based/block_based_table_builder.cc
-        table/block_based/block_based_table_factory.cc
-        table/block_based/block_based_table_reader.cc
-        table/block_based/block_builder.cc
-        table/block_based/block_prefix_index.cc
-        table/block_based/data_block_hash_index.cc
-        table/block_based/data_block_footer.cc
-        table/block_based/filter_block_reader_common.cc
-        table/block_based/flush_block_policy.cc
-        table/block_based/full_filter_block.cc
-        table/block_based/index_builder.cc
-        table/block_based/partitioned_filter_block.cc
-        table/block_based/uncompression_dict_reader.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_fetcher.cc
-        table/cuckoo/cuckoo_table_builder.cc
-        table/cuckoo/cuckoo_table_factory.cc
-        table/cuckoo/cuckoo_table_reader.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/data_block_hash_index.cc
+        table/data_block_footer.cc
+        table/flush_block_policy.cc
        table/format.cc
+        table/full_filter_block.cc
        table/get_context.cc
+        table/index_builder.cc
        table/iterator.cc
        table/merging_iterator.cc
        table/meta_blocks.cc
+        table/partitioned_filter_block.cc
        table/persistent_cache_helper.cc
-        table/plain/plain_table_bloom.cc
-        table/plain/plain_table_builder.cc
-        table/plain/plain_table_factory.cc
-        table/plain/plain_table_index.cc
-        table/plain/plain_table_key_coding.cc
-        table/plain/plain_table_reader.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/sst_file_reader.cc
        table/sst_file_writer.cc
        table/table_properties.cc
        table/two_level_iterator.cc
-        test_util/sync_point.cc
-        test_util/sync_point_impl.cc
-        test_util/testutil.cc
-        test_util/transaction_test_util.cc
-        tools/block_cache_analyzer/block_cache_trace_analyzer.cc
        tools/db_bench_tool.cc
        tools/dump/db_dump_tool.cc
        tools/ldb_cmd.cc
        tools/ldb_tool.cc
        tools/sst_dump_tool.cc
        tools/trace_analyzer_tool.cc
-        trace_replay/trace_replay.cc
-        trace_replay/block_cache_tracer.cc
+        util/arena.cc
+        util/auto_roll_logger.cc
        util/bloom.cc
        util/coding.cc
        util/compaction_job_stats_impl.cc
        util/comparator.cc
        util/compression_context_cache.cc
+        util/concurrent_arena.cc
        util/concurrent_task_limiter_impl.cc
        util/crc32c.cc
+        util/delete_scheduler.cc
        util/dynamic_bloom.cc
+        util/event_logger.cc
+        util/file_reader_writer.cc
+        util/file_util.cc
+        util/filename.cc
        util/filter_policy.cc
        util/hash.cc
+        util/jemalloc_nodump_allocator.cc
+        util/log_buffer.cc
        util/murmurhash.cc
        util/random.cc
        util/rate_limiter.cc
        util/slice.cc
+        util/sst_file_manager_impl.cc
        util/status.cc
        util/string_util.cc
+        util/sync_point.cc
+        util/sync_point_impl.cc
+        util/testutil.cc
        util/thread_local.cc
        util/threadpool_imp.cc
+        util/trace_replay.cc
+        util/transaction_test_util.cc
        util/xxhash.cc
        utilities/backupable/backupable_db.cc
        utilities/blob_db/blob_compaction_filter.cc
@@ -675,15 +648,14 @@ set(SOURCES
        utilities/env_mirror.cc
        utilities/env_timed.cc
        utilities/leveldb_options/leveldb_options.cc
+        utilities/lua/rocks_lua_compaction_filter.cc
        utilities/memory/memory_util.cc
        utilities/merge_operators/bytesxor.cc
        utilities/merge_operators/max.cc
        utilities/merge_operators/put.cc
-        utilities/merge_operators/sortlist.cc
        utilities/merge_operators/string_append/stringappend.cc
        utilities/merge_operators/string_append/stringappend2.cc
        utilities/merge_operators/uint64add.cc
-        utilities/object_registry.cc
        utilities/option_change_migration/option_change_migration.cc
        utilities/options/options_util.cc
        utilities/persistent_cache/block_cache_tier.cc
@@ -691,7 +663,6 @@ set(SOURCES
        utilities/persistent_cache/block_cache_tier_metadata.cc
        utilities/persistent_cache/persistent_cache_tier.cc
        utilities/persistent_cache/volatile_tier_impl.cc
-        utilities/simulator_cache/cache_simulator.cc
        utilities/simulator_cache/sim_cache.cc
        utilities/table_properties_collectors/compact_on_deletion_collector.cc
        utilities/trace/file_trace_reader_writer.cc
@@ -725,11 +696,6 @@ if(HAVE_POWER8)
    util/crc32c_ppc_asm.S)
 endif(HAVE_POWER8)

-if(HAS_ARMV8_CRC)
-  list(APPEND SOURCES
-    util/crc32c_arm64.cc)
-endif(HAS_ARMV8_CRC)
-
 if(WIN32)
  list(APPEND SOURCES
    port/win/io_win.cc
@@ -756,15 +722,6 @@ else()
    env/io_posix.cc)
 endif()

-if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-  list(APPEND SOURCES
-    third-party/folly/folly/detail/Futex.cpp
-    third-party/folly/folly/synchronization/AtomicNotification.cpp
-    third-party/folly/folly/synchronization/DistributedMutex.cpp
-    third-party/folly/folly/synchronization/ParkingLot.cpp
-    third-party/folly/folly/synchronization/WaitOptions.cpp)
-endif()
-
 set(ROCKSDB_STATIC_LIB rocksdb${ARTIFACT_SUFFIX})
 set(ROCKSDB_SHARED_LIB rocksdb-shared${ARTIFACT_SUFFIX})
 set(ROCKSDB_IMPORT_LIB ${ROCKSDB_SHARED_LIB})
@@ -788,8 +745,8 @@ else()
    ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
  set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
                        LINKER_LANGUAGE CXX
-                        VERSION ${rocksdb_VERSION}
-                        SOVERSION ${rocksdb_VERSION_MAJOR}
+                        VERSION ${ROCKSDB_VERSION}
+                        SOVERSION ${ROCKSDB_VERSION_MAJOR}
                        CXX_STANDARD 11
                        OUTPUT_NAME "rocksdb")
 endif()
@@ -844,7 +801,7 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)

  write_basic_package_version_file(
    RocksDBConfigVersion.cmake
-    VERSION ${rocksdb_VERSION}
+    VERSION ${ROCKSDB_VERSION}
    COMPATIBILITY SameMajorVersion
  )

@@ -886,16 +843,15 @@ endif()

 option(WITH_TESTS "build with tests" ON)
 if(WITH_TESTS)
-  add_subdirectory(third-party/gtest-1.8.1/fused-src/gtest)
  set(TESTS
        cache/cache_test.cc
        cache/lru_cache_test.cc
        db/column_family_test.cc
        db/compact_files_test.cc
-        db/compaction/compaction_job_stats_test.cc
-        db/compaction/compaction_job_test.cc
-        db/compaction/compaction_iterator_test.cc
-        db/compaction/compaction_picker_test.cc
+        db/compaction_iterator_test.cc
+        db/compaction_job_stats_test.cc
+        db/compaction_job_test.cc
+        db/compaction_picker_test.cc
        db/comparator_db_test.cc
        db/corruption_test.cc
        db/cuckoo_table_db_test.cc
@@ -915,11 +871,9 @@ if(WITH_TESTS)
        db/db_log_iter_test.cc
        db/db_memtable_test.cc
        db/db_merge_operator_test.cc
-        db/db_merge_operand_test.cc
        db/db_options_test.cc
        db/db_properties_test.cc
        db/db_range_del_test.cc
-        db/db_impl/db_secondary_test.cc
        db/db_sst_test.cc
        db/db_statistics_test.cc
        db/db_table_properties_test.cc
@@ -963,41 +917,37 @@ if(WITH_TESTS)
        env/env_basic_test.cc
        env/env_test.cc
        env/mock_env_test.cc
-        file/delete_scheduler_test.cc
-        logging/auto_roll_logger_test.cc
-        logging/env_logger_test.cc
-        logging/event_logger_test.cc
-        memory/arena_test.cc
        memtable/inlineskiplist_test.cc
        memtable/skiplist_test.cc
        memtable/write_buffer_manager_test.cc
        monitoring/histogram_test.cc
        monitoring/iostats_context_test.cc
        monitoring/statistics_test.cc
-        monitoring/stats_history_test.cc
        options/options_settable_test.cc
        options/options_test.cc
-        table/block_based/block_based_filter_block_test.cc
-        table/block_based/block_test.cc
-        table/block_based/data_block_hash_index_test.cc
-        table/block_based/full_filter_block_test.cc
-        table/block_based/partitioned_filter_block_test.cc
+        table/block_based_filter_block_test.cc
+        table/block_test.cc
        table/cleanable_test.cc
-        table/cuckoo/cuckoo_table_builder_test.cc
-        table/cuckoo/cuckoo_table_reader_test.cc
+        table/cuckoo_table_builder_test.cc
+        table/cuckoo_table_reader_test.cc
+        table/data_block_hash_index_test.cc
+        table/full_filter_block_test.cc
        table/merger_test.cc
        table/sst_file_reader_test.cc
        table/table_test.cc
-        tools/block_cache_analyzer/block_cache_trace_analyzer_test.cc
        tools/ldb_cmd_test.cc
        tools/reduce_levels_test.cc
        tools/sst_dump_test.cc
        tools/trace_analyzer_test.cc
+        util/arena_test.cc
+        util/auto_roll_logger_test.cc
        util/autovector_test.cc
        util/bloom_test.cc
        util/coding_test.cc
        util/crc32c_test.cc
+        util/delete_scheduler_test.cc
        util/dynamic_bloom_test.cc
+        util/event_logger_test.cc
        util/file_reader_writer_test.cc
        util/filelock_test.cc
        util/hash_test.cc
@@ -1015,6 +965,7 @@ if(WITH_TESTS)
        utilities/cassandra/cassandra_row_merge_test.cc
        utilities/cassandra/cassandra_serialize_test.cc
        utilities/checkpoint/checkpoint_test.cc
+        utilities/lua/rocks_lua_test.cc
        utilities/memory/memory_test.cc
        utilities/merge_operators/string_append/stringappend_test.cc
        utilities/object_registry_test.cc
@@ -1022,7 +973,6 @@ if(WITH_TESTS)
        utilities/options/options_util_test.cc
        utilities/persistent_cache/hash_table_test.cc
        utilities/persistent_cache/persistent_cache_test.cc
-        utilities/simulator_cache/cache_simulator_test.cc
        utilities/simulator_cache/sim_cache_test.cc
        utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
        utilities/transactions/optimistic_transaction_test.cc
@@ -1036,10 +986,6 @@ if(WITH_TESTS)
    list(APPEND TESTS utilities/env_librados_test.cc)
  endif()

-  if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-    list(APPEND TESTS third-party/folly/folly/synchronization/test/DistributedMutexTest.cpp)
-  endif()
-
  set(BENCHMARKS
    cache/cache_bench.cc
    memtable/memtablerep_bench.cc
@@ -1047,7 +993,7 @@ if(WITH_TESTS)
    tools/db_bench.cc
    table/table_reader_bench.cc
    utilities/persistent_cache/hash_table_bench.cc)
-  add_library(testharness OBJECT test_util/testharness.cc)
+  add_library(testharness OBJECT util/testharness.cc)
  foreach(sourcefile ${BENCHMARKS})
    get_filename_component(exename ${sourcefile} NAME_WE)
    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
@@ -1061,7 +1007,7 @@ if(WITH_TESTS)
      db/db_test_util.cc
      monitoring/thread_status_updater_debug.cc
      table/mock_table.cc
-      test_util/fault_injection_test_env.cc
+      util/fault_injection_test_env.cc
      utilities/cassandra/test_utils.cc
  )
  # test utilities are only build in debug
@@ -1,77 +1,3 @@
 # Code of Conduct

-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to make participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, sex characteristics, gender identity and expression,
-level of experience, education, socio-economic status, nationality, personal
-appearance, race, religion, or sexual identity and orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-  advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-  address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies within all project spaces, and it also applies when
-an individual is representing the project or its community in public spaces.
-Examples of representing a project or community include using an official
-project e-mail address, posting via an official social media account, or acting
-as an appointed representative at an online or offline event. Representation of
-a project may be further defined and clarified by project maintainers.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at <opensource-conduct@fb.com>. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
-
+Facebook has adopted a Code of Conduct that we expect project participants to adhere to. Please [read the full text](https://code.facebook.com/codeofconduct) so that you can understand what actions will and will not be tolerated.
@@ -1,165 +1,5 @@
 # Rocksdb Change Log
 ## Unreleased
-### Bug Fixes
-* Fixed a number of data races in BlobDB.
-* Fix a bug where the compaction snapshot refresh feature is not disabled as advertised when `snap_refresh_nanos` is set to 0..
-* Fix bloom filter lookups by the MultiGet batching API when BlockBasedTableOptions::whole_key_filtering is false, by checking that a key is in the perfix_extractor domain and extracting the prefix before looking up.
-* Fix a bug in file ingestion caused by incorrect file number allocation when the number of column families involved in the ingestion exceeds 2.
-* Fix a bug when format_version=3, partitioned fitlers, and prefix search are used in conjunction. The bug could result into Seek::(prefix) returning NotFound for an existing prefix.
-* Revert the feature "Merging iterator to avoid child iterator reseek for some cases (#5286)" since it might cause strong results when reseek happens with a different iterator upper bound.
-### New Features
-* Introduced DBOptions::max_write_batch_group_size_bytes to configure maximum limit on number of bytes that are written in a single batch of WAL or memtable write. It is followed when the leader write size is larger than 1/8 of this limit.
-* VerifyChecksum() by default will issue readahead. Allow ReadOptions to be passed in to those functions to override the readhead size. For checksum verifying before external SST file ingestion, a new option IngestExternalFileOptions.verify_checksums_readahead_size, is added for this readahead setting.
-* When user uses options.force_consistency_check in RocksDb, instead of crashing the process, we now pass the error back to the users without killing the process.
-* Add an option `memtable_insert_hint_per_batch` to WriteOptions. If it is true, each WriteBatch will maintain its own insert hints for each memtable in concurrent write. See include/rocksdb/options.h for more details.
-* The `sst_dump` command line tool `recompress` command now displays how many blocks were compressed and how many were not, in particular how many were not compressed because the compression ratio was not met (12.5% threshold for GoodCompressionRatio), as seen in the `number.block.not_compressed` counter stat since version 6.0.0.
-* The block cache usage is now takes into account the overhead of metadata per each entry. This results into more accurate managment of memory. A side-effect of this feature is that less items are fit into the block cache of the same size, which would result to higher cache miss rates. This can be remedied by increasing the block cache size or passing kDontChargeCacheMetadata to its constuctor to restore the old behavior.
-### Public API Change
-* Added max_write_buffer_size_to_maintain option to better control memory usage of immutable memtables.
-* Added a lightweight API GetCurrentWalFile() to get last live WAL filename and size. Meant to be used as a helper for backup/restore tooling in a larger ecosystem such as MySQL with a MyRocks storage engine.
-* The MemTable Bloom filter, when enabled, now always uses cache locality. Options::bloom_locality now only affects the PlainTable SST format.
-* Deprecate `snap_refresh_nanos` option.
-* Added DisableManualCompaction/EnableManualCompaction to stop and resume manual compaction.
-* Add TryCatchUpWithPrimary() to StackableDB in non-LITE mode.
-### Performance Improvements
-* Improve the speed of the MemTable Bloom filter, reducing the write overhead of enabling it by 1/3 to 1/2, with similar benefit to read performance.
-
-## 6.4.0 (7/30/2019)
-### Default Option Change
-* LRUCacheOptions.high_pri_pool_ratio is set to 0.5 (previously 0.0) by default, which means that by default midpoint insertion is enabled. The same change is made for the default value of high_pri_pool_ratio argument in NewLRUCache(). When block cache is not explictly created, the small block cache created by BlockBasedTable will still has this option to be 0.0.
-* Change BlockBasedTableOptions.cache_index_and_filter_blocks_with_high_priority's default value from false to true.
-
-### Public API Change
-* Filter and compression dictionary blocks are now handled similarly to data blocks with regards to the block cache: instead of storing objects in the cache, only the blocks themselves are cached. In addition, filter and compression dictionary blocks (as well as filter partitions) no longer get evicted from the cache when a table is closed.
-* Due to the above refactoring, block cache eviction statistics for filter and compression dictionary blocks are temporarily broken. We plan to reintroduce them in a later phase.
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-* Errors related to the retrieval of the compression dictionary are now propagated to the user.
-* db_bench adds a "benchmark" stats_history, which prints out the whole stats history.
-* Overload GetAllKeyVersions() to support non-default column family.
-* Added new APIs ExportColumnFamily() and CreateColumnFamilyWithImport() to support export and import of a Column Family. https://github.com/facebook/rocksdb/issues/3469
-* ldb sometimes uses a string-append merge operator if no merge operator is passed in. This is to allow users to print keys from a DB with a merge operator.
-* Replaces old Registra with ObjectRegistry to allow user to create custom object from string, also add LoadEnv() to Env.
-* Added new overload of GetApproximateSizes which gets SizeApproximationOptions object and returns a Status. The older overloads are redirecting their calls to this new method and no longer assert if the include_flags doesn't have either of INCLUDE_MEMTABLES or INCLUDE_FILES bits set. It's recommended to use the new method only, as it is more type safe and returns a meaningful status in case of errors.
-* LDBCommandRunner::RunCommand() to return the status code as an integer, rather than call exit() using the code.
-
-### New Features
-* Add argument `--secondary_path` to ldb to open the database as the secondary instance. This would keep the original DB intact.
-* Compression dictionary blocks are now prefetched and pinned in the cache (based on the customer's settings) the same way as index and filter blocks.
-* Added DBOptions::log_readahead_size which specifies the number of bytes to prefetch when reading the log. This is mostly useful for reading a remotely located log, as it can save the number of round-trips. If 0 (default), then the prefetching is disabled.
-* Added new option in SizeApproximationOptions used with DB::GetApproximateSizes. When approximating the files total size that is used to store a keys range, allow approximation with an error margin of up to total_files_size * files_size_error_margin. This allows to take some shortcuts in files size approximation, resulting in better performance, while guaranteeing the resulting error is within a reasonable margin.
-* Support loading custom objects in unit tests. In the affected unit tests, RocksDB will create custom Env objects based on environment variable TEST_ENV_URI. Users need to make sure custom object types are properly registered. For example, a static library should expose a `RegisterCustomObjects` function. By linking the unit test binary with the static library, the unit test can execute this function.
-
-### Performance Improvements
-* Reduce iterator key comparision for upper/lower bound check.
-* Improve performance of row_cache: make reads with newer snapshots than data in an SST file share the same cache key, except in some transaction cases.
-* The compression dictionary is no longer copied to a new object upon retrieval.
-
-### Bug Fixes
-* Fix ingested file and directory not being fsync.
-* Return TryAgain status in place of Corruption when new tail is not visible to TransactionLogIterator.
-* Fixed a regression where the fill_cache read option also affected index blocks.
-* Fixed an issue where using cache_index_and_filter_blocks==false affected partitions of partitioned indexes/filters as well.
-
-## 6.3.2 (8/15/2019)
-### Public API Change
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-
-### Bug Fixes
-* Fixed a regression where the fill_cache read option also affected index blocks.
-* Fixed an issue where using cache_index_and_filter_blocks==false affected partitions of partitioned indexes as well.
-
-## 6.3.1 (7/24/2019)
-### Bug Fixes
-* Fix auto rolling bug introduced in 6.3.0, which causes segfault if log file creation fails.
-
-## 6.3.0 (6/18/2019)
-### Public API Change
-* Now DB::Close() will return Aborted() error when there is unreleased snapshot. Users can retry after all snapshots are released.
-* Index blocks are now handled similarly to data blocks with regards to the block cache: instead of storing objects in the cache, only the blocks themselves are cached. In addition, index blocks no longer get evicted from the cache when a table is closed, can now use the compressed block cache (if any), and can be shared among multiple table readers.
-* Partitions of partitioned indexes no longer affect the read amplification statistics.
-* Due to the above refactoring, block cache eviction statistics for indexes are temporarily broken. We plan to reintroduce them in a later phase.
-* options.keep_log_file_num will be enforced strictly all the time. File names of all log files will be tracked, which may take significantly amount of memory if options.keep_log_file_num is large and either of options.max_log_file_size or options.log_file_time_to_roll is set.
-* Add initial support for Get/Put with user timestamps. Users can specify timestamps via ReadOptions and WriteOptions when calling DB::Get and DB::Put.
-* Accessing a partition of a partitioned filter or index through a pinned reference is no longer considered a cache hit.
-* Add C bindings for secondary instance, i.e. DBImplSecondary.
-* Rate limited deletion of WALs is only enabled if DBOptions::wal_dir is not set, or explicitly set to db_name passed to DB::Open and DBOptions::db_paths is empty, or same as db_paths[0].path
-
-### New Features
-* Add an option `snap_refresh_nanos` (default to 0) to periodically refresh the snapshot list in compaction jobs. Assign to 0 to disable the feature.
-* Add an option `unordered_write` which trades snapshot guarantees with higher write throughput. When used with WRITE_PREPARED transactions with two_write_queues=true, it offers higher throughput with however no compromise on guarantees.
-* Allow DBImplSecondary to remove memtables with obsolete data after replaying MANIFEST and WAL.
-* Add an option `failed_move_fall_back_to_copy` (default is true) for external SST ingestion. When `move_files` is true and hard link fails, ingestion falls back to copy if `failed_move_fall_back_to_copy` is true. Otherwise, ingestion reports an error.
-* Add command `list_file_range_deletes` in ldb, which prints out tombstones in SST files.
-
-### Performance Improvements
-* Reduce binary search when iterator reseek into the same data block.
-* DBIter::Next() can skip user key checking if previous entry's seqnum is 0.
-* Merging iterator to avoid child iterator reseek for some cases
-* Log Writer will flush after finishing the whole record, rather than a fragment.
-* Lower MultiGet batching API latency by reading data blocks from disk in parallel
-
-### General Improvements
-* Added new status code kColumnFamilyDropped to distinguish between Column Family Dropped and DB Shutdown in progress.
-* Improve ColumnFamilyOptions validation when creating a new column family.
-
-### Bug Fixes
-* Fix a bug in WAL replay of secondary instance by skipping write batches with older sequence numbers than the current last sequence number.
-* Fix flush's/compaction's merge processing logic which allowed `Put`s covered by range tombstones to reappear. Note `Put`s may exist even if the user only ever called `Merge()` due to an internal conversion during compaction to the bottommost level.
-* Fix/improve memtable earliest sequence assignment and WAL replay so that WAL entries of unflushed column families will not be skipped after replaying the MANIFEST and increasing db sequence due to another flushed/compacted column family.
-* Fix a bug caused by secondary not skipping the beginning of new MANIFEST.
-* On DB open, delete WAL trash files left behind in wal_dir
-
-## 6.2.0 (4/30/2019)
-### New Features
-* Add an option `strict_bytes_per_sync` that causes a file-writing thread to block rather than exceed the limit on bytes pending writeback specified by `bytes_per_sync` or `wal_bytes_per_sync`.
-* Improve range scan performance by avoiding per-key upper bound check in BlockBasedTableIterator.
-* Introduce Periodic Compaction for Level style compaction. Files are re-compacted periodically and put in the same level.
-* Block-based table index now contains exact highest key in the file, rather than an upper bound. This may improve Get() and iterator Seek() performance in some situations, especially when direct IO is enabled and block cache is disabled. A setting BlockBasedTableOptions::index_shortening is introduced to control this behavior. Set it to kShortenSeparatorsAndSuccessor to get the old behavior.
-* When reading from option file/string/map, customized envs can be filled according to object registry.
-* Improve range scan performance when using explicit user readahead by not creating new table readers for every iterator.
-* Add index type BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey. It significantly reduces read amplification in some setups, especially for iterator seeks. It's not fully implemented yet: IO errors are not handled right.
-
-### Public API Change
-* Change the behavior of OptimizeForPointLookup(): move away from hash-based block-based-table index, and use whole key memtable filtering.
-* Change the behavior of OptimizeForSmallDb(): use a 16MB block cache, put index and filter blocks into it, and cost the memtable size to it. DBOptions.OptimizeForSmallDb() and ColumnFamilyOptions.OptimizeForSmallDb() start to take an optional cache object.
-* Added BottommostLevelCompaction::kForceOptimized to avoid double compacting newly compacted files in the bottommost level compaction of manual compaction. Note this option may prohibit the manual compaction to produce a single file in the bottommost level.
-
-### Bug Fixes
-* Adjust WriteBufferManager's dummy entry size to block cache from 1MB to 256KB.
-* Fix a race condition between WritePrepared::Get and ::Put with duplicate keys.
-* Fix crash when memtable prefix bloom is enabled and read/write a key out of domain of prefix extractor.
-* Close a WAL file before another thread deletes it.
-* Fix an assertion failure `IsFlushPending() == true` caused by one bg thread releasing the db mutex in ~ColumnFamilyData and another thread clearing `flush_requested_` flag.
-
-## 6.1.1 (4/9/2019)
-### New Features
-* When reading from option file/string/map, customized comparators and/or merge operators can be filled according to object registry.
-
-### Public API Change
-
-### Bug Fixes
-* Fix a bug in 2PC where a sequence of txn prepare, memtable flush, and crash could result in losing the prepared transaction.
-* Fix a bug in Encryption Env which could cause encrypted files to be read beyond file boundaries.
-
-## 6.1.0 (3/27/2019)
-### New Features
-* Introduce two more stats levels, kExceptHistogramOrTimers and kExceptTimers.
-* Added a feature to perform data-block sampling for compressibility, and report stats to user.
-* Add support for trace filtering.
-* Add DBOptions.avoid_unnecessary_blocking_io. If true, we avoid file deletion when destorying ColumnFamilyHandle and Iterator. Instead, a job is scheduled to delete the files in background.
-
-### Public API Change
-* Remove bundled fbson library.
-* statistics.stats_level_ becomes atomic. It is preferred to use statistics.set_stats_level() and statistics.get_stats_level() to access it.
-* Introduce a new IOError subcode, PathNotFound, to indicate trying to open a nonexistent file or directory for read.
-* Add initial support for multiple db instances sharing the same data in single-writer, multi-reader mode.
-* Removed some "using std::xxx" from public headers.
-
-### Bug Fixes
-* Fix JEMALLOC_CXX_THROW macro missing from older Jemalloc versions, causing build failures on some platforms.
-* Fix SstFileReader not able to open file ingested with write_glbal_seqno=true.
-
-## 6.0.0 (2/19/2019)
 ### New Features
 * Enabled checkpoint on readonly db (DBImplReadOnly).
 * Make DB ignore dropped column families while committing results of atomic flush.
@@ -167,16 +7,8 @@
 * For users of dictionary compression with ZSTD v0.7.0+, we now reuse the same digested dictionary when compressing each of an SST file's data blocks for faster compression speeds.
 * For all users of dictionary compression who set `cache_index_and_filter_blocks == true`, we now store dictionary data used for decompression in the block cache for better control over memory usage. For users of ZSTD v1.1.4+ who compile with -DZSTD_STATIC_LINKING_ONLY, this includes a digested dictionary, which is used to increase decompression speed.
 * Add support for block checksums verification for external SST files before ingestion.
-* Introduce stats history which periodically saves Statistics snapshots and added `GetStatsHistory` API to retrieve these snapshots.
-* Add a place holder in manifest which indicate a record from future that can be safely ignored.
-* Add support for trace sampling.
-* Enable properties block checksum verification for block-based tables.
-* For all users of dictionary compression, we now generate a separate dictionary for compressing each bottom-level SST file. Previously we reused a single dictionary for a whole compaction to bottom level. The new approach achieves better compression ratios; however, it uses more memory and CPU for buffering/sampling data blocks and training dictionaries.
-* Add whole key bloom filter support in memtable.
-* Files written by `SstFileWriter` will now use dictionary compression if it is configured in the file writer's `CompressionOptions`.

 ### Public API Change
-* Disallow CompactionFilter::IgnoreSnapshots() = false, because it is not very useful and the behavior is confusing. The filter will filter everything if there is no snapshot declared by the time the compaction starts. However, users can define a snapshot after the compaction starts and before it finishes and this new snapshot won't be repeatable, because after the compaction finishes, some keys may be dropped.
 * CompactionPri = kMinOverlappingRatio also uses compensated file size, which boosts file with lots of tombstones to be compacted first.
 * Transaction::GetForUpdate is extended with a do_validate parameter with default value of true. If false it skips validating the snapshot before doing the read. Similarly ::Merge, ::Put, ::Delete, and ::SingleDelete are extended with assume_tracked with default value of false. If true it indicates that call is assumed to be after a ::GetForUpdate.
 * `TableProperties::num_entries` and `TableProperties::num_deletions` now also account for number of range tombstones.
@@ -184,11 +16,7 @@
 * With "ldb ----try_load_options", when wal_dir specified by the option file doesn't exist, ignore it.
 * Change time resolution in FileOperationInfo.
 * Deleting Blob files also go through SStFileManager.
-* Remove CuckooHash memtable.
-* The counter stat `number.block.not_compressed` now also counts blocks not compressed due to poor compression ratio.
-* Remove ttl option from `CompactionOptionsFIFO`. The option has been deprecated and ttl in `ColumnFamilyOptions` is used instead.
-* Support SST file ingestion across multiple column families via DB::IngestExternalFiles. See the function's comment about atomicity.
-* Remove Lua compaction filter.
+* Remove PlainTable's store_index_in_file feature. When opening an existing DB with index in SST files, the index and bloom filter will still be rebuild while SST files are opened, in the same way as there is no index in the file.

 ### Bug Fixes
 * Fix a deadlock caused by compaction and file ingestion waiting for each other in the event of write stalls.
@@ -1,9 +1,7 @@
 This is the list of all known third-party language bindings for RocksDB. If something is missing, please open a pull request to add it.

 * Java - https://github.com/facebook/rocksdb/tree/master/java
-* Python
-    * http://python-rocksdb.readthedocs.io/en/latest/
-    * http://pyrocksdb.readthedocs.org/en/latest/ (unmaintained)
+* Python - http://pyrocksdb.readthedocs.org/en/latest/
 * Perl - https://metacpan.org/pod/RocksDB
 * Node.js - https://npmjs.org/package/rocksdb
 * Go - https://github.com/tecbot/gorocksdb
@@ -82,23 +82,17 @@ ifeq ($(MAKECMDGOALS),rocksdbjavastatic)
 endif

 ifeq ($(MAKECMDGOALS),rocksdbjavastaticrelease)
-	ifneq ($(DEBUG_LEVEL),2)
-		DEBUG_LEVEL=0
-	endif
+	DEBUG_LEVEL=0
 endif

 ifeq ($(MAKECMDGOALS),rocksdbjavastaticreleasedocker)
-	ifneq ($(DEBUG_LEVEL),2)
-		DEBUG_LEVEL=0
-	endif
+        DEBUG_LEVEL=0
 endif

 ifeq ($(MAKECMDGOALS),rocksdbjavastaticpublish)
 	DEBUG_LEVEL=0
 endif

-$(info $$DEBUG_LEVEL is ${DEBUG_LEVEL})
-
 # Lite build flag.
 LITE ?= 0
 ifeq ($(LITE), 0)
@@ -143,12 +137,6 @@ CFLAGS +=  -DHAVE_POWER8
 HAVE_POWER8=1
 endif

-ifeq (,$(shell $(CXX) -fsyntax-only -march=armv8-a+crc+crypto -xc /dev/null 2>&1))
-CXXFLAGS += -march=armv8-a+crc+crypto
-CFLAGS += -march=armv8-a+crc+crypto
-ARMCRC_SOURCE=1
-endif
-
 # if we're compiling for release, compile without debug code (-DNDEBUG)
 ifeq ($(DEBUG_LEVEL),0)
 OPT += -DNDEBUG
@@ -256,8 +244,8 @@ endif
 ifdef COMPILE_WITH_TSAN
 	DISABLE_JEMALLOC=1
 	EXEC_LDFLAGS += -fsanitize=thread
-	PLATFORM_CCFLAGS += -fsanitize=thread -fPIC -DFOLLY_SANITIZE_THREAD
-	PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC -DFOLLY_SANITIZE_THREAD
+	PLATFORM_CCFLAGS += -fsanitize=thread -fPIC
+	PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC
        # Turn off -pg when enabling TSAN testing, because that induces
        # a link failure.  TODO: find the root cause
 	PROFILING_FLAGS =
@@ -304,13 +292,9 @@ ifndef DISABLE_JEMALLOC
 	PLATFORM_CCFLAGS += $(JEMALLOC_INCLUDE)
 endif

-ifndef USE_FOLLY_DISTRIBUTED_MUTEX
-	USE_FOLLY_DISTRIBUTED_MUTEX=0
-endif
-
 export GTEST_THROW_ON_FAILURE=1
 export GTEST_HAS_EXCEPTIONS=1
-GTEST_DIR = ./third-party/gtest-1.8.1/fused-src
+GTEST_DIR = ./third-party/gtest-1.7.0/fused-src
 # AIX: pre-defined system headers are surrounded by an extern "C" block
 ifeq ($(PLATFORM), OS_AIX)
 	PLATFORM_CCFLAGS += -I$(GTEST_DIR)
@@ -320,23 +304,6 @@ else
 	PLATFORM_CXXFLAGS += -isystem $(GTEST_DIR)
 endif

-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-	FOLLY_DIR = ./third-party/folly
-	# AIX: pre-defined system headers are surrounded by an extern "C" block
-	ifeq ($(PLATFORM), OS_AIX)
-		PLATFORM_CCFLAGS += -I$(FOLLY_DIR)
-		PLATFORM_CXXFLAGS += -I$(FOLLY_DIR)
-	else
-		PLATFORM_CCFLAGS += -isystem $(FOLLY_DIR)
-		PLATFORM_CXXFLAGS += -isystem $(FOLLY_DIR)
-	endif
-endif
-
-ifdef TEST_CACHE_LINE_SIZE
-  PLATFORM_CCFLAGS += -DTEST_CACHE_LINE_SIZE=$(TEST_CACHE_LINE_SIZE)
-  PLATFORM_CXXFLAGS += -DTEST_CACHE_LINE_SIZE=$(TEST_CACHE_LINE_SIZE)
-endif
-
 # This (the first rule) must depend on "all".
 default: all

@@ -423,13 +390,10 @@ endif

 LIBOBJECTS += $(TOOL_LIB_SOURCES:.cc=.o)
 MOCKOBJECTS = $(MOCK_LIB_SOURCES:.cc=.o)
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-  FOLLYOBJECTS = $(FOLLY_SOURCES:.cpp=.o)
-endif

 GTEST = $(GTEST_DIR)/gtest/gtest-all.o
-TESTUTIL = ./test_util/testutil.o
-TESTHARNESS = ./test_util/testharness.o $(TESTUTIL) $(MOCKOBJECTS) $(GTEST)
+TESTUTIL = ./util/testutil.o
+TESTHARNESS = ./util/testharness.o $(TESTUTIL) $(MOCKOBJECTS) $(GTEST)
 VALGRIND_ERROR = 2
 VALGRIND_VER := $(join $(VALGRIND_VER),valgrind)

@@ -456,7 +420,6 @@ TESTS = \
 	inlineskiplist_test \
 	env_basic_test \
 	env_test \
-	env_logger_test \
 	hash_test \
 	thread_local_test \
 	rate_limiter_test \
@@ -466,10 +429,10 @@ TESTS = \
 	db_block_cache_test \
 	db_test \
 	db_blob_index_test \
+	db_bloom_filter_test \
 	db_iter_test \
 	db_iter_stress_test \
 	db_log_iter_test \
-	db_bloom_filter_test \
 	db_compaction_filter_test \
 	db_compaction_test \
 	db_dynamic_level_test \
@@ -478,10 +441,8 @@ TESTS = \
 	db_iterator_test \
 	db_memtable_test \
 	db_merge_operator_test \
-	db_merge_operand_test \
 	db_options_test \
 	db_range_del_test \
-	db_secondary_test \
 	db_sst_test \
 	db_tailing_iter_test \
 	db_io_failure_test \
@@ -525,7 +486,6 @@ TESTS = \
 	plain_table_db_test \
 	comparator_db_test \
 	external_sst_file_test \
-	import_column_family_test \
 	prefix_test \
 	skiplist_test \
 	write_buffer_manager_test \
@@ -536,7 +496,6 @@ TESTS = \
 	cassandra_serialize_test \
 	ttl_test \
 	backupable_db_test \
-	cache_simulator_test \
 	sim_cache_test \
 	version_edit_test \
 	version_set_test \
@@ -576,7 +535,7 @@ TESTS = \
 	ldb_cmd_test \
 	persistent_cache_test \
 	statistics_test \
-	stats_history_test \
+	lua_test \
 	lru_cache_test \
 	object_registry_test \
 	repair_test \
@@ -589,17 +548,9 @@ TESTS = \
 	range_tombstone_fragmenter_test \
 	range_del_aggregator_test \
 	sst_file_reader_test \
-	db_secondary_test \
-	block_cache_tracer_test \
-	block_cache_trace_analyzer_test \
-
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-	TESTS += folly_synchronization_distributed_mutex_test
-endif

 PARALLEL_TEST = \
 	backupable_db_test \
-	db_bloom_filter_test \
 	db_compaction_filter_test \
 	db_compaction_test \
 	db_merge_operator_test \
@@ -608,9 +559,7 @@ PARALLEL_TEST = \
 	db_universal_compaction_test \
 	db_wal_test \
 	external_sst_file_test \
-	import_column_family_test \
 	fault_injection_test \
-	file_reader_writer_test \
 	inlineskiplist_test \
 	manual_compaction_test \
 	persistent_cache_test \
@@ -643,7 +592,6 @@ TOOLS = \
 	rocksdb_undump \
 	blob_dump \
 	trace_analyzer \
-	block_cache_trace_analyzer \

 TEST_LIBS = \
 	librocksdb_env_basic_test.a
@@ -739,8 +687,7 @@ endif  # PLATFORM_SHARED_EXT
 .PHONY: blackbox_crash_test check clean coverage crash_test ldb_tests package \
 	release tags tags0 valgrind_check whitebox_crash_test format static_lib shared_lib all \
 	dbg rocksdbjavastatic rocksdbjava install install-static install-shared uninstall \
-	analyze tools tools_lib \
-	blackbox_crash_test_with_atomic_flush whitebox_crash_test_with_atomic_flush
+	analyze tools tools_lib


 all: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(TESTS)
@@ -948,15 +895,11 @@ ldb_tests: ldb

 crash_test: whitebox_crash_test blackbox_crash_test

-crash_test_with_atomic_flush: whitebox_crash_test_with_atomic_flush blackbox_crash_test_with_atomic_flush
-
 blackbox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --enable_atomic_flush blackbox $(CRASH_TEST_EXT_ARGS)
 	python -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)

-blackbox_crash_test_with_atomic_flush: db_stress
-	python -u tools/db_crashtest.py --cf_consistency blackbox $(CRASH_TEST_EXT_ARGS)
-
 ifeq ($(CRASH_TEST_KILL_ODD),)
  CRASH_TEST_KILL_ODD=888887
 endif
@@ -964,11 +907,9 @@ endif
 whitebox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-	python -u tools/db_crashtest.py whitebox  --random_kill_odd \
+	python -u tools/db_crashtest.py --enable_atomic_flush whitebox  --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
-whitebox_crash_test_with_atomic_flush: db_stress
-	python -u tools/db_crashtest.py --cf_consistency whitebox  --random_kill_odd \
+	python -u tools/db_crashtest.py whitebox  --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

 asan_check:
@@ -981,11 +922,6 @@ asan_crash_test:
 	COMPILE_WITH_ASAN=1 $(MAKE) crash_test
 	$(MAKE) clean

-asan_crash_test_with_atomic_flush:
-	$(MAKE) clean
-	COMPILE_WITH_ASAN=1 $(MAKE) crash_test_with_atomic_flush
-	$(MAKE) clean
-
 ubsan_check:
 	$(MAKE) clean
 	COMPILE_WITH_UBSAN=1 $(MAKE) check -j32
@@ -996,11 +932,6 @@ ubsan_crash_test:
 	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test
 	$(MAKE) clean

-ubsan_crash_test_with_atomic_flush:
-	$(MAKE) clean
-	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test_with_atomic_flush
-	$(MAKE) clean
-
 valgrind_test:
 	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check

@@ -1099,7 +1030,7 @@ rocksdb.h rocksdb.cc: build_tools/amalgamate.py Makefile $(LIB_SOURCES) unity.cc
 	build_tools/amalgamate.py -I. -i./include unity.cc -x include/rocksdb/c.h -H rocksdb.h -o rocksdb.cc

 clean:
-	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(LIBRARY) $(SHARED)
+	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(LIBRARY) $(SHARED)
 	rm -rf $(CLEAN_FILES) ios-x86 ios-arm scan_build_report
 	$(FIND) . -name "*.[oda]" -exec rm -f {} \;
 	$(FIND) . -type f -regex ".*\.\(\(gcda\)\|\(gcno\)\)" -exec rm {} \;
@@ -1145,14 +1076,6 @@ db_bench: tools/db_bench.o $(BENCHTOOLOBJECTS)
 trace_analyzer: tools/trace_analyzer.o $(ANALYZETOOLOBJECTS) $(LIBOBJECTS)
 	$(AM_LINK)

-block_cache_trace_analyzer: tools/block_cache_analyzer/block_cache_trace_analyzer_tool.o $(ANALYZETOOLOBJECTS) $(LIBOBJECTS)
-	$(AM_LINK)
-
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-folly_synchronization_distributed_mutex_test: $(LIBOBJECTS) $(TESTHARNESS) $(FOLLYOBJECTS) third-party/folly/folly/synchronization/test/DistributedMutexTest.o
-	$(AM_LINK)
-endif
-
 cache_bench: cache/cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)

@@ -1174,7 +1097,7 @@ db_sanity_test: tools/db_sanity_test.o $(LIBOBJECTS) $(TESTUTIL)
 db_repl_stress: tools/db_repl_stress.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)

-arena_test: memory/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
+arena_test: util/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 autovector_test: util/autovector_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1231,7 +1154,7 @@ histogram_test: monitoring/histogram_test.o $(LIBOBJECTS) $(TESTHARNESS)
 thread_local_test: util/thread_local_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-corruption_test: db/corruption_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+corruption_test: db/corruption_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 crc32c_test: util/crc32c_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1288,9 +1211,6 @@ db_memtable_test: db/db_memtable_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHA
 db_merge_operator_test: db/db_merge_operator_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-db_merge_operand_test: db/db_merge_operand_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 db_options_test: db/db_options_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1315,9 +1235,6 @@ external_sst_file_basic_test: db/external_sst_file_basic_test.o db/db_test_util.
 external_sst_file_test: db/external_sst_file_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-import_column_family_test: db/import_column_family_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 db_tailing_iter_test: db/db_tailing_iter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1366,9 +1283,6 @@ backupable_db_test: utilities/backupable/backupable_db_test.o $(LIBOBJECTS) $(TE
 checkpoint_test: utilities/checkpoint/checkpoint_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-cache_simulator_test: utilities/simulator_cache/cache_simulator_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 sim_cache_test: utilities/simulator_cache/sim_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1395,13 +1309,13 @@ write_batch_with_index_test: utilities/write_batch_with_index/write_batch_with_i
 flush_job_test: db/flush_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-compaction_iterator_test: db/compaction/compaction_iterator_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_iterator_test: db/compaction_iterator_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-compaction_job_test: db/compaction/compaction_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_job_test: db/compaction_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-compaction_job_stats_test: db/compaction/compaction_job_stats_test.o $(LIBOBJECTS) $(TESTHARNESS)
+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)
@@ -1425,7 +1339,7 @@ fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
 rate_limiter_test: util/rate_limiter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-delete_scheduler_test: file/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
+delete_scheduler_test: util/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1434,13 +1348,13 @@ filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
 file_reader_writer_test: util/file_reader_writer_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-block_based_filter_block_test: table/block_based/block_based_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+block_based_filter_block_test: table/block_based_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-full_filter_block_test: table/block_based/full_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+full_filter_block_test: table/full_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-partitioned_filter_block_test: table/block_based/partitioned_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+partitioned_filter_block_test: table/partitioned_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 log_test: db/log_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1452,10 +1366,10 @@ cleanable_test: table/cleanable_test.o $(LIBOBJECTS) $(TESTHARNESS)
 table_test: table/table_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-block_test: table/block_based/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+block_test: table/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-data_block_hash_index_test: table/block_based/data_block_hash_index_test.o $(LIBOBJECTS) $(TESTHARNESS)
+data_block_hash_index_test: table/data_block_hash_index_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 inlineskiplist_test: memtable/inlineskiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1473,7 +1387,7 @@ version_edit_test: db/version_edit_test.o $(LIBOBJECTS) $(TESTHARNESS)
 version_set_test: db/version_set_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-compaction_picker_test: db/compaction/compaction_picker_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_picker_test: db/compaction_picker_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 version_builder_test: db/version_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1509,10 +1423,10 @@ util_merge_operators_test: utilities/util_merge_operators_test.o $(LIBOBJECTS) $
 options_file_test: db/options_file_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-deletefile_test: db/deletefile_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+deletefile_test: db/deletefile_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-obsolete_files_test: db/obsolete_files_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+obsolete_files_test: db/obsolete_files_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
@@ -1521,10 +1435,10 @@ rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
 rocksdb_undump: tools/dump/rocksdb_undump.o $(LIBOBJECTS)
 	$(AM_LINK)

-cuckoo_table_builder_test: table/cuckoo/cuckoo_table_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
+cuckoo_table_builder_test: table/cuckoo_table_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-cuckoo_table_reader_test: table/cuckoo/cuckoo_table_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
+cuckoo_table_reader_test: table/cuckoo_table_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 cuckoo_table_db_test: db/cuckoo_table_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1554,7 +1468,7 @@ db_bench_tool_test: tools/db_bench_tool_test.o $(BENCHTOOLOBJECTS) $(TESTHARNESS
 trace_analyzer_test: tools/trace_analyzer_test.o $(LIBOBJECTS) $(ANALYZETOOLOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-event_logger_test: logging/event_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
+event_logger_test: util/event_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 timer_queue_test: util/timer_queue_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1575,10 +1489,7 @@ manual_compaction_test: db/manual_compaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 filelock_test: util/filelock_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-auto_roll_logger_test: logging/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-env_logger_test: logging/env_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
+auto_roll_logger_test: util/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 memtable_list_test: db/memtable_list_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1623,10 +1534,10 @@ persistent_cache_test: utilities/persistent_cache/persistent_cache_test.o  db/db
 statistics_test: monitoring/statistics_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-stats_history_test: monitoring/stats_history_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+lru_cache_test: cache/lru_cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-lru_cache_test: cache/lru_cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
+lua_test: utilities/lua/rocks_lua_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 range_del_aggregator_test: db/range_del_aggregator_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1647,15 +1558,6 @@ range_tombstone_fragmenter_test: db/range_tombstone_fragmenter_test.o db/db_test
 sst_file_reader_test: table/sst_file_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-db_secondary_test: db/db_impl/db_secondary_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-block_cache_tracer_test: trace_replay/block_cache_tracer_test.o trace_replay/block_cache_tracer.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-block_cache_trace_analyzer_test: tools/block_cache_analyzer/block_cache_trace_analyzer_test.o tools/block_cache_analyzer/block_cache_trace_analyzer.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1701,7 +1603,7 @@ JAVA_INCLUDE = -I$(JAVA_HOME)/include/ -I$(JAVA_HOME)/include/linux
 ifeq ($(PLATFORM), OS_SOLARIS)
 	ARCH := $(shell isainfo -b)
 else ifeq ($(PLATFORM), OS_OPENBSD)
-	ifneq (,$(filter $(MACHINE), amd64 arm64 aarch64 sparc64))
+	ifneq (,$(filter $(MACHINE), amd64 arm64 sparc64))
 		ARCH := 64
 	else
 		ARCH := 32
@@ -1710,7 +1612,7 @@ else
 	ARCH := $(shell getconf LONG_BIT)
 endif

-ifeq (,$(filter $(MACHINE), ppc arm64 aarch64 sparc64))
+ifeq (,$(findstring ppc,$(MACHINE)))
        ROCKSDBJNILIB = librocksdbjni-linux$(ARCH).so
 else
        ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE).so
@@ -1733,8 +1635,8 @@ SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/archive
 LZ4_VER ?= 1.8.3
 LZ4_SHA256 ?= 33af5936ac06536805f9745e0b6d61da606a1f8b4cc5c04dd3cbaca3b9b4fc43
 LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
-ZSTD_VER ?= 1.4.0
-ZSTD_SHA256 ?= 63be339137d2b683c6d19a9e34f4fb684790e864fee13c7dd40e197a64c705c1
+ZSTD_VER ?= 1.3.7
+ZSTD_SHA256 ?= 5dd1e90eb16c25425880c8a91327f63de22891ffed082fcc17e5ae84fce0d5fb
 ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
 CURL_SSL_OPTS ?= --tlsv1

@@ -1811,7 +1713,7 @@ endif
 	fi
 	tar xvzf snappy-$(SNAPPY_VER).tar.gz
 	mkdir snappy-$(SNAPPY_VER)/build
-	cd snappy-$(SNAPPY_VER)/build && CFLAGS='${EXTRA_CFLAGS}' CXXFLAGS='${EXTRA_CXXFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
+	cd snappy-$(SNAPPY_VER)/build && CFLAGS='${EXTRA_CFLAGS}' CXXFLAGS='${EXTRA_CXXFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' cmake .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
 	cp snappy-$(SNAPPY_VER)/build/libsnappy.a .

 liblz4.a:
@@ -1901,23 +1803,27 @@ rocksdbjavastaticreleasedocker: rocksdbjavastatic rocksdbjavastaticdockerx86 roc

 rocksdbjavastaticdockerx86:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	DOCKER_LINUX_X86_CONTAINER=`docker ps -aqf name=rocksdb_linux_x86-be`; \
+	if [ -z "$$DOCKER_LINUX_X86_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x86-be evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_x86-be

 rocksdbjavastaticdockerx86_64:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x64-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	DOCKER_LINUX_X64_CONTAINER=`docker ps -aqf name=rocksdb_linux_x64-be`; \
+	if [ -z "$$DOCKER_LINUX_X64_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_x64-be

 rocksdbjavastaticdockerppc64le:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_ppc64le-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerarm64v8:
-	mkdir -p java/target
-	DOCKER_LINUX_ARM64V8_CONTAINER=`docker ps -aqf name=rocksdb_linux_arm64v8-be`; \
-	if [ -z "$$DOCKER_LINUX_ARM64V8_CONTAINER" ]; then \
-		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_arm64v8-be evolvedbinary/rocksjava:centos7_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	DOCKER_LINUX_PPC64LE_CONTAINER=`docker ps -aqf name=rocksdb_linux_ppc64le-be`; \
+	if [ -z "$$DOCKER_LINUX_PPC64LE_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_ppc64le-be evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
 	fi
-	docker start -a rocksdb_linux_arm64v8-be
+	docker start -a rocksdb_linux_ppc64le-be

 rocksdbjavastaticpublish: rocksdbjavastaticrelease rocksdbjavastaticpublishcentral

@@ -5,7 +5,7 @@
 [![PPC64le Build Status](http://140.211.168.68:8080/buildStatus/icon?job=Rocksdb)](http://140.211.168.68:8080/job/Rocksdb)

 RocksDB is developed and maintained by Facebook Database Engineering Team.
-It is built on earlier work on [LevelDB](https://github.com/google/leveldb) by Sanjay Ghemawat (sanjay@google.com)
+It is built on earlier work on LevelDB by Sanjay Ghemawat (sanjay@google.com)
 and Jeff Dean (jeff@google.com)

 This code is a library that forms the core building block for a fast
@@ -50,10 +50,6 @@ Check out their blog post: http://blog.cloudera.com/blog/2015/08/inside-santande
 ## Airbnb
 Airbnb is using RocksDB as a storage engine for their personalized search service. You can learn more about it here: https://www.youtube.com/watch?v=ASQ6XMtogMs

-## Alluxio
-[Alluxio](https://www.alluxio.io) uses RocksDB to serve and scale file system metadata to beyond 1 Billion files. The detailed design and implementation is described in this engineering blog:
-https://www.alluxio.io/blog/scalable-metadata-service-in-alluxio-storing-billions-of-files/
-
 ## Pinterest
 Pinterest's Object Retrieval System uses RocksDB for storage: https://www.youtube.com/watch?v=MtFEVEs_2Vo

@@ -95,10 +91,4 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 [ProfaneDB](https://profanedb.gitlab.io/) is a database for Protocol Buffers, and uses RocksDB for storage. It is accessible via gRPC, and the schema is defined using directly `.proto` files.

 ## IOTA Foundation
- [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
- 
-## Avrio Project
- [Avrio Project](http://avrio-project.github.io/avrio.network/) is using RocksDB in [Avrio ](https://github.com/avrio-project/avrio) to store blocks, account balances and data and other blockchain-releated data. Avrio is a multiblockchain decentralized cryptocurrency empowering monetary transactions.
- 
-## Crux
-[Crux](https://github.com/juxt/crux) is a document database that uses RocksDB for local [EAV](https://en.wikipedia.org/wiki/Entity%E2%80%93attribute%E2%80%93value_model) index storage to enable point-in-time bitemporal Datalog queries. The "unbundled" architecture uses Kafka to provide horizontal scalability.
+ [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
@@ -43,7 +43,7 @@ We plan to use this port for our business purposes here at Bing and this provide

 * Certain headers that are not present and not necessary on Windows were simply `#ifndef OS_WIN` in a few places (`unistd.h`)
 * All posix specific headers were replaced to port/port.h which worked well
-* Replaced `dirent.h` for `port/port_dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
+* Replaced `dirent.h` for `port/dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
 * Replaced `sys/time.h` to `port/sys_time.h` (few places) implemented equivalents within `rocksdb::port`
 * `printf %z` specification is not supported on Windows. To imitate existing standards we came up with a string macro `ROCKSDB_PRIszt` which expands to `zu` on posix systems and to `Iu` on windows.
 * in class member initialization were moved to a __ctors in some cases
@@ -1,67 +1,15 @@
 version: 1.0.{build}
-
 image: Visual Studio 2017
-
-environment:
-  JAVA_HOME: C:\Program Files\Java\jdk1.8.0
-  THIRDPARTY_HOME: $(APPVEYOR_BUILD_FOLDER)\thirdparty
-  SNAPPY_HOME: $(THIRDPARTY_HOME)\snappy-1.1.7
-  SNAPPY_INCLUDE: $(SNAPPY_HOME);$(SNAPPY_HOME)\build
-  SNAPPY_LIB_DEBUG: $(SNAPPY_HOME)\build\Debug\snappy.lib
-  SNAPPY_LIB_RELEASE: $(SNAPPY_HOME)\build\Release\snappy.lib
-  LZ4_HOME: $(THIRDPARTY_HOME)\lz4-1.8.3
-  LZ4_INCLUDE: $(LZ4_HOME)\lib
-  LZ4_LIB_DEBUG: $(LZ4_HOME)\visual\VS2010\bin\x64_Debug\liblz4_static.lib
-  LZ4_LIB_RELEASE: $(LZ4_HOME)\visual\VS2010\bin\x64_Release\liblz4_static.lib
-  ZSTD_HOME: $(THIRDPARTY_HOME)\zstd-1.4.0
-  ZSTD_INCLUDE: $(ZSTD_HOME)\lib;$(ZSTD_HOME)\lib\dictBuilder
-  ZSTD_LIB_DEBUG: $(ZSTD_HOME)\build\VS2010\bin\x64_Debug\libzstd_static.lib
-  ZSTD_LIB_RELEASE: $(ZSTD_HOME)\build\VS2010\bin\x64_Release\libzstd_static.lib
-
-install:
-  - md %THIRDPARTY_HOME%
-  - echo "Building Snappy dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o snappy-1.1.7.zip https://github.com/google/snappy/archive/1.1.7.zip
-  - unzip snappy-1.1.7.zip
-  - cd snappy-1.1.7
-  - mkdir build
-  - cd build
-  - cmake -DCMAKE_GENERATOR_PLATFORM=x64 ..
-  - msbuild Snappy.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild Snappy.sln /p:Configuration=Release /p:Platform=x64
-  - echo "Building LZ4 dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o lz4-1.8.3.zip https://github.com/lz4/lz4/archive/v1.8.3.zip
-  - unzip lz4-1.8.3.zip
-  - cd lz4-1.8.3\visual\VS2010
-  - ps: $CMD="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $CMD lz4.sln /upgrade
-  - msbuild lz4.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild lz4.sln /p:Configuration=Release /p:Platform=x64
-  - echo "Building ZStd dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o zstd-1.4.0.zip https://github.com/facebook/zstd/archive/v1.4.0.zip
-  - unzip zstd-1.4.0.zip
-  - cd zstd-1.4.0\build\VS2010
-  - ps: $CMD="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $CMD zstd.sln /upgrade
-  - msbuild zstd.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild zstd.sln /p:Configuration=Release /p:Platform=x64
-
 before_build:
-  - md %APPVEYOR_BUILD_FOLDER%\build
-  - cd %APPVEYOR_BUILD_FOLDER%\build
-  - cmake -G "Visual Studio 15 Win64" -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1 ..
-  - cd ..
+- md %APPVEYOR_BUILD_FOLDER%\build
+- cd %APPVEYOR_BUILD_FOLDER%\build
+- cmake -G "Visual Studio 15 Win64" -DOPTDBG=1 -DWITH_XPRESS=1 -DPORTABLE=1 -DJNI=1 ..
+- cd ..
 build:
  project: build\rocksdb.sln
  parallel: true
  verbosity: normal
-
 test:
-
 test_script:
-  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test,db_merge_operand_test -Concurrency 8
-
-on_failure:
-  - cmd: 7z a build-failed.zip %APPVEYOR_BUILD_FOLDER%\build\ && appveyor PushArtifact build-failed.zip
+- ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test -Concurrency 8

@@ -1,34 +1,14 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
 from targets_builder import TARGETSBuilder
-import json
 import os
 import fnmatch
 import sys

 from util import ColorString

-# This script generates TARGETS file for Buck.
-# Buck is a build tool specifying dependencies among different build targets.
-# User can pass extra dependencies as a JSON object via command line, and this
-# script can include these dependencies in the generate TARGETS file.
-# Usage:
-# $python buckifier/buckify_rocksdb.py
-# (This generates a TARGET file without user-specified dependency for unit
-# tests.)
-# $python buckifier/buckify_rocksdb.py \
-#        '{"fake": { \
-#                      "extra_deps": [":test_dep", "//fakes/module:mock1"],  \
-#                      "extra_compiler_flags": ["-DROCKSDB_LITE", "-Os"], \
-#                  } \
-#         }'
-# (Generated TARGETS file has test_dep and mock1 as dependencies for RocksDB
-# unit tests, and will use the extra_compiler_flags to compile the unit test
-# source.)
-
 # tests to export as libraries for inclusion in other projects
 _EXPORTED_TEST_LIBS = ["env_basic_test"]

@@ -101,42 +81,12 @@ def get_tests(repo_path):
            else:
                # we consumed all the parallel tests
                break
-
+    
    return tests


-# Parse extra dependencies passed by user from command line
-def get_dependencies():
-    deps_map = {
-        ''.encode('ascii'): {
-            'extra_deps'.encode('ascii'): [],
-            'extra_compiler_flags'.encode('ascii'): []
-        }
-    }
-    if len(sys.argv) < 2:
-        return deps_map
-
-    def encode_dict(data):
-        rv = {}
-        for k, v in data.items():
-            if isinstance(k, unicode):
-                k = k.encode('ascii')
-            if isinstance(v, unicode):
-                v = v.encode('ascii')
-            elif isinstance(v, list):
-                v = [x.encode('ascii') for x in v]
-            elif isinstance(v, dict):
-                v = encode_dict(v)
-            rv[k] = v
-        return rv
-    extra_deps = json.loads(sys.argv[1], object_hook=encode_dict)
-    for target_alias, deps in extra_deps.items():
-        deps_map[target_alias] = deps
-    return deps_map
-
-
 # Prepare TARGETS file for buck
-def generate_targets(repo_path, deps_map):
+def generate_targets(repo_path):
    print(ColorString.info("Generating TARGETS"))
    # parsed src.mk file
    src_mk = parse_src_mk(repo_path)
@@ -167,36 +117,27 @@ def generate_targets(repo_path, deps_map):
        "rocksdb_tools_lib",
        src_mk.get("BENCH_LIB_SOURCES", []) +
        src_mk.get("ANALYZER_LIB_SOURCES", []) +
-        ["test_util/testutil.cc"],
+        ["util/testutil.cc"],
        [":rocksdb_lib"])

-    print("Extra dependencies:\n{0}".format(str(deps_map)))
    # test for every test we found in the Makefile
-    for target_alias, deps in deps_map.items():
-        for test in sorted(tests):
-            match_src = [src for src in cc_files if ("/%s.c" % test) in src]
-            if len(match_src) == 0:
-                print(ColorString.warning("Cannot find .cc file for %s" % test))
-                continue
-            elif len(match_src) > 1:
-                print(ColorString.warning("Found more than one .cc for %s" % test))
-                print(match_src)
-                continue
+    for test in sorted(tests):
+        match_src = [src for src in cc_files if ("/%s.c" % test) in src]
+        if len(match_src) == 0:
+            print(ColorString.warning("Cannot find .cc file for %s" % test))
+            continue
+        elif len(match_src) > 1:
+            print(ColorString.warning("Found more than one .cc for %s" % test))
+            print(match_src)
+            continue

-            assert(len(match_src) == 1)
-            is_parallel = tests[test]
-            test_target_name = \
-                test if not target_alias else test + "_" + target_alias
-            TARGETS.register_test(
-                test_target_name,
-                match_src[0],
-                is_parallel,
-                deps['extra_deps'],
-                deps['extra_compiler_flags'])
+        assert(len(match_src) == 1)
+        is_parallel = tests[test]
+        TARGETS.register_test(test, match_src[0], is_parallel)

-            if test in _EXPORTED_TEST_LIBS:
-                test_library = "%s_lib" % test_target_name
-                TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
+        if test in _EXPORTED_TEST_LIBS:
+            test_library = "%s_lib" % test
+            TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
    TARGETS.flush_tests()

    print(ColorString.info("Generated TARGETS Summary:"))
@@ -221,9 +162,8 @@ def exit_with_error(msg):


 def main():
-    deps_map = get_dependencies()
    # Generate TARGETS file for buck
-    ok = generate_targets(get_rocksdb_path(), deps_map)
+    ok = generate_targets(get_rocksdb_path())
    if not ok:
        exit_with_error("Failed to generate TARGETS files")

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # Create a tmp directory for the test to use
 TEST_DIR=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
 # shellcheck disable=SC2068
@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
@@ -51,21 +50,14 @@ class TARGETSBuilder:
            pretty_list(deps)))
        self.total_bin = self.total_bin + 1

-    def register_test(self,
-                      test_name,
-                      src,
-                      is_parallel,
-                      extra_deps,
-                      extra_compiler_flags):
+    def register_test(self, test_name, src, is_parallel):
        exec_mode = "serial"
        if is_parallel:
            exec_mode = "parallel"
        self.tests_cfg += targets_cfg.test_cfg_template % (
            test_name,
            str(src),
-            str(exec_mode),
-            extra_deps,
-            extra_compiler_flags)
+            str(exec_mode))

        self.total_test = self.total_test + 1

@@ -1,21 +1,37 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
 rocksdb_target_header = """load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
-load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
 load(":defs.bzl", "test_binary")

 REPO_PATH = package_name() + "/"

 ROCKSDB_COMPILER_FLAGS = [
    "-fno-builtin-memcmp",
+    "-DROCKSDB_PLATFORM_POSIX",
+    "-DROCKSDB_LIB_IO_POSIX",
+    "-DROCKSDB_FALLOCATE_PRESENT",
+    "-DROCKSDB_MALLOC_USABLE_SIZE",
+    "-DROCKSDB_RANGESYNC_PRESENT",
+    "-DROCKSDB_SCHED_GETCPU_PRESENT",
+    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
+    "-DOS_LINUX",
+    # Flags to enable libs we include
+    "-DSNAPPY",
+    "-DZLIB",
+    "-DBZIP2",
+    "-DLZ4",
+    "-DZSTD",
+    "-DGFLAGS=gflags",
+    "-DNUMA",
+    "-DTBB",
    # Needed to compile in fbcode
    "-Wno-expansion-to-defined",
    # Added missing flags from output of build_detect_platform
+    "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
+    "-DROCKSDB_BACKTRACE",
    "-Wnarrowing",
-    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
 ]

 ROCKSDB_EXTERNAL_DEPS = [
@@ -26,54 +42,11 @@ ROCKSDB_EXTERNAL_DEPS = [
    ("lz4", None, "lz4"),
    ("zstd", None),
    ("tbb", None),
+    ("numa", None, "numa"),
    ("googletest", None, "gtest"),
 ]

-ROCKSDB_OS_DEPS = [
-    (
-        "linux",
-        ["third-party//numa:numa"],
-    ),
-]
-
-ROCKSDB_OS_PREPROCESSOR_FLAGS = [
-    (
-        "linux",
-        [
-            "-DOS_LINUX",
-            "-DROCKSDB_FALLOCATE_PRESENT",
-            "-DROCKSDB_MALLOC_USABLE_SIZE",
-            "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
-            "-DROCKSDB_RANGESYNC_PRESENT",
-            "-DROCKSDB_SCHED_GETCPU_PRESENT",
-            "-DHAVE_SSE42",
-            "-DNUMA",
-        ],
-    ),
-    (
-        "macos",
-        ["-DOS_MACOSX"],
-    ),
-]
-
 ROCKSDB_PREPROCESSOR_FLAGS = [
-    "-DROCKSDB_PLATFORM_POSIX",
-    "-DROCKSDB_LIB_IO_POSIX",
-    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
-
-    # Flags to enable libs we include
-    "-DSNAPPY",
-    "-DZLIB",
-    "-DBZIP2",
-    "-DLZ4",
-    "-DZSTD",
-    "-DZSTD_STATIC_LINKING_ONLY",
-    "-DGFLAGS=gflags",
-    "-DTBB",
-
-    # Added missing flags from output of build_detect_platform
-    "-DROCKSDB_BACKTRACE",
-
    # Directories with files for #include
    "-I" + REPO_PATH + "include/",
    "-I" + REPO_PATH,
@@ -81,6 +54,7 @@ ROCKSDB_PREPROCESSOR_FLAGS = [

 ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
    "x86_64": [
+        "-DHAVE_SSE42",
        "-DHAVE_PCLMUL",
    ],
 }
@@ -97,15 +71,9 @@ sanitizer = read_config("fbcode", "sanitizer")

 # Do not enable jemalloc if sanitizer presents. RocksDB will further detect
 # whether the binary is linked with jemalloc at runtime.
-ROCKSDB_OS_PREPROCESSOR_FLAGS += ([(
-    "linux",
-    ["-DROCKSDB_JEMALLOC"],
-)] if sanitizer == "" else [])
+ROCKSDB_COMPILER_FLAGS += (["-DROCKSDB_JEMALLOC"] if sanitizer == "" else [])

-ROCKSDB_OS_DEPS += ([(
-    "linux",
-    ["third-party//jemalloc:headers"],
-)] if sanitizer == "" else [])
+ROCKSDB_EXTERNAL_DEPS += ([("jemalloc", None, "headers")] if sanitizer == "" else [])
 """


@@ -116,8 +84,6 @@ cpp_library(
    {headers_attr_prefix}headers = {headers},
    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    os_deps = ROCKSDB_OS_DEPS,
-    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
    deps = [{deps}],
    external_deps = ROCKSDB_EXTERNAL_DEPS,
@@ -140,13 +106,11 @@ test_cfg_template = """    [
        "%s",
        "%s",
        "%s",
-        %s,
-        %s,
    ],
 """

 unittests_template = """
-# [test_name, test_src, test_type, extra_deps, extra_compiler_flags]
+# [test_name, test_src, test_type]
 ROCKS_TESTS = [
 %s]

@@ -155,19 +119,15 @@ ROCKS_TESTS = [
 # will not be included.
 [
    test_binary(
-        extra_compiler_flags = extra_compiler_flags,
-        extra_deps = extra_deps,
        parallelism = parallelism,
        rocksdb_arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
        rocksdb_compiler_flags = ROCKSDB_COMPILER_FLAGS,
        rocksdb_external_deps = ROCKSDB_EXTERNAL_DEPS,
-        rocksdb_os_deps = ROCKSDB_OS_DEPS,
-        rocksdb_os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
        rocksdb_preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
        test_cc = test_cc,
        test_name = test_name,
    )
-    for test_name, test_cc, parallelism, extra_deps, extra_compiler_flags in ROCKS_TESTS
+    for test_name, test_cc, parallelism in ROCKS_TESTS
    if not is_opt_mode
 ]
 """
@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 """
 This module keeps commonly used components.
 """
@@ -0,0 +1,377 @@
+<?php
+// Copyright 2004-present Facebook. All Rights Reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+// Name of the environment variables which need to be set by the entity which
+// triggers continuous runs so that code at the end of the file gets executed
+// and Sandcastle run starts.
+const ENV_POST_RECEIVE_HOOK = "POST_RECEIVE_HOOK";
+const ENV_HTTPS_APP_VALUE = "HTTPS_APP_VALUE";
+const ENV_HTTPS_TOKEN_VALUE = "HTTPS_TOKEN_VALUE";
+
+const PRIMARY_TOKEN_FILE = '/home/krad/.sandcastle';
+const CONT_RUN_ALIAS = "leveldb";
+
+//////////////////////////////////////////////////////////////////////
+/*  Run tests in sandcastle */
+function postURL($diffID, $url) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($url) > 0);
+
+  $cmd_args = array(
+    'diff_id' => (int)$diffID,
+    'name' => sprintf(
+      'click here for sandcastle tests for D%d',
+      (int)$diffID
+    ),
+    'link' => $url
+  );
+  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
+         . ' | arc call-conduit differential.updateunitresults';
+
+  shell_exec($cmd);
+}
+
+function buildUpdateTestStatusCmd($diffID, $test, $status) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($test) > 0);
+  assert(strlen($status) > 0);
+
+  $cmd_args = array(
+    'diff_id' => (int)$diffID,
+    'name' => $test,
+    'result' => $status
+  );
+
+  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
+         . ' | arc call-conduit differential.updateunitresults';
+
+  return $cmd;
+}
+
+function updateTestStatus($diffID, $test) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($test) > 0);
+
+  shell_exec(buildUpdateTestStatusCmd($diffID, $test, "waiting"));
+}
+
+function getSteps($applyDiff, $diffID, $username, $test) {
+  assert(strlen($username) > 0);
+  assert(strlen($test) > 0);
+
+  if ($applyDiff) {
+    assert(strlen($diffID) > 0);
+    assert(is_numeric($diffID));
+
+    $arcrc_content = (PHP_OS == "Darwin" ?
+        exec("cat ~/.arcrc | gzip -f | base64") :
+            exec("cat ~/.arcrc | gzip -f | base64 -w0"));
+    assert(strlen($arcrc_content) > 0);
+
+    // Sandcastle machines don't have arc setup. We copy the user certificate
+    // and authenticate using that in Sandcastle.
+    $setup = array(
+      "name" => "Setup arcrc",
+      "shell" => "echo " . escapeshellarg($arcrc_content) . " | base64 --decode"
+                 . " | gzip -d > ~/.arcrc",
+      "user" => "root"
+    );
+
+    // arc demands certain permission on its config.
+    // also fix the sticky bit issue in sandcastle
+    $fix_permission = array(
+      "name" => "Fix environment",
+      "shell" => "chmod 600 ~/.arcrc && chmod +t /dev/shm",
+      "user" => "root"
+    );
+
+    // Construct the steps in the order of execution.
+    $steps[] = $setup;
+    $steps[] = $fix_permission;
+  }
+
+  // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
+  // Git thinks it is an uncommitted change.
+  $fix_git_ignore = array(
+    "name" => "Fix git ignore",
+    "shell" => "echo fbcode >> .git/info/exclude",
+    "user" => "root"
+  );
+
+  // This fixes "FATAL: ThreadSanitizer can not mmap the shadow memory"
+  // Source:
+  // https://github.com/google/sanitizers/wiki/ThreadSanitizerCppManual#FAQ
+  $fix_kernel_issue = array(
+    "name" => "Fix kernel issue with tsan",
+    "shell" => "echo 2 >/proc/sys/kernel/randomize_va_space",
+    "user" => "root"
+  );
+
+  $steps[] = $fix_git_ignore;
+  $steps[] = $fix_kernel_issue;
+
+  // This will be the command used to execute particular type of tests.
+  $cmd = "";
+
+  if ($applyDiff) {
+    // Patch the code (keep your fingures crossed).
+    $patch = array(
+      "name" => "Patch " . $diffID,
+      "shell" => "arc --arcrc-file ~/.arcrc "
+                  . "patch --nocommit --diff " . escapeshellarg($diffID),
+      "user" => "root"
+    );
+
+    $steps[] = $patch;
+
+    updateTestStatus($diffID, $test);
+    $cmd = buildUpdateTestStatusCmd($diffID, $test, "running") . "; ";
+  }
+
+  // Run the actual command.
+  $cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " .
+           escapeshellarg($test) . "; exit_code=$?; ";
+
+  if ($applyDiff) {
+    $cmd = $cmd . "([[ \$exit_code -eq 0 ]] &&"
+                . buildUpdateTestStatusCmd($diffID, $test, "pass") . ")"
+                . "||" . buildUpdateTestStatusCmd($diffID, $test, "fail")
+                . "; ";
+  }
+
+  // shell command to sort the tests based on exit code and print
+  // the output of the log files.
+  $cat_sorted_logs = "
+    while read code log_file;
+      do echo \"################ cat \$log_file [exit_code : \$code] ################\";
+      cat \$log_file;
+    done < <(tail -n +2 LOG | sort -k7,7n -k4,4gr | awk '{print \$7,\$NF}')";
+
+  // Shell command to cat all log files
+  $cat_all_logs = "for f in `ls t/!(run-*)`; do echo \$f;cat \$f; done";
+
+  // If LOG file exist use it to cat log files sorted by exit code, otherwise
+  // cat everything
+  $logs_cmd = "if [ -f LOG ]; then {$cat_sorted_logs}; else {$cat_all_logs}; fi";
+
+  $cmd = $cmd . " cat /tmp/precommit-check.log"
+              . "; shopt -s extglob; {$logs_cmd}"
+              . "; shopt -u extglob; [[ \$exit_code -eq 0 ]]";
+  assert(strlen($cmd) > 0);
+
+  $run_test = array(
+    "name" => "Run " . $test,
+    "shell" => $cmd,
+    "user" => "root",
+    "parser" => "python build_tools/error_filter.py " . escapeshellarg($test),
+  );
+
+  $steps[] = $run_test;
+
+  if ($applyDiff) {
+    // Clean up the user arc config we are using.
+    $cleanup = array(
+      "name" => "Arc cleanup",
+      "shell" => "rm -f ~/.arcrc",
+      "user" => "root"
+    );
+
+    $steps[] = $cleanup;
+  }
+
+  assert(count($steps) > 0);
+  return $steps;
+}
+
+function getSandcastleConfig() {
+  $sandcastle_config = array();
+
+  $cwd = getcwd();
+  $cwd_token_file = "{$cwd}/.sandcastle";
+  // This is a case when we're executed from a continuous run. Fetch the values
+  // from the environment.
+  if (getenv(ENV_POST_RECEIVE_HOOK)) {
+    $sandcastle_config[0] = getenv(ENV_HTTPS_APP_VALUE);
+    $sandcastle_config[1] = getenv(ENV_HTTPS_TOKEN_VALUE);
+  } else {
+    // This is a typical `[p]arc diff` case. Fetch the values from the specific
+    // configuration files.
+    for ($i = 0; $i < 50; $i++) {
+      if (file_exists(PRIMARY_TOKEN_FILE) ||
+          file_exists($cwd_token_file)) {
+        break;
+      }
+      // If we failed to fetch the tokens, sleep for 0.2 second and try again
+      usleep(200000);
+    }
+    assert(file_exists(PRIMARY_TOKEN_FILE) ||
+           file_exists($cwd_token_file));
+
+    // Try the primary location first, followed by a secondary.
+    if (file_exists(PRIMARY_TOKEN_FILE)) {
+      $cmd = 'cat ' . PRIMARY_TOKEN_FILE;
+    } else {
+      $cmd = 'cat ' . escapeshellarg($cwd_token_file);
+    }
+
+    assert(strlen($cmd) > 0);
+    $sandcastle_config = explode(':', rtrim(shell_exec($cmd)));
+  }
+
+  // In this case be very explicit about the implications.
+  if (count($sandcastle_config) != 2) {
+    echo "Sandcastle configuration files don't contain valid information " .
+         "or the necessary environment variables aren't defined. Unable " .
+         "to validate the code changes.";
+    exit(1);
+  }
+
+  assert(strlen($sandcastle_config[0]) > 0);
+  assert(strlen($sandcastle_config[1]) > 0);
+  assert(count($sandcastle_config) > 0);
+
+  return $sandcastle_config;
+}
+
+// This function can be called either from `[p]arc diff` command or during
+// the Git post-receive hook.
+ function startTestsInSandcastle($applyDiff, $workflow, $diffID) {
+  // Default options don't terminate on failure, but that's what we want. In
+  // the current case we use assertions intentionally as "terminate on failure
+  // invariants".
+  assert_options(ASSERT_BAIL, true);
+
+  // In case of a diff we'll send notificatios to the author. Else it'll go to
+  // the entire team because failures indicate that build quality has regressed.
+  $username = $applyDiff ? exec("whoami") : CONT_RUN_ALIAS;
+  assert(strlen($username) > 0);
+
+  if ($applyDiff) {
+    assert($workflow);
+    assert(strlen($diffID) > 0);
+    assert(is_numeric($diffID));
+  }
+
+  // List of tests we want to run in Sandcastle.
+  $tests = array("unit", "unit_non_shm", "unit_481", "clang_unit", "tsan",
+                 "asan", "lite_test", "valgrind", "release", "release_481",
+                 "clang_release", "clang_analyze", "code_cov",
+                 "java_build", "no_compression", "unity", "ubsan");
+
+  $send_email_template = array(
+    'type' => 'email',
+    'triggers' => array('fail'),
+    'emails' => array($username . '@fb.com'),
+  );
+
+  // Construct a job definition for each test and add it to the master plan.
+  foreach ($tests as $test) {
+    $stepName = "RocksDB diff " . $diffID . " test " . $test;
+
+    if (!$applyDiff) {
+      $stepName = "RocksDB continuous integration test " . $test;
+    }
+
+    $arg[] = array(
+      "name" => $stepName,
+      "report" => array($send_email_template),
+      "steps" => getSteps($applyDiff, $diffID, $username, $test)
+    );
+  }
+
+  // We cannot submit the parallel execution master plan to Sandcastle and
+  // need supply the job plan as a determinator. So we construct a small job
+  // that will spit out the master job plan which Sandcastle will parse and
+  // execute. Why compress the job definitions? Otherwise we run over the max
+  // string size.
+  $cmd = "echo " . base64_encode(json_encode($arg))
+         . (PHP_OS == "Darwin" ?
+             " | gzip -f | base64" :
+                 " | gzip -f | base64 -w0");
+  assert(strlen($cmd) > 0);
+
+  $arg_encoded = shell_exec($cmd);
+  assert(strlen($arg_encoded) > 0);
+
+  $runName = "Run diff " . $diffID . "for user " . $username;
+
+  if (!$applyDiff) {
+    $runName = "RocksDB continuous integration build and test run";
+  }
+
+  $command = array(
+    "name" => $runName,
+    "steps" => array()
+  );
+
+  $command["steps"][] = array(
+    "name" => "Generate determinator",
+    "shell" => "echo " . $arg_encoded . " | base64 --decode | gzip -d"
+               . " | base64 --decode",
+    "determinator" => true,
+    "user" => "root"
+  );
+
+  // Submit to Sandcastle.
+  $url = 'https://interngraph.intern.facebook.com/sandcastle/create';
+
+  $job = array(
+    'command' => 'SandcastleUniversalCommand',
+    'args' => $command,
+    'capabilities' => array(
+      'vcs' => 'rocksdb-int-git',
+      'type' => 'lego',
+    ),
+    'hash' => 'origin/master',
+    'user' => $username,
+    'alias' => 'rocksdb-precommit',
+    'tags' => array('rocksdb'),
+    'description' => 'Rocksdb precommit job',
+  );
+
+  // Fetch the configuration necessary to submit a successful HTTPS request.
+  $sandcastle_config = getSandcastleConfig();
+
+  $app = $sandcastle_config[0];
+  $token = $sandcastle_config[1];
+
+  $cmd = 'curl -s -k '
+          . ' -F app=' . escapeshellarg($app)
+          . ' -F token=' . escapeshellarg($token)
+          . ' -F job=' . escapeshellarg(json_encode($job))
+          .' ' . escapeshellarg($url);
+
+  $output = shell_exec($cmd);
+  assert(strlen($output) > 0);
+
+  // Extract Sandcastle URL from the response.
+  preg_match('/url": "(.+)"/', $output, $sandcastle_url);
+
+  assert(count($sandcastle_url) > 0, "Unable to submit Sandcastle request.");
+  assert(strlen($sandcastle_url[1]) > 0, "Unable to extract Sandcastle URL.");
+
+  if ($applyDiff) {
+    echo "\nSandcastle URL: " . $sandcastle_url[1] . "\n";
+    // Ask Phabricator to display it on the diff UI.
+    postURL($diffID, $sandcastle_url[1]);
+  } else {
+    echo "Continuous integration started Sandcastle tests. You can look at ";
+    echo "the progress at:\n" . $sandcastle_url[1] . "\n";
+  }
+}
+
+// Continuous run cript will set the environment variable and based on that
+// we'll trigger the execution of tests in Sandcastle. In that case we don't
+// need to apply any diffs and there's no associated workflow either.
+if (getenv(ENV_POST_RECEIVE_HOOK)) {
+  startTestsInSandcastle(
+    false /* $applyDiff */,
+    NULL /* $workflow */,
+    NULL /* $diffID */);
+}
@@ -1,5 +1,4 @@
 #!/usr/bin/python
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 # amalgamate.py creates an amalgamation from a unity build.
 # It can be run with either Python 2 or 3.
@@ -150,9 +150,6 @@ case "$TARGET_OS" in
            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
        fi
        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
-        if test -z "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-          USE_FOLLY_DISTRIBUTED_MUTEX=1
-        fi
        # PORT_FILES=port/linux/linux_specific.cc
        ;;
    SunOS)
@@ -237,7 +234,7 @@ else
          #include <linux/falloc.h>
          int main() {
      int fd = open("/dev/null", 0);
-      fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, 1024);
+      fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
          }
 EOF
        if [ "$?" = 0 ]; then
@@ -400,7 +397,6 @@ EOF
          #include <malloc.h>
          int main() {
            size_t res = malloc_usable_size(0);
-            (void)res;
            return 0;
          }
 EOF
@@ -415,7 +411,6 @@ EOF
          #include <pthread.h>
          int main() {
            int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-            (void)x;
            return 0;
          }
 EOF
@@ -427,7 +422,7 @@ EOF
    if ! test $ROCKSDB_DISABLE_BACKTRACE; then
        # Test whether backtrace is available
        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <execinfo.h>
+          #include <execinfo.h>>
          int main() {
            void* frames[1];
            backtrace_symbols(frames, backtrace(frames, 1));
@@ -485,7 +480,6 @@ EOF
          #include <sched.h>
          int main() {
            int cpuid = sched_getcpu();
-            (void)cpuid;
          }
 EOF
        if [ "$?" = 0 ]; then
@@ -521,11 +515,11 @@ fi

 if test "$USE_HDFS"; then
  if test -z "$JAVA_HOME"; then
-    echo "JAVA_HOME has to be set for HDFS usage." >&2
+    echo "JAVA_HOME has to be set for HDFS usage."
    exit 1
  fi
-  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS -I$HADOOP_HOME/include"
-  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64 -L$HADOOP_HOME/lib/native"
+  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64"
  HDFS_LDFLAGS="$HDFS_LDFLAGS -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib"
  HDFS_LDFLAGS="$HDFS_LDFLAGS -ldl -lverify -ljava -ljvm"
  COMMON_FLAGS="$COMMON_FLAGS $HDFS_CCFLAGS"
@@ -533,62 +527,42 @@ if test "$USE_HDFS"; then
  JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi

-if test "0$PORTABLE" -eq 0; then
+if test -z "$PORTABLE"; then
  if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
    # Tune for this POWER processor, treating '+' models as base models
    POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
    COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
    COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep -e^arm -e^aarch64`"; then
+  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^arm`"; then
    # TODO: Handle this with approprite options.
    COMMON_FLAGS="$COMMON_FLAGS"
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^aarch64`"; then
-    COMMON_FLAGS="$COMMON_FLAGS"
  elif [ "$TARGET_OS" == "IOS" ]; then
    COMMON_FLAGS="$COMMON_FLAGS"
-  elif [ "$TARGET_OS" == "AIX" ] || [ "$TARGET_OS" == "SunOS" ]; then
-    # TODO: Not sure why we don't use -march=native on these OSes
-    if test "$USE_SSE"; then
-      TRY_SSE_ETC="1"
-    fi
-  else
+  elif [ "$TARGET_OS" != "AIX" ] && [ "$TARGET_OS" != "SunOS" ]; then
    COMMON_FLAGS="$COMMON_FLAGS -march=native "
+  elif test "$USE_SSE"; then
+    COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
  fi
-else
-  # PORTABLE=1
-  if test "$USE_SSE"; then
-    TRY_SSE_ETC="1"
-  fi
+elif test "$USE_SSE"; then
+  COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
 fi

-if test "$TRY_SSE_ETC"; then
-  # The USE_SSE flag now means "attempt to compile with widely-available
-  # Intel architecture extensions utilized by specific optimizations in the
-  # source code." It's a qualifier on PORTABLE=1 that means "mostly portable."
-  # It doesn't even really check that your current CPU is compatible.
-  #
-  # SSE4.2 available since nehalem, ca. 2008-2010
-  TRY_SSE42="-msse4.2"
-  # PCLMUL available since westmere, ca. 2010-2011
-  TRY_PCLMUL="-mpclmul"
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o /dev/null 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <nmmintrin.h>
  int main() {
    volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
  }
 EOF
 if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_SSE42 -DHAVE_SSE42"
+  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_SSE42"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
+  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling"
+  exit 1
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <wmmintrin.h>
  int main() {
@@ -596,13 +570,13 @@ $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/n
    const auto b = _mm_set_epi64x(0, 0);
    const auto c = _mm_clmulepi64_si128(a, b, 0x00);
    auto d = _mm_cvtsi128_si64(c);
-    (void)d;
  }
 EOF
 if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_PCLMUL -DHAVE_PCLMUL"
+  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_PCLMUL"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
+  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling"
+  exit 1
 fi

 # iOS doesn't support thread-local storage, but this check would erroneously
@@ -615,7 +589,6 @@ if [ "$PLATFORM" != IOS ]; then
  #endif
  int main() {
    static __thread int tls;
-    (void)tls;
  }
 EOF
  if [ "$?" = 0 ]; then
@@ -623,19 +596,6 @@ EOF
  fi
 fi

-if [ "$FBCODE_BUILD" != "true" -a "$PLATFORM" = OS_LINUX ]; then
-  $CXX $COMMON_FLAGS $PLATFORM_SHARED_CFLAGS -x c++ -c - -o test_dl.o 2>/dev/null <<EOF
-  void dummy_func() {}
-EOF
-  if [ "$?" = 0 ]; then
-    $CXX $COMMON_FLAGS $PLATFORM_SHARED_LDFLAGS test_dl.o -o /dev/null 2>/dev/null
-    if [ "$?" = 0 ]; then
-      EXEC_LDFLAGS+="-ldl"
-      rm -f test_dl.o
-    fi
-  fi
-fi
-
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"

@@ -680,6 +640,3 @@ if test -n "$WITH_JEMALLOC_FLAG"; then
  echo "WITH_JEMALLOC_FLAG=$WITH_JEMALLOC_FLAG" >> "$OUTPUT"
 fi
 echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
-if test -n "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-  echo "USE_FOLLY_DISTRIBUTED_MUTEX=$USE_FOLLY_DISTRIBUTED_MUTEX" >> "$OUTPUT"
-fi
@@ -1,19 +1,18 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/5.x/centos7-native/c447969
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1bd23f9917738974ad0ff305aa23eb5f93f18305/9.0.0/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/5.x/gcc-5-glibc-2.23/339d858
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.23/gcc-5-glibc-2.23/ca1d1c0
+GCC_BASE=/mnt/gvfs/third-party2/gcc/112ec378fec7002ad3e09afde022e656049f7191/5.x/centos7-native/c447969
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/04999bdb3ce81a11073535dcb00b5e13dc1cbaf5/stable/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/92b0c8e5c8eecc71eb042594ce1ab3413799b385/5.x/gcc-5-glibc-2.23/339d858
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/3d8698d5973ba94f41620a80a67e4457fdf01e90/2.23/gcc-5-glibc-2.23/ca1d1c0
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/gcc-5-glibc-2.23/9bc6787
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/gcc-5-glibc-2.23/9bc6787
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/gcc-5-glibc-2.23/9bc6787
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/gcc-5-glibc-2.23/9bc6787
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/gcc-5-glibc-2.23/9bc6787
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/gcc-5-glibc-2.23/03859b5
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/gcc-5-glibc-2.23/9bc6787
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/af6628a46758f1a15484a1760cd7294164bc5ba1/1.3.5/gcc-5-glibc-2.23/03859b5
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/gcc-5-glibc-2.23/9bc6787
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/gcc-5-glibc-2.23/0c8f76d
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/gcc-5-glibc-2.23/9bc6787
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/gcc-5-glibc-2.23/b443de1
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/gcc-5-glibc-2.23/9bc6787
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/2e3cb7d119b3cea5f1e738cc13a1ac69f49eb875/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/gcc-5-glibc-2.23/9bc6787
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b1a0e56c1e3e6929813a4331ade3a58ff083afbb/master/gcc-5-glibc-2.23/aa64d6b
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/gcc-5-glibc-2.23/9bc6787
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/gcc-5-glibc-2.23/b443de1
+TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/gcc-5-glibc-2.23/9bc6787
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/55031de95a2b46c82948743419a603b3d6aefe28/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/gcc-5-glibc-2.23/9bc6787
 LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.2.3/gcc-5-glibc-2.23/65372bd
@@ -1,5 +1,4 @@
 # shellcheck disable=SC2148
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 GCC_BASE=/mnt/gvfs/third-party2/gcc/cf7d14c625ce30bae1a4661c2319c5a283e4dd22/4.8.1/centos6-native/cc6c9dc
 CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/8598c375b0e94e1448182eb3df034704144a838d/stable/centos6-native/3f16ddd
 LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d6e0a7da6faba45f5e5b1638f9edd7afc2f34e7d/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
@@ -1,19 +1,18 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1bd23f9917738974ad0ff305aa23eb5f93f18305/9.0.0/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+GCC_BASE=/mnt/gvfs/third-party2/gcc/6e8e715624fd15256a7970073387793dfcf79b46/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/ef37e1faa1c29782abfac1ae65a291b9b7966f6d/stable/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/c67031f0f739ac61575a061518d6ef5038f99f90/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/60d6f124a78798b73944f5ba87c2306ae3460153/2.26/platform007/f259413
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/platform007/ca4da3d
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/3ee276cbacfad3074e3f07bf826ac47f06970f4e/1.3.5/platform007/15a3614
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/2e3cb7d119b3cea5f1e738cc13a1ac69f49eb875/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/9c910d36d6235cc40e8ff559358f1833452300ca/master/platform007/5b0f53e
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/92ff90349e2f43ea0a8246d8b1cf17b6869013e3/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/platform007/ca4da3d
 LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832
@@ -1,3 +1,2 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 docker run -v $PWD:/rocks -w /rocks buildpack-deps make
@@ -132,14 +132,11 @@ _TEST_NAME_TO_PARSERS = {
    'lite': [CompilerErrorParser],
    'lite_test': [CompilerErrorParser, GTestErrorParser],
    'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_atomic_flush': [CompilerErrorParser, DbCrashErrorParser],
    'write_stress': [CompilerErrorParser, WriteStressErrorParser],
    'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
    'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_atomic_flush': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
    'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
    'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_atomic_flush': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
    'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
    'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
    'format_compatible': [CompilerErrorParser, CompatErrorParser],
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+
 # fail early
 set -e

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ and clang compilers and also
@@ -86,10 +85,9 @@ else
 fi
 CFLAGS+=" -DTBB"

-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1

 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -160,6 +158,4 @@ else
  LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
 fi

-USE_FOLLY_DISTRIBUTED_MUTEX=1
-
 export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ compiler and also
@@ -53,10 +52,9 @@ LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
 TBB_INCLUDE=" -isystem $TBB_BASE/include/"
 TBB_LIBS="$TBB_BASE/lib/libtbb.a"

-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1

 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ and clang compilers and also
@@ -86,10 +85,9 @@ else
 fi
 CFLAGS+=" -DTBB"

-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1

 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -156,6 +154,4 @@ VALGRIND_VER="$VALGRIND_BASE/bin/"
 LUA_PATH=
 LUA_LIB=

-USE_FOLLY_DISTRIBUTED_MUTEX=1
-
 export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # If clang_format_diff.py command is not specfied, we assume we are able to
 # access directly without any path.
 if [ -z $CLANG_FORMAT_DIFF ]
@@ -54,25 +53,15 @@ fi
 set -e

 uncommitted_code=`git diff HEAD`
+LAST_MASTER=`git merge-base master HEAD`

 # If there's no uncommitted changes, we assume user are doing post-commit
-# format check, in which case we'll try to check the modified lines vs. the
-# facebook/rocksdb.git master branch. Otherwise, we'll check format of the
-# uncommitted code only.
+# format check, in which case we'll check the modified lines since last commit
+# from master. Otherwise, we'll check format of the uncommitted code only.
 if [ -z "$uncommitted_code" ]
 then
-  # Attempt to get name of facebook/rocksdb.git remote.
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE="$(git remote -v | grep 'facebook/rocksdb.git' | head -n 1 | cut -f 1)"
-  # Fall back on 'origin' if that fails
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE=origin
-  # Use master branch from that remote
-  [ "$FORMAT_UPSTREAM" ] || FORMAT_UPSTREAM="$FORMAT_REMOTE/master"
-  # Get the common ancestor with that remote branch. Everything after that
-  # common ancestor would be considered the contents of a pull request, so
-  # should be relevant for formatting fixes.
-  FORMAT_UPSTREAM_MERGE_BASE="$(git merge-base "$FORMAT_UPSTREAM" HEAD)"
-  # Get the differences
-  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1)
+  # Check the format of last commit
+  diffs=$(git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -p 1)
 else
  # Check the format of uncommitted lines,
  diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
@@ -86,12 +75,12 @@ fi

 # Highlight the insertion/deletion from the clang-format-diff.py's output
 COLOR_END="\033[0m"
-COLOR_RED="\033[0;31m"
-COLOR_GREEN="\033[0;32m"
+COLOR_RED="\033[0;31m" 
+COLOR_GREEN="\033[0;32m" 

 echo -e "Detect lines that doesn't follow the format rules:\r"
 # Add the color to the diff. lines added will be green; lines removed will be red.
-echo "$diffs" |
+echo "$diffs" | 
  sed -e "s/\(^-.*$\)/`echo -e \"$COLOR_RED\1$COLOR_END\"`/" |
  sed -e "s/\(^+.*$\)/`echo -e \"$COLOR_GREEN\1$COLOR_END\"`/"

@@ -114,7 +103,7 @@ fi
 # Do in-place format adjustment.
 if [ -z "$uncommitted_code" ]
 then
-  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -i -p 1
 else
  git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -i -p 1
 fi
@@ -1,6 +1,5 @@
 # shellcheck disable=SC1113
 #/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 set -e

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

 from __future__ import absolute_import
 from __future__ import division
@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 set -e

@@ -63,21 +63,6 @@ CLEANUP_ENV="
    'user':'root'
 }"

-UPLOAD_DB_DIR="
-{
-    'name':'Upload database directory',
-    'shell':'tar -cvzf rocksdb_db.tar.gz /dev/shm/rocksdb/',
-    'user':'root',
-    'cleanup':true,
-    'provide_artifacts': [
-    {
-      'name':'rocksdb_db_dir',
-      'paths': ['rocksdb_db.tar.gz'],
-      'bundle': false,
-    },
-    ],
-}"
-
 # We will eventually set the RATIO to 1, but we want do this
 # in steps. RATIO=$(nproc) will make it work as J=1
 if [ -z $RATIO ]; then
@@ -124,6 +109,13 @@ else
  TASK_CREATION_TOOL="false"
 fi

+ARTIFACTS=" 'artifacts': [
+    {
+        'name':'database',
+        'paths':[ '/dev/shm/rocksdb' ],
+    }
+]"
+
 #
 # A mechanism to disable tests temporarily
 #
@@ -148,7 +140,6 @@ UNIT_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -169,7 +160,6 @@ UNIT_TEST_NON_SHM_COMMANDS="[
    {
        'name':'Rocksdb Unit Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -192,7 +182,6 @@ RELEASE_BUILD_COMMANDS="[
    {
        'name':'Rocksdb Release Build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -213,7 +202,6 @@ UNIT_TEST_COMMANDS_481="[
    {
        'name':'Rocksdb Unit Test on GCC 4.8.1',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -234,7 +222,6 @@ RELEASE_BUILD_COMMANDS_481="[
    {
        'name':'Rocksdb Release on GCC 4.8.1',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -255,7 +242,6 @@ CLANG_UNIT_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -276,7 +262,6 @@ CLANG_RELEASE_BUILD_COMMANDS="[
    {
        'name':'Rocksdb CLANG Release Build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -297,7 +282,6 @@ CLANG_ANALYZE_COMMANDS="[
    {
        'name':'Rocksdb analyze',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -318,7 +302,6 @@ CODE_COV_COMMANDS="[
    {
        'name':'Rocksdb Unit Test Code Coverage',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -339,7 +322,6 @@ UNITY_COMMANDS="[
    {
        'name':'Rocksdb Unity',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -360,7 +342,6 @@ LITE_BUILD_COMMANDS="[
    {
        'name':'Rocksdb Lite build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -380,7 +361,6 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
    {
        'name':'Rocksdb Lite Binary Size',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -396,9 +376,8 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
 #
 STRESS_CRASH_TEST_COMMANDS="[
    {
-        'name':'Rocksdb Stress and Crash Test',
+        'name':'Rocksdb Stress/Crash Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -416,36 +395,7 @@ STRESS_CRASH_TEST_COMMANDS="[
                $PARSER
            }
        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test with atomic flush
-#
-STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with atomic flush',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests with atomic flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_atomic_flush || $CONTRUN_NAME=crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
+        $ARTIFACTS,
        $REPORT
    }
 ]"
@@ -457,7 +407,6 @@ WRITE_STRESS_COMMANDS="[
    {
        'name':'Rocksdb Write Stress Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -480,7 +429,6 @@ ASAN_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under ASAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -501,7 +449,6 @@ ASAN_CRASH_TEST_COMMANDS="[
    {
        'name':'Rocksdb crash test under ASAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -517,30 +464,6 @@ ASAN_CRASH_TEST_COMMANDS="[
    }
 ]"

-#
-# RocksDB crash testing with atomic flush under address sanitizer
-#
-ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with atomic flush under ASAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test_with_atomic_flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_atomic_flush || $CONTRUN_NAME=asan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB test under undefined behavior sanitizer
 #
@@ -548,7 +471,6 @@ UBSAN_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under UBSAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -569,7 +491,6 @@ UBSAN_CRASH_TEST_COMMANDS="[
    {
        'name':'Rocksdb crash test under UBSAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -585,30 +506,6 @@ UBSAN_CRASH_TEST_COMMANDS="[
    }
 ]"

-#
-# RocksDB crash testing with atomic flush under undefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with atomic flush under UBSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test_with_atomic_flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB unit test under valgrind
 #
@@ -616,7 +513,6 @@ VALGRIND_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under valgrind',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -639,7 +535,6 @@ TSAN_UNIT_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under TSAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -662,7 +557,6 @@ TSAN_CRASH_TEST_COMMANDS="[
    {
        'name':'Rocksdb Crash Test under TSAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -678,30 +572,6 @@ TSAN_CRASH_TEST_COMMANDS="[
    }
 ]"

-#
-# RocksDB crash test with atomic flush under TSAN
-#
-TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test with atomic flush under TSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_atomic_flush || $CONTRUN_NAME=tsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB format compatible
 #
@@ -719,7 +589,6 @@ FORMAT_COMPATIBLE_COMMANDS="[
    {
        'name':'Rocksdb Format Compatible tests',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -742,7 +611,7 @@ run_no_compression()
  rm -rf /dev/shm/rocksdb
  mkdir /dev/shm/rocksdb
  make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzstd | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
+  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
  mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
  cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
  mv .tmp.Makefile Makefile
@@ -753,7 +622,6 @@ NO_COMPRESSION_COMMANDS="[
    {
        'name':'Rocksdb No Compression tests',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -831,7 +699,6 @@ JAVA_BUILD_TEST_COMMANDS="[
    {
        'name':'Rocksdb Java Build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -886,9 +753,6 @@ case $1 in
  stress_crash)
    echo $STRESS_CRASH_TEST_COMMANDS
    ;;
-  stress_crash_with_atomic_flush)
-    echo $STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
  write_stress)
    echo $WRITE_STRESS_COMMANDS
    ;;
@@ -898,18 +762,12 @@ case $1 in
  asan_crash)
    echo $ASAN_CRASH_TEST_COMMANDS
    ;;
-  asan_crash_with_atomic_flush)
-    echo $ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
  ubsan)
    echo $UBSAN_TEST_COMMANDS
    ;;
  ubsan_crash)
    echo $UBSAN_CRASH_TEST_COMMANDS
    ;;
-  ubsan_crash_with_atomic_flush)
-    echo $UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
  valgrind)
    echo $VALGRIND_TEST_COMMANDS
    ;;
@@ -919,9 +777,6 @@ case $1 in
  tsan_crash)
    echo $TSAN_CRASH_TEST_COMMANDS
    ;;
-  tsan_crash_with_atomic_flush)
-    echo $TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
  format_compatible)
    echo $FORMAT_COMPATIBLE_COMMANDS
    ;;
@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # This script enables you running RocksDB tests by running
 # All the tests concurrently and utilizing all the cores
 Param(
@@ -1,5 +1,4 @@
 #!/bin/bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 set -e

 ROCKSDB_VERSION="5.10.3"
@@ -1,17 +1,10 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Update dependencies.sh file with the latest avaliable versions

 BASEDIR=$(dirname $0)
 OUTPUT=""

-function log_header()
-{
-  echo "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved." >> "$OUTPUT"
-}
-
-
 function log_variable()
 {
  echo "$1=${!1}" >> "$OUTPUT"
@@ -75,7 +68,6 @@ echo "Writing dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/7.x/centos7-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`

-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE

@@ -115,7 +107,6 @@ echo "Writing dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos7-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`

-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE

@@ -155,7 +146,6 @@ echo "Writing 4.8.1 dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`

-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 if [ "$#" = "0" ]; then
  echo "Usage: $0 major|minor|patch|full"
  exit 1
@@ -3,6 +3,9 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
 #ifndef GFLAGS
 #include <cstdio>
 int main() {
@@ -11,9 +14,9 @@ int main() {
 }
 #else

-#include <stdio.h>
+#include <inttypes.h>
 #include <sys/types.h>
-#include <cinttypes>
+#include <stdio.h>

 #include "port/port.h"
 #include "rocksdb/cache.h"
@@ -16,9 +16,9 @@
 #include <vector>
 #include "cache/clock_cache.h"
 #include "cache/lru_cache.h"
-#include "test_util/testharness.h"
 #include "util/coding.h"
 #include "util/string_util.h"
+#include "util/testharness.h"

 namespace rocksdb {

@@ -73,7 +73,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
    current_ = this;
  }

-  ~CacheTest() override {}
+  ~CacheTest() {
+  }

  std::shared_ptr<Cache> NewCache(size_t capacity) {
    auto type = GetParam();
@@ -86,27 +87,19 @@ class CacheTest : public testing::TestWithParam<std::string> {
    return nullptr;
  }

-  std::shared_ptr<Cache> NewCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      CacheMetadataChargePolicy charge_policy = kDontChargeCacheMetadata) {
+  std::shared_ptr<Cache> NewCache(size_t capacity, int num_shard_bits,
+                                  bool strict_capacity_limit) {
    auto type = GetParam();
    if (type == kLRU) {
-      LRUCacheOptions co;
-      co.capacity = capacity;
-      co.num_shard_bits = num_shard_bits;
-      co.strict_capacity_limit = strict_capacity_limit;
-      co.high_pri_pool_ratio = 0;
-      co.metadata_charge_policy = charge_policy;
-      return NewLRUCache(co);
+      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit);
    }
    if (type == kClock) {
-      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit,
-                           charge_policy);
+      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit);
    }
    return nullptr;
  }

-  int Lookup(std::shared_ptr<Cache> cache, int key) {
+  int Lookup(shared_ptr<Cache> cache, int key) {
    Cache::Handle* handle = cache->Lookup(EncodeKey(key));
    const int r = (handle == nullptr) ? -1 : DecodeValue(cache->Value(handle));
    if (handle != nullptr) {
@@ -115,16 +108,16 @@ class CacheTest : public testing::TestWithParam<std::string> {
    return r;
  }

-  void Insert(std::shared_ptr<Cache> cache, int key, int value,
-              int charge = 1) {
+  void Insert(shared_ptr<Cache> cache, int key, int value, int charge = 1) {
    cache->Insert(EncodeKey(key), EncodeValue(value), charge,
                  &CacheTest::Deleter);
  }

-  void Erase(std::shared_ptr<Cache> cache, int key) {
+  void Erase(shared_ptr<Cache> cache, int key) {
    cache->Erase(EncodeKey(key));
  }

+
  int Lookup(int key) {
    return Lookup(cache_, key);
  }
@@ -151,15 +144,10 @@ class CacheTest : public testing::TestWithParam<std::string> {
 };
 CacheTest* CacheTest::current_;

-class LRUCacheTest : public CacheTest {};
-
 TEST_P(CacheTest, UsageTest) {
  // cache is std::shared_ptr and will be automatically cleaned up.
  const uint64_t kCapacity = 100000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 0, false, kFullChargeCacheMetadata);
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
+  auto cache = NewCache(kCapacity, 8, false);

  size_t usage = 0;
  char value[10] = "abcdef";
@@ -168,45 +156,31 @@ TEST_P(CacheTest, UsageTest) {
    std::string key(i, 'a');
    auto kv_size = key.size() + 5;
    cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter);
    usage += kv_size;
    ASSERT_EQ(usage, cache->GetUsage());
-    ASSERT_LT(usage, precise_cache->GetUsage());
  }

-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
-
  // make sure the cache will be overloaded
  for (uint64_t i = 1; i < kCapacity; ++i) {
    auto key = ToString(i);
    cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                  dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
  }

  // the usage should be close to the capacity
  ASSERT_GT(kCapacity, cache->GetUsage());
-  ASSERT_GT(kCapacity, precise_cache->GetUsage());
  ASSERT_LT(kCapacity * 0.95, cache->GetUsage());
-  ASSERT_LT(kCapacity * 0.95, precise_cache->GetUsage());
 }

 TEST_P(CacheTest, PinnedUsageTest) {
  // cache is std::shared_ptr and will be automatically cleaned up.
-  const uint64_t kCapacity = 200000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 8, false, kFullChargeCacheMetadata);
+  const uint64_t kCapacity = 100000;
+  auto cache = NewCache(kCapacity, 8, false);

  size_t pinned_usage = 0;
  char value[10] = "abcdef";

  std::forward_list<Cache::Handle*> unreleased_handles;
-  std::forward_list<Cache::Handle*> unreleased_handles_in_precise_cache;

  // Add entries. Unpin some of them after insertion. Then, pin some of them
  // again. Check GetPinnedUsage().
@@ -214,72 +188,40 @@ TEST_P(CacheTest, PinnedUsageTest) {
    std::string key(i, 'a');
    auto kv_size = key.size() + 5;
    Cache::Handle* handle;
-    Cache::Handle* handle_in_precise_cache;
    cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter,
                  &handle);
-    assert(handle);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter, &handle_in_precise_cache);
-    assert(handle_in_precise_cache);
    pinned_usage += kv_size;
    ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-    ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
    if (i % 2 == 0) {
      cache->Release(handle);
-      precise_cache->Release(handle_in_precise_cache);
      pinned_usage -= kv_size;
      ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
    } else {
      unreleased_handles.push_front(handle);
-      unreleased_handles_in_precise_cache.push_front(handle_in_precise_cache);
    }
    if (i % 3 == 0) {
      unreleased_handles.push_front(cache->Lookup(key));
-      auto x = precise_cache->Lookup(key);
-      assert(x);
-      unreleased_handles_in_precise_cache.push_front(x);
      // If i % 2 == 0, then the entry was unpinned before Lookup, so pinned
      // usage increased
      if (i % 2 == 0) {
        pinned_usage += kv_size;
      }
      ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
    }
  }
-  auto precise_cache_pinned_usage = precise_cache->GetPinnedUsage();
-  ASSERT_LT(pinned_usage, precise_cache_pinned_usage);

  // check that overloading the cache does not change the pinned usage
  for (uint64_t i = 1; i < 2 * kCapacity; ++i) {
    auto key = ToString(i);
    cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                  dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
  }
  ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
-
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());

  // release handles for pinned entries to prevent memory leaks
  for (auto handle : unreleased_handles) {
    cache->Release(handle);
  }
-  for (auto handle : unreleased_handles_in_precise_cache) {
-    precise_cache->Release(handle);
-  }
-  ASSERT_EQ(0, cache->GetPinnedUsage());
-  ASSERT_EQ(0, precise_cache->GetPinnedUsage());
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
 }

 TEST_P(CacheTest, HitAndMiss) {
@@ -365,7 +307,7 @@ TEST_P(CacheTest, EvictionPolicy) {
  Insert(200, 201);

  // Frequently used entry must be kept around
-  for (int i = 0; i < kCacheSize + 200; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
    Insert(1000+i, 2000+i);
    ASSERT_EQ(101, Lookup(100));
  }
@@ -418,7 +360,7 @@ TEST_P(CacheTest, EvictionPolicyRef) {
  Insert(303, 104);

  // Insert entries much more than Cache capacity
-  for (int i = 0; i < kCacheSize + 200; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
    Insert(1000 + i, 2000 + i);
  }

@@ -609,10 +551,10 @@ TEST_P(CacheTest, SetCapacity) {
  }
 }

-TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
+TEST_P(CacheTest, SetStrictCapacityLimit) {
  // test1: set the flag to false. Insert more keys than capacity. See if they
  // all go through.
-  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
+  std::shared_ptr<Cache> cache = NewLRUCache(5, 0, false);
  std::vector<Cache::Handle*> handles(10);
  Status s;
  for (size_t i = 0; i < 10; i++) {
@@ -621,7 +563,6 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
    ASSERT_OK(s);
    ASSERT_NE(nullptr, handles[i]);
  }
-  ASSERT_EQ(10, cache->GetUsage());

  // test2: set the flag to true. Insert and check if it fails.
  std::string extra_key = "extra";
@@ -631,14 +572,13 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
  s = cache->Insert(extra_key, extra_value, 1, &deleter, &handle);
  ASSERT_TRUE(s.IsIncomplete());
  ASSERT_EQ(nullptr, handle);
-  ASSERT_EQ(10, cache->GetUsage());

  for (size_t i = 0; i < 10; i++) {
    cache->Release(handles[i]);
  }

  // test3: init with flag being true.
-  std::shared_ptr<Cache> cache2 = NewCache(5, 0, true);
+  std::shared_ptr<Cache> cache2 = NewLRUCache(5, 0, true);
  for (size_t i = 0; i < 5; i++) {
    std::string key = ToString(i + 1);
    s = cache2->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
@@ -652,7 +592,7 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
  s = cache2->Insert(extra_key, extra_value, 1, &deleter);
  // AS if the key have been inserted into cache but get evicted immediately.
  ASSERT_OK(s);
-  ASSERT_EQ(5, cache2->GetUsage());
+  ASSERT_EQ(5, cache->GetUsage());
  ASSERT_EQ(nullptr, cache2->Lookup(extra_key));

  for (size_t i = 0; i < 5; i++) {
@@ -747,23 +687,13 @@ TEST_P(CacheTest, DefaultShardBits) {
  ASSERT_EQ(6, sc->GetNumShardBits());
 }

-TEST_P(CacheTest, GetCharge) {
-  Insert(1, 2);
-  Cache::Handle* h1 = cache_->Lookup(EncodeKey(1));
-  ASSERT_EQ(2, DecodeValue(cache_->Value(h1)));
-  ASSERT_EQ(1, cache_->GetCharge(h1));
-  cache_->Release(h1);
-}
-
 #ifdef SUPPORT_CLOCK_CACHE
-std::shared_ptr<Cache> (*new_clock_cache_func)(
-    size_t, int, bool, CacheMetadataChargePolicy) = NewClockCache;
+shared_ptr<Cache> (*new_clock_cache_func)(size_t, int, bool) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                        testing::Values(kLRU, kClock));
 #else
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest, testing::Values(kLRU));
 #endif  // SUPPORT_CLOCK_CACHE
-INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest, testing::Values(kLRU));

 }  // namespace rocksdb

@@ -13,9 +13,8 @@

 namespace rocksdb {

-std::shared_ptr<Cache> NewClockCache(
-    size_t /*capacity*/, int /*num_shard_bits*/, bool /*strict_capacity_limit*/,
-    CacheMetadataChargePolicy /*metadata_charge_policy*/) {
+std::shared_ptr<Cache> NewClockCache(size_t /*capacity*/, int /*num_shard_bits*/,
+                                     bool /*strict_capacity_limit*/) {
  // Clock cache not supported.
  return nullptr;
 }
@@ -36,7 +35,6 @@ std::shared_ptr<Cache> NewClockCache(
 #include "tbb/concurrent_hash_map.h"

 #include "cache/sharded_cache.h"
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 #include "util/mutexlock.h"
@@ -204,27 +202,6 @@ struct CacheHandle {
    deleter = a.deleter;
    return *this;
  }
-
-  inline static size_t CalcTotalCharge(
-      Slice key, size_t charge,
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-      meta_charge += sizeof(CacheHandle);
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge +=
-          malloc_usable_size(static_cast<void*>(const_cast<char*>(key.data())));
-#else
-      meta_charge += key.size();
-#endif
-    }
-    return charge + meta_charge;
-  }
-
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    return CalcTotalCharge(key, charge, metadata_charge_policy);
-  }
 };

 // Key of hash map. We store hash value with the key for convenience.
@@ -257,35 +234,38 @@ struct CleanupContext {
 };

 // A cache shard which maintains its own CLOCK cache.
-class ClockCacheShard final : public CacheShard {
+class ClockCacheShard : public CacheShard {
 public:
  // Hash map type.
  typedef tbb::concurrent_hash_map<CacheKey, CacheHandle*, CacheKey> HashTable;

  ClockCacheShard();
-  ~ClockCacheShard() override;
+  ~ClockCacheShard();

  // Interfaces
-  void SetCapacity(size_t capacity) override;
-  void SetStrictCapacityLimit(bool strict_capacity_limit) override;
-  Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value),
-                Cache::Handle** handle, Cache::Priority priority) override;
-  Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
+  virtual void SetCapacity(size_t capacity) override;
+  virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override;
+  virtual Status Insert(const Slice& key, uint32_t hash, void* value,
+                        size_t charge,
+                        void (*deleter)(const Slice& key, void* value),
+                        Cache::Handle** handle,
+                        Cache::Priority priority) override;
+  virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
  // If the entry in in cache, increase reference count and return true.
  // Return false otherwise.
  //
  // Not necessary to hold mutex_ before being called.
-  bool Ref(Cache::Handle* handle) override;
-  bool Release(Cache::Handle* handle, bool force_erase = false) override;
-  void Erase(const Slice& key, uint32_t hash) override;
+  virtual bool Ref(Cache::Handle* handle) override;
+  virtual bool Release(Cache::Handle* handle,
+                       bool force_erase = false) override;
+  virtual void Erase(const Slice& key, uint32_t hash) override;
  bool EraseAndConfirm(const Slice& key, uint32_t hash,
                       CleanupContext* context);
-  size_t GetUsage() const override;
-  size_t GetPinnedUsage() const override;
-  void EraseUnRefEntries() override;
-  void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
-                              bool thread_safe) override;
+  virtual size_t GetUsage() const override;
+  virtual size_t GetPinnedUsage() const override;
+  virtual void EraseUnRefEntries() override;
+  virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
+                                      bool thread_safe) override;

 private:
  static const uint32_t kInCacheBit = 1;
@@ -427,12 +407,11 @@ void ClockCacheShard::RecycleHandle(CacheHandle* handle,
  assert(!InCache(handle->flags) && CountRefs(handle->flags) == 0);
  context->to_delete_key.push_back(handle->key.data());
  context->to_delete_value.emplace_back(*handle);
-  size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
  handle->key.clear();
  handle->value = nullptr;
  handle->deleter = nullptr;
  recycle_.push_back(handle);
-  usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+  usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
 }

 void ClockCacheShard::Cleanup(const CleanupContext& context) {
@@ -458,8 +437,7 @@ bool ClockCacheShard::Ref(Cache::Handle* h) {
                                            std::memory_order_relaxed)) {
      if (CountRefs(flags) == 0) {
        // No reference count before the operation.
-        size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-        pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+        pinned_usage_.fetch_add(handle->charge, std::memory_order_relaxed);
      }
      return true;
    }
@@ -479,8 +457,7 @@ bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
  assert(CountRefs(flags) > 0);
  if (CountRefs(flags) == 1) {
    // this is the last reference.
-    size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-    pinned_usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
    // Cleanup if it is the last reference.
    if (!InCache(flags)) {
      MutexLock l(&mutex_);
@@ -565,10 +542,8 @@ CacheHandle* ClockCacheShard::Insert(
    const Slice& key, uint32_t hash, void* value, size_t charge,
    void (*deleter)(const Slice& key, void* value), bool hold_reference,
    CleanupContext* context) {
-  size_t total_charge =
-      CacheHandle::CalcTotalCharge(key, charge, metadata_charge_policy_);
  MutexLock l(&mutex_);
-  bool success = EvictFromCache(total_charge, context);
+  bool success = EvictFromCache(charge, context);
  bool strict = strict_capacity_limit_.load(std::memory_order_relaxed);
  if (!success && (strict || !hold_reference)) {
    context->to_delete_key.push_back(key.data());
@@ -603,9 +578,9 @@ CacheHandle* ClockCacheShard::Insert(
  }
  table_.insert(HashTable::value_type(CacheKey(key, hash), handle));
  if (hold_reference) {
-    pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_add(charge, std::memory_order_relaxed);
  }
-  usage_.fetch_add(total_charge, std::memory_order_relaxed);
+  usage_.fetch_add(charge, std::memory_order_relaxed);
  return handle;
 }

@@ -700,45 +675,41 @@ void ClockCacheShard::EraseUnRefEntries() {
  Cleanup(context);
 }

-class ClockCache final : public ShardedCache {
+class ClockCache : public ShardedCache {
 public:
-  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-             CacheMetadataChargePolicy metadata_charge_policy)
+  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit)
      : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
    int num_shards = 1 << num_shard_bits;
    shards_ = new ClockCacheShard[num_shards];
-    for (int i = 0; i < num_shards; i++) {
-      shards_[i].set_metadata_charge_policy(metadata_charge_policy);
-    }
    SetCapacity(capacity);
    SetStrictCapacityLimit(strict_capacity_limit);
  }

-  ~ClockCache() override { delete[] shards_; }
+  virtual ~ClockCache() { delete[] shards_; }

-  const char* Name() const override { return "ClockCache"; }
+  virtual const char* Name() const override { return "ClockCache"; }

-  CacheShard* GetShard(int shard) override {
+  virtual CacheShard* GetShard(int shard) override {
    return reinterpret_cast<CacheShard*>(&shards_[shard]);
  }

-  const CacheShard* GetShard(int shard) const override {
+  virtual const CacheShard* GetShard(int shard) const override {
    return reinterpret_cast<CacheShard*>(&shards_[shard]);
  }

-  void* Value(Handle* handle) override {
+  virtual void* Value(Handle* handle) override {
    return reinterpret_cast<const CacheHandle*>(handle)->value;
  }

-  size_t GetCharge(Handle* handle) const override {
+  virtual size_t GetCharge(Handle* handle) const override {
    return reinterpret_cast<const CacheHandle*>(handle)->charge;
  }

-  uint32_t GetHash(Handle* handle) const override {
+  virtual uint32_t GetHash(Handle* handle) const override {
    return reinterpret_cast<const CacheHandle*>(handle)->hash;
  }

-  void DisownData() override { shards_ = nullptr; }
+  virtual void DisownData() override { shards_ = nullptr; }

 private:
  ClockCacheShard* shards_;
@@ -746,14 +717,13 @@ class ClockCache final : public ShardedCache {

 }  // end anonymous namespace

-std::shared_ptr<Cache> NewClockCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
+                                     bool strict_capacity_limit) {
  if (num_shard_bits < 0) {
    num_shard_bits = GetDefaultCacheShardBits(capacity);
  }
-  return std::make_shared<ClockCache>(
-      capacity, num_shard_bits, strict_capacity_limit, metadata_charge_policy);
+  return std::make_shared<ClockCache>(capacity, num_shard_bits,
+                                      strict_capacity_limit);
 }

 }  // namespace rocksdb
@@ -7,6 +7,10 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/lru_cache.h"

 #include <assert.h>
@@ -24,7 +28,7 @@ LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {

 LRUHandleTable::~LRUHandleTable() {
  ApplyToAllCacheEntries([](LRUHandle* h) {
-    if (!h->HasRefs()) {
+    if (h->refs == 1) {
      h->Free();
    }
  });
@@ -96,18 +100,14 @@ void LRUHandleTable::Resize() {
 }

 LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                             double high_pri_pool_ratio,
-                             bool use_adaptive_mutex,
-                             CacheMetadataChargePolicy metadata_charge_policy)
+                             double high_pri_pool_ratio)
    : capacity_(0),
      high_pri_pool_usage_(0),
      strict_capacity_limit_(strict_capacity_limit),
      high_pri_pool_ratio_(high_pri_pool_ratio),
      high_pri_pool_capacity_(0),
      usage_(0),
-      lru_usage_(0),
-      mutex_(use_adaptive_mutex) {
-  set_metadata_charge_policy(metadata_charge_policy);
+      lru_usage_(0) {
  // Make empty circular linked list
  lru_.next = &lru_;
  lru_.prev = &lru_;
@@ -115,20 +115,30 @@ LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
  SetCapacity(capacity);
 }

+LRUCacheShard::~LRUCacheShard() {}
+
+bool LRUCacheShard::Unref(LRUHandle* e) {
+  assert(e->refs > 0);
+  e->refs--;
+  return e->refs == 0;
+}
+
+// Call deleter and free
+
 void LRUCacheShard::EraseUnRefEntries() {
  autovector<LRUHandle*> last_reference_list;
  {
    MutexLock l(&mutex_);
    while (lru_.next != &lru_) {
      LRUHandle* old = lru_.next;
-      // LRU list contains only elements which can be evicted
-      assert(old->InCache() && !old->HasRefs());
+      assert(old->InCache());
+      assert(old->refs ==
+             1);  // LRU list contains elements which may be evicted
      LRU_Remove(old);
      table_.Remove(old->key(), old->hash);
      old->SetInCache(false);
-      size_t total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
+      Unref(old);
+      usage_ -= old->charge;
      last_reference_list.push_back(old);
    }
  }
@@ -140,27 +150,22 @@ void LRUCacheShard::EraseUnRefEntries() {

 void LRUCacheShard::ApplyToAllCacheEntries(void (*callback)(void*, size_t),
                                           bool thread_safe) {
-  const auto applyCallback = [&]() {
-    table_.ApplyToAllCacheEntries(
-        [callback](LRUHandle* h) { callback(h->value, h->charge); });
-  };
-
  if (thread_safe) {
-    MutexLock l(&mutex_);
-    applyCallback();
-  } else {
-    applyCallback();
+    mutex_.Lock();
+  }
+  table_.ApplyToAllCacheEntries(
+      [callback](LRUHandle* h) { callback(h->value, h->charge); });
+  if (thread_safe) {
+    mutex_.Unlock();
  }
 }

 void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
-  MutexLock l(&mutex_);
  *lru = &lru_;
  *lru_low_pri = lru_low_pri_;
 }

 size_t LRUCacheShard::TEST_GetLRUSize() {
-  MutexLock l(&mutex_);
  LRUHandle* lru_handle = lru_.next;
  size_t lru_size = 0;
  while (lru_handle != &lru_) {
@@ -184,19 +189,16 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
  e->next->prev = e->prev;
  e->prev->next = e->next;
  e->prev = e->next = nullptr;
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-  assert(lru_usage_ >= total_charge);
-  lru_usage_ -= total_charge;
+  lru_usage_ -= e->charge;
  if (e->InHighPriPool()) {
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    assert(high_pri_pool_usage_ >= e->charge);
+    high_pri_pool_usage_ -= e->charge;
  }
 }

 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
  assert(e->next == nullptr);
  assert(e->prev == nullptr);
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
  if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
    // Inset "e" to head of LRU list.
    e->next = &lru_;
@@ -204,7 +206,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
    e->prev->next = e;
    e->next->prev = e;
    e->SetInHighPriPool(true);
-    high_pri_pool_usage_ += total_charge;
+    high_pri_pool_usage_ += e->charge;
    MaintainPoolSize();
  } else {
    // Insert "e" to the head of low-pri pool. Note that when
@@ -216,7 +218,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
    e->SetInHighPriPool(false);
    lru_low_pri_ = e;
  }
-  lru_usage_ += total_charge;
+  lru_usage_ += e->charge;
 }

 void LRUCacheShard::MaintainPoolSize() {
@@ -225,25 +227,21 @@ void LRUCacheShard::MaintainPoolSize() {
    lru_low_pri_ = lru_low_pri_->next;
    assert(lru_low_pri_ != &lru_);
    lru_low_pri_->SetInHighPriPool(false);
-    size_t total_charge =
-        lru_low_pri_->CalcTotalCharge(metadata_charge_policy_);
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    high_pri_pool_usage_ -= lru_low_pri_->charge;
  }
 }

 void LRUCacheShard::EvictFromLRU(size_t charge,
                                 autovector<LRUHandle*>* deleted) {
-  while ((usage_ + charge) > capacity_ && lru_.next != &lru_) {
+  while (usage_ + charge > capacity_ && lru_.next != &lru_) {
    LRUHandle* old = lru_.next;
-    // LRU list contains only elements which can be evicted
-    assert(old->InCache() && !old->HasRefs());
+    assert(old->InCache());
+    assert(old->refs == 1);  // LRU list contains elements which may be evicted
    LRU_Remove(old);
    table_.Remove(old->key(), old->hash);
    old->SetInCache(false);
-    size_t old_total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-    assert(usage_ >= old_total_charge);
-    usage_ -= old_total_charge;
+    Unref(old);
+    usage_ -= old->charge;
    deleted->push_back(old);
  }
 }
@@ -256,8 +254,8 @@ void LRUCacheShard::SetCapacity(size_t capacity) {
    high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
    EvictFromLRU(0, &last_reference_list);
  }
-
-  // Free the entries outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
  for (auto entry : last_reference_list) {
    entry->Free();
  }
@@ -273,22 +271,22 @@ Cache::Handle* LRUCacheShard::Lookup(const Slice& key, uint32_t hash) {
  LRUHandle* e = table_.Lookup(key, hash);
  if (e != nullptr) {
    assert(e->InCache());
-    if (!e->HasRefs()) {
-      // The entry is in LRU since it's in hash and has no external references
+    if (e->refs == 1) {
      LRU_Remove(e);
    }
-    e->Ref();
+    e->refs++;
    e->SetHit();
  }
  return reinterpret_cast<Cache::Handle*>(e);
 }

 bool LRUCacheShard::Ref(Cache::Handle* h) {
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(h);
+  LRUHandle* handle = reinterpret_cast<LRUHandle*>(h);
  MutexLock l(&mutex_);
-  // To create another reference - entry must be already externally referenced
-  assert(e->HasRefs());
-  e->Ref();
+  if (handle->InCache() && handle->refs == 1) {
+    LRU_Remove(handle);
+  }
+  handle->refs++;
  return true;
 }

@@ -307,29 +305,30 @@ bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
  bool last_reference = false;
  {
    MutexLock l(&mutex_);
-    last_reference = e->Unref();
-    if (last_reference && e->InCache()) {
+    last_reference = Unref(e);
+    if (last_reference) {
+      usage_ -= e->charge;
+    }
+    if (e->refs == 1 && e->InCache()) {
      // The item is still in cache, and nobody else holds a reference to it
      if (usage_ > capacity_ || force_erase) {
+        // the cache is full
        // The LRU list must be empty since the cache is full
-        assert(lru_.next == &lru_ || force_erase);
-        // Take this opportunity and remove the item
+        assert(!(usage_ > capacity_) || lru_.next == &lru_);
+        // take this opportunity and remove the item
        table_.Remove(e->key(), e->hash);
        e->SetInCache(false);
+        Unref(e);
+        usage_ -= e->charge;
+        last_reference = true;
      } else {
-        // Put the item back on the LRU list, and don't free it
+        // put the item on the list to be potentially freed
        LRU_Insert(e);
-        last_reference = false;
      }
    }
-    if (last_reference) {
-      size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
-    }
  }

-  // Free the entry here outside of mutex for performance reasons
+  // free outside of mutex
  if (last_reference) {
    e->Free();
  }
@@ -345,7 +344,7 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
  // It shouldn't happen very often though.
  LRUHandle* e = reinterpret_cast<LRUHandle*>(
      new char[sizeof(LRUHandle) - 1 + key.size()]);
-  Status s = Status::OK();
+  Status s;
  autovector<LRUHandle*> last_reference_list;

  e->value = value;
@@ -354,26 +353,26 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
  e->key_length = key.size();
  e->flags = 0;
  e->hash = hash;
-  e->refs = 0;
+  e->refs = (handle == nullptr
+                 ? 1
+                 : 2);  // One from LRUCache, one for the returned handle
  e->next = e->prev = nullptr;
  e->SetInCache(true);
  e->SetPriority(priority);
  memcpy(e->key_data, key.data(), key.size());
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);

  {
    MutexLock l(&mutex_);

    // Free the space following strict LRU policy until enough space
    // is freed or the lru list is empty
-    EvictFromLRU(total_charge, &last_reference_list);
+    EvictFromLRU(charge, &last_reference_list);

-    if ((usage_ + total_charge) > capacity_ &&
+    if (usage_ - lru_usage_ + charge > capacity_ &&
        (strict_capacity_limit_ || handle == nullptr)) {
      if (handle == nullptr) {
        // Don't insert the entry but still return ok, as if the entry inserted
        // into cache and get evicted immediately.
-        e->SetInCache(false);
        last_reference_list.push_back(e);
      } else {
        delete[] reinterpret_cast<char*>(e);
@@ -381,33 +380,32 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
        s = Status::Incomplete("Insert failed due to LRU cache being full.");
      }
    } else {
-      // Insert into the cache. Note that the cache might get larger than its
-      // capacity if not enough space was freed up.
+      // insert into the cache
+      // note that the cache might get larger than its capacity if not enough
+      // space was freed
      LRUHandle* old = table_.Insert(e);
-      usage_ += total_charge;
+      usage_ += e->charge;
      if (old != nullptr) {
-        assert(old->InCache());
        old->SetInCache(false);
-        if (!old->HasRefs()) {
-          // old is on LRU because it's in cache and its reference count is 0
+        if (Unref(old)) {
+          usage_ -= old->charge;
+          // old is on LRU because it's in cache and its reference count
+          // was just 1 (Unref returned 0)
          LRU_Remove(old);
-          size_t old_total_charge =
-              old->CalcTotalCharge(metadata_charge_policy_);
-          assert(usage_ >= old_total_charge);
-          usage_ -= old_total_charge;
          last_reference_list.push_back(old);
        }
      }
      if (handle == nullptr) {
        LRU_Insert(e);
      } else {
-        e->Ref();
        *handle = reinterpret_cast<Cache::Handle*>(e);
      }
+      s = Status::OK();
    }
  }

-  // Free the entries here outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
  for (auto entry : last_reference_list) {
    entry->Free();
  }
@@ -422,20 +420,18 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
    MutexLock l(&mutex_);
    e = table_.Remove(key, hash);
    if (e != nullptr) {
-      assert(e->InCache());
-      e->SetInCache(false);
-      if (!e->HasRefs()) {
-        // The entry is in LRU since it's in hash and has no external references
-        LRU_Remove(e);
-        size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-        assert(usage_ >= total_charge);
-        usage_ -= total_charge;
-        last_reference = true;
+      last_reference = Unref(e);
+      if (last_reference) {
+        usage_ -= e->charge;
      }
+      if (last_reference && e->InCache()) {
+        LRU_Remove(e);
+      }
+      e->SetInCache(false);
    }
  }

-  // Free the entry here outside of mutex for performance reasons
+  // mutex not held here
  // last_reference will only be true if e != nullptr
  if (last_reference) {
    e->Free();
@@ -466,9 +462,7 @@ std::string LRUCacheShard::GetPrintableOptions() const {

 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
                   bool strict_capacity_limit, double high_pri_pool_ratio,
-                   std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex,
-                   CacheMetadataChargePolicy metadata_charge_policy)
+                   std::shared_ptr<MemoryAllocator> allocator)
    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
                   std::move(allocator)) {
  num_shards_ = 1 << num_shard_bits;
@@ -477,8 +471,7 @@ LRUCache::LRUCache(size_t capacity, int num_shard_bits,
  size_t per_shard = (capacity + (num_shards_ - 1)) / num_shards_;
  for (int i = 0; i < num_shards_; i++) {
    new (&shards_[i])
-        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio,
-                      use_adaptive_mutex, metadata_charge_policy);
+        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio);
  }
 }

@@ -547,15 +540,13 @@ std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
  return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
                     cache_opts.strict_capacity_limit,
                     cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-                     cache_opts.metadata_charge_policy);
+                     cache_opts.memory_allocator);
 }

 std::shared_ptr<Cache> NewLRUCache(
    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+    std::shared_ptr<MemoryAllocator> memory_allocator) {
  if (num_shard_bits >= 20) {
    return nullptr;  // the cache cannot be sharded into too many fine pieces
  }
@@ -566,9 +557,9 @@ std::shared_ptr<Cache> NewLRUCache(
  if (num_shard_bits < 0) {
    num_shard_bits = GetDefaultCacheShardBits(capacity);
  }
-  return std::make_shared<LRUCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      std::move(memory_allocator), use_adaptive_mutex, metadata_charge_policy);
+  return std::make_shared<LRUCache>(capacity, num_shard_bits,
+                                    strict_capacity_limit, high_pri_pool_ratio,
+                                    std::move(memory_allocator));
 }

 }  // namespace rocksdb
@@ -12,40 +12,36 @@

 #include "cache/sharded_cache.h"

-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"

 namespace rocksdb {

-// LRU cache implementation. This class is not thread-safe.
+// LRU cache implementation

 // An entry is a variable length heap-allocated structure.
 // Entries are referenced by cache and/or by any external entity.
-// The cache keeps all its entries in a hash table. Some elements
+// The cache keeps all its entries in table. Some elements
 // are also stored on LRU list.
 //
 // LRUHandle can be in these states:
 // 1. Referenced externally AND in hash table.
-//    In that case the entry is *not* in the LRU list
-//    (refs >= 1 && in_cache == true)
-// 2. Not referenced externally AND in hash table.
-//    In that case the entry is in the LRU list and can be freed.
-//    (refs == 0 && in_cache == true)
-// 3. Referenced externally AND not in hash table.
-//    In that case the entry is not in the LRU list and not in hash table.
-//    The entry can be freed when refs becomes 0.
-//    (refs >= 1 && in_cache == false)
+//  In that case the entry is *not* in the LRU. (refs > 1 && in_cache == true)
+// 2. Not referenced externally and in hash table. In that case the entry is
+// in the LRU and can be freed. (refs == 1 && in_cache == true)
+// 3. Referenced externally and not in hash table. In that case the entry is
+// in not on LRU and not in table. (refs >= 1 && in_cache == false)
 //
 // All newly created LRUHandles are in state 1. If you call
-// LRUCacheShard::Release on entry in state 1, it will go into state 2.
-// To move from state 1 to state 3, either call LRUCacheShard::Erase or
-// LRUCacheShard::Insert with the same key (but possibly different value).
+// LRUCacheShard::Release
+// on entry in state 1, it will go into state 2. To move from state 1 to
+// state 3, either call LRUCacheShard::Erase or LRUCacheShard::Insert with the
+// same key.
 // To move from state 2 to state 1, use LRUCacheShard::Lookup.
 // Before destruction, make sure that no handles are in state 1. This means
 // that any successful LRUCacheShard::Lookup/LRUCacheShard::Insert have a
-// matching LRUCache::Release (to move into state 2) or LRUCacheShard::Erase
-// (to move into state 3).
+// matching
+// RUCache::Release (to move into state 2) or LRUCacheShard::Erase (for state 3)

 struct LRUHandle {
  void* value;
@@ -55,96 +51,67 @@ struct LRUHandle {
  LRUHandle* prev;
  size_t charge;  // TODO(opt): Only allow uint32_t?
  size_t key_length;
-  // The hash of key(). Used for fast sharding and comparisons.
-  uint32_t hash;
-  // The number of external refs to this entry. The cache itself is not counted.
-  uint32_t refs;
+  uint32_t refs;     // a number of refs to this entry
+                     // cache itself is counted as 1

-  enum Flags : uint8_t {
-    // Whether this entry is referenced by the hash table.
-    IN_CACHE = (1 << 0),
-    // Whether this entry is high priority entry.
-    IS_HIGH_PRI = (1 << 1),
-    // Whether this entry is in high-pri pool.
-    IN_HIGH_PRI_POOL = (1 << 2),
-    // Wwhether this entry has had any lookups (hits).
-    HAS_HIT = (1 << 3),
-  };
+  // Include the following flags:
+  //   in_cache:    whether this entry is referenced by the hash table.
+  //   is_high_pri: whether this entry is high priority entry.
+  //   in_high_pri_pool: whether this entry is in high-pri pool.
+  char flags;

-  uint8_t flags;
+  uint32_t hash;     // Hash of key(); used for fast sharding and comparisons

-  // Beginning of the key (MUST BE THE LAST FIELD IN THIS STRUCT!)
-  char key_data[1];
+  char key_data[1];  // Beginning of key

-  Slice key() const { return Slice(key_data, key_length); }
-
-  // Increase the reference count by 1.
-  void Ref() { refs++; }
-
-  // Just reduce the reference count by 1. Return true if it was last reference.
-  bool Unref() {
-    assert(refs > 0);
-    refs--;
-    return refs == 0;
+  Slice key() const {
+    // For cheaper lookups, we allow a temporary Handle object
+    // to store a pointer to a key in "value".
+    if (next == this) {
+      return *(reinterpret_cast<Slice*>(value));
+    } else {
+      return Slice(key_data, key_length);
+    }
  }

-  // Return true if there are external refs, false otherwise.
-  bool HasRefs() const { return refs > 0; }
-
-  bool InCache() const { return flags & IN_CACHE; }
-  bool IsHighPri() const { return flags & IS_HIGH_PRI; }
-  bool InHighPriPool() const { return flags & IN_HIGH_PRI_POOL; }
-  bool HasHit() const { return flags & HAS_HIT; }
+  bool InCache() { return flags & 1; }
+  bool IsHighPri() { return flags & 2; }
+  bool InHighPriPool() { return flags & 4; }
+  bool HasHit() { return flags & 8; }

  void SetInCache(bool in_cache) {
    if (in_cache) {
-      flags |= IN_CACHE;
+      flags |= 1;
    } else {
-      flags &= ~IN_CACHE;
+      flags &= ~1;
    }
  }

  void SetPriority(Cache::Priority priority) {
    if (priority == Cache::Priority::HIGH) {
-      flags |= IS_HIGH_PRI;
+      flags |= 2;
    } else {
-      flags &= ~IS_HIGH_PRI;
+      flags &= ~2;
    }
  }

  void SetInHighPriPool(bool in_high_pri_pool) {
    if (in_high_pri_pool) {
-      flags |= IN_HIGH_PRI_POOL;
+      flags |= 4;
    } else {
-      flags &= ~IN_HIGH_PRI_POOL;
+      flags &= ~4;
    }
  }

-  void SetHit() { flags |= HAS_HIT; }
+  void SetHit() { flags |= 8; }

  void Free() {
-    assert(refs == 0);
+    assert((refs == 1 && InCache()) || (refs == 0 && !InCache()));
    if (deleter) {
      (*deleter)(key(), value);
    }
    delete[] reinterpret_cast<char*>(this);
  }
-
-  // Caclculate the memory usage by metadata
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    assert(key_length);
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge += malloc_usable_size(static_cast<void*>(this));
-#else
-      // This is the size that is used when a new handle is created
-      meta_charge += sizeof(LRUHandle) - 1 + key_length;
-#endif
-    }
-    return charge + meta_charge;
-  }
 };

 // We provide our own simple hash table since it removes a whole bunch
@@ -190,12 +157,11 @@ class LRUHandleTable {
 };

 // A single shard of sharded cache.
-class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
+class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
 public:
  LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                double high_pri_pool_ratio, bool use_adaptive_mutex,
-                CacheMetadataChargePolicy metadata_charge_policy);
-  virtual ~LRUCacheShard() override = default;
+                double high_pri_pool_ratio);
+  virtual ~LRUCacheShard();

  // Separate from constructor so caller can easily make an array of LRUCache
  // if current usage is more than new capacity, the function will attempt to
@@ -251,6 +217,10 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  // high-pri pool is no larger than the size specify by high_pri_pool_pct.
  void MaintainPoolSize();

+  // Just reduce the reference count by 1.
+  // Return true if last reference
+  bool Unref(LRUHandle* e);
+
  // Free some space following strict LRU policy until enough space
  // to hold (usage_ + charge) is freed or the lru list is empty
  // This function is not thread safe - it needs to be executed while
@@ -306,18 +276,11 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  mutable port::Mutex mutex_;
 };

-class LRUCache
-#ifdef NDEBUG
-    final
-#endif
-    : public ShardedCache {
+class LRUCache : public ShardedCache {
 public:
  LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
           double high_pri_pool_ratio,
-           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
+           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
  virtual ~LRUCache();
  virtual const char* Name() const override { return "LRUCache"; }
  virtual CacheShard* GetShard(int shard) override;
@@ -8,14 +8,14 @@
 #include <string>
 #include <vector>
 #include "port/port.h"
-#include "test_util/testharness.h"
+#include "util/testharness.h"

 namespace rocksdb {

 class LRUCacheTest : public testing::Test {
 public:
  LRUCacheTest() {}
-  ~LRUCacheTest() override { DeleteCache(); }
+  ~LRUCacheTest() { DeleteCache(); }

  void DeleteCache() {
    if (cache_ != nullptr) {
@@ -25,14 +25,12 @@ class LRUCacheTest : public testing::Test {
    }
  }

-  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0,
-                bool use_adaptive_mutex = kDefaultToAdaptiveMutex) {
+  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0) {
    DeleteCache();
    cache_ = reinterpret_cast<LRUCacheShard*>(
        port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
    new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
-                               high_pri_pool_ratio, use_adaptive_mutex,
-                               kDontChargeCacheMetadata);
+                               high_pri_pool_ratio);
  }

  void Insert(const std::string& key,
@@ -7,6 +7,10 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/sharded_cache.h"

 #include <string>
@@ -40,13 +40,6 @@ class CacheShard {
                                      bool thread_safe) = 0;
  virtual void EraseUnRefEntries() = 0;
  virtual std::string GetPrintableOptions() const { return ""; }
-  void set_metadata_charge_policy(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    metadata_charge_policy_ = metadata_charge_policy;
-  }
-
- protected:
-  CacheMetadataChargePolicy metadata_charge_policy_ = kDontChargeCacheMetadata;
 };

 // Generic cache interface which shards cache by hash of keys. 2^num_shard_bits
@@ -61,8 +54,7 @@ class ShardedCache : public Cache {
  virtual CacheShard* GetShard(int shard) = 0;
  virtual const CacheShard* GetShard(int shard) const = 0;
  virtual void* Value(Handle* handle) override = 0;
-  virtual size_t GetCharge(Handle* handle) const override = 0;
-
+  virtual size_t GetCharge(Handle* handle) const = 0;
  virtual uint32_t GetHash(Handle* handle) const = 0;
  virtual void DisownData() override = 0;

@@ -91,7 +83,7 @@ class ShardedCache : public Cache {

 private:
  static inline uint32_t HashSlice(const Slice& s) {
-    return static_cast<uint32_t>(GetSliceNPHash64(s));
+    return Hash(s.data(), s.size(), 0);
  }

  uint32_t Shard(uint32_t hash) {
@@ -1,29 +1,21 @@
 # - Find JeMalloc library
 # Find the native JeMalloc includes and library
 #
-# JeMalloc_INCLUDE_DIRS - where to find jemalloc.h, etc.
-# JeMalloc_LIBRARIES - List of libraries when using jemalloc.
-# JeMalloc_FOUND - True if jemalloc found.
+# JEMALLOC_INCLUDE_DIR - where to find jemalloc.h, etc.
+# JEMALLOC_LIBRARIES - List of libraries when using jemalloc.
+# JEMALLOC_FOUND - True if jemalloc found.

-find_path(JeMalloc_INCLUDE_DIRS
+find_path(JEMALLOC_INCLUDE_DIR
  NAMES jemalloc/jemalloc.h
  HINTS ${JEMALLOC_ROOT_DIR}/include)

-find_library(JeMalloc_LIBRARIES
+find_library(JEMALLOC_LIBRARIES
  NAMES jemalloc
  HINTS ${JEMALLOC_ROOT_DIR}/lib)

 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(JeMalloc DEFAULT_MSG JeMalloc_LIBRARIES JeMalloc_INCLUDE_DIRS)
+find_package_handle_standard_args(jemalloc DEFAULT_MSG JEMALLOC_LIBRARIES JEMALLOC_INCLUDE_DIR)

 mark_as_advanced(
-  JeMalloc_LIBRARIES
-  JeMalloc_INCLUDE_DIRS)
-
-if(JeMalloc_FOUND AND NOT (TARGET JeMalloc::JeMalloc))
-  add_library (JeMalloc::JeMalloc UNKNOWN IMPORTED)
-  set_target_properties(JeMalloc::JeMalloc
-    PROPERTIES
-      IMPORTED_LOCATION ${JeMalloc_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${JeMalloc_INCLUDE_DIRS})
-endif()
+  JEMALLOC_LIBRARIES
+  JEMALLOC_INCLUDE_DIR)
@@ -1,11 +1,11 @@
 # - Find NUMA
 # Find the NUMA library and includes
 #
-# NUMA_INCLUDE_DIRS - where to find numa.h, etc.
+# NUMA_INCLUDE_DIR - where to find numa.h, etc.
 # NUMA_LIBRARIES - List of libraries when using NUMA.
 # NUMA_FOUND - True if NUMA found.

-find_path(NUMA_INCLUDE_DIRS
+find_path(NUMA_INCLUDE_DIR
  NAMES numa.h numaif.h
  HINTS ${NUMA_ROOT_DIR}/include)

@@ -14,16 +14,8 @@ find_library(NUMA_LIBRARIES
  HINTS ${NUMA_ROOT_DIR}/lib)

 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIRS)
+find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIR)

 mark_as_advanced(
  NUMA_LIBRARIES
-  NUMA_INCLUDE_DIRS)
-
-if(NUMA_FOUND AND NOT (TARGET NUMA::NUMA))
-  add_library (NUMA::NUMA UNKNOWN IMPORTED)
-  set_target_properties(NUMA::NUMA
-    PROPERTIES
-      IMPORTED_LOCATION ${NUMA_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${NUMA_INCLUDE_DIRS})
-endif()
+  NUMA_INCLUDE_DIR)
@@ -1,7 +1,7 @@
 # - Find TBB
 # Find the Thread Building Blocks library and includes
 #
-# TBB_INCLUDE_DIRS - where to find tbb.h, etc.
+# TBB_INCLUDE_DIR - where to find tbb.h, etc.
 # TBB_LIBRARIES - List of libraries when using TBB.
 # TBB_FOUND - True if TBB found.

@@ -9,25 +9,17 @@ if(NOT DEFINED TBB_ROOT_DIR)
  set(TBB_ROOT_DIR "$ENV{TBBROOT}")
 endif()

-find_path(TBB_INCLUDE_DIRS
-  NAMES tbb/tbb.h
-  HINTS ${TBB_ROOT_DIR}/include)
+find_path(TBB_INCLUDE_DIR
+NAMES tbb/tbb.h
+HINTS ${TBB_ROOT_DIR}/include)

 find_library(TBB_LIBRARIES
-  NAMES tbb
-  HINTS ${TBB_ROOT_DIR}/lib ENV LIBRARY_PATH)
+NAMES tbb
+HINTS ${TBB_ROOT_DIR}/lib ENV LIBRARY_PATH)

 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIRS)
+find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIR)

 mark_as_advanced(
-  TBB_LIBRARIES
-  TBB_INCLUDE_DIRS)
-
-if(TBB_FOUND AND NOT (TARGET TBB::TBB))
-  add_library (TBB::TBB UNKNOWN IMPORTED)
-  set_target_properties(TBB::TBB
-    PROPERTIES
-      IMPORTED_LOCATION ${TBB_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${TBB_INCLUDE_DIRS})
-endif()
+TBB_LIBRARIES
+TBB_INCLUDE_DIR)
@@ -0,0 +1,21 @@
+# - Find Bzip2
+# Find the bzip2 compression library and includes
+#
+# BZIP2_INCLUDE_DIR - where to find bzlib.h, etc.
+# BZIP2_LIBRARIES - List of libraries when using bzip2.
+# BZIP2_FOUND - True if bzip2 found.
+
+find_path(BZIP2_INCLUDE_DIR
+  NAMES bzlib.h
+  HINTS ${BZIP2_ROOT_DIR}/include)
+
+find_library(BZIP2_LIBRARIES
+  NAMES bz2
+  HINTS ${BZIP2_ROOT_DIR}/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(bzip2 DEFAULT_MSG BZIP2_LIBRARIES BZIP2_INCLUDE_DIR)
+
+mark_as_advanced(
+  BZIP2_LIBRARIES
+  BZIP2_INCLUDE_DIR)
@@ -1,29 +1,21 @@
 # - Find Lz4
 # Find the lz4 compression library and includes
 #
-# lz4_INCLUDE_DIRS - where to find lz4.h, etc.
-# lz4_LIBRARIES - List of libraries when using lz4.
-# lz4_FOUND - True if lz4 found.
+# LZ4_INCLUDE_DIR - where to find lz4.h, etc.
+# LZ4_LIBRARIES - List of libraries when using lz4.
+# LZ4_FOUND - True if lz4 found.

-find_path(lz4_INCLUDE_DIRS
+find_path(LZ4_INCLUDE_DIR
  NAMES lz4.h
-  HINTS ${lz4_ROOT_DIR}/include)
+  HINTS ${LZ4_ROOT_DIR}/include)

-find_library(lz4_LIBRARIES
+find_library(LZ4_LIBRARIES
  NAMES lz4
-  HINTS ${lz4_ROOT_DIR}/lib)
+  HINTS ${LZ4_ROOT_DIR}/lib)

 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(lz4 DEFAULT_MSG lz4_LIBRARIES lz4_INCLUDE_DIRS)
+find_package_handle_standard_args(lz4 DEFAULT_MSG LZ4_LIBRARIES LZ4_INCLUDE_DIR)

 mark_as_advanced(
-  lz4_LIBRARIES
-  lz4_INCLUDE_DIRS)
-
-if(lz4_FOUND AND NOT (TARGET lz4::lz4))
-  add_library(lz4::lz4 UNKNOWN IMPORTED)
-  set_target_properties(lz4::lz4
-    PROPERTIES
-      IMPORTED_LOCATION ${lz4_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${lz4_INCLUDE_DIRS})
-endif()
+  LZ4_LIBRARIES
+  LZ4_INCLUDE_DIR)
@@ -1,29 +1,21 @@
 # - Find Snappy
 # Find the snappy compression library and includes
 #
-# snappy_INCLUDE_DIRS - where to find snappy.h, etc.
-# snappy_LIBRARIES - List of libraries when using snappy.
-# snappy_FOUND - True if snappy found.
+# SNAPPY_INCLUDE_DIR - where to find snappy.h, etc.
+# SNAPPY_LIBRARIES - List of libraries when using snappy.
+# SNAPPY_FOUND - True if snappy found.

-find_path(snappy_INCLUDE_DIRS
+find_path(SNAPPY_INCLUDE_DIR
  NAMES snappy.h
-  HINTS ${snappy_ROOT_DIR}/include)
+  HINTS ${SNAPPY_ROOT_DIR}/include)

-find_library(snappy_LIBRARIES
+find_library(SNAPPY_LIBRARIES
  NAMES snappy
-  HINTS ${snappy_ROOT_DIR}/lib)
+  HINTS ${SNAPPY_ROOT_DIR}/lib)

 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(snappy DEFAULT_MSG snappy_LIBRARIES snappy_INCLUDE_DIRS)
+find_package_handle_standard_args(snappy DEFAULT_MSG SNAPPY_LIBRARIES SNAPPY_INCLUDE_DIR)

 mark_as_advanced(
-  snappy_LIBRARIES
-  snappy_INCLUDE_DIRS)
-
-if(snappy_FOUND AND NOT (TARGET snappy::snappy))
-  add_library (snappy::snappy UNKNOWN IMPORTED)
-  set_target_properties(snappy::snappy
-    PROPERTIES
-      IMPORTED_LOCATION ${snappy_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${snappy_INCLUDE_DIRS})
-endif()
+  SNAPPY_LIBRARIES
+  SNAPPY_INCLUDE_DIR)
@@ -1,29 +1,21 @@
 # - Find zstd
 # Find the zstd compression library and includes
 #
-# zstd_INCLUDE_DIRS - where to find zstd.h, etc.
-# zstd_LIBRARIES - List of libraries when using zstd.
-# zstd_FOUND - True if zstd found.
+# ZSTD_INCLUDE_DIR - where to find zstd.h, etc.
+# ZSTD_LIBRARIES - List of libraries when using zstd.
+# ZSTD_FOUND - True if zstd found.

-find_path(zstd_INCLUDE_DIRS
+find_path(ZSTD_INCLUDE_DIR
  NAMES zstd.h
-  HINTS ${zstd_ROOT_DIR}/include)
+  HINTS ${ZSTD_ROOT_DIR}/include)

-find_library(zstd_LIBRARIES
+find_library(ZSTD_LIBRARIES
  NAMES zstd
-  HINTS ${zstd_ROOT_DIR}/lib)
+  HINTS ${ZSTD_ROOT_DIR}/lib)

 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(zstd DEFAULT_MSG zstd_LIBRARIES zstd_INCLUDE_DIRS)
+find_package_handle_standard_args(zstd DEFAULT_MSG ZSTD_LIBRARIES ZSTD_INCLUDE_DIR)

 mark_as_advanced(
-  zstd_LIBRARIES
-  zstd_INCLUDE_DIRS)
-
-if(zstd_FOUND AND NOT (TARGET zstd::zstd))
-  add_library (zstd::zstd UNKNOWN IMPORTED)
-  set_target_properties(zstd::zstd
-    PROPERTIES
-      IMPORTED_LOCATION ${zstd_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${zstd_INCLUDE_DIRS})
-endif()
+  ZSTD_LIBRARIES
+  ZSTD_INCLUDE_DIR)
@@ -1,10 +0,0 @@
-# Read rocksdb version from version.h header file.
-
-function(get_rocksdb_version version_var)
-  file(READ "${CMAKE_SOURCE_DIR}/include/rocksdb/version.h" version_header_file)
-  foreach(component MAJOR MINOR PATCH)
-    string(REGEX MATCH "#define ROCKSDB_${component} ([0-9]+)" _ ${version_header_file})
-    set(ROCKSDB_VERSION_${component} ${CMAKE_MATCH_1})
-  endforeach()
-  set(${version_var} "${ROCKSDB_VERSION_MAJOR}.${ROCKSDB_VERSION_MINOR}.${ROCKSDB_VERSION_PATCH}" PARENT_SCOPE)
-endfunction()
@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 # Exit on error.
 set -e
@@ -1,5 +1,3 @@
-#!/usr/bin/env python2
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 import re
 import sys

@@ -1,106 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/arena_wrapped_db_iter.h"
-#include "memory/arena.h"
-#include "rocksdb/env.h"
-#include "rocksdb/iterator.h"
-#include "rocksdb/options.h"
-#include "table/internal_iterator.h"
-#include "table/iterator_wrapper.h"
-#include "util/user_comparator_wrapper.h"
-
-namespace rocksdb {
-
-Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
-                                       std::string* prop) {
-  if (prop_name == "rocksdb.iterator.super-version-number") {
-    // First try to pass the value returned from inner iterator.
-    if (!db_iter_->GetProperty(prop_name, prop).ok()) {
-      *prop = ToString(sv_number_);
-    }
-    return Status::OK();
-  }
-  return db_iter_->GetProperty(prop_name, prop);
-}
-
-void ArenaWrappedDBIter::Init(Env* env, const ReadOptions& read_options,
-                              const ImmutableCFOptions& cf_options,
-                              const MutableCFOptions& mutable_cf_options,
-                              const SequenceNumber& sequence,
-                              uint64_t max_sequential_skip_in_iteration,
-                              uint64_t version_number,
-                              ReadCallback* read_callback, DBImpl* db_impl,
-                              ColumnFamilyData* cfd, bool allow_blob,
-                              bool allow_refresh) {
-  auto mem = arena_.AllocateAligned(sizeof(DBIter));
-  db_iter_ = new (mem) DBIter(env, read_options, cf_options, mutable_cf_options,
-                              cf_options.user_comparator, nullptr, sequence,
-                              true, max_sequential_skip_in_iteration,
-                              read_callback, db_impl, cfd, allow_blob);
-  sv_number_ = version_number;
-  allow_refresh_ = allow_refresh;
-}
-
-Status ArenaWrappedDBIter::Refresh() {
-  if (cfd_ == nullptr || db_impl_ == nullptr || !allow_refresh_) {
-    return Status::NotSupported("Creating renew iterator is not allowed.");
-  }
-  assert(db_iter_ != nullptr);
-  // TODO(yiwu): For last_seq_same_as_publish_seq_==false, this is not the
-  // correct behavior. Will be corrected automatically when we take a snapshot
-  // here for the case of WritePreparedTxnDB.
-  SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
-  uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
-  if (sv_number_ != cur_sv_number) {
-    Env* env = db_iter_->env();
-    db_iter_->~DBIter();
-    arena_.~Arena();
-    new (&arena_) Arena();
-
-    SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_->mutex());
-    if (read_callback_) {
-      read_callback_->Refresh(latest_seq);
-    }
-    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
-         latest_seq, sv->mutable_cf_options.max_sequential_skip_in_iterations,
-         cur_sv_number, read_callback_, db_impl_, cfd_, allow_blob_,
-         allow_refresh_);
-
-    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
-        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
-        latest_seq);
-    SetIterUnderDBIter(internal_iter);
-  } else {
-    db_iter_->set_sequence(latest_seq);
-    db_iter_->set_valid(false);
-  }
-  return Status::OK();
-}
-
-ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-    bool allow_blob, bool allow_refresh) {
-  ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
-  iter->Init(env, read_options, cf_options, mutable_cf_options, sequence,
-             max_sequential_skip_in_iterations, version_number, read_callback,
-             db_impl, cfd, allow_blob, allow_refresh);
-  if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
-    iter->StoreRefreshInfo(read_options, db_impl, cfd, read_callback,
-                           allow_blob);
-  }
-
-  return iter;
-}
-
-}  // namespace rocksdb
@@ -1,112 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-#include <stdint.h>
-#include <string>
-#include "db/db_impl/db_impl.h"
-#include "db/db_iter.h"
-#include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
-#include "memory/arena.h"
-#include "options/cf_options.h"
-#include "rocksdb/db.h"
-#include "rocksdb/iterator.h"
-#include "util/autovector.h"
-
-namespace rocksdb {
-
-class Arena;
-
-// A wrapper iterator which wraps DB Iterator and the arena, with which the DB
-// iterator is supposed to be allocated. This class is used as an entry point of
-// a iterator hierarchy whose memory can be allocated inline. In that way,
-// accessing the iterator tree can be more cache friendly. It is also faster
-// to allocate.
-// When using the class's Iterator interface, the behavior is exactly
-// the same as the inner DBIter.
-class ArenaWrappedDBIter : public Iterator {
- public:
-  virtual ~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
-
-  // Get the arena to be used to allocate memory for DBIter to be wrapped,
-  // as well as child iterators in it.
-  virtual Arena* GetArena() { return &arena_; }
-  virtual ReadRangeDelAggregator* GetRangeDelAggregator() {
-    return db_iter_->GetRangeDelAggregator();
-  }
-
-  // Set the internal iterator wrapped inside the DB Iterator. Usually it is
-  // a merging iterator.
-  virtual void SetIterUnderDBIter(InternalIterator* iter) {
-    static_cast<DBIter*>(db_iter_)->SetIter(iter);
-  }
-
-  virtual bool Valid() const override { return db_iter_->Valid(); }
-  virtual void SeekToFirst() override { db_iter_->SeekToFirst(); }
-  virtual void SeekToLast() override { db_iter_->SeekToLast(); }
-  virtual void Seek(const Slice& target) override { db_iter_->Seek(target); }
-  virtual void SeekForPrev(const Slice& target) override {
-    db_iter_->SeekForPrev(target);
-  }
-  virtual void Next() override { db_iter_->Next(); }
-  virtual void Prev() override { db_iter_->Prev(); }
-  virtual Slice key() const override { return db_iter_->key(); }
-  virtual Slice value() const override { return db_iter_->value(); }
-  virtual Status status() const override { return db_iter_->status(); }
-  bool IsBlob() const { return db_iter_->IsBlob(); }
-
-  virtual Status GetProperty(std::string prop_name, std::string* prop) override;
-
-  virtual Status Refresh() override;
-
-  void Init(Env* env, const ReadOptions& read_options,
-            const ImmutableCFOptions& cf_options,
-            const MutableCFOptions& mutable_cf_options,
-            const SequenceNumber& sequence,
-            uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-            ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-            bool allow_blob, bool allow_refresh);
-
-  // Store some parameters so we can refresh the iterator at a later point
-  // with these same params
-  void StoreRefreshInfo(const ReadOptions& read_options, DBImpl* db_impl,
-                        ColumnFamilyData* cfd, ReadCallback* read_callback,
-                        bool allow_blob) {
-    read_options_ = read_options;
-    db_impl_ = db_impl;
-    cfd_ = cfd;
-    read_callback_ = read_callback;
-    allow_blob_ = allow_blob;
-  }
-
- private:
-  DBIter* db_iter_;
-  Arena arena_;
-  uint64_t sv_number_;
-  ColumnFamilyData* cfd_ = nullptr;
-  DBImpl* db_impl_ = nullptr;
-  ReadOptions read_options_;
-  ReadCallback* read_callback_;
-  bool allow_blob_ = false;
-  bool allow_refresh_ = true;
-};
-
-// Generate the arena wrapped iterator class.
-// `db_impl` and `cfd` are used for reneweal. If left null, renewal will not
-// be supported.
-extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl = nullptr,
-    ColumnFamilyData* cfd = nullptr, bool allow_blob = false,
-    bool allow_refresh = true);
-}  // namespace rocksdb
@@ -13,7 +13,7 @@
 #include <deque>
 #include <vector>

-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
@@ -21,9 +21,6 @@
 #include "db/range_del_aggregator.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
-#include "file/filename.h"
-#include "file/read_write_util.h"
-#include "file/writable_file_writer.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -31,11 +28,13 @@
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block_based_table_builder.h"
+#include "table/block_based_table_builder.h"
 #include "table/format.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
+#include "util/file_reader_writer.h"
+#include "util/filename.h"
 #include "util/stop_watch.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -48,20 +47,18 @@ TableBuilder* NewTableBuilder(
        int_tbl_prop_collector_factories,
    uint32_t column_family_id, const std::string& column_family_name,
    WritableFileWriter* file, const CompressionType compression_type,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    int level, const bool skip_filters, const uint64_t creation_time,
-    const uint64_t oldest_key_time, const uint64_t target_file_size,
-    const uint64_t file_creation_time) {
+    const CompressionOptions& compression_opts, int level,
+    const std::string* compression_dict, const bool skip_filters,
+    const uint64_t creation_time, const uint64_t oldest_key_time) {
  assert((column_family_id ==
          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
         column_family_name.empty());
  return ioptions.table_factory->NewTableBuilder(
      TableBuilderOptions(ioptions, moptions, internal_comparator,
                          int_tbl_prop_collector_factories, compression_type,
-                          sample_for_compression, compression_opts,
-                          skip_filters, column_family_name, level,
-                          creation_time, oldest_key_time, target_file_size,
-                          file_creation_time),
+                          compression_opts, compression_dict, skip_filters,
+                          column_family_name, level, creation_time,
+                          oldest_key_time),
      column_family_id, file);
 }

@@ -78,12 +75,11 @@ Status BuildTable(
    std::vector<SequenceNumber> snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
    SnapshotChecker* snapshot_checker, const CompressionType compression,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    bool paranoid_file_checks, InternalStats* internal_stats,
-    TableFileCreationReason reason, EventLogger* event_logger, int job_id,
-    const Env::IOPriority io_priority, TableProperties* table_properties,
-    int level, const uint64_t creation_time, const uint64_t oldest_key_time,
-    Env::WriteLifeTimeHint write_hint, const uint64_t file_creation_time) {
+    const CompressionOptions& compression_opts, bool paranoid_file_checks,
+    InternalStats* internal_stats, TableFileCreationReason reason,
+    EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
+    TableProperties* table_properties, int level, const uint64_t creation_time,
+    const uint64_t oldest_key_time, Env::WriteLifeTimeHint write_hint) {
  assert((column_family_id ==
          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
         column_family_name.empty());
@@ -109,11 +105,6 @@ Status BuildTable(
  if (iter->Valid() || !range_del_agg->IsEmpty()) {
    TableBuilder* builder;
    std::unique_ptr<WritableFileWriter> file_writer;
-    // Currently we only enable dictionary compression during compaction to the
-    // bottommost level.
-    CompressionOptions compression_opts_for_flush(compression_opts);
-    compression_opts_for_flush.max_dict_bytes = 0;
-    compression_opts_for_flush.zstd_max_train_bytes = 0;
    {
      std::unique_ptr<WritableFile> file;
 #ifndef NDEBUG
@@ -136,10 +127,9 @@ Status BuildTable(
      builder = NewTableBuilder(
          ioptions, mutable_cf_options, internal_comparator,
          int_tbl_prop_collector_factories, column_family_id,
-          column_family_name, file_writer.get(), compression,
-          sample_for_compression, compression_opts_for_flush, level,
-          false /* skip_filters */, creation_time, oldest_key_time,
-          0 /*target_file_size*/, file_creation_time);
+          column_family_name, file_writer.get(), compression, compression_opts,
+          level, nullptr /* compression_dict */, false /* skip_filters */,
+          creation_time, oldest_key_time);
    }

    MergeHelper merge(env, internal_comparator.user_comparator(),
@@ -222,9 +212,8 @@ Status BuildTable(
          mutable_cf_options.prefix_extractor.get(), nullptr,
          (internal_stats == nullptr) ? nullptr
                                      : internal_stats->GetFileReadHist(0),
-          TableReaderCaller::kFlush, /*arena=*/nullptr,
-          /*skip_filter=*/false, level, /*smallest_compaction_key=*/nullptr,
-          /*largest_compaction_key*/ nullptr));
+          false /* for_compaction */, nullptr /* arena */,
+          false /* skip_filter */, level));
      s = it->status();
      if (s.ok() && paranoid_file_checks) {
        for (it->SeekToFirst(); it->Valid(); it->Next()) {
@@ -11,7 +11,6 @@
 #include <vector>
 #include "db/range_tombstone_fragmenter.h"
 #include "db/table_properties_collector.h"
-#include "logging/event_logger.h"
 #include "options/cf_options.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/env.h"
@@ -21,6 +20,7 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/event_logger.h"

 namespace rocksdb {

@@ -40,6 +40,8 @@ class InternalStats;
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown. It must outlive the
 //    TableBuilder returned by this function.
+// @param compression_dict Data for presetting the compression library's
+//    dictionary, or nullptr.
 TableBuilder* NewTableBuilder(
    const ImmutableCFOptions& options, const MutableCFOptions& moptions,
    const InternalKeyComparator& internal_comparator,
@@ -47,11 +49,10 @@ TableBuilder* NewTableBuilder(
        int_tbl_prop_collector_factories,
    uint32_t column_family_id, const std::string& column_family_name,
    WritableFileWriter* file, const CompressionType compression_type,
-    const uint64_t sample_for_compression,
    const CompressionOptions& compression_opts, int level,
+    const std::string* compression_dict = nullptr,
    const bool skip_filters = false, const uint64_t creation_time = 0,
-    const uint64_t oldest_key_time = 0, const uint64_t target_file_size = 0,
-    const uint64_t file_creation_time = 0);
+    const uint64_t oldest_key_time = 0);

 // Build a Table file from the contents of *iter.  The generated file
 // will be named according to number specified in meta. On success, the rest of
@@ -74,14 +75,12 @@ extern Status BuildTable(
    std::vector<SequenceNumber> snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
    SnapshotChecker* snapshot_checker, const CompressionType compression,
-    const uint64_t sample_for_compression,
    const CompressionOptions& compression_opts, bool paranoid_file_checks,
    InternalStats* internal_stats, TableFileCreationReason reason,
    EventLogger* event_logger = nullptr, int job_id = 0,
    const Env::IOPriority io_priority = Env::IO_HIGH,
    TableProperties* table_properties = nullptr, int level = -1,
    const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
-    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
-    const uint64_t file_creation_time = 0);
+    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET);

 }  // namespace rocksdb
@@ -208,10 +208,13 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
  const char* (*name_)(void*);
  unsigned char ignore_snapshots_;

-  ~rocksdb_compactionfilter_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_compactionfilter_t() {
+    (*destructor_)(state_);
+  }

-  bool Filter(int level, const Slice& key, const Slice& existing_value,
-              std::string* new_value, bool* value_changed) const override {
+  virtual bool Filter(int level, const Slice& key, const Slice& existing_value,
+                      std::string* new_value,
+                      bool* value_changed) const override {
    char* c_new_value = nullptr;
    size_t new_value_length = 0;
    unsigned char c_value_changed = 0;
@@ -228,9 +231,9 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
    return result;
  }

-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }

-  bool IgnoreSnapshots() const override { return ignore_snapshots_; }
+  virtual bool IgnoreSnapshots() const override { return ignore_snapshots_; }
 };

 struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
@@ -240,9 +243,9 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
      void*, rocksdb_compactionfiltercontext_t* context);
  const char* (*name_)(void*);

-  ~rocksdb_compactionfilterfactory_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_compactionfilterfactory_t() { (*destructor_)(state_); }

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    rocksdb_compactionfiltercontext_t ccontext;
    ccontext.rep = context;
@@ -250,7 +253,7 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
    return std::unique_ptr<CompactionFilter>(cf);
  }

-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 };

 struct rocksdb_comparator_t : public Comparator {
@@ -262,17 +265,20 @@ struct rocksdb_comparator_t : public Comparator {
      const char* b, size_t blen);
  const char* (*name_)(void*);

-  ~rocksdb_comparator_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_comparator_t() {
+    (*destructor_)(state_);
+  }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
    return (*compare_)(state_, a.data(), a.size(), b.data(), b.size());
  }

-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }

  // No-ops since the C binding does not support key shortening methods.
-  void FindShortestSeparator(std::string*, const Slice&) const override {}
-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortestSeparator(std::string*,
+                                     const Slice&) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };

 struct rocksdb_filterpolicy_t : public FilterPolicy {
@@ -292,11 +298,14 @@ struct rocksdb_filterpolicy_t : public FilterPolicy {
      void*,
      const char* filter, size_t filter_length);

-  ~rocksdb_filterpolicy_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_filterpolicy_t() {
+    (*destructor_)(state_);
+  }

-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }

-  void CreateFilter(const Slice* keys, int n, std::string* dst) const override {
+  virtual void CreateFilter(const Slice* keys, int n,
+                            std::string* dst) const override {
    std::vector<const char*> key_pointers(n);
    std::vector<size_t> key_sizes(n);
    for (int i = 0; i < n; i++) {
@@ -314,7 +323,8 @@ struct rocksdb_filterpolicy_t : public FilterPolicy {
    }
  }

-  bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
+  virtual bool KeyMayMatch(const Slice& key,
+                           const Slice& filter) const override {
    return (*key_match_)(state_, key.data(), key.size(),
                         filter.data(), filter.size());
  }
@@ -339,12 +349,14 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
      void*,
      const char* value, size_t value_length);

-  ~rocksdb_mergeoperator_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_mergeoperator_t() {
+    (*destructor_)(state_);
+  }

-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }

-  bool FullMergeV2(const MergeOperationInput& merge_in,
-                   MergeOperationOutput* merge_out) const override {
+  virtual bool FullMergeV2(const MergeOperationInput& merge_in,
+                           MergeOperationOutput* merge_out) const override {
    size_t n = merge_in.operand_list.size();
    std::vector<const char*> operand_pointers(n);
    std::vector<size_t> operand_sizes(n);
@@ -378,10 +390,10 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
    return success;
  }

-  bool PartialMergeMulti(const Slice& key,
-                         const std::deque<Slice>& operand_list,
-                         std::string* new_value,
-                         Logger* /*logger*/) const override {
+  virtual bool PartialMergeMulti(const Slice& key,
+                                 const std::deque<Slice>& operand_list,
+                                 std::string* new_value,
+                                 Logger* /*logger*/) const override {
    size_t operand_count = operand_list.size();
    std::vector<const char*> operand_pointers(operand_count);
    std::vector<size_t> operand_sizes(operand_count);
@@ -432,21 +444,23 @@ struct rocksdb_slicetransform_t : public SliceTransform {
      void*,
      const char* key, size_t length);

-  ~rocksdb_slicetransform_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_slicetransform_t() {
+    (*destructor_)(state_);
+  }

-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }

-  Slice Transform(const Slice& src) const override {
+  virtual Slice Transform(const Slice& src) const override {
    size_t len;
    char* dst = (*transform_)(state_, src.data(), src.size(), &len);
    return Slice(dst, len);
  }

-  bool InDomain(const Slice& src) const override {
+  virtual bool InDomain(const Slice& src) const override {
    return (*in_domain_)(state_, src.data(), src.size());
  }

-  bool InRange(const Slice& src) const override {
+  virtual bool InRange(const Slice& src) const override {
    return (*in_range_)(state_, src.data(), src.size());
  }
 };
@@ -517,21 +531,6 @@ rocksdb_t* rocksdb_open_for_read_only(
  return result;
 }

-rocksdb_t* rocksdb_open_as_secondary(const rocksdb_options_t* options,
-                                     const char* name,
-                                     const char* secondary_path,
-                                     char** errptr) {
-  DB* db;
-  if (SaveError(errptr,
-                DB::OpenAsSecondary(options->rep, std::string(name),
-                                    std::string(secondary_path), &db))) {
-    return nullptr;
-  }
-  rocksdb_t* result = new rocksdb_t;
-  result->rep = db;
-  return result;
-}
-
 rocksdb_backup_engine_t* rocksdb_backup_engine_open(
    const rocksdb_options_t* options, const char* path, char** errptr) {
  BackupEngine* be;
@@ -732,37 +731,6 @@ rocksdb_t* rocksdb_open_for_read_only_column_families(
  return result;
 }

-rocksdb_t* rocksdb_open_as_secondary_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    const char* secondary_path, int num_column_families,
-    const char** column_family_names,
-    const rocksdb_options_t** column_family_options,
-    rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
-  std::vector<ColumnFamilyDescriptor> column_families;
-  for (int i = 0; i != num_column_families; ++i) {
-    column_families.emplace_back(
-        std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
-  }
-  DB* db;
-  std::vector<ColumnFamilyHandle*> handles;
-  if (SaveError(errptr, DB::OpenAsSecondary(DBOptions(db_options->rep),
-                                            std::string(name),
-                                            std::string(secondary_path),
-                                            column_families, &handles, &db))) {
-    return nullptr;
-  }
-  for (size_t i = 0; i != handles.size(); ++i) {
-    rocksdb_column_family_handle_t* c_handle =
-        new rocksdb_column_family_handle_t;
-    c_handle->rep = handles[i];
-    column_family_handles[i] = c_handle;
-  }
-  rocksdb_t* result = new rocksdb_t;
-  result->rep = db;
-  return result;
-}
-
 char** rocksdb_list_column_families(
    const rocksdb_options_t* options,
    const char* name,
@@ -1034,7 +1002,7 @@ void rocksdb_wal_iter_destroy (const rocksdb_wal_iterator_t* iter) {
 rocksdb_writebatch_t* rocksdb_wal_iter_get_batch (const rocksdb_wal_iterator_t* iter, uint64_t* seq) {
  rocksdb_writebatch_t* result = rocksdb_writebatch_create();
  BatchResult wal_batch = iter->rep->GetBatch();
-  result->rep = std::move(*wal_batch.writeBatchPtr);
+  result->rep = * wal_batch.writeBatchPtr.release();
  if (seq != nullptr) {
    *seq = wal_batch.sequence;
  }
@@ -1116,18 +1084,6 @@ int rocksdb_property_int(
  }
 }

-int rocksdb_property_int_cf(
-    rocksdb_t* db,
-    rocksdb_column_family_handle_t* column_family,
-    const char* propname,
-    uint64_t *out_val) {
-  if (db->rep->GetIntProperty(column_family->rep, Slice(propname), out_val)) {
-    return 0;
-  } else {
-    return -1;
-  }
-}
-
 char* rocksdb_property_value_cf(
    rocksdb_t* db,
    rocksdb_column_family_handle_t* column_family,
@@ -1241,14 +1197,6 @@ void rocksdb_flush(
  SaveError(errptr, db->rep->Flush(options->rep));
 }

-void rocksdb_flush_cf(
-    rocksdb_t* db,
-    const rocksdb_flushoptions_t* options,
-    rocksdb_column_family_handle_t* column_family,
-    char** errptr) {
-  SaveError(errptr, db->rep->Flush(options->rep, column_family->rep));
-}
-
 void rocksdb_disable_file_deletions(
    rocksdb_t* db,
    char** errptr) {
@@ -1547,10 +1495,10 @@ class H : public WriteBatch::Handler {
  void* state_;
  void (*put_)(void*, const char* k, size_t klen, const char* v, size_t vlen);
  void (*deleted_)(void*, const char* k, size_t klen);
-  void Put(const Slice& key, const Slice& value) override {
+  virtual void Put(const Slice& key, const Slice& value) override {
    (*put_)(state_, key.data(), key.size(), value.data(), value.size());
  }
-  void Delete(const Slice& key) override {
+  virtual void Delete(const Slice& key) override {
    (*deleted_)(state_, key.data(), key.size());
  }
 };
@@ -2509,21 +2457,11 @@ void rocksdb_options_set_max_write_buffer_number_to_maintain(
  opt->rep.max_write_buffer_number_to_maintain = n;
 }

-void rocksdb_options_set_max_write_buffer_size_to_maintain(
-    rocksdb_options_t* opt, int64_t n) {
-  opt->rep.max_write_buffer_size_to_maintain = n;
-}
-
 void rocksdb_options_set_enable_pipelined_write(rocksdb_options_t* opt,
                                                unsigned char v) {
  opt->rep.enable_pipelined_write = v;
 }

-void rocksdb_options_set_unordered_write(rocksdb_options_t* opt,
-                                         unsigned char v) {
-  opt->rep.unordered_write = v;
-}
-
 void rocksdb_options_set_max_subcompactions(rocksdb_options_t* opt,
                                            uint32_t n) {
  opt->rep.max_subcompactions = n;
@@ -2928,7 +2866,7 @@ rocksdb_compactionfilter_t* rocksdb_compactionfilter_create(
  result->state_ = state;
  result->destructor_ = destructor;
  result->filter_ = filter;
-  result->ignore_snapshots_ = true;
+  result->ignore_snapshots_ = false;
  result->name_ = name;
  return result;
 }
@@ -3028,7 +2966,7 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
  // supplied C functions.
  struct Wrapper : public rocksdb_filterpolicy_t {
    const FilterPolicy* rep_;
-    ~Wrapper() override { delete rep_; }
+    ~Wrapper() { delete rep_; }
    const char* Name() const override { return rep_->Name(); }
    void CreateFilter(const Slice* keys, int n,
                      std::string* dst) const override {
@@ -3219,11 +3157,6 @@ void rocksdb_writeoptions_set_low_pri(
  opt->rep.low_pri = v;
 }

-void rocksdb_writeoptions_set_memtable_insert_hint_per_batch(
-    rocksdb_writeoptions_t* opt, unsigned char v) {
-  opt->rep.memtable_insert_hint_per_batch = v;
-}
-
 rocksdb_compactoptions_t* rocksdb_compactoptions_create() {
  return new rocksdb_compactoptions_t;
 }
@@ -3324,22 +3257,6 @@ void rocksdb_env_join_all_threads(rocksdb_env_t* env) {
  env->rep->WaitForJoin();
 }

-void rocksdb_env_lower_thread_pool_io_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolIOPriority();
-}
-
-void rocksdb_env_lower_high_priority_thread_pool_io_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolIOPriority(Env::HIGH);
-}
-
-void rocksdb_env_lower_thread_pool_cpu_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolCPUPriority();
-}
-
-void rocksdb_env_lower_high_priority_thread_pool_cpu_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolCPUPriority(Env::HIGH);
-}
-
 void rocksdb_env_destroy(rocksdb_env_t* env) {
  if (!env->is_default) delete env->rep;
  delete env;
@@ -3474,10 +3391,6 @@ void rocksdb_ingest_external_file_cf(
  SaveError(errptr, db->rep->IngestExternalFile(handle->rep, files, opt->rep));
 }

-void rocksdb_try_catch_up_with_primary(rocksdb_t* db, char** errptr) {
-  SaveError(errptr, db->rep->TryCatchUpWithPrimary());
-}
-
 rocksdb_slicetransform_t* rocksdb_slicetransform_create(
    void* state,
    void (*destructor)(void*),
@@ -3508,7 +3421,7 @@ void rocksdb_slicetransform_destroy(rocksdb_slicetransform_t* st) {

 struct Wrapper : public rocksdb_slicetransform_t {
  const SliceTransform* rep_;
-  ~Wrapper() override { delete rep_; }
+  ~Wrapper() { delete rep_; }
  const char* Name() const override { return rep_->Name(); }
  Slice Transform(const Slice& src) const override {
    return rep_->Transform(src);
@@ -3803,38 +3716,6 @@ rocksdb_transactiondb_t* rocksdb_transactiondb_open(
  return result;
 }

-rocksdb_transactiondb_t* rocksdb_transactiondb_open_column_families(
-    const rocksdb_options_t* options,
-    const rocksdb_transactiondb_options_t* txn_db_options, const char* name,
-    int num_column_families, const char** column_family_names,
-    const rocksdb_options_t** column_family_options,
-    rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
-  std::vector<ColumnFamilyDescriptor> column_families;
-  for (int i = 0; i < num_column_families; i++) {
-    column_families.push_back(ColumnFamilyDescriptor(
-        std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep)));
-  }
-
-  TransactionDB* txn_db;
-  std::vector<ColumnFamilyHandle*> handles;
-  if (SaveError(errptr, TransactionDB::Open(options->rep, txn_db_options->rep,
-                                            std::string(name), column_families,
-                                            &handles, &txn_db))) {
-    return nullptr;
-  }
-
-  for (size_t i = 0; i < handles.size(); i++) {
-    rocksdb_column_family_handle_t* c_handle =
-        new rocksdb_column_family_handle_t;
-    c_handle->rep = handles[i];
-    column_family_handles[i] = c_handle;
-  }
-  rocksdb_transactiondb_t* result = new rocksdb_transactiondb_t;
-  result->rep = txn_db;
-  return result;
-}
-
 const rocksdb_snapshot_t* rocksdb_transactiondb_create_snapshot(
    rocksdb_transactiondb_t* txn_db) {
  rocksdb_snapshot_t* result = new rocksdb_snapshot_t;
@@ -3955,26 +3836,6 @@ char* rocksdb_transaction_get_for_update(rocksdb_transaction_t* txn,
  return result;
 }

-char* rocksdb_transaction_get_for_update_cf(
-    rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key, size_t klen,
-    size_t* vlen, unsigned char exclusive, char** errptr) {
-  char* result = nullptr;
-  std::string tmp;
-  Status s = txn->rep->GetForUpdate(options->rep, column_family->rep,
-                                    Slice(key, klen), &tmp, exclusive);
-  if (s.ok()) {
-    *vlen = tmp.size();
-    result = CopyString(tmp);
-  } else {
-    *vlen = 0;
-    if (!s.IsNotFound()) {
-      SaveError(errptr, s);
-    }
-  }
-  return result;
-}
-
 // Read a key outside a transaction
 char* rocksdb_transactiondb_get(
    rocksdb_transactiondb_t* txn_db,
@@ -4067,14 +3928,6 @@ void rocksdb_transaction_merge(rocksdb_transaction_t* txn, const char* key,
  SaveError(errptr, txn->rep->Merge(Slice(key, klen), Slice(val, vlen)));
 }

-void rocksdb_transaction_merge_cf(rocksdb_transaction_t* txn,
-                                  rocksdb_column_family_handle_t* column_family,
-                                  const char* key, size_t klen, const char* val,
-                                  size_t vlen, char** errptr) {
-  SaveError(errptr, txn->rep->Merge(column_family->rep, Slice(key, klen),
-                                    Slice(val, vlen)));
-}
-
 // Merge a key outside a transaction
 void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
                                 const rocksdb_writeoptions_t* options,
@@ -4084,14 +3937,6 @@ void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
                                       Slice(val, vlen)));
 }

-void rocksdb_transactiondb_merge_cf(
-    rocksdb_transactiondb_t* txn_db, const rocksdb_writeoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key, size_t klen,
-    const char* val, size_t vlen, char** errptr) {
-  SaveError(errptr, txn_db->rep->Merge(options->rep, column_family->rep,
-                                       Slice(key, klen), Slice(val, vlen)));
-}
-
 // Delete a key inside a transaction
 void rocksdb_transaction_delete(rocksdb_transaction_t* txn, const char* key,
                                size_t klen, char** errptr) {
@@ -4144,14 +3989,6 @@ rocksdb_iterator_t* rocksdb_transactiondb_create_iterator(
  return result;
 }

-rocksdb_iterator_t* rocksdb_transactiondb_create_iterator_cf(
-    rocksdb_transactiondb_t* txn_db, const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family) {
-  rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep = txn_db->rep->NewIterator(options->rep, column_family->rep);
-  return result;
-}
-
 void rocksdb_transactiondb_close(rocksdb_transactiondb_t* txn_db) {
  delete txn_db->rep;
  delete txn_db;
@@ -1,7 +1,6 @@
 /* Copyright (c) 2011 The LevelDB Authors. All rights reserved.
   Use of this source code is governed by a BSD-style license that can be
   found in the LICENSE file. See the AUTHORS file for names of contributors. */
-// Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 #include <stdio.h>

@@ -45,7 +44,6 @@ static char sstfilename[200];
 static char dbbackupname[200];
 static char dbcheckpointname[200];
 static char dbpathname[200];
-static char secondary_path[200];

 static void StartPhase(const char* name) {
  fprintf(stderr, "=== Test %s\n", name);
@@ -1189,12 +1187,6 @@ int main(int argc, char** argv) {
    rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &err);
    CheckNoError(err);

-    rocksdb_flushoptions_t *flush_options = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_options, 1);
-    rocksdb_flush_cf(db, flush_options, handles[1], &err);
-    CheckNoError(err)
-    rocksdb_flushoptions_destroy(flush_options);
-
    CheckGetCF(db, roptions, handles[1], "foo", "hello");
    CheckPinGetCF(db, roptions, handles[1], "foo", "hello");

@@ -1723,59 +1715,6 @@ int main(int argc, char** argv) {
    CheckNoError(err);
  }

-  // Check that secondary instance works.
-  StartPhase("open_as_secondary");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-
-    rocksdb_options_t* db_options = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(db_options, 1);
-    db = rocksdb_open(db_options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_t* db1;
-    rocksdb_options_t* opts = rocksdb_options_create();
-    rocksdb_options_set_max_open_files(opts, -1);
-    rocksdb_options_set_create_if_missing(opts, 1);
-    snprintf(secondary_path, sizeof(secondary_path),
-             "%s/rocksdb_c_test_secondary-%d", GetTempDir(), ((int)geteuid()));
-    db1 = rocksdb_open_as_secondary(opts, dbname, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_writeoptions_set_sync(woptions, 0);
-    rocksdb_writeoptions_disable_WAL(woptions, 1);
-    rocksdb_put(db, woptions, "key0", 4, "value0", 6, &err);
-    CheckNoError(err);
-    rocksdb_flushoptions_t* flush_opts = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_opts, 1);
-    rocksdb_flush(db, flush_opts, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    rocksdb_readoptions_t* ropts = rocksdb_readoptions_create();
-    rocksdb_readoptions_set_verify_checksums(ropts, 1);
-    rocksdb_readoptions_set_snapshot(ropts, NULL);
-    CheckGet(db, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key0", "value0");
-
-    rocksdb_writeoptions_disable_WAL(woptions, 0);
-    rocksdb_put(db, woptions, "key1", 4, "value1", 6, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    CheckGet(db1, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key1", "value1");
-
-    rocksdb_close(db1);
-    rocksdb_destroy_db(opts, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_options_destroy(db_options);
-    rocksdb_options_destroy(opts);
-    rocksdb_readoptions_destroy(ropts);
-    rocksdb_flushoptions_destroy(flush_opts);
-  }
-
  // Simple sanity check that options setting db_paths work.
  StartPhase("open_db_paths");
  {
@@ -9,31 +9,34 @@

 #include "db/column_family.h"

-#include <algorithm>
-#include <cinttypes>
-#include <limits>
-#include <string>
-#include <vector>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif

-#include "db/compaction/compaction_picker.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
-#include "db/db_impl/db_impl.h"
+#include <inttypes.h>
+#include <vector>
+#include <string>
+#include <algorithm>
+#include <limits>
+
+#include "db/compaction_picker.h"
+#include "db/compaction_picker_fifo.h"
+#include "db/compaction_picker_universal.h"
+#include "db/db_impl.h"
 #include "db/internal_stats.h"
 #include "db/job_context.h"
 #include "db/range_del_aggregator.h"
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
-#include "file/sst_file_manager_impl.h"
 #include "memtable/hash_skiplist_rep.h"
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "util/autovector.h"
 #include "util/compression.h"
+#include "util/sst_file_manager_impl.h"

 namespace rocksdb {

@@ -60,24 +63,12 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
    JobContext job_context(0);
    mutex_->Lock();
    if (cfd_->Unref()) {
-      bool dropped = cfd_->IsDropped();
-
      delete cfd_;
-
-      if (dropped) {
-        db_->FindObsoleteFiles(&job_context, false, true);
-      }
    }
+    db_->FindObsoleteFiles(&job_context, false, true);
    mutex_->Unlock();
    if (job_context.HaveSomethingToDelete()) {
-      bool defer_purge =
-          db_->immutable_db_options().avoid_unnecessary_blocking_io;
-      db_->PurgeObsoleteFiles(job_context, defer_purge);
-      if (defer_purge) {
-        mutex_->Lock();
-        db_->SchedulePurge();
-        mutex_->Unlock();
-      }
+      db_->PurgeObsoleteFiles(job_context);
    }
    job_context.Clean();
  }
@@ -227,14 +218,7 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
  if (result.max_write_buffer_number < 2) {
    result.max_write_buffer_number = 2;
  }
-  // fall back max_write_buffer_number_to_maintain if
-  // max_write_buffer_size_to_maintain is not set
-  if (result.max_write_buffer_size_to_maintain < 0) {
-    result.max_write_buffer_size_to_maintain =
-        result.max_write_buffer_number *
-        static_cast<int64_t>(result.write_buffer_size);
-  } else if (result.max_write_buffer_size_to_maintain == 0 &&
-             result.max_write_buffer_number_to_maintain < 0) {
+  if (result.max_write_buffer_number_to_maintain < 0) {
    result.max_write_buffer_number_to_maintain = result.max_write_buffer_number;
  }
  // bloom filter size shouldn't exceed 1/4 of memtable size.
@@ -412,8 +396,7 @@ ColumnFamilyData::ColumnFamilyData(
    uint32_t id, const std::string& name, Version* _dummy_versions,
    Cache* _table_cache, WriteBufferManager* write_buffer_manager,
    const ColumnFamilyOptions& cf_options, const ImmutableDBOptions& db_options,
-    const EnvOptions& env_options, ColumnFamilySet* column_family_set,
-    BlockCacheTracer* const block_cache_tracer)
+    const EnvOptions& env_options, ColumnFamilySet* column_family_set)
    : id_(id),
      name_(name),
      dummy_versions_(_dummy_versions),
@@ -430,8 +413,7 @@ ColumnFamilyData::ColumnFamilyData(
      write_buffer_manager_(write_buffer_manager),
      mem_(nullptr),
      imm_(ioptions_.min_write_buffer_number_to_merge,
-           ioptions_.max_write_buffer_number_to_maintain,
-           ioptions_.max_write_buffer_size_to_maintain),
+           ioptions_.max_write_buffer_number_to_maintain),
      super_version_(nullptr),
      super_version_number_(0),
      local_sv_(new ThreadLocalPtr(&SuperVersionUnrefHandle)),
@@ -454,8 +436,7 @@ ColumnFamilyData::ColumnFamilyData(
  if (_dummy_versions != nullptr) {
    internal_stats_.reset(
        new InternalStats(ioptions_.num_levels, db_options.env, this));
-    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache,
-                                      block_cache_tracer));
+    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache));
    if (ioptions_.compaction_style == kCompactionStyleLevel) {
      compaction_picker_.reset(
          new LevelCompactionPicker(ioptions_, &internal_comparator_));
@@ -1001,14 +982,13 @@ const int ColumnFamilyData::kCompactToBaseLevel = -2;

 Compaction* ColumnFamilyData::CompactRange(
    const MutableCFOptions& mutable_cf_options, int input_level,
-    int output_level, const CompactRangeOptions& compact_range_options,
+    int output_level, uint32_t output_path_id, uint32_t max_subcompactions,
    const InternalKey* begin, const InternalKey* end,
-    InternalKey** compaction_end, bool* conflict,
-    uint64_t max_file_num_to_ignore) {
+    InternalKey** compaction_end, bool* conflict) {
  auto* result = compaction_picker_->CompactRange(
      GetName(), mutable_cf_options, current_->storage_info(), input_level,
-      output_level, compact_range_options, begin, end, compaction_end, conflict,
-      max_file_num_to_ignore);
+      output_level, output_path_id, max_subcompactions, begin, end,
+      compaction_end, conflict);
  if (result != nullptr) {
    result->SetInputVersion(current_);
  }
@@ -1154,60 +1134,13 @@ void ColumnFamilyData::ResetThreadLocalSuperVersions() {
  }
 }

-Status ColumnFamilyData::ValidateOptions(
-    const DBOptions& db_options, const ColumnFamilyOptions& cf_options) {
-  Status s;
-  s = CheckCompressionSupported(cf_options);
-  if (s.ok() && db_options.allow_concurrent_memtable_write) {
-    s = CheckConcurrentWritesSupported(cf_options);
-  }
-  if (s.ok()) {
-    s = CheckCFPathsSupported(db_options, cf_options);
-  }
-  if (!s.ok()) {
-    return s;
-  }
-
-  if (cf_options.ttl > 0) {
-    if (db_options.max_open_files != -1) {
-      return Status::NotSupported(
-          "TTL is only supported when files are always "
-          "kept open (set max_open_files = -1). ");
-    }
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "TTL is only supported in Block-Based Table format. ");
-    }
-  }
-
-  if (cf_options.periodic_compaction_seconds > 0) {
-    if (db_options.max_open_files != -1) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported when files are always "
-          "kept open (set max_open_files = -1). ");
-    }
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported in "
-          "Block-Based Table format. ");
-    }
-  }
-  return s;
-}
-
 #ifndef ROCKSDB_LITE
 Status ColumnFamilyData::SetOptions(
-    const DBOptions& db_options,
-    const std::unordered_map<std::string, std::string>& options_map) {
+      const std::unordered_map<std::string, std::string>& options_map) {
  MutableCFOptions new_mutable_cf_options;
  Status s =
      GetMutableOptionsFromStrings(mutable_cf_options_, options_map,
                                   ioptions_.info_log, &new_mutable_cf_options);
-  if (s.ok()) {
-    ColumnFamilyOptions cf_options =
-        BuildColumnFamilyOptions(initial_cf_options_, new_mutable_cf_options);
-    s = ValidateOptions(db_options, cf_options);
-  }
  if (s.ok()) {
    mutable_cf_options_ = new_mutable_cf_options;
    mutable_cf_options_.RefreshDerivedOptions(ioptions_);
@@ -1264,20 +1197,18 @@ ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                 const EnvOptions& env_options,
                                 Cache* table_cache,
                                 WriteBufferManager* write_buffer_manager,
-                                 WriteController* write_controller,
-                                 BlockCacheTracer* const block_cache_tracer)
+                                 WriteController* write_controller)
    : max_column_family_(0),
-      dummy_cfd_(new ColumnFamilyData(
-          0, "", nullptr, nullptr, nullptr, ColumnFamilyOptions(), *db_options,
-          env_options, nullptr, block_cache_tracer)),
+      dummy_cfd_(new ColumnFamilyData(0, "", nullptr, nullptr, nullptr,
+                                      ColumnFamilyOptions(), *db_options,
+                                      env_options, nullptr)),
      default_cfd_cache_(nullptr),
      db_name_(dbname),
      db_options_(db_options),
      env_options_(env_options),
      table_cache_(table_cache),
      write_buffer_manager_(write_buffer_manager),
-      write_controller_(write_controller),
-      block_cache_tracer_(block_cache_tracer) {
+      write_controller_(write_controller) {
  // initialize linked list
  dummy_cfd_->prev_ = dummy_cfd_;
  dummy_cfd_->next_ = dummy_cfd_;
@@ -1345,7 +1276,7 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
  assert(column_families_.find(name) == column_families_.end());
  ColumnFamilyData* new_cfd = new ColumnFamilyData(
      id, name, dummy_versions, table_cache_, write_buffer_manager_, options,
-      *db_options_, env_options_, this, block_cache_tracer_);
+      *db_options_, env_options_, this);
  column_families_.insert({name, id});
  column_family_data_.insert({id, new_cfd});
  max_column_family_ = std::max(max_column_family_, id);
@@ -24,7 +24,6 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
-#include "trace_replay/block_cache_tracer.h"
 #include "util/thread_local.h"

 namespace rocksdb {
@@ -46,112 +45,6 @@ class InstrumentedMutexLock;
 struct SuperVersionContext;

 extern const double kIncSlowdownRatio;
-// This file contains a list of data structures for managing column family
-// level metadata.
-//
-// The basic relationships among classes declared here are illustrated as
-// following:
-//
-//       +----------------------+    +----------------------+   +--------+
-//   +---+ ColumnFamilyHandle 1 | +--+ ColumnFamilyHandle 2 |   | DBImpl |
-//   |   +----------------------+ |  +----------------------+   +----+---+
-//   | +--------------------------+                                  |
-//   | |                               +-----------------------------+
-//   | |                               |
-//   | | +-----------------------------v-------------------------------+
-//   | | |                                                             |
-//   | | |                      ColumnFamilySet                        |
-//   | | |                                                             |
-//   | | +-------------+--------------------------+----------------+---+
-//   | |               |                          |                |
-//   | +-------------------------------------+    |                |
-//   |                 |                     |    |                v
-//   |   +-------------v-------------+ +-----v----v---------+
-//   |   |                           | |                    |
-//   |   |     ColumnFamilyData 1    | | ColumnFamilyData 2 |    ......
-//   |   |                           | |                    |
-//   +--->                           | |                    |
-//       |                 +---------+ |                    |
-//       |                 | MemTable| |                    |
-//       |                 |  List   | |                    |
-//       +--------+---+--+-+----+----+ +--------------------++
-//                |   |  |      |
-//                |   |  |      |
-//                |   |  |      +-----------------------+
-//                |   |  +-----------+                  |
-//                v   +--------+     |                  |
-//       +--------+--------+   |     |                  |
-//       |                 |   |     |       +----------v----------+
-// +---> |SuperVersion 1.a +----------------->                     |
-//       |                 +------+  |       | MemTableListVersion |
-//       +---+-------------+   |  |  |       |                     |
-//           |                 |  |  |       +----+------------+---+
-//           |      current    |  |  |            |            |
-//           |   +-------------+  |  |mem         |            |
-//           |   |                |  |            |            |
-//         +-v---v-------+    +---v--v---+  +-----v----+  +----v-----+
-//         |             |    |          |  |          |  |          |
-//         | Version 1.a |    | memtable |  | memtable |  | memtable |
-//         |             |    |   1.a    |  |   1.b    |  |   1.c    |
-//         +-------------+    |          |  |          |  |          |
-//                            +----------+  +----------+  +----------+
-//
-// DBImpl keeps a ColumnFamilySet, which references to all column families by
-// pointing to respective ColumnFamilyData object of each column family.
-// This is how DBImpl can list and operate on all the column families.
-// ColumnFamilyHandle also points to ColumnFamilyData directly, so that
-// when a user executes a query, it can directly find memtables and Version
-// as well as SuperVersion to the column family, without going through
-// ColumnFamilySet.
-//
-// ColumnFamilySet points to the latest view of the LSM-tree (list of memtables
-// and SST files) indirectly, while ongoing operations may hold references
-// to a current or an out-of-date SuperVersion, which in turn points to a
-// point-in-time view of the LSM-tree. This guarantees the memtables and SST
-// files being operated on will not go away, until the SuperVersion is
-// unreferenced to 0 and destoryed.
-//
-// The following graph illustrates a possible referencing relationships:
-//
-// Column       +--------------+      current       +-----------+
-// Family +---->+              +------------------->+           |
-//  Data        | SuperVersion +----------+         | Version A |
-//              |      3       |   imm    |         |           |
-// Iter2 +----->+              |  +-------v------+  +-----------+
-//              +-----+--------+  | MemtableList +----------------> Empty
-//                    |           |   Version r  |  +-----------+
-//                    |           +--------------+  |           |
-//                    +------------------+   current| Version B |
-//              +--------------+         |   +----->+           |
-//              |              |         |   |      +-----+-----+
-// Compaction +>+ SuperVersion +-------------+            ^
-//    Job       |      2       +------+  |                |current
-//              |              +----+ |  |     mem        |    +------------+
-//              +--------------+    | |  +--------------------->            |
-//                                  | +------------------------> MemTable a |
-//                                  |          mem        |    |            |
-//              +--------------+    |                     |    +------------+
-//              |              +--------------------------+
-//  Iter1 +-----> SuperVersion |    |                          +------------+
-//              |      1       +------------------------------>+            |
-//              |              +-+  |        mem               | MemTable b |
-//              +--------------+ |  |                          |            |
-//                               |  |    +--------------+      +-----^------+
-//                               |  |imm | MemtableList |            |
-//                               |  +--->+   Version s  +------------+
-//                               |       +--------------+
-//                               |       +--------------+
-//                               |       | MemtableList |
-//                               +------>+   Version t  +-------->  Empty
-//                                 imm   +--------------+
-//
-// In this example, even if the current LSM-tree consists of Version A and
-// memtable a, which is also referenced by SuperVersion, two older SuperVersion
-// SuperVersion2 and Superversion1 still exist, and are referenced by a
-// compaction job and an old iterator Iter1, respectively. SuperVersion2
-// contains Version B, memtable a and memtable b; SuperVersion1 contains
-// Version B and memtable b (mutable). As a result, Version B and memtable b
-// are prevented from being destroyed or deleted.

 // ColumnFamilyHandleImpl is the class that clients use to access different
 // column families. It has non-trivial destructor, which gets called when client
@@ -275,7 +168,7 @@ class ColumnFamilyData {
  // Ref() can only be called from a context where the caller can guarantee
  // that ColumnFamilyData is alive (while holding a non-zero ref already,
  // holding a DB mutex, or as the leader in a write batch group).
-  void Ref() { refs_.fetch_add(1); }
+  void Ref() { refs_.fetch_add(1, std::memory_order_relaxed); }

  // Unref decreases the reference count, but does not handle deletion
  // when the count goes to 0.  If this method returns true then the
@@ -283,7 +176,7 @@ class ColumnFamilyData {
  // FreeDeadColumnFamilies().  Unref() can only be called while holding
  // a DB mutex, or during single-threaded recovery.
  bool Unref() {
-    int old_refs = refs_.fetch_sub(1);
+    int old_refs = refs_.fetch_sub(1, std::memory_order_relaxed);
    assert(old_refs > 0);
    return old_refs == 1;
  }
@@ -339,13 +232,9 @@ class ColumnFamilyData {

  bool is_delete_range_supported() { return is_delete_range_supported_; }

-  // Validate CF options against DB options
-  static Status ValidateOptions(const DBOptions& db_options,
-                                const ColumnFamilyOptions& cf_options);
 #ifndef ROCKSDB_LITE
  // REQUIRES: DB mutex held
  Status SetOptions(
-      const DBOptions& db_options,
      const std::unordered_map<std::string, std::string>& options_map);
 #endif  // ROCKSDB_LITE

@@ -407,10 +296,9 @@ class ColumnFamilyData {
  // REQUIRES: DB mutex held
  Compaction* CompactRange(const MutableCFOptions& mutable_cf_options,
                           int input_level, int output_level,
-                           const CompactRangeOptions& compact_range_options,
+                           uint32_t output_path_id, uint32_t max_subcompactions,
                           const InternalKey* begin, const InternalKey* end,
-                           InternalKey** compaction_end, bool* manual_conflict,
-                           uint64_t max_file_num_to_ignore);
+                           InternalKey** compaction_end, bool* manual_conflict);

  CompactionPicker* compaction_picker() { return compaction_picker_.get(); }
  // thread-safe
@@ -505,8 +393,7 @@ class ColumnFamilyData {
                   const ColumnFamilyOptions& options,
                   const ImmutableDBOptions& db_options,
                   const EnvOptions& env_options,
-                   ColumnFamilySet* column_family_set,
-                   BlockCacheTracer* const block_cache_tracer);
+                   ColumnFamilySet* column_family_set);

  uint32_t id_;
  const std::string name_;
@@ -634,8 +521,7 @@ class ColumnFamilySet {
                  const ImmutableDBOptions* db_options,
                  const EnvOptions& env_options, Cache* table_cache,
                  WriteBufferManager* write_buffer_manager,
-                  WriteController* write_controller,
-                  BlockCacheTracer* const block_cache_tracer);
+                  WriteController* write_controller);
  ~ColumnFamilySet();

  ColumnFamilyData* GetDefault() const;
@@ -694,7 +580,6 @@ class ColumnFamilySet {
  Cache* table_cache_;
  WriteBufferManager* write_buffer_manager_;
  WriteController* write_controller_;
-  BlockCacheTracer* const block_cache_tracer_;
 };

 // We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access
@@ -12,22 +12,19 @@
 #include <string>
 #include <thread>

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/db_test_util.h"
-#include "memtable/hash_skiplist_rep.h"
 #include "options/options_parser.h"
 #include "port/port.h"
-#include "port/stack_trace.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
-#include "rocksdb/utilities/object_registry.h"
-#include "test_util/fault_injection_test_env.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/coding.h"
+#include "util/fault_injection_test_env.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"

 namespace rocksdb {
@@ -62,20 +59,8 @@ class EnvCounter : public EnvWrapper {

 class ColumnFamilyTestBase : public testing::Test {
 public:
-  explicit ColumnFamilyTestBase(uint32_t format) : rnd_(139), format_(format) {
-    Env* base_env = Env::Default();
-#ifndef ROCKSDB_LITE
-    const char* test_env_uri = getenv("TEST_ENV_URI");
-    if (test_env_uri) {
-      Status s = ObjectRegistry::NewInstance()->NewSharedObject(test_env_uri,
-                                                                &env_guard_);
-      base_env = env_guard_.get();
-      EXPECT_OK(s);
-      EXPECT_NE(Env::Default(), base_env);
-    }
-#endif  // !ROCKSDB_LITE
-    EXPECT_NE(nullptr, base_env);
-    env_ = new EnvCounter(base_env);
+  ColumnFamilyTestBase(uint32_t format) : rnd_(139), format_(format) {
+    env_ = new EnvCounter(Env::Default());
    dbname_ = test::PerThreadDBPath("column_family_test");
    db_options_.create_if_missing = true;
    db_options_.fail_if_options_file_error = true;
@@ -83,7 +68,7 @@ class ColumnFamilyTestBase : public testing::Test {
    DestroyDB(dbname_, Options(db_options_, column_family_options_));
  }

-  ~ColumnFamilyTestBase() override {
+  virtual ~ColumnFamilyTestBase() {
    std::vector<ColumnFamilyDescriptor> column_families;
    for (auto h : handles_) {
      ColumnFamilyDescriptor cfdescriptor;
@@ -546,7 +531,6 @@ class ColumnFamilyTestBase : public testing::Test {
  std::string dbname_;
  DB* db_ = nullptr;
  EnvCounter* env_;
-  std::shared_ptr<Env> env_guard_;
  Random rnd_;
  uint32_t format_;
 };
@@ -1132,25 +1116,22 @@ TEST_P(ColumnFamilyTest, DifferentWriteBufferSizes) {
  default_cf.arena_block_size = 4 * 4096;
  default_cf.max_write_buffer_number = 10;
  default_cf.min_write_buffer_number_to_merge = 1;
-  default_cf.max_write_buffer_size_to_maintain = 0;
+  default_cf.max_write_buffer_number_to_maintain = 0;
  one.write_buffer_size = 200000;
  one.arena_block_size = 4 * 4096;
  one.max_write_buffer_number = 10;
  one.min_write_buffer_number_to_merge = 2;
-  one.max_write_buffer_size_to_maintain =
-      static_cast<int>(one.write_buffer_size);
+  one.max_write_buffer_number_to_maintain = 1;
  two.write_buffer_size = 1000000;
  two.arena_block_size = 4 * 4096;
  two.max_write_buffer_number = 10;
  two.min_write_buffer_number_to_merge = 3;
-  two.max_write_buffer_size_to_maintain =
-      static_cast<int>(two.write_buffer_size);
+  two.max_write_buffer_number_to_maintain = 2;
  three.write_buffer_size = 4096 * 22;
  three.arena_block_size = 4096;
  three.max_write_buffer_number = 10;
  three.min_write_buffer_number_to_merge = 4;
-  three.max_write_buffer_size_to_maintain =
-      static_cast<int>(three.write_buffer_size);
+  three.max_write_buffer_number_to_maintain = -1;

  Reopen({default_cf, one, two, three});

@@ -1225,32 +1206,29 @@ TEST_P(ColumnFamilyTest, DifferentWriteBufferSizes) {
 }
 #endif  // !ROCKSDB_LITE

-// The test is commented out because we want to test that snapshot is
-// not created for memtables not supported it, but There isn't a memtable
-// that doesn't support snapshot right now. If we have one later, we can
-// re-enable the test.
-//
-// #ifndef ROCKSDB_LITE  // Cuckoo is not supported in lite
-//   TEST_P(ColumnFamilyTest, MemtableNotSupportSnapshot) {
-//   db_options_.allow_concurrent_memtable_write = false;
-//   Open();
-//   auto* s1 = dbfull()->GetSnapshot();
-//   ASSERT_TRUE(s1 != nullptr);
-//   dbfull()->ReleaseSnapshot(s1);
+#ifndef ROCKSDB_LITE  // Cuckoo is not supported in lite
+TEST_P(ColumnFamilyTest, MemtableNotSupportSnapshot) {
+  db_options_.allow_concurrent_memtable_write = false;
+  Open();
+  auto* s1 = dbfull()->GetSnapshot();
+  ASSERT_TRUE(s1 != nullptr);
+  dbfull()->ReleaseSnapshot(s1);

-//   // Add a column family that doesn't support snapshot
-//   ColumnFamilyOptions first;
-//   first.memtable_factory.reset(new DummyMemtableNotSupportingSnapshot());
-//   CreateColumnFamilies({"first"}, {first});
-//   auto* s2 = dbfull()->GetSnapshot();
-//   ASSERT_TRUE(s2 == nullptr);
+  // Add a column family that doesn't support snapshot
+  ColumnFamilyOptions first;
+  first.memtable_factory.reset(NewHashCuckooRepFactory(1024 * 1024));
+  CreateColumnFamilies({"first"}, {first});
+  auto* s2 = dbfull()->GetSnapshot();
+  ASSERT_TRUE(s2 == nullptr);

-//   // Add a column family that supports snapshot. Snapshot stays not
-//   supported. ColumnFamilyOptions second; CreateColumnFamilies({"second"},
-//   {second}); auto* s3 = dbfull()->GetSnapshot(); ASSERT_TRUE(s3 == nullptr);
-//   Close();
-// }
-// #endif  // !ROCKSDB_LITE
+  // Add a column family that supports snapshot. Snapshot stays not supported.
+  ColumnFamilyOptions second;
+  CreateColumnFamilies({"second"}, {second});
+  auto* s3 = dbfull()->GetSnapshot();
+  ASSERT_TRUE(s3 == nullptr);
+  Close();
+}
+#endif  // !ROCKSDB_LITE

 class TestComparator : public Comparator {
  int Compare(const rocksdb::Slice& /*a*/,
@@ -3330,17 +3308,7 @@ TEST_P(ColumnFamilyTest, MultipleCFPathsTest) {

 }  // namespace rocksdb

-#ifdef ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
-extern "C" {
-void RegisterCustomObjects(int argc, char** argv);
-}
-#else
-void RegisterCustomObjects(int /*argc*/, char** /*argv*/) {}
-#endif  // !ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
-
 int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
  ::testing::InitGoogleTest(&argc, argv);
-  RegisterCustomObjects(argc, argv);
  return RUN_ALL_TESTS();
 }
@@ -10,13 +10,13 @@
 #include <thread>
 #include <vector>

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"

 namespace rocksdb {

@@ -35,9 +35,9 @@ class CompactFilesTest : public testing::Test {
 class FlushedFileCollector : public EventListener {
 public:
  FlushedFileCollector() {}
-  ~FlushedFileCollector() override {}
+  ~FlushedFileCollector() {}

-  void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
+  virtual void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
    std::lock_guard<std::mutex> lock(mutex_);
    flushed_files_.push_back(info.file_path);
  }
@@ -256,9 +256,9 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
 TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
  class FilterWithGet : public CompactionFilter {
   public:
-    bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-                std::string* /*new_value*/,
-                bool* /*value_changed*/) const override {
+    virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                        const Slice& /*value*/, std::string* /*new_value*/,
+                        bool* /*value_changed*/) const override {
      if (db_ == nullptr) {
        return true;
      }
@@ -271,7 +271,7 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
      db_ = db;
    }

-    const char* Name() const override { return "FilterWithGet"; }
+    virtual const char* Name() const override { return "FilterWithGet"; }

   private:
    DB* db_;
@@ -5,7 +5,7 @@

 #ifndef ROCKSDB_LITE
 #include "db/compacted_db_impl.h"
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/version_set.h"
 #include "table/get_context.h"

@@ -37,7 +37,7 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                            const Slice& key, PinnableSlice* value) {
  GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                         GetContext::kNotFound, key, value, nullptr, nullptr,
-                         true, nullptr, nullptr);
+                         nullptr, nullptr);
  LookupKey lkey(key, kMaxSequenceNumber);
  files_.files[FindFile(key)].fd.table_reader->Get(options, lkey.internal_key(),
                                                   &get_context, nullptr);
@@ -70,7 +70,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
      std::string& value = (*values)[idx];
      GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                             GetContext::kNotFound, keys[idx], &pinnable_val,
-                             nullptr, nullptr, true, nullptr, nullptr);
+                             nullptr, nullptr, nullptr, nullptr);
      LookupKey lkey(keys[idx], kMaxSequenceNumber);
      r->Get(options, lkey.internal_key(), &get_context, nullptr);
      value.assign(pinnable_val.data(), pinnable_val.size());
@@ -5,19 +5,15 @@

 #pragma once
 #ifndef ROCKSDB_LITE
-#include <string>
+#include "db/db_impl.h"
 #include <vector>
-#include "db/db_impl/db_impl.h"
+#include <string>

 namespace rocksdb {

 class CompactedDBImpl : public DBImpl {
 public:
  CompactedDBImpl(const DBOptions& options, const std::string& dbname);
-  // No copying allowed
-  CompactedDBImpl(const CompactedDBImpl&) = delete;
-  void operator=(const CompactedDBImpl&) = delete;
-
  virtual ~CompactedDBImpl();

  static Status Open(const Options& options, const std::string& dbname,
@@ -89,15 +85,6 @@ class CompactedDBImpl : public DBImpl {
      const IngestExternalFileOptions& /*ingestion_options*/) override {
    return Status::NotSupported("Not supported in compacted db mode.");
  }
-  using DB::CreateColumnFamilyWithImport;
-  virtual Status CreateColumnFamilyWithImport(
-      const ColumnFamilyOptions& /*options*/,
-      const std::string& /*column_family_name*/,
-      const ImportColumnFamilyOptions& /*import_options*/,
-      const ExportImportFilesMetaData& /*metadata*/,
-      ColumnFamilyHandle** /*handle*/) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }

 private:
  friend class DB;
@@ -108,6 +95,10 @@ class CompactedDBImpl : public DBImpl {
  Version* version_;
  const Comparator* user_comparator_;
  LevelFilesBrief files_;
+
+  // No copying allowed
+  CompactedDBImpl(const CompactedDBImpl&);
+  void operator=(const CompactedDBImpl&);
 };
 }
 #endif  // ROCKSDB_LITE
@@ -7,14 +7,19 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

-#include <cinttypes>
+#include "db/compaction.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <vector>

 #include "db/column_family.h"
-#include "db/compaction/compaction.h"
 #include "rocksdb/compaction_filter.h"
-#include "test_util/sync_point.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -245,12 +250,6 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
  if (max_subcompactions_ == 0) {
    max_subcompactions_ = immutable_cf_options_.max_subcompactions;
  }
-  if (!bottommost_level_) {
-    // Currently we only enable dictionary compression during compaction to the
-    // bottommost level.
-    output_compression_opts_.max_dict_bytes = 0;
-    output_compression_opts_.zstd_max_train_bytes = 0;
-  }

 #ifndef NDEBUG
  for (size_t i = 1; i < inputs_.size(); ++i) {
@@ -9,13 +9,11 @@

 #pragma once
 #include "db/version_set.h"
-#include "memory/arena.h"
 #include "options/cf_options.h"
+#include "util/arena.h"
 #include "util/autovector.h"

 namespace rocksdb {
-// The file contains class Compaction, as well as some helper functions
-// and data structures used by the class.

 // Utility for comparing sstable boundary keys. Returns -1 if either a or b is
 // null which provides the property that a==null indicates a key that is less
@@ -65,7 +63,7 @@ class ColumnFamilyData;
 class VersionStorageInfo;
 class CompactionFilter;

-// A Compaction encapsulates metadata about a compaction.
+// A Compaction encapsulates information about a compaction.
 class Compaction {
 public:
  Compaction(VersionStorageInfo* input_version,
@@ -378,7 +376,7 @@ class Compaction {
  CompactionReason compaction_reason_;
 };

-// Return sum of sizes of all files in `files`.
+// Utility function
 extern uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);

 }  // namespace rocksdb
@@ -1,553 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "db/compaction/compaction_picker_level.h"
-#include "logging/log_buffer.h"
-#include "test_util/sync_point.h"
-
-namespace rocksdb {
-
-bool LevelCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  if (!vstorage->ExpiredTtlFiles().empty()) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForPeriodicCompaction().empty()) {
-    return true;
-  }
-  if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  for (int i = 0; i <= vstorage->MaxInputLevel(); i++) {
-    if (vstorage->CompactionScore(i) >= 1) {
-      return true;
-    }
-  }
-  return false;
-}
-
-namespace {
-// A class to build a leveled compaction step-by-step.
-class LevelCompactionBuilder {
- public:
-  LevelCompactionBuilder(const std::string& cf_name,
-                         VersionStorageInfo* vstorage,
-                         CompactionPicker* compaction_picker,
-                         LogBuffer* log_buffer,
-                         const MutableCFOptions& mutable_cf_options,
-                         const ImmutableCFOptions& ioptions)
-      : cf_name_(cf_name),
-        vstorage_(vstorage),
-        compaction_picker_(compaction_picker),
-        log_buffer_(log_buffer),
-        mutable_cf_options_(mutable_cf_options),
-        ioptions_(ioptions) {}
-
-  // Pick and return a compaction.
-  Compaction* PickCompaction();
-
-  // Pick the initial files to compact to the next level. (or together
-  // in Intra-L0 compactions)
-  void SetupInitialFiles();
-
-  // If the initial files are from L0 level, pick other L0
-  // files if needed.
-  bool SetupOtherL0FilesIfNeeded();
-
-  // Based on initial files, setup other files need to be compacted
-  // in this compaction, accordingly.
-  bool SetupOtherInputsIfNeeded();
-
-  Compaction* GetCompaction();
-
-  // For the specfied level, pick a file that we want to compact.
-  // Returns false if there is no file to compact.
-  // If it returns true, inputs->files.size() will be exactly one.
-  // If level is 0 and there is already a compaction on that level, this
-  // function will return false.
-  bool PickFileToCompact();
-
-  // For L0->L0, picks the longest span of files that aren't currently
-  // undergoing compaction for which work-per-deleted-file decreases. The span
-  // always starts from the newest L0 file.
-  //
-  // Intra-L0 compaction is independent of all other files, so it can be
-  // performed even when L0->base_level compactions are blocked.
-  //
-  // Returns true if `inputs` is populated with a span of files to be compacted;
-  // otherwise, returns false.
-  bool PickIntraL0Compaction();
-
-  void PickExpiredTtlFiles();
-
-  void PickFilesMarkedForPeriodicCompaction();
-
-  const std::string& cf_name_;
-  VersionStorageInfo* vstorage_;
-  CompactionPicker* compaction_picker_;
-  LogBuffer* log_buffer_;
-  int start_level_ = -1;
-  int output_level_ = -1;
-  int parent_index_ = -1;
-  int base_index_ = -1;
-  double start_level_score_ = 0;
-  bool is_manual_ = false;
-  CompactionInputFiles start_level_inputs_;
-  std::vector<CompactionInputFiles> compaction_inputs_;
-  CompactionInputFiles output_level_inputs_;
-  std::vector<FileMetaData*> grandparents_;
-  CompactionReason compaction_reason_ = CompactionReason::kUnknown;
-
-  const MutableCFOptions& mutable_cf_options_;
-  const ImmutableCFOptions& ioptions_;
-  // Pick a path ID to place a newly generated file, with its level
-  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
-                            const MutableCFOptions& mutable_cf_options,
-                            int level);
-
-  static const int kMinFilesForIntraL0Compaction = 4;
-};
-
-void LevelCompactionBuilder::PickExpiredTtlFiles() {
-  if (vstorage_->ExpiredTtlFiles().empty()) {
-    return;
-  }
-
-  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    start_level_ = level_file.first;
-    output_level_ =
-        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-
-    if ((start_level_ == vstorage_->num_non_empty_levels() - 1) ||
-        (start_level_ == 0 &&
-         !compaction_picker_->level0_compactions_in_progress()->empty())) {
-      return false;
-    }
-
-    start_level_inputs_.files = {level_file.second};
-    start_level_inputs_.level = start_level_;
-    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                      &start_level_inputs_);
-  };
-
-  for (auto& level_file : vstorage_->ExpiredTtlFiles()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-
-  start_level_inputs_.files.clear();
-}
-
-void LevelCompactionBuilder::PickFilesMarkedForPeriodicCompaction() {
-  if (vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
-    return;
-  }
-
-  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    output_level_ = start_level_ = level_file.first;
-
-    if (start_level_ == 0 &&
-        !compaction_picker_->level0_compactions_in_progress()->empty()) {
-      return false;
-    }
-
-    start_level_inputs_.files = {level_file.second};
-    start_level_inputs_.level = start_level_;
-    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                      &start_level_inputs_);
-  };
-
-  for (auto& level_file : vstorage_->FilesMarkedForPeriodicCompaction()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-
-  start_level_inputs_.files.clear();
-}
-
-void LevelCompactionBuilder::SetupInitialFiles() {
-  // Find the compactions by size on all levels.
-  bool skipped_l0_to_base = false;
-  for (int i = 0; i < compaction_picker_->NumberLevels() - 1; i++) {
-    start_level_score_ = vstorage_->CompactionScore(i);
-    start_level_ = vstorage_->CompactionScoreLevel(i);
-    assert(i == 0 || start_level_score_ <= vstorage_->CompactionScore(i - 1));
-    if (start_level_score_ >= 1) {
-      if (skipped_l0_to_base && start_level_ == vstorage_->base_level()) {
-        // If L0->base_level compaction is pending, don't schedule further
-        // compaction from base level. Otherwise L0->base_level compaction
-        // may starve.
-        continue;
-      }
-      output_level_ =
-          (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-      if (PickFileToCompact()) {
-        // found the compaction!
-        if (start_level_ == 0) {
-          // L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
-          compaction_reason_ = CompactionReason::kLevelL0FilesNum;
-        } else {
-          // L1+ score = `Level files size` / `MaxBytesForLevel`
-          compaction_reason_ = CompactionReason::kLevelMaxLevelSize;
-        }
-        break;
-      } else {
-        // didn't find the compaction, clear the inputs
-        start_level_inputs_.clear();
-        if (start_level_ == 0) {
-          skipped_l0_to_base = true;
-          // L0->base_level may be blocked due to ongoing L0->base_level
-          // compactions. It may also be blocked by an ongoing compaction from
-          // base_level downwards.
-          //
-          // In these cases, to reduce L0 file count and thus reduce likelihood
-          // of write stalls, we can attempt compacting a span of files within
-          // L0.
-          if (PickIntraL0Compaction()) {
-            output_level_ = 0;
-            compaction_reason_ = CompactionReason::kLevelL0FilesNum;
-            break;
-          }
-        }
-      }
-    }
-  }
-
-  // if we didn't find a compaction, check if there are any files marked for
-  // compaction
-  if (start_level_inputs_.empty()) {
-    parent_index_ = base_index_ = -1;
-
-    compaction_picker_->PickFilesMarkedForCompaction(
-        cf_name_, vstorage_, &start_level_, &output_level_,
-        &start_level_inputs_);
-    if (!start_level_inputs_.empty()) {
-      is_manual_ = true;
-      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
-      return;
-    }
-  }
-
-  // Bottommost Files Compaction on deleting tombstones
-  if (start_level_inputs_.empty()) {
-    size_t i;
-    for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
-         ++i) {
-      auto& level_and_file = vstorage_->BottommostFilesMarkedForCompaction()[i];
-      assert(!level_and_file.second->being_compacted);
-      start_level_inputs_.level = output_level_ = start_level_ =
-          level_and_file.first;
-      start_level_inputs_.files = {level_and_file.second};
-      if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                     &start_level_inputs_)) {
-        break;
-      }
-    }
-    if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
-      start_level_inputs_.clear();
-    } else {
-      assert(!start_level_inputs_.empty());
-      compaction_reason_ = CompactionReason::kBottommostFiles;
-      return;
-    }
-  }
-
-  // TTL Compaction
-  if (start_level_inputs_.empty()) {
-    PickExpiredTtlFiles();
-    if (!start_level_inputs_.empty()) {
-      compaction_reason_ = CompactionReason::kTtl;
-      return;
-    }
-  }
-
-  // Periodic Compaction
-  if (start_level_inputs_.empty()) {
-    PickFilesMarkedForPeriodicCompaction();
-    if (!start_level_inputs_.empty()) {
-      compaction_reason_ = CompactionReason::kPeriodicCompaction;
-      return;
-    }
-  }
-}
-
-bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
-  if (start_level_ == 0 && output_level_ != 0) {
-    return compaction_picker_->GetOverlappingL0Files(
-        vstorage_, &start_level_inputs_, output_level_, &parent_index_);
-  }
-  return true;
-}
-
-bool LevelCompactionBuilder::SetupOtherInputsIfNeeded() {
-  // Setup input files from output level. For output to L0, we only compact
-  // spans of files that do not interact with any pending compactions, so don't
-  // need to consider other levels.
-  if (output_level_ != 0) {
-    output_level_inputs_.level = output_level_;
-    if (!compaction_picker_->SetupOtherInputs(
-            cf_name_, mutable_cf_options_, vstorage_, &start_level_inputs_,
-            &output_level_inputs_, &parent_index_, base_index_)) {
-      return false;
-    }
-
-    compaction_inputs_.push_back(start_level_inputs_);
-    if (!output_level_inputs_.empty()) {
-      compaction_inputs_.push_back(output_level_inputs_);
-    }
-
-    // In some edge cases we could pick a compaction that will be compacting
-    // a key range that overlap with another running compaction, and both
-    // of them have the same output level. This could happen if
-    // (1) we are running a non-exclusive manual compaction
-    // (2) AddFile ingest a new file into the LSM tree
-    // We need to disallow this from happening.
-    if (compaction_picker_->FilesRangeOverlapWithCompaction(compaction_inputs_,
-                                                            output_level_)) {
-      // This compaction output could potentially conflict with the output
-      // of a currently running compaction, we cannot run it.
-      return false;
-    }
-    compaction_picker_->GetGrandparents(vstorage_, start_level_inputs_,
-                                        output_level_inputs_, &grandparents_);
-  } else {
-    compaction_inputs_.push_back(start_level_inputs_);
-  }
-  return true;
-}
-
-Compaction* LevelCompactionBuilder::PickCompaction() {
-  // Pick up the first file to start compaction. It may have been extended
-  // to a clean cut.
-  SetupInitialFiles();
-  if (start_level_inputs_.empty()) {
-    return nullptr;
-  }
-  assert(start_level_ >= 0 && output_level_ >= 0);
-
-  // If it is a L0 -> base level compaction, we need to set up other L0
-  // files if needed.
-  if (!SetupOtherL0FilesIfNeeded()) {
-    return nullptr;
-  }
-
-  // Pick files in the output level and expand more files in the start level
-  // if needed.
-  if (!SetupOtherInputsIfNeeded()) {
-    return nullptr;
-  }
-
-  // Form a compaction object containing the files we picked.
-  Compaction* c = GetCompaction();
-
-  TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
-
-  return c;
-}
-
-Compaction* LevelCompactionBuilder::GetCompaction() {
-  auto c = new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(compaction_inputs_),
-      output_level_,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level_,
-                          ioptions_.compaction_style, vstorage_->base_level(),
-                          ioptions_.level_compaction_dynamic_level_bytes),
-      mutable_cf_options_.max_compaction_bytes,
-      GetPathId(ioptions_, mutable_cf_options_, output_level_),
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
-                         output_level_, vstorage_->base_level()),
-      GetCompressionOptions(ioptions_, vstorage_, output_level_),
-      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
-      start_level_score_, false /* deletion_compaction */, compaction_reason_);
-
-  // If it's level 0 compaction, make sure we don't execute any other level 0
-  // compactions in parallel
-  compaction_picker_->RegisterCompaction(c);
-
-  // Creating a compaction influences the compaction score because the score
-  // takes running compactions into account (by skipping files that are already
-  // being compacted). Since we just changed compaction score, we recalculate it
-  // here
-  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
-  return c;
-}
-
-/*
- * Find the optimal path to place a file
- * Given a level, finds the path where levels up to it will fit in levels
- * up to and including this path
- */
-uint32_t LevelCompactionBuilder::GetPathId(
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, int level) {
-  uint32_t p = 0;
-  assert(!ioptions.cf_paths.empty());
-
-  // size remaining in the most recent path
-  uint64_t current_path_size = ioptions.cf_paths[0].target_size;
-
-  uint64_t level_size;
-  int cur_level = 0;
-
-  // max_bytes_for_level_base denotes L1 size.
-  // We estimate L0 size to be the same as L1.
-  level_size = mutable_cf_options.max_bytes_for_level_base;
-
-  // Last path is the fallback
-  while (p < ioptions.cf_paths.size() - 1) {
-    if (level_size <= current_path_size) {
-      if (cur_level == level) {
-        // Does desired level fit in this path?
-        return p;
-      } else {
-        current_path_size -= level_size;
-        if (cur_level > 0) {
-          if (ioptions.level_compaction_dynamic_level_bytes) {
-            // Currently, level_compaction_dynamic_level_bytes is ignored when
-            // multiple db paths are specified. https://github.com/facebook/
-            // rocksdb/blob/master/db/column_family.cc.
-            // Still, adding this check to avoid accidentally using
-            // max_bytes_for_level_multiplier_additional
-            level_size = static_cast<uint64_t>(
-                level_size * mutable_cf_options.max_bytes_for_level_multiplier);
-          } else {
-            level_size = static_cast<uint64_t>(
-                level_size * mutable_cf_options.max_bytes_for_level_multiplier *
-                mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
-          }
-        }
-        cur_level++;
-        continue;
-      }
-    }
-    p++;
-    current_path_size = ioptions.cf_paths[p].target_size;
-  }
-  return p;
-}
-
-bool LevelCompactionBuilder::PickFileToCompact() {
-  // level 0 files are overlapping. So we cannot pick more
-  // than one concurrent compactions at this level. This
-  // could be made better by looking at key-ranges that are
-  // being compacted at level 0.
-  if (start_level_ == 0 &&
-      !compaction_picker_->level0_compactions_in_progress()->empty()) {
-    TEST_SYNC_POINT("LevelCompactionPicker::PickCompactionBySize:0");
-    return false;
-  }
-
-  start_level_inputs_.clear();
-
-  assert(start_level_ >= 0);
-
-  // Pick the largest file in this level that is not already
-  // being compacted
-  const std::vector<int>& file_size =
-      vstorage_->FilesByCompactionPri(start_level_);
-  const std::vector<FileMetaData*>& level_files =
-      vstorage_->LevelFiles(start_level_);
-
-  unsigned int cmp_idx;
-  for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
-       cmp_idx < file_size.size(); cmp_idx++) {
-    int index = file_size[cmp_idx];
-    auto* f = level_files[index];
-
-    // do not pick a file to compact if it is being compacted
-    // from n-1 level.
-    if (f->being_compacted) {
-      continue;
-    }
-
-    start_level_inputs_.files.push_back(f);
-    start_level_inputs_.level = start_level_;
-    if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                    &start_level_inputs_) ||
-        compaction_picker_->FilesRangeOverlapWithCompaction(
-            {start_level_inputs_}, output_level_)) {
-      // A locked (pending compaction) input-level file was pulled in due to
-      // user-key overlap.
-      start_level_inputs_.clear();
-      continue;
-    }
-
-    // Now that input level is fully expanded, we check whether any output files
-    // are locked due to pending compaction.
-    //
-    // Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
-    // level files are locked, not just the extra ones pulled in for user-key
-    // overlap.
-    InternalKey smallest, largest;
-    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
-    CompactionInputFiles output_level_inputs;
-    output_level_inputs.level = output_level_;
-    vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
-                                    &output_level_inputs.files);
-    if (!output_level_inputs.empty() &&
-        !compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                    &output_level_inputs)) {
-      start_level_inputs_.clear();
-      continue;
-    }
-    base_index_ = index;
-    break;
-  }
-
-  // store where to start the iteration in the next call to PickCompaction
-  vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
-
-  return start_level_inputs_.size() > 0;
-}
-
-bool LevelCompactionBuilder::PickIntraL0Compaction() {
-  start_level_inputs_.clear();
-  const std::vector<FileMetaData*>& level_files =
-      vstorage_->LevelFiles(0 /* level */);
-  if (level_files.size() <
-          static_cast<size_t>(
-              mutable_cf_options_.level0_file_num_compaction_trigger + 2) ||
-      level_files[0]->being_compacted) {
-    // If L0 isn't accumulating much files beyond the regular trigger, don't
-    // resort to L0->L0 compaction yet.
-    return false;
-  }
-  return FindIntraL0Compaction(
-      level_files, kMinFilesForIntraL0Compaction, port::kMaxUint64,
-      mutable_cf_options_.max_compaction_bytes, &start_level_inputs_);
-}
-}  // namespace
-
-Compaction* LevelCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
-                                 mutable_cf_options, ioptions_);
-  return builder.PickCompaction();
-}
-}  // namespace rocksdb
@@ -1,32 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-
-#include "db/compaction/compaction_picker.h"
-
-namespace rocksdb {
-// Picking compactions for leveled compaction. See wiki page
-// https://github.com/facebook/rocksdb/wiki/Leveled-Compaction
-// for description of Leveled compaction.
-class LevelCompactionPicker : public CompactionPicker {
- public:
-  LevelCompactionPicker(const ImmutableCFOptions& ioptions,
-                        const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* vstorage,
-                                     LogBuffer* log_buffer) override;
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-
-}  // namespace rocksdb
@@ -1,32 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-#ifndef ROCKSDB_LITE
-
-#include "db/compaction/compaction_picker.h"
-
-namespace rocksdb {
-class UniversalCompactionPicker : public CompactionPicker {
- public:
-  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
-                            const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* vstorage,
-                                     LogBuffer* log_buffer) override;
-
-  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-}  // namespace rocksdb
-#endif  // !ROCKSDB_LITE
@@ -3,12 +3,13 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
+
 #include "db/snapshot_checker.h"
 #include "port/likely.h"
 #include "rocksdb/listener.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
+#include "util/sync_point.h"

 #define DEFINITELY_IN_SNAPSHOT(seq, snapshot)                       \
  ((seq) <= (snapshot) &&                                           \
@@ -37,16 +38,14 @@ CompactionIterator::CompactionIterator(
    CompactionRangeDelAggregator* range_del_agg, const Compaction* compaction,
    const CompactionFilter* compaction_filter,
    const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused)
+    const SequenceNumber preserve_deletes_seqnum)
    : CompactionIterator(
          input, cmp, merge_helper, last_sequence, snapshots,
          earliest_write_conflict_snapshot, snapshot_checker, env,
          report_detailed_time, expect_valid_internal_key, range_del_agg,
          std::unique_ptr<CompactionProxy>(
              compaction ? new CompactionProxy(compaction) : nullptr),
-          compaction_filter, shutting_down, preserve_deletes_seqnum,
-          manual_compaction_paused) {}
+          compaction_filter, shutting_down, preserve_deletes_seqnum) {}

 CompactionIterator::CompactionIterator(
    InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -58,8 +57,7 @@ CompactionIterator::CompactionIterator(
    std::unique_ptr<CompactionProxy> compaction,
    const CompactionFilter* compaction_filter,
    const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused)
+    const SequenceNumber preserve_deletes_seqnum)
    : input_(input),
      cmp_(cmp),
      merge_helper_(merge_helper),
@@ -73,8 +71,8 @@ CompactionIterator::CompactionIterator(
      compaction_(std::move(compaction)),
      compaction_filter_(compaction_filter),
      shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
      preserve_deletes_seqnum_(preserve_deletes_seqnum),
+      ignore_snapshots_(false),
      current_user_key_sequence_(0),
      current_user_key_snapshot_(0),
      merge_out_iter_(merge_helper_),
@@ -104,6 +102,13 @@ CompactionIterator::CompactionIterator(
    assert(snapshots_->at(i - 1) < snapshots_->at(i));
  }
 #endif
+  if (compaction_filter_ != nullptr) {
+    if (compaction_filter_->IgnoreSnapshots()) {
+      ignore_snapshots_ = true;
+    }
+  } else {
+    ignore_snapshots_ = false;
+  }
  input_->SetPinnedItersMgr(&pinned_iters_mgr_);
  TEST_SYNC_POINT_CALLBACK("CompactionIterator:AfterInit", compaction_.get());
 }
@@ -175,7 +180,9 @@ void CompactionIterator::Next() {
 void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
                                              Slice* skip_until) {
  if (compaction_filter_ != nullptr &&
-      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex)) {
+      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex) &&
+      (visible_at_tip_ || ignore_snapshots_ ||
+       DEFINITELY_NOT_IN_SNAPSHOT(ikey_.sequence, latest_snapshot_))) {
    // If the user has specified a compaction filter and the sequence
    // number is greater than any external snapshot, then invoke the
    // filter. If the return value of the compaction filter is true,
@@ -229,8 +236,7 @@ void CompactionIterator::NextFromInput() {
  at_next_ = false;
  valid_ = false;

-  while (!valid_ && input_->Valid() && !IsPausingManualCompaction() &&
-         !IsShuttingDown()) {
+  while (!valid_ && input_->Valid() && !IsShuttingDown()) {
    key_ = input_->key();
    value_ = input_->value();
    iter_stats_.num_input_records++;
@@ -481,6 +487,17 @@ void CompactionIterator::NextFromInput() {
      // in this snapshot.
      assert(last_sequence >= current_user_key_sequence_);

+      // Note2: if last_snapshot < current_user_key_snapshot, it can only
+      // mean last_snapshot is released between we process last value and
+      // this value, and findEarliestVisibleSnapshot returns the next snapshot
+      // as current_user_key_snapshot. In this case last value and current
+      // value are both in current_user_key_snapshot currently.
+      assert(last_snapshot == current_user_key_snapshot_ ||
+             (snapshot_checker_ != nullptr &&
+              snapshot_checker_->CheckInSnapshot(current_user_key_sequence_,
+                                                 last_snapshot) ==
+                  SnapshotCheckerResult::kSnapshotReleased));
+
      ++iter_stats_.num_record_drop_hidden;  // (A)
      input_->Next();
    } else if (compaction_ != nullptr && ikey_.type == kTypeDeletion &&
@@ -601,10 +618,6 @@ void CompactionIterator::NextFromInput() {
  if (!valid_ && IsShuttingDown()) {
    status_ = Status::ShutdownInProgress();
  }
-
-  if (IsPausingManualCompaction()) {
-    status_ = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
-  }
 }

 void CompactionIterator::PrepareOutput() {
@@ -621,7 +634,8 @@ void CompactionIterator::PrepareOutput() {
  // KeyNotExistsBeyondOutputLevel() return true?
  if ((compaction_ != nullptr && !compaction_->allow_ingest_behind()) &&
      ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ && valid_ &&
-      IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
+      IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge &&
+      !cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
    assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
    ikey_.sequence = 0;
    current_key_.UpdateInternalKey(0, ikey_.type);
@@ -10,8 +10,8 @@
 #include <unordered_set>
 #include <vector>

-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_iteration_stats.h"
+#include "db/compaction.h"
+#include "db/compaction_iteration_stats.h"
 #include "db/merge_helper.h"
 #include "db/pinned_iterators_manager.h"
 #include "db/range_del_aggregator.h"
@@ -59,32 +59,30 @@ class CompactionIterator {
    const Compaction* compaction_;
  };

-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      const Compaction* compaction = nullptr,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr);
+  CompactionIterator(InternalIterator* input, const Comparator* cmp,
+                     MergeHelper* merge_helper, SequenceNumber last_sequence,
+                     std::vector<SequenceNumber>* snapshots,
+                     SequenceNumber earliest_write_conflict_snapshot,
+                     const SnapshotChecker* snapshot_checker, Env* env,
+                     bool report_detailed_time, bool expect_valid_internal_key,
+                     CompactionRangeDelAggregator* range_del_agg,
+                     const Compaction* compaction = nullptr,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0);

  // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      std::unique_ptr<CompactionProxy> compaction,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr);
+  CompactionIterator(InternalIterator* input, const Comparator* cmp,
+                     MergeHelper* merge_helper, SequenceNumber last_sequence,
+                     std::vector<SequenceNumber>* snapshots,
+                     SequenceNumber earliest_write_conflict_snapshot,
+                     const SnapshotChecker* snapshot_checker, Env* env,
+                     bool report_detailed_time, bool expect_valid_internal_key,
+                     CompactionRangeDelAggregator* range_del_agg,
+                     std::unique_ptr<CompactionProxy> compaction,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0);

  ~CompactionIterator();

@@ -163,7 +161,6 @@ class CompactionIterator {
  std::unique_ptr<CompactionProxy> compaction_;
  const CompactionFilter* compaction_filter_;
  const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
  const SequenceNumber preserve_deletes_seqnum_;
  bool bottommost_level_;
  bool valid_ = false;
@@ -171,6 +168,8 @@ class CompactionIterator {
  SequenceNumber earliest_snapshot_;
  SequenceNumber latest_snapshot_;

+  bool ignore_snapshots_;
+
  // State
  //
  // Points to a copy of the current compaction iterator output (current_key_)
@@ -227,11 +226,5 @@ class CompactionIterator {
    // This is a best-effort facility, so memory_order_relaxed is sufficient.
    return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
  }
-
-  bool IsPausingManualCompaction() {
-    // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return manual_compaction_paused_ &&
-           manual_compaction_paused_->load(std::memory_order_relaxed);
-  }
 };
 }  // namespace rocksdb
@@ -3,15 +3,15 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

+#include "db/compaction_iterator.h"

 #include <string>
 #include <vector>

-#include "db/compaction/compaction_iterator.h"
 #include "port/port.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"

 namespace rocksdb {
@@ -112,39 +112,39 @@ class LoggingForwardVectorIterator : public InternalIterator {
    assert(keys_.size() == values_.size());
  }

-  bool Valid() const override { return current_ < keys_.size(); }
+  virtual bool Valid() const override { return current_ < keys_.size(); }

-  void SeekToFirst() override {
+  virtual void SeekToFirst() override {
    log.emplace_back(Action::Type::SEEK_TO_FIRST);
    current_ = 0;
  }
-  void SeekToLast() override { assert(false); }
+  virtual void SeekToLast() override { assert(false); }

-  void Seek(const Slice& target) override {
+  virtual void Seek(const Slice& target) override {
    log.emplace_back(Action::Type::SEEK, target.ToString());
    current_ = std::lower_bound(keys_.begin(), keys_.end(), target.ToString()) -
               keys_.begin();
  }

-  void SeekForPrev(const Slice& /*target*/) override { assert(false); }
+  virtual void SeekForPrev(const Slice& /*target*/) override { assert(false); }

-  void Next() override {
+  virtual void Next() override {
    assert(Valid());
    log.emplace_back(Action::Type::NEXT);
    current_++;
  }
-  void Prev() override { assert(false); }
+  virtual void Prev() override { assert(false); }

-  Slice key() const override {
+  virtual Slice key() const override {
    assert(Valid());
    return Slice(keys_[current_]);
  }
-  Slice value() const override {
+  virtual Slice value() const override {
    assert(Valid());
    return Slice(values_[current_]);
  }

-  Status status() const override { return Status::OK(); }
+  virtual Status status() const override { return Status::OK(); }

  std::vector<Action> log;

@@ -158,20 +158,22 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
 public:
  FakeCompaction() = default;

-  int level(size_t /*compaction_input_level*/) const override { return 0; }
-  bool KeyNotExistsBeyondOutputLevel(
+  virtual int level(size_t /*compaction_input_level*/) const override {
+    return 0;
+  }
+  virtual bool KeyNotExistsBeyondOutputLevel(
      const Slice& /*user_key*/,
      std::vector<size_t>* /*level_ptrs*/) const override {
    return is_bottommost_level || key_not_exists_beyond_output_level;
  }
-  bool bottommost_level() const override { return is_bottommost_level; }
-  int number_levels() const override { return 1; }
-  Slice GetLargestUserKey() const override {
+  virtual bool bottommost_level() const override { return is_bottommost_level; }
+  virtual int number_levels() const override { return 1; }
+  virtual Slice GetLargestUserKey() const override {
    return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
  }
-  bool allow_ingest_behind() const override { return false; }
+  virtual bool allow_ingest_behind() const override { return false; }

-  bool preserve_deletes() const override { return false; }
+  virtual bool preserve_deletes() const override { return false; }

  bool key_not_exists_beyond_output_level = false;

@@ -375,9 +377,10 @@ TEST_P(CompactionIteratorTest, RangeDeletionWithSnapshots) {

 TEST_P(CompactionIteratorTest, CompactionFilterSkipUntil) {
  class Filter : public CompactionFilter {
-    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                      const Slice& existing_value, std::string* /*new_value*/,
-                      std::string* skip_until) const override {
+    virtual Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
+                              const Slice& existing_value,
+                              std::string* /*new_value*/,
+                              std::string* skip_until) const override {
      std::string k = key.ToString();
      std::string v = existing_value.ToString();
      // See InitIterators() call below for the sequence of keys and their
@@ -557,9 +560,10 @@ TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {

 TEST_P(CompactionIteratorTest, SingleMergeOperand) {
  class Filter : public CompactionFilter {
-    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                      const Slice& existing_value, std::string* /*new_value*/,
-                      std::string* /*skip_until*/) const override {
+    virtual Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
+                              const Slice& existing_value,
+                              std::string* /*new_value*/,
+                              std::string* /*skip_until*/) const override {
      std::string k = key.ToString();
      std::string v = existing_value.ToString();

@@ -7,8 +7,14 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

+#include "db/compaction_job.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
-#include <cinttypes>
 #include <functional>
 #include <list>
 #include <memory>
@@ -19,8 +25,7 @@
 #include <vector>

 #include "db/builder.h"
-#include "db/compaction/compaction_job.h"
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/db_iter.h"
 #include "db/dbformat.h"
 #include "db/error_handler.h"
@@ -33,12 +38,6 @@
 #include "db/merge_helper.h"
 #include "db/range_del_aggregator.h"
 #include "db/version_set.h"
-#include "file/filename.h"
-#include "file/read_write_util.h"
-#include "file/sst_file_manager_impl.h"
-#include "file/writable_file_writer.h"
-#include "logging/log_buffer.h"
-#include "logging/logging.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/thread_status_util.h"
@@ -48,16 +47,21 @@
 #include "rocksdb/statistics.h"
 #include "rocksdb/status.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block.h"
+#include "table/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "table/table_builder.h"
-#include "test_util/sync_point.h"
 #include "util/coding.h"
+#include "util/file_reader_writer.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
+#include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
+#include "util/sst_file_manager_impl.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -93,8 +97,6 @@ const char* GetCompactionReasonString(CompactionReason compaction_reason) {
      return "Flush";
    case CompactionReason::kExternalSstIngestion:
      return "ExternalSstIngestion";
-    case CompactionReason::kPeriodicCompaction:
-      return "PeriodicCompaction";
    case CompactionReason::kNumOfReasons:
      // fall through
    default:
@@ -155,6 +157,7 @@ struct CompactionJob::SubcompactionState {
  uint64_t overlapped_bytes = 0;
  // A flag determine whether the key has been seen in ShouldStopBefore()
  bool seen_key = false;
+  std::string compression_dict;

  SubcompactionState(Compaction* c, Slice* _start, Slice* _end,
                     uint64_t size = 0)
@@ -170,7 +173,8 @@ struct CompactionJob::SubcompactionState {
        approx_size(size),
        grandparent_index(0),
        overlapped_bytes(0),
-        seen_key(false) {
+        seen_key(false),
+        compression_dict() {
    assert(compaction != nullptr);
  }

@@ -193,6 +197,7 @@ struct CompactionJob::SubcompactionState {
    grandparent_index = std::move(o.grandparent_index);
    overlapped_bytes = std::move(o.overlapped_bytes);
    seen_key = std::move(o.seen_key);
+    compression_dict = std::move(o.compression_dict);
    return *this;
  }

@@ -310,8 +315,7 @@ CompactionJob::CompactionJob(
    SequenceNumber earliest_write_conflict_snapshot,
    const SnapshotChecker* snapshot_checker, std::shared_ptr<Cache> table_cache,
    EventLogger* event_logger, bool paranoid_file_checks, bool measure_io_stats,
-    const std::string& dbname, CompactionJobStats* compaction_job_stats,
-    Env::Priority thread_pri, const std::atomic<bool>* manual_compaction_paused)
+    const std::string& dbname, CompactionJobStats* compaction_job_stats)
    : job_id_(job_id),
      compact_(new CompactionState(compaction)),
      compaction_job_stats_(compaction_job_stats),
@@ -320,11 +324,10 @@ CompactionJob::CompactionJob(
      db_options_(db_options),
      env_options_(env_options),
      env_(db_options.env),
-      env_options_for_read_(
+      env_optiosn_for_read_(
          env_->OptimizeForCompactionTableRead(env_options, db_options_)),
      versions_(versions),
      shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
      preserve_deletes_seqnum_(preserve_deletes_seqnum),
      log_buffer_(log_buffer),
      db_directory_(db_directory),
@@ -340,8 +343,7 @@ CompactionJob::CompactionJob(
      bottommost_level_(false),
      paranoid_file_checks_(paranoid_file_checks),
      measure_io_stats_(measure_io_stats),
-      write_hint_(Env::WLTH_NOT_SET),
-      thread_pri_(thread_pri) {
+      write_hint_(Env::WLTH_NOT_SET) {
  assert(log_buffer_ != nullptr);
  const auto* cfd = compact_->compaction->column_family_data();
  ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
@@ -411,13 +413,15 @@ void CompactionJob::Prepare() {

  write_hint_ =
      c->column_family_data()->CalculateSSTWriteHint(c->output_level());
+  // Is this compaction producing files at the bottommost level?
  bottommost_level_ = c->bottommost_level();

  if (c->ShouldFormSubcompactions()) {
-    {
-      StopWatch sw(env_, stats_, SUBCOMPACTION_SETUP_TIME);
-      GenSubcompactionBoundaries();
-    }
+    const uint64_t start_micros = env_->NowMicros();
+    GenSubcompactionBoundaries();
+    MeasureTime(stats_, SUBCOMPACTION_SETUP_TIME,
+                env_->NowMicros() - start_micros);
+
    assert(sizes_.size() == boundaries_.size() + 1);

    for (size_t i = 0; i <= boundaries_.size(); i++) {
@@ -425,8 +429,8 @@ void CompactionJob::Prepare() {
      Slice* end = i == boundaries_.size() ? nullptr : &boundaries_[i];
      compact_->sub_compact_states.emplace_back(c, start, end, sizes_[i]);
    }
-    RecordInHistogram(stats_, NUM_SUBCOMPACTIONS_SCHEDULED,
-                      compact_->sub_compact_states.size());
+    MeasureTime(stats_, NUM_SUBCOMPACTIONS_SCHEDULED,
+                compact_->sub_compact_states.size());
  } else {
    compact_->sub_compact_states.emplace_back(c, nullptr, nullptr);
  }
@@ -440,6 +444,11 @@ struct RangeWithSize {
      : range(a, b), size(s) {}
 };

+// Generates a histogram representing potential divisions of key ranges from
+// the input. It adds the starting and/or ending keys of certain input files
+// to the working set and then finds the approximate size of data in between
+// each consecutive pair of slices. Then it divides these ranges into
+// consecutive groups such that each group has a similar size.
 void CompactionJob::GenSubcompactionBoundaries() {
  auto* c = compact_->compaction;
  auto* cfd = c->column_family_data();
@@ -509,7 +518,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
  auto* v = compact_->compaction->input_version();
  for (auto it = bounds.begin();;) {
    const Slice a = *it;
-    ++it;
+    it++;

    if (it == bounds.end()) {
      break;
@@ -521,9 +530,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
    // to the index block and may incur I/O cost in the process. Unlock db
    // mutex to reduce contention
    db_mutex_->Unlock();
-    uint64_t size = versions_->ApproximateSize(SizeApproximationOptions(), v, a,
-                                               b, start_lvl, out_lvl + 1,
-                                               TableReaderCaller::kCompaction);
+    uint64_t size = versions_->ApproximateSize(v, a, b, start_lvl, out_lvl + 1);
    db_mutex_->Lock();
    ranges.emplace_back(a, b, size);
    sum += size;
@@ -603,9 +610,8 @@ Status CompactionJob::Run() {
        compact_->sub_compact_states[i].compaction_job_stats.cpu_micros;
  }

-  RecordTimeToHistogram(stats_, COMPACTION_TIME, compaction_stats_.micros);
-  RecordTimeToHistogram(stats_, COMPACTION_CPU_TIME,
-                        compaction_stats_.cpu_micros);
+  MeasureTime(stats_, COMPACTION_TIME, compaction_stats_.micros);
+  MeasureTime(stats_, COMPACTION_CPU_TIME, compaction_stats_.cpu_micros);

  TEST_SYNC_POINT("CompactionJob::Run:BeforeVerify");

@@ -648,14 +654,12 @@ Status CompactionJob::Run() {
        // to cache it here for further user reads
        InternalIterator* iter = cfd->table_cache()->NewIterator(
            ReadOptions(), env_options_, cfd->internal_comparator(),
-            *files_meta[file_idx], /*range_del_agg=*/nullptr, prefix_extractor,
-            /*table_reader_ptr=*/nullptr,
+            *files_meta[file_idx], nullptr /* range_del_agg */,
+            prefix_extractor, nullptr,
            cfd->internal_stats()->GetFileReadHist(
                compact_->compaction->output_level()),
-            TableReaderCaller::kCompactionRefill, /*arena=*/nullptr,
-            /*skip_filters=*/false, compact_->compaction->output_level(),
-            /*smallest_compaction_key=*/nullptr,
-            /*largest_compaction_key=*/nullptr);
+            false, nullptr /* arena */, false /* skip_filters */,
+            compact_->compaction->output_level());
        auto s = iter->status();

        if (s.ok() && paranoid_file_checks_) {
@@ -716,7 +720,7 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
  Status status = compact_->status;
  ColumnFamilyData* cfd = compact_->compaction->column_family_data();
  cfd->internal_stats()->AddCompactionStats(
-      compact_->compaction->output_level(), thread_pri_, compaction_stats_);
+      compact_->compaction->output_level(), compaction_stats_);

  if (status.ok()) {
    status = InstallCompactionResults(mutable_cf_options);
@@ -812,31 +816,13 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  uint64_t prev_cpu_micros = env_->NowCPUNanos() / 1000;

  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-
-  // Create compaction filter and fail the compaction if
-  // IgnoreSnapshots() = false because it is not supported anymore
-  const CompactionFilter* compaction_filter =
-      cfd->ioptions()->compaction_filter;
-  std::unique_ptr<CompactionFilter> compaction_filter_from_factory = nullptr;
-  if (compaction_filter == nullptr) {
-    compaction_filter_from_factory =
-        sub_compact->compaction->CreateCompactionFilter();
-    compaction_filter = compaction_filter_from_factory.get();
-  }
-  if (compaction_filter != nullptr && !compaction_filter->IgnoreSnapshots()) {
-    sub_compact->status = Status::NotSupported(
-        "CompactionFilter::IgnoreSnapshots() = false is not supported "
-        "anymore.");
-    return;
-  }
-
  CompactionRangeDelAggregator range_del_agg(&cfd->internal_comparator(),
                                             existing_snapshots_);

  // Although the v2 aggregator is what the level iterator(s) know about,
  // the AddTombstones calls will be propagated down to the v1 aggregator.
  std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
-      sub_compact->compaction, &range_del_agg, env_options_for_read_));
+      sub_compact->compaction, &range_del_agg, env_optiosn_for_read_));

  AutoThreadOperationStageUpdater stage_updater(
      ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -861,19 +847,58 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
    prev_cpu_read_nanos = IOSTATS(cpu_read_nanos);
  }

+  const MutableCFOptions* mutable_cf_options =
+      sub_compact->compaction->mutable_cf_options();
+
+  // To build compression dictionary, we sample the first output file, assuming
+  // it'll reach the maximum length. We optionally pass these samples through
+  // zstd's dictionary trainer, or just use them directly. Then, the dictionary
+  // is used for compressing subsequent output files in the same subcompaction.
+  const bool kUseZstdTrainer =
+      sub_compact->compaction->output_compression_opts().zstd_max_train_bytes >
+      0;
+  const size_t kSampleBytes =
+      kUseZstdTrainer
+          ? sub_compact->compaction->output_compression_opts()
+                .zstd_max_train_bytes
+          : sub_compact->compaction->output_compression_opts().max_dict_bytes;
+  const int kSampleLenShift = 6;  // 2^6 = 64-byte samples
+  std::set<size_t> sample_begin_offsets;
+  if (bottommost_level_ && kSampleBytes > 0) {
+    const size_t kMaxSamples = kSampleBytes >> kSampleLenShift;
+    const size_t kOutFileLen =
+        static_cast<size_t>(MaxFileSizeForLevel(*mutable_cf_options,
+            compact_->compaction->output_level(),
+            cfd->ioptions()->compaction_style,
+            compact_->compaction->GetInputBaseLevel(),
+            cfd->ioptions()->level_compaction_dynamic_level_bytes));
+    if (kOutFileLen != port::kMaxSizet) {
+      const size_t kOutFileNumSamples = kOutFileLen >> kSampleLenShift;
+      Random64 generator{versions_->NewFileNumber()};
+      for (size_t i = 0; i < kMaxSamples; ++i) {
+        sample_begin_offsets.insert(
+            static_cast<size_t>(generator.Uniform(kOutFileNumSamples))
+            << kSampleLenShift);
+      }
+    }
+  }
+
+  auto compaction_filter = cfd->ioptions()->compaction_filter;
+  std::unique_ptr<CompactionFilter> compaction_filter_from_factory = nullptr;
+  if (compaction_filter == nullptr) {
+    compaction_filter_from_factory =
+        sub_compact->compaction->CreateCompactionFilter();
+    compaction_filter = compaction_filter_from_factory.get();
+  }
  MergeHelper merge(
      env_, cfd->user_comparator(), cfd->ioptions()->merge_operator,
      compaction_filter, db_options_.info_log.get(),
      false /* internal key corruption is expected */,
      existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
      snapshot_checker_, compact_->compaction->level(),
-      db_options_.statistics.get());
+      db_options_.statistics.get(), shutting_down_);

  TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
-  TEST_SYNC_POINT_CALLBACK(
-      "CompactionJob::Run():PausingManualCompaction:1",
-      reinterpret_cast<void*>(
-          const_cast<std::atomic<bool>*>(manual_compaction_paused_)));

  Slice* start = sub_compact->start;
  Slice* end = sub_compact->end;
@@ -891,7 +916,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
      &existing_snapshots_, earliest_write_conflict_snapshot_,
      snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_), false,
      &range_del_agg, sub_compact->compaction, compaction_filter,
-      shutting_down_, preserve_deletes_seqnum_, manual_compaction_paused_));
+      shutting_down_, preserve_deletes_seqnum_));
  auto c_iter = sub_compact->c_iter.get();
  c_iter->SeekToFirst();
  if (c_iter->Valid() && sub_compact->compaction->output_level() != 0) {
@@ -902,6 +927,12 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
                                  sub_compact->current_output_file_size);
  }
  const auto& c_iter_stats = c_iter->iter_stats();
+  auto sample_begin_offset_iter = sample_begin_offsets.cbegin();
+  // data_begin_offset and dict_sample_data are only valid while generating
+  // dictionary from the first output file.
+  size_t data_begin_offset = 0;
+  std::string dict_sample_data;
+  dict_sample_data.reserve(kSampleBytes);

  while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
    // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
@@ -937,6 +968,55 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
        key, c_iter->ikey().sequence);
    sub_compact->num_output_records++;

+    if (sub_compact->outputs.size() == 1) {  // first output file
+      // Check if this key/value overlaps any sample intervals; if so, appends
+      // overlapping portions to the dictionary.
+      for (const auto& data_elmt : {key, value}) {
+        size_t data_end_offset = data_begin_offset + data_elmt.size();
+        while (sample_begin_offset_iter != sample_begin_offsets.cend() &&
+               *sample_begin_offset_iter < data_end_offset) {
+          size_t sample_end_offset =
+              *sample_begin_offset_iter + (1 << kSampleLenShift);
+          // Invariant: Because we advance sample iterator while processing the
+          // data_elmt containing the sample's last byte, the current sample
+          // cannot end before the current data_elmt.
+          assert(data_begin_offset < sample_end_offset);
+
+          size_t data_elmt_copy_offset, data_elmt_copy_len;
+          if (*sample_begin_offset_iter <= data_begin_offset) {
+            // The sample starts before data_elmt starts, so take bytes starting
+            // at the beginning of data_elmt.
+            data_elmt_copy_offset = 0;
+          } else {
+            // data_elmt starts before the sample starts, so take bytes starting
+            // at the below offset into data_elmt.
+            data_elmt_copy_offset =
+                *sample_begin_offset_iter - data_begin_offset;
+          }
+          if (sample_end_offset <= data_end_offset) {
+            // The sample ends before data_elmt ends, so take as many bytes as
+            // needed.
+            data_elmt_copy_len =
+                sample_end_offset - (data_begin_offset + data_elmt_copy_offset);
+          } else {
+            // data_elmt ends before the sample ends, so take all remaining
+            // bytes in data_elmt.
+            data_elmt_copy_len =
+                data_end_offset - (data_begin_offset + data_elmt_copy_offset);
+          }
+          dict_sample_data.append(&data_elmt.data()[data_elmt_copy_offset],
+                                  data_elmt_copy_len);
+          if (sample_end_offset > data_end_offset) {
+            // Didn't finish sample. Try to finish it with the next data_elmt.
+            break;
+          }
+          // Next sample may require bytes from same data_elmt.
+          sample_begin_offset_iter++;
+        }
+        data_begin_offset = data_end_offset;
+      }
+    }
+
    // Close output file if it is big enough. Two possibilities determine it's
    // time to close it: (1) the current key should be this file's last key, (2)
    // the next key should not be in this file.
@@ -955,14 +1035,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
      input_status = input->status();
      output_file_ended = true;
    }
-    TEST_SYNC_POINT_CALLBACK(
-        "CompactionJob::Run():PausingManualCompaction:2",
-        reinterpret_cast<void*>(
-            const_cast<std::atomic<bool>*>(manual_compaction_paused_)));
    c_iter->Next();
-    if (c_iter->status().IsManualCompactionPaused()) {
-      break;
-    }
    if (!output_file_ended && c_iter->Valid() &&
        sub_compact->compaction->output_level() != 0 &&
        sub_compact->ShouldStopBefore(c_iter->key(),
@@ -985,6 +1058,18 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
                                     &range_del_out_stats, next_key);
      RecordDroppedKeys(range_del_out_stats,
                        &sub_compact->compaction_job_stats);
+      if (sub_compact->outputs.size() == 1) {
+        // Use samples from first output file to create dictionary for
+        // compression of subsequent files.
+        if (kUseZstdTrainer) {
+          sub_compact->compression_dict = ZSTD_TrainDictionary(
+              dict_sample_data, kSampleLenShift,
+              sub_compact->compaction->output_compression_opts()
+                  .max_dict_bytes);
+        } else {
+          sub_compact->compression_dict = std::move(dict_sample_data);
+        }
+      }
    }
  }

@@ -1007,18 +1092,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  RecordDroppedKeys(c_iter_stats, &sub_compact->compaction_job_stats);
  RecordCompactionIOStats();

-  if (status.ok() && cfd->IsDropped()) {
-    status =
-        Status::ColumnFamilyDropped("Column family dropped during compaction");
-  }
-  if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      shutting_down_->load(std::memory_order_relaxed)) {
-    status = Status::ShutdownInProgress("Database shutdown");
-  }
-  if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      (manual_compaction_paused_ &&
-       manual_compaction_paused_->load(std::memory_order_relaxed))) {
-    status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
+  if (status.ok() &&
+      (shutting_down_->load(std::memory_order_relaxed) || cfd->IsDropped())) {
+    status = Status::ShutdownInProgress(
+        "Database shutdown or Column family drop during compaction");
  }
  if (status.ok()) {
    status = input->status();
@@ -1151,19 +1228,10 @@ Status CompactionJob::FinishCompactionOutputFile(
      lower_bound = nullptr;
    }
    if (next_table_min_key != nullptr) {
-      // This may be the last file in the subcompaction in some cases, so we
-      // need to compare the end key of subcompaction with the next file start
-      // key. When the end key is chosen by the subcompaction, we know that
-      // it must be the biggest key in output file. Therefore, it is safe to
-      // use the smaller key as the upper bound of the output file, to ensure
-      // that there is no overlapping between different output files.
+      // This isn't the last file in the subcompaction, so extend until the next
+      // file starts.
      upper_bound_guard = ExtractUserKey(*next_table_min_key);
-      if (sub_compact->end != nullptr &&
-          ucmp->Compare(upper_bound_guard, *sub_compact->end) >= 0) {
-        upper_bound = sub_compact->end;
-      } else {
-        upper_bound = &upper_bound_guard;
-      }
+      upper_bound = &upper_bound_guard;
    } else {
      // This is the last file in the subcompaction, so extend until the
      // subcompaction ends.
@@ -1181,13 +1249,6 @@ Status CompactionJob::FinishCompactionOutputFile(
      has_overlapping_endpoints = false;
    }

-    // The end key of the subcompaction must be bigger or equal to the upper
-    // bound. If the end of subcompaction is null or the upper bound is null,
-    // it means that this file is the last file in the compaction. So there
-    // will be no overlapping between this file and others.
-    assert(sub_compact->end == nullptr ||
-           upper_bound == nullptr ||
-           ucmp->Compare(*upper_bound , *sub_compact->end) <= 0);
    auto it = range_del_agg->NewIterator(lower_bound, upper_bound,
                                         has_overlapping_endpoints);
    // Position the range tombstone output iterator. There may be tombstone
@@ -1496,20 +1557,20 @@ Status CompactionJob::OpenCompactionOutputFile(
  bool skip_filters =
      cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;

-  int64_t temp_current_time = 0;
-  auto get_time_status = env_->GetCurrentTime(&temp_current_time);
-  // Safe to proceed even if GetCurrentTime fails. So, log and proceed.
-  if (!get_time_status.ok()) {
-    ROCKS_LOG_WARN(db_options_.info_log,
-                   "Failed to get current time. Status: %s",
-                   get_time_status.ToString().c_str());
-  }
-  uint64_t current_time = static_cast<uint64_t>(temp_current_time);
-
-  uint64_t latest_key_time =
+  uint64_t output_file_creation_time =
      sub_compact->compaction->MaxInputFileCreationTime();
-  if (latest_key_time == 0) {
-    latest_key_time = current_time;
+  if (output_file_creation_time == 0) {
+    int64_t _current_time = 0;
+    auto status = db_options_.env->GetCurrentTime(&_current_time);
+    // Safe to proceed even if GetCurrentTime fails. So, log and proceed.
+    if (!status.ok()) {
+      ROCKS_LOG_WARN(
+          db_options_.info_log,
+          "Failed to get current time to populate creation_time property. "
+          "Status: %s",
+          status.ToString().c_str());
+    }
+    output_file_creation_time = static_cast<uint64_t>(_current_time);
  }

  sub_compact->builder.reset(NewTableBuilder(
@@ -1517,11 +1578,9 @@ Status CompactionJob::OpenCompactionOutputFile(
      cfd->internal_comparator(), cfd->int_tbl_prop_collector_factories(),
      cfd->GetID(), cfd->GetName(), sub_compact->outfile.get(),
      sub_compact->compaction->output_compression(),
-      0 /*sample_for_compression */,
      sub_compact->compaction->output_compression_opts(),
-      sub_compact->compaction->output_level(), skip_filters, latest_key_time,
-      0 /* oldest_key_time */, sub_compact->compaction->max_output_file_size(),
-      current_time));
+      sub_compact->compaction->output_level(), &sub_compact->compression_dict,
+      skip_filters, output_file_creation_time));
  LogFlush(db_options_.info_log);
  return s;
 }
@@ -18,7 +18,7 @@
 #include <vector>

 #include "db/column_family.h"
-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/flush_scheduler.h"
 #include "db/internal_stats.h"
@@ -29,7 +29,6 @@
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
-#include "logging/event_logger.h"
 #include "options/cf_options.h"
 #include "options/db_options.h"
 #include "port/port.h"
@@ -41,6 +40,7 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"

@@ -55,11 +55,6 @@ class Version;
 class VersionEdit;
 class VersionSet;

-// CompactionJob is responsible for executing the compaction. Each (manual or
-// automated) compaction corresponds to a CompactionJob object, and usually
-// goes through the stages of `Prepare()`->`Run()`->`Install()`. CompactionJob
-// will divide the compaction into subcompactions and execute them in parallel
-// if needed.
 class CompactionJob {
 public:
  CompactionJob(int job_id, Compaction* compaction,
@@ -67,18 +62,17 @@ class CompactionJob {
                const EnvOptions env_options, VersionSet* versions,
                const std::atomic<bool>* shutting_down,
                const SequenceNumber preserve_deletes_seqnum,
-                LogBuffer* log_buffer, Directory* db_directory,
-                Directory* output_directory, Statistics* stats,
-                InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
+                LogBuffer* log_buffer,
+                Directory* db_directory, Directory* output_directory,
+                Statistics* stats, InstrumentedMutex* db_mutex,
+                ErrorHandler* db_error_handler,
                std::vector<SequenceNumber> existing_snapshots,
                SequenceNumber earliest_write_conflict_snapshot,
                const SnapshotChecker* snapshot_checker,
                std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
                bool paranoid_file_checks, bool measure_io_stats,
                const std::string& dbname,
-                CompactionJobStats* compaction_job_stats,
-                Env::Priority thread_pri,
-                const std::atomic<bool>* manual_compaction_paused = nullptr);
+                CompactionJobStats* compaction_job_stats);

  ~CompactionJob();

@@ -88,28 +82,17 @@ class CompactionJob {
  CompactionJob& operator=(const CompactionJob& job) = delete;

  // REQUIRED: mutex held
-  // Prepare for the compaction by setting up boundaries for each subcompaction
  void Prepare();
  // REQUIRED mutex not held
-  // Launch threads for each subcompaction and wait for them to finish. After
-  // that, verify table is usable and finally do bookkeeping to unify
-  // subcompaction results
  Status Run();

  // REQUIRED: mutex held
-  // Add compaction input/output to the current version
  Status Install(const MutableCFOptions& mutable_cf_options);

 private:
  struct SubcompactionState;

  void AggregateStatistics();
-
-  // Generates a histogram representing potential divisions of key ranges from
-  // the input. It adds the starting and/or ending keys of certain input files
-  // to the working set and then finds the approximate size of data in between
-  // each consecutive pair of slices. Then it divides these ranges into
-  // consecutive groups such that each group has a similar size.
  void GenSubcompactionBoundaries();

  // update the thread status for starting a compaction.
@@ -154,10 +137,9 @@ class CompactionJob {

  Env* env_;
  // env_option optimized for compaction table reads
-  EnvOptions env_options_for_read_;
+  EnvOptions env_optiosn_for_read_;
  VersionSet* versions_;
  const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
  const SequenceNumber preserve_deletes_seqnum_;
  LogBuffer* log_buffer_;
  Directory* db_directory_;
@@ -182,7 +164,6 @@ class CompactionJob {

  EventLogger* event_logger_;

-  // Is this compaction creating a file in the bottom most level?
  bool bottommost_level_;
  bool paranoid_file_checks_;
  bool measure_io_stats_;
@@ -191,7 +172,6 @@ class CompactionJob {
  // Stores the approx size of keys covered in the range of each subcompaction
  std::vector<uint64_t> sizes_;
  Env::WriteLifeTimeHint write_hint_;
-  Env::Priority thread_pri_;
 };

 }  // namespace rocksdb
@@ -7,8 +7,12 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
-#include <cinttypes>
 #include <iostream>
 #include <mutex>
 #include <queue>
@@ -17,14 +21,12 @@
 #include <unordered_set>
 #include <utility>

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/dbformat.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "db/write_batch_internal.h"
 #include "env/mock_env.h"
-#include "file/filename.h"
-#include "logging/logging.h"
 #include "memtable/hash_linklist_rep.h"
 #include "monitoring/statistics.h"
 #include "monitoring/thread_status_util.h"
@@ -45,18 +47,20 @@
 #include "rocksdb/thread_status.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/write_batch_with_index.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/mock_table.h"
-#include "table/plain/plain_table_factory.h"
+#include "table/plain_table_factory.h"
 #include "table/scoped_arena_iterator.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/compression.h"
+#include "util/filename.h"
 #include "util/hash.h"
+#include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/rate_limiter.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"

 #if !defined(IOS_CROSS_COMPILE)
@@ -109,7 +113,7 @@ class CompactionJobStatsTest : public testing::Test,
    Reopen(options);
  }

-  ~CompactionJobStatsTest() override {
+  ~CompactionJobStatsTest() {
    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
    rocksdb::SyncPoint::GetInstance()->LoadDependency({});
    rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -422,7 +426,7 @@ class CompactionJobStatsChecker : public EventListener {
  // Once a compaction completed, this function will verify the returned
  // CompactionJobInfo with the oldest CompactionJobInfo added earlier
  // in "expected_stats_" which has not yet being used for verification.
-  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
+  virtual void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) {
    if (verify_next_comp_io_stats_) {
      ASSERT_GT(ci.stats.file_write_nanos, 0);
      ASSERT_GT(ci.stats.file_range_sync_nanos, 0);
@@ -519,7 +523,7 @@ class CompactionJobDeletionStatsChecker : public CompactionJobStatsChecker {
 public:
  // Verifies whether two CompactionJobStats match.
  void Verify(const CompactionJobStats& current_stats,
-              const CompactionJobStats& stats) override {
+              const CompactionJobStats& stats) {
    ASSERT_EQ(
      current_stats.num_input_deletion_records,
      stats.num_input_deletion_records);
@@ -6,26 +6,23 @@
 #ifndef ROCKSDB_LITE

 #include <algorithm>
-#include <array>
-#include <cinttypes>
 #include <map>
 #include <string>
 #include <tuple>

 #include "db/column_family.h"
-#include "db/compaction/compaction_job.h"
-#include "db/db_impl/db_impl.h"
+#include "db/compaction_job.h"
 #include "db/error_handler.h"
 #include "db/version_set.h"
-#include "file/writable_file_writer.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/options.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/mock_table.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/file_reader_writer.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"

 namespace rocksdb {
@@ -78,8 +75,7 @@ class CompactionJobTest : public testing::Test {
        write_buffer_manager_(db_options_.db_write_buffer_size),
        versions_(new VersionSet(dbname_, &db_options_, env_options_,
                                 table_cache_.get(), &write_buffer_manager_,
-                                 &write_controller_,
-                                 /*block_cache_tracer=*/nullptr)),
+                                 &write_controller_)),
        shutting_down_(false),
        preserve_deletes_seqnum_(0),
        mock_table_factory_(new mock::MockTableFactory()),
@@ -176,7 +172,7 @@ class CompactionJobTest : public testing::Test {
        // This is how the key will look like once it's written in bottommost
        // file
        InternalKey bottommost_internal_key(
-            key, 0, kTypeValue);
+            key, (key == "9999") ? sequence_number : 0, kTypeValue);

        if (corrupt_id(k)) {
          test::CorruptKeyType(&internal_key);
@@ -198,22 +194,7 @@ class CompactionJobTest : public testing::Test {
  }

  void NewDB() {
-    DestroyDB(dbname_, Options());
-    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    versions_.reset(new VersionSet(dbname_, &db_options_, env_options_,
-                                   table_cache_.get(), &write_buffer_manager_,
-                                   &write_controller_,
-                                   /*block_cache_tracer=*/nullptr));
-    compaction_job_stats_.Reset();
-    SetIdentityFile(env_, dbname_);
-
    VersionEdit new_db;
-    if (db_options_.write_dbid_to_manifest) {
-      DBImpl* impl = new DBImpl(DBOptions(), dbname_);
-      std::string db_id;
-      impl->GetDbIdentityFromIdentityFile(&db_id);
-      new_db.SetDBId(db_id);
-    }
    new_db.SetLogNumber(0);
    new_db.SetNextFile(2);
    new_db.SetLastSequence(0);
@@ -249,8 +230,7 @@ class CompactionJobTest : public testing::Test {
      const std::vector<std::vector<FileMetaData*>>& input_files,
      const stl_wrappers::KVMap& expected_results,
      const std::vector<SequenceNumber>& snapshots = {},
-      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber,
-      int output_level = 1, bool verify = true) {
+      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
    auto cfd = versions_->GetColumnFamilySet()->GetDefault();

    size_t num_input_files = 0;
@@ -267,7 +247,7 @@ class CompactionJobTest : public testing::Test {

    Compaction compaction(cfd->current()->storage_info(), *cfd->ioptions(),
                          *cfd->GetLatestMutableCFOptions(),
-                          compaction_input_files, output_level, 1024 * 1024,
+                          compaction_input_files, 1, 1024 * 1024,
                          10 * 1024 * 1024, 0, kNoCompression,
                          cfd->ioptions()->compression_opts, 0, {}, true);
    compaction.SetInputVersion(cfd->current());
@@ -282,8 +262,7 @@ class CompactionJobTest : public testing::Test {
        &shutting_down_, preserve_deletes_seqnum_, &log_buffer, nullptr,
        nullptr, nullptr, &mutex_, &error_handler_, snapshots,
        earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_,
-        Env::Priority::USER);
+        &event_logger, false, false, dbname_, &compaction_job_stats_);
    VerifyInitializationOfCompactionJobStats(compaction_job_stats_);

    compaction_job.Prepare();
@@ -295,17 +274,15 @@ class CompactionJobTest : public testing::Test {
    ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions()));
    mutex_.Unlock();

-    if (verify) {
-      if (expected_results.size() == 0) {
-        ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
-        ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-        ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
-      } else {
-        ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
-        ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-        ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
-        mock_table_factory_->AssertLatestFile(expected_results);
-      }
+    if (expected_results.size() == 0) {
+      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
+      ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
+    } else {
+      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
+      ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
+      mock_table_factory_->AssertLatestFile(expected_results);
    }
  }

@@ -402,7 +379,7 @@ TEST_F(CompactionJobTest, SimpleOverwrite) {

  auto expected_results =
      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "val2"},
-                          {KeyStr("b", 0U, kTypeValue), "val3"}});
+                          {KeyStr("b", 4U, kTypeValue), "val3"}});

  SetLastSequence(4U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -455,7 +432,7 @@ TEST_F(CompactionJobTest, SimpleMerge) {

  auto expected_results =
      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 0U, kTypeValue), "1,2"}});
+                          {KeyStr("b", 2U, kTypeValue), "1,2"}});

  SetLastSequence(5U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -479,7 +456,7 @@ TEST_F(CompactionJobTest, NonAssocMerge) {

  auto expected_results =
      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 0U, kTypeValue), "1,2"}});
+                          {KeyStr("b", 2U, kTypeValue), "1,2"}});

  SetLastSequence(5U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -506,7 +483,7 @@ TEST_F(CompactionJobTest, MergeOperandFilter) {

  auto expected_results =
      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), test::EncodeInt(8U)},
-                          {KeyStr("b", 0U, kTypeValue), test::EncodeInt(2U)}});
+                          {KeyStr("b", 2U, kTypeValue), test::EncodeInt(2U)}});

  SetLastSequence(5U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -769,7 +746,7 @@ TEST_F(CompactionJobTest, SingleDeleteZeroSeq) {
  AddMockFile(file2);

  auto expected_results = mock::MakeMockFile({
-      {KeyStr("dummy", 0U, kTypeValue), "val2"},
+      {KeyStr("dummy", 5U, kTypeValue), "val2"},
  });

  SetLastSequence(22U);
@@ -953,7 +930,7 @@ TEST_F(CompactionJobTest, CorruptionAfterDeletion) {
      mock::MakeMockFile({{test::KeyStr("A", 0U, kTypeValue), "val3"},
                          {test::KeyStr("a", 0U, kTypeValue, true), "val"},
                          {test::KeyStr("b", 0U, kTypeValue, true), "val"},
-                          {test::KeyStr("c", 0U, kTypeValue), "val2"}});
+                          {test::KeyStr("c", 1U, kTypeValue), "val2"}});

  SetLastSequence(6U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -7,21 +7,25 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

-#include "db/compaction/compaction_picker.h"
+#include "db/compaction_picker.h"

-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <limits>
 #include <queue>
 #include <string>
 #include <utility>
 #include <vector>
 #include "db/column_family.h"
-#include "file/filename.h"
-#include "logging/log_buffer.h"
 #include "monitoring/statistics.h"
-#include "test_util/sync_point.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
 #include "util/random.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -38,23 +42,19 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
 bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                           size_t min_files_to_compact,
                           uint64_t max_compact_bytes_per_del_file,
-                           uint64_t max_compaction_bytes,
                           CompactionInputFiles* comp_inputs) {
  size_t compact_bytes = static_cast<size_t>(level_files[0]->fd.file_size);
-  uint64_t compensated_compact_bytes = level_files[0]->compensated_file_size;
  size_t compact_bytes_per_del_file = port::kMaxSizet;
-  // Compaction range will be [0, span_len).
+  // compaction range will be [0, span_len).
  size_t span_len;
-  // Pull in files until the amount of compaction work per deleted file begins
-  // increasing or maximum total compaction size is reached.
+  // pull in files until the amount of compaction work per deleted file begins
+  // increasing.
  size_t new_compact_bytes_per_del_file = 0;
  for (span_len = 1; span_len < level_files.size(); ++span_len) {
    compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
-    compensated_compact_bytes += level_files[span_len]->compensated_file_size;
    new_compact_bytes_per_del_file = compact_bytes / span_len;
    if (level_files[span_len]->being_compacted ||
-        new_compact_bytes_per_del_file > compact_bytes_per_del_file ||
-        compensated_compact_bytes > max_compaction_bytes) {
+        new_compact_bytes_per_del_file > compact_bytes_per_del_file) {
      break;
    }
    compact_bytes_per_del_file = new_compact_bytes_per_del_file;
@@ -543,9 +543,9 @@ void CompactionPicker::GetGrandparents(
 Compaction* CompactionPicker::CompactRange(
    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
    VersionStorageInfo* vstorage, int input_level, int output_level,
-    const CompactRangeOptions& compact_range_options, const InternalKey* begin,
-    const InternalKey* end, InternalKey** compaction_end, bool* manual_conflict,
-    uint64_t max_file_num_to_ignore) {
+    uint32_t output_path_id, uint32_t max_subcompactions,
+    const InternalKey* begin, const InternalKey* end,
+    InternalKey** compaction_end, bool* manual_conflict) {
  // CompactionPickerFIFO has its own implementation of compact range
  assert(ioptions_.compaction_style != kCompactionStyleFIFO);

@@ -609,13 +609,11 @@ Compaction* CompactionPicker::CompactRange(
        output_level,
        MaxFileSizeForLevel(mutable_cf_options, output_level,
                            ioptions_.compaction_style),
-        /* max_compaction_bytes */ LLONG_MAX,
-        compact_range_options.target_path_id,
+        /* max_compaction_bytes */ LLONG_MAX, output_path_id,
        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
                           output_level, 1),
        GetCompressionOptions(ioptions_, vstorage, output_level),
-        compact_range_options.max_subcompactions, /* grandparents */ {},
-        /* is manual */ true);
+        max_subcompactions, /* grandparents */ {}, /* is manual */ true);
    RegisterCompaction(c);
    return c;
  }
@@ -660,43 +658,7 @@ Compaction* CompactionPicker::CompactRange(
      }
    }
  }
-  assert(compact_range_options.target_path_id <
-         static_cast<uint32_t>(ioptions_.cf_paths.size()));
-
-  // for BOTTOM LEVEL compaction only, use max_file_num_to_ignore to filter out
-  // files that are created during the current compaction.
-  if (compact_range_options.bottommost_level_compaction ==
-          BottommostLevelCompaction::kForceOptimized &&
-      max_file_num_to_ignore != port::kMaxUint64) {
-    assert(input_level == output_level);
-    // inputs_shrunk holds a continuous subset of input files which were all
-    // created before the current manual compaction
-    std::vector<FileMetaData*> inputs_shrunk;
-    size_t skip_input_index = inputs.size();
-    for (size_t i = 0; i < inputs.size(); ++i) {
-      if (inputs[i]->fd.GetNumber() < max_file_num_to_ignore) {
-        inputs_shrunk.push_back(inputs[i]);
-      } else if (!inputs_shrunk.empty()) {
-        // inputs[i] was created during the current manual compaction and
-        // need to be skipped
-        skip_input_index = i;
-        break;
-      }
-    }
-    if (inputs_shrunk.empty()) {
-      return nullptr;
-    }
-    if (inputs.size() != inputs_shrunk.size()) {
-      inputs.files.swap(inputs_shrunk);
-    }
-    // set covering_the_whole_range to false if there is any file that need to
-    // be compacted in the range of inputs[skip_input_index+1, inputs.size())
-    for (size_t i = skip_input_index + 1; i < inputs.size(); ++i) {
-      if (inputs[i]->fd.GetNumber() < max_file_num_to_ignore) {
-        covering_the_whole_range = false;
-      }
-    }
-  }
+  assert(output_path_id < static_cast<uint32_t>(ioptions_.cf_paths.size()));

  InternalKey key_storage;
  InternalKey* next_smallest = &key_storage;
@@ -762,12 +724,11 @@ Compaction* CompactionPicker::CompactRange(
      MaxFileSizeForLevel(mutable_cf_options, output_level,
                          ioptions_.compaction_style, vstorage->base_level(),
                          ioptions_.level_compaction_dynamic_level_bytes),
-      mutable_cf_options.max_compaction_bytes,
-      compact_range_options.target_path_id,
+      mutable_cf_options.max_compaction_bytes, output_path_id,
      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                         vstorage->base_level()),
      GetCompressionOptions(ioptions_, vstorage, output_level),
-      compact_range_options.max_subcompactions, std::move(grandparents),
+      max_subcompactions, std::move(grandparents),
      /* is manual compaction */ true);

  TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);
@@ -1107,4 +1068,484 @@ bool CompactionPicker::GetOverlappingL0Files(
  return true;
 }

+bool LevelCompactionPicker::NeedsCompaction(
+    const VersionStorageInfo* vstorage) const {
+  if (!vstorage->ExpiredTtlFiles().empty()) {
+    return true;
+  }
+  if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
+    return true;
+  }
+  if (!vstorage->FilesMarkedForCompaction().empty()) {
+    return true;
+  }
+  for (int i = 0; i <= vstorage->MaxInputLevel(); i++) {
+    if (vstorage->CompactionScore(i) >= 1) {
+      return true;
+    }
+  }
+  return false;
+}
+
+namespace {
+// A class to build a leveled compaction step-by-step.
+class LevelCompactionBuilder {
+ public:
+  LevelCompactionBuilder(const std::string& cf_name,
+                         VersionStorageInfo* vstorage,
+                         CompactionPicker* compaction_picker,
+                         LogBuffer* log_buffer,
+                         const MutableCFOptions& mutable_cf_options,
+                         const ImmutableCFOptions& ioptions)
+      : cf_name_(cf_name),
+        vstorage_(vstorage),
+        compaction_picker_(compaction_picker),
+        log_buffer_(log_buffer),
+        mutable_cf_options_(mutable_cf_options),
+        ioptions_(ioptions) {}
+
+  // Pick and return a compaction.
+  Compaction* PickCompaction();
+
+  // Pick the initial files to compact to the next level. (or together
+  // in Intra-L0 compactions)
+  void SetupInitialFiles();
+
+  // If the initial files are from L0 level, pick other L0
+  // files if needed.
+  bool SetupOtherL0FilesIfNeeded();
+
+  // Based on initial files, setup other files need to be compacted
+  // in this compaction, accordingly.
+  bool SetupOtherInputsIfNeeded();
+
+  Compaction* GetCompaction();
+
+  // For the specfied level, pick a file that we want to compact.
+  // Returns false if there is no file to compact.
+  // If it returns true, inputs->files.size() will be exactly one.
+  // If level is 0 and there is already a compaction on that level, this
+  // function will return false.
+  bool PickFileToCompact();
+
+  // For L0->L0, picks the longest span of files that aren't currently
+  // undergoing compaction for which work-per-deleted-file decreases. The span
+  // always starts from the newest L0 file.
+  //
+  // Intra-L0 compaction is independent of all other files, so it can be
+  // performed even when L0->base_level compactions are blocked.
+  //
+  // Returns true if `inputs` is populated with a span of files to be compacted;
+  // otherwise, returns false.
+  bool PickIntraL0Compaction();
+
+  void PickExpiredTtlFiles();
+
+  const std::string& cf_name_;
+  VersionStorageInfo* vstorage_;
+  CompactionPicker* compaction_picker_;
+  LogBuffer* log_buffer_;
+  int start_level_ = -1;
+  int output_level_ = -1;
+  int parent_index_ = -1;
+  int base_index_ = -1;
+  double start_level_score_ = 0;
+  bool is_manual_ = false;
+  CompactionInputFiles start_level_inputs_;
+  std::vector<CompactionInputFiles> compaction_inputs_;
+  CompactionInputFiles output_level_inputs_;
+  std::vector<FileMetaData*> grandparents_;
+  CompactionReason compaction_reason_ = CompactionReason::kUnknown;
+
+  const MutableCFOptions& mutable_cf_options_;
+  const ImmutableCFOptions& ioptions_;
+  // Pick a path ID to place a newly generated file, with its level
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            int level);
+
+  static const int kMinFilesForIntraL0Compaction = 4;
+};
+
+void LevelCompactionBuilder::PickExpiredTtlFiles() {
+  if (vstorage_->ExpiredTtlFiles().empty()) {
+    return;
+  }
+
+  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
+    // If it's being compacted it has nothing to do here.
+    // If this assert() fails that means that some function marked some
+    // files as being_compacted, but didn't call ComputeCompactionScore()
+    assert(!level_file.second->being_compacted);
+    start_level_ = level_file.first;
+    output_level_ =
+        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
+
+    if ((start_level_ == vstorage_->num_non_empty_levels() - 1) ||
+        (start_level_ == 0 &&
+         !compaction_picker_->level0_compactions_in_progress()->empty())) {
+      return false;
+    }
+
+    start_level_inputs_.files = {level_file.second};
+    start_level_inputs_.level = start_level_;
+    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                      &start_level_inputs_);
+  };
+
+  for (auto& level_file : vstorage_->ExpiredTtlFiles()) {
+    if (continuation(level_file)) {
+      // found the compaction!
+      return;
+    }
+  }
+
+  start_level_inputs_.files.clear();
+}
+
+void LevelCompactionBuilder::SetupInitialFiles() {
+  // Find the compactions by size on all levels.
+  bool skipped_l0_to_base = false;
+  for (int i = 0; i < compaction_picker_->NumberLevels() - 1; i++) {
+    start_level_score_ = vstorage_->CompactionScore(i);
+    start_level_ = vstorage_->CompactionScoreLevel(i);
+    assert(i == 0 || start_level_score_ <= vstorage_->CompactionScore(i - 1));
+    if (start_level_score_ >= 1) {
+      if (skipped_l0_to_base && start_level_ == vstorage_->base_level()) {
+        // If L0->base_level compaction is pending, don't schedule further
+        // compaction from base level. Otherwise L0->base_level compaction
+        // may starve.
+        continue;
+      }
+      output_level_ =
+          (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
+      if (PickFileToCompact()) {
+        // found the compaction!
+        if (start_level_ == 0) {
+          // L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
+          compaction_reason_ = CompactionReason::kLevelL0FilesNum;
+        } else {
+          // L1+ score = `Level files size` / `MaxBytesForLevel`
+          compaction_reason_ = CompactionReason::kLevelMaxLevelSize;
+        }
+        break;
+      } else {
+        // didn't find the compaction, clear the inputs
+        start_level_inputs_.clear();
+        if (start_level_ == 0) {
+          skipped_l0_to_base = true;
+          // L0->base_level may be blocked due to ongoing L0->base_level
+          // compactions. It may also be blocked by an ongoing compaction from
+          // base_level downwards.
+          //
+          // In these cases, to reduce L0 file count and thus reduce likelihood
+          // of write stalls, we can attempt compacting a span of files within
+          // L0.
+          if (PickIntraL0Compaction()) {
+            output_level_ = 0;
+            compaction_reason_ = CompactionReason::kLevelL0FilesNum;
+            break;
+          }
+        }
+      }
+    }
+  }
+
+  // if we didn't find a compaction, check if there are any files marked for
+  // compaction
+  if (start_level_inputs_.empty()) {
+    parent_index_ = base_index_ = -1;
+
+    // PickFilesMarkedForCompaction();
+    compaction_picker_->PickFilesMarkedForCompaction(
+        cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_);
+    if (!start_level_inputs_.empty()) {
+      is_manual_ = true;
+      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
+      return;
+    }
+
+    size_t i;
+    for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
+         ++i) {
+      auto& level_and_file = vstorage_->BottommostFilesMarkedForCompaction()[i];
+      assert(!level_and_file.second->being_compacted);
+      start_level_inputs_.level = output_level_ = start_level_ =
+          level_and_file.first;
+      start_level_inputs_.files = {level_and_file.second};
+      if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                     &start_level_inputs_)) {
+        break;
+      }
+    }
+    if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
+      start_level_inputs_.clear();
+    } else {
+      assert(!start_level_inputs_.empty());
+      compaction_reason_ = CompactionReason::kBottommostFiles;
+      return;
+    }
+
+    assert(start_level_inputs_.empty());
+    PickExpiredTtlFiles();
+    if (!start_level_inputs_.empty()) {
+      compaction_reason_ = CompactionReason::kTtl;
+    }
+  }
+}
+
+bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
+  if (start_level_ == 0 && output_level_ != 0) {
+    return compaction_picker_->GetOverlappingL0Files(
+        vstorage_, &start_level_inputs_, output_level_, &parent_index_);
+  }
+  return true;
+}
+
+bool LevelCompactionBuilder::SetupOtherInputsIfNeeded() {
+  // Setup input files from output level. For output to L0, we only compact
+  // spans of files that do not interact with any pending compactions, so don't
+  // need to consider other levels.
+  if (output_level_ != 0) {
+    output_level_inputs_.level = output_level_;
+    if (!compaction_picker_->SetupOtherInputs(
+            cf_name_, mutable_cf_options_, vstorage_, &start_level_inputs_,
+            &output_level_inputs_, &parent_index_, base_index_)) {
+      return false;
+    }
+
+    compaction_inputs_.push_back(start_level_inputs_);
+    if (!output_level_inputs_.empty()) {
+      compaction_inputs_.push_back(output_level_inputs_);
+    }
+
+    // In some edge cases we could pick a compaction that will be compacting
+    // a key range that overlap with another running compaction, and both
+    // of them have the same output level. This could happen if
+    // (1) we are running a non-exclusive manual compaction
+    // (2) AddFile ingest a new file into the LSM tree
+    // We need to disallow this from happening.
+    if (compaction_picker_->FilesRangeOverlapWithCompaction(compaction_inputs_,
+                                                            output_level_)) {
+      // This compaction output could potentially conflict with the output
+      // of a currently running compaction, we cannot run it.
+      return false;
+    }
+    compaction_picker_->GetGrandparents(vstorage_, start_level_inputs_,
+                                        output_level_inputs_, &grandparents_);
+  } else {
+    compaction_inputs_.push_back(start_level_inputs_);
+  }
+  return true;
+}
+
+Compaction* LevelCompactionBuilder::PickCompaction() {
+  // Pick up the first file to start compaction. It may have been extended
+  // to a clean cut.
+  SetupInitialFiles();
+  if (start_level_inputs_.empty()) {
+    return nullptr;
+  }
+  assert(start_level_ >= 0 && output_level_ >= 0);
+
+  // If it is a L0 -> base level compaction, we need to set up other L0
+  // files if needed.
+  if (!SetupOtherL0FilesIfNeeded()) {
+    return nullptr;
+  }
+
+  // Pick files in the output level and expand more files in the start level
+  // if needed.
+  if (!SetupOtherInputsIfNeeded()) {
+    return nullptr;
+  }
+
+  // Form a compaction object containing the files we picked.
+  Compaction* c = GetCompaction();
+
+  TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
+
+  return c;
+}
+
+Compaction* LevelCompactionBuilder::GetCompaction() {
+  auto c = new Compaction(
+      vstorage_, ioptions_, mutable_cf_options_, std::move(compaction_inputs_),
+      output_level_,
+      MaxFileSizeForLevel(mutable_cf_options_, output_level_,
+                          ioptions_.compaction_style, vstorage_->base_level(),
+                          ioptions_.level_compaction_dynamic_level_bytes),
+      mutable_cf_options_.max_compaction_bytes,
+      GetPathId(ioptions_, mutable_cf_options_, output_level_),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level_, vstorage_->base_level()),
+      GetCompressionOptions(ioptions_, vstorage_, output_level_),
+      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
+      start_level_score_, false /* deletion_compaction */, compaction_reason_);
+
+  // If it's level 0 compaction, make sure we don't execute any other level 0
+  // compactions in parallel
+  compaction_picker_->RegisterCompaction(c);
+
+  // Creating a compaction influences the compaction score because the score
+  // takes running compactions into account (by skipping files that are already
+  // being compacted). Since we just changed compaction score, we recalculate it
+  // here
+  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
+  return c;
+}
+
+/*
+ * Find the optimal path to place a file
+ * Given a level, finds the path where levels up to it will fit in levels
+ * up to and including this path
+ */
+uint32_t LevelCompactionBuilder::GetPathId(
+    const ImmutableCFOptions& ioptions,
+    const MutableCFOptions& mutable_cf_options, int level) {
+  uint32_t p = 0;
+  assert(!ioptions.cf_paths.empty());
+
+  // size remaining in the most recent path
+  uint64_t current_path_size = ioptions.cf_paths[0].target_size;
+
+  uint64_t level_size;
+  int cur_level = 0;
+
+  // max_bytes_for_level_base denotes L1 size.
+  // We estimate L0 size to be the same as L1.
+  level_size = mutable_cf_options.max_bytes_for_level_base;
+
+  // Last path is the fallback
+  while (p < ioptions.cf_paths.size() - 1) {
+    if (level_size <= current_path_size) {
+      if (cur_level == level) {
+        // Does desired level fit in this path?
+        return p;
+      } else {
+        current_path_size -= level_size;
+        if (cur_level > 0) {
+          if (ioptions.level_compaction_dynamic_level_bytes) {
+            // Currently, level_compaction_dynamic_level_bytes is ignored when
+            // multiple db paths are specified. https://github.com/facebook/
+            // rocksdb/blob/master/db/column_family.cc.
+            // Still, adding this check to avoid accidentally using
+            // max_bytes_for_level_multiplier_additional
+            level_size = static_cast<uint64_t>(
+                level_size * mutable_cf_options.max_bytes_for_level_multiplier);
+          } else {
+            level_size = static_cast<uint64_t>(
+                level_size * mutable_cf_options.max_bytes_for_level_multiplier *
+                mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
+          }
+        }
+        cur_level++;
+        continue;
+      }
+    }
+    p++;
+    current_path_size = ioptions.cf_paths[p].target_size;
+  }
+  return p;
+}
+
+bool LevelCompactionBuilder::PickFileToCompact() {
+  // level 0 files are overlapping. So we cannot pick more
+  // than one concurrent compactions at this level. This
+  // could be made better by looking at key-ranges that are
+  // being compacted at level 0.
+  if (start_level_ == 0 &&
+      !compaction_picker_->level0_compactions_in_progress()->empty()) {
+    TEST_SYNC_POINT("LevelCompactionPicker::PickCompactionBySize:0");
+    return false;
+  }
+
+  start_level_inputs_.clear();
+
+  assert(start_level_ >= 0);
+
+  // Pick the largest file in this level that is not already
+  // being compacted
+  const std::vector<int>& file_size =
+      vstorage_->FilesByCompactionPri(start_level_);
+  const std::vector<FileMetaData*>& level_files =
+      vstorage_->LevelFiles(start_level_);
+
+  unsigned int cmp_idx;
+  for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
+       cmp_idx < file_size.size(); cmp_idx++) {
+    int index = file_size[cmp_idx];
+    auto* f = level_files[index];
+
+    // do not pick a file to compact if it is being compacted
+    // from n-1 level.
+    if (f->being_compacted) {
+      continue;
+    }
+
+    start_level_inputs_.files.push_back(f);
+    start_level_inputs_.level = start_level_;
+    if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                    &start_level_inputs_) ||
+        compaction_picker_->FilesRangeOverlapWithCompaction(
+            {start_level_inputs_}, output_level_)) {
+      // A locked (pending compaction) input-level file was pulled in due to
+      // user-key overlap.
+      start_level_inputs_.clear();
+      continue;
+    }
+
+    // Now that input level is fully expanded, we check whether any output files
+    // are locked due to pending compaction.
+    //
+    // Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
+    // level files are locked, not just the extra ones pulled in for user-key
+    // overlap.
+    InternalKey smallest, largest;
+    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
+    CompactionInputFiles output_level_inputs;
+    output_level_inputs.level = output_level_;
+    vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
+                                    &output_level_inputs.files);
+    if (!output_level_inputs.empty() &&
+        !compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                    &output_level_inputs)) {
+      start_level_inputs_.clear();
+      continue;
+    }
+    base_index_ = index;
+    break;
+  }
+
+  // store where to start the iteration in the next call to PickCompaction
+  vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
+
+  return start_level_inputs_.size() > 0;
+}
+
+bool LevelCompactionBuilder::PickIntraL0Compaction() {
+  start_level_inputs_.clear();
+  const std::vector<FileMetaData*>& level_files =
+      vstorage_->LevelFiles(0 /* level */);
+  if (level_files.size() <
+          static_cast<size_t>(
+              mutable_cf_options_.level0_file_num_compaction_trigger + 2) ||
+      level_files[0]->being_compacted) {
+    // If L0 isn't accumulating much files beyond the regular trigger, don't
+    // resort to L0->L0 compaction yet.
+    return false;
+  }
+  return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
+                               port::kMaxUint64, &start_level_inputs_);
+}
+}  // namespace
+
+Compaction* LevelCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
+                                 mutable_cf_options, ioptions_);
+  return builder.PickCompaction();
+}
+
 }  // namespace rocksdb
@@ -15,7 +15,7 @@
 #include <unordered_set>
 #include <vector>

-#include "db/compaction/compaction.h"
+#include "db/compaction.h"
 #include "db/version_set.h"
 #include "options/cf_options.h"
 #include "rocksdb/env.h"
@@ -24,26 +24,11 @@

 namespace rocksdb {

-// The file contains an abstract class CompactionPicker, and its two
-// sub-classes LevelCompactionPicker and NullCompactionPicker, as
-// well as some helper functions used by them.
-
 class LogBuffer;
 class Compaction;
 class VersionStorageInfo;
 struct CompactionInputFiles;

-// An abstract class to pick compactions from an existing LSM-tree.
-//
-// Each compaction style inherits the class and implement the
-// interface to form automatic compactions. If NeedCompaction() is true,
-// then call PickCompaction() to find what files need to be compacted
-// and where to put the output files.
-//
-// Non-virtual functions CompactRange() and CompactFiles() are used to
-// pick files to compact based on users' DB::CompactRange() and
-// DB::CompactFiles() requests, respectively. There is little
-// compaction style specific logic for them.
 class CompactionPicker {
 public:
  CompactionPicker(const ImmutableCFOptions& ioptions,
@@ -73,10 +58,9 @@ class CompactionPicker {
  virtual Compaction* CompactRange(
      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
      VersionStorageInfo* vstorage, int input_level, int output_level,
-      const CompactRangeOptions& compact_range_options,
+      uint32_t output_path_id, uint32_t max_subcompactions,
      const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore);
+      InternalKey** compaction_end, bool* manual_conflict);

  // The maximum allowed output level.  Default value is NumberLevels() - 1.
  virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
@@ -236,9 +220,21 @@ class CompactionPicker {
  const InternalKeyComparator* const icmp_;
 };

+class LevelCompactionPicker : public CompactionPicker {
+ public:
+  LevelCompactionPicker(const ImmutableCFOptions& ioptions,
+                        const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+};
+
 #ifndef ROCKSDB_LITE
-// A dummy compaction that never triggers any automatic
-// compaction.
 class NullCompactionPicker : public CompactionPicker {
 public:
  NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -259,12 +255,12 @@ class NullCompactionPicker : public CompactionPicker {
                           const MutableCFOptions& /*mutable_cf_options*/,
                           VersionStorageInfo* /*vstorage*/,
                           int /*input_level*/, int /*output_level*/,
-                           const CompactRangeOptions& /*compact_range_options*/,
+                           uint32_t /*output_path_id*/,
+                           uint32_t /*max_subcompactions*/,
                           const InternalKey* /*begin*/,
                           const InternalKey* /*end*/,
                           InternalKey** /*compaction_end*/,
-                           bool* /*manual_conflict*/,
-                           uint64_t /*max_file_num_to_ignore*/) override {
+                           bool* /*manual_conflict*/) override {
    return nullptr;
  }

@@ -276,26 +272,9 @@ class NullCompactionPicker : public CompactionPicker {
 };
 #endif  // !ROCKSDB_LITE

-// Attempts to find an intra L0 compaction conforming to the given parameters.
-//
-// @param level_files                     Metadata for L0 files.
-// @param min_files_to_compact            Minimum number of files required to
-//                                        do the compaction.
-// @param max_compact_bytes_per_del_file  Maximum average size in bytes per
-//                                        file that is going to get deleted by
-//                                        the compaction.
-// @param max_compaction_bytes            Maximum total size in bytes (in terms
-//                                        of compensated file size) for files
-//                                        to be compacted.
-// @param [out] comp_inputs               If a compaction was found, will be
-//                                        initialized with corresponding input
-//                                        files. Cannot be nullptr.
-//
-// @return                                true iff compaction was found.
 bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                           size_t min_files_to_compact,
                           uint64_t max_compact_bytes_per_del_file,
-                           uint64_t max_compaction_bytes,
                           CompactionInputFiles* comp_inputs);

 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
@@ -7,14 +7,18 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

-#include "db/compaction/compaction_picker_fifo.h"
+#include "db/compaction_picker_fifo.h"
 #ifndef ROCKSDB_LITE

-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <string>
 #include <vector>
 #include "db/column_family.h"
-#include "logging/log_buffer.h"
+#include "util/log_buffer.h"
 #include "util/string_util.h"

 namespace rocksdb {
@@ -37,7 +41,7 @@ bool FIFOCompactionPicker::NeedsCompaction(
 Compaction* FIFOCompactionPicker::PickTTLCompaction(
    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(mutable_cf_options.ttl > 0);
+  assert(mutable_cf_options.compaction_options_fifo.ttl > 0);

  const int kLevel0 = 0;
  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
@@ -54,21 +58,12 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
  }
  const uint64_t current_time = static_cast<uint64_t>(_current_time);

-  if (!level0_compactions_in_progress_.empty()) {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: Already executing compaction. No need "
-        "to run parallel compactions since compactions are very fast",
-        cf_name.c_str());
-    return nullptr;
-  }
-
  std::vector<CompactionInputFiles> inputs;
  inputs.emplace_back();
  inputs[0].level = 0;

  // avoid underflow
-  if (current_time > mutable_cf_options.ttl) {
+  if (current_time > mutable_cf_options.compaction_options_fifo.ttl) {
    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
      auto f = *ritr;
      if (f->fd.table_reader != nullptr &&
@@ -76,7 +71,8 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
        auto creation_time =
            f->fd.table_reader->GetTableProperties()->creation_time;
        if (creation_time == 0 ||
-            creation_time >= (current_time - mutable_cf_options.ttl)) {
+            creation_time >= (current_time -
+                              mutable_cf_options.compaction_options_fifo.ttl)) {
          break;
        }
        total_size -= f->compensated_file_size;
@@ -139,8 +135,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
              mutable_cf_options
                  .level0_file_num_compaction_trigger /* min_files_to_compact */
              ,
-              max_compact_bytes_per_del_file,
-              mutable_cf_options.max_compaction_bytes, &comp_inputs)) {
+              max_compact_bytes_per_del_file, &comp_inputs)) {
        Compaction* c = new Compaction(
            vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
            16 * 1024 * 1024 /* output file size limit */,
@@ -206,7 +201,7 @@ Compaction* FIFOCompactionPicker::PickCompaction(
  assert(vstorage->num_levels() == 1);

  Compaction* c = nullptr;
-  if (mutable_cf_options.ttl > 0) {
+  if (mutable_cf_options.compaction_options_fifo.ttl > 0) {
    c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
  }
  if (c == nullptr) {
@@ -219,10 +214,9 @@ Compaction* FIFOCompactionPicker::PickCompaction(
 Compaction* FIFOCompactionPicker::CompactRange(
    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
    VersionStorageInfo* vstorage, int input_level, int output_level,
-    const CompactRangeOptions& /*compact_range_options*/,
+    uint32_t /*output_path_id*/, uint32_t /*max_subcompactions*/,
    const InternalKey* /*begin*/, const InternalKey* /*end*/,
-    InternalKey** compaction_end, bool* /*manual_conflict*/,
-    uint64_t /*max_file_num_to_ignore*/) {
+    InternalKey** compaction_end, bool* /*manual_conflict*/) {
 #ifdef NDEBUG
  (void)input_level;
  (void)output_level;
@@ -10,7 +10,7 @@
 #pragma once
 #ifndef ROCKSDB_LITE

-#include "db/compaction/compaction_picker.h"
+#include "db/compaction_picker.h"

 namespace rocksdb {
 class FIFOCompactionPicker : public CompactionPicker {
@@ -27,10 +27,9 @@ class FIFOCompactionPicker : public CompactionPicker {
  virtual Compaction* CompactRange(
      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
      VersionStorageInfo* vstorage, int input_level, int output_level,
-      const CompactRangeOptions& compact_range_options,
+      uint32_t output_path_id, uint32_t max_subcompactions,
      const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore) override;
+      InternalKey** compaction_end, bool* manual_conflict) override;

  // The maximum allowed output level.  Always returns 0.
  virtual int MaxOutputLevel() const override { return 0; }
@@ -3,26 +3,28 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

+#include "db/compaction_picker.h"

 #include <limits>
 #include <string>
 #include <utility>
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
+#include "db/compaction.h"
+#include "db/compaction_picker_fifo.h"
+#include "db/compaction_picker_universal.h"

-#include "logging/logging.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/logging.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"

 namespace rocksdb {

 class CountingLogger : public Logger {
 public:
  using Logger::Logv;
-  void Logv(const char* /*format*/, va_list /*ap*/) override { log_count++; }
+  virtual void Logv(const char* /*format*/, va_list /*ap*/) override {
+    log_count++;
+  }
  size_t log_count;
 };

@@ -66,7 +68,8 @@ class CompactionPickerTest : public testing::Test {
                                    std::numeric_limits<uint64_t>::max());
  }

-  ~CompactionPickerTest() override {}
+  ~CompactionPickerTest() {
+  }

  void NewVersionStorage(int num_levels, CompactionStyle style) {
    DeleteVersionStorage();
@@ -1478,65 +1481,6 @@ TEST_F(CompactionPickerTest, CacheNextCompactionIndex) {
  ASSERT_EQ(4, vstorage_->NextCompactionIndex(1 /* level */));
 }

-TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesNotHit) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 1000000u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // All 5 L0 files will be picked for intra L0 compaction. The one L1 file
-  // spans entire L0 key range and is marked as being compacted to avoid
-  // L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U);
-  Add(0, 2U, "151", "200", 200000U);
-  Add(0, 3U, "201", "250", 200000U);
-  Add(0, 4U, "251", "300", 200000U);
-  Add(0, 5U, "301", "350", 200000U);
-  Add(1, 6U, "100", "350", 200000U);
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(5U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesHit) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 999999u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // 4 out of 5 L0 files will be picked for intra L0 compaction due to
-  // max_compaction_bytes limit (the minimum number of files for triggering
-  // intra L0 compaction is 4). The one L1 file spans entire L0 key range and
-  // is marked as being compacted to avoid L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U);
-  Add(0, 2U, "151", "200", 200000U);
-  Add(0, 3U, "201", "250", 200000U);
-  Add(0, 4U, "251", "300", 200000U);
-  Add(0, 5U, "301", "350", 200000U);
-  Add(1, 6U, "100", "350", 200000U);
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(4U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -7,116 +7,28 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

-#include "db/compaction/compaction_picker_universal.h"
+#include "db/compaction_picker_universal.h"
 #ifndef ROCKSDB_LITE

-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <limits>
 #include <queue>
 #include <string>
 #include <utility>
 #include "db/column_family.h"
-#include "file/filename.h"
-#include "logging/log_buffer.h"
 #include "monitoring/statistics.h"
-#include "test_util/sync_point.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
 #include "util/random.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"

 namespace rocksdb {
 namespace {
-// A helper class that form universal compactions. The class is used by
-// UniversalCompactionPicker::PickCompaction().
-// The usage is to create the class, and get the compaction object by calling
-// PickCompaction().
-class UniversalCompactionBuilder {
- public:
-  UniversalCompactionBuilder(const ImmutableCFOptions& ioptions,
-                             const InternalKeyComparator* icmp,
-                             const std::string& cf_name,
-                             const MutableCFOptions& mutable_cf_options,
-                             VersionStorageInfo* vstorage,
-                             UniversalCompactionPicker* picker,
-                             LogBuffer* log_buffer)
-      : ioptions_(ioptions),
-        icmp_(icmp),
-        cf_name_(cf_name),
-        mutable_cf_options_(mutable_cf_options),
-        vstorage_(vstorage),
-        picker_(picker),
-        log_buffer_(log_buffer) {}
-
-  // Form and return the compaction object. The caller owns return object.
-  Compaction* PickCompaction();
-
- private:
-  struct SortedRun {
-    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
-              uint64_t _compensated_file_size, bool _being_compacted)
-        : level(_level),
-          file(_file),
-          size(_size),
-          compensated_file_size(_compensated_file_size),
-          being_compacted(_being_compacted) {
-      assert(compensated_file_size > 0);
-      assert(level != 0 || file != nullptr);
-    }
-
-    void Dump(char* out_buf, size_t out_buf_size,
-              bool print_path = false) const;
-
-    // sorted_run_count is added into the string to print
-    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
-                      size_t sorted_run_count) const;
-
-    int level;
-    // `file` Will be null for level > 0. For level = 0, the sorted run is
-    // for this file.
-    FileMetaData* file;
-    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
-    // files in the level. `being_compacted` should be the same for all files
-    // in a non-zero level. Use the value here.
-    uint64_t size;
-    uint64_t compensated_file_size;
-    bool being_compacted;
-  };
-
-  // Pick Universal compaction to limit read amplification
-  Compaction* PickCompactionToReduceSortedRuns(
-      unsigned int ratio, unsigned int max_number_of_files_to_compact);
-
-  // Pick Universal compaction to limit space amplification.
-  Compaction* PickCompactionToReduceSizeAmp();
-
-  Compaction* PickDeleteTriggeredCompaction();
-
-  // Used in universal compaction when the enabled_trivial_move
-  // option is set. Checks whether there are any overlapping files
-  // in the input. Returns true if the input files are non
-  // overlapping.
-  bool IsInputFilesNonOverlapping(Compaction* c);
-
-  const ImmutableCFOptions& ioptions_;
-  const InternalKeyComparator* icmp_;
-  double score_;
-  std::vector<SortedRun> sorted_runs_;
-  const std::string& cf_name_;
-  const MutableCFOptions& mutable_cf_options_;
-  VersionStorageInfo* vstorage_;
-  UniversalCompactionPicker* picker_;
-  LogBuffer* log_buffer_;
-
-  static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
-      const MutableCFOptions& mutable_cf_options);
-
-  // Pick a path ID to place a newly generated file, with its estimated file
-  // size.
-  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
-                            const MutableCFOptions& mutable_cf_options,
-                            uint64_t file_size);
-};
-
 // 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
@@ -205,7 +117,7 @@ void GetSmallestLargestSeqno(const std::vector<FileMetaData*>& files,

 // Algorithm that checks to see if there are any overlapping
 // files in the input
-bool UniversalCompactionBuilder::IsInputFilesNonOverlapping(Compaction* c) {
+bool UniversalCompactionPicker::IsInputFilesNonOverlapping(Compaction* c) {
  auto comparator = icmp_->user_comparator();
  int first_iter = 1;

@@ -259,18 +171,9 @@ bool UniversalCompactionPicker::NeedsCompaction(
  return false;
 }

-Compaction* UniversalCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  UniversalCompactionBuilder builder(ioptions_, icmp_, cf_name,
-                                     mutable_cf_options, vstorage, this,
-                                     log_buffer);
-  return builder.PickCompaction();
-}
-
-void UniversalCompactionBuilder::SortedRun::Dump(char* out_buf,
-                                                 size_t out_buf_size,
-                                                 bool print_path) const {
+void UniversalCompactionPicker::SortedRun::Dump(char* out_buf,
+                                                size_t out_buf_size,
+                                                bool print_path) const {
  if (level == 0) {
    assert(file != nullptr);
    if (file->fd.GetPathId() == 0 || !print_path) {
@@ -286,7 +189,7 @@ void UniversalCompactionBuilder::SortedRun::Dump(char* out_buf,
  }
 }

-void UniversalCompactionBuilder::SortedRun::DumpSizeInfo(
+void UniversalCompactionPicker::SortedRun::DumpSizeInfo(
    char* out_buf, size_t out_buf_size, size_t sorted_run_count) const {
  if (level == 0) {
    assert(file != nullptr);
@@ -305,11 +208,11 @@ void UniversalCompactionBuilder::SortedRun::DumpSizeInfo(
  }
 }

-std::vector<UniversalCompactionBuilder::SortedRun>
-UniversalCompactionBuilder::CalculateSortedRuns(
+std::vector<UniversalCompactionPicker::SortedRun>
+UniversalCompactionPicker::CalculateSortedRuns(
    const VersionStorageInfo& vstorage, const ImmutableCFOptions& /*ioptions*/,
    const MutableCFOptions& mutable_cf_options) {
-  std::vector<UniversalCompactionBuilder::SortedRun> ret;
+  std::vector<UniversalCompactionPicker::SortedRun> ret;
  for (FileMetaData* f : vstorage.LevelFiles(0)) {
    ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
                     f->being_compacted);
@@ -332,8 +235,8 @@ UniversalCompactionBuilder::CalculateSortedRuns(
        // non-zero level, all the files should share the same being_compacted
        // value.
        // This assumption is only valid when
-        // mutable_cf_options.compaction_options_universal.allow_trivial_move
-        // is false
+        // mutable_cf_options.compaction_options_universal.allow_trivial_move is
+        // false
        assert(is_first || f->being_compacted == being_compacted);
      }
      if (is_first) {
@@ -351,59 +254,65 @@ UniversalCompactionBuilder::CalculateSortedRuns(

 // Universal style of compaction. Pick files that are contiguous in
 // time-range to compact.
-Compaction* UniversalCompactionBuilder::PickCompaction() {
+Compaction* UniversalCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
  const int kLevel0 = 0;
-  score_ = vstorage_->CompactionScore(kLevel0);
-  sorted_runs_ =
-      CalculateSortedRuns(*vstorage_, ioptions_, mutable_cf_options_);
+  double score = vstorage->CompactionScore(kLevel0);
+  std::vector<SortedRun> sorted_runs =
+      CalculateSortedRuns(*vstorage, ioptions_, mutable_cf_options);

-  if (sorted_runs_.size() == 0 ||
-      (vstorage_->FilesMarkedForCompaction().empty() &&
-       sorted_runs_.size() < (unsigned int)mutable_cf_options_
-                                 .level0_file_num_compaction_trigger)) {
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: nothing to do\n",
-                     cf_name_.c_str());
-    TEST_SYNC_POINT_CALLBACK(
-        "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
+  if (sorted_runs.size() == 0 ||
+      (vstorage->FilesMarkedForCompaction().empty() &&
+       sorted_runs.size() < (unsigned int)mutable_cf_options
+                                .level0_file_num_compaction_trigger)) {
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: nothing to do\n",
+                     cf_name.c_str());
+    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
+                             nullptr);
    return nullptr;
  }
  VersionStorageInfo::LevelSummaryStorage tmp;
  ROCKS_LOG_BUFFER_MAX_SZ(
-      log_buffer_, 3072,
+      log_buffer, 3072,
      "[%s] Universal: sorted runs files(%" ROCKSDB_PRIszt "): %s\n",
-      cf_name_.c_str(), sorted_runs_.size(), vstorage_->LevelSummary(&tmp));
+      cf_name.c_str(), sorted_runs.size(), vstorage->LevelSummary(&tmp));

  // Check for size amplification first.
  Compaction* c = nullptr;
-  if (sorted_runs_.size() >=
+  if (sorted_runs.size() >=
      static_cast<size_t>(
-          mutable_cf_options_.level0_file_num_compaction_trigger)) {
-    if ((c = PickCompactionToReduceSizeAmp()) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: compacting for size amp\n",
-                       cf_name_.c_str());
+          mutable_cf_options.level0_file_num_compaction_trigger)) {
+    if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options,
+                                           vstorage, score, sorted_runs,
+                                           log_buffer)) != nullptr) {
+      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
+                       cf_name.c_str());
    } else {
      // Size amplification is within limits. Try reducing read
      // amplification while maintaining file size ratios.
      unsigned int ratio =
-          mutable_cf_options_.compaction_options_universal.size_ratio;
+          mutable_cf_options.compaction_options_universal.size_ratio;

-      if ((c = PickCompactionToReduceSortedRuns(ratio, UINT_MAX)) != nullptr) {
-        ROCKS_LOG_BUFFER(log_buffer_,
+      if ((c = PickCompactionToReduceSortedRuns(
+               cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
+               sorted_runs, log_buffer)) != nullptr) {
+        ROCKS_LOG_BUFFER(log_buffer,
                         "[%s] Universal: compacting for size ratio\n",
-                         cf_name_.c_str());
+                         cf_name.c_str());
      } else {
        // Size amplification and file size ratios are within configured limits.
        // If max read amplification is exceeding configured limits, then force
        // compaction without looking at filesize ratios and try to reduce
        // the number of files to fewer than level0_file_num_compaction_trigger.
        // This is guaranteed by NeedsCompaction()
-        assert(sorted_runs_.size() >=
+        assert(sorted_runs.size() >=
               static_cast<size_t>(
-                   mutable_cf_options_.level0_file_num_compaction_trigger));
+                   mutable_cf_options.level0_file_num_compaction_trigger));
        // Get the total number of sorted runs that are not being compacted
        int num_sr_not_compacted = 0;
-        for (size_t i = 0; i < sorted_runs_.size(); i++) {
-          if (sorted_runs_[i].being_compacted == false) {
+        for (size_t i = 0; i < sorted_runs.size(); i++) {
+          if (sorted_runs[i].being_compacted == false) {
            num_sr_not_compacted++;
          }
        }
@@ -411,15 +320,16 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
        // The number of sorted runs that are not being compacted is greater
        // than the maximum allowed number of sorted runs
        if (num_sr_not_compacted >
-            mutable_cf_options_.level0_file_num_compaction_trigger) {
+            mutable_cf_options.level0_file_num_compaction_trigger) {
          unsigned int num_files =
              num_sr_not_compacted -
-              mutable_cf_options_.level0_file_num_compaction_trigger + 1;
-          if ((c = PickCompactionToReduceSortedRuns(UINT_MAX, num_files)) !=
-              nullptr) {
-            ROCKS_LOG_BUFFER(log_buffer_,
+              mutable_cf_options.level0_file_num_compaction_trigger + 1;
+          if ((c = PickCompactionToReduceSortedRuns(
+                   cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
+                   num_files, sorted_runs, log_buffer)) != nullptr) {
+            ROCKS_LOG_BUFFER(log_buffer,
                             "[%s] Universal: compacting for file num -- %u\n",
-                             cf_name_.c_str(), num_files);
+                             cf_name.c_str(), num_files);
          }
        }
      }
@@ -427,20 +337,22 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
  }

  if (c == nullptr) {
-    if ((c = PickDeleteTriggeredCompaction()) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer_,
+    if ((c = PickDeleteTriggeredCompaction(cf_name, mutable_cf_options,
+                                           vstorage, score, sorted_runs,
+                                           log_buffer)) != nullptr) {
+      ROCKS_LOG_BUFFER(log_buffer,
                       "[%s] Universal: delete triggered compaction\n",
-                       cf_name_.c_str());
+                       cf_name.c_str());
    }
  }

  if (c == nullptr) {
-    TEST_SYNC_POINT_CALLBACK(
-        "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
+    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
+                             nullptr);
    return nullptr;
  }

-  if (mutable_cf_options_.compaction_options_universal.allow_trivial_move ==
+  if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
      true) {
    c->set_is_trivial_move(IsInputFilesNonOverlapping(c));
  }
@@ -483,18 +395,18 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
  }
 #endif
  // update statistics
-  RecordInHistogram(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
-                    c->inputs(0)->size());
+  MeasureTime(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
+              c->inputs(0)->size());

-  picker_->RegisterCompaction(c);
-  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
+  RegisterCompaction(c);
+  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);

-  TEST_SYNC_POINT_CALLBACK("UniversalCompactionBuilder::PickCompaction:Return",
+  TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
                           c);
  return c;
 }

-uint32_t UniversalCompactionBuilder::GetPathId(
+uint32_t UniversalCompactionPicker::GetPathId(
    const ImmutableCFOptions& ioptions,
    const MutableCFOptions& mutable_cf_options, uint64_t file_size) {
  // Two conditions need to be satisfied:
@@ -532,12 +444,15 @@ uint32_t UniversalCompactionBuilder::GetPathId(
 // Consider compaction files based on their size differences with
 // the next file in time order.
 //
-Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
-    unsigned int ratio, unsigned int max_number_of_files_to_compact) {
+Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, double score, unsigned int ratio,
+    unsigned int max_number_of_files_to_compact,
+    const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
  unsigned int min_merge_width =
-      mutable_cf_options_.compaction_options_universal.min_merge_width;
+      mutable_cf_options.compaction_options_universal.min_merge_width;
  unsigned int max_merge_width =
-      mutable_cf_options_.compaction_options_universal.max_merge_width;
+      mutable_cf_options.compaction_options_universal.max_merge_width;

  const SortedRun* sr = nullptr;
  bool done = false;
@@ -551,16 +466,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
  // Caller checks the size before executing this function. This invariant is
  // important because otherwise we may have a possible integer underflow when
  // dealing with unsigned types.
-  assert(sorted_runs_.size() > 0);
+  assert(sorted_runs.size() > 0);

  // Considers a candidate file only if it is smaller than the
  // total size accumulated so far.
-  for (size_t loop = 0; loop < sorted_runs_.size(); loop++) {
+  for (size_t loop = 0; loop < sorted_runs.size(); loop++) {
    candidate_count = 0;

    // Skip files that are already being compacted
-    for (sr = nullptr; loop < sorted_runs_.size(); loop++) {
-      sr = &sorted_runs_[loop];
+    for (sr = nullptr; loop < sorted_runs.size(); loop++) {
+      sr = &sorted_runs[loop];

      if (!sr->being_compacted) {
        candidate_count = 1;
@@ -568,10 +483,10 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
      }
      char file_num_buf[kFormatFileNumberBufSize];
      sr->Dump(file_num_buf, sizeof(file_num_buf));
-      ROCKS_LOG_BUFFER(log_buffer_,
+      ROCKS_LOG_BUFFER(log_buffer,
                       "[%s] Universal: %s"
                       "[%d] being compacted, skipping",
-                       cf_name_.c_str(), file_num_buf, loop);
+                       cf_name.c_str(), file_num_buf, loop);

      sr = nullptr;
    }
@@ -582,16 +497,15 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
    if (sr != nullptr) {
      char file_num_buf[kFormatFileNumberBufSize];
      sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: Possible candidate %s[%d].",
-                       cf_name_.c_str(), file_num_buf, loop);
+      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Possible candidate %s[%d].",
+                       cf_name.c_str(), file_num_buf, loop);
    }

    // Check if the succeeding files need compaction.
    for (size_t i = loop + 1;
-         candidate_count < max_files_to_compact && i < sorted_runs_.size();
+         candidate_count < max_files_to_compact && i < sorted_runs.size();
         i++) {
-      const SortedRun* succeeding_sr = &sorted_runs_[i];
+      const SortedRun* succeeding_sr = &sorted_runs[i];
      if (succeeding_sr->being_compacted) {
        break;
      }
@@ -605,7 +519,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
      if (sz < static_cast<double>(succeeding_sr->size)) {
        break;
      }
-      if (mutable_cf_options_.compaction_options_universal.stop_style ==
+      if (mutable_cf_options.compaction_options_universal.stop_style ==
          kCompactionStopStyleSimilarSize) {
        // Similar-size stopping rule: also check the last picked file isn't
        // far larger than the next candidate file.
@@ -631,12 +545,12 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
      break;
    } else {
      for (size_t i = loop;
-           i < loop + candidate_count && i < sorted_runs_.size(); i++) {
-        const SortedRun* skipping_sr = &sorted_runs_[i];
+           i < loop + candidate_count && i < sorted_runs.size(); i++) {
+        const SortedRun* skipping_sr = &sorted_runs[i];
        char file_num_buf[256];
        skipping_sr->DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
-        ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: Skipping %s",
-                         cf_name_.c_str(), file_num_buf);
+        ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Skipping %s",
+                         cf_name.c_str(), file_num_buf);
      }
    }
  }
@@ -648,16 +562,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
  // size ratio of compression.
  bool enable_compression = true;
  int ratio_to_compress =
-      mutable_cf_options_.compaction_options_universal.compression_size_percent;
+      mutable_cf_options.compaction_options_universal.compression_size_percent;
  if (ratio_to_compress >= 0) {
    uint64_t total_size = 0;
-    for (auto& sorted_run : sorted_runs_) {
+    for (auto& sorted_run : sorted_runs) {
      total_size += sorted_run.compensated_file_size;
    }

    uint64_t older_file_size = 0;
-    for (size_t i = sorted_runs_.size() - 1; i >= first_index_after; i--) {
-      older_file_size += sorted_runs_[i].size;
+    for (size_t i = sorted_runs.size() - 1; i >= first_index_after; i--) {
+      older_file_size += sorted_runs[i].size;
      if (older_file_size * 100L >= total_size * (long)ratio_to_compress) {
        enable_compression = false;
        break;
@@ -667,46 +581,46 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(

  uint64_t estimated_total_size = 0;
  for (unsigned int i = 0; i < first_index_after; i++) {
-    estimated_total_size += sorted_runs_[i].size;
+    estimated_total_size += sorted_runs[i].size;
  }
  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
-  int start_level = sorted_runs_[start_index].level;
+      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
+  int start_level = sorted_runs[start_index].level;
  int output_level;
-  if (first_index_after == sorted_runs_.size()) {
-    output_level = vstorage_->num_levels() - 1;
-  } else if (sorted_runs_[first_index_after].level == 0) {
+  if (first_index_after == sorted_runs.size()) {
+    output_level = vstorage->num_levels() - 1;
+  } else if (sorted_runs[first_index_after].level == 0) {
    output_level = 0;
  } else {
-    output_level = sorted_runs_[first_index_after].level - 1;
+    output_level = sorted_runs[first_index_after].level - 1;
  }

  // last level is reserved for the files ingested behind
  if (ioptions_.allow_ingest_behind &&
-      (output_level == vstorage_->num_levels() - 1)) {
+      (output_level == vstorage->num_levels() - 1)) {
    assert(output_level > 1);
    output_level--;
  }

-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
  for (size_t i = 0; i < inputs.size(); ++i) {
    inputs[i].level = start_level + static_cast<int>(i);
  }
  for (size_t i = start_index; i < first_index_after; i++) {
-    auto& picking_sr = sorted_runs_[i];
+    auto& picking_sr = sorted_runs[i];
    if (picking_sr.level == 0) {
      FileMetaData* picking_file = picking_sr.file;
      inputs[0].files.push_back(picking_file);
    } else {
      auto& files = inputs[picking_sr.level - start_level].files;
-      for (auto* f : vstorage_->LevelFiles(picking_sr.level)) {
+      for (auto* f : vstorage->LevelFiles(picking_sr.level)) {
        files.push_back(f);
      }
    }
    char file_num_buf[256];
    picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), i);
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: Picking %s",
-                     cf_name_.c_str(), file_num_buf);
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Picking %s", cf_name.c_str(),
+                     file_num_buf);
  }

  CompactionReason compaction_reason;
@@ -716,17 +630,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
    compaction_reason = CompactionReason::kUniversalSortedRunNum;
  }
  return new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(inputs),
-      output_level,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level,
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options, output_level,
                          kCompactionStyleUniversal),
      LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_, start_level,
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options, start_level,
                         1, enable_compression),
-      GetCompressionOptions(ioptions_, vstorage_, start_level,
+      GetCompressionOptions(ioptions_, vstorage, start_level,
                            enable_compression),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      score_, false /* deletion_compaction */, compaction_reason);
+      score, false /* deletion_compaction */, compaction_reason);
 }

 // Look at overall size amplification. If size amplification
@@ -735,9 +648,12 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
 // base file (overrides configured values of file-size ratios,
 // min_merge_width and max_merge_width).
 //
-Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
+Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, double score,
+    const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
  // percentage flexibility while reducing size amplification
-  uint64_t ratio = mutable_cf_options_.compaction_options_universal
+  uint64_t ratio = mutable_cf_options.compaction_options_universal
                       .max_size_amplification_percent;

  unsigned int candidate_count = 0;
@@ -745,23 +661,21 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
  size_t start_index = 0;
  const SortedRun* sr = nullptr;

-  assert(!sorted_runs_.empty());
-  if (sorted_runs_.back().being_compacted) {
+  if (sorted_runs.back().being_compacted) {
    return nullptr;
  }

  // Skip files that are already being compacted
-  for (size_t loop = 0; loop < sorted_runs_.size() - 1; loop++) {
-    sr = &sorted_runs_[loop];
+  for (size_t loop = 0; loop < sorted_runs.size() - 1; loop++) {
+    sr = &sorted_runs[loop];
    if (!sr->being_compacted) {
      start_index = loop;  // Consider this as the first candidate.
      break;
    }
    char file_num_buf[kFormatFileNumberBufSize];
    sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-    ROCKS_LOG_BUFFER(log_buffer_,
-                     "[%s] Universal: skipping %s[%d] compacted %s",
-                     cf_name_.c_str(), file_num_buf, loop,
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: skipping %s[%d] compacted %s",
+                     cf_name.c_str(), file_num_buf, loop,
                     " cannot be a candidate to reduce size amp.\n");
    sr = nullptr;
  }
@@ -773,20 +687,20 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
    char file_num_buf[kFormatFileNumberBufSize];
    sr->Dump(file_num_buf, sizeof(file_num_buf), true);
    ROCKS_LOG_BUFFER(
-        log_buffer_,
+        log_buffer,
        "[%s] Universal: First candidate %s[%" ROCKSDB_PRIszt "] %s",
-        cf_name_.c_str(), file_num_buf, start_index, " to reduce size amp.\n");
+        cf_name.c_str(), file_num_buf, start_index, " to reduce size amp.\n");
  }

  // keep adding up all the remaining files
-  for (size_t loop = start_index; loop < sorted_runs_.size() - 1; loop++) {
-    sr = &sorted_runs_[loop];
+  for (size_t loop = start_index; loop < sorted_runs.size() - 1; loop++) {
+    sr = &sorted_runs[loop];
    if (sr->being_compacted) {
      char file_num_buf[kFormatFileNumberBufSize];
      sr->Dump(file_num_buf, sizeof(file_num_buf), true);
      ROCKS_LOG_BUFFER(
-          log_buffer_, "[%s] Universal: Possible candidate %s[%d] %s",
-          cf_name_.c_str(), file_num_buf, start_index,
+          log_buffer, "[%s] Universal: Possible candidate %s[%d] %s",
+          cf_name.c_str(), file_num_buf, start_index,
          " is already being compacted. No size amp reduction possible.\n");
      return nullptr;
    }
@@ -798,58 +712,58 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
  }

  // size of earliest file
-  uint64_t earliest_file_size = sorted_runs_.back().size;
+  uint64_t earliest_file_size = sorted_runs.back().size;

  // size amplification = percentage of additional size
  if (candidate_size * 100 < ratio * earliest_file_size) {
    ROCKS_LOG_BUFFER(
-        log_buffer_,
+        log_buffer,
        "[%s] Universal: size amp not needed. newer-files-total-size %" PRIu64
        " earliest-file-size %" PRIu64,
-        cf_name_.c_str(), candidate_size, earliest_file_size);
+        cf_name.c_str(), candidate_size, earliest_file_size);
    return nullptr;
  } else {
    ROCKS_LOG_BUFFER(
-        log_buffer_,
+        log_buffer,
        "[%s] Universal: size amp needed. newer-files-total-size %" PRIu64
        " earliest-file-size %" PRIu64,
-        cf_name_.c_str(), candidate_size, earliest_file_size);
+        cf_name.c_str(), candidate_size, earliest_file_size);
  }
-  assert(start_index < sorted_runs_.size() - 1);
+  assert(start_index < sorted_runs.size() - 1);

  // Estimate total file size
  uint64_t estimated_total_size = 0;
-  for (size_t loop = start_index; loop < sorted_runs_.size(); loop++) {
-    estimated_total_size += sorted_runs_[loop].size;
+  for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
+    estimated_total_size += sorted_runs[loop].size;
  }
  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
-  int start_level = sorted_runs_[start_index].level;
+      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
+  int start_level = sorted_runs[start_index].level;

-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
  for (size_t i = 0; i < inputs.size(); ++i) {
    inputs[i].level = start_level + static_cast<int>(i);
  }
  // We always compact all the files, so always compress.
-  for (size_t loop = start_index; loop < sorted_runs_.size(); loop++) {
-    auto& picking_sr = sorted_runs_[loop];
+  for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
+    auto& picking_sr = sorted_runs[loop];
    if (picking_sr.level == 0) {
      FileMetaData* f = picking_sr.file;
      inputs[0].files.push_back(f);
    } else {
      auto& files = inputs[picking_sr.level - start_level].files;
-      for (auto* f : vstorage_->LevelFiles(picking_sr.level)) {
+      for (auto* f : vstorage->LevelFiles(picking_sr.level)) {
        files.push_back(f);
      }
    }
    char file_num_buf[256];
    picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: size amp picking %s",
-                     cf_name_.c_str(), file_num_buf);
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: size amp picking %s",
+                     cf_name.c_str(), file_num_buf);
  }

  // output files at the bottom most level, unless it's reserved
-  int output_level = vstorage_->num_levels() - 1;
+  int output_level = vstorage->num_levels() - 1;
  // last level is reserved for the files ingested behind
  if (ioptions_.allow_ingest_behind) {
    assert(output_level > 1);
@@ -857,27 +771,29 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
  }

  return new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(inputs),
-      output_level,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level,
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options, output_level,
                          kCompactionStyleUniversal),
      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
-                         output_level, 1),
-      GetCompressionOptions(ioptions_, vstorage_, output_level),
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
+                         1),
+      GetCompressionOptions(ioptions_, vstorage, output_level),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      score_, false /* deletion_compaction */,
+      score, false /* deletion_compaction */,
      CompactionReason::kUniversalSizeAmplification);
 }

 // Pick files marked for compaction. Typically, files are marked by
 // CompactOnDeleteCollector due to the presence of tombstones.
-Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
+Compaction* UniversalCompactionPicker::PickDeleteTriggeredCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, double score,
+    const std::vector<SortedRun>& /*sorted_runs*/, LogBuffer* /*log_buffer*/) {
  CompactionInputFiles start_level_inputs;
  int output_level;
  std::vector<CompactionInputFiles> inputs;

-  if (vstorage_->num_levels() == 1) {
+  if (vstorage->num_levels() == 1) {
    // This is single level universal. Since we're basically trying to reclaim
    // space by processing files marked for compaction due to high tombstone
    // density, let's do the same thing as compaction to reduce size amp which
@@ -887,7 +803,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
    start_level_inputs.level = 0;
    start_level_inputs.files.clear();
    output_level = 0;
-    for (FileMetaData* f : vstorage_->LevelFiles(0)) {
+    for (FileMetaData* f : vstorage->LevelFiles(0)) {
      if (f->marked_for_compaction) {
        compact = true;
      }
@@ -906,24 +822,24 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
    // For multi-level universal, the strategy is to make this look more like
    // leveled. We pick one of the files marked for compaction and compact with
    // overlapping files in the adjacent level.
-    picker_->PickFilesMarkedForCompaction(cf_name_, vstorage_, &start_level,
-                                          &output_level, &start_level_inputs);
+    PickFilesMarkedForCompaction(cf_name, vstorage, &start_level, &output_level,
+                                 &start_level_inputs);
    if (start_level_inputs.empty()) {
      return nullptr;
    }

    // Pick the first non-empty level after the start_level
-    for (output_level = start_level + 1; output_level < vstorage_->num_levels();
+    for (output_level = start_level + 1; output_level < vstorage->num_levels();
         output_level++) {
-      if (vstorage_->NumLevelFiles(output_level) != 0) {
+      if (vstorage->NumLevelFiles(output_level) != 0) {
        break;
      }
    }

    // If all higher levels are empty, pick the highest level as output level
-    if (output_level == vstorage_->num_levels()) {
+    if (output_level == vstorage->num_levels()) {
      if (start_level == 0) {
-        output_level = vstorage_->num_levels() - 1;
+        output_level = vstorage->num_levels() - 1;
      } else {
        // If start level is non-zero and all higher levels are empty, this
        // compaction will translate into a trivial move. Since the idea is
@@ -933,15 +849,15 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
      }
    }
    if (ioptions_.allow_ingest_behind &&
-        output_level == vstorage_->num_levels() - 1) {
+        output_level == vstorage->num_levels() - 1) {
      assert(output_level > 1);
      output_level--;
    }

    if (output_level != 0) {
      if (start_level == 0) {
-        if (!picker_->GetOverlappingL0Files(vstorage_, &start_level_inputs,
-                                            output_level, nullptr)) {
+        if (!GetOverlappingL0Files(vstorage, &start_level_inputs, output_level,
+                                   nullptr)) {
          return nullptr;
        }
      }
@@ -950,16 +866,16 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
      int parent_index = -1;

      output_level_inputs.level = output_level;
-      if (!picker_->SetupOtherInputs(cf_name_, mutable_cf_options_, vstorage_,
-                                     &start_level_inputs, &output_level_inputs,
-                                     &parent_index, -1)) {
+      if (!SetupOtherInputs(cf_name, mutable_cf_options, vstorage,
+                            &start_level_inputs, &output_level_inputs,
+                            &parent_index, -1)) {
        return nullptr;
      }
      inputs.push_back(start_level_inputs);
      if (!output_level_inputs.empty()) {
        inputs.push_back(output_level_inputs);
      }
-      if (picker_->FilesRangeOverlapWithCompaction(inputs, output_level)) {
+      if (FilesRangeOverlapWithCompaction(inputs, output_level)) {
        return nullptr;
      }
    } else {
@@ -969,22 +885,21 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {

  uint64_t estimated_total_size = 0;
  // Use size of the output level as estimated file size
-  for (FileMetaData* f : vstorage_->LevelFiles(output_level)) {
+  for (FileMetaData* f : vstorage->LevelFiles(output_level)) {
    estimated_total_size += f->fd.GetFileSize();
  }
  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
+      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
  return new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(inputs),
-      output_level,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level,
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options, output_level,
                          kCompactionStyleUniversal),
      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
-                         output_level, 1),
-      GetCompressionOptions(ioptions_, vstorage_, output_level),
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
+                         1),
+      GetCompressionOptions(ioptions_, vstorage, output_level),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ true,
-      score_, false /* deletion_compaction */,
+      score, false /* deletion_compaction */,
      CompactionReason::kFilesMarkedForCompaction);
 }
 }  // namespace rocksdb
@@ -0,0 +1,98 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+
+#pragma once
+#ifndef ROCKSDB_LITE
+
+#include "db/compaction_picker.h"
+
+namespace rocksdb {
+class UniversalCompactionPicker : public CompactionPicker {
+ public:
+  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
+                            const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+
+ private:
+  struct SortedRun {
+    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
+              uint64_t _compensated_file_size, bool _being_compacted)
+        : level(_level),
+          file(_file),
+          size(_size),
+          compensated_file_size(_compensated_file_size),
+          being_compacted(_being_compacted) {
+      assert(compensated_file_size > 0);
+      assert(level != 0 || file != nullptr);
+    }
+
+    void Dump(char* out_buf, size_t out_buf_size,
+              bool print_path = false) const;
+
+    // sorted_run_count is added into the string to print
+    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
+                      size_t sorted_run_count) const;
+
+    int level;
+    // `file` Will be null for level > 0. For level = 0, the sorted run is
+    // for this file.
+    FileMetaData* file;
+    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
+    // files in the level. `being_compacted` should be the same for all files
+    // in a non-zero level. Use the value here.
+    uint64_t size;
+    uint64_t compensated_file_size;
+    bool being_compacted;
+  };
+
+  // Pick Universal compaction to limit read amplification
+  Compaction* PickCompactionToReduceSortedRuns(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score, unsigned int ratio,
+      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
+      LogBuffer* log_buffer);
+
+  // Pick Universal compaction to limit space amplification.
+  Compaction* PickCompactionToReduceSizeAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  Compaction* PickDeleteTriggeredCompaction(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  // Used in universal compaction when the enabled_trivial_move
+  // option is set. Checks whether there are any overlapping files
+  // in the input. Returns true if the input files are non
+  // overlapping.
+  bool IsInputFilesNonOverlapping(Compaction* c);
+
+  static std::vector<SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
+      const MutableCFOptions& mutable_cf_options);
+
+  // Pick a path ID to place a newly generated file, with its estimated file
+  // size.
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            uint64_t file_size);
+};
+}  // namespace rocksdb
+#endif  // !ROCKSDB_LITE
@@ -9,11 +9,11 @@
 #include "memtable/stl_wrappers.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/hash.h"
 #include "util/kv_map.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"

 using std::unique_ptr;
@@ -27,24 +27,24 @@ class KVIter : public Iterator {
 public:
  explicit KVIter(const stl_wrappers::KVMap* map)
      : map_(map), iter_(map_->end()) {}
-  bool Valid() const override { return iter_ != map_->end(); }
-  void SeekToFirst() override { iter_ = map_->begin(); }
-  void SeekToLast() override {
+  virtual bool Valid() const override { return iter_ != map_->end(); }
+  virtual void SeekToFirst() override { iter_ = map_->begin(); }
+  virtual void SeekToLast() override {
    if (map_->empty()) {
      iter_ = map_->end();
    } else {
      iter_ = map_->find(map_->rbegin()->first);
    }
  }
-  void Seek(const Slice& k) override {
+  virtual void Seek(const Slice& k) override {
    iter_ = map_->lower_bound(k.ToString());
  }
-  void SeekForPrev(const Slice& k) override {
+  virtual void SeekForPrev(const Slice& k) override {
    iter_ = map_->upper_bound(k.ToString());
    Prev();
  }
-  void Next() override { ++iter_; }
-  void Prev() override {
+  virtual void Next() override { ++iter_; }
+  virtual void Prev() override {
    if (iter_ == map_->begin()) {
      iter_ = map_->end();
      return;
@@ -52,9 +52,9 @@ class KVIter : public Iterator {
    --iter_;
  }

-  Slice key() const override { return iter_->first; }
-  Slice value() const override { return iter_->second; }
-  Status status() const override { return Status::OK(); }
+  virtual Slice key() const override { return iter_->first; }
+  virtual Slice value() const override { return iter_->second; }
+  virtual Status status() const override { return Status::OK(); }

 private:
  const stl_wrappers::KVMap* const map_;
@@ -171,9 +171,9 @@ class DoubleComparator : public Comparator {
 public:
  DoubleComparator() {}

-  const char* Name() const override { return "DoubleComparator"; }
+  virtual const char* Name() const override { return "DoubleComparator"; }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
 #ifndef CYGWIN
    double da = std::stod(a.ToString());
    double db = std::stod(b.ToString());
@@ -189,19 +189,19 @@ class DoubleComparator : public Comparator {
      return -1;
    }
  }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}

-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };

 class HashComparator : public Comparator {
 public:
  HashComparator() {}

-  const char* Name() const override { return "HashComparator"; }
+  virtual const char* Name() const override { return "HashComparator"; }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
    uint32_t ha = Hash(a.data(), a.size(), 66);
    uint32_t hb = Hash(b.data(), b.size(), 66);
    if (ha == hb) {
@@ -212,19 +212,19 @@ class HashComparator : public Comparator {
      return -1;
    }
  }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}

-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };

 class TwoStrComparator : public Comparator {
 public:
  TwoStrComparator() {}

-  const char* Name() const override { return "TwoStrComparator"; }
+  virtual const char* Name() const override { return "TwoStrComparator"; }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
    assert(a.size() >= 2);
    assert(b.size() >= 2);
    size_t size_a1 = static_cast<size_t>(a[0]);
@@ -244,10 +244,10 @@ class TwoStrComparator : public Comparator {
    }
    return a2.compare(b2);
  }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}

-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 }  // namespace

@@ -272,7 +272,7 @@ class ComparatorDBTest
    EXPECT_OK(DestroyDB(dbname_, last_options_));
  }

-  ~ComparatorDBTest() override {
+  ~ComparatorDBTest() {
    delete db_;
    EXPECT_OK(DestroyDB(dbname_, last_options_));
    comparator = BytewiseComparator();
@@ -8,7 +8,7 @@

 #include "rocksdb/convenience.h"

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "util/cast_util.h"

 namespace rocksdb {
@@ -35,12 +35,6 @@ Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
 Status VerifySstFileChecksum(const Options& options,
                             const EnvOptions& env_options,
                             const std::string& file_path) {
-  return VerifySstFileChecksum(options, env_options, ReadOptions(), file_path);
-}
-Status VerifySstFileChecksum(const Options& options,
-                             const EnvOptions& env_options,
-                             const ReadOptions& read_options,
-                             const std::string& file_path) {
  std::unique_ptr<RandomAccessFile> file;
  uint64_t file_size;
  InternalKeyComparator internal_comparator(options.comparator);
@@ -65,8 +59,7 @@ Status VerifySstFileChecksum(const Options& options,
  if (!s.ok()) {
    return s;
  }
-  s = table_reader->VerifyChecksum(read_options,
-                                   TableReaderCaller::kUserVerifyChecksum);
+  s = table_reader->VerifyChecksum();
  return s;
 }

@@ -13,24 +13,23 @@

 #include <errno.h>
 #include <fcntl.h>
+#include <inttypes.h>
 #include <sys/stat.h>
 #include <sys/types.h>
-#include <cinttypes>
-#include "db/db_impl/db_impl.h"
-#include "db/db_test_util.h"
+#include "db/db_impl.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "file/filename.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/convenience.h"
 #include "rocksdb/env.h"
 #include "rocksdb/table.h"
 #include "rocksdb/write_batch.h"
-#include "table/block_based/block_based_table_builder.h"
+#include "table/block_based_table_builder.h"
 #include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/filename.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"

 namespace rocksdb {

@@ -63,9 +62,9 @@ class CorruptionTest : public testing::Test {
    options_.create_if_missing = false;
  }

-  ~CorruptionTest() override {
-    delete db_;
-    DestroyDB(dbname_, Options());
+  ~CorruptionTest() {
+     delete db_;
+     DestroyDB(dbname_, Options());
  }

  void CloseDb() {
@@ -77,11 +76,7 @@ class CorruptionTest : public testing::Test {
    delete db_;
    db_ = nullptr;
    Options opt = (options ? *options : options_);
-    if (opt.env == Options().env) {
-      // If env is not overridden, replace it with ErrorEnv.
-      // Otherwise, the test already uses a non-default Env.
-      opt.env = &env_;
-    }
+    opt.env = &env_;
    opt.arena_block_size = 4096;
    BlockBasedTableOptions table_options;
    table_options.block_cache = tiny_cache_;
@@ -326,52 +321,6 @@ TEST_F(CorruptionTest, TableFile) {
  ASSERT_NOK(dbi->VerifyChecksum());
 }

-TEST_F(CorruptionTest, VerifyChecksumReadahead) {
-  Options options;
-  SpecialEnv senv(Env::Default());
-  options.env = &senv;
-  // Disable block cache as we are going to check checksum for
-  // the same file twice and measure number of reads.
-  BlockBasedTableOptions table_options_no_bc;
-  table_options_no_bc.no_block_cache = true;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options_no_bc));
-
-  Reopen(&options);
-
-  Build(10000);
-  DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
-  dbi->TEST_FlushMemTable();
-  dbi->TEST_CompactRange(0, nullptr, nullptr);
-  dbi->TEST_CompactRange(1, nullptr, nullptr);
-
-  senv.count_random_reads_ = true;
-  senv.random_read_counter_.Reset();
-  ASSERT_OK(dbi->VerifyChecksum());
-
-  // Make sure the counter is enabled.
-  ASSERT_GT(senv.random_read_counter_.Read(), 0);
-
-  // The SST file is about 10MB. Default readahead size is 256KB.
-  // Give a conservative 20 reads for metadata blocks, The number
-  // of random reads should be within 10 MB / 256KB + 20 = 60.
-  ASSERT_LT(senv.random_read_counter_.Read(), 60);
-
-  senv.random_read_bytes_counter_ = 0;
-  ReadOptions ro;
-  ro.readahead_size = size_t{32 * 1024};
-  ASSERT_OK(dbi->VerifyChecksum(ro));
-  // The SST file is about 10MB. We set readahead size to 32KB.
-  // Give 0 to 20 reads for metadata blocks, and allow real read
-  // to range from 24KB to 48KB. The lower bound would be:
-  //   10MB / 48KB + 0 = 213
-  // The higher bound is
-  //   10MB / 24KB + 20 = 447.
-  ASSERT_GE(senv.random_read_counter_.Read(), 213);
-  ASSERT_LE(senv.random_read_counter_.Read(), 447);
-
-  CloseDb();
-}
-
 TEST_F(CorruptionTest, TableFileIndexData) {
  Options options;
  // very big, we'll trigger flushes manually
@@ -5,15 +5,15 @@

 #ifndef ROCKSDB_LITE

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "table/cuckoo/cuckoo_table_factory.h"
-#include "table/cuckoo/cuckoo_table_reader.h"
+#include "table/cuckoo_table_factory.h"
+#include "table/cuckoo_table_reader.h"
 #include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"

 namespace rocksdb {

@@ -31,7 +31,7 @@ class CuckooTableDBTest : public testing::Test {
    Reopen();
  }

-  ~CuckooTableDBTest() override {
+  ~CuckooTableDBTest() {
    delete db_;
    EXPECT_OK(DestroyDB(dbname_, Options()));
  }
@@ -12,7 +12,6 @@
 #include <utility>
 #include <vector>

-#include "db/arena_wrapped_db_iter.h"
 #include "db/column_family.h"
 #include "db/db_iter.h"
 #include "db/db_test_util.h"
@@ -64,11 +63,9 @@ class DBBlobIndexTest : public DBTestBase {
    ReadOptions read_options;
    read_options.snapshot = snapshot;
    PinnableSlice value;
-    DBImpl::GetImplOptions get_impl_options;
-    get_impl_options.column_family = cfh();
-    get_impl_options.value = &value;
-    get_impl_options.is_blob_index = is_blob_index;
-    auto s = dbfull()->GetImpl(read_options, key, get_impl_options);
+    auto s = dbfull()->GetImpl(read_options, cfh(), key, &value,
+                               nullptr /*value_found*/, nullptr /*callback*/,
+                               is_blob_index);
    if (s.IsNotFound()) {
      return "NOT_FOUND";
    }
@@ -19,9 +19,6 @@ class DBBlockCacheTest : public DBTestBase {
  size_t hit_count_ = 0;
  size_t insert_count_ = 0;
  size_t failure_count_ = 0;
-  size_t compression_dict_miss_count_ = 0;
-  size_t compression_dict_hit_count_ = 0;
-  size_t compression_dict_insert_count_ = 0;
  size_t compressed_miss_count_ = 0;
  size_t compressed_hit_count_ = 0;
  size_t compressed_insert_count_ = 0;
@@ -72,15 +69,6 @@ class DBBlockCacheTest : public DBTestBase {
        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
  }

-  void RecordCacheCountersForCompressionDict(const Options& options) {
-    compression_dict_miss_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS);
-    compression_dict_hit_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_HIT);
-    compression_dict_insert_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_ADD);
-  }
-
  void CheckCacheCounters(const Options& options, size_t expected_misses,
                          size_t expected_hits, size_t expected_inserts,
                          size_t expected_failures) {
@@ -99,28 +87,6 @@ class DBBlockCacheTest : public DBTestBase {
    failure_count_ = new_failure_count;
  }

-  void CheckCacheCountersForCompressionDict(
-      const Options& options, size_t expected_compression_dict_misses,
-      size_t expected_compression_dict_hits,
-      size_t expected_compression_dict_inserts) {
-    size_t new_compression_dict_miss_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS);
-    size_t new_compression_dict_hit_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_HIT);
-    size_t new_compression_dict_insert_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_ADD);
-    ASSERT_EQ(compression_dict_miss_count_ + expected_compression_dict_misses,
-              new_compression_dict_miss_count);
-    ASSERT_EQ(compression_dict_hit_count_ + expected_compression_dict_hits,
-              new_compression_dict_hit_count);
-    ASSERT_EQ(
-        compression_dict_insert_count_ + expected_compression_dict_inserts,
-        new_compression_dict_insert_count);
-    compression_dict_miss_count_ = new_compression_dict_miss_count;
-    compression_dict_hit_count_ = new_compression_dict_hit_count;
-    compression_dict_insert_count_ = new_compression_dict_insert_count;
-  }
-
  void CheckCompressedCacheCounters(const Options& options,
                                    size_t expected_misses,
                                    size_t expected_hits,
@@ -380,19 +346,14 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
  options.statistics = rocksdb::CreateDBStatistics();
  BlockBasedTableOptions table_options;
  table_options.cache_index_and_filter_blocks = true;
-  LRUCacheOptions co;
-  // 500 bytes are enough to hold the first two blocks
-  co.capacity = 500;
-  co.num_shard_bits = 0;
-  co.strict_capacity_limit = false;
-  co.metadata_charge_policy = kDontChargeCacheMetadata;
-  std::shared_ptr<Cache> cache = NewLRUCache(co);
+  // 200 bytes are enough to hold the first two blocks
+  std::shared_ptr<Cache> cache = NewLRUCache(200, 0, false);
  table_options.block_cache = cache;
  table_options.filter_policy.reset(NewBloomFilterPolicy(20, true));
  options.table_factory.reset(new BlockBasedTableFactory(table_options));
  CreateAndReopenWithCF({"pikachu"}, options);

-  ASSERT_OK(Put(1, "longer_key", "val"));
+  ASSERT_OK(Put(1, "key", "val"));
  // Create a new table
  ASSERT_OK(Flush(1));
  size_t index_bytes_insert =
@@ -404,14 +365,9 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
  ASSERT_EQ(cache->GetUsage(), index_bytes_insert + filter_bytes_insert);
  // set the cache capacity to the current usage
  cache->SetCapacity(index_bytes_insert + filter_bytes_insert);
-  // The index and filter eviction statistics were broken by the refactoring
-  // that moved the readers out of the block cache. Disabling these until we can
-  // bring the stats back.
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT), 0);
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT), 0);
-  // Note that the second key needs to be no longer than the first one.
-  // Otherwise the second index block may not fit in cache.
-  ASSERT_OK(Put(1, "key", "val"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT), 0);
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT), 0);
+  ASSERT_OK(Put(1, "key2", "val"));
  // Create a new table
  ASSERT_OK(Flush(1));
  // cache evicted old index and block entries
@@ -419,13 +375,10 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
            index_bytes_insert);
  ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_INSERT),
            filter_bytes_insert);
-  // The index and filter eviction statistics were broken by the refactoring
-  // that moved the readers out of the block cache. Disabling these until we can
-  // bring the stats back.
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT),
-  //           index_bytes_insert);
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT),
-  //           filter_bytes_insert);
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT),
+            index_bytes_insert);
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT),
+            filter_bytes_insert);
 }

 namespace {
@@ -442,9 +395,9 @@ class MockCache : public LRUCache {
                 false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/) {
  }

-  Status Insert(const Slice& key, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value), Handle** handle,
-                Priority priority) override {
+  virtual Status Insert(const Slice& key, void* value, size_t charge,
+                        void (*deleter)(const Slice& key, void* value),
+                        Handle** handle, Priority priority) override {
    if (priority == Priority::LOW) {
      low_pri_insert_count++;
    } else {
@@ -489,11 +442,11 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksCachePriority) {
              TestGetTickerCount(options, BLOCK_CACHE_ADD));
    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_MISS));
    if (priority == Cache::Priority::LOW) {
-      ASSERT_EQ(0u, MockCache::high_pri_insert_count);
-      ASSERT_EQ(2u, MockCache::low_pri_insert_count);
+      ASSERT_EQ(0, MockCache::high_pri_insert_count);
+      ASSERT_EQ(2, MockCache::low_pri_insert_count);
    } else {
-      ASSERT_EQ(2u, MockCache::high_pri_insert_count);
-      ASSERT_EQ(0u, MockCache::low_pri_insert_count);
+      ASSERT_EQ(2, MockCache::high_pri_insert_count);
+      ASSERT_EQ(0, MockCache::low_pri_insert_count);
    }

    // Access data block.
@@ -507,11 +460,11 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksCachePriority) {

    // Data block should be inserted with low priority.
    if (priority == Cache::Priority::LOW) {
-      ASSERT_EQ(0u, MockCache::high_pri_insert_count);
-      ASSERT_EQ(3u, MockCache::low_pri_insert_count);
+      ASSERT_EQ(0, MockCache::high_pri_insert_count);
+      ASSERT_EQ(3, MockCache::low_pri_insert_count);
    } else {
-      ASSERT_EQ(2u, MockCache::high_pri_insert_count);
-      ASSERT_EQ(1u, MockCache::low_pri_insert_count);
+      ASSERT_EQ(2, MockCache::high_pri_insert_count);
+      ASSERT_EQ(1, MockCache::low_pri_insert_count);
    }
  }
 }
@@ -680,7 +633,7 @@ TEST_F(DBBlockCacheTest, CompressedCache) {

 TEST_F(DBBlockCacheTest, CacheCompressionDict) {
  const int kNumFiles = 4;
-  const int kNumEntriesPerFile = 128;
+  const int kNumEntriesPerFile = 32;
  const int kNumBytesPerEntry = 1024;

  // Try all the available libraries that support dictionary compression
@@ -710,8 +663,6 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
    options.table_factory.reset(new BlockBasedTableFactory(table_options));
    DestroyAndReopen(options);

-    RecordCacheCountersForCompressionDict(options);
-
    for (int i = 0; i < kNumFiles; ++i) {
      ASSERT_EQ(i, NumTableFilesAtLevel(0, 0));
      for (int j = 0; j < kNumEntriesPerFile; ++j) {
@@ -724,26 +675,27 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
    ASSERT_EQ(0, NumTableFilesAtLevel(0));
    ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(1));

-    // Compression dictionary blocks are preloaded.
-    CheckCacheCountersForCompressionDict(
-        options, kNumFiles /* expected_compression_dict_misses */,
-        0 /* expected_compression_dict_hits */,
-        kNumFiles /* expected_compression_dict_inserts */);
-
    // Seek to a key in a file. It should cause the SST's dictionary meta-block
    // to be read.
    RecordCacheCounters(options);
-    RecordCacheCountersForCompressionDict(options);
+    ASSERT_EQ(0,
+              TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
+    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_ADD));
+    ASSERT_EQ(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        0);
    ReadOptions read_options;
    ASSERT_NE("NOT_FOUND", Get(Key(kNumFiles * kNumEntriesPerFile - 1)));
-    // Two block hits: index and dictionary since they are prefetched
-    // One block missed/added: data block
-    CheckCacheCounters(options, 1 /* expected_misses */, 2 /* expected_hits */,
-                       1 /* expected_inserts */, 0 /* expected_failures */);
-    CheckCacheCountersForCompressionDict(
-        options, 0 /* expected_compression_dict_misses */,
-        1 /* expected_compression_dict_hits */,
-        0 /* expected_compression_dict_inserts */);
+    // Two blocks missed/added: dictionary and data block
+    // One block hit: index since it's prefetched
+    CheckCacheCounters(options, 2 /* expected_misses */, 1 /* expected_hits */,
+                       2 /* expected_inserts */, 0 /* expected_failures */);
+    ASSERT_EQ(1,
+              TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
+    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_ADD));
+    ASSERT_GT(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        0);
  }
 }

@@ -32,7 +32,7 @@ class DBBloomFilterTestWithParam
 public:
  DBBloomFilterTestWithParam() : DBTestBase("/db_bloom_filter_tests") {}

-  ~DBBloomFilterTestWithParam() override {}
+  ~DBBloomFilterTestWithParam() {}

  void SetUp() override {
    use_block_based_filter_ = std::get<0>(GetParam());
@@ -642,7 +642,7 @@ class WrappedBloom : public FilterPolicy {
  explicit WrappedBloom(int bits_per_key)
      : filter_(NewBloomFilterPolicy(bits_per_key)), counter_(0) {}

-  ~WrappedBloom() override { delete filter_; }
+  ~WrappedBloom() { delete filter_; }

  const char* Name() const override { return "WrappedRocksDbFilterPolicy"; }

@@ -786,75 +786,6 @@ TEST_F(DBBloomFilterTest, PrefixExtractorBlockFilter) {
  delete iter;
 }

-TEST_F(DBBloomFilterTest, MemtableWholeKeyBloomFilter) {
-  // regression test for #2743. the range delete tombstones in memtable should
-  // be added even when Get() skips searching due to its prefix bloom filter
-  const int kMemtableSize = 1 << 20;              // 1MB
-  const int kMemtablePrefixFilterSize = 1 << 13;  // 8KB
-  const int kPrefixLen = 4;
-  Options options = CurrentOptions();
-  options.memtable_prefix_bloom_size_ratio =
-      static_cast<double>(kMemtablePrefixFilterSize) / kMemtableSize;
-  options.prefix_extractor.reset(rocksdb::NewFixedPrefixTransform(kPrefixLen));
-  options.write_buffer_size = kMemtableSize;
-  options.memtable_whole_key_filtering = false;
-  Reopen(options);
-  std::string key1("AAAABBBB");
-  std::string key2("AAAACCCC");  // not in DB
-  std::string key3("AAAADDDD");
-  std::string key4("AAAAEEEE");
-  std::string value1("Value1");
-  std::string value3("Value3");
-  std::string value4("Value4");
-
-  ASSERT_OK(Put(key1, value1, WriteOptions()));
-
-  // check memtable bloom stats
-  ASSERT_EQ("NOT_FOUND", Get(key2));
-  ASSERT_EQ(0, get_perf_context()->bloom_memtable_miss_count);
-  // same prefix, bloom filter false positive
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-
-  // enable whole key bloom filter
-  options.memtable_whole_key_filtering = true;
-  Reopen(options);
-  // check memtable bloom stats
-  ASSERT_OK(Put(key3, value3, WriteOptions()));
-  ASSERT_EQ("NOT_FOUND", Get(key2));
-  // whole key bloom filter kicks in and determines it's a miss
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_miss_count);
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-
-  // verify whole key filtering does not depend on prefix_extractor
-  options.prefix_extractor.reset();
-  Reopen(options);
-  // check memtable bloom stats
-  ASSERT_OK(Put(key4, value4, WriteOptions()));
-  ASSERT_EQ("NOT_FOUND", Get(key2));
-  // whole key bloom filter kicks in and determines it's a miss
-  ASSERT_EQ(2, get_perf_context()->bloom_memtable_miss_count);
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-}
-
-TEST_F(DBBloomFilterTest, MemtablePrefixBloomOutOfDomain) {
-  constexpr size_t kPrefixSize = 8;
-  const std::string kKey = "key";
-  assert(kKey.size() < kPrefixSize);
-  Options options = CurrentOptions();
-  options.prefix_extractor.reset(NewFixedPrefixTransform(kPrefixSize));
-  options.memtable_prefix_bloom_size_ratio = 0.25;
-  Reopen(options);
-  ASSERT_OK(Put(kKey, "v"));
-  ASSERT_EQ("v", Get(kKey));
-  std::unique_ptr<Iterator> iter(dbfull()->NewIterator(ReadOptions()));
-  iter->Seek(kKey);
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ(kKey, iter->key());
-  iter->SeekForPrev(kKey);
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ(kKey, iter->key());
-}
-
 #ifndef ROCKSDB_LITE
 class BloomStatsTestWithParam
    : public DBBloomFilterTest,
@@ -892,7 +823,7 @@ class BloomStatsTestWithParam
    DestroyAndReopen(options_);
  }

-  ~BloomStatsTestWithParam() override {
+  ~BloomStatsTestWithParam() {
    get_perf_context()->Reset();
    Destroy(options_);
  }
@@ -1004,16 +935,13 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
  ASSERT_OK(iter->status());
  ASSERT_TRUE(iter->Valid());
  ASSERT_EQ(value3, iter->value().ToString());
-  // The seek doesn't check block-based bloom filter because last index key
-  // starts with the same prefix we're seeking to.
-  uint64_t expected_hits = use_block_based_builder_ ? 1 : 2;
-  ASSERT_EQ(expected_hits, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);

  iter->Seek(key2);
  ASSERT_OK(iter->status());
  ASSERT_TRUE(!iter->Valid());
  ASSERT_EQ(1, get_perf_context()->bloom_sst_miss_count);
-  ASSERT_EQ(expected_hits, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);
 }

 INSTANTIATE_TEST_CASE_P(BloomStatsTestWithParam, BloomStatsTestWithParam,
@@ -1095,8 +1023,6 @@ TEST_F(DBBloomFilterTest, PrefixScan) {
    options.max_background_compactions = 2;
    options.create_if_missing = true;
    options.memtable_factory.reset(NewHashSkipListRepFactory(16));
-    assert(!options.unordered_write);
-    // It is incompatible with allow_concurrent_memtable_write=false
    options.allow_concurrent_memtable_write = false;

    BlockBasedTableOptions table_options;
@@ -1340,8 +1266,6 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
    table_options.cache_index_and_filter_blocks = true;
    table_options.filter_policy.reset(
        NewBloomFilterPolicy(10, use_block_based_builder));
-    table_options.index_shortening = BlockBasedTableOptions::
-        IndexShorteningMode::kShortenSeparatorsAndSuccessor;
    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
    DestroyAndReopen(options);

@@ -63,33 +63,33 @@ INSTANTIATE_TEST_CASE_P(DBTestCompactionFilterWithCompactOption,

 class KeepFilter : public CompactionFilter {
 public:
-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
+  virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                      const Slice& /*value*/, std::string* /*new_value*/,
+                      bool* /*value_changed*/) const override {
    cfilter_count++;
    return false;
  }

-  const char* Name() const override { return "KeepFilter"; }
+  virtual const char* Name() const override { return "KeepFilter"; }
 };

 class DeleteFilter : public CompactionFilter {
 public:
-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
+  virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                      const Slice& /*value*/, std::string* /*new_value*/,
+                      bool* /*value_changed*/) const override {
    cfilter_count++;
    return true;
  }

-  const char* Name() const override { return "DeleteFilter"; }
+  virtual const char* Name() const override { return "DeleteFilter"; }
 };

 class DeleteISFilter : public CompactionFilter {
 public:
-  bool Filter(int /*level*/, const Slice& key, const Slice& /*value*/,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
+  virtual bool Filter(int /*level*/, const Slice& key, const Slice& /*value*/,
+                      std::string* /*new_value*/,
+                      bool* /*value_changed*/) const override {
    cfilter_count++;
    int i = std::stoi(key.ToString());
    if (i > 5 && i <= 105) {
@@ -98,18 +98,20 @@ class DeleteISFilter : public CompactionFilter {
    return false;
  }

-  bool IgnoreSnapshots() const override { return true; }
+  virtual bool IgnoreSnapshots() const override { return true; }

-  const char* Name() const override { return "DeleteFilter"; }
+  virtual const char* Name() const override { return "DeleteFilter"; }
 };

 // Skip x if floor(x/10) is even, use range skips. Requires that keys are
 // zero-padded to length 10.
 class SkipEvenFilter : public CompactionFilter {
 public:
-  Decision FilterV2(int /*level*/, const Slice& key, ValueType /*value_type*/,
-                    const Slice& /*existing_value*/, std::string* /*new_value*/,
-                    std::string* skip_until) const override {
+  virtual Decision FilterV2(int /*level*/, const Slice& key,
+                            ValueType /*value_type*/,
+                            const Slice& /*existing_value*/,
+                            std::string* /*new_value*/,
+                            std::string* skip_until) const override {
    cfilter_count++;
    int i = std::stoi(key.ToString());
    if (i / 10 % 2 == 0) {
@@ -122,22 +124,22 @@ class SkipEvenFilter : public CompactionFilter {
    return Decision::kKeep;
  }

-  bool IgnoreSnapshots() const override { return true; }
+  virtual bool IgnoreSnapshots() const override { return true; }

-  const char* Name() const override { return "DeleteFilter"; }
+  virtual const char* Name() const override { return "DeleteFilter"; }
 };

 class DelayFilter : public CompactionFilter {
 public:
  explicit DelayFilter(DBTestBase* d) : db_test(d) {}
-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
+  virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                      const Slice& /*value*/, std::string* /*new_value*/,
+                      bool* /*value_changed*/) const override {
    db_test->env_->addon_time_.fetch_add(1000);
    return true;
  }

-  const char* Name() const override { return "DelayFilter"; }
+  virtual const char* Name() const override { return "DelayFilter"; }

 private:
  DBTestBase* db_test;
@@ -147,13 +149,13 @@ class ConditionalFilter : public CompactionFilter {
 public:
  explicit ConditionalFilter(const std::string* filtered_value)
      : filtered_value_(filtered_value) {}
-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& value,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
+  virtual bool Filter(int /*level*/, const Slice& /*key*/, const Slice& value,
+                      std::string* /*new_value*/,
+                      bool* /*value_changed*/) const override {
    return value.ToString() == *filtered_value_;
  }

-  const char* Name() const override { return "ConditionalFilter"; }
+  virtual const char* Name() const override { return "ConditionalFilter"; }

 private:
  const std::string* filtered_value_;
@@ -163,15 +165,16 @@ class ChangeFilter : public CompactionFilter {
 public:
  explicit ChangeFilter() {}

-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-              std::string* new_value, bool* value_changed) const override {
+  virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                      const Slice& /*value*/, std::string* new_value,
+                      bool* value_changed) const override {
    assert(new_value != nullptr);
    *new_value = NEW_VALUE;
    *value_changed = true;
    return false;
  }

-  const char* Name() const override { return "ChangeFilter"; }
+  virtual const char* Name() const override { return "ChangeFilter"; }
 };

 class KeepFilterFactory : public CompactionFilterFactory {
@@ -182,7 +185,7 @@ class KeepFilterFactory : public CompactionFilterFactory {
        check_context_cf_id_(check_context_cf_id),
        compaction_filter_created_(false) {}

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (check_context_) {
      EXPECT_EQ(expect_full_compaction_.load(), context.is_full_compaction);
@@ -197,7 +200,7 @@ class KeepFilterFactory : public CompactionFilterFactory {

  bool compaction_filter_created() const { return compaction_filter_created_; }

-  const char* Name() const override { return "KeepFilterFactory"; }
+  virtual const char* Name() const override { return "KeepFilterFactory"; }
  bool check_context_;
  bool check_context_cf_id_;
  std::atomic_bool expect_full_compaction_;
@@ -208,7 +211,7 @@ class KeepFilterFactory : public CompactionFilterFactory {

 class DeleteFilterFactory : public CompactionFilterFactory {
 public:
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (context.is_manual_compaction) {
      return std::unique_ptr<CompactionFilter>(new DeleteFilter());
@@ -217,13 +220,13 @@ class DeleteFilterFactory : public CompactionFilterFactory {
    }
  }

-  const char* Name() const override { return "DeleteFilterFactory"; }
+  virtual const char* Name() const override { return "DeleteFilterFactory"; }
 };

 // Delete Filter Factory which ignores snapshots
 class DeleteISFilterFactory : public CompactionFilterFactory {
 public:
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (context.is_manual_compaction) {
      return std::unique_ptr<CompactionFilter>(new DeleteISFilter());
@@ -232,12 +235,12 @@ class DeleteISFilterFactory : public CompactionFilterFactory {
    }
  }

-  const char* Name() const override { return "DeleteFilterFactory"; }
+  virtual const char* Name() const override { return "DeleteFilterFactory"; }
 };

 class SkipEvenFilterFactory : public CompactionFilterFactory {
 public:
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (context.is_manual_compaction) {
      return std::unique_ptr<CompactionFilter>(new SkipEvenFilter());
@@ -246,18 +249,18 @@ class SkipEvenFilterFactory : public CompactionFilterFactory {
    }
  }

-  const char* Name() const override { return "SkipEvenFilterFactory"; }
+  virtual const char* Name() const override { return "SkipEvenFilterFactory"; }
 };

 class DelayFilterFactory : public CompactionFilterFactory {
 public:
  explicit DelayFilterFactory(DBTestBase* d) : db_test(d) {}
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
    return std::unique_ptr<CompactionFilter>(new DelayFilter(db_test));
  }

-  const char* Name() const override { return "DelayFilterFactory"; }
+  virtual const char* Name() const override { return "DelayFilterFactory"; }

 private:
  DBTestBase* db_test;
@@ -268,13 +271,15 @@ class ConditionalFilterFactory : public CompactionFilterFactory {
  explicit ConditionalFilterFactory(const Slice& filtered_value)
      : filtered_value_(filtered_value.ToString()) {}

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
    return std::unique_ptr<CompactionFilter>(
        new ConditionalFilter(&filtered_value_));
  }

-  const char* Name() const override { return "ConditionalFilterFactory"; }
+  virtual const char* Name() const override {
+    return "ConditionalFilterFactory";
+  }

 private:
  std::string filtered_value_;
@@ -284,12 +289,12 @@ class ChangeFilterFactory : public CompactionFilterFactory {
 public:
  explicit ChangeFilterFactory() {}

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
    return std::unique_ptr<CompactionFilter>(new ChangeFilter());
  }

-  const char* Name() const override { return "ChangeFilterFactory"; }
+  virtual const char* Name() const override { return "ChangeFilterFactory"; }
 };

 #ifndef ROCKSDB_LITE
@@ -352,7 +357,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
    }
  }
  ASSERT_EQ(total, 100000);
-  ASSERT_EQ(count, 0);
+  ASSERT_EQ(count, 1);

  // overwrite all the 100K keys once again.
  for (int i = 0; i < 100000; i++) {
@@ -659,7 +664,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
      iter->Next();
    }
    ASSERT_EQ(total, 700);
-    ASSERT_EQ(count, 0);
+    ASSERT_EQ(count, 1);
  }
 }
 #endif  // ROCKSDB_LITE
@@ -694,7 +699,44 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextCfId) {
 }

 #ifndef ROCKSDB_LITE
-// Compaction filters aplies to all records, regardless snapshots.
+// Compaction filters should only be applied to records that are newer than the
+// latest snapshot. This test inserts records and applies a delete filter.
+TEST_F(DBTestCompactionFilter, CompactionFilterSnapshot) {
+  Options options = CurrentOptions();
+  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
+  options.disable_auto_compactions = true;
+  options.create_if_missing = true;
+  DestroyAndReopen(options);
+
+  // Put some data.
+  const Snapshot* snapshot = nullptr;
+  for (int table = 0; table < 4; ++table) {
+    for (int i = 0; i < 10; ++i) {
+      Put(ToString(table * 100 + i), "val");
+    }
+    Flush();
+
+    if (table == 0) {
+      snapshot = db_->GetSnapshot();
+    }
+  }
+  assert(snapshot != nullptr);
+
+  cfilter_count = 0;
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  // The filter should delete 10 records.
+  ASSERT_EQ(30U, cfilter_count);
+
+  // Release the snapshot and compact again -> now all records should be
+  // removed.
+  db_->ReleaseSnapshot(snapshot);
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  ASSERT_EQ(0U, CountLiveFiles());
+}
+
+// Compaction filters should only be applied to records that are newer than the
+// latest snapshot. However, if the compaction filter asks to ignore snapshots
+// records newer than the snapshot will also be processed
 TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
  std::string five = ToString(5);
  Options options = CurrentOptions();
@@ -720,7 +762,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
  cfilter_count = 0;
  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
  // The filter should delete 40 records.
-  ASSERT_EQ(40, cfilter_count);
+  ASSERT_EQ(40U, cfilter_count);

  {
    // Scan the entire database as of the snapshot to ensure
@@ -832,38 +874,6 @@ TEST_F(DBTestCompactionFilter, SkipUntilWithBloomFilter) {
  EXPECT_EQ("v50", val);
 }

-class TestNotSupportedFilter : public CompactionFilter {
- public:
-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
-    return true;
-  }
-
-  const char* Name() const override { return "NotSupported"; }
-  bool IgnoreSnapshots() const override { return false; }
-};
-
-TEST_F(DBTestCompactionFilter, IgnoreSnapshotsFalse) {
-  Options options = CurrentOptions();
-  options.compaction_filter = new TestNotSupportedFilter();
-  DestroyAndReopen(options);
-
-  Put("a", "v10");
-  Put("z", "v20");
-  Flush();
-
-  Put("a", "v10");
-  Put("z", "v20");
-  Flush();
-
-  // Comapction should fail because IgnoreSnapshots() = false
-  EXPECT_TRUE(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr)
-                  .IsNotSupported());
-
-  delete options.compaction_filter;
-}
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -13,9 +13,9 @@
 #include "rocksdb/concurrent_task_limiter.h"
 #include "rocksdb/experimental.h"
 #include "rocksdb/utilities/convenience.h"
-#include "test_util/fault_injection_test_env.h"
-#include "test_util/sync_point.h"
 #include "util/concurrent_task_limiter_impl.h"
+#include "util/fault_injection_test_env.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -55,9 +55,9 @@ namespace {
 class FlushedFileCollector : public EventListener {
 public:
  FlushedFileCollector() {}
-  ~FlushedFileCollector() override {}
+  ~FlushedFileCollector() {}

-  void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
+  virtual void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
    std::lock_guard<std::mutex> lock(mutex_);
    flushed_files_.push_back(info.file_path);
  }
@@ -87,23 +87,24 @@ public:
    }
  }

-  ~CompactionStatsCollector() override {}
+  ~CompactionStatsCollector() {}

-  void OnCompactionCompleted(DB* /* db */,
-                             const CompactionJobInfo& info) override {
+  virtual void OnCompactionCompleted(DB* /* db */,
+      const CompactionJobInfo& info) override {
    int k = static_cast<int>(info.compaction_reason);
    int num_of_reasons = static_cast<int>(CompactionReason::kNumOfReasons);
    assert(k >= 0 && k < num_of_reasons);
    compaction_completed_[k]++;
  }

-  void OnExternalFileIngested(
-      DB* /* db */, const ExternalFileIngestionInfo& /* info */) override {
+  virtual void OnExternalFileIngested(DB* /* db */,
+      const ExternalFileIngestionInfo& /* info */) override {
    int k = static_cast<int>(CompactionReason::kExternalSstIngestion);
    compaction_completed_[k]++;
  }

-  void OnFlushCompleted(DB* /* db */, const FlushJobInfo& /* info */) override {
+  virtual void OnFlushCompleted(DB* /* db */,
+      const FlushJobInfo& /* info */) override {
    int k = static_cast<int>(CompactionReason::kFlush);
    compaction_completed_[k]++;
  }
@@ -141,7 +142,7 @@ Options DeletionTriggerOptions(Options options) {
  options.compression = kNoCompression;
  options.write_buffer_size = kCDTKeysPerBuffer * (kCDTValueSize + 24);
  options.min_write_buffer_number_to_merge = 1;
-  options.max_write_buffer_size_to_maintain = 0;
+  options.max_write_buffer_number_to_maintain = 0;
  options.num_levels = kCDTNumLevels;
  options.level0_file_num_compaction_trigger = 1;
  options.target_file_size_base = options.write_buffer_size * 2;
@@ -353,8 +354,7 @@ TEST_P(DBCompactionTestWithParam, CompactionsPreserveDeletes) {
    CompactRangeOptions cro;
    cro.change_level = true;
    cro.target_level = 2;
-    cro.bottommost_level_compaction =
-        BottommostLevelCompaction::kForceOptimized;
+    cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;

    dbfull()->TEST_WaitForFlushMemTable();
    dbfull()->CompactRange(cro, nullptr, nullptr);
@@ -497,14 +497,14 @@ TEST_F(DBCompactionTest, TestTableReaderForCompaction) {

  // Create new iterator for:
  // (1) 1 for verifying flush results
-  // (2) 1 for verifying compaction results.
-  // (3) New TableReaders will not be created for compaction inputs
-  ASSERT_EQ(num_new_table_reader, 2);
+  // (2) 3 for compaction input files
+  // (3) 1 for verifying compaction results.
+  ASSERT_EQ(num_new_table_reader, 5);

  num_table_cache_lookup = 0;
  num_new_table_reader = 0;
  ASSERT_EQ(Key(1), Get(Key(1)));
-  ASSERT_EQ(num_table_cache_lookup + old_num_table_cache_lookup2, 5);
+  ASSERT_EQ(num_table_cache_lookup + old_num_table_cache_lookup2, 3);
  ASSERT_EQ(num_new_table_reader, 0);

  num_table_cache_lookup = 0;
@@ -512,21 +512,20 @@ TEST_F(DBCompactionTest, TestTableReaderForCompaction) {
  CompactRangeOptions cro;
  cro.change_level = true;
  cro.target_level = 2;
-  cro.bottommost_level_compaction = BottommostLevelCompaction::kForceOptimized;
+  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
  db_->CompactRange(cro, nullptr, nullptr);
  // Only verifying compaction outputs issues one table cache lookup
  // for both data block and range deletion block).
  // May preload table cache too.
  ASSERT_GE(num_table_cache_lookup, 1);
  old_num_table_cache_lookup2 = num_table_cache_lookup;
-  // One for verifying compaction results.
-  // No new iterator created for compaction.
-  ASSERT_EQ(num_new_table_reader, 1);
+  // One for compaction input, one for verifying compaction results.
+  ASSERT_EQ(num_new_table_reader, 2);

  num_table_cache_lookup = 0;
  num_new_table_reader = 0;
  ASSERT_EQ(Key(1), Get(Key(1)));
-  ASSERT_EQ(num_table_cache_lookup + old_num_table_cache_lookup2, 3);
+  ASSERT_EQ(num_table_cache_lookup + old_num_table_cache_lookup2, 2);
  ASSERT_EQ(num_new_table_reader, 0);

  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -732,7 +731,7 @@ TEST_F(DBCompactionTest, BGCompactionsAllowed) {

  // Now all column families qualify compaction but only one should be
  // scheduled, because no column family hits speed up condition.
-  ASSERT_EQ(1u, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
+  ASSERT_EQ(1, env_->GetThreadPoolQueueLen(Env::Priority::LOW));

  // Create two more files for one column family, which triggers speed up
  // condition, three compactions will be scheduled.
@@ -746,7 +745,7 @@ TEST_F(DBCompactionTest, BGCompactionsAllowed) {
    ASSERT_EQ(options.level0_file_num_compaction_trigger + num + 1,
              NumTableFilesAtLevel(0, 2));
  }
-  ASSERT_EQ(3U, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
+  ASSERT_EQ(3, env_->GetThreadPoolQueueLen(Env::Priority::LOW));

  // Unblock all threads to unblock all compactions.
  for (size_t i = 0; i < kTotalTasks; i++) {
@@ -777,7 +776,7 @@ TEST_F(DBCompactionTest, BGCompactionsAllowed) {

  // Now all column families qualify compaction but only one should be
  // scheduled, because no column family hits speed up condition.
-  ASSERT_EQ(1U, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
+  ASSERT_EQ(1, env_->GetThreadPoolQueueLen(Env::Priority::LOW));

  for (size_t i = 0; i < kTotalTasks; i++) {
    sleeping_tasks[i].WakeUp();
@@ -2262,8 +2261,6 @@ TEST_P(DBCompactionTestWithParam, ConvertCompactionStyle) {
  CompactRangeOptions compact_options;
  compact_options.change_level = true;
  compact_options.target_level = 0;
-  // cannot use kForceOptimized here because the compaction here is expected
-  // to generate one output file
  compact_options.bottommost_level_compaction =
      BottommostLevelCompaction::kForce;
  compact_options.exclusive_manual_compaction = exclusive_manual_compaction_;
@@ -3043,7 +3040,7 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
  // then compacte the bottommost level L3=>L3 (non trivial move)
  compact_options = CompactRangeOptions();
  compact_options.bottommost_level_compaction =
-      BottommostLevelCompaction::kForceOptimized;
+      BottommostLevelCompaction::kForce;
  ASSERT_OK(db_->CompactRange(compact_options, nullptr, nullptr));
  ASSERT_EQ("0,0,0,1", FilesPerLevel(0));
  ASSERT_EQ(trivial_move, 4);
@@ -3352,7 +3349,7 @@ TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
  options.level0_file_num_compaction_trigger = kNumLevelFiles;
  // inflate it a bit to account for key/metadata overhead
  options.target_file_size_base = 120 * kNumKeysPerFile * kValueSize / 100;
-  CreateAndReopenWithCF({"one"}, options);
+  Reopen(options);

  Random rnd(301);
  const Snapshot* snapshot = nullptr;
@@ -3383,12 +3380,10 @@ TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
  // just need to bump seqnum so ReleaseSnapshot knows the newest key in the SST
  // files does not need to be preserved in case of a future snapshot.
  ASSERT_OK(Put(Key(0), "val"));
-  ASSERT_NE(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
  // release snapshot and wait for compactions to finish. Single-file
  // compactions should be triggered, which reduce the size of each bottom-level
  // file without changing file count.
  db_->ReleaseSnapshot(snapshot);
-  ASSERT_EQ(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
  rocksdb::SyncPoint::GetInstance()->SetCallBack(
      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
@@ -3521,234 +3516,6 @@ TEST_F(DBCompactionTest, LevelCompactExpiredTtlFiles) {
  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }

-TEST_F(DBCompactionTest, LevelPeriodicCompaction) {
-  const int kNumKeysPerFile = 32;
-  const int kNumLevelFiles = 2;
-  const int kValueSize = 100;
-
-  Options options = CurrentOptions();
-  options.periodic_compaction_seconds = 48 * 60 * 60;  // 2 days
-  options.max_open_files = -1;       // needed for ttl compaction
-  env_->time_elapse_only_sleep_ = false;
-  options.env = env_;
-
-  env_->addon_time_.store(0);
-  DestroyAndReopen(options);
-
-  int periodic_compactions = 0;
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
-        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
-        auto compaction_reason = compaction->compaction_reason();
-        if (compaction_reason == CompactionReason::kPeriodicCompaction) {
-          periodic_compactions++;
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Random rnd(301);
-  for (int i = 0; i < kNumLevelFiles; ++i) {
-    for (int j = 0; j < kNumKeysPerFile; ++j) {
-      ASSERT_OK(
-          Put(Key(i * kNumKeysPerFile + j), RandomString(&rnd, kValueSize)));
-    }
-    Flush();
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  ASSERT_EQ("2", FilesPerLevel());
-  ASSERT_EQ(0, periodic_compactions);
-
-  // Add 50 hours and do a write
-  env_->addon_time_.fetch_add(50 * 60 * 60);
-  ASSERT_OK(Put("a", "1"));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  // Assert that the files stay in the same level
-  ASSERT_EQ("3", FilesPerLevel());
-  // The two old files go through the periodic compaction process
-  ASSERT_EQ(2, periodic_compactions);
-
-  MoveFilesToLevel(1);
-  ASSERT_EQ("0,3", FilesPerLevel());
-
-  // Add another 50 hours and do another write
-  env_->addon_time_.fetch_add(50 * 60 * 60);
-  ASSERT_OK(Put("b", "2"));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ("1,3", FilesPerLevel());
-  // The three old files now go through the periodic compaction process. 2 + 3.
-  ASSERT_EQ(5, periodic_compactions);
-
-  // Add another 50 hours and do another write
-  env_->addon_time_.fetch_add(50 * 60 * 60);
-  ASSERT_OK(Put("c", "3"));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ("2,3", FilesPerLevel());
-  // The four old files now go through the periodic compaction process. 5 + 4.
-  ASSERT_EQ(9, periodic_compactions);
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
-
-TEST_F(DBCompactionTest, LevelPeriodicCompactionWithOldDB) {
-  // This test makes sure that periodic compactions are working with a DB
-  // where file_creation_time of some files is 0.
-  // After compactions the new files are created with a valid file_creation_time
-
-  const int kNumKeysPerFile = 32;
-  const int kNumFiles = 4;
-  const int kValueSize = 100;
-
-  Options options = CurrentOptions();
-  options.max_open_files = -1;  // needed for ttl compaction
-  env_->time_elapse_only_sleep_ = false;
-  options.env = env_;
-
-  env_->addon_time_.store(0);
-  DestroyAndReopen(options);
-
-  int periodic_compactions = 0;
-  bool set_file_creation_time_to_zero = true;
-  bool set_creation_time_to_zero = true;
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
-        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
-        auto compaction_reason = compaction->compaction_reason();
-        if (compaction_reason == CompactionReason::kPeriodicCompaction) {
-          periodic_compactions++;
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "PropertyBlockBuilder::AddTableProperty:Start", [&](void* arg) {
-        TableProperties* props = reinterpret_cast<TableProperties*>(arg);
-        if (set_file_creation_time_to_zero) {
-          props->file_creation_time = 0;
-        }
-        if (set_creation_time_to_zero) {
-          props->creation_time = 0;
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Random rnd(301);
-  for (int i = 0; i < kNumFiles; ++i) {
-    for (int j = 0; j < kNumKeysPerFile; ++j) {
-      ASSERT_OK(
-          Put(Key(i * kNumKeysPerFile + j), RandomString(&rnd, kValueSize)));
-    }
-    Flush();
-    // Move the first two files to L2.
-    if (i == 1) {
-      MoveFilesToLevel(2);
-      set_creation_time_to_zero = false;
-    }
-  }
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-  ASSERT_EQ("2,0,2", FilesPerLevel());
-  ASSERT_EQ(0, periodic_compactions);
-
-  Close();
-
-  set_file_creation_time_to_zero = false;
-  // Forward the clock by 2 days.
-  env_->addon_time_.fetch_add(2 * 24 * 60 * 60);
-  options.periodic_compaction_seconds = 1 * 24 * 60 * 60;  // 1 day
-
-  Reopen(options);
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  ASSERT_EQ("2,0,2", FilesPerLevel());
-  // Make sure that all files go through periodic compaction.
-  ASSERT_EQ(kNumFiles, periodic_compactions);
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
-
-TEST_F(DBCompactionTest, LevelPeriodicAndTtlCompaction) {
-  const int kNumKeysPerFile = 32;
-  const int kNumLevelFiles = 2;
-  const int kValueSize = 100;
-
-  Options options = CurrentOptions();
-  options.ttl = 10 * 60 * 60;  // 10 hours
-  options.periodic_compaction_seconds = 48 * 60 * 60;  // 2 days
-  options.max_open_files = -1;   // needed for both periodic and ttl compactions
-  env_->time_elapse_only_sleep_ = false;
-  options.env = env_;
-
-  env_->addon_time_.store(0);
-  DestroyAndReopen(options);
-
-  int periodic_compactions = 0;
-  int ttl_compactions = 0;
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
-        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
-        auto compaction_reason = compaction->compaction_reason();
-        if (compaction_reason == CompactionReason::kPeriodicCompaction) {
-          periodic_compactions++;
-        } else if (compaction_reason == CompactionReason::kTtl) {
-          ttl_compactions++;
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Random rnd(301);
-  for (int i = 0; i < kNumLevelFiles; ++i) {
-    for (int j = 0; j < kNumKeysPerFile; ++j) {
-      ASSERT_OK(
-          Put(Key(i * kNumKeysPerFile + j), RandomString(&rnd, kValueSize)));
-    }
-    Flush();
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  MoveFilesToLevel(3);
-
-  ASSERT_EQ("0,0,0,2", FilesPerLevel());
-  ASSERT_EQ(0, periodic_compactions);
-  ASSERT_EQ(0, ttl_compactions);
-
-  // Add some time greater than periodic_compaction_time.
-  env_->addon_time_.fetch_add(50 * 60 * 60);
-  ASSERT_OK(Put("a", "1"));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  // Files in the bottom level go through periodic compactions.
-  ASSERT_EQ("1,0,0,2", FilesPerLevel());
-  ASSERT_EQ(2, periodic_compactions);
-  ASSERT_EQ(0, ttl_compactions);
-
-  // Add a little more time than ttl
-  env_->addon_time_.fetch_add(11 * 60 * 60);
-  ASSERT_OK(Put("b", "1"));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  // Notice that the previous file in level 1 falls down to the bottom level
-  // due to ttl compactions, one level at a time.
-  // And bottom level files don't get picked up for ttl compactions.
-  ASSERT_EQ("1,0,0,3", FilesPerLevel());
-  ASSERT_EQ(2, periodic_compactions);
-  ASSERT_EQ(3, ttl_compactions);
-
-  // Add some time greater than periodic_compaction_time.
-  env_->addon_time_.fetch_add(50 * 60 * 60);
-  ASSERT_OK(Put("c", "1"));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  // Previous L0 file falls one level at a time to bottom level due to ttl.
-  // And all 4 bottom files go through periodic compactions.
-  ASSERT_EQ("1,0,0,4", FilesPerLevel());
-  ASSERT_EQ(6, periodic_compactions);
-  ASSERT_EQ(6, ttl_compactions);
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
-
-
 TEST_F(DBCompactionTest, CompactRangeDelayedByL0FileCount) {
  // Verify that, when `CompactRangeOptions::allow_write_stall == false`, manual
  // compaction only triggers flush after it's sure stall won't be triggered for
@@ -3891,17 +3658,11 @@ TEST_F(DBCompactionTest, CompactRangeShutdownWhileDelayed) {
      }
      Flush(1);
    }
-    auto manual_compaction_thread = port::Thread([this, i]() {
+    auto manual_compaction_thread = port::Thread([this]() {
      CompactRangeOptions cro;
      cro.allow_write_stall = false;
-      Status s = db_->CompactRange(cro, handles_[1], nullptr, nullptr);
-      if (i == 0) {
-        ASSERT_TRUE(db_->CompactRange(cro, handles_[1], nullptr, nullptr)
-                        .IsColumnFamilyDropped());
-      } else {
-        ASSERT_TRUE(db_->CompactRange(cro, handles_[1], nullptr, nullptr)
-                        .IsShutdownInProgress());
-      }
+      ASSERT_TRUE(db_->CompactRange(cro, handles_[1], nullptr, nullptr)
+                      .IsShutdownInProgress());
    });

    TEST_SYNC_POINT(
@@ -4165,7 +3926,7 @@ TEST_F(DBCompactionTest, CompactionLimiter) {

  const char* cf_names[] = {"default", "0", "1", "2", "3", "4", "5",
    "6", "7", "8", "9", "a", "b", "c", "d", "e", "f" };
-  const unsigned int cf_count = sizeof cf_names / sizeof cf_names[0];
+  const int cf_count = sizeof cf_names / sizeof cf_names[0];

  std::unordered_map<std::string, CompactionLimiter*> cf_to_limiter;

@@ -4184,7 +3945,7 @@ TEST_F(DBCompactionTest, CompactionLimiter) {
  std::vector<Options> option_vector;
  option_vector.reserve(cf_count);

-  for (unsigned int cf = 0; cf < cf_count; cf++) {
+  for (int cf = 0; cf < cf_count; cf++) {
    ColumnFamilyOptions cf_opt(options);
    if (cf == 0) {
      // "Default" CF does't use compaction limiter
@@ -4202,7 +3963,7 @@ TEST_F(DBCompactionTest, CompactionLimiter) {
    option_vector.emplace_back(DBOptions(options), cf_opt);
  }

-  for (unsigned int cf = 1; cf < cf_count; cf++) {
+  for (int cf = 1; cf < cf_count; cf++) {
    CreateColumnFamilies({cf_names[cf]}, option_vector[cf]);
  }

@@ -4254,7 +4015,7 @@ TEST_F(DBCompactionTest, CompactionLimiter) {
  int keyIndex = 0;

  for (int n = 0; n < options.level0_file_num_compaction_trigger; n++) {
-    for (unsigned int cf = 0; cf < cf_count; cf++) {
+    for (int cf = 0; cf < cf_count; cf++) {
      for (int i = 0; i < kNumKeysPerFile; i++) {
        ASSERT_OK(Put(cf, Key(keyIndex++), ""));
      }
@@ -4262,13 +4023,13 @@ TEST_F(DBCompactionTest, CompactionLimiter) {
      ASSERT_OK(Put(cf, "", ""));
    }

-    for (unsigned int cf = 0; cf < cf_count; cf++) {
+    for (int cf = 0; cf < cf_count; cf++) {
      dbfull()->TEST_WaitForFlushMemTable(handles_[cf]);
    }
  }

  // Enough L0 files to trigger compaction
-  for (unsigned int cf = 0; cf < cf_count; cf++) {
+  for (int cf = 0; cf < cf_count; cf++) {
    ASSERT_EQ(NumTableFilesAtLevel(0, cf),
      options.level0_file_num_compaction_trigger);
  }
@@ -4295,7 +4056,7 @@ TEST_F(DBCompactionTest, CompactionLimiter) {
    sleeping_compact_tasks[i].WaitUntilDone();
  }

-  for (unsigned int cf = 0; cf < cf_count; cf++) {
+  for (int cf = 0; cf < cf_count; cf++) {
    dbfull()->TEST_WaitForFlushMemTable(handles_[cf]);
  }

@@ -4340,6 +4101,12 @@ TEST_P(DBCompactionDirectIOTest, DirectIO) {
  options.env = new MockEnv(Env::Default());
  Reopen(options);
  bool readahead = false;
+  SyncPoint::GetInstance()->SetCallBack(
+      "TableCache::NewIterator:for_compaction", [&](void* arg) {
+        bool* use_direct_reads = static_cast<bool*>(arg);
+        ASSERT_EQ(*use_direct_reads,
+                  options.use_direct_reads);
+      });
  SyncPoint::GetInstance()->SetCallBack(
      "CompactionJob::OpenCompactionOutputFile", [&](void* arg) {
        bool* use_direct_writes = static_cast<bool*>(arg);
@@ -4420,14 +4187,14 @@ class NoopMergeOperator : public MergeOperator {
 public:
  NoopMergeOperator() {}

-  bool FullMergeV2(const MergeOperationInput& /*merge_in*/,
-                   MergeOperationOutput* merge_out) const override {
+  virtual bool FullMergeV2(const MergeOperationInput& /*merge_in*/,
+                           MergeOperationOutput* merge_out) const override {
    std::string val("bar");
    merge_out->new_value = val;
    return true;
  }

-  const char* Name() const override { return "Noop"; }
+  virtual const char* Name() const override { return "Noop"; }
 };

 TEST_F(DBCompactionTest, PartialManualCompaction) {
@@ -4456,7 +4223,7 @@ TEST_F(DBCompactionTest, PartialManualCompaction) {
      {{"max_compaction_bytes", std::to_string(max_compaction_bytes)}}));

  CompactRangeOptions cro;
-  cro.bottommost_level_compaction = BottommostLevelCompaction::kForceOptimized;
+  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
  dbfull()->CompactRange(cro, nullptr, nullptr);
 }

@@ -4500,88 +4267,6 @@ TEST_F(DBCompactionTest, ManualCompactionFailsInReadOnlyMode) {
  Close();
 }

-// ManualCompactionBottomLevelOptimization tests the bottom level manual
-// compaction optimization to skip recompacting files created by Ln-1 to Ln
-// compaction
-TEST_F(DBCompactionTest, ManualCompactionBottomLevelOptimized) {
-  Options opts = CurrentOptions();
-  opts.num_levels = 3;
-  opts.level0_file_num_compaction_trigger = 5;
-  opts.compression = kNoCompression;
-  opts.merge_operator.reset(new NoopMergeOperator());
-  opts.target_file_size_base = 1024;
-  opts.max_bytes_for_level_multiplier = 2;
-  opts.disable_auto_compactions = true;
-  DestroyAndReopen(opts);
-  ColumnFamilyHandleImpl* cfh =
-      static_cast<ColumnFamilyHandleImpl*>(dbfull()->DefaultColumnFamily());
-  ColumnFamilyData* cfd = cfh->cfd();
-  InternalStats* internal_stats_ptr = cfd->internal_stats();
-  ASSERT_NE(internal_stats_ptr, nullptr);
-
-  Random rnd(301);
-  for (auto i = 0; i < 8; ++i) {
-    for (auto j = 0; j < 10; ++j) {
-      ASSERT_OK(
-          Put("foo" + std::to_string(i * 10 + j), RandomString(&rnd, 1024)));
-    }
-    Flush();
-  }
-
-  MoveFilesToLevel(2);
-
-  for (auto i = 0; i < 8; ++i) {
-    for (auto j = 0; j < 10; ++j) {
-      ASSERT_OK(
-          Put("bar" + std::to_string(i * 10 + j), RandomString(&rnd, 1024)));
-    }
-    Flush();
-  }
-  const std::vector<InternalStats::CompactionStats>& comp_stats =
-      internal_stats_ptr->TEST_GetCompactionStats();
-  int num = comp_stats[2].num_input_files_in_output_level;
-  ASSERT_EQ(num, 0);
-
-  CompactRangeOptions cro;
-  cro.bottommost_level_compaction = BottommostLevelCompaction::kForceOptimized;
-  dbfull()->CompactRange(cro, nullptr, nullptr);
-
-  const std::vector<InternalStats::CompactionStats>& comp_stats2 =
-      internal_stats_ptr->TEST_GetCompactionStats();
-  num = comp_stats2[2].num_input_files_in_output_level;
-  ASSERT_EQ(num, 0);
-}
-
-TEST_F(DBCompactionTest, CompactionDuringShutdown) {
-  Options opts = CurrentOptions();
-  opts.level0_file_num_compaction_trigger = 2;
-  opts.disable_auto_compactions = true;
-  DestroyAndReopen(opts);
-  ColumnFamilyHandleImpl* cfh =
-      static_cast<ColumnFamilyHandleImpl*>(dbfull()->DefaultColumnFamily());
-  ColumnFamilyData* cfd = cfh->cfd();
-  InternalStats* internal_stats_ptr = cfd->internal_stats();
-  ASSERT_NE(internal_stats_ptr, nullptr);
-
-  Random rnd(301);
-  for (auto i = 0; i < 2; ++i) {
-    for (auto j = 0; j < 10; ++j) {
-      ASSERT_OK(
-          Put("foo" + std::to_string(i * 10 + j), RandomString(&rnd, 1024)));
-    }
-    Flush();
-  }
-
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::BackgroundCompaction:NonTrivial:BeforeRun",
-      [&](void* /*arg*/) {
-    dbfull()->shutting_down_.store(true);
-  });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_OK(dbfull()->error_handler_.GetBGError());
-}
-
 // FixFileIngestionCompactionDeadlock tests and verifies that compaction and
 // file ingestion do not cause deadlock in the event of write stall triggered
 // by number of L0 files reaching level0_stop_writes_trigger.
@@ -4658,31 +4343,7 @@ TEST_P(DBCompactionTestWithParam, FixFileIngestionCompactionDeadlock) {
  ASSERT_OK(dbfull()->TEST_WaitForCompact());
  Close();
 }
-TEST_F(DBCompactionTest, ConsistencyFailTest) {
-  Options options = CurrentOptions();
-  DestroyAndReopen(options);

-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "VersionBuilder::CheckConsistency", [&](void* arg) {
-        auto p =
-            reinterpret_cast<std::pair<FileMetaData**, FileMetaData**>*>(arg);
-        // just swap the two FileMetaData so that we hit error
-        // in CheckConsistency funcion
-        FileMetaData* temp = *(p->first);
-        *(p->first) = *(p->second);
-        *(p->second) = temp;
-      });
-
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  for (int k = 0; k < 2; ++k) {
-    ASSERT_OK(Put("foo", "bar"));
-    Flush();
-  }
-
-  ASSERT_NOK(Put("foo", "bar"));
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
 #endif // !defined(ROCKSDB_LITE)
 }  // namespace rocksdb

@@ -7,7 +7,7 @@
 #include "port/stack_trace.h"
 #include "rocksdb/perf_context.h"
 #if !defined(ROCKSDB_LITE)
-#include "test_util/sync_point.h"
+#include "util/sync_point.h"
 #endif
 #include <iostream>
 #include <string>
@@ -83,34 +83,6 @@ TEST_F(DBEncryptionTest, CheckEncrypted) {
  }
 }

-TEST_F(DBEncryptionTest, ReadEmptyFile) {
-  auto defaultEnv = Env::Default();
-
-  // create empty file for reading it back in later
-  auto envOptions = EnvOptions(CurrentOptions());
-  auto filePath = dbname_ + "/empty.empty";
-
-  Status status;
-  {
-    std::unique_ptr<WritableFile> writableFile;
-    status = defaultEnv->NewWritableFile(filePath, &writableFile, envOptions);
-    ASSERT_OK(status);
-  }
-
-  std::unique_ptr<SequentialFile> seqFile;
-  status = defaultEnv->NewSequentialFile(filePath, &seqFile, envOptions);
-  ASSERT_OK(status);
-
-  std::string scratch;
-  Slice data;
-  // reading back 16 bytes from the empty file shouldn't trigger an assertion.
-  // it should just work and return an empty string
-  status = seqFile->Read(16, &data, (char*)scratch.data());
-  ASSERT_OK(status);
-
-  ASSERT_TRUE(data.empty());
-}
-
 #endif // ROCKSDB_LITE

 }  // namespace rocksdb