Add 6.24.2

Summary:
Potential bugs in the IO uring implementation can cause bad data to be returned in the completion queue. Add some checks in the PosixRandomAccessFile::MultiRead completion handling code to catch such errors and fail the entire MultiRead. Also log some diagnostic messages and stack trace.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/8894

Reviewed By: siying, pdillinger

Differential Revision: D30826982

Pulled By: anand1976

fbshipit-source-id: af91815ac760e095d6cc0466cf8bd5c10167fd15

.circleci/config.yml

@@ -49,6 +49,9 @@ commands:
             echo "export GTEST_OUTPUT=\"xml:/tmp/test-results/\"" >> $BASH_ENV
             echo "export SKIP_FORMAT_BUCK_CHECKS=1" >> $BASH_ENV
             echo "export PRINT_PARALLEL_OUTPUTS=1" >> $BASH_ENV
+            echo "export GTEST_COLOR=1" >> $BASH_ENV
+            echo "export CTEST_OUTPUT_ON_FAILURE=1" >> $BASH_ENV
+            echo "export CTEST_TEST_TIMEOUT=300" >> $BASH_ENV
 
   pre-steps-macos:
       steps:
@@ -88,6 +91,21 @@ commands:
           command: |
             sudo apt-get update -y && sudo apt-get install -y libgflags-dev
 
+  install-benchmark:
+    steps:
+      - run: # currently doesn't support ubuntu-1604 which doesn't have libbenchmark package, user can still install by building it youself
+          name: Install benchmark
+          command: |
+            sudo apt-get update -y && sudo apt-get install -y libbenchmark-dev
+
+  upgrade-cmake:
+    steps:
+      - run:
+          name: Upgrade cmake
+          command: |
+            sudo apt remove --purge cmake
+            sudo snap install cmake --classic
+
   install-gflags-on-macos:
     steps:
       - run:
@@ -140,12 +158,12 @@ jobs:
       - install-cmake-on-macos
       - install-gflags-on-macos
       - pre-steps-macos
-      - run: ulimit -S -n 1048576 && (mkdir build && cd build && cmake -DWITH_GFLAGS=1 .. && make V=1 -j32) | .circleci/cat_ignore_eagain
+      - run: ulimit -S -n 1048576 && (mkdir build && cd build && cmake -DWITH_GFLAGS=1 .. && make V=1 -j32 && ctest -j10) | .circleci/cat_ignore_eagain
       - post-steps
 
   build-linux:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -155,7 +173,7 @@ jobs:
 
   build-linux-mem-env:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -165,7 +183,7 @@ jobs:
 
   build-linux-encrypted-env:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -175,7 +193,7 @@ jobs:
 
   build-linux-shared_lib-alt_namespace-status_checked:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -185,7 +203,7 @@ jobs:
 
   build-linux-release:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: large
     steps:
       - checkout # check out the code in the project directory
@@ -212,7 +230,7 @@ jobs:
 
   build-linux-lite:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -222,7 +240,7 @@ jobs:
 
   build-linux-lite-release:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: large
     steps:
       - checkout # check out the code in the project directory
@@ -235,7 +253,7 @@ jobs:
 
   build-linux-clang-no_test_run:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: xlarge
     steps:
       - checkout # check out the code in the project directory
@@ -245,7 +263,7 @@ jobs:
 
   build-linux-clang10-asan:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -256,7 +274,7 @@ jobs:
 
   build-linux-clang10-mini-tsan:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -267,7 +285,7 @@ jobs:
 
   build-linux-clang10-ubsan:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -278,7 +296,7 @@ jobs:
 
   build-linux-clang10-clang-analyze:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -288,13 +306,26 @@ jobs:
       - run: CC=clang-10 CXX=clang++-10 ROCKSDB_DISABLE_ALIGNED_NEW=1 CLANG_ANALYZER="/usr/bin/clang++-10" CLANG_SCAN_BUILD=scan-build-10 USE_CLANG=1 make V=1 -j32 analyze | .circleci/cat_ignore_eagain # aligned new doesn't work for reason we haven't figured out. For unknown, reason passing "clang++-10" as CLANG_ANALYZER doesn't work, and we need a full path.
       - post-steps
 
-  build-linux-cmake-no_test_run:
+  build-linux-cmake:
     machine:
-      image: ubuntu-1604:202007-01
-    resource_class: large
+      image: ubuntu-1604:202104-01
+    resource_class: 2xlarge
     steps:
-      - checkout # check out the code in the project directory
-      - run: (mkdir build && cd build && cmake -DWITH_GFLAGS=0 .. && make V=1 -j8) | .circleci/cat_ignore_eagain
+      - pre-steps
+      - install-gflags
+      - upgrade-cmake
+      - run: (mkdir build && cd build && cmake -DWITH_GFLAGS=1 .. && make V=1 -j20 && ctest -j20) | .circleci/cat_ignore_eagain
+      - post-steps
+
+  build-linux-cmake-ubuntu-20:
+    machine:
+      image: ubuntu-2004:202104-01
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - install-gflags
+      - install-benchmark
+      - run: (mkdir build && cd build && cmake -DWITH_GFLAGS=1 -DWITH_BENCHMARK=1 .. && make V=1 -j20 && ctest -j20 && make microbench) | .circleci/cat_ignore_eagain
       - post-steps
 
   build-linux-unity:
@@ -309,7 +340,7 @@ jobs:
 
   build-linux-gcc-4_8-no_test_run:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: large
     steps:
       - pre-steps
@@ -347,6 +378,17 @@ jobs:
       - run: CC=gcc-10 CXX=g++-10 V=1 SKIP_LINK=1 ROCKSDB_CXX_STANDARD=c++20 make -j16 all | .circleci/cat_ignore_eagain # Linking broken because libgflags compiled with newer ABI
       - post-steps
 
+  # This job is only to make sure the microbench tests are able to run, the benchmark result is not meaningful as the CI host is changing.
+  build-linux-microbench:
+    machine:
+      image: ubuntu-2004:202010-01
+    resource_class: xlarge
+    steps:
+      - pre-steps
+      - install-benchmark
+      - run: DEBUG_LEVEL=0 make microbench | .circleci/cat_ignore_eagain
+      - post-steps
+
   build-windows:
     executor: windows-2xlarge
     parameters:
@@ -417,7 +459,7 @@ jobs:
 
   build-linux-java:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: large
     environment:
       JAVA_HOME: /usr/lib/jvm/java-1.8.0-openjdk-amd64
@@ -441,7 +483,7 @@ jobs:
 
   build-linux-java-static:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: large
     environment:
       JAVA_HOME: /usr/lib/jvm/java-1.8.0-openjdk-amd64
@@ -512,7 +554,7 @@ jobs:
 
   build-examples:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: large
     steps:
       - pre-steps
@@ -525,7 +567,7 @@ jobs:
 
   build-cmake-mingw:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -548,7 +590,7 @@ jobs:
 
   build-linux-non-shm:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     parameters:
       start_test:
@@ -604,6 +646,7 @@ jobs:
       JAVA_HOME: /usr/lib/jvm/java-8-openjdk-arm64
     steps:
       - pre-steps
+      - install-gflags
       - run:
           name: "Set Java Environment"
           command: |
@@ -616,7 +659,7 @@ jobs:
           command: |
             mkdir build
             cd build
-            cmake -DCMAKE_BUILD_TYPE=Release -DWITH_TESTS=0 -DWITH_GFLAGS=0 -DWITH_BENCHMARK_TOOLS=0 -DWITH_TOOLS=0 -DWITH_CORE_TOOLS=1 ..
+            cmake -DCMAKE_BUILD_TYPE=Release -DWITH_TESTS=0 -DWITH_GFLAGS=1 -DWITH_BENCHMARK_TOOLS=0 -DWITH_TOOLS=0 -DWITH_CORE_TOOLS=1 ..
             make -j4
       - run:
           name: "Build Java with cmake"
@@ -624,13 +667,13 @@ jobs:
             rm -rf build
             mkdir build
             cd build
-            cmake -DJNI=1 -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=0 ..
+            cmake -DJNI=1 -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 ..
             make -j4 rocksdb rocksdbjni
       - post-steps
 
   build-format-compatible:
     machine:
-      image: ubuntu-1604:202007-01
+      image: ubuntu-1604:202104-01
     resource_class: 2xlarge
     steps:
       - pre-steps
@@ -650,6 +693,10 @@ workflows:
   build-linux:
     jobs:
       - build-linux
+  build-linux-cmake:
+    jobs:
+      - build-linux-cmake
+      - build-linux-cmake-ubuntu-20
   build-linux-mem-env:
     jobs:
       - build-linux-mem-env
@@ -701,12 +748,6 @@ workflows:
           name: "build-windows-vs2017"
           vs_year: "2017"
           cmake_generator: "Visual Studio 15 Win64"
-#  build-windows-vs2015:
-#    jobs:
-#      - build-windows:
-#          name: "build-windows-vs2015"
-#          vs_year: "2015"
-#          cmake_generator: "Visual Studio 14 Win64"
   build-java:
     jobs:
       - build-linux-java
@@ -733,7 +774,6 @@ workflows:
   build-linux-compilers-no_test_run:
     jobs:
       - build-linux-clang-no_test_run
-      - build-linux-cmake-no_test_run
       - build-linux-gcc-4_8-no_test_run
       - build-linux-gcc-8-no_test_run
       - build-linux-gcc-9-no_test_run
@@ -751,6 +791,9 @@ workflows:
   build-linux-arm:
     jobs:
       - build-linux-arm
+  build-microbench:
+    jobs:
+      - build-linux-microbench
   nightly:
     triggers:
       - schedule:

CMakeLists.txt

@@ -32,10 +32,11 @@
 # 3. cmake ..
 # 4. make -j
 
-cmake_minimum_required(VERSION 3.5.1)
+cmake_minimum_required(VERSION 3.10)
 
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
 include(ReadVersion)
+include(GoogleTest)
 get_rocksdb_version(rocksdb_VERSION)
 project(rocksdb
   VERSION ${rocksdb_VERSION}
@@ -71,6 +72,12 @@ option(WITH_WINDOWS_UTF8_FILENAMES "use UTF8 as characterset for opening files,
 if (WITH_WINDOWS_UTF8_FILENAMES)
   add_definitions(-DROCKSDB_WINDOWS_UTF8_FILENAMES)
 endif()
+
+if ($ENV{CIRCLECI})
+  message(STATUS "Build for CircieCI env, a few tests may be disabled")
+  add_definitions(-DCIRCLECI)
+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|Windows")
@@ -123,11 +130,11 @@ else()
         set(GFLAGS_LIB ${GFLAGS_TARGET})
       else()
         # Config with GFLAGS_LIBRARIES available since gflags 2.1.0
-        set(GFLAGS_LIB ${GFLAGS_LIBRARIES})
+        set(GFLAGS_LIB ${gflags_LIBRARIES})
       endif()
     else()
       find_package(gflags REQUIRED)
-        set(GFLAGS_LIB gflags::gflags)
+      set(GFLAGS_LIB gflags::gflags)
     endif()
     include_directories(${GFLAGS_INCLUDE_DIR})
     list(APPEND THIRDPARTY_LIBS ${GFLAGS_LIB})
@@ -211,7 +218,7 @@ if(MSVC)
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4800 /wd4996 /wd4351 /wd4100 /wd4204 /wd4324")
 else()
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall -pthread")
   set(CMAKE_CXX_FLAGS "${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(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64")
     set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wstrict-prototypes")
@@ -621,12 +628,14 @@ set(SOURCES
         cache/lru_cache.cc
         cache/sharded_cache.cc
         db/arena_wrapped_db_iter.cc
+        db/blob/blob_fetcher.cc
         db/blob/blob_file_addition.cc
         db/blob/blob_file_builder.cc
         db/blob/blob_file_cache.cc
         db/blob/blob_file_garbage.cc
         db/blob/blob_file_meta.cc
         db/blob/blob_file_reader.cc
+        db/blob/blob_garbage_meter.cc
         db/blob/blob_log_format.cc
         db/blob/blob_log_sequential_reader.cc
         db/blob/blob_log_writer.cc
@@ -807,9 +816,12 @@ set(SOURCES
         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
         trace_replay/io_tracer.cc
+        trace_replay/trace_record_handler.cc
+        trace_replay/trace_record_result.cc
+        trace_replay/trace_record.cc
+        trace_replay/trace_replay.cc
         util/coding.cc
         util/compaction_job_stats_impl.cc
         util/comparator.cc
@@ -840,6 +852,7 @@ set(SOURCES
         utilities/cassandra/format.cc
         utilities/cassandra/merge_operator.cc
         utilities/checkpoint/checkpoint_impl.cc
+        utilities/compaction_filters.cc
         utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
         utilities/debug.cc
         utilities/env_mirror.cc
@@ -848,6 +861,7 @@ set(SOURCES
         utilities/fault_injection_fs.cc
         utilities/leveldb_options/leveldb_options.cc
         utilities/memory/memory_util.cc
+        utilities/merge_operators.cc
         utilities/merge_operators/bytesxor.cc
         utilities/merge_operators/max.cc
         utilities/merge_operators/put.cc
@@ -867,6 +881,7 @@ set(SOURCES
         utilities/simulator_cache/sim_cache.cc
         utilities/table_properties_collectors/compact_on_deletion_collector.cc
         utilities/trace/file_trace_reader_writer.cc
+        utilities/trace/replayer_impl.cc
         utilities/transactions/lock/lock_manager.cc
         utilities/transactions/lock/point/point_lock_tracker.cc
         utilities/transactions/lock/point/point_lock_manager.cc
@@ -925,13 +940,8 @@ if(WIN32)
     port/win/env_win.cc
     port/win/env_default.cc
     port/win/port_win.cc
-    port/win/win_logger.cc)
-  if(NOT MINGW)
-    # Mingw only supports std::thread when using
-    # posix threads.
-    list(APPEND SOURCES
-      port/win/win_thread.cc)
-  endif()
+    port/win/win_logger.cc
+    port/win/win_thread.cc)
 if(WITH_XPRESS)
   list(APPEND SOURCES
     port/win/xpress_win.cc)
@@ -1115,17 +1125,20 @@ if(WITH_TESTS)
     list(APPEND TESTS
         cache/cache_test.cc
         cache/lru_cache_test.cc
+        db/blob/blob_counting_iterator_test.cc
         db/blob/blob_file_addition_test.cc
         db/blob/blob_file_builder_test.cc
         db/blob/blob_file_cache_test.cc
         db/blob/blob_file_garbage_test.cc
         db/blob/blob_file_reader_test.cc
+        db/blob/blob_garbage_meter_test.cc
         db/blob/db_blob_basic_test.cc
         db/blob/db_blob_compaction_test.cc
         db/blob/db_blob_corruption_test.cc
         db/blob/db_blob_index_test.cc
         db/column_family_test.cc
         db/compact_files_test.cc
+        db/compaction/clipping_iterator_test.cc
         db/compaction/compaction_job_stats_test.cc
         db/compaction/compaction_job_test.cc
         db/compaction/compaction_iterator_test.cc
@@ -1321,21 +1334,21 @@ if(WITH_TESTS)
 
   foreach(sourcefile ${TESTS})
       get_filename_component(exename ${sourcefile} NAME_WE)
-      add_executable(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} ${sourcefile})
-      set_target_properties(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX}
+      add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+      set_target_properties(${exename}${ARTIFACT_SUFFIX}
         PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
         EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
         EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
         OUTPUT_NAME ${exename}${ARTIFACT_SUFFIX}
       )
-      target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} testharness gtest ${THIRDPARTY_LIBS} ${ROCKSDB_LIB})
+      target_link_libraries(${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} testharness gtest ${THIRDPARTY_LIBS} ${ROCKSDB_LIB})
       if(NOT "${exename}" MATCHES "db_sanity_test")
-        add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
-        add_dependencies(check ${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX})
+        gtest_discover_tests(${exename} DISCOVERY_TIMEOUT 120)
+        add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
       endif()
       if("${exename}" MATCHES "env_librados_test")
         # env_librados_test.cc uses librados directly
-        target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} rados)
+        target_link_libraries(${exename}${ARTIFACT_SUFFIX} rados)
       endif()
   endforeach(sourcefile ${TESTS})
 
@@ -1415,3 +1428,8 @@ option(WITH_EXAMPLES "build with examples" OFF)
 if(WITH_EXAMPLES)
   add_subdirectory(examples)
 endif()
+
+option(WITH_BENCHMARK "build benchmark tests" OFF)
+if(WITH_BENCHMARK)
+  add_subdirectory(${PROJECT_SOURCE_DIR}/microbench/)
+endif()

HISTORY.md

@@ -1,5 +1,97 @@
 # Rocksdb Change Log
-## Unreleased
+## 6.24.2 (2021-09-16)
+### Bug Fixes
+* Add checks for validity of the IO uring completion queue entries, and fail the BlockBasedTableReader MultiGet sub-batch if there's an invalid completion
+
+## 6.24.1 (2021-08-31)
+### Bug Fixes
+* Fix a race in item ref counting in LRUCache when promoting an item from the SecondaryCache.
+
+## 6.24.0 (2021-08-20)
+### Bug Fixes
+* If the primary's CURRENT file is missing or inaccessible, the secondary instance should not hang repeatedly trying to switch to a new MANIFEST. It should instead return the error code encountered while accessing the file.
+* Restoring backups with BackupEngine is now a logically atomic operation, so that if a restore operation is interrupted, DB::Open on it will fail. Using BackupEngineOptions::sync (default) ensures atomicity even in case of power loss or OS crash.
+* Fixed a race related to the destruction of `ColumnFamilyData` objects. The earlier logic unlocked the DB mutex before destroying the thread-local `SuperVersion` pointers, which could result in a process crash if another thread managed to get a reference to the `ColumnFamilyData` object.
+* Removed a call to `RenameFile()` on a non-existent info log file ("LOG") when opening a new DB. Such a call was guaranteed to fail though did not impact applications since we swallowed the error. Now we also stopped swallowing errors in renaming "LOG" file.
+* Fixed an issue where `OnFlushCompleted` was not called for atomic flush.
+* Fixed a bug affecting the batched `MultiGet` API when used with keys spanning multiple column families and `sorted_input == false`.
+* Fixed a potential incorrect result in opt mode and assertion failures caused by releasing snapshot(s) during compaction.
+* Fixed passing of BlobFileCompletionCallback to Compaction job and Atomic flush job which was default paramter (nullptr). BlobFileCompletitionCallback is internal callback that manages addition of blob files to SSTFileManager.
+* Fixed MultiGet not updating the block_read_count and block_read_byte PerfContext counters
+
+### New Features
+* Made the EventListener extend the Customizable class.
+* EventListeners that have a non-empty Name() and that are registered with the ObjectRegistry can now be serialized to/from the OPTIONS file.
+* Insert warm blocks (data blocks, uncompressed dict blocks, index and filter blocks) in Block cache during flush under option BlockBasedTableOptions.prepopulate_block_cache. Previously it was enabled for only data blocks.
+* BlockBasedTableOptions.prepopulate_block_cache can be dynamically configured using DB::SetOptions.
+* Add CompactionOptionsFIFO.age_for_warm, which allows RocksDB to move old files to warm tier in FIFO compactions. Note that file temperature is still an experimental feature.
+* Add a comment to suggest btrfs user to disable file preallocation by setting `options.allow_fallocate=false`.
+* Fast forward option in Trace replay changed to double type to allow replaying at a lower speed, by settings the value between 0 and 1. This option can be set via `ReplayOptions` in `Replayer::Replay()`, or via `--trace_replay_fast_forward` in db_bench.
+* Add property `LiveSstFilesSizeAtTemperature` to retrieve sst file size at different temperature.
+* Added a stat rocksdb.secondary.cache.hits
+* Added a PerfContext counter secondary_cache_hit_count
+* The integrated BlobDB implementation now supports the tickers `BLOB_DB_BLOB_FILE_BYTES_READ`, `BLOB_DB_GC_NUM_KEYS_RELOCATED`, and `BLOB_DB_GC_BYTES_RELOCATED`, as well as the histograms `BLOB_DB_COMPRESSION_MICROS` and `BLOB_DB_DECOMPRESSION_MICROS`.
+* Added hybrid configuration of Ribbon filter and Bloom filter where some LSM levels use Ribbon for memory space efficiency and some use Bloom for speed. See NewRibbonFilterPolicy. This also changes the default behavior of NewRibbonFilterPolicy to use Bloom for flushes under Leveled and Universal compaction and Ribbon otherwise. The C API function `rocksdb_filterpolicy_create_ribbon` is unchanged but adds new `rocksdb_filterpolicy_create_ribbon_hybrid`.
+
+### Public API change
+* Added APIs to decode and replay trace file via Replayer class. Added `DB::NewDefaultReplayer()` to create a default Replayer instance. Added `TraceReader::Reset()` to restart reading a trace file. Created trace_record.h, trace_record_result.h and utilities/replayer.h files to access the decoded Trace records, replay them, and query the actual operation results.
+* Added Configurable::GetOptionsMap to the public API for use in creating new Customizable classes.
+* Generalized bits_per_key parameters in C API from int to double for greater configurability. Although this is a compatible change for existing C source code, anything depending on C API signatures, such as foreign function interfaces, will need to be updated.
+
+### Performance Improvements
+* Try to avoid updating DBOptions if `SetDBOptions()` does not change any option value.
+
+### Behavior Changes
+* `StringAppendOperator` additionally accepts a string as the delimiter.
+* BackupEngineOptions::sync (default true) now applies to restoring backups in addition to creating backups. This could slow down restores, but ensures they are fully persisted before returning OK. (Consider increasing max_background_operations to improve performance.)
+
+## 6.23.0 (2021-07-16)
+### Behavior Changes
+* Obsolete keys in the bottommost level that were preserved for a snapshot will now be cleaned upon snapshot release in all cases. This form of compaction (snapshot release triggered compaction) previously had an artificial limitation that multiple tombstones needed to be present.
+### Bug Fixes
+* Blob file checksums are now printed in hexadecimal format when using the `manifest_dump` `ldb` command.
+* `GetLiveFilesMetaData()` now populates the `temperature`, `oldest_ancester_time`, and `file_creation_time` fields of its `LiveFileMetaData` results when the information is available. Previously these fields always contained zero indicating unknown.
+* Fix mismatches of OnCompaction{Begin,Completed} in case of DisableManualCompaction().
+* Fix continuous logging of an existing background error on every user write
+* Fix a bug that `Get()` return Status::OK() and an empty value for non-existent key when `read_options.read_tier = kBlockCacheTier`.
+* Fix a bug that stat in `get_context` didn't accumulate to statistics when query is failed.
+* Fixed handling of DBOptions::wal_dir with LoadLatestOptions() or ldb --try_load_options on a copied or moved DB. Previously, when the WAL directory is same as DB directory (default), a copied or moved DB would reference the old path of the DB as the WAL directory, potentially corrupting both copies. Under this change, the wal_dir from DB::GetOptions() or LoadLatestOptions() may now be empty, indicating that the current DB directory is used for WALs. This is also a subtle API change.
+
+### New Features
+* ldb has a new feature, `list_live_files_metadata`, that shows the live SST files, as well as their LSM storage level and the column family they belong to.
+* The new BlobDB implementation now tracks the amount of garbage in each blob file in the MANIFEST.
+* Integrated BlobDB now supports Merge with base values (Put/Delete etc.).
+* RemoteCompaction supports sub-compaction, the job_id in the user interface is changed from `int` to `uint64_t` to support sub-compaction id.
+* Expose statistics option in RemoteCompaction worker.
+
+### Public API change
+* Added APIs to the Customizable class to allow developers to create their own Customizable classes.  Created the utilities/customizable_util.h file to contain helper methods for developing new Customizable classes.
+* Change signature of SecondaryCache::Name().  Make SecondaryCache customizable and add SecondaryCache::CreateFromString method.
+
+## 6.22.0 (2021-06-18)
+### Behavior Changes
+* Added two additional tickers, MEMTABLE_PAYLOAD_BYTES_AT_FLUSH and MEMTABLE_GARBAGE_BYTES_AT_FLUSH. These stats can be used to estimate the ratio of "garbage" (outdated) bytes in the memtable that are discarded at flush time.
+* Added API comments clarifying safe usage of Disable/EnableManualCompaction and EventListener callbacks for compaction.
+### Bug Fixes
+* fs_posix.cc GetFreeSpace() always report disk space available to root even when running as non-root.  Linux defaults often have disk mounts with 5 to 10 percent of total space reserved only for root.  Out of space could result for non-root users.
+* Subcompactions are now disabled when user-defined timestamps are used, since the subcompaction boundary picking logic is currently not timestamp-aware, which could lead to incorrect results when different subcompactions process keys that only differ by timestamp.
+* Fix an issue that `DeleteFilesInRange()` may cause ongoing compaction reports corruption exception, or ASSERT for debug build. There's no actual data loss or corruption that we find.
+* Fixed confusingly duplicated output in LOG for periodic stats ("DUMPING STATS"), including "Compaction Stats" and "File Read Latency Histogram By Level".
+* Fixed performance bugs in background gathering of block cache entry statistics, that could consume a lot of CPU when there are many column families with a shared block cache.
+
+### New Features
+* Marked the Ribbon filter and optimize_filters_for_memory features as production-ready, each enabling memory savings for Bloom-like filters. Use `NewRibbonFilterPolicy` in place of `NewBloomFilterPolicy` to use Ribbon filters instead of Bloom, or `ribbonfilter` in place of `bloomfilter` in configuration string.
+* Allow `DBWithTTL` to use `DeleteRange` api just like other DBs. `DeleteRangeCF()` which executes `WriteBatchInternal::DeleteRange()` has been added to the handler in `DBWithTTLImpl::Write()` to implement it.
+* Add BlockBasedTableOptions.prepopulate_block_cache.  If enabled, it prepopulate warm/hot data blocks which are already in memory into block cache at the time of flush. On a flush, the data block that is in memory (in memtables) get flushed to the device. If using Direct IO, additional IO is incurred to read this data back into memory again, which is avoided by enabling this option and it also helps with Distributed FileSystem. More details in include/rocksdb/table.h.
+* Added a `cancel` field to `CompactRangeOptions`, allowing individual in-process manual range compactions to be cancelled.
+
+### New Features
+* Added BlobMetaData to the ColumnFamilyMetaData to return information about blob files
+
+### Public API change
+* Added GetAllColumnFamilyMetaData API to retrieve the ColumnFamilyMetaData about all column families.
+
+## 6.21.0 (2021-05-21)
 ### Bug Fixes
 * Fixed a bug in handling file rename error in distributed/network file systems when the server succeeds but client returns error. The bug can cause CURRENT file to point to non-existing MANIFEST file, thus DB cannot be opened.
 * Fixed a bug where ingested files were written with incorrect boundary key metadata. In rare cases this could have led to a level's files being wrongly ordered and queries for the boundary keys returning wrong results.

Makefile

@@ -344,6 +344,12 @@ ifdef ROCKSDB_VALGRIND_RUN
 	PLATFORM_CCFLAGS += -DROCKSDB_VALGRIND_RUN
 	PLATFORM_CXXFLAGS += -DROCKSDB_VALGRIND_RUN
 endif
+ifdef ROCKSDB_FULL_VALGRIND_RUN
+	# Some tests are slow when run under valgrind and are only run when
+	# explicitly requested via the ROCKSDB_FULL_VALGRIND_RUN compiler flag.
+	PLATFORM_CCFLAGS += -DROCKSDB_VALGRIND_RUN -DROCKSDB_FULL_VALGRIND_RUN
+	PLATFORM_CXXFLAGS += -DROCKSDB_VALGRIND_RUN -DROCKSDB_FULL_VALGRIND_RUN
+endif
 
 ifndef DISABLE_JEMALLOC
 	ifdef JEMALLOC
@@ -488,6 +494,7 @@ VALGRIND_ERROR = 2
 VALGRIND_VER := $(join $(VALGRIND_VER),valgrind)
 
 VALGRIND_OPTS = --error-exitcode=$(VALGRIND_ERROR) --leak-check=full
+# Not yet supported: --show-leak-kinds=definite,possible,reachable --errors-for-leak-kinds=definite,possible,reachable
 
 TEST_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(TEST_LIB_SOURCES) $(MOCK_LIB_SOURCES)) $(GTEST)
 BENCH_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(BENCH_LIB_SOURCES))
@@ -516,8 +523,9 @@ endif
 ifdef ASSERT_STATUS_CHECKED
 	# TODO: finish fixing all tests to pass this check
 	TESTS_FAILING_ASC = \
+		c_test \
 		db_test \
-		db_test2 \
+		env_test \
 		range_locking_test \
 		testutil_test \
 
@@ -593,6 +601,8 @@ TEST_LIBS = \
 # TODO: add back forward_iterator_bench, after making it build in all environemnts.
 BENCHMARKS = $(patsubst %.cc, %, $(notdir $(BENCH_MAIN_SOURCES)))
 
+MICROBENCHS = $(patsubst %.cc, %, $(notdir $(MICROBENCH_SOURCES)))
+
 # if user didn't config LIBNAME, set the default
 ifeq ($(LIBNAME),)
   LIBNAME=librocksdb
@@ -731,6 +741,9 @@ test_libs: $(TEST_LIBS)
 
 benchmarks: $(BENCHMARKS)
 
+microbench: $(MICROBENCHS)
+	for t in $(MICROBENCHS); do echo "===== Running benchmark $$t (`date`)"; ./$$t || exit 1; done;
+
 dbg: $(LIBRARY) $(BENCHMARKS) tools $(TESTS)
 
 # creates library and programs
@@ -1044,6 +1057,12 @@ ubsan_crash_test_with_best_efforts_recovery: clean
 	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test_with_best_efforts_recovery
 	$(MAKE) clean
 
+full_valgrind_test:
+	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
+
+full_valgrind_test_some:
+	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check_some
+
 valgrind_test:
 	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
@@ -1162,7 +1181,7 @@ clean-not-downloaded: clean-ext-libraries-bin clean-rocks clean-not-downloaded-r
 clean-rocks:
 	echo shared=$(ALL_SHARED_LIBS)
 	echo static=$(ALL_STATIC_LIBS)
-	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(ALL_STATIC_LIBS) $(ALL_SHARED_LIBS)
+	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(ALL_STATIC_LIBS) $(ALL_SHARED_LIBS) $(MICROBENCHS)
 	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 -f {} \;
@@ -1825,6 +1844,9 @@ block_cache_trace_analyzer_test: $(OBJ_DIR)/tools/block_cache_analyzer/block_cac
 defer_test: $(OBJ_DIR)/util/defer_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+blob_counting_iterator_test: $(OBJ_DIR)/db/blob/blob_counting_iterator_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 blob_file_addition_test: $(OBJ_DIR)/db/blob/blob_file_addition_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1840,6 +1862,9 @@ blob_file_garbage_test: $(OBJ_DIR)/db/blob/blob_file_garbage_test.o $(TEST_LIBRA
 blob_file_reader_test: $(OBJ_DIR)/db/blob/blob_file_reader_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+blob_garbage_meter_test: $(OBJ_DIR)/db/blob/blob_garbage_meter_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 timer_test: $(OBJ_DIR)/util/timer_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1866,6 +1891,13 @@ db_blob_corruption_test: $(OBJ_DIR)/db/blob/db_blob_corruption_test.o $(TEST_LIB
 
 db_write_buffer_manager_test: $(OBJ_DIR)/db/db_write_buffer_manager_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
+
+clipping_iterator_test: $(OBJ_DIR)/db/compaction/clipping_iterator_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
+ribbon_bench: $(OBJ_DIR)/microbench/ribbon_bench.o $(LIBRARY)
+	$(AM_LINK)
+
 #-------------------------------------------------
 # make install related stuff
 PREFIX ?= /usr/local

TARGETS

@@ -10,7 +10,7 @@ load(":defs.bzl", "test_binary")
 
 REPO_PATH = package_name() + "/"
 
-ROCKSDB_COMPILER_FLAGS = [
+ROCKSDB_COMPILER_FLAGS_0 = [
     "-fno-builtin-memcmp",
     # Needed to compile in fbcode
     "-Wno-expansion-to-defined",
@@ -28,7 +28,7 @@ ROCKSDB_EXTERNAL_DEPS = [
     ("zstd", None, "zstd"),
 ]
 
-ROCKSDB_OS_DEPS = [
+ROCKSDB_OS_DEPS_0 = [
     (
         "linux",
         ["third-party//numa:numa", "third-party//liburing:uring", "third-party//tbb:tbb"],
@@ -39,7 +39,7 @@ ROCKSDB_OS_DEPS = [
     ),
 ]
 
-ROCKSDB_OS_PREPROCESSOR_FLAGS = [
+ROCKSDB_OS_PREPROCESSOR_FLAGS_0 = [
     (
         "linux",
         [
@@ -107,18 +107,18 @@ is_opt_mode = build_mode.startswith("opt")
 
 # -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
 # doesn't harm and avoid forgetting to add it.
-ROCKSDB_COMPILER_FLAGS += (["-DNDEBUG"] if is_opt_mode else [])
+ROCKSDB_COMPILER_FLAGS = ROCKSDB_COMPILER_FLAGS_0 + (["-DNDEBUG"] if is_opt_mode else [])
 
 sanitizer = read_config("fbcode", "sanitizer")
 
 # Do not enable jemalloc if sanitizer presents. RocksDB will further detect
 # whether the binary is linked with jemalloc at runtime.
-ROCKSDB_OS_PREPROCESSOR_FLAGS += ([(
+ROCKSDB_OS_PREPROCESSOR_FLAGS = ROCKSDB_OS_PREPROCESSOR_FLAGS_0 + ([(
     "linux",
     ["-DROCKSDB_JEMALLOC"],
 )] if sanitizer == "" else [])
 
-ROCKSDB_OS_DEPS += ([(
+ROCKSDB_OS_DEPS = ROCKSDB_OS_DEPS_0 + ([(
     "linux",
     ["third-party//jemalloc:headers"],
 )] if sanitizer == "" else [])
@@ -137,12 +137,14 @@ cpp_library(
         "cache/lru_cache.cc",
         "cache/sharded_cache.cc",
         "db/arena_wrapped_db_iter.cc",
+        "db/blob/blob_fetcher.cc",
         "db/blob/blob_file_addition.cc",
         "db/blob/blob_file_builder.cc",
         "db/blob/blob_file_cache.cc",
         "db/blob/blob_file_garbage.cc",
         "db/blob/blob_file_meta.cc",
         "db/blob/blob_file_reader.cc",
+        "db/blob/blob_garbage_meter.cc",
         "db/blob/blob_log_format.cc",
         "db/blob/blob_log_sequential_reader.cc",
         "db/blob/blob_log_writer.cc",
@@ -333,6 +335,9 @@ cpp_library(
         "tools/sst_dump_tool.cc",
         "trace_replay/block_cache_tracer.cc",
         "trace_replay/io_tracer.cc",
+        "trace_replay/trace_record.cc",
+        "trace_replay/trace_record_handler.cc",
+        "trace_replay/trace_record_result.cc",
         "trace_replay/trace_replay.cc",
         "util/build_version.cc",
         "util/coding.cc",
@@ -366,6 +371,7 @@ cpp_library(
         "utilities/cassandra/format.cc",
         "utilities/cassandra/merge_operator.cc",
         "utilities/checkpoint/checkpoint_impl.cc",
+        "utilities/compaction_filters.cc",
         "utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc",
         "utilities/convenience/info_log_finder.cc",
         "utilities/debug.cc",
@@ -375,6 +381,7 @@ cpp_library(
         "utilities/fault_injection_fs.cc",
         "utilities/leveldb_options/leveldb_options.cc",
         "utilities/memory/memory_util.cc",
+        "utilities/merge_operators.cc",
         "utilities/merge_operators/bytesxor.cc",
         "utilities/merge_operators/max.cc",
         "utilities/merge_operators/put.cc",
@@ -394,6 +401,7 @@ cpp_library(
         "utilities/simulator_cache/sim_cache.cc",
         "utilities/table_properties_collectors/compact_on_deletion_collector.cc",
         "utilities/trace/file_trace_reader_writer.cc",
+        "utilities/trace/replayer_impl.cc",
         "utilities/transactions/lock/lock_manager.cc",
         "utilities/transactions/lock/point/point_lock_manager.cc",
         "utilities/transactions/lock/point/point_lock_tracker.cc",
@@ -448,12 +456,14 @@ cpp_library(
         "cache/lru_cache.cc",
         "cache/sharded_cache.cc",
         "db/arena_wrapped_db_iter.cc",
+        "db/blob/blob_fetcher.cc",
         "db/blob/blob_file_addition.cc",
         "db/blob/blob_file_builder.cc",
         "db/blob/blob_file_cache.cc",
         "db/blob/blob_file_garbage.cc",
         "db/blob/blob_file_meta.cc",
         "db/blob/blob_file_reader.cc",
+        "db/blob/blob_garbage_meter.cc",
         "db/blob/blob_log_format.cc",
         "db/blob/blob_log_sequential_reader.cc",
         "db/blob/blob_log_writer.cc",
@@ -644,6 +654,9 @@ cpp_library(
         "tools/sst_dump_tool.cc",
         "trace_replay/block_cache_tracer.cc",
         "trace_replay/io_tracer.cc",
+        "trace_replay/trace_record.cc",
+        "trace_replay/trace_record_handler.cc",
+        "trace_replay/trace_record_result.cc",
         "trace_replay/trace_replay.cc",
         "util/build_version.cc",
         "util/coding.cc",
@@ -677,6 +690,7 @@ cpp_library(
         "utilities/cassandra/format.cc",
         "utilities/cassandra/merge_operator.cc",
         "utilities/checkpoint/checkpoint_impl.cc",
+        "utilities/compaction_filters.cc",
         "utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc",
         "utilities/convenience/info_log_finder.cc",
         "utilities/debug.cc",
@@ -686,6 +700,7 @@ cpp_library(
         "utilities/fault_injection_fs.cc",
         "utilities/leveldb_options/leveldb_options.cc",
         "utilities/memory/memory_util.cc",
+        "utilities/merge_operators.cc",
         "utilities/merge_operators/bytesxor.cc",
         "utilities/merge_operators/max.cc",
         "utilities/merge_operators/put.cc",
@@ -705,6 +720,7 @@ cpp_library(
         "utilities/simulator_cache/sim_cache.cc",
         "utilities/table_properties_collectors/compact_on_deletion_collector.cc",
         "utilities/trace/file_trace_reader_writer.cc",
+        "utilities/trace/replayer_impl.cc",
         "utilities/transactions/lock/lock_manager.cc",
         "utilities/transactions/lock/point/point_lock_manager.cc",
         "utilities/transactions/lock/point/point_lock_tracker.cc",
@@ -904,6 +920,13 @@ ROCKS_TESTS = [
         [],
         [],
     ],
+    [
+        "blob_counting_iterator_test",
+        "db/blob/blob_counting_iterator_test.cc",
+        "parallel",
+        [],
+        [],
+    ],
     [
         "blob_db_test",
         "utilities/blob_db/blob_db_test.cc",
@@ -946,6 +969,13 @@ ROCKS_TESTS = [
         [],
         [],
     ],
+    [
+        "blob_garbage_meter_test",
+        "db/blob/blob_garbage_meter_test.cc",
+        "parallel",
+        [],
+        [],
+    ],
     [
         "block_based_filter_block_test",
         "table/block_based/block_based_filter_block_test.cc",
@@ -1051,6 +1081,13 @@ ROCKS_TESTS = [
         [],
         [],
     ],
+    [
+        "clipping_iterator_test",
+        "db/compaction/clipping_iterator_test.cc",
+        "parallel",
+        [],
+        [],
+    ],
     [
         "coding_test",
         "util/coding_test.cc",

buckifier/targets_cfg.py

@@ -17,7 +17,7 @@ load(":defs.bzl", "test_binary")
 
 REPO_PATH = package_name() + "/"
 
-ROCKSDB_COMPILER_FLAGS = [
+ROCKSDB_COMPILER_FLAGS_0 = [
     "-fno-builtin-memcmp",
     # Needed to compile in fbcode
     "-Wno-expansion-to-defined",
@@ -35,7 +35,7 @@ ROCKSDB_EXTERNAL_DEPS = [
     ("zstd", None, "zstd"),
 ]
 
-ROCKSDB_OS_DEPS = [
+ROCKSDB_OS_DEPS_0 = [
     (
         "linux",
         ["third-party//numa:numa", "third-party//liburing:uring", "third-party//tbb:tbb"],
@@ -46,7 +46,7 @@ ROCKSDB_OS_DEPS = [
     ),
 ]
 
-ROCKSDB_OS_PREPROCESSOR_FLAGS = [
+ROCKSDB_OS_PREPROCESSOR_FLAGS_0 = [
     (
         "linux",
         [
@@ -114,18 +114,18 @@ is_opt_mode = build_mode.startswith("opt")
 
 # -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
 # doesn't harm and avoid forgetting to add it.
-ROCKSDB_COMPILER_FLAGS += (["-DNDEBUG"] if is_opt_mode else [])
+ROCKSDB_COMPILER_FLAGS = ROCKSDB_COMPILER_FLAGS_0 + (["-DNDEBUG"] if is_opt_mode else [])
 
 sanitizer = read_config("fbcode", "sanitizer")
 
 # Do not enable jemalloc if sanitizer presents. RocksDB will further detect
 # whether the binary is linked with jemalloc at runtime.
-ROCKSDB_OS_PREPROCESSOR_FLAGS += ([(
+ROCKSDB_OS_PREPROCESSOR_FLAGS = ROCKSDB_OS_PREPROCESSOR_FLAGS_0 + ([(
     "linux",
     ["-DROCKSDB_JEMALLOC"],
 )] if sanitizer == "" else [])
 
-ROCKSDB_OS_DEPS += ([(
+ROCKSDB_OS_DEPS = ROCKSDB_OS_DEPS_0 + ([(
     "linux",
     ["third-party//jemalloc:headers"],
 )] if sanitizer == "" else [])

build_tools/build_detect_platform

@@ -69,10 +69,6 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
       source "$PWD/build_tools/fbcode_config_platform007.sh"
     elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM009" ]; then
       source "$PWD/build_tools/fbcode_config_platform009.sh"
-    elif [ -z "$USE_CLANG" ]; then
-        # Still use platform007 for gcc by default for build break on
-        # some hosts.
-      source "$PWD/build_tools/fbcode_config_platform007.sh"
     else
       source "$PWD/build_tools/fbcode_config_platform009.sh"
     fi
@@ -193,9 +189,6 @@ EOF
                 COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
             fi
         fi
-        if test -z "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-          USE_FOLLY_DISTRIBUTED_MUTEX=1
-        fi
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
@@ -600,6 +593,16 @@ EOF
             PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS -faligned-new -DHAVE_ALIGNED_NEW"
         fi
     fi
+    if ! test $ROCKSDB_DISABLE_BENCHMARK; then
+        # Test whether google benchmark is available
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -lbenchmark 2>/dev/null  <<EOF
+          #include <benchmark/benchmark.h>
+          int main() {}
+EOF
+        if [ "$?" = 0 ]; then
+            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbenchmark"
+        fi
+    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.

build_tools/fbcode_config_platform007.sh

@@ -167,6 +167,4 @@ 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

build_tools/fbcode_config_platform009.sh

@@ -120,7 +120,7 @@ if [ -z "$USE_CLANG" ]; then
   CXX="$GCC_BASE/bin/g++"
   AR="$GCC_BASE/bin/gcc-ar"
 
-  CFLAGS+=" -B$BINUTILS/gold"
+  CFLAGS+=" -B$BINUTILS"
   CFLAGS+=" -isystem $LIBGCC_INCLUDE"
   CFLAGS+=" -isystem $GLIBC_INCLUDE"
   JEMALLOC=1
@@ -133,7 +133,7 @@ else
 
   KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
 
-  CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
+  CFLAGS+=" -B$BINUTILS -nostdinc -nostdlib"
   CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/9.x "
   CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/9.x/x86_64-facebook-linux "
   CFLAGS+=" -isystem $GLIBC_INCLUDE"
@@ -150,10 +150,11 @@ CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PR
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS"
-EXEC_LDFLAGS+=" -B$BINUTILS/gold"
+EXEC_LDFLAGS+=" -B$BINUTILS"
 EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform009/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
 EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform009/lib"
+EXEC_LDFLAGS+=" -Wl,-rpath=$GCC_BASE/lib64"
 # required by libtbb
 EXEC_LDFLAGS+=" -ldl"
 
@@ -167,6 +168,4 @@ 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

build_tools/rocksdb-lego-determinator

@@ -106,9 +106,7 @@ NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-# in gcc-5 there are known problems with TSAN like https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71090.
-# using platform007 gives us gcc-8 or higher which has that bug fixed.
-TSAN="ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007=1 COMPILE_WITH_TSAN=1"
+TSAN="COMPILE_WITH_TSAN=1"
 UBSAN="COMPILE_WITH_UBSAN=1"
 TSAN_CRASH='CRASH_TEST_EXT_ARGS="--compression_type=zstd --log2_keys_per_lock=22"'
 NON_TSAN_CRASH="CRASH_TEST_EXT_ARGS=--compression_type=zstd"
@@ -1197,6 +1195,40 @@ JAVA_BUILD_TEST_COMMANDS="[
     }
 ]"
 
+#
+# RocksDB fbcode stress/crash test
+#
+FBCODE_STRESS_CRASH_TEST_COMMANDS="[
+    {
+        'name':'Rocksdb Fbcode Stress and Crash Test',
+        'oncall':'$ONCALL',
+        'executeLocal': 'true',
+        'timeout': 86400,
+        'steps': [
+            {
+                'name':'Copy RocksDB code to fbcode repo',
+                'shell':'cd internal_repo_rocksdb/repo && git init && git add * && git commit -a -m \"Make internal_repo_rocksdb/repo a git repo\" && cd ../.. && echo Y | python3 rocks/release_script/release_to_fbcode.py -u internal_repo_rocksdb/repo master || $CONTRUN_NAME=db_stress_fbcode $TASK_CREATION_TOOL',
+                'user':'root',
+                $PARSER
+            },
+            {
+                'name':'Build RocksDB fbcode stress tests',
+                'shell':'cd $WORKING_DIR; buck build @mode/dbg rocks/tools:rocks_db_stress || $CONTRUN_NAME=db_stress_fbcode $TASK_CREATION_TOOL',
+                'user':'root',
+                $PARSER
+            },
+            {
+                'name':'Run RocksDB whitebox crash tests',
+                'timeout': 86400,
+                'shell':'cd $WORKING_DIR; mkdir /dev/shm/rocksdb_whitebox_crash_test && TEST_TMPDIR=\$(mktemp -d --tmpdir=/dev/shm/rocksdb_whitebox_crash_test) python3 rocksdb/src/tools/db_crashtest.py --stress_cmd=buck-out/dbg/gen/rocks/tools/rocks_db_stress -secondary_cache_uri=\"$SECONDARY_CACHE_URI\" --env_uri=$ENV_URI -checkpoint_one_in=0 -backup_one_in=0 -cache_size=134217728 -cache_numshardbits=4 $EXTRA_DB_STRESS_ARGS -logtostderr=false whitebox || $CONTRUN_NAME=whitebox_crash_test $TASK_CREATION_TOOL',
+                'user':'root',
+                $PARSER
+            },
+        ],
+        $REPORT
+    }
+]"
+
 
 case $1 in
   unit)
@@ -1334,6 +1366,11 @@ case $1 in
   java_build)
     echo $JAVA_BUILD_TEST_COMMANDS
     ;;
+  fbcode_stress_crash)
+    set -f
+    echo $FBCODE_STRESS_CRASH_TEST_COMMANDS
+    set +f
+    ;;
   *)
     echo "Invalid determinator command"
     exit 1

cache/cache.cc

@@ -10,6 +10,8 @@
 #include "rocksdb/cache.h"
 
 #include "cache/lru_cache.h"
+#include "rocksdb/secondary_cache.h"
+#include "rocksdb/utilities/customizable_util.h"
 #include "rocksdb/utilities/options_type.h"
 #include "util/string_util.h"
 
@@ -34,6 +36,13 @@ static std::unordered_map<std::string, OptionTypeInfo>
 };
 #endif  // ROCKSDB_LITE
 
+Status SecondaryCache::CreateFromString(
+    const ConfigOptions& config_options, const std::string& value,
+    std::shared_ptr<SecondaryCache>* result) {
+  return LoadSharedObject<SecondaryCache>(config_options, value, nullptr,
+                                          result);
+}
+
 Status Cache::CreateFromString(const ConfigOptions& config_options,
                                const std::string& value,
                                std::shared_ptr<Cache>* result) {

cache/cache_bench_tool.cc

@@ -13,11 +13,11 @@
 #include "monitoring/histogram.h"
 #include "port/port.h"
 #include "rocksdb/cache.h"
+#include "rocksdb/convenience.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/secondary_cache.h"
 #include "rocksdb/system_clock.h"
-#include "rocksdb/utilities/object_registry.h"
 #include "table/block_based/cachable_entry.h"
 #include "util/coding.h"
 #include "util/gflags_compat.h"
@@ -233,9 +233,8 @@ class CacheBench {
       LRUCacheOptions opts(FLAGS_cache_size, FLAGS_num_shard_bits, false, 0.5);
 #ifndef ROCKSDB_LITE
       if (!FLAGS_secondary_cache_uri.empty()) {
-        Status s =
-            ObjectRegistry::NewInstance()->NewSharedObject<SecondaryCache>(
-                FLAGS_secondary_cache_uri, &secondary_cache);
+        Status s = SecondaryCache::CreateFromString(
+            ConfigOptions(), FLAGS_secondary_cache_uri, &secondary_cache);
         if (secondary_cache == nullptr) {
           fprintf(
               stderr,

cache/cache_entry_roles.h

@@ -27,7 +27,7 @@ enum class CacheEntryRole {
   kIndexBlock,
   // Other kinds of block-based table block
   kOtherBlock,
-  // WriteBufferManager resevations to account for memtable usage
+  // WriteBufferManager reservations to account for memtable usage
   kWriteBuffer,
   // Default bucket, for miscellaneous cache entries. Do not use for
   // entries that could potentially add up to large usage.

cache/cache_entry_stats.h

@@ -51,35 +51,56 @@ namespace ROCKSDB_NAMESPACE {
 template <class Stats>
 class CacheEntryStatsCollector {
  public:
-  // Gathers stats and saves results into `stats`
-  void GetStats(Stats *stats, int maximum_age_in_seconds = 180) {
+  // Gather and save stats if saved stats are too old. (Use GetStats() to
+  // read saved stats.)
+  //
+  // Maximum allowed age for a "hit" on saved results is determined by the
+  // two interval parameters. Both set to 0 forces a re-scan. For example
+  // with min_interval_seconds=300 and min_interval_factor=100, if the last
+  // scan took 10s, we would only rescan ("miss") if the age in seconds of
+  // the saved results is > max(300, 100*10).
+  // Justification: scans can vary wildly in duration, e.g. from 0.02 sec
+  // to as much as 20 seconds, so we want to be able to cap the absolute
+  // and relative frequency of scans.
+  void CollectStats(int min_interval_seconds, int min_interval_factor) {
     // Waits for any pending reader or writer (collector)
-    std::lock_guard<std::mutex> lock(mutex_);
+    std::lock_guard<std::mutex> lock(working_mutex_);
 
-    // Maximum allowed age is nominally given by the parameter
     uint64_t max_age_micros =
-        static_cast<uint64_t>(std::min(maximum_age_in_seconds, 0)) * 1000000U;
-    // But we will re-scan more frequently if it means scanning < 1%
-    // of the time and no more than once per second.
-    max_age_micros = std::min(
-        max_age_micros,
-        std::max(uint64_t{1000000},
-                 100U * (last_end_time_micros_ - last_start_time_micros_)));
+        static_cast<uint64_t>(std::max(min_interval_seconds, 0)) * 1000000U;
+
+    if (last_end_time_micros_ > last_start_time_micros_ &&
+        min_interval_factor > 0) {
+      max_age_micros = std::max(
+          max_age_micros, min_interval_factor * (last_end_time_micros_ -
+                                                 last_start_time_micros_));
+    }
 
     uint64_t start_time_micros = clock_->NowMicros();
     if ((start_time_micros - last_end_time_micros_) > max_age_micros) {
       last_start_time_micros_ = start_time_micros;
-      saved_stats_.BeginCollection(cache_, clock_, start_time_micros);
+      working_stats_.BeginCollection(cache_, clock_, start_time_micros);
 
-      cache_->ApplyToAllEntries(saved_stats_.GetEntryCallback(), {});
+      cache_->ApplyToAllEntries(working_stats_.GetEntryCallback(), {});
+      TEST_SYNC_POINT_CALLBACK(
+          "CacheEntryStatsCollector::GetStats:AfterApplyToAllEntries", nullptr);
 
       uint64_t end_time_micros = clock_->NowMicros();
       last_end_time_micros_ = end_time_micros;
-      saved_stats_.EndCollection(cache_, clock_, end_time_micros);
+      working_stats_.EndCollection(cache_, clock_, end_time_micros);
     } else {
-      saved_stats_.SkippedCollection();
+      working_stats_.SkippedCollection();
     }
-    // Copy to caller
+
+    // Save so that we don't need to wait for an outstanding collection in
+    // order to make of copy of the last saved stats
+    std::lock_guard<std::mutex> lock2(saved_mutex_);
+    saved_stats_ = working_stats_;
+  }
+
+  // Gets saved stats, regardless of age
+  void GetStats(Stats *stats) {
+    std::lock_guard<std::mutex> lock(saved_mutex_);
     *stats = saved_stats_;
   }
 
@@ -113,9 +134,11 @@ class CacheEntryStatsCollector {
         // usage to go flaky. Fix the problem somehow so we can use an
         // accurate charge.
         size_t charge = 0;
-        Status s = cache->Insert(cache_key, new_ptr, charge, Deleter, &h);
+        Status s = cache->Insert(cache_key, new_ptr, charge, Deleter, &h,
+                                 Cache::Priority::HIGH);
         if (!s.ok()) {
           assert(h == nullptr);
+          delete new_ptr;
           return s;
         }
       }
@@ -132,6 +155,7 @@ class CacheEntryStatsCollector {
  private:
   explicit CacheEntryStatsCollector(Cache *cache, SystemClock *clock)
       : saved_stats_(),
+        working_stats_(),
         last_start_time_micros_(0),
         last_end_time_micros_(/*pessimistic*/ 10000000),
         cache_(cache),
@@ -141,10 +165,14 @@ class CacheEntryStatsCollector {
     delete static_cast<CacheEntryStatsCollector *>(value);
   }
 
-  std::mutex mutex_;
+  std::mutex saved_mutex_;
   Stats saved_stats_;
+
+  std::mutex working_mutex_;
+  Stats working_stats_;
   uint64_t last_start_time_micros_;
   uint64_t last_end_time_micros_;
+
   Cache *const cache_;
   SystemClock *const clock_;
 };

cache/clock_cache.cc

@@ -280,7 +280,8 @@ class ClockCacheShard final : public CacheShard {
   Cache::Handle* Lookup(const Slice& key, uint32_t hash,
                         const Cache::CacheItemHelper* /*helper*/,
                         const Cache::CreateCallback& /*create_cb*/,
-                        Cache::Priority /*priority*/, bool /*wait*/) override {
+                        Cache::Priority /*priority*/, bool /*wait*/,
+                        Statistics* /*stats*/) override {
     return Lookup(key, hash);
   }
   bool Release(Cache::Handle* handle, bool /*useful*/,

cache/lru_cache.cc

@@ -13,6 +13,8 @@
 #include <cstdint>
 #include <cstdio>
 
+#include "monitoring/perf_context_imp.h"
+#include "monitoring/statistics.h"
 #include "util/mutexlock.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -309,7 +311,8 @@ void LRUCacheShard::SetStrictCapacityLimit(bool strict_capacity_limit) {
   strict_capacity_limit_ = strict_capacity_limit;
 }
 
-Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle) {
+Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle,
+                                 bool free_handle_on_fail) {
   Status s = Status::OK();
   autovector<LRUHandle*> last_reference_list;
   size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
@@ -323,14 +326,16 @@ Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle) {
 
     if ((usage_ + total_charge) > capacity_ &&
         (strict_capacity_limit_ || handle == nullptr)) {
+      e->SetInCache(false);
       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);
-        *handle = nullptr;
+        if (free_handle_on_fail) {
+          delete[] reinterpret_cast<char*>(e);
+          *handle = nullptr;
+        }
         s = Status::Incomplete("Insert failed due to LRU cache being full.");
       }
     } else {
@@ -355,7 +360,10 @@ Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle) {
       if (handle == nullptr) {
         LRU_Insert(e);
       } else {
-        e->Ref();
+        // If caller already holds a ref, no need to take one here
+        if (!e->HasRefs()) {
+          e->Ref();
+        }
         *handle = reinterpret_cast<Cache::Handle*>(e);
       }
     }
@@ -375,11 +383,43 @@ Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle) {
   return s;
 }
 
+void LRUCacheShard::Promote(LRUHandle* e) {
+  SecondaryCacheResultHandle* secondary_handle = e->sec_handle;
+
+  assert(secondary_handle->IsReady());
+  e->SetIncomplete(false);
+  e->SetInCache(true);
+  e->SetPromoted(true);
+  e->value = secondary_handle->Value();
+  e->charge = secondary_handle->Size();
+  delete secondary_handle;
+
+  // This call could fail if the cache is over capacity and
+  // strict_capacity_limit_ is true. In such a case, we don't want
+  // InsertItem() to free the handle, since the item is already in memory
+  // and the caller will most likely just read from disk if we erase it here.
+  if (e->value) {
+    Cache::Handle* handle = reinterpret_cast<Cache::Handle*>(e);
+    Status s = InsertItem(e, &handle, /*free_handle_on_fail=*/false);
+    if (!s.ok()) {
+      // Item is in memory, but not accounted against the cache capacity.
+      // When the handle is released, the item should get deleted
+      assert(!e->InCache());
+    }
+  } else {
+    // Since the secondary cache lookup failed, mark the item as not in cache
+    // Don't charge the cache as its only metadata that'll shortly be released
+    MutexLock l(&mutex_);
+    e->charge = 0;
+    e->SetInCache(false);
+  }
+}
+
 Cache::Handle* LRUCacheShard::Lookup(
     const Slice& key, uint32_t hash,
     const ShardedCache::CacheItemHelper* helper,
     const ShardedCache::CreateCallback& create_cb, Cache::Priority priority,
-    bool wait) {
+    bool wait, Statistics* stats) {
   LRUHandle* e = nullptr;
   {
     MutexLock l(&mutex_);
@@ -399,47 +439,51 @@ Cache::Handle* LRUCacheShard::Lookup(
   // mutex if we're going to lookup in the secondary cache
   // Only support synchronous for now
   // TODO: Support asynchronous lookup in secondary cache
-  if (!e && secondary_cache_ && helper && helper->saveto_cb && wait) {
+  if (!e && secondary_cache_ && helper && helper->saveto_cb) {
     // For objects from the secondary cache, we expect the caller to provide
     // a way to create/delete the primary cache object. The only case where
     // a deleter would not be required is for dummy entries inserted for
     // accounting purposes, which we won't demote to the secondary cache
     // anyway.
     assert(create_cb && helper->del_cb);
-    std::unique_ptr<SecondaryCacheHandle> secondary_handle =
+    std::unique_ptr<SecondaryCacheResultHandle> secondary_handle =
         secondary_cache_->Lookup(key, create_cb, wait);
     if (secondary_handle != nullptr) {
-      void* value = nullptr;
       e = reinterpret_cast<LRUHandle*>(
           new char[sizeof(LRUHandle) - 1 + key.size()]);
 
       e->flags = 0;
-      e->SetPromoted(true);
       e->SetSecondaryCacheCompatible(true);
       e->info_.helper = helper;
       e->key_length = key.size();
       e->hash = hash;
       e->refs = 0;
       e->next = e->prev = nullptr;
-      e->SetInCache(true);
       e->SetPriority(priority);
       memcpy(e->key_data, key.data(), key.size());
+      e->value = nullptr;
+      e->sec_handle = secondary_handle.release();
+      e->Ref();
 
-      value = secondary_handle->Value();
-      e->value = value;
-      e->charge = secondary_handle->Size();
-
-      // This call could nullify e if the cache is over capacity and
-      // strict_capacity_limit_ is true. In such a case, the caller will try
-      // to insert later, which might again fail, but its ok as this should
-      // not be common
-      // Being conservative here since there could be lookups that are
-      // actually ok to fail rather than succeed and bloat up the memory
-      // usage (preloading partitioned index blocks, for example).
-      Status s = InsertItem(e, reinterpret_cast<Cache::Handle**>(&e));
-      if (!s.ok()) {
-        assert(e == nullptr);
-        (*helper->del_cb)(key, value);
+      if (wait) {
+        Promote(e);
+        if (!e->value) {
+          // The secondary cache returned a handle, but the lookup failed
+          e->Unref();
+          e->Free();
+          e = nullptr;
+        } else {
+          PERF_COUNTER_ADD(secondary_cache_hit_count, 1);
+          RecordTick(stats, SECONDARY_CACHE_HITS);
+        }
+      } else {
+        // If wait is false, we always return a handle and let the caller
+        // release the handle after checking for success or failure
+        e->SetIncomplete(true);
+        // This may be slightly inaccurate, if the lookup eventually fails.
+        // But the probability is very low.
+        PERF_COUNTER_ADD(secondary_cache_hit_count, 1);
+        RecordTick(stats, SECONDARY_CACHE_HITS);
       }
     }
   }
@@ -485,7 +529,12 @@ bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
         last_reference = false;
       }
     }
-    if (last_reference) {
+    // If it was the last reference, and the entry is either not secondary
+    // cache compatible (i.e a dummy entry for accounting), or is secondary
+    // cache compatible and has a non-null value, then decrement the cache
+    // usage. If value is null in the latter case, taht means the lookup
+    // failed and we didn't charge the cache.
+    if (last_reference && (!e->IsSecondaryCacheCompatible() || e->value)) {
       size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
       assert(usage_ >= total_charge);
       usage_ -= total_charge;
@@ -516,6 +565,9 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
     e->SetSecondaryCacheCompatible(true);
     e->info_.helper = helper;
   } else {
+#ifdef __SANITIZE_THREAD__
+    e->is_secondary_cache_compatible_for_tsan = false;
+#endif  // __SANITIZE_THREAD__
     e->info_.deleter = deleter;
   }
   e->charge = charge;
@@ -527,7 +579,7 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   e->SetPriority(priority);
   memcpy(e->key_data, key.data(), key.size());
 
-  return InsertItem(e, handle);
+  return InsertItem(e, handle, /* free_handle_on_fail */ true);
 }
 
 void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
@@ -557,6 +609,18 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
   }
 }
 
+bool LRUCacheShard::IsReady(Cache::Handle* handle) {
+  LRUHandle* e = reinterpret_cast<LRUHandle*>(handle);
+  MutexLock l(&mutex_);
+  bool ready = true;
+  if (e->IsPending()) {
+    assert(secondary_cache_);
+    assert(e->sec_handle);
+    ready = e->sec_handle->IsReady();
+  }
+  return ready;
+}
+
 size_t LRUCacheShard::GetUsage() const {
   MutexLock l(&mutex_);
   return usage_;
@@ -597,6 +661,7 @@ LRUCache::LRUCache(size_t capacity, int num_shard_bits,
         use_adaptive_mutex, metadata_charge_policy,
         /* max_upper_hash_bits */ 32 - num_shard_bits, secondary_cache);
   }
+  secondary_cache_ = secondary_cache;
 }
 
 LRUCache::~LRUCache() {
@@ -662,6 +727,36 @@ double LRUCache::GetHighPriPoolRatio() {
   return result;
 }
 
+void LRUCache::WaitAll(std::vector<Handle*>& handles) {
+  if (secondary_cache_) {
+    std::vector<SecondaryCacheResultHandle*> sec_handles;
+    sec_handles.reserve(handles.size());
+    for (Handle* handle : handles) {
+      if (!handle) {
+        continue;
+      }
+      LRUHandle* lru_handle = reinterpret_cast<LRUHandle*>(handle);
+      if (!lru_handle->IsPending()) {
+        continue;
+      }
+      sec_handles.emplace_back(lru_handle->sec_handle);
+    }
+    secondary_cache_->WaitAll(sec_handles);
+    for (Handle* handle : handles) {
+      if (!handle) {
+        continue;
+      }
+      LRUHandle* lru_handle = reinterpret_cast<LRUHandle*>(handle);
+      if (!lru_handle->IsPending()) {
+        continue;
+      }
+      uint32_t hash = GetHash(handle);
+      LRUCacheShard* shard = static_cast<LRUCacheShard*>(GetShard(Shard(hash)));
+      shard->Promote(lru_handle);
+    }
+  }
+}
+
 std::shared_ptr<Cache> NewLRUCache(
     size_t capacity, int num_shard_bits, bool strict_capacity_limit,
     double high_pri_pool_ratio,

cache/lru_cache.h

@@ -12,6 +12,7 @@
 #include <string>
 
 #include "cache/sharded_cache.h"
+#include "port/lang.h"
 #include "port/malloc.h"
 #include "port/port.h"
 #include "rocksdb/secondary_cache.h"
@@ -56,7 +57,12 @@ struct LRUHandle {
     Cache::DeleterFn deleter;
     const ShardedCache::CacheItemHelper* helper;
   } info_;
-  LRUHandle* next_hash;
+  // An entry is not added to the LRUHandleTable until the secondary cache
+  // lookup is complete, so its safe to have this union.
+  union {
+    LRUHandle* next_hash;
+    SecondaryCacheResultHandle* sec_handle;
+  };
   LRUHandle* next;
   LRUHandle* prev;
   size_t charge;  // TODO(opt): Only allow uint32_t?
@@ -75,8 +81,8 @@ struct LRUHandle {
     IN_HIGH_PRI_POOL = (1 << 2),
     // Whether this entry has had any lookups (hits).
     HAS_HIT = (1 << 3),
-    // Can this be inserted into the tiered cache
-    IS_TIERED_CACHE_COMPATIBLE = (1 << 4),
+    // Can this be inserted into the secondary cache
+    IS_SECONDARY_CACHE_COMPATIBLE = (1 << 4),
     // Is the handle still being read from a lower tier
     IS_PENDING = (1 << 5),
     // Has the item been promoted from a lower tier
@@ -85,6 +91,14 @@ struct LRUHandle {
 
   uint8_t flags;
 
+#ifdef __SANITIZE_THREAD__
+  // TSAN can report a false data race on flags, where one thread is writing
+  // to one of the mutable bits and another thread is reading this immutable
+  // bit. So precisely suppress that TSAN warning, we separate out this bit
+  // during TSAN runs.
+  bool is_secondary_cache_compatible_for_tsan;
+#endif  // __SANITIZE_THREAD__
+
   // Beginning of the key (MUST BE THE LAST FIELD IN THIS STRUCT!)
   char key_data[1];
 
@@ -108,7 +122,11 @@ struct LRUHandle {
   bool InHighPriPool() const { return flags & IN_HIGH_PRI_POOL; }
   bool HasHit() const { return flags & HAS_HIT; }
   bool IsSecondaryCacheCompatible() const {
-    return flags & IS_TIERED_CACHE_COMPATIBLE;
+#ifdef __SANITIZE_THREAD__
+    return is_secondary_cache_compatible_for_tsan;
+#else
+    return flags & IS_SECONDARY_CACHE_COMPATIBLE;
+#endif  // __SANITIZE_THREAD__
   }
   bool IsPending() const { return flags & IS_PENDING; }
   bool IsPromoted() const { return flags & IS_PROMOTED; }
@@ -139,12 +157,15 @@ struct LRUHandle {
 
   void SetHit() { flags |= HAS_HIT; }
 
-  void SetSecondaryCacheCompatible(bool tiered) {
-    if (tiered) {
-      flags |= IS_TIERED_CACHE_COMPATIBLE;
+  void SetSecondaryCacheCompatible(bool compat) {
+    if (compat) {
+      flags |= IS_SECONDARY_CACHE_COMPATIBLE;
     } else {
-      flags &= ~IS_TIERED_CACHE_COMPATIBLE;
+      flags &= ~IS_SECONDARY_CACHE_COMPATIBLE;
     }
+#ifdef __SANITIZE_THREAD__
+    is_secondary_cache_compatible_for_tsan = compat;
+#endif  // __SANITIZE_THREAD__
   }
 
   void SetIncomplete(bool incomp) {
@@ -165,10 +186,24 @@ struct LRUHandle {
 
   void Free() {
     assert(refs == 0);
+#ifdef __SANITIZE_THREAD__
+    // Here we can safely assert they are the same without a data race reported
+    assert(((flags & IS_SECONDARY_CACHE_COMPATIBLE) != 0) ==
+           is_secondary_cache_compatible_for_tsan);
+#endif  // __SANITIZE_THREAD__
     if (!IsSecondaryCacheCompatible() && info_.deleter) {
       (*info_.deleter)(key(), value);
     } else if (IsSecondaryCacheCompatible()) {
-      (*info_.helper->del_cb)(key(), value);
+      if (IsPending()) {
+        assert(sec_handle != nullptr);
+        SecondaryCacheResultHandle* tmp_sec_handle = sec_handle;
+        tmp_sec_handle->Wait();
+        value = tmp_sec_handle->Value();
+        delete tmp_sec_handle;
+      }
+      if (value) {
+        (*info_.helper->del_cb)(key(), value);
+      }
     }
     delete[] reinterpret_cast<char*>(this);
   }
@@ -284,16 +319,17 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash,
                                 const ShardedCache::CacheItemHelper* helper,
                                 const ShardedCache::CreateCallback& create_cb,
-                                ShardedCache::Priority priority,
-                                bool wait) override;
+                                ShardedCache::Priority priority, bool wait,
+                                Statistics* stats) override;
   virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override {
-    return Lookup(key, hash, nullptr, nullptr, Cache::Priority::LOW, true);
+    return Lookup(key, hash, nullptr, nullptr, Cache::Priority::LOW, true,
+                  nullptr);
   }
   virtual bool Release(Cache::Handle* handle, bool /*useful*/,
                        bool force_erase) override {
     return Release(handle, force_erase);
   }
-  virtual bool IsReady(Cache::Handle* /*handle*/) override { return true; }
+  virtual bool IsReady(Cache::Handle* /*handle*/) override;
   virtual void Wait(Cache::Handle* /*handle*/) override {}
   virtual bool Ref(Cache::Handle* handle) override;
   virtual bool Release(Cache::Handle* handle,
@@ -326,10 +362,23 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   double GetHighPriPoolRatio();
 
  private:
-  Status InsertItem(LRUHandle* item, Cache::Handle** handle);
+  friend class LRUCache;
+  // Insert an item into the hash table and, if handle is null, insert into
+  // the LRU list. Older items are evicted as necessary. If the cache is full
+  // and free_handle_on_fail is true, the item is deleted and handle is set to.
+  Status InsertItem(LRUHandle* item, Cache::Handle** handle,
+                    bool free_handle_on_fail);
   Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
                 DeleterFn deleter, const Cache::CacheItemHelper* helper,
                 Cache::Handle** handle, Cache::Priority priority);
+  // Promote an item looked up from the secondary cache to the LRU cache. The
+  // item is only inserted into the hash table and not the LRU list, and only
+  // if the cache is not at full capacity, as is the case during Insert.  The
+  // caller should hold a reference on the LRUHandle. When the caller releases
+  // the last reference, the item is added to the LRU list.
+  // The item is promoted to the high pri or low pri pool as specified by the
+  // caller in Lookup.
+  void Promote(LRUHandle* e);
   void LRU_Remove(LRUHandle* e);
   void LRU_Insert(LRUHandle* e);
 
@@ -416,7 +465,7 @@ class LRUCache
   virtual uint32_t GetHash(Handle* handle) const override;
   virtual DeleterFn GetDeleter(Handle* handle) const override;
   virtual void DisownData() override;
-  virtual void WaitAll(std::vector<Handle*>& /*handles*/) override {}
+  virtual void WaitAll(std::vector<Handle*>& handles) override;
 
   //  Retrieves number of elements in LRU, for unit test purpose only
   size_t TEST_GetLRUSize();
@@ -426,6 +475,7 @@ class LRUCache
  private:
   LRUCacheShard* shards_ = nullptr;
   int num_shards_ = 0;
+  std::shared_ptr<SecondaryCache> secondary_cache_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

cache/lru_cache_test.cc

@@ -18,6 +18,7 @@
 #include "test_util/testharness.h"
 #include "util/coding.h"
 #include "util/random.h"
+#include "utilities/fault_injection_fs.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -203,6 +204,19 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
 
 class TestSecondaryCache : public SecondaryCache {
  public:
+  // Specifies what action to take on a lookup for a particular key
+  enum ResultType {
+    SUCCESS,
+    // Fail lookup immediately
+    FAIL,
+    // Defer the result. It will returned after Wait/WaitAll is called
+    DEFER,
+    // Defer the result and eventually return failure
+    DEFER_AND_FAIL
+  };
+
+  using ResultMap = std::unordered_map<std::string, ResultType>;
+
   explicit TestSecondaryCache(size_t capacity)
       : num_inserts_(0), num_lookups_(0), inject_failure_(false) {
     cache_ = NewLRUCache(capacity, 0, false, 0.5, nullptr,
@@ -210,17 +224,22 @@ class TestSecondaryCache : public SecondaryCache {
   }
   ~TestSecondaryCache() override { cache_.reset(); }
 
-  std::string Name() override { return "TestSecondaryCache"; }
+  const char* Name() const override { return "TestSecondaryCache"; }
 
   void InjectFailure() { inject_failure_ = true; }
 
   void ResetInjectFailure() { inject_failure_ = false; }
 
+  void SetDbSessionId(const std::string& db_session_id) {
+    db_session_id_ = db_session_id;
+  }
+
   Status Insert(const Slice& key, void* value,
                 const Cache::CacheItemHelper* helper) override {
     if (inject_failure_) {
       return Status::Corruption("Insertion Data Corrupted");
     }
+    assert(IsDbSessionIdAsKeyPrefix(key) == true);
     size_t size;
     char* buf;
     Status s;
@@ -240,22 +259,37 @@ class TestSecondaryCache : public SecondaryCache {
                           });
   }
 
-  std::unique_ptr<SecondaryCacheHandle> Lookup(
+  std::unique_ptr<SecondaryCacheResultHandle> Lookup(
       const Slice& key, const Cache::CreateCallback& create_cb,
       bool /*wait*/) override {
-    std::unique_ptr<SecondaryCacheHandle> secondary_handle;
+    std::string key_str = key.ToString();
+    TEST_SYNC_POINT_CALLBACK("TestSecondaryCache::Lookup", &key_str);
+
+    std::unique_ptr<SecondaryCacheResultHandle> secondary_handle;
+    ResultType type = ResultType::SUCCESS;
+    auto iter = result_map_.find(key.ToString());
+    if (iter != result_map_.end()) {
+      type = iter->second;
+    }
+    if (type == ResultType::FAIL) {
+      return secondary_handle;
+    }
+
     Cache::Handle* handle = cache_->Lookup(key);
     num_lookups_++;
     if (handle) {
-      void* value;
-      size_t charge;
-      char* ptr = (char*)cache_->Value(handle);
-      size_t size = DecodeFixed64(ptr);
-      ptr += sizeof(uint64_t);
-      Status s = create_cb(ptr, size, &value, &charge);
+      void* value = nullptr;
+      size_t charge = 0;
+      Status s;
+      if (type != ResultType::DEFER_AND_FAIL) {
+        char* ptr = (char*)cache_->Value(handle);
+        size_t size = DecodeFixed64(ptr);
+        ptr += sizeof(uint64_t);
+        s = create_cb(ptr, size, &value, &charge);
+      }
       if (s.ok()) {
-        secondary_handle.reset(
-            new TestSecondaryCacheHandle(cache_.get(), handle, value, charge));
+        secondary_handle.reset(new TestSecondaryCacheResultHandle(
+            cache_.get(), handle, value, charge, type));
       } else {
         cache_->Release(handle);
       }
@@ -265,47 +299,92 @@ class TestSecondaryCache : public SecondaryCache {
 
   void Erase(const Slice& /*key*/) override {}
 
-  void WaitAll(std::vector<SecondaryCacheHandle*> /*handles*/) override {}
+  void WaitAll(std::vector<SecondaryCacheResultHandle*> handles) override {
+    for (SecondaryCacheResultHandle* handle : handles) {
+      TestSecondaryCacheResultHandle* sec_handle =
+          static_cast<TestSecondaryCacheResultHandle*>(handle);
+      sec_handle->SetReady();
+    }
+  }
 
   std::string GetPrintableOptions() const override { return ""; }
 
+  void SetResultMap(ResultMap&& map) { result_map_ = std::move(map); }
+
   uint32_t num_inserts() { return num_inserts_; }
 
   uint32_t num_lookups() { return num_lookups_; }
 
- private:
-  class TestSecondaryCacheHandle : public SecondaryCacheHandle {
-   public:
-    TestSecondaryCacheHandle(Cache* cache, Cache::Handle* handle, void* value,
-                             size_t size)
-        : cache_(cache), handle_(handle), value_(value), size_(size) {}
-    ~TestSecondaryCacheHandle() override { cache_->Release(handle_); }
+  bool IsDbSessionIdAsKeyPrefix(const Slice& key) {
+    if (db_session_id_.size() == 0) {
+      return true;
+    }
+    if (key.size() < 20) {
+      return false;
+    }
+    std::string s_key = key.ToString();
+    if (s_key.substr(0, 20) != db_session_id_) {
+      return false;
+    }
+    return true;
+  }
 
-    bool IsReady() override { return true; }
+ private:
+  class TestSecondaryCacheResultHandle : public SecondaryCacheResultHandle {
+   public:
+    TestSecondaryCacheResultHandle(Cache* cache, Cache::Handle* handle,
+                                   void* value, size_t size, ResultType type)
+        : cache_(cache),
+          handle_(handle),
+          value_(value),
+          size_(size),
+          is_ready_(true) {
+      if (type != ResultType::SUCCESS) {
+        is_ready_ = false;
+      }
+    }
+
+    ~TestSecondaryCacheResultHandle() override { cache_->Release(handle_); }
+
+    bool IsReady() override { return is_ready_; }
 
     void Wait() override {}
 
-    void* Value() override { return value_; }
+    void* Value() override {
+      assert(is_ready_);
+      return value_;
+    }
 
-    size_t Size() override { return size_; }
+    size_t Size() override { return Value() ? size_ : 0; }
+
+    void SetReady() { is_ready_ = true; }
 
    private:
     Cache* cache_;
     Cache::Handle* handle_;
     void* value_;
     size_t size_;
+    bool is_ready_;
   };
 
   std::shared_ptr<Cache> cache_;
   uint32_t num_inserts_;
   uint32_t num_lookups_;
   bool inject_failure_;
+  std::string db_session_id_;
+  ResultMap result_map_;
 };
 
 class DBSecondaryCacheTest : public DBTestBase {
  public:
   DBSecondaryCacheTest()
-      : DBTestBase("/db_secondary_cache_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_secondary_cache_test", /*env_do_fsync=*/true) {
+    fault_fs_.reset(new FaultInjectionTestFS(env_->GetFileSystem()));
+    fault_env_.reset(new CompositeEnvWrapper(env_, fault_fs_));
+  }
+
+  std::shared_ptr<FaultInjectionTestFS> fault_fs_;
+  std::unique_ptr<Env> fault_env_;
 };
 
 class LRUSecondaryCacheTest : public LRUCacheTest {
@@ -323,6 +402,7 @@ class LRUSecondaryCacheTest : public LRUCacheTest {
 
     char* Buf() { return buf_.get(); }
     size_t Size() { return size_; }
+    std::string ToString() { return std::string(Buf(), Size()); }
 
    private:
     std::unique_ptr<char[]> buf_;
@@ -388,6 +468,7 @@ TEST_F(LRUSecondaryCacheTest, BasicTest) {
       std::make_shared<TestSecondaryCache>(2048);
   opts.secondary_cache = secondary_cache;
   std::shared_ptr<Cache> cache = NewLRUCache(opts);
+  std::shared_ptr<Statistics> stats = CreateDBStatistics();
 
   Random rnd(301);
   std::string str1 = rnd.RandomString(1020);
@@ -396,22 +477,29 @@ TEST_F(LRUSecondaryCacheTest, BasicTest) {
                           str1.length()));
   std::string str2 = rnd.RandomString(1020);
   TestItem* item2 = new TestItem(str2.data(), str2.length());
-  // k2 should be demoted to NVM
+  // k1 should be demoted to NVM
   ASSERT_OK(cache->Insert("k2", item2, &LRUSecondaryCacheTest::helper_,
                           str2.length()));
 
+  get_perf_context()->Reset();
   Cache::Handle* handle;
-  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
-                         test_item_creator, Cache::Priority::LOW, true);
+  handle =
+      cache->Lookup("k2", &LRUSecondaryCacheTest::helper_, test_item_creator,
+                    Cache::Priority::LOW, true, stats.get());
   ASSERT_NE(handle, nullptr);
   cache->Release(handle);
   // This lookup should promote k1 and demote k2
-  handle = cache->Lookup("k1", &LRUSecondaryCacheTest::helper_,
-                         test_item_creator, Cache::Priority::LOW, true);
+  handle =
+      cache->Lookup("k1", &LRUSecondaryCacheTest::helper_, test_item_creator,
+                    Cache::Priority::LOW, true, stats.get());
   ASSERT_NE(handle, nullptr);
   cache->Release(handle);
   ASSERT_EQ(secondary_cache->num_inserts(), 2u);
   ASSERT_EQ(secondary_cache->num_lookups(), 1u);
+  ASSERT_EQ(stats->getTickerCount(SECONDARY_CACHE_HITS),
+            secondary_cache->num_lookups());
+  PerfContext perf_ctx = *get_perf_context();
+  ASSERT_EQ(perf_ctx.secondary_cache_hit_count, secondary_cache->num_lookups());
 
   cache.reset();
   secondary_cache.reset();
@@ -548,14 +636,15 @@ TEST_F(LRUSecondaryCacheTest, FullCapacityTest) {
   handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
                          test_item_creator, Cache::Priority::LOW, true);
   ASSERT_NE(handle, nullptr);
-  // This lookup should fail, since k1 promotion would have failed due to
-  // the block cache being at capacity
+  // k1 promotion should fail due to the block cache being at capacity,
+  // but the lookup should still succeed
   Cache::Handle* handle2;
   handle2 = cache->Lookup("k1", &LRUSecondaryCacheTest::helper_,
                           test_item_creator, Cache::Priority::LOW, true);
-  ASSERT_EQ(handle2, nullptr);
-  // Since k1 didn't get promoted, k2 should still be in cache
+  ASSERT_NE(handle2, nullptr);
+  // Since k1 didn't get inserted, k2 should still be in cache
   cache->Release(handle);
+  cache->Release(handle2);
   handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
                          test_item_creator, Cache::Priority::LOW, true);
   ASSERT_NE(handle, nullptr);
@@ -586,11 +675,16 @@ TEST_F(DBSecondaryCacheTest, TestSecondaryCacheCorrectness1) {
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  options.env = fault_env_.get();
+  fault_fs_->SetFailGetUniqueId(true);
 
   // Set the file paranoid check, so after flush, the file will be read
   // all the blocks will be accessed.
   options.paranoid_file_checks = true;
   DestroyAndReopen(options);
+  std::string session_id;
+  ASSERT_OK(db_->GetDbSessionId(session_id));
+  secondary_cache->SetDbSessionId(session_id);
   Random rnd(301);
   const int N = 6;
   for (int i = 0; i < N; i++) {
@@ -659,14 +753,14 @@ TEST_F(DBSecondaryCacheTest, TestSecondaryCacheCorrectness1) {
   Destroy(options);
 }
 
-// In this test, the block cache size is set to 5100, after insert 6 KV-pairs
+// In this test, the block cache size is set to 6100, after insert 6 KV-pairs
 // and flush, there are 5 blocks in this SST file, 2 data blocks and 3 meta
 // blocks. block_1 size is 4096 and block_2 size is 2056. The total size
 // of the meta blocks are about 900 to 1000. Therefore, we can successfully
 // insert and cache block_1 in the block cache (this is the different place
 // from TestSecondaryCacheCorrectness1)
 TEST_F(DBSecondaryCacheTest, TestSecondaryCacheCorrectness2) {
-  LRUCacheOptions opts(5100, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
+  LRUCacheOptions opts(6100, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
                        kDontChargeCacheMetadata);
   std::shared_ptr<TestSecondaryCache> secondary_cache(
       new TestSecondaryCache(2048 * 1024));
@@ -679,7 +773,12 @@ TEST_F(DBSecondaryCacheTest, TestSecondaryCacheCorrectness2) {
   options.create_if_missing = true;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   options.paranoid_file_checks = true;
+  options.env = fault_env_.get();
+  fault_fs_->SetFailGetUniqueId(true);
   DestroyAndReopen(options);
+  std::string session_id;
+  ASSERT_OK(db_->GetDbSessionId(session_id));
+  secondary_cache->SetDbSessionId(session_id);
   Random rnd(301);
   const int N = 6;
   for (int i = 0; i < N; i++) {
@@ -767,7 +866,13 @@ TEST_F(DBSecondaryCacheTest, NoSecondaryCacheInsertion) {
   options.create_if_missing = true;
   options.paranoid_file_checks = true;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  options.env = fault_env_.get();
+  fault_fs_->SetFailGetUniqueId(true);
+
   DestroyAndReopen(options);
+  std::string session_id;
+  ASSERT_OK(db_->GetDbSessionId(session_id));
+  secondary_cache->SetDbSessionId(session_id);
   Random rnd(301);
   const int N = 6;
   for (int i = 0; i < N; i++) {
@@ -814,7 +919,12 @@ TEST_F(DBSecondaryCacheTest, SecondaryCacheIntensiveTesting) {
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  options.env = fault_env_.get();
+  fault_fs_->SetFailGetUniqueId(true);
   DestroyAndReopen(options);
+  std::string session_id;
+  ASSERT_OK(db_->GetDbSessionId(session_id));
+  secondary_cache->SetDbSessionId(session_id);
   Random rnd(301);
   const int N = 256;
   for (int i = 0; i < N; i++) {
@@ -859,7 +969,12 @@ TEST_F(DBSecondaryCacheTest, SecondaryCacheFailureTest) {
   options.create_if_missing = true;
   options.paranoid_file_checks = true;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  options.env = fault_env_.get();
+  fault_fs_->SetFailGetUniqueId(true);
   DestroyAndReopen(options);
+  std::string session_id;
+  ASSERT_OK(db_->GetDbSessionId(session_id));
+  secondary_cache->SetDbSessionId(session_id);
   Random rnd(301);
   const int N = 6;
   for (int i = 0; i < N; i++) {
@@ -932,6 +1047,141 @@ TEST_F(DBSecondaryCacheTest, SecondaryCacheFailureTest) {
   Destroy(options);
 }
 
+TEST_F(LRUSecondaryCacheTest, BasicWaitAllTest) {
+  LRUCacheOptions opts(1024, 2, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
+                       kDontChargeCacheMetadata);
+  std::shared_ptr<TestSecondaryCache> secondary_cache =
+      std::make_shared<TestSecondaryCache>(32 * 1024);
+  opts.secondary_cache = secondary_cache;
+  std::shared_ptr<Cache> cache = NewLRUCache(opts);
+  const int num_keys = 32;
+
+  Random rnd(301);
+  std::vector<std::string> values;
+  for (int i = 0; i < num_keys; ++i) {
+    std::string str = rnd.RandomString(1020);
+    values.emplace_back(str);
+    TestItem* item = new TestItem(str.data(), str.length());
+    ASSERT_OK(cache->Insert("k" + std::to_string(i), item,
+                            &LRUSecondaryCacheTest::helper_, str.length()));
+  }
+  // Force all entries to be evicted to the secondary cache
+  cache->SetCapacity(0);
+  ASSERT_EQ(secondary_cache->num_inserts(), 32u);
+  cache->SetCapacity(32 * 1024);
+
+  secondary_cache->SetResultMap(
+      {{"k3", TestSecondaryCache::ResultType::DEFER},
+       {"k4", TestSecondaryCache::ResultType::DEFER_AND_FAIL},
+       {"k5", TestSecondaryCache::ResultType::FAIL}});
+  std::vector<Cache::Handle*> results;
+  for (int i = 0; i < 6; ++i) {
+    results.emplace_back(
+        cache->Lookup("k" + std::to_string(i), &LRUSecondaryCacheTest::helper_,
+                      test_item_creator, Cache::Priority::LOW, false));
+  }
+  cache->WaitAll(results);
+  for (int i = 0; i < 6; ++i) {
+    if (i == 4) {
+      ASSERT_EQ(cache->Value(results[i]), nullptr);
+    } else if (i == 5) {
+      ASSERT_EQ(results[i], nullptr);
+      continue;
+    } else {
+      TestItem* item = static_cast<TestItem*>(cache->Value(results[i]));
+      ASSERT_EQ(item->ToString(), values[i]);
+    }
+    cache->Release(results[i]);
+  }
+
+  cache.reset();
+  secondary_cache.reset();
+}
+
+// In this test, we have one KV pair per data block. We indirectly determine
+// the cache key associated with each data block (and thus each KV) by using
+// a sync point callback in TestSecondaryCache::Lookup. We then control the
+// lookup result by setting the ResultMap.
+TEST_F(DBSecondaryCacheTest, TestSecondaryCacheMultiGet) {
+  LRUCacheOptions opts(1 << 20, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
+                       kDontChargeCacheMetadata);
+  std::shared_ptr<TestSecondaryCache> secondary_cache(
+      new TestSecondaryCache(2048 * 1024));
+  opts.secondary_cache = secondary_cache;
+  std::shared_ptr<Cache> cache = NewLRUCache(opts);
+  BlockBasedTableOptions table_options;
+  table_options.block_cache = cache;
+  table_options.block_size = 4 * 1024;
+  table_options.cache_index_and_filter_blocks = false;
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  options.paranoid_file_checks = true;
+  DestroyAndReopen(options);
+  Random rnd(301);
+  const int N = 8;
+  std::vector<std::string> keys;
+  for (int i = 0; i < N; i++) {
+    std::string p_v = rnd.RandomString(4000);
+    keys.emplace_back(p_v);
+    ASSERT_OK(Put(Key(i), p_v));
+  }
+
+  ASSERT_OK(Flush());
+  // After Flush is successful, RocksDB does the paranoid check for the new
+  // SST file. This will try to lookup all data blocks in the secondary
+  // cache.
+  ASSERT_EQ(secondary_cache->num_inserts(), 0u);
+  ASSERT_EQ(secondary_cache->num_lookups(), 8u);
+
+  cache->SetCapacity(0);
+  ASSERT_EQ(secondary_cache->num_inserts(), 8u);
+  cache->SetCapacity(1 << 20);
+
+  std::vector<std::string> cache_keys;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "TestSecondaryCache::Lookup", [&cache_keys](void* key) -> void {
+        cache_keys.emplace_back(*(static_cast<std::string*>(key)));
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  for (int i = 0; i < N; ++i) {
+    std::string v = Get(Key(i));
+    ASSERT_EQ(4000, v.size());
+    ASSERT_EQ(v, keys[i]);
+  }
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ASSERT_EQ(secondary_cache->num_lookups(), 16u);
+  cache->SetCapacity(0);
+  cache->SetCapacity(1 << 20);
+
+  ASSERT_EQ(Get(Key(2)), keys[2]);
+  ASSERT_EQ(Get(Key(7)), keys[7]);
+  secondary_cache->SetResultMap(
+      {{cache_keys[3], TestSecondaryCache::ResultType::DEFER},
+       {cache_keys[4], TestSecondaryCache::ResultType::DEFER_AND_FAIL},
+       {cache_keys[5], TestSecondaryCache::ResultType::FAIL}});
+
+  std::vector<std::string> mget_keys(
+      {Key(0), Key(1), Key(2), Key(3), Key(4), Key(5), Key(6), Key(7)});
+  std::vector<PinnableSlice> values(mget_keys.size());
+  std::vector<Status> s(keys.size());
+  std::vector<Slice> key_slices;
+  for (const std::string& key : mget_keys) {
+    key_slices.emplace_back(key);
+  }
+  uint32_t num_lookups = secondary_cache->num_lookups();
+  dbfull()->MultiGet(ReadOptions(), dbfull()->DefaultColumnFamily(),
+                     key_slices.size(), key_slices.data(), values.data(),
+                     s.data(), false);
+  ASSERT_EQ(secondary_cache->num_lookups(), num_lookups + 5);
+  for (int i = 0; i < N; ++i) {
+    ASSERT_OK(s[i]);
+    ASSERT_EQ(values[i].ToString(), keys[i]);
+    values[i].Reset();
+  }
+  Destroy(options);
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

cache/sharded_cache.cc

@@ -83,10 +83,10 @@ Cache::Handle* ShardedCache::Lookup(const Slice& key,
                                     const CacheItemHelper* helper,
                                     const CreateCallback& create_cb,
                                     Priority priority, bool wait,
-                                    Statistics* /*stats*/) {
+                                    Statistics* stats) {
   uint32_t hash = HashSlice(key);
   return GetShard(Shard(hash))
-      ->Lookup(key, hash, helper, create_cb, priority, wait);
+      ->Lookup(key, hash, helper, create_cb, priority, wait, stats);
 }
 
 bool ShardedCache::IsReady(Handle* handle) {

cache/sharded_cache.h

@@ -34,7 +34,8 @@ class CacheShard {
   virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash,
                                 const Cache::CacheItemHelper* helper,
                                 const Cache::CreateCallback& create_cb,
-                                Cache::Priority priority, bool wait) = 0;
+                                Cache::Priority priority, bool wait,
+                                Statistics* stats) = 0;
   virtual bool Release(Cache::Handle* handle, bool useful,
                        bool force_erase) = 0;
   virtual bool IsReady(Cache::Handle* handle) = 0;
@@ -115,9 +116,10 @@ class ShardedCache : public Cache {
   int GetNumShardBits() const;
   uint32_t GetNumShards() const;
 
- private:
+ protected:
   inline uint32_t Shard(uint32_t hash) { return hash & shard_mask_; }
 
+ private:
   const uint32_t shard_mask_;
   mutable port::Mutex capacity_mutex_;
   size_t capacity_;

db/arena_wrapped_db_iter.cc

@@ -31,16 +31,15 @@ Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
 }
 
 void ArenaWrappedDBIter::Init(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableOptions& cf_options,
+    Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const Version* version,
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iteration,
     uint64_t version_number, ReadCallback* read_callback, DBImpl* db_impl,
     ColumnFamilyData* cfd, bool expose_blob_index, 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, /* iter */ nullptr, version,
+      new (mem) DBIter(env, read_options, ioptions, mutable_cf_options,
+                       ioptions.user_comparator, /* iter */ nullptr, version,
                        sequence, true, max_sequential_skip_in_iteration,
                        read_callback, db_impl, cfd, expose_blob_index);
   sv_number_ = version_number;
@@ -88,16 +87,15 @@ Status ArenaWrappedDBIter::Refresh() {
 }
 
 ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableOptions& cf_options,
+    Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const Version* version,
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
     uint64_t version_number, ReadCallback* read_callback, DBImpl* db_impl,
     ColumnFamilyData* cfd, bool expose_blob_index, bool allow_refresh) {
   ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
-  iter->Init(env, read_options, cf_options, mutable_cf_options, version,
-             sequence, max_sequential_skip_in_iterations, version_number,
-             read_callback, db_impl, cfd, expose_blob_index, allow_refresh);
+  iter->Init(env, read_options, ioptions, mutable_cf_options, version, sequence,
+             max_sequential_skip_in_iterations, version_number, read_callback,
+             db_impl, cfd, expose_blob_index, allow_refresh);
   if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
     iter->StoreRefreshInfo(db_impl, cfd, read_callback, expose_blob_index);
   }

db/arena_wrapped_db_iter.h

@@ -72,7 +72,7 @@ class ArenaWrappedDBIter : public Iterator {
   Status Refresh() override;
 
   void Init(Env* env, const ReadOptions& read_options,
-            const ImmutableOptions& cf_options,
+            const ImmutableOptions& ioptions,
             const MutableCFOptions& mutable_cf_options, const Version* version,
             const SequenceNumber& sequence,
             uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
@@ -105,8 +105,7 @@ class ArenaWrappedDBIter : public Iterator {
 // `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 ImmutableOptions& cf_options,
+    Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const Version* version,
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
     uint64_t version_number, ReadCallback* read_callback,

db/blob/blob_counting_iterator.h

@@ -0,0 +1,146 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <cassert>
+
+#include "db/blob/blob_garbage_meter.h"
+#include "rocksdb/rocksdb_namespace.h"
+#include "rocksdb/status.h"
+#include "table/internal_iterator.h"
+#include "test_util/sync_point.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+// An internal iterator that passes each key-value encountered to
+// BlobGarbageMeter as inflow in order to measure the total number and size of
+// blobs in the compaction input on a per-blob file basis.
+class BlobCountingIterator : public InternalIterator {
+ public:
+  BlobCountingIterator(InternalIterator* iter,
+                       BlobGarbageMeter* blob_garbage_meter)
+      : iter_(iter), blob_garbage_meter_(blob_garbage_meter) {
+    assert(iter_);
+    assert(blob_garbage_meter_);
+
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  bool Valid() const override { return iter_->Valid() && status_.ok(); }
+
+  void SeekToFirst() override {
+    iter_->SeekToFirst();
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  void SeekToLast() override {
+    iter_->SeekToLast();
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  void Seek(const Slice& target) override {
+    iter_->Seek(target);
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  void SeekForPrev(const Slice& target) override {
+    iter_->SeekForPrev(target);
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  void Next() override {
+    assert(Valid());
+
+    iter_->Next();
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  bool NextAndGetResult(IterateResult* result) override {
+    assert(Valid());
+
+    const bool res = iter_->NextAndGetResult(result);
+    UpdateAndCountBlobIfNeeded();
+    return res;
+  }
+
+  void Prev() override {
+    assert(Valid());
+
+    iter_->Prev();
+    UpdateAndCountBlobIfNeeded();
+  }
+
+  Slice key() const override {
+    assert(Valid());
+    return iter_->key();
+  }
+
+  Slice user_key() const override {
+    assert(Valid());
+    return iter_->user_key();
+  }
+
+  Slice value() const override {
+    assert(Valid());
+    return iter_->value();
+  }
+
+  Status status() const override { return status_; }
+
+  bool PrepareValue() override {
+    assert(Valid());
+    return iter_->PrepareValue();
+  }
+
+  bool MayBeOutOfLowerBound() override {
+    assert(Valid());
+    return iter_->MayBeOutOfLowerBound();
+  }
+
+  IterBoundCheck UpperBoundCheckResult() override {
+    assert(Valid());
+    return iter_->UpperBoundCheckResult();
+  }
+
+  void SetPinnedItersMgr(PinnedIteratorsManager* pinned_iters_mgr) override {
+    iter_->SetPinnedItersMgr(pinned_iters_mgr);
+  }
+
+  bool IsKeyPinned() const override {
+    assert(Valid());
+    return iter_->IsKeyPinned();
+  }
+
+  bool IsValuePinned() const override {
+    assert(Valid());
+    return iter_->IsValuePinned();
+  }
+
+  Status GetProperty(std::string prop_name, std::string* prop) override {
+    return iter_->GetProperty(prop_name, prop);
+  }
+
+ private:
+  void UpdateAndCountBlobIfNeeded() {
+    assert(!iter_->Valid() || iter_->status().ok());
+
+    if (!iter_->Valid()) {
+      status_ = iter_->status();
+      return;
+    }
+
+    TEST_SYNC_POINT(
+        "BlobCountingIterator::UpdateAndCountBlobIfNeeded:ProcessInFlow");
+
+    status_ = blob_garbage_meter_->ProcessInFlow(key(), value());
+  }
+
+  InternalIterator* iter_;
+  BlobGarbageMeter* blob_garbage_meter_;
+  Status status_;
+};
+
+}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_counting_iterator_test.cc

@@ -0,0 +1,325 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/blob/blob_counting_iterator.h"
+
+#include <string>
+#include <vector>
+
+#include "db/blob/blob_garbage_meter.h"
+#include "db/blob/blob_index.h"
+#include "db/blob/blob_log_format.h"
+#include "db/dbformat.h"
+#include "test_util/testharness.h"
+#include "test_util/testutil.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+void CheckInFlow(const BlobGarbageMeter& blob_garbage_meter,
+                 uint64_t blob_file_number, uint64_t count, uint64_t bytes) {
+  const auto& flows = blob_garbage_meter.flows();
+
+  const auto it = flows.find(blob_file_number);
+  if (it == flows.end()) {
+    ASSERT_EQ(count, 0);
+    ASSERT_EQ(bytes, 0);
+    return;
+  }
+
+  const auto& in = it->second.GetInFlow();
+
+  ASSERT_EQ(in.GetCount(), count);
+  ASSERT_EQ(in.GetBytes(), bytes);
+}
+
+TEST(BlobCountingIteratorTest, CountBlobs) {
+  // Note: the input consists of three key-values: two are blob references to
+  // different blob files, while the third one is a plain value.
+  constexpr char user_key0[] = "key0";
+  constexpr char user_key1[] = "key1";
+  constexpr char user_key2[] = "key2";
+
+  const std::vector<std::string> keys{
+      test::KeyStr(user_key0, 1, kTypeBlobIndex),
+      test::KeyStr(user_key1, 2, kTypeBlobIndex),
+      test::KeyStr(user_key2, 3, kTypeValue)};
+
+  constexpr uint64_t first_blob_file_number = 4;
+  constexpr uint64_t first_offset = 1000;
+  constexpr uint64_t first_size = 2000;
+
+  std::string first_blob_index;
+  BlobIndex::EncodeBlob(&first_blob_index, first_blob_file_number, first_offset,
+                        first_size, kNoCompression);
+
+  constexpr uint64_t second_blob_file_number = 6;
+  constexpr uint64_t second_offset = 2000;
+  constexpr uint64_t second_size = 4000;
+
+  std::string second_blob_index;
+  BlobIndex::EncodeBlob(&second_blob_index, second_blob_file_number,
+                        second_offset, second_size, kNoCompression);
+
+  const std::vector<std::string> values{first_blob_index, second_blob_index,
+                                        "raw_value"};
+
+  assert(keys.size() == values.size());
+
+  test::VectorIterator input(keys, values);
+  BlobGarbageMeter blob_garbage_meter;
+
+  BlobCountingIterator blob_counter(&input, &blob_garbage_meter);
+
+  constexpr uint64_t first_expected_bytes =
+      first_size +
+      BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(user_key0) - 1);
+  constexpr uint64_t second_expected_bytes =
+      second_size +
+      BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(user_key1) - 1);
+
+  // Call SeekToFirst and iterate forward
+  blob_counter.SeekToFirst();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[0]);
+  ASSERT_EQ(blob_counter.user_key(), user_key0);
+  ASSERT_EQ(blob_counter.value(), values[0]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 1,
+              first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 0, 0);
+
+  blob_counter.Next();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[1]);
+  ASSERT_EQ(blob_counter.user_key(), user_key1);
+  ASSERT_EQ(blob_counter.value(), values[1]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 1,
+              first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 1,
+              second_expected_bytes);
+
+  blob_counter.Next();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[2]);
+  ASSERT_EQ(blob_counter.user_key(), user_key2);
+  ASSERT_EQ(blob_counter.value(), values[2]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 1,
+              first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 1,
+              second_expected_bytes);
+
+  blob_counter.Next();
+  ASSERT_FALSE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 1,
+              first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 1,
+              second_expected_bytes);
+
+  // Do it again using NextAndGetResult
+  blob_counter.SeekToFirst();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[0]);
+  ASSERT_EQ(blob_counter.user_key(), user_key0);
+  ASSERT_EQ(blob_counter.value(), values[0]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 2,
+              2 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 1,
+              second_expected_bytes);
+
+  {
+    IterateResult result;
+    ASSERT_TRUE(blob_counter.NextAndGetResult(&result));
+    ASSERT_EQ(result.key, keys[1]);
+    ASSERT_EQ(blob_counter.user_key(), user_key1);
+    ASSERT_TRUE(blob_counter.Valid());
+    ASSERT_OK(blob_counter.status());
+    ASSERT_EQ(blob_counter.key(), keys[1]);
+    ASSERT_EQ(blob_counter.value(), values[1]);
+    CheckInFlow(blob_garbage_meter, first_blob_file_number, 2,
+                2 * first_expected_bytes);
+    CheckInFlow(blob_garbage_meter, second_blob_file_number, 2,
+                2 * second_expected_bytes);
+  }
+
+  {
+    IterateResult result;
+    ASSERT_TRUE(blob_counter.NextAndGetResult(&result));
+    ASSERT_EQ(result.key, keys[2]);
+    ASSERT_EQ(blob_counter.user_key(), user_key2);
+    ASSERT_TRUE(blob_counter.Valid());
+    ASSERT_OK(blob_counter.status());
+    ASSERT_EQ(blob_counter.key(), keys[2]);
+    ASSERT_EQ(blob_counter.value(), values[2]);
+    CheckInFlow(blob_garbage_meter, first_blob_file_number, 2,
+                2 * first_expected_bytes);
+    CheckInFlow(blob_garbage_meter, second_blob_file_number, 2,
+                2 * second_expected_bytes);
+  }
+
+  {
+    IterateResult result;
+    ASSERT_FALSE(blob_counter.NextAndGetResult(&result));
+    ASSERT_FALSE(blob_counter.Valid());
+    ASSERT_OK(blob_counter.status());
+    CheckInFlow(blob_garbage_meter, first_blob_file_number, 2,
+                2 * first_expected_bytes);
+    CheckInFlow(blob_garbage_meter, second_blob_file_number, 2,
+                2 * second_expected_bytes);
+  }
+
+  // Call SeekToLast and iterate backward
+  blob_counter.SeekToLast();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[2]);
+  ASSERT_EQ(blob_counter.user_key(), user_key2);
+  ASSERT_EQ(blob_counter.value(), values[2]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 2,
+              2 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 2,
+              2 * second_expected_bytes);
+
+  blob_counter.Prev();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[1]);
+  ASSERT_EQ(blob_counter.user_key(), user_key1);
+  ASSERT_EQ(blob_counter.value(), values[1]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 2,
+              2 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 3,
+              3 * second_expected_bytes);
+
+  blob_counter.Prev();
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[0]);
+  ASSERT_EQ(blob_counter.user_key(), user_key0);
+  ASSERT_EQ(blob_counter.value(), values[0]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 3,
+              3 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 3,
+              3 * second_expected_bytes);
+
+  blob_counter.Prev();
+  ASSERT_FALSE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 3,
+              3 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 3,
+              3 * second_expected_bytes);
+
+  // Call Seek for all keys (plus one that's greater than all of them)
+  blob_counter.Seek(keys[0]);
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[0]);
+  ASSERT_EQ(blob_counter.user_key(), user_key0);
+  ASSERT_EQ(blob_counter.value(), values[0]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 4,
+              4 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 3,
+              3 * second_expected_bytes);
+
+  blob_counter.Seek(keys[1]);
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[1]);
+  ASSERT_EQ(blob_counter.user_key(), user_key1);
+  ASSERT_EQ(blob_counter.value(), values[1]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 4,
+              4 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 4,
+              4 * second_expected_bytes);
+
+  blob_counter.Seek(keys[2]);
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[2]);
+  ASSERT_EQ(blob_counter.user_key(), user_key2);
+  ASSERT_EQ(blob_counter.value(), values[2]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 4,
+              4 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 4,
+              4 * second_expected_bytes);
+
+  blob_counter.Seek("zzz");
+  ASSERT_FALSE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 4,
+              4 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 4,
+              4 * second_expected_bytes);
+
+  // Call SeekForPrev for all keys (plus one that's less than all of them)
+  blob_counter.SeekForPrev("aaa");
+  ASSERT_FALSE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 4,
+              4 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 4,
+              4 * second_expected_bytes);
+
+  blob_counter.SeekForPrev(keys[0]);
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[0]);
+  ASSERT_EQ(blob_counter.user_key(), user_key0);
+  ASSERT_EQ(blob_counter.value(), values[0]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 5,
+              5 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 4,
+              4 * second_expected_bytes);
+
+  blob_counter.SeekForPrev(keys[1]);
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[1]);
+  ASSERT_EQ(blob_counter.user_key(), user_key1);
+  ASSERT_EQ(blob_counter.value(), values[1]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 5,
+              5 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 5,
+              5 * second_expected_bytes);
+
+  blob_counter.SeekForPrev(keys[2]);
+  ASSERT_TRUE(blob_counter.Valid());
+  ASSERT_OK(blob_counter.status());
+  ASSERT_EQ(blob_counter.key(), keys[2]);
+  ASSERT_EQ(blob_counter.user_key(), user_key2);
+  ASSERT_EQ(blob_counter.value(), values[2]);
+  CheckInFlow(blob_garbage_meter, first_blob_file_number, 5,
+              5 * first_expected_bytes);
+  CheckInFlow(blob_garbage_meter, second_blob_file_number, 5,
+              5 * second_expected_bytes);
+}
+
+TEST(BlobCountingIteratorTest, CorruptBlobIndex) {
+  const std::vector<std::string> keys{
+      test::KeyStr("user_key", 1, kTypeBlobIndex)};
+  const std::vector<std::string> values{"i_am_not_a_blob_index"};
+
+  assert(keys.size() == values.size());
+
+  test::VectorIterator input(keys, values);
+  BlobGarbageMeter blob_garbage_meter;
+
+  BlobCountingIterator blob_counter(&input, &blob_garbage_meter);
+
+  blob_counter.SeekToFirst();
+  ASSERT_FALSE(blob_counter.Valid());
+  ASSERT_NOK(blob_counter.status());
+}
+
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/blob/blob_fetcher.cc

@@ -0,0 +1,22 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/blob/blob_fetcher.h"
+
+#include "db/version_set.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+Status BlobFetcher::FetchBlob(const Slice& user_key, const Slice& blob_index,
+                              PinnableSlice* blob_value) {
+  Status s;
+  assert(version_);
+  constexpr uint64_t* bytes_read = nullptr;
+  s = version_->GetBlob(read_options_, user_key, blob_index, blob_value,
+                        bytes_read);
+  return s;
+}
+
+}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_fetcher.h

@@ -0,0 +1,26 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include "rocksdb/options.h"
+#include "rocksdb/status.h"
+
+namespace ROCKSDB_NAMESPACE {
+class Version;
+
+class BlobFetcher {
+ public:
+  BlobFetcher(Version* version, const ReadOptions& read_options)
+      : version_(version), read_options_(read_options) {}
+
+  Status FetchBlob(const Slice& user_key, const Slice& blob_index,
+                   PinnableSlice* blob_value);
+
+ private:
+  Version* version_;
+  ReadOptions read_options_;
+};
+}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_addition.cc

@@ -135,7 +135,8 @@ std::ostream& operator<<(std::ostream& os,
      << " total_blob_count: " << blob_file_addition.GetTotalBlobCount()
      << " total_blob_bytes: " << blob_file_addition.GetTotalBlobBytes()
      << " checksum_method: " << blob_file_addition.GetChecksumMethod()
-     << " checksum_value: " << blob_file_addition.GetChecksumValue();
+     << " checksum_value: "
+     << Slice(blob_file_addition.GetChecksumValue()).ToString(/* hex */ true);
 
   return os;
 }
@@ -146,7 +147,8 @@ JSONWriter& operator<<(JSONWriter& jw,
      << "TotalBlobCount" << blob_file_addition.GetTotalBlobCount()
      << "TotalBlobBytes" << blob_file_addition.GetTotalBlobBytes()
      << "ChecksumMethod" << blob_file_addition.GetChecksumMethod()
-     << "ChecksumValue" << blob_file_addition.GetChecksumValue();
+     << "ChecksumValue"
+     << Slice(blob_file_addition.GetChecksumValue()).ToString(/* hex */ true);
 
   return jw;
 }

db/blob/blob_file_addition_test.cc

@@ -46,7 +46,9 @@ TEST_F(BlobFileAdditionTest, NonEmpty) {
   constexpr uint64_t total_blob_count = 2;
   constexpr uint64_t total_blob_bytes = 123456;
   const std::string checksum_method("SHA1");
-  const std::string checksum_value("bdb7f34a59dfa1592ce7f52e99f98c570c525cbd");
+  const std::string checksum_value(
+      "\xbd\xb7\xf3\x4a\x59\xdf\xa1\x59\x2c\xe7\xf5\x2e\x99\xf9\x8c\x57\x0c\x52"
+      "\x5c\xbd");
 
   BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
                                       total_blob_bytes, checksum_method,
@@ -113,7 +115,9 @@ TEST_F(BlobFileAdditionTest, DecodeErrors) {
     ASSERT_TRUE(std::strstr(s.getState(), "checksum value"));
   }
 
-  constexpr char checksum_value[] = "bdb7f34a59dfa1592ce7f52e99f98c570c525cbd";
+  constexpr char checksum_value[] =
+      "\xbd\xb7\xf3\x4a\x59\xdf\xa1\x59\x2c\xe7\xf5\x2e\x99\xf9\x8c\x57\x0c\x52"
+      "\x5c\xbd";
   PutLengthPrefixedSlice(&str, checksum_value);
   slice = str;
 
@@ -150,7 +154,7 @@ TEST_F(BlobFileAdditionTest, ForwardCompatibleCustomField) {
   constexpr uint64_t total_blob_count = 9999;
   constexpr uint64_t total_blob_bytes = 100000000;
   const std::string checksum_method("CRC32");
-  const std::string checksum_value("3d87ff57");
+  const std::string checksum_value("\x3d\x87\xff\x57");
 
   BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
                                       total_blob_bytes, checksum_method,
@@ -178,7 +182,7 @@ TEST_F(BlobFileAdditionTest, ForwardIncompatibleCustomField) {
   constexpr uint64_t total_blob_count = 100;
   constexpr uint64_t total_blob_bytes = 2000000;
   const std::string checksum_method("CRC32B");
-  const std::string checksum_value("6dbdf23a");
+  const std::string checksum_value("\x6d\xbd\xf2\x3a");
 
   BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
                                       total_blob_bytes, checksum_method,

db/blob/blob_file_builder.cc

@@ -29,7 +29,7 @@ namespace ROCKSDB_NAMESPACE {
 
 BlobFileBuilder::BlobFileBuilder(
     VersionSet* versions, FileSystem* fs,
-    const ImmutableOptions* immutable_cf_options,
+    const ImmutableOptions* immutable_options,
     const MutableCFOptions* mutable_cf_options, const FileOptions* file_options,
     int job_id, uint32_t column_family_id,
     const std::string& column_family_name, Env::IOPriority io_priority,
@@ -39,14 +39,14 @@ BlobFileBuilder::BlobFileBuilder(
     std::vector<std::string>* blob_file_paths,
     std::vector<BlobFileAddition>* blob_file_additions)
     : BlobFileBuilder([versions]() { return versions->NewFileNumber(); }, fs,
-                      immutable_cf_options, mutable_cf_options, file_options,
+                      immutable_options, mutable_cf_options, file_options,
                       job_id, column_family_id, column_family_name, io_priority,
                       write_hint, io_tracer, blob_callback, blob_file_paths,
                       blob_file_additions) {}
 
 BlobFileBuilder::BlobFileBuilder(
     std::function<uint64_t()> file_number_generator, FileSystem* fs,
-    const ImmutableOptions* immutable_cf_options,
+    const ImmutableOptions* immutable_options,
     const MutableCFOptions* mutable_cf_options, const FileOptions* file_options,
     int job_id, uint32_t column_family_id,
     const std::string& column_family_name, Env::IOPriority io_priority,
@@ -57,7 +57,7 @@ BlobFileBuilder::BlobFileBuilder(
     std::vector<BlobFileAddition>* blob_file_additions)
     : file_number_generator_(std::move(file_number_generator)),
       fs_(fs),
-      immutable_cf_options_(immutable_cf_options),
+      immutable_options_(immutable_options),
       min_blob_size_(mutable_cf_options->min_blob_size),
       blob_file_size_(mutable_cf_options->blob_file_size),
       blob_compression_type_(mutable_cf_options->blob_compression_type),
@@ -75,7 +75,7 @@ BlobFileBuilder::BlobFileBuilder(
       blob_bytes_(0) {
   assert(file_number_generator_);
   assert(fs_);
-  assert(immutable_cf_options_);
+  assert(immutable_options_);
   assert(file_options_);
   assert(blob_file_paths_);
   assert(blob_file_paths_->empty());
@@ -156,10 +156,10 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
   assert(file_number_generator_);
   const uint64_t blob_file_number = file_number_generator_();
 
-  assert(immutable_cf_options_);
-  assert(!immutable_cf_options_->cf_paths.empty());
-  std::string blob_file_path = BlobFileName(
-      immutable_cf_options_->cf_paths.front().path, blob_file_number);
+  assert(immutable_options_);
+  assert(!immutable_options_->cf_paths.empty());
+  std::string blob_file_path =
+      BlobFileName(immutable_options_->cf_paths.front().path, blob_file_number);
 
   std::unique_ptr<FSWritableFile> file;
 
@@ -184,20 +184,20 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
   assert(file);
   file->SetIOPriority(io_priority_);
   file->SetWriteLifeTimeHint(write_hint_);
-  FileTypeSet tmp_set = immutable_cf_options_->checksum_handoff_file_types;
-  Statistics* const statistics = immutable_cf_options_->stats;
+  FileTypeSet tmp_set = immutable_options_->checksum_handoff_file_types;
+  Statistics* const statistics = immutable_options_->stats;
   std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
       std::move(file), blob_file_paths_->back(), *file_options_,
-      immutable_cf_options_->clock, io_tracer_, statistics,
-      immutable_cf_options_->listeners,
-      immutable_cf_options_->file_checksum_gen_factory.get(),
-      tmp_set.Contains(FileType::kBlobFile)));
+      immutable_options_->clock, io_tracer_, statistics,
+      immutable_options_->listeners,
+      immutable_options_->file_checksum_gen_factory.get(),
+      tmp_set.Contains(FileType::kBlobFile), false));
 
   constexpr bool do_flush = false;
 
   std::unique_ptr<BlobLogWriter> blob_log_writer(new BlobLogWriter(
-      std::move(file_writer), immutable_cf_options_->clock, statistics,
-      blob_file_number, immutable_cf_options_->use_fsync, do_flush));
+      std::move(file_writer), immutable_options_->clock, statistics,
+      blob_file_number, immutable_options_->use_fsync, do_flush));
 
   constexpr bool has_ttl = false;
   constexpr ExpirationRange expiration_range;
@@ -228,6 +228,7 @@ Status BlobFileBuilder::CompressBlobIfNeeded(
   assert(blob);
   assert(compressed_blob);
   assert(compressed_blob->empty());
+  assert(immutable_options_);
 
   if (blob_compression_type_ == kNoCompression) {
     return Status::OK();
@@ -242,7 +243,16 @@ Status BlobFileBuilder::CompressBlobIfNeeded(
 
   constexpr uint32_t compression_format_version = 2;
 
-  if (!CompressData(*blob, info, compression_format_version, compressed_blob)) {
+  bool success = false;
+
+  {
+    StopWatch stop_watch(immutable_options_->clock, immutable_options_->stats,
+                         BLOB_DB_COMPRESSION_MICROS);
+    success =
+        CompressData(*blob, info, compression_format_version, compressed_blob);
+  }
+
+  if (!success) {
     return Status::Corruption("Error compressing blob");
   }
 
@@ -300,8 +310,8 @@ Status BlobFileBuilder::CloseBlobFile() {
                                      std::move(checksum_method),
                                      std::move(checksum_value));
 
-  assert(immutable_cf_options_);
-  ROCKS_LOG_INFO(immutable_cf_options_->logger,
+  assert(immutable_options_);
+  ROCKS_LOG_INFO(immutable_options_->logger,
                  "[%s] [JOB %d] Generated blob file #%" PRIu64 ": %" PRIu64
                  " total blobs, %" PRIu64 " total bytes",
                  column_family_name_.c_str(), job_id_, blob_file_number,

db/blob/blob_file_builder.h

@@ -77,7 +77,7 @@ class BlobFileBuilder {
 
   std::function<uint64_t()> file_number_generator_;
   FileSystem* fs_;
-  const ImmutableOptions* immutable_cf_options_;
+  const ImmutableOptions* immutable_options_;
   uint64_t min_blob_size_;
   uint64_t blob_file_size_;
   CompressionType blob_compression_type_;

db/blob/blob_file_builder_test.cc

@@ -129,7 +129,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
   options.enable_blob_files = true;
   options.env = &mock_env_;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -141,12 +141,11 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   std::vector<std::pair<std::string, std::string>> expected_key_value_pairs(
       number_of_blobs);
@@ -178,9 +177,9 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
 
   const std::string& blob_file_path = blob_file_paths[0];
 
-  ASSERT_EQ(blob_file_path,
-            BlobFileName(immutable_cf_options.cf_paths.front().path,
-                         blob_file_number));
+  ASSERT_EQ(
+      blob_file_path,
+      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number));
 
   ASSERT_EQ(blob_file_additions.size(), 1);
 
@@ -214,7 +213,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
   options.blob_file_size = value_size;
   options.env = &mock_env_;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -226,12 +225,11 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   std::vector<std::pair<std::string, std::string>> expected_key_value_pairs(
       number_of_blobs);
@@ -264,7 +262,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
     const uint64_t blob_file_number = i + 2;
 
     ASSERT_EQ(blob_file_paths[i],
-              BlobFileName(immutable_cf_options.cf_paths.front().path,
+              BlobFileName(immutable_options.cf_paths.front().path,
                            blob_file_number));
 
     const auto& blob_file_addition = blob_file_additions[i];
@@ -301,7 +299,7 @@ TEST_F(BlobFileBuilderTest, InlinedValues) {
   options.min_blob_size = 1024;
   options.env = &mock_env_;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -313,12 +311,11 @@ TEST_F(BlobFileBuilderTest, InlinedValues) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   for (size_t i = 0; i < number_of_blobs; ++i) {
     const std::string key = std::to_string(i);
@@ -355,7 +352,7 @@ TEST_F(BlobFileBuilderTest, Compression) {
   options.blob_compression_type = kSnappyCompression;
   options.env = &mock_env_;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -367,12 +364,11 @@ TEST_F(BlobFileBuilderTest, Compression) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   const std::string key("1");
   const std::string uncompressed_value(value_size, 'x');
@@ -391,9 +387,9 @@ TEST_F(BlobFileBuilderTest, Compression) {
 
   const std::string& blob_file_path = blob_file_paths[0];
 
-  ASSERT_EQ(blob_file_path,
-            BlobFileName(immutable_cf_options.cf_paths.front().path,
-                         blob_file_number));
+  ASSERT_EQ(
+      blob_file_path,
+      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number));
 
   ASSERT_EQ(blob_file_additions.size(), 1);
 
@@ -438,7 +434,7 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
   options.enable_blob_files = true;
   options.blob_compression_type = kSnappyCompression;
   options.env = &mock_env_;
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -450,12 +446,11 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   SyncPoint::GetInstance()->SetCallBack("CompressData:TamperWithReturnValue",
                                         [](void* arg) {
@@ -477,9 +472,9 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
   constexpr uint64_t blob_file_number = 2;
 
   ASSERT_EQ(blob_file_paths.size(), 1);
-  ASSERT_EQ(blob_file_paths[0],
-            BlobFileName(immutable_cf_options.cf_paths.front().path,
-                         blob_file_number));
+  ASSERT_EQ(
+      blob_file_paths[0],
+      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number));
 
   ASSERT_TRUE(blob_file_additions.empty());
 }
@@ -517,7 +512,7 @@ TEST_F(BlobFileBuilderTest, Checksum) {
       std::make_shared<DummyFileChecksumGenFactory>();
   options.env = &mock_env_;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -529,12 +524,11 @@ TEST_F(BlobFileBuilderTest, Checksum) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   const std::string key("1");
   const std::string value("deadbeef");
@@ -553,9 +547,9 @@ TEST_F(BlobFileBuilderTest, Checksum) {
 
   const std::string& blob_file_path = blob_file_paths[0];
 
-  ASSERT_EQ(blob_file_path,
-            BlobFileName(immutable_cf_options.cf_paths.front().path,
-                         blob_file_number));
+  ASSERT_EQ(
+      blob_file_path,
+      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number));
 
   ASSERT_EQ(blob_file_additions.size(), 1);
 
@@ -614,7 +608,7 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {
   options.blob_file_size = value_size;
   options.env = &mock_env_;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   MutableCFOptions mutable_cf_options(options);
 
   constexpr int job_id = 1;
@@ -626,12 +620,11 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {
   std::vector<std::string> blob_file_paths;
   std::vector<BlobFileAddition> blob_file_additions;
 
-  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
-                          &mutable_cf_options, &file_options_, job_id,
-                          column_family_id, column_family_name, io_priority,
-                          write_hint, nullptr /*IOTracer*/,
-                          nullptr /*BlobFileCompletionCallback*/,
-                          &blob_file_paths, &blob_file_additions);
+  BlobFileBuilder builder(
+      TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
+      &file_options_, job_id, column_family_id, column_family_name, io_priority,
+      write_hint, nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
+      &blob_file_paths, &blob_file_additions);
 
   SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* arg) {
     Status* const s = static_cast<Status*>(arg);
@@ -658,7 +651,7 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {
 
     ASSERT_EQ(blob_file_paths.size(), 1);
     ASSERT_EQ(blob_file_paths[0],
-              BlobFileName(immutable_cf_options.cf_paths.front().path,
+              BlobFileName(immutable_options.cf_paths.front().path,
                            blob_file_number));
   }
 

db/blob/blob_file_cache.cc

@@ -26,13 +26,13 @@ BlobFileCache::BlobFileCache(Cache* cache,
                              const std::shared_ptr<IOTracer>& io_tracer)
     : cache_(cache),
       mutex_(kNumberOfMutexStripes, kGetSliceNPHash64UnseededFnPtr),
-      immutable_cf_options_(immutable_options),
+      immutable_options_(immutable_options),
       file_options_(file_options),
       column_family_id_(column_family_id),
       blob_file_read_hist_(blob_file_read_hist),
       io_tracer_(io_tracer) {
   assert(cache_);
-  assert(immutable_cf_options_);
+  assert(immutable_options_);
   assert(file_options_);
 }
 
@@ -63,8 +63,8 @@ Status BlobFileCache::GetBlobFileReader(
     return Status::OK();
   }
 
-  assert(immutable_cf_options_);
-  Statistics* const statistics = immutable_cf_options_->stats;
+  assert(immutable_options_);
+  Statistics* const statistics = immutable_options_->stats;
 
   RecordTick(statistics, NO_FILE_OPENS);
 
@@ -73,7 +73,7 @@ Status BlobFileCache::GetBlobFileReader(
   {
     assert(file_options_);
     const Status s = BlobFileReader::Create(
-        *immutable_cf_options_, *file_options_, column_family_id_,
+        *immutable_options_, *file_options_, column_family_id_,
         blob_file_read_hist_, blob_file_number, io_tracer_, &reader);
     if (!s.ok()) {
       RecordTick(statistics, NO_FILE_ERRORS);

db/blob/blob_file_cache.h

@@ -40,7 +40,7 @@ class BlobFileCache {
   // Note: mutex_ below is used to guard against multiple threads racing to open
   // the same file.
   Striped<port::Mutex, Slice> mutex_;
-  const ImmutableOptions* immutable_cf_options_;
+  const ImmutableOptions* immutable_options_;
   const FileOptions* file_options_;
   uint32_t column_family_id_;
   HistogramImpl* blob_file_read_hist_;

db/blob/blob_file_cache_test.cc

@@ -29,28 +29,27 @@ namespace {
 
 // Creates a test blob file with a single blob in it.
 void WriteBlobFile(uint32_t column_family_id,
-                   const ImmutableOptions& immutable_cf_options,
+                   const ImmutableOptions& immutable_options,
                    uint64_t blob_file_number) {
-  assert(!immutable_cf_options.cf_paths.empty());
+  assert(!immutable_options.cf_paths.empty());
 
-  const std::string blob_file_path = BlobFileName(
-      immutable_cf_options.cf_paths.front().path, blob_file_number);
+  const std::string blob_file_path =
+      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number);
 
   std::unique_ptr<FSWritableFile> file;
-  ASSERT_OK(NewWritableFile(immutable_cf_options.fs.get(), blob_file_path,
-                            &file, FileOptions()));
+  ASSERT_OK(NewWritableFile(immutable_options.fs.get(), blob_file_path, &file,
+                            FileOptions()));
 
-  std::unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(file), blob_file_path, FileOptions(),
-                             immutable_cf_options.clock));
+  std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
+      std::move(file), blob_file_path, FileOptions(), immutable_options.clock));
 
   constexpr Statistics* statistics = nullptr;
   constexpr bool use_fsync = false;
   constexpr bool do_flush = false;
 
-  BlobLogWriter blob_log_writer(std::move(file_writer),
-                                immutable_cf_options.clock, statistics,
-                                blob_file_number, use_fsync, do_flush);
+  BlobLogWriter blob_log_writer(std::move(file_writer), immutable_options.clock,
+                                statistics, blob_file_number, use_fsync,
+                                do_flush);
 
   constexpr bool has_ttl = false;
   constexpr ExpirationRange expiration_range;
@@ -100,10 +99,10 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader) {
   options.enable_blob_files = true;
 
   constexpr uint32_t column_family_id = 1;
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   constexpr uint64_t blob_file_number = 123;
 
-  WriteBlobFile(column_family_id, immutable_cf_options, blob_file_number);
+  WriteBlobFile(column_family_id, immutable_options, blob_file_number);
 
   constexpr size_t capacity = 10;
   std::shared_ptr<Cache> backing_cache = NewLRUCache(capacity);
@@ -111,7 +110,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader) {
   FileOptions file_options;
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
-  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
+  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_options,
                                 &file_options, column_family_id,
                                 blob_file_read_hist, nullptr /*IOTracer*/);
 
@@ -145,10 +144,10 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_Race) {
   options.enable_blob_files = true;
 
   constexpr uint32_t column_family_id = 1;
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   constexpr uint64_t blob_file_number = 123;
 
-  WriteBlobFile(column_family_id, immutable_cf_options, blob_file_number);
+  WriteBlobFile(column_family_id, immutable_options, blob_file_number);
 
   constexpr size_t capacity = 10;
   std::shared_ptr<Cache> backing_cache = NewLRUCache(capacity);
@@ -156,7 +155,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_Race) {
   FileOptions file_options;
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
-  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
+  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_options,
                                 &file_options, column_family_id,
                                 blob_file_read_hist, nullptr /*IOTracer*/);
 
@@ -199,12 +198,12 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_IOError) {
   constexpr size_t capacity = 10;
   std::shared_ptr<Cache> backing_cache = NewLRUCache(capacity);
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   FileOptions file_options;
   constexpr uint32_t column_family_id = 1;
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
-  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
+  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_options,
                                 &file_options, column_family_id,
                                 blob_file_read_hist, nullptr /*IOTracer*/);
 
@@ -231,10 +230,10 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_CacheFull) {
   options.enable_blob_files = true;
 
   constexpr uint32_t column_family_id = 1;
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
   constexpr uint64_t blob_file_number = 123;
 
-  WriteBlobFile(column_family_id, immutable_cf_options, blob_file_number);
+  WriteBlobFile(column_family_id, immutable_options, blob_file_number);
 
   constexpr size_t capacity = 0;
   constexpr int num_shard_bits = -1;  // determined automatically
@@ -245,7 +244,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_CacheFull) {
   FileOptions file_options;
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
-  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
+  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_options,
                                 &file_options, column_family_id,
                                 blob_file_read_hist, nullptr /*IOTracer*/);
 

db/blob/blob_file_meta.cc

@@ -8,7 +8,13 @@
 #include <ostream>
 #include <sstream>
 
+#include "db/blob/blob_log_format.h"
+#include "rocksdb/slice.h"
+
 namespace ROCKSDB_NAMESPACE {
+uint64_t SharedBlobFileMetaData::GetBlobFileSize() const {
+  return BlobLogHeader::kSize + total_blob_bytes_ + BlobLogFooter::kSize;
+}
 
 std::string SharedBlobFileMetaData::DebugString() const {
   std::ostringstream oss;
@@ -23,7 +29,8 @@ std::ostream& operator<<(std::ostream& os,
      << " total_blob_count: " << shared_meta.GetTotalBlobCount()
      << " total_blob_bytes: " << shared_meta.GetTotalBlobBytes()
      << " checksum_method: " << shared_meta.GetChecksumMethod()
-     << " checksum_value: " << shared_meta.GetChecksumValue();
+     << " checksum_value: "
+     << Slice(shared_meta.GetChecksumValue()).ToString(/* hex */ true);
 
   return os;
 }

db/blob/blob_file_meta.h

@@ -51,6 +51,7 @@ class SharedBlobFileMetaData {
   SharedBlobFileMetaData(SharedBlobFileMetaData&&) = delete;
   SharedBlobFileMetaData& operator=(SharedBlobFileMetaData&&) = delete;
 
+  uint64_t GetBlobFileSize() const;
   uint64_t GetBlobFileNumber() const { return blob_file_number_; }
   uint64_t GetTotalBlobCount() const { return total_blob_count_; }
   uint64_t GetTotalBlobBytes() const { return total_blob_bytes_; }
@@ -112,6 +113,11 @@ class BlobFileMetaData {
     return shared_meta_;
   }
 
+  uint64_t GetBlobFileSize() const {
+    assert(shared_meta_);
+    return shared_meta_->GetBlobFileSize();
+  }
+
   uint64_t GetBlobFileNumber() const {
     assert(shared_meta_);
     return shared_meta_->GetBlobFileNumber();

db/blob/blob_file_reader.cc

@@ -10,6 +10,7 @@
 
 #include "db/blob/blob_log_format.h"
 #include "file/filename.h"
+#include "monitoring/statistics.h"
 #include "options/cf_options.h"
 #include "rocksdb/file_system.h"
 #include "rocksdb/slice.h"
@@ -17,14 +18,14 @@
 #include "test_util/sync_point.h"
 #include "util/compression.h"
 #include "util/crc32c.h"
+#include "util/stop_watch.h"
 
 namespace ROCKSDB_NAMESPACE {
 
 Status BlobFileReader::Create(
-    const ImmutableOptions& immutable_cf_options,
-    const FileOptions& file_options, uint32_t column_family_id,
-    HistogramImpl* blob_file_read_hist, uint64_t blob_file_number,
-    const std::shared_ptr<IOTracer>& io_tracer,
+    const ImmutableOptions& immutable_options, const FileOptions& file_options,
+    uint32_t column_family_id, HistogramImpl* blob_file_read_hist,
+    uint64_t blob_file_number, const std::shared_ptr<IOTracer>& io_tracer,
     std::unique_ptr<BlobFileReader>* blob_file_reader) {
   assert(blob_file_reader);
   assert(!*blob_file_reader);
@@ -34,7 +35,7 @@ Status BlobFileReader::Create(
 
   {
     const Status s =
-        OpenFile(immutable_cf_options, file_options, blob_file_read_hist,
+        OpenFile(immutable_options, file_options, blob_file_read_hist,
                  blob_file_number, io_tracer, &file_size, &file_reader);
     if (!s.ok()) {
       return s;
@@ -43,44 +44,47 @@ Status BlobFileReader::Create(
 
   assert(file_reader);
 
+  Statistics* const statistics = immutable_options.stats;
+
   CompressionType compression_type = kNoCompression;
 
   {
-    const Status s =
-        ReadHeader(file_reader.get(), column_family_id, &compression_type);
+    const Status s = ReadHeader(file_reader.get(), column_family_id, statistics,
+                                &compression_type);
     if (!s.ok()) {
       return s;
     }
   }
 
   {
-    const Status s = ReadFooter(file_size, file_reader.get());
+    const Status s = ReadFooter(file_reader.get(), file_size, statistics);
     if (!s.ok()) {
       return s;
     }
   }
 
   blob_file_reader->reset(
-      new BlobFileReader(std::move(file_reader), file_size, compression_type));
+      new BlobFileReader(std::move(file_reader), file_size, compression_type,
+                         immutable_options.clock, statistics));
 
   return Status::OK();
 }
 
 Status BlobFileReader::OpenFile(
-    const ImmutableOptions& immutable_cf_options, const FileOptions& file_opts,
+    const ImmutableOptions& immutable_options, const FileOptions& file_opts,
     HistogramImpl* blob_file_read_hist, uint64_t blob_file_number,
     const std::shared_ptr<IOTracer>& io_tracer, uint64_t* file_size,
     std::unique_ptr<RandomAccessFileReader>* file_reader) {
   assert(file_size);
   assert(file_reader);
 
-  const auto& cf_paths = immutable_cf_options.cf_paths;
+  const auto& cf_paths = immutable_options.cf_paths;
   assert(!cf_paths.empty());
 
   const std::string blob_file_path =
       BlobFileName(cf_paths.front().path, blob_file_number);
 
-  FileSystem* const fs = immutable_cf_options.fs.get();
+  FileSystem* const fs = immutable_options.fs.get();
   assert(fs);
 
   constexpr IODebugContext* dbg = nullptr;
@@ -113,21 +117,22 @@ Status BlobFileReader::OpenFile(
 
   assert(file);
 
-  if (immutable_cf_options.advise_random_on_open) {
+  if (immutable_options.advise_random_on_open) {
     file->Hint(FSRandomAccessFile::kRandom);
   }
 
   file_reader->reset(new RandomAccessFileReader(
-      std::move(file), blob_file_path, immutable_cf_options.clock, io_tracer,
-      immutable_cf_options.stats, BLOB_DB_BLOB_FILE_READ_MICROS,
-      blob_file_read_hist, immutable_cf_options.rate_limiter.get(),
-      immutable_cf_options.listeners));
+      std::move(file), blob_file_path, immutable_options.clock, io_tracer,
+      immutable_options.stats, BLOB_DB_BLOB_FILE_READ_MICROS,
+      blob_file_read_hist, immutable_options.rate_limiter.get(),
+      immutable_options.listeners));
 
   return Status::OK();
 }
 
 Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
                                   uint32_t column_family_id,
+                                  Statistics* statistics,
                                   CompressionType* compression_type) {
   assert(file_reader);
   assert(compression_type);
@@ -142,8 +147,9 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
     constexpr uint64_t read_offset = 0;
     constexpr size_t read_size = BlobLogHeader::kSize;
 
-    const Status s = ReadFromFile(file_reader, read_offset, read_size,
-                                  &header_slice, &buf, &aligned_buf);
+    const Status s =
+        ReadFromFile(file_reader, read_offset, read_size, statistics,
+                     &header_slice, &buf, &aligned_buf);
     if (!s.ok()) {
       return s;
     }
@@ -176,8 +182,8 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
   return Status::OK();
 }
 
-Status BlobFileReader::ReadFooter(uint64_t file_size,
-                                  const RandomAccessFileReader* file_reader) {
+Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
+                                  uint64_t file_size, Statistics* statistics) {
   assert(file_size >= BlobLogHeader::kSize + BlobLogFooter::kSize);
   assert(file_reader);
 
@@ -191,8 +197,9 @@ Status BlobFileReader::ReadFooter(uint64_t file_size,
     const uint64_t read_offset = file_size - BlobLogFooter::kSize;
     constexpr size_t read_size = BlobLogFooter::kSize;
 
-    const Status s = ReadFromFile(file_reader, read_offset, read_size,
-                                  &footer_slice, &buf, &aligned_buf);
+    const Status s =
+        ReadFromFile(file_reader, read_offset, read_size, statistics,
+                     &footer_slice, &buf, &aligned_buf);
     if (!s.ok()) {
       return s;
     }
@@ -221,14 +228,16 @@ Status BlobFileReader::ReadFooter(uint64_t file_size,
 
 Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
                                     uint64_t read_offset, size_t read_size,
-                                    Slice* slice, Buffer* buf,
-                                    AlignedBuf* aligned_buf) {
+                                    Statistics* statistics, Slice* slice,
+                                    Buffer* buf, AlignedBuf* aligned_buf) {
   assert(slice);
   assert(buf);
   assert(aligned_buf);
 
   assert(file_reader);
 
+  RecordTick(statistics, BLOB_DB_BLOB_FILE_BYTES_READ, read_size);
+
   Status s;
 
   if (file_reader->use_direct_io()) {
@@ -257,10 +266,13 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
 
 BlobFileReader::BlobFileReader(
     std::unique_ptr<RandomAccessFileReader>&& file_reader, uint64_t file_size,
-    CompressionType compression_type)
+    CompressionType compression_type, SystemClock* clock,
+    Statistics* statistics)
     : file_reader_(std::move(file_reader)),
       file_size_(file_size),
-      compression_type_(compression_type) {
+      compression_type_(compression_type),
+      clock_(clock),
+      statistics_(statistics) {
   assert(file_reader_);
 }
 
@@ -305,7 +317,7 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,
     TEST_SYNC_POINT("BlobFileReader::GetBlob:ReadFromFile");
 
     const Status s = ReadFromFile(file_reader_.get(), record_offset,
-                                  static_cast<size_t>(record_size),
+                                  static_cast<size_t>(record_size), statistics_,
                                   &record_slice, &buf, &aligned_buf);
     if (!s.ok()) {
       return s;
@@ -325,8 +337,8 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,
   const Slice value_slice(record_slice.data() + adjustment, value_size);
 
   {
-    const Status s =
-        UncompressBlobIfNeeded(value_slice, compression_type, value);
+    const Status s = UncompressBlobIfNeeded(value_slice, compression_type,
+                                            clock_, statistics_, value);
     if (!s.ok()) {
       return s;
     }
@@ -383,6 +395,8 @@ Status BlobFileReader::VerifyBlob(const Slice& record_slice,
 
 Status BlobFileReader::UncompressBlobIfNeeded(const Slice& value_slice,
                                               CompressionType compression_type,
+                                              SystemClock* clock,
+                                              Statistics* statistics,
                                               PinnableSlice* value) {
   assert(value);
 
@@ -400,9 +414,14 @@ Status BlobFileReader::UncompressBlobIfNeeded(const Slice& value_slice,
   constexpr uint32_t compression_format_version = 2;
   constexpr MemoryAllocator* allocator = nullptr;
 
-  CacheAllocationPtr output =
-      UncompressData(info, value_slice.data(), value_slice.size(),
-                     &uncompressed_size, compression_format_version, allocator);
+  CacheAllocationPtr output;
+
+  {
+    StopWatch stop_watch(clock, statistics, BLOB_DB_DECOMPRESSION_MICROS);
+    output = UncompressData(info, value_slice.data(), value_slice.size(),
+                            &uncompressed_size, compression_format_version,
+                            allocator);
+  }
 
   TEST_SYNC_POINT_CALLBACK(
       "BlobFileReader::UncompressBlobIfNeeded:TamperWithResult", &output);

db/blob/blob_file_reader.h

@@ -21,6 +21,7 @@ class HistogramImpl;
 struct ReadOptions;
 class Slice;
 class PinnableSlice;
+class Statistics;
 
 class BlobFileReader {
  public:
@@ -44,7 +45,8 @@ class BlobFileReader {
 
  private:
   BlobFileReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
-                 uint64_t file_size, CompressionType compression_type);
+                 uint64_t file_size, CompressionType compression_type,
+                 SystemClock* clock, Statistics* statistics);
 
   static Status OpenFile(const ImmutableOptions& immutable_options,
                          const FileOptions& file_opts,
@@ -55,17 +57,17 @@ class BlobFileReader {
                          std::unique_ptr<RandomAccessFileReader>* file_reader);
 
   static Status ReadHeader(const RandomAccessFileReader* file_reader,
-                           uint32_t column_family_id,
+                           uint32_t column_family_id, Statistics* statistics,
                            CompressionType* compression_type);
 
-  static Status ReadFooter(uint64_t file_size,
-                           const RandomAccessFileReader* file_reader);
+  static Status ReadFooter(const RandomAccessFileReader* file_reader,
+                           uint64_t file_size, Statistics* statistics);
 
   using Buffer = std::unique_ptr<char[]>;
 
   static Status ReadFromFile(const RandomAccessFileReader* file_reader,
                              uint64_t read_offset, size_t read_size,
-                             Slice* slice, Buffer* buf,
+                             Statistics* statistics, Slice* slice, Buffer* buf,
                              AlignedBuf* aligned_buf);
 
   static Status VerifyBlob(const Slice& record_slice, const Slice& user_key,
@@ -73,6 +75,8 @@ class BlobFileReader {
 
   static Status UncompressBlobIfNeeded(const Slice& value_slice,
                                        CompressionType compression_type,
+                                       SystemClock* clock,
+                                       Statistics* statistics,
                                        PinnableSlice* value);
 
   static void SaveValue(const Slice& src, PinnableSlice* dst);
@@ -80,6 +84,8 @@ class BlobFileReader {
   std::unique_ptr<RandomAccessFileReader> file_reader_;
   uint64_t file_size_;
   CompressionType compression_type_;
+  SystemClock* clock_;
+  Statistics* statistics_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_reader_test.cc

@@ -30,35 +30,34 @@ namespace {
 // Creates a test blob file with a single blob in it. Note: this method
 // makes it possible to test various corner cases by allowing the caller
 // to specify the contents of various blob file header/footer fields.
-void WriteBlobFile(const ImmutableOptions& immutable_cf_options,
+void WriteBlobFile(const ImmutableOptions& immutable_options,
                    uint32_t column_family_id, bool has_ttl,
                    const ExpirationRange& expiration_range_header,
                    const ExpirationRange& expiration_range_footer,
                    uint64_t blob_file_number, const Slice& key,
                    const Slice& blob, CompressionType compression_type,
                    uint64_t* blob_offset, uint64_t* blob_size) {
-  assert(!immutable_cf_options.cf_paths.empty());
+  assert(!immutable_options.cf_paths.empty());
   assert(blob_offset);
   assert(blob_size);
 
-  const std::string blob_file_path = BlobFileName(
-      immutable_cf_options.cf_paths.front().path, blob_file_number);
+  const std::string blob_file_path =
+      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number);
 
   std::unique_ptr<FSWritableFile> file;
-  ASSERT_OK(NewWritableFile(immutable_cf_options.fs.get(), blob_file_path,
-                            &file, FileOptions()));
+  ASSERT_OK(NewWritableFile(immutable_options.fs.get(), blob_file_path, &file,
+                            FileOptions()));
 
-  std::unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(file), blob_file_path, FileOptions(),
-                             immutable_cf_options.clock));
+  std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
+      std::move(file), blob_file_path, FileOptions(), immutable_options.clock));
 
   constexpr Statistics* statistics = nullptr;
   constexpr bool use_fsync = false;
   constexpr bool do_flush = false;
 
-  BlobLogWriter blob_log_writer(std::move(file_writer),
-                                immutable_cf_options.clock, statistics,
-                                blob_file_number, use_fsync, do_flush);
+  BlobLogWriter blob_log_writer(std::move(file_writer), immutable_options.clock,
+                                statistics, blob_file_number, use_fsync,
+                                do_flush);
 
   BlobLogHeader header(column_family_id, compression_type, has_ttl,
                        expiration_range_header);
@@ -122,7 +121,7 @@ TEST_F(BlobFileReaderTest, CreateReaderAndGetBlob) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -134,17 +133,17 @@ TEST_F(BlobFileReaderTest, CreateReaderAndGetBlob) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
-                kNoCompression, &blob_offset, &blob_size);
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob, kNoCompression,
+                &blob_offset, &blob_size);
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
 
   ASSERT_OK(BlobFileReader::Create(
-      immutable_cf_options, FileOptions(), column_family_id,
-      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
+      blob_file_number, nullptr /*IOTracer*/, &reader));
 
   // Make sure the blob can be retrieved with and without checksum verification
   ReadOptions read_options;
@@ -262,7 +261,7 @@ TEST_F(BlobFileReaderTest, Malformed) {
       test::PerThreadDBPath(&mock_env_, "BlobFileReaderTest_Malformed"), 0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr uint64_t blob_file_number = 1;
@@ -271,23 +270,23 @@ TEST_F(BlobFileReaderTest, Malformed) {
     constexpr bool has_ttl = false;
     constexpr ExpirationRange expiration_range;
 
-    const std::string blob_file_path = BlobFileName(
-        immutable_cf_options.cf_paths.front().path, blob_file_number);
+    const std::string blob_file_path =
+        BlobFileName(immutable_options.cf_paths.front().path, blob_file_number);
 
     std::unique_ptr<FSWritableFile> file;
-    ASSERT_OK(NewWritableFile(immutable_cf_options.fs.get(), blob_file_path,
-                              &file, FileOptions()));
+    ASSERT_OK(NewWritableFile(immutable_options.fs.get(), blob_file_path, &file,
+                              FileOptions()));
 
     std::unique_ptr<WritableFileWriter> file_writer(
         new WritableFileWriter(std::move(file), blob_file_path, FileOptions(),
-                               immutable_cf_options.clock));
+                               immutable_options.clock));
 
     constexpr Statistics* statistics = nullptr;
     constexpr bool use_fsync = false;
     constexpr bool do_flush = false;
 
     BlobLogWriter blob_log_writer(std::move(file_writer),
-                                  immutable_cf_options.clock, statistics,
+                                  immutable_options.clock, statistics,
                                   blob_file_number, use_fsync, do_flush);
 
     BlobLogHeader header(column_family_id, kNoCompression, has_ttl,
@@ -300,7 +299,7 @@ TEST_F(BlobFileReaderTest, Malformed) {
 
   std::unique_ptr<BlobFileReader> reader;
 
-  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
                                      column_family_id, blob_file_read_hist,
                                      blob_file_number, nullptr /*IOTracer*/,
                                      &reader)
@@ -314,7 +313,7 @@ TEST_F(BlobFileReaderTest, TTL) {
       test::PerThreadDBPath(&mock_env_, "BlobFileReaderTest_TTL"), 0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = true;
@@ -326,15 +325,15 @@ TEST_F(BlobFileReaderTest, TTL) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
-                kNoCompression, &blob_offset, &blob_size);
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob, kNoCompression,
+                &blob_offset, &blob_size);
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
 
-  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
                                      column_family_id, blob_file_read_hist,
                                      blob_file_number, nullptr /*IOTracer*/,
                                      &reader)
@@ -350,7 +349,7 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInHeader) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -364,7 +363,7 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInHeader) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
+  WriteBlobFile(immutable_options, column_family_id, has_ttl,
                 expiration_range_header, expiration_range_footer,
                 blob_file_number, key, blob, kNoCompression, &blob_offset,
                 &blob_size);
@@ -373,7 +372,7 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInHeader) {
 
   std::unique_ptr<BlobFileReader> reader;
 
-  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
                                      column_family_id, blob_file_read_hist,
                                      blob_file_number, nullptr /*IOTracer*/,
                                      &reader)
@@ -389,7 +388,7 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInFooter) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -403,7 +402,7 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInFooter) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
+  WriteBlobFile(immutable_options, column_family_id, has_ttl,
                 expiration_range_header, expiration_range_footer,
                 blob_file_number, key, blob, kNoCompression, &blob_offset,
                 &blob_size);
@@ -412,7 +411,7 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInFooter) {
 
   std::unique_ptr<BlobFileReader> reader;
 
-  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
                                      column_family_id, blob_file_read_hist,
                                      blob_file_number, nullptr /*IOTracer*/,
                                      &reader)
@@ -428,7 +427,7 @@ TEST_F(BlobFileReaderTest, IncorrectColumnFamily) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -440,9 +439,9 @@ TEST_F(BlobFileReaderTest, IncorrectColumnFamily) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
-                kNoCompression, &blob_offset, &blob_size);
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob, kNoCompression,
+                &blob_offset, &blob_size);
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
@@ -450,7 +449,7 @@ TEST_F(BlobFileReaderTest, IncorrectColumnFamily) {
 
   constexpr uint32_t incorrect_column_family_id = 2;
 
-  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
                                      incorrect_column_family_id,
                                      blob_file_read_hist, blob_file_number,
                                      nullptr /*IOTracer*/, &reader)
@@ -464,7 +463,7 @@ TEST_F(BlobFileReaderTest, BlobCRCError) {
       test::PerThreadDBPath(&mock_env_, "BlobFileReaderTest_BlobCRCError"), 0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -476,17 +475,17 @@ TEST_F(BlobFileReaderTest, BlobCRCError) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
-                kNoCompression, &blob_offset, &blob_size);
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob, kNoCompression,
+                &blob_offset, &blob_size);
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
 
   ASSERT_OK(BlobFileReader::Create(
-      immutable_cf_options, FileOptions(), column_family_id,
-      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
+      blob_file_number, nullptr /*IOTracer*/, &reader));
 
   SyncPoint::GetInstance()->SetCallBack(
       "BlobFileReader::VerifyBlob:CheckBlobCRC", [](void* arg) {
@@ -522,7 +521,7 @@ TEST_F(BlobFileReaderTest, Compression) {
       test::PerThreadDBPath(&mock_env_, "BlobFileReaderTest_Compression"), 0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -534,8 +533,8 @@ TEST_F(BlobFileReaderTest, Compression) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob,
                 kSnappyCompression, &blob_offset, &blob_size);
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
@@ -543,8 +542,8 @@ TEST_F(BlobFileReaderTest, Compression) {
   std::unique_ptr<BlobFileReader> reader;
 
   ASSERT_OK(BlobFileReader::Create(
-      immutable_cf_options, FileOptions(), column_family_id,
-      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
+      blob_file_number, nullptr /*IOTracer*/, &reader));
 
   // Make sure the blob can be retrieved with and without checksum verification
   ReadOptions read_options;
@@ -590,7 +589,7 @@ TEST_F(BlobFileReaderTest, UncompressionError) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -602,8 +601,8 @@ TEST_F(BlobFileReaderTest, UncompressionError) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob,
                 kSnappyCompression, &blob_offset, &blob_size);
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
@@ -611,8 +610,8 @@ TEST_F(BlobFileReaderTest, UncompressionError) {
   std::unique_ptr<BlobFileReader> reader;
 
   ASSERT_OK(BlobFileReader::Create(
-      immutable_cf_options, FileOptions(), column_family_id,
-      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
+      blob_file_number, nullptr /*IOTracer*/, &reader));
 
   SyncPoint::GetInstance()->SetCallBack(
       "BlobFileReader::UncompressBlobIfNeeded:TamperWithResult", [](void* arg) {
@@ -671,7 +670,7 @@ TEST_P(BlobFileReaderIOErrorTest, IOError) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -683,9 +682,9 @@ TEST_P(BlobFileReaderIOErrorTest, IOError) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
-                kNoCompression, &blob_offset, &blob_size);
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob, kNoCompression,
+                &blob_offset, &blob_size);
 
   SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
     fault_injection_env_.SetFilesystemActive(false,
@@ -698,8 +697,8 @@ TEST_P(BlobFileReaderIOErrorTest, IOError) {
   std::unique_ptr<BlobFileReader> reader;
 
   const Status s = BlobFileReader::Create(
-      immutable_cf_options, FileOptions(), column_family_id,
-      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader);
+      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
+      blob_file_number, nullptr /*IOTracer*/, &reader);
 
   const bool fail_during_create =
       (sync_point_ != "BlobFileReader::GetBlob:ReadFromFile");
@@ -749,7 +748,7 @@ TEST_P(BlobFileReaderDecodingErrorTest, DecodingError) {
       0);
   options.enable_blob_files = true;
 
-  ImmutableOptions immutable_cf_options(options);
+  ImmutableOptions immutable_options(options);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -761,9 +760,9 @@ TEST_P(BlobFileReaderDecodingErrorTest, DecodingError) {
   uint64_t blob_offset = 0;
   uint64_t blob_size = 0;
 
-  WriteBlobFile(immutable_cf_options, column_family_id, has_ttl,
-                expiration_range, expiration_range, blob_file_number, key, blob,
-                kNoCompression, &blob_offset, &blob_size);
+  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
+                expiration_range, blob_file_number, key, blob, kNoCompression,
+                &blob_offset, &blob_size);
 
   SyncPoint::GetInstance()->SetCallBack(sync_point_, [](void* arg) {
     Slice* const slice = static_cast<Slice*>(arg);
@@ -780,8 +779,8 @@ TEST_P(BlobFileReaderDecodingErrorTest, DecodingError) {
   std::unique_ptr<BlobFileReader> reader;
 
   const Status s = BlobFileReader::Create(
-      immutable_cf_options, FileOptions(), column_family_id,
-      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader);
+      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
+      blob_file_number, nullptr /*IOTracer*/, &reader);
 
   const bool fail_during_create =
       sync_point_ != "BlobFileReader::GetBlob:TamperWithResult";

db/blob/blob_garbage_meter.cc

@@ -0,0 +1,100 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/blob/blob_garbage_meter.h"
+
+#include "db/blob/blob_index.h"
+#include "db/blob/blob_log_format.h"
+#include "db/dbformat.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+Status BlobGarbageMeter::ProcessInFlow(const Slice& key, const Slice& value) {
+  uint64_t blob_file_number = kInvalidBlobFileNumber;
+  uint64_t bytes = 0;
+
+  const Status s = Parse(key, value, &blob_file_number, &bytes);
+  if (!s.ok()) {
+    return s;
+  }
+
+  if (blob_file_number == kInvalidBlobFileNumber) {
+    return Status::OK();
+  }
+
+  flows_[blob_file_number].AddInFlow(bytes);
+
+  return Status::OK();
+}
+
+Status BlobGarbageMeter::ProcessOutFlow(const Slice& key, const Slice& value) {
+  uint64_t blob_file_number = kInvalidBlobFileNumber;
+  uint64_t bytes = 0;
+
+  const Status s = Parse(key, value, &blob_file_number, &bytes);
+  if (!s.ok()) {
+    return s;
+  }
+
+  if (blob_file_number == kInvalidBlobFileNumber) {
+    return Status::OK();
+  }
+
+  // Note: in order to measure the amount of additional garbage, we only need to
+  // track the outflow for preexisting files, i.e. those that also had inflow.
+  // (Newly written files would only have outflow.)
+  auto it = flows_.find(blob_file_number);
+  if (it == flows_.end()) {
+    return Status::OK();
+  }
+
+  it->second.AddOutFlow(bytes);
+
+  return Status::OK();
+}
+
+Status BlobGarbageMeter::Parse(const Slice& key, const Slice& value,
+                               uint64_t* blob_file_number, uint64_t* bytes) {
+  assert(blob_file_number);
+  assert(*blob_file_number == kInvalidBlobFileNumber);
+  assert(bytes);
+  assert(*bytes == 0);
+
+  ParsedInternalKey ikey;
+
+  {
+    constexpr bool log_err_key = false;
+    const Status s = ParseInternalKey(key, &ikey, log_err_key);
+    if (!s.ok()) {
+      return s;
+    }
+  }
+
+  if (ikey.type != kTypeBlobIndex) {
+    return Status::OK();
+  }
+
+  BlobIndex blob_index;
+
+  {
+    const Status s = blob_index.DecodeFrom(value);
+    if (!s.ok()) {
+      return s;
+    }
+  }
+
+  if (blob_index.IsInlined() || blob_index.HasTTL()) {
+    return Status::Corruption("Unexpected TTL/inlined blob index");
+  }
+
+  *blob_file_number = blob_index.file_number();
+  *bytes =
+      blob_index.size() +
+      BlobLogRecord::CalculateAdjustmentForRecordHeader(ikey.user_key.size());
+
+  return Status::OK();
+}
+
+}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_garbage_meter.h

@@ -0,0 +1,102 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <cassert>
+#include <cstdint>
+#include <unordered_map>
+
+#include "db/blob/blob_constants.h"
+#include "rocksdb/rocksdb_namespace.h"
+#include "rocksdb/status.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class Slice;
+
+// A class that can be used to compute the amount of additional garbage
+// generated by a compaction. It parses the keys and blob references in the
+// input and output of a compaction, and aggregates the "inflow" and "outflow"
+// on a per-blob file basis. The amount of additional garbage for any given blob
+// file can then be computed by subtracting the outflow from the inflow.
+class BlobGarbageMeter {
+ public:
+  // A class to store the number and total size of blobs on a per-blob file
+  // basis.
+  class BlobStats {
+   public:
+    void Add(uint64_t bytes) {
+      ++count_;
+      bytes_ += bytes;
+    }
+    void Add(uint64_t count, uint64_t bytes) {
+      count_ += count;
+      bytes_ += bytes;
+    }
+
+    uint64_t GetCount() const { return count_; }
+    uint64_t GetBytes() const { return bytes_; }
+
+   private:
+    uint64_t count_ = 0;
+    uint64_t bytes_ = 0;
+  };
+
+  // A class to keep track of the "inflow" and the "outflow" and to compute the
+  // amount of additional garbage for a given blob file.
+  class BlobInOutFlow {
+   public:
+    void AddInFlow(uint64_t bytes) {
+      in_flow_.Add(bytes);
+      assert(IsValid());
+    }
+    void AddOutFlow(uint64_t bytes) {
+      out_flow_.Add(bytes);
+      assert(IsValid());
+    }
+
+    const BlobStats& GetInFlow() const { return in_flow_; }
+    const BlobStats& GetOutFlow() const { return out_flow_; }
+
+    bool IsValid() const {
+      return in_flow_.GetCount() >= out_flow_.GetCount() &&
+             in_flow_.GetBytes() >= out_flow_.GetBytes();
+    }
+    bool HasGarbage() const {
+      assert(IsValid());
+      return in_flow_.GetCount() > out_flow_.GetCount();
+    }
+    uint64_t GetGarbageCount() const {
+      assert(IsValid());
+      assert(HasGarbage());
+      return in_flow_.GetCount() - out_flow_.GetCount();
+    }
+    uint64_t GetGarbageBytes() const {
+      assert(IsValid());
+      assert(HasGarbage());
+      return in_flow_.GetBytes() - out_flow_.GetBytes();
+    }
+
+   private:
+    BlobStats in_flow_;
+    BlobStats out_flow_;
+  };
+
+  Status ProcessInFlow(const Slice& key, const Slice& value);
+  Status ProcessOutFlow(const Slice& key, const Slice& value);
+
+  const std::unordered_map<uint64_t, BlobInOutFlow>& flows() const {
+    return flows_;
+  }
+
+ private:
+  static Status Parse(const Slice& key, const Slice& value,
+                      uint64_t* blob_file_number, uint64_t* bytes);
+
+  std::unordered_map<uint64_t, BlobInOutFlow> flows_;
+};
+
+}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_garbage_meter_test.cc

@@ -0,0 +1,196 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/blob/blob_garbage_meter.h"
+
+#include <string>
+#include <vector>
+
+#include "db/blob/blob_index.h"
+#include "db/blob/blob_log_format.h"
+#include "db/dbformat.h"
+#include "test_util/testharness.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+TEST(BlobGarbageMeterTest, MeasureGarbage) {
+  BlobGarbageMeter blob_garbage_meter;
+
+  struct BlobDescriptor {
+    std::string user_key;
+    uint64_t blob_file_number;
+    uint64_t offset;
+    uint64_t size;
+    CompressionType compression_type;
+    bool has_in_flow;
+    bool has_out_flow;
+
+    uint64_t GetExpectedBytes() const {
+      return size +
+             BlobLogRecord::CalculateAdjustmentForRecordHeader(user_key.size());
+    }
+  };
+
+  // Note: blob file 4 has the same inflow and outflow and hence no additional
+  // garbage. Blob file 5 has less outflow than inflow and thus it does have
+  // additional garbage. Blob file 6 is a newly written file (i.e. no inflow,
+  // only outflow) and is thus not tracked by the meter.
+  std::vector<BlobDescriptor> blobs{
+      {"key", 4, 1234, 555, kLZ4Compression, true, true},
+      {"other_key", 4, 6789, 101010, kLZ4Compression, true, true},
+      {"yet_another_key", 5, 22222, 3456, kLZ4Compression, true, true},
+      {"foo_key", 5, 77777, 8888, kLZ4Compression, true, true},
+      {"bar_key", 5, 999999, 1212, kLZ4Compression, true, false},
+      {"baz_key", 5, 1234567, 890, kLZ4Compression, true, false},
+      {"new_key", 6, 7777, 9999, kNoCompression, false, true}};
+
+  for (const auto& blob : blobs) {
+    constexpr SequenceNumber seq = 123;
+    const InternalKey key(blob.user_key, seq, kTypeBlobIndex);
+    const Slice key_slice = key.Encode();
+
+    std::string value;
+    BlobIndex::EncodeBlob(&value, blob.blob_file_number, blob.offset, blob.size,
+                          blob.compression_type);
+    const Slice value_slice(value);
+
+    if (blob.has_in_flow) {
+      ASSERT_OK(blob_garbage_meter.ProcessInFlow(key_slice, value_slice));
+    }
+    if (blob.has_out_flow) {
+      ASSERT_OK(blob_garbage_meter.ProcessOutFlow(key_slice, value_slice));
+    }
+  }
+
+  const auto& flows = blob_garbage_meter.flows();
+  ASSERT_EQ(flows.size(), 2);
+
+  {
+    const auto it = flows.find(4);
+    ASSERT_NE(it, flows.end());
+
+    const auto& flow = it->second;
+
+    constexpr uint64_t expected_count = 2;
+    const uint64_t expected_bytes =
+        blobs[0].GetExpectedBytes() + blobs[1].GetExpectedBytes();
+
+    const auto& in = flow.GetInFlow();
+    ASSERT_EQ(in.GetCount(), expected_count);
+    ASSERT_EQ(in.GetBytes(), expected_bytes);
+
+    const auto& out = flow.GetOutFlow();
+    ASSERT_EQ(out.GetCount(), expected_count);
+    ASSERT_EQ(out.GetBytes(), expected_bytes);
+
+    ASSERT_TRUE(flow.IsValid());
+    ASSERT_FALSE(flow.HasGarbage());
+  }
+
+  {
+    const auto it = flows.find(5);
+    ASSERT_NE(it, flows.end());
+
+    const auto& flow = it->second;
+
+    const auto& in = flow.GetInFlow();
+
+    constexpr uint64_t expected_in_count = 4;
+    const uint64_t expected_in_bytes =
+        blobs[2].GetExpectedBytes() + blobs[3].GetExpectedBytes() +
+        blobs[4].GetExpectedBytes() + blobs[5].GetExpectedBytes();
+
+    ASSERT_EQ(in.GetCount(), expected_in_count);
+    ASSERT_EQ(in.GetBytes(), expected_in_bytes);
+
+    const auto& out = flow.GetOutFlow();
+
+    constexpr uint64_t expected_out_count = 2;
+    const uint64_t expected_out_bytes =
+        blobs[2].GetExpectedBytes() + blobs[3].GetExpectedBytes();
+
+    ASSERT_EQ(out.GetCount(), expected_out_count);
+    ASSERT_EQ(out.GetBytes(), expected_out_bytes);
+
+    ASSERT_TRUE(flow.IsValid());
+    ASSERT_TRUE(flow.HasGarbage());
+    ASSERT_EQ(flow.GetGarbageCount(), expected_in_count - expected_out_count);
+    ASSERT_EQ(flow.GetGarbageBytes(), expected_in_bytes - expected_out_bytes);
+  }
+}
+
+TEST(BlobGarbageMeterTest, PlainValue) {
+  constexpr char user_key[] = "user_key";
+  constexpr SequenceNumber seq = 123;
+
+  const InternalKey key(user_key, seq, kTypeValue);
+  const Slice key_slice = key.Encode();
+
+  constexpr char value[] = "value";
+  const Slice value_slice(value);
+
+  BlobGarbageMeter blob_garbage_meter;
+
+  ASSERT_OK(blob_garbage_meter.ProcessInFlow(key_slice, value_slice));
+  ASSERT_OK(blob_garbage_meter.ProcessOutFlow(key_slice, value_slice));
+  ASSERT_TRUE(blob_garbage_meter.flows().empty());
+}
+
+TEST(BlobGarbageMeterTest, CorruptInternalKey) {
+  constexpr char corrupt_key[] = "i_am_corrupt";
+  const Slice key_slice(corrupt_key);
+
+  constexpr char value[] = "value";
+  const Slice value_slice(value);
+
+  BlobGarbageMeter blob_garbage_meter;
+
+  ASSERT_NOK(blob_garbage_meter.ProcessInFlow(key_slice, value_slice));
+  ASSERT_NOK(blob_garbage_meter.ProcessOutFlow(key_slice, value_slice));
+}
+
+TEST(BlobGarbageMeterTest, CorruptBlobIndex) {
+  constexpr char user_key[] = "user_key";
+  constexpr SequenceNumber seq = 123;
+
+  const InternalKey key(user_key, seq, kTypeBlobIndex);
+  const Slice key_slice = key.Encode();
+
+  constexpr char value[] = "i_am_not_a_blob_index";
+  const Slice value_slice(value);
+
+  BlobGarbageMeter blob_garbage_meter;
+
+  ASSERT_NOK(blob_garbage_meter.ProcessInFlow(key_slice, value_slice));
+  ASSERT_NOK(blob_garbage_meter.ProcessOutFlow(key_slice, value_slice));
+}
+
+TEST(BlobGarbageMeterTest, InlinedTTLBlobIndex) {
+  constexpr char user_key[] = "user_key";
+  constexpr SequenceNumber seq = 123;
+
+  const InternalKey key(user_key, seq, kTypeBlobIndex);
+  const Slice key_slice = key.Encode();
+
+  constexpr uint64_t expiration = 1234567890;
+  constexpr char inlined_value[] = "inlined";
+
+  std::string value;
+  BlobIndex::EncodeInlinedTTL(&value, expiration, inlined_value);
+
+  const Slice value_slice(value);
+
+  BlobGarbageMeter blob_garbage_meter;
+
+  ASSERT_NOK(blob_garbage_meter.ProcessInFlow(key_slice, value_slice));
+  ASSERT_NOK(blob_garbage_meter.ProcessOutFlow(key_slice, value_slice));
+}
+
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/blob/blob_log_format.h

@@ -107,7 +107,8 @@ struct BlobLogRecord {
   // Note that the offset field of BlobIndex actually points to the blob value
   // as opposed to the start of the blob record. The following method can
   // be used to calculate the adjustment needed to read the blob record header.
-  static uint64_t CalculateAdjustmentForRecordHeader(uint64_t key_size) {
+  static constexpr uint64_t CalculateAdjustmentForRecordHeader(
+      uint64_t key_size) {
     return key_size + kHeaderSize;
   }
 

db/blob/blob_log_sequential_reader.h

@@ -10,6 +10,8 @@
 #include "db/blob/blob_log_format.h"
 #include "rocksdb/slice.h"
 
+#define MAX_HEADER_SIZE(a, b, c) (a > b ? (a > c ? a : c) : (b > c ? b : c))
+
 namespace ROCKSDB_NAMESPACE {
 
 class RandomAccessFileReader;
@@ -69,10 +71,13 @@ class BlobLogSequentialReader {
   Statistics* statistics_;
 
   Slice buffer_;
-  char header_buf_[BlobLogRecord::kHeaderSize];
+  char header_buf_[MAX_HEADER_SIZE(BlobLogHeader::kSize, BlobLogFooter::kSize,
+                                   BlobLogRecord::kHeaderSize)];
 
   // which byte to read next
   uint64_t next_byte_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE
+
+#undef MAX_HEADER_SIZE

db/blob/db_blob_basic_test.cc

@@ -16,7 +16,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBBlobBasicTest : public DBTestBase {
  protected:
   DBBlobBasicTest()
-      : DBTestBase("/db_blob_basic_test", /* env_do_fsync */ false) {}
+      : DBTestBase("db_blob_basic_test", /* env_do_fsync */ false) {}
 };
 
 TEST_F(DBBlobBasicTest, GetBlob) {
@@ -310,6 +310,63 @@ TEST_F(DBBlobBasicTest, BestEffortsRecovery_MissingNewestBlobFile) {
   ASSERT_EQ("value" + std::to_string(kNumTableFiles - 2), value);
 }
 
+TEST_F(DBBlobBasicTest, GetMergeBlobWithPut) {
+  Options options = GetDefaultOptions();
+  options.merge_operator = MergeOperators::CreateStringAppendOperator();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+
+  Reopen(options);
+
+  ASSERT_OK(Put("Key1", "v1"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Merge("Key1", "v2"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Merge("Key1", "v3"));
+  ASSERT_OK(Flush());
+
+  std::string value;
+  ASSERT_OK(db_->Get(ReadOptions(), "Key1", &value));
+  ASSERT_EQ(Get("Key1"), "v1,v2,v3");
+}
+
+TEST_F(DBBlobBasicTest, MultiGetMergeBlobWithPut) {
+  constexpr size_t num_keys = 3;
+
+  Options options = GetDefaultOptions();
+  options.merge_operator = MergeOperators::CreateStringAppendOperator();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+
+  Reopen(options);
+
+  ASSERT_OK(Put("Key0", "v0_0"));
+  ASSERT_OK(Put("Key1", "v1_0"));
+  ASSERT_OK(Put("Key2", "v2_0"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Merge("Key0", "v0_1"));
+  ASSERT_OK(Merge("Key1", "v1_1"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Merge("Key0", "v0_2"));
+  ASSERT_OK(Flush());
+
+  std::array<Slice, num_keys> keys{{"Key0", "Key1", "Key2"}};
+  std::array<PinnableSlice, num_keys> values;
+  std::array<Status, num_keys> statuses;
+
+  db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys, &keys[0],
+                &values[0], &statuses[0]);
+
+  ASSERT_OK(statuses[0]);
+  ASSERT_EQ(values[0], "v0_0,v0_1,v0_2");
+
+  ASSERT_OK(statuses[1]);
+  ASSERT_EQ(values[1], "v1_0,v1_1");
+
+  ASSERT_OK(statuses[2]);
+  ASSERT_EQ(values[2], "v2_0");
+}
+
 class DBBlobBasicIOErrorTest : public DBBlobBasicTest,
                                public testing::WithParamInterface<std::string> {
  protected:

db/blob/db_blob_compaction_test.cc

@@ -4,6 +4,7 @@
 //  (found in the LICENSE.Apache file in the root directory).
 
 #include "db/blob/blob_index.h"
+#include "db/blob/blob_log_format.h"
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
 #include "test_util/sync_point.h"
@@ -14,7 +15,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBBlobCompactionTest : public DBTestBase {
  public:
   explicit DBBlobCompactionTest()
-      : DBTestBase("/db_blob_compaction_test", /*env_do_fsync=*/false) {}
+      : DBTestBase("db_blob_compaction_test", /*env_do_fsync=*/false) {}
 
 #ifndef ROCKSDB_LITE
   const std::vector<InternalStats::CompactionStats>& GetCompactionStats() {
@@ -152,6 +153,31 @@ class AlwaysKeepFilter : public CompactionFilter {
     return CompactionFilter::Decision::kKeep;
   }
 };
+
+class SkipUntilFilter : public CompactionFilter {
+ public:
+  explicit SkipUntilFilter(std::string skip_until)
+      : skip_until_(std::move(skip_until)) {}
+
+  const char* Name() const override {
+    return "rocksdb.compaction.filter.skip.until";
+  }
+
+  CompactionFilter::Decision FilterV2(int /* level */, const Slice& /* key */,
+                                      ValueType /* value_type */,
+                                      const Slice& /* existing_value */,
+                                      std::string* /* new_value */,
+                                      std::string* skip_until) const override {
+    assert(skip_until);
+    *skip_until = skip_until_;
+
+    return CompactionFilter::Decision::kRemoveAndSkipUntil;
+  }
+
+ private:
+  std::string skip_until_;
+};
+
 }  // anonymous namespace
 
 class DBBlobBadCompactionFilterTest
@@ -254,6 +280,49 @@ TEST_F(DBBlobCompactionTest, BlindWriteFilter) {
   Close();
 }
 
+TEST_F(DBBlobCompactionTest, SkipUntilFilter) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new SkipUntilFilter("z"));
+  options.compaction_filter = compaction_filter_guard.get();
+
+  Reopen(options);
+
+  const std::vector<std::string> keys{"a", "b", "c"};
+  const std::vector<std::string> values{"a_value", "b_value", "c_value"};
+  assert(keys.size() == values.size());
+
+  for (size_t i = 0; i < keys.size(); ++i) {
+    ASSERT_OK(Put(keys[i], values[i]));
+  }
+
+  ASSERT_OK(Flush());
+
+  int process_in_flow_called = 0;
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "BlobCountingIterator::UpdateAndCountBlobIfNeeded:ProcessInFlow",
+      [&process_in_flow_called](void* /* arg */) { ++process_in_flow_called; });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /* begin */ nullptr,
+                              /* end */ nullptr));
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  for (const auto& key : keys) {
+    ASSERT_EQ(Get(key), "NOT_FOUND");
+  }
+
+  // Make sure SkipUntil was performed using iteration rather than Seek
+  ASSERT_EQ(process_in_flow_called, keys.size());
+
+  Close();
+}
+
 TEST_P(DBBlobBadCompactionFilterTest, BadDecisionFromCompactionFilter) {
   Options options = GetDefaultOptions();
   options.enable_blob_files = true;
@@ -390,6 +459,138 @@ TEST_F(DBBlobCompactionTest, CompactionFilterReadBlobAndKeep) {
   Close();
 }
 
+TEST_F(DBBlobCompactionTest, TrackGarbage) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+
+  Reopen(options);
+
+  // First table+blob file pair: 4 blobs with different keys
+  constexpr char first_key[] = "first_key";
+  constexpr char first_value[] = "first_value";
+  constexpr char second_key[] = "second_key";
+  constexpr char second_value[] = "second_value";
+  constexpr char third_key[] = "third_key";
+  constexpr char third_value[] = "third_value";
+  constexpr char fourth_key[] = "fourth_key";
+  constexpr char fourth_value[] = "fourth_value";
+
+  ASSERT_OK(Put(first_key, first_value));
+  ASSERT_OK(Put(second_key, second_value));
+  ASSERT_OK(Put(third_key, third_value));
+  ASSERT_OK(Put(fourth_key, fourth_value));
+  ASSERT_OK(Flush());
+
+  // Second table+blob file pair: overwrite 2 existing keys
+  constexpr char new_first_value[] = "new_first_value";
+  constexpr char new_second_value[] = "new_second_value";
+
+  ASSERT_OK(Put(first_key, new_first_value));
+  ASSERT_OK(Put(second_key, new_second_value));
+  ASSERT_OK(Flush());
+
+  // Compact them together. The first blob file should have 2 garbage blobs
+  // corresponding to the 2 overwritten keys.
+  constexpr Slice* begin = nullptr;
+  constexpr Slice* end = nullptr;
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), begin, end));
+
+  VersionSet* const versions = dbfull()->TEST_GetVersionSet();
+  assert(versions);
+  assert(versions->GetColumnFamilySet());
+
+  ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
+  assert(cfd);
+
+  Version* const current = cfd->current();
+  assert(current);
+
+  const VersionStorageInfo* const storage_info = current->storage_info();
+  assert(storage_info);
+
+  const auto& blob_files = storage_info->GetBlobFiles();
+  ASSERT_EQ(blob_files.size(), 2);
+
+  {
+    auto it = blob_files.begin();
+    const auto& meta = it->second;
+    assert(meta);
+
+    constexpr uint64_t first_expected_bytes =
+        sizeof(first_value) - 1 +
+        BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(first_key) -
+                                                          1);
+    constexpr uint64_t second_expected_bytes =
+        sizeof(second_value) - 1 +
+        BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(second_key) -
+                                                          1);
+    constexpr uint64_t third_expected_bytes =
+        sizeof(third_value) - 1 +
+        BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(third_key) -
+                                                          1);
+    constexpr uint64_t fourth_expected_bytes =
+        sizeof(fourth_value) - 1 +
+        BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(fourth_key) -
+                                                          1);
+
+    ASSERT_EQ(meta->GetTotalBlobCount(), 4);
+    ASSERT_EQ(meta->GetTotalBlobBytes(),
+              first_expected_bytes + second_expected_bytes +
+                  third_expected_bytes + fourth_expected_bytes);
+    ASSERT_EQ(meta->GetGarbageBlobCount(), 2);
+    ASSERT_EQ(meta->GetGarbageBlobBytes(),
+              first_expected_bytes + second_expected_bytes);
+  }
+
+  {
+    auto it = blob_files.rbegin();
+    const auto& meta = it->second;
+    assert(meta);
+
+    constexpr uint64_t new_first_expected_bytes =
+        sizeof(new_first_value) - 1 +
+        BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(first_key) -
+                                                          1);
+    constexpr uint64_t new_second_expected_bytes =
+        sizeof(new_second_value) - 1 +
+        BlobLogRecord::CalculateAdjustmentForRecordHeader(sizeof(second_key) -
+                                                          1);
+
+    ASSERT_EQ(meta->GetTotalBlobCount(), 2);
+    ASSERT_EQ(meta->GetTotalBlobBytes(),
+              new_first_expected_bytes + new_second_expected_bytes);
+    ASSERT_EQ(meta->GetGarbageBlobCount(), 0);
+    ASSERT_EQ(meta->GetGarbageBlobBytes(), 0);
+  }
+}
+
+TEST_F(DBBlobCompactionTest, MergeBlobWithBase) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  options.merge_operator = MergeOperators::CreateStringAppendOperator();
+  options.disable_auto_compactions = true;
+
+  Reopen(options);
+  ASSERT_OK(Put("Key1", "v1_1"));
+  ASSERT_OK(Put("Key2", "v2_1"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(Merge("Key1", "v1_2"));
+  ASSERT_OK(Merge("Key2", "v2_2"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(Merge("Key1", "v1_3"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                              /*end=*/nullptr));
+  ASSERT_EQ(Get("Key1"), "v1_1,v1_2,v1_3");
+  ASSERT_EQ(Get("Key2"), "v2_1,v2_2");
+  Close();
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/blob/db_blob_corruption_test.cc

@@ -12,7 +12,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBBlobCorruptionTest : public DBTestBase {
  protected:
   DBBlobCorruptionTest()
-      : DBTestBase("/db_blob_corruption_test", /* env_do_fsync */ false) {}
+      : DBTestBase("db_blob_corruption_test", /* env_do_fsync */ false) {}
 
   void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
     // Pick file to corrupt

db/blob/db_blob_index_test.cc

@@ -41,8 +41,7 @@ class DBBlobIndexTest : public DBTestBase {
                                        Tier::kImmutableMemtables,
                                        Tier::kL0SstFile, Tier::kLnSstFile};
 
-  DBBlobIndexTest()
-      : DBTestBase("/db_blob_index_test", /*env_do_fsync=*/true) {}
+  DBBlobIndexTest() : DBTestBase("db_blob_index_test", /*env_do_fsync=*/true) {}
 
   ColumnFamilyHandle* cfh() { return dbfull()->DefaultColumnFamily(); }
 
@@ -399,7 +398,7 @@ TEST_F(DBBlobIndexTest, Iterate) {
            create_normal_iterator);
     verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
            create_normal_iterator);
-    verify(11, Status::kNotSupported, "", "", create_normal_iterator);
+    verify(11, Status::kCorruption, "", "", create_normal_iterator);
     verify(13, Status::kOk,
            get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
            get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
@@ -418,7 +417,11 @@ TEST_F(DBBlobIndexTest, Iterate) {
            create_blob_iterator, check_is_blob(false));
     verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
            create_blob_iterator, check_is_blob(false));
-    verify(11, Status::kNotSupported, "", "", create_blob_iterator);
+    if (tier <= kImmutableMemtables) {
+      verify(11, Status::kNotSupported, "", "", create_blob_iterator);
+    } else {
+      verify(11, Status::kCorruption, "", "", create_blob_iterator);
+    }
     verify(13, Status::kOk,
            get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
            get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
@@ -440,7 +443,11 @@ TEST_F(DBBlobIndexTest, Iterate) {
            create_blob_iterator, check_is_blob(false));
     verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
            create_blob_iterator, check_is_blob(false));
-    verify(11, Status::kNotSupported, "", "", create_blob_iterator);
+    if (tier <= kImmutableMemtables) {
+      verify(11, Status::kNotSupported, "", "", create_blob_iterator);
+    } else {
+      verify(11, Status::kCorruption, "", "", create_blob_iterator);
+    }
     verify(13, Status::kOk,
            get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
            get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
@@ -455,6 +462,106 @@ TEST_F(DBBlobIndexTest, Iterate) {
   }
 }
 
+TEST_F(DBBlobIndexTest, IntegratedBlobIterate) {
+  const std::vector<std::vector<std::string>> data = {
+      /*00*/ {"Put"},
+      /*01*/ {"Put", "Merge", "Merge", "Merge"},
+      /*02*/ {"Put"}};
+
+  auto get_key = [](size_t index) { return ("key" + std::to_string(index)); };
+
+  auto get_value = [&](size_t index, size_t version) {
+    return get_key(index) + "_value" + ToString(version);
+  };
+
+  auto check_iterator = [&](Iterator* iterator, Status expected_status,
+                            const Slice& expected_value) {
+    ASSERT_EQ(expected_status, iterator->status());
+    if (expected_status.ok()) {
+      ASSERT_TRUE(iterator->Valid());
+      ASSERT_EQ(expected_value, iterator->value());
+    } else {
+      ASSERT_FALSE(iterator->Valid());
+    }
+  };
+
+  auto verify = [&](size_t index, Status expected_status,
+                    const Slice& expected_value) {
+    // Seek
+    {
+      Iterator* iterator = db_->NewIterator(ReadOptions());
+      std::unique_ptr<Iterator> iterator_guard(iterator);
+      ASSERT_OK(iterator->status());
+      ASSERT_OK(iterator->Refresh());
+      iterator->Seek(get_key(index));
+      check_iterator(iterator, expected_status, expected_value);
+    }
+    // Next
+    {
+      Iterator* iterator = db_->NewIterator(ReadOptions());
+      std::unique_ptr<Iterator> iterator_guard(iterator);
+      ASSERT_OK(iterator->Refresh());
+      iterator->Seek(get_key(index - 1));
+      ASSERT_TRUE(iterator->Valid());
+      ASSERT_OK(iterator->status());
+      iterator->Next();
+      check_iterator(iterator, expected_status, expected_value);
+    }
+    // SeekForPrev
+    {
+      Iterator* iterator = db_->NewIterator(ReadOptions());
+      std::unique_ptr<Iterator> iterator_guard(iterator);
+      ASSERT_OK(iterator->status());
+      ASSERT_OK(iterator->Refresh());
+      iterator->SeekForPrev(get_key(index));
+      check_iterator(iterator, expected_status, expected_value);
+    }
+    // Prev
+    {
+      Iterator* iterator = db_->NewIterator(ReadOptions());
+      std::unique_ptr<Iterator> iterator_guard(iterator);
+      iterator->Seek(get_key(index + 1));
+      ASSERT_TRUE(iterator->Valid());
+      ASSERT_OK(iterator->status());
+      iterator->Prev();
+      check_iterator(iterator, expected_status, expected_value);
+    }
+  };
+
+  Options options = GetTestOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+
+  DestroyAndReopen(options);
+
+  // fill data
+  for (size_t i = 0; i < data.size(); i++) {
+    for (size_t j = 0; j < data[i].size(); j++) {
+      std::string key = get_key(i);
+      std::string value = get_value(i, j);
+      if (data[i][j] == "Put") {
+        ASSERT_OK(Put(key, value));
+        ASSERT_OK(Flush());
+      } else if (data[i][j] == "Merge") {
+        ASSERT_OK(Merge(key, value));
+        ASSERT_OK(Flush());
+      }
+    }
+  }
+
+  std::string expected_value = get_value(1, 0) + "," + get_value(1, 1) + "," +
+                               get_value(1, 2) + "," + get_value(1, 3);
+  Status expected_status;
+  verify(1, expected_status, expected_value);
+
+#ifndef ROCKSDB_LITE
+  // Test DBIter::FindValueForCurrentKeyUsingSeek flow.
+  ASSERT_OK(dbfull()->SetOptions(cfh(),
+                                 {{"max_sequential_skip_in_iterations", "0"}}));
+  verify(1, expected_status, expected_value);
+#endif  // !ROCKSDB_LITE
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/builder.cc

@@ -69,7 +69,8 @@ Status BuildTable(
     int job_id, const Env::IOPriority io_priority,
     TableProperties* table_properties, Env::WriteLifeTimeHint write_hint,
     const std::string* full_history_ts_low,
-    BlobFileCompletionCallback* blob_callback, uint64_t* num_input_entries) {
+    BlobFileCompletionCallback* blob_callback, uint64_t* num_input_entries,
+    uint64_t* memtable_payload_bytes, uint64_t* memtable_garbage_bytes) {
   assert((tboptions.column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          tboptions.column_family_name.empty());
@@ -89,9 +90,12 @@ Status BuildTable(
       new CompactionRangeDelAggregator(&tboptions.internal_comparator,
                                        snapshots));
   uint64_t num_unfragmented_tombstones = 0;
+  uint64_t total_tombstone_payload_bytes = 0;
   for (auto& range_del_iter : range_del_iters) {
     num_unfragmented_tombstones +=
         range_del_iter->num_unfragmented_tombstones();
+    total_tombstone_payload_bytes +=
+        range_del_iter->total_tombstone_payload_bytes();
     range_del_agg->AddTombstones(std::move(range_del_iter));
   }
 
@@ -161,7 +165,7 @@ Status BuildTable(
           std::move(file), fname, file_options, ioptions.clock, io_tracer,
           ioptions.stats, ioptions.listeners,
           ioptions.file_checksum_gen_factory.get(),
-          tmp_set.Contains(FileType::kTableFile)));
+          tmp_set.Contains(FileType::kTableFile), false));
 
       builder = NewTableBuilder(tboptions, file_writer.get());
     }
@@ -191,7 +195,8 @@ Status BuildTable(
         /*compaction=*/nullptr, compaction_filter.get(),
         /*shutting_down=*/nullptr,
         /*preserve_deletes_seqnum=*/0, /*manual_compaction_paused=*/nullptr,
-        db_options.info_log, full_history_ts_low);
+        /*manual_compaction_canceled=*/nullptr, db_options.info_log,
+        full_history_ts_low);
 
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
@@ -199,6 +204,8 @@ Status BuildTable(
       const Slice& value = c_iter.value();
       const ParsedInternalKey& ikey = c_iter.ikey();
       // Generate a rolling 64-bit hash of the key and values
+      // Note :
+      // Here "key" integrates 'sequence_number'+'kType'+'user key'.
       s = output_validator.Add(key, value);
       if (!s.ok()) {
         break;
@@ -253,6 +260,25 @@ Status BuildTable(
       meta->marked_for_compaction = builder->NeedCompact();
       assert(meta->fd.GetFileSize() > 0);
       tp = builder->GetTableProperties(); // refresh now that builder is finished
+      if (memtable_payload_bytes != nullptr &&
+          memtable_garbage_bytes != nullptr) {
+        const CompactionIterationStats& ci_stats = c_iter.iter_stats();
+        uint64_t total_payload_bytes = ci_stats.total_input_raw_key_bytes +
+                                       ci_stats.total_input_raw_value_bytes +
+                                       total_tombstone_payload_bytes;
+        uint64_t total_payload_bytes_written =
+            (tp.raw_key_size + tp.raw_value_size);
+        // Prevent underflow, which may still happen at this point
+        // since we only support inserts, deletes, and deleteRanges.
+        if (total_payload_bytes_written <= total_payload_bytes) {
+          *memtable_payload_bytes = total_payload_bytes;
+          *memtable_garbage_bytes =
+              total_payload_bytes - total_payload_bytes_written;
+        } else {
+          *memtable_payload_bytes = 0;
+          *memtable_garbage_bytes = 0;
+        }
+      }
       if (table_properties) {
         *table_properties = tp;
       }

db/builder.h

@@ -66,6 +66,8 @@ extern Status BuildTable(
     Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
     const std::string* full_history_ts_low = nullptr,
     BlobFileCompletionCallback* blob_callback = nullptr,
-    uint64_t* num_input_entries = nullptr);
+    uint64_t* num_input_entries = nullptr,
+    uint64_t* memtable_payload_bytes = nullptr,
+    uint64_t* memtable_garbage_bytes = nullptr);
 
 }  // namespace ROCKSDB_NAMESPACE

db/c.cc

@@ -88,6 +88,7 @@ using ROCKSDB_NAMESPACE::NewBloomFilterPolicy;
 using ROCKSDB_NAMESPACE::NewCompactOnDeletionCollectorFactory;
 using ROCKSDB_NAMESPACE::NewGenericRateLimiter;
 using ROCKSDB_NAMESPACE::NewLRUCache;
+using ROCKSDB_NAMESPACE::NewRibbonFilterPolicy;
 using ROCKSDB_NAMESPACE::OptimisticTransactionDB;
 using ROCKSDB_NAMESPACE::OptimisticTransactionOptions;
 using ROCKSDB_NAMESPACE::Options;
@@ -3028,6 +3029,11 @@ unsigned char rocksdb_options_get_advise_random_on_open(
   return opt->rep.advise_random_on_open;
 }
 
+void rocksdb_options_set_experimental_mempurge_threshold(rocksdb_options_t* opt,
+                                                         double v) {
+  opt->rep.experimental_mempurge_threshold = v;
+}
+
 void rocksdb_options_set_access_hint_on_compaction_start(
     rocksdb_options_t* opt, int v) {
   switch(v) {
@@ -3834,7 +3840,8 @@ void rocksdb_filterpolicy_destroy(rocksdb_filterpolicy_t* filter) {
   delete filter;
 }
 
-rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_key, bool original_format) {
+rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(
+    double bits_per_key, bool original_format) {
   // Make a rocksdb_filterpolicy_t, but override all of its methods so
   // they delegate to a NewBloomFilterPolicy() instead of user
   // supplied C functions.
@@ -3869,14 +3876,63 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
   return wrapper;
 }
 
-rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_full(int bits_per_key) {
+rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_full(
+    double bits_per_key) {
   return rocksdb_filterpolicy_create_bloom_format(bits_per_key, false);
 }
 
-rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom(int bits_per_key) {
+rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom(double bits_per_key) {
   return rocksdb_filterpolicy_create_bloom_format(bits_per_key, true);
 }
 
+rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_ribbon_format(
+    double bloom_equivalent_bits_per_key, int bloom_before_level) {
+  // Make a rocksdb_filterpolicy_t, but override all of its methods so
+  // they delegate to a NewRibbonFilterPolicy() instead of user
+  // supplied C functions.
+  struct Wrapper : public rocksdb_filterpolicy_t {
+    const FilterPolicy* rep_;
+    ~Wrapper() override { delete rep_; }
+    const char* Name() const override { return rep_->Name(); }
+    void CreateFilter(const Slice* keys, int n,
+                      std::string* dst) const override {
+      return rep_->CreateFilter(keys, n, dst);
+    }
+    bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
+      return rep_->KeyMayMatch(key, filter);
+    }
+    ROCKSDB_NAMESPACE::FilterBitsBuilder* GetBuilderWithContext(
+        const ROCKSDB_NAMESPACE::FilterBuildingContext& context)
+        const override {
+      return rep_->GetBuilderWithContext(context);
+    }
+    ROCKSDB_NAMESPACE::FilterBitsReader* GetFilterBitsReader(
+        const Slice& contents) const override {
+      return rep_->GetFilterBitsReader(contents);
+    }
+    static void DoNothing(void*) {}
+  };
+  Wrapper* wrapper = new Wrapper;
+  wrapper->rep_ =
+      NewRibbonFilterPolicy(bloom_equivalent_bits_per_key, bloom_before_level);
+  wrapper->state_ = nullptr;
+  wrapper->delete_filter_ = nullptr;
+  wrapper->destructor_ = &Wrapper::DoNothing;
+  return wrapper;
+}
+
+rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_ribbon(
+    double bloom_equivalent_bits_per_key) {
+  return rocksdb_filterpolicy_create_ribbon_format(
+      bloom_equivalent_bits_per_key, /*bloom_before_level = disabled*/ -1);
+}
+
+rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_ribbon_hybrid(
+    double bloom_equivalent_bits_per_key, int bloom_before_level) {
+  return rocksdb_filterpolicy_create_ribbon_format(
+      bloom_equivalent_bits_per_key, bloom_before_level);
+}
+
 rocksdb_mergeoperator_t* rocksdb_mergeoperator_create(
     void* state, void (*destructor)(void*),
     char* (*full_merge)(void*, const char* key, size_t key_length,
@@ -4828,6 +4884,27 @@ void rocksdb_optimistictransaction_options_set_set_snapshot(
   opt->rep.set_snapshot = v;
 }
 
+char* rocksdb_optimistictransactiondb_property_value(
+    rocksdb_optimistictransactiondb_t* db, const char* propname) {
+  std::string tmp;
+  if (db->rep->GetProperty(Slice(propname), &tmp)) {
+    // We use strdup() since we expect human readable output.
+    return strdup(tmp.c_str());
+  } else {
+    return nullptr;
+  }
+}
+
+int rocksdb_optimistictransactiondb_property_int(
+    rocksdb_optimistictransactiondb_t* db, const char* propname,
+    uint64_t* out_val) {
+  if (db->rep->GetIntProperty(Slice(propname), out_val)) {
+    return 0;
+  } else {
+    return -1;
+  }
+}
+
 rocksdb_column_family_handle_t* rocksdb_transactiondb_create_column_family(
     rocksdb_transactiondb_t* txn_db,
     const rocksdb_options_t* column_family_options,
@@ -4898,6 +4975,27 @@ void rocksdb_transactiondb_release_snapshot(
   delete snapshot;
 }
 
+char* rocksdb_transactiondb_property_value(rocksdb_transactiondb_t* db,
+                                           const char* propname) {
+  std::string tmp;
+  if (db->rep->GetProperty(Slice(propname), &tmp)) {
+    // We use strdup() since we expect human readable output.
+    return strdup(tmp.c_str());
+  } else {
+    return nullptr;
+  }
+}
+
+int rocksdb_transactiondb_property_int(rocksdb_transactiondb_t* db,
+                                       const char* propname,
+                                       uint64_t* out_val) {
+  if (db->rep->GetIntProperty(Slice(propname), out_val)) {
+    return 0;
+  } else {
+    return -1;
+  }
+}
+
 rocksdb_transaction_t* rocksdb_transaction_begin(
     rocksdb_transactiondb_t* txn_db,
     const rocksdb_writeoptions_t* write_options,
@@ -5300,12 +5398,31 @@ rocksdb_transaction_t* rocksdb_optimistictransaction_begin(
   return old_txn;
 }
 
+// Write batch into OptimisticTransactionDB
+void rocksdb_optimistictransactiondb_write(
+    rocksdb_optimistictransactiondb_t* otxn_db,
+    const rocksdb_writeoptions_t* options, rocksdb_writebatch_t* batch,
+    char** errptr) {
+  SaveError(errptr, otxn_db->rep->Write(options->rep, &batch->rep));
+}
+
 void rocksdb_optimistictransactiondb_close(
     rocksdb_optimistictransactiondb_t* otxn_db) {
   delete otxn_db->rep;
   delete otxn_db;
 }
 
+rocksdb_checkpoint_t* rocksdb_optimistictransactiondb_checkpoint_object_create(
+    rocksdb_optimistictransactiondb_t* otxn_db, char** errptr) {
+  Checkpoint* checkpoint;
+  if (SaveError(errptr, Checkpoint::Create(otxn_db->rep, &checkpoint))) {
+    return nullptr;
+  }
+  rocksdb_checkpoint_t* result = new rocksdb_checkpoint_t;
+  result->rep = checkpoint;
+  return result;
+}
+
 void rocksdb_free(void* ptr) { free(ptr); }
 
 rocksdb_pinnableslice_t* rocksdb_get_pinned(

db/c_test.c

@@ -1043,19 +1043,25 @@ int main(int argc, char** argv) {
   }
 
   StartPhase("filter");
-  for (run = 0; run <= 2; run++) {
-    // First run uses custom filter
-    // Second run uses old block-based bloom filter
-    // Third run uses full bloom filter
+  for (run = 0; run <= 4; run++) {
+    // run=0 uses custom filter
+    // run=1 uses old block-based bloom filter
+    // run=2 run uses full bloom filter
+    // run=3 uses Ribbon
+    // run=4 uses Ribbon-Bloom hybrid configuration
     CheckNoError(err);
     rocksdb_filterpolicy_t* policy;
     if (run == 0) {
       policy = rocksdb_filterpolicy_create(NULL, FilterDestroy, FilterCreate,
                                            FilterKeyMatch, NULL, FilterName);
     } else if (run == 1) {
-      policy = rocksdb_filterpolicy_create_bloom(8);
+      policy = rocksdb_filterpolicy_create_bloom(8.0);
+    } else if (run == 2) {
+      policy = rocksdb_filterpolicy_create_bloom_full(8.0);
+    } else if (run == 3) {
+      policy = rocksdb_filterpolicy_create_ribbon(8.0);
     } else {
-      policy = rocksdb_filterpolicy_create_bloom_full(8);
+      policy = rocksdb_filterpolicy_create_ribbon_hybrid(8.0, 1);
     }
     rocksdb_block_based_options_set_filter_policy(table_options, policy);
 
@@ -1121,9 +1127,12 @@ int main(int argc, char** argv) {
       } else if (run == 1) {
         // Essentially a fingerprint of the block-based Bloom schema
         CheckCondition(hits == 241);
-      } else {
+      } else if (run == 2 || run == 4) {
         // Essentially a fingerprint of full Bloom schema, format_version=5
         CheckCondition(hits == 188);
+      } else {
+        // Essentially a fingerprint of Ribbon schema
+        CheckCondition(hits == 226);
       }
       CheckCondition(
           (keys_to_query - hits) ==

db/column_family.cc

@@ -445,6 +445,9 @@ bool SuperVersion::Unref() {
 
 void SuperVersion::Cleanup() {
   assert(refs.load(std::memory_order_relaxed) == 0);
+  // Since this SuperVersion object is being deleted,
+  // decrement reference to the immutable MemtableList
+  // this SV object was pointing to.
   imm->Unref(&to_delete);
   MemTable* m = mem->Unref();
   if (m != nullptr) {
@@ -454,7 +457,7 @@ void SuperVersion::Cleanup() {
     to_delete.push_back(m);
   }
   current->Unref();
-  cfd->UnrefAndTryDelete(this);
+  cfd->UnrefAndTryDelete();
 }
 
 void SuperVersion::Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
@@ -472,10 +475,10 @@ void SuperVersion::Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
 
 namespace {
 void SuperVersionUnrefHandle(void* ptr) {
-  // UnrefHandle is called when a thread exists or a ThreadLocalPtr gets
-  // destroyed. When former happens, the thread shouldn't see kSVInUse.
-  // When latter happens, we are in ~ColumnFamilyData(), no get should happen as
-  // well.
+  // UnrefHandle is called when a thread exits or a ThreadLocalPtr gets
+  // destroyed. When the former happens, the thread shouldn't see kSVInUse.
+  // When the latter happens, only super_version_ holds a reference
+  // to ColumnFamilyData, so no further queries are possible.
   SuperVersion* sv = static_cast<SuperVersion*>(ptr);
   bool was_last_ref __attribute__((__unused__));
   was_last_ref = sv->Unref();
@@ -502,9 +505,10 @@ ColumnFamilyData::ColumnFamilyData(
     uint32_t id, const std::string& name, Version* _dummy_versions,
     Cache* _table_cache, WriteBufferManager* write_buffer_manager,
     const ColumnFamilyOptions& cf_options, const ImmutableDBOptions& db_options,
-    const FileOptions& file_options, ColumnFamilySet* column_family_set,
+    const FileOptions* file_options, ColumnFamilySet* column_family_set,
     BlockCacheTracer* const block_cache_tracer,
-    const std::shared_ptr<IOTracer>& io_tracer)
+    const std::shared_ptr<IOTracer>& io_tracer,
+    const std::string& db_session_id)
     : id_(id),
       name_(name),
       dummy_versions_(_dummy_versions),
@@ -562,7 +566,8 @@ ColumnFamilyData::ColumnFamilyData(
     internal_stats_.reset(
         new InternalStats(ioptions_.num_levels, ioptions_.clock, this));
     table_cache_.reset(new TableCache(ioptions_, file_options, _table_cache,
-                                      block_cache_tracer, io_tracer));
+                                      block_cache_tracer, io_tracer,
+                                      db_session_id));
     blob_file_cache_.reset(
         new BlobFileCache(_table_cache, ioptions(), soptions(), id_,
                           internal_stats_->GetBlobFileReadHist(), io_tracer));
@@ -663,7 +668,7 @@ ColumnFamilyData::~ColumnFamilyData() {
   }
 }
 
-bool ColumnFamilyData::UnrefAndTryDelete(SuperVersion* sv_under_cleanup) {
+bool ColumnFamilyData::UnrefAndTryDelete() {
   int old_refs = refs_.fetch_sub(1);
   assert(old_refs > 0);
 
@@ -673,22 +678,17 @@ bool ColumnFamilyData::UnrefAndTryDelete(SuperVersion* sv_under_cleanup) {
     return true;
   }
 
-  // If called under SuperVersion::Cleanup, we should not re-enter Cleanup on
-  // the same SuperVersion. (But while installing a new SuperVersion, this
-  // cfd could be referenced only by two SuperVersions.)
-  if (old_refs == 2 && super_version_ != nullptr &&
-      super_version_ != sv_under_cleanup) {
+  if (old_refs == 2 && super_version_ != nullptr) {
     // Only the super_version_ holds me
     SuperVersion* sv = super_version_;
     super_version_ = nullptr;
-    // Release SuperVersion reference kept in ThreadLocalPtr.
-    // This must be done outside of mutex_ since unref handler can lock mutex.
-    sv->db_mutex->Unlock();
+
+    // Release SuperVersion references kept in ThreadLocalPtr.
     local_sv_.reset();
-    sv->db_mutex->Lock();
 
     if (sv->Unref()) {
-      // May delete this ColumnFamilyData after calling Cleanup()
+      // Note: sv will delete this ColumnFamilyData during Cleanup()
+      assert(sv->cfd == this);
       sv->Cleanup();
       delete sv;
       return true;
@@ -1253,14 +1253,13 @@ bool ColumnFamilyData::ReturnThreadLocalSuperVersion(SuperVersion* sv) {
 void ColumnFamilyData::InstallSuperVersion(
     SuperVersionContext* sv_context, InstrumentedMutex* db_mutex) {
   db_mutex->AssertHeld();
-  return InstallSuperVersion(sv_context, db_mutex, mutable_cf_options_);
+  return InstallSuperVersion(sv_context, mutable_cf_options_);
 }
 
 void ColumnFamilyData::InstallSuperVersion(
-    SuperVersionContext* sv_context, InstrumentedMutex* db_mutex,
+    SuperVersionContext* sv_context,
     const MutableCFOptions& mutable_cf_options) {
   SuperVersion* new_superversion = sv_context->new_superversion.release();
-  new_superversion->db_mutex = db_mutex;
   new_superversion->mutable_cf_options = mutable_cf_options;
   new_superversion->Init(this, mem_, imm_.current(), current_);
   SuperVersion* old_superversion = super_version_;
@@ -1451,21 +1450,23 @@ ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                  WriteBufferManager* _write_buffer_manager,
                                  WriteController* _write_controller,
                                  BlockCacheTracer* const block_cache_tracer,
-                                 const std::shared_ptr<IOTracer>& io_tracer)
+                                 const std::shared_ptr<IOTracer>& io_tracer,
+                                 const std::string& db_session_id)
     : max_column_family_(0),
+      file_options_(file_options),
       dummy_cfd_(new ColumnFamilyData(
           ColumnFamilyData::kDummyColumnFamilyDataId, "", nullptr, nullptr,
-          nullptr, ColumnFamilyOptions(), *db_options, file_options, nullptr,
-          block_cache_tracer, io_tracer)),
+          nullptr, ColumnFamilyOptions(), *db_options, &file_options_, nullptr,
+          block_cache_tracer, io_tracer, db_session_id)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
-      file_options_(file_options),
       table_cache_(table_cache),
       write_buffer_manager_(_write_buffer_manager),
       write_controller_(_write_controller),
       block_cache_tracer_(block_cache_tracer),
-      io_tracer_(io_tracer) {
+      io_tracer_(io_tracer),
+      db_session_id_(db_session_id) {
   // initialize linked list
   dummy_cfd_->prev_ = dummy_cfd_;
   dummy_cfd_->next_ = dummy_cfd_;
@@ -1531,7 +1532,8 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
   assert(column_families_.find(name) == column_families_.end());
   ColumnFamilyData* new_cfd = new ColumnFamilyData(
       id, name, dummy_versions, table_cache_, write_buffer_manager_, options,
-      *db_options_, file_options_, this, block_cache_tracer_, io_tracer_);
+      *db_options_, &file_options_, this, block_cache_tracer_, io_tracer_,
+      db_session_id_);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   max_column_family_ = std::max(max_column_family_, id);

db/column_family.h

@@ -208,8 +208,6 @@ struct SuperVersion {
   uint64_t version_number;
   WriteStallCondition write_stall_condition;
 
-  InstrumentedMutex* db_mutex;
-
   // should be called outside the mutex
   SuperVersion() = default;
   ~SuperVersion();
@@ -281,8 +279,7 @@ class ColumnFamilyData {
   // UnrefAndTryDelete() decreases the reference count and do free if needed,
   // return true if this is freed else false, UnrefAndTryDelete() can only
   // be called while holding a DB mutex, or during single-threaded recovery.
-  // sv_under_cleanup is only provided when called from SuperVersion::Cleanup.
-  bool UnrefAndTryDelete(SuperVersion* sv_under_cleanup = nullptr);
+  bool UnrefAndTryDelete();
 
   // SetDropped() can only be called under following conditions:
   // 1) Holding a DB mutex,
@@ -453,7 +450,6 @@ class ColumnFamilyData {
   // the clients to allocate SuperVersion outside of mutex.
   // IMPORTANT: Only call this from DBImpl::InstallSuperVersion()
   void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex,
                            const MutableCFOptions& mutable_cf_options);
   void InstallSuperVersion(SuperVersionContext* sv_context,
                            InstrumentedMutex* db_mutex);
@@ -520,6 +516,7 @@ class ColumnFamilyData {
   }
 
   ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
+  WriteBufferManager* write_buffer_mgr() { return write_buffer_manager_; }
 
  private:
   friend class ColumnFamilySet;
@@ -529,10 +526,11 @@ class ColumnFamilyData {
                    WriteBufferManager* write_buffer_manager,
                    const ColumnFamilyOptions& options,
                    const ImmutableDBOptions& db_options,
-                   const FileOptions& file_options,
+                   const FileOptions* file_options,
                    ColumnFamilySet* column_family_set,
                    BlockCacheTracer* const block_cache_tracer,
-                   const std::shared_ptr<IOTracer>& io_tracer);
+                   const std::shared_ptr<IOTracer>& io_tracer,
+                   const std::string& db_session_id);
 
   std::vector<std::string> GetDbPaths() const;
 
@@ -668,7 +666,8 @@ class ColumnFamilySet {
                   WriteBufferManager* _write_buffer_manager,
                   WriteController* _write_controller,
                   BlockCacheTracer* const block_cache_tracer,
-                  const std::shared_ptr<IOTracer>& io_tracer);
+                  const std::shared_ptr<IOTracer>& io_tracer,
+                  const std::string& db_session_id);
   ~ColumnFamilySet();
 
   ColumnFamilyData* GetDefault() const;
@@ -718,6 +717,8 @@ class ColumnFamilySet {
   std::unordered_map<uint32_t, ColumnFamilyData*> column_family_data_;
 
   uint32_t max_column_family_;
+  const FileOptions file_options_;
+
   ColumnFamilyData* dummy_cfd_;
   // We don't hold the refcount here, since default column family always exists
   // We are also not responsible for cleaning up default_cfd_cache_. This is
@@ -727,12 +728,12 @@ class ColumnFamilySet {
 
   const std::string db_name_;
   const ImmutableDBOptions* const db_options_;
-  const FileOptions file_options_;
   Cache* table_cache_;
   WriteBufferManager* write_buffer_manager_;
   WriteController* write_controller_;
   BlockCacheTracer* const block_cache_tracer_;
   std::shared_ptr<IOTracer> io_tracer_;
+  std::string db_session_id_;
 };
 
 // We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access

db/column_family_test.cc

@@ -56,16 +56,8 @@ 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) {
-      Env* test_env = nullptr;
-      Status s = Env::LoadEnv(test_env_uri, &test_env, &env_guard_);
-      base_env = test_env;
-      EXPECT_OK(s);
-      EXPECT_NE(Env::Default(), base_env);
-    }
-#endif  // !ROCKSDB_LITE
+    EXPECT_OK(
+        test::CreateEnvFromSystem(ConfigOptions(), &base_env, &env_guard_));
     EXPECT_NE(nullptr, base_env);
     env_ = new EnvCounter(base_env);
     env_->skip_fsync_ = true;

db/compaction/clipping_iterator.h

@@ -0,0 +1,275 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <cassert>
+
+#include "table/internal_iterator.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+// An internal iterator that wraps another one and ensures that any keys
+// returned are strictly within a range [start, end). If the underlying
+// iterator has already performed the bounds checking, it relies on that result;
+// otherwise, it performs the necessary key comparisons itself. Both bounds
+// are optional.
+class ClippingIterator : public InternalIterator {
+ public:
+  ClippingIterator(InternalIterator* iter, const Slice* start, const Slice* end,
+                   const Comparator* cmp)
+      : iter_(iter), start_(start), end_(end), cmp_(cmp), valid_(false) {
+    assert(iter_);
+    assert(cmp_);
+    assert(!start_ || !end_ || cmp_->Compare(*start_, *end_) <= 0);
+
+    UpdateAndEnforceBounds();
+  }
+
+  bool Valid() const override { return valid_; }
+
+  void SeekToFirst() override {
+    if (start_) {
+      iter_->Seek(*start_);
+    } else {
+      iter_->SeekToFirst();
+    }
+
+    UpdateAndEnforceUpperBound();
+  }
+
+  void SeekToLast() override {
+    if (end_) {
+      iter_->SeekForPrev(*end_);
+
+      // Upper bound is exclusive, so we need a key which is strictly smaller
+      if (iter_->Valid() && cmp_->Compare(iter_->key(), *end_) == 0) {
+        iter_->Prev();
+      }
+    } else {
+      iter_->SeekToLast();
+    }
+
+    UpdateAndEnforceLowerBound();
+  }
+
+  void Seek(const Slice& target) override {
+    if (start_ && cmp_->Compare(target, *start_) < 0) {
+      iter_->Seek(*start_);
+      UpdateAndEnforceUpperBound();
+      return;
+    }
+
+    if (end_ && cmp_->Compare(target, *end_) >= 0) {
+      valid_ = false;
+      return;
+    }
+
+    iter_->Seek(target);
+    UpdateAndEnforceUpperBound();
+  }
+
+  void SeekForPrev(const Slice& target) override {
+    if (start_ && cmp_->Compare(target, *start_) < 0) {
+      valid_ = false;
+      return;
+    }
+
+    if (end_ && cmp_->Compare(target, *end_) >= 0) {
+      iter_->SeekForPrev(*end_);
+
+      // Upper bound is exclusive, so we need a key which is strictly smaller
+      if (iter_->Valid() && cmp_->Compare(iter_->key(), *end_) == 0) {
+        iter_->Prev();
+      }
+
+      UpdateAndEnforceLowerBound();
+      return;
+    }
+
+    iter_->SeekForPrev(target);
+    UpdateAndEnforceLowerBound();
+  }
+
+  void Next() override {
+    assert(valid_);
+    iter_->Next();
+    UpdateAndEnforceUpperBound();
+  }
+
+  bool NextAndGetResult(IterateResult* result) override {
+    assert(valid_);
+    assert(result);
+
+    IterateResult res;
+    valid_ = iter_->NextAndGetResult(&res);
+
+    if (!valid_) {
+      return false;
+    }
+
+    if (end_) {
+      EnforceUpperBoundImpl(res.bound_check_result);
+
+      if (!valid_) {
+        return false;
+      }
+    }
+
+    res.bound_check_result = IterBoundCheck::kInbound;
+    *result = res;
+
+    return true;
+  }
+
+  void Prev() override {
+    assert(valid_);
+    iter_->Prev();
+    UpdateAndEnforceLowerBound();
+  }
+
+  Slice key() const override {
+    assert(valid_);
+    return iter_->key();
+  }
+
+  Slice user_key() const override {
+    assert(valid_);
+    return iter_->user_key();
+  }
+
+  Slice value() const override {
+    assert(valid_);
+    return iter_->value();
+  }
+
+  Status status() const override { return iter_->status(); }
+
+  bool PrepareValue() override {
+    assert(valid_);
+
+    if (iter_->PrepareValue()) {
+      return true;
+    }
+
+    assert(!iter_->Valid());
+    valid_ = false;
+    return false;
+  }
+
+  bool MayBeOutOfLowerBound() override {
+    assert(valid_);
+    return false;
+  }
+
+  IterBoundCheck UpperBoundCheckResult() override {
+    assert(valid_);
+    return IterBoundCheck::kInbound;
+  }
+
+  void SetPinnedItersMgr(PinnedIteratorsManager* pinned_iters_mgr) override {
+    iter_->SetPinnedItersMgr(pinned_iters_mgr);
+  }
+
+  bool IsKeyPinned() const override {
+    assert(valid_);
+    return iter_->IsKeyPinned();
+  }
+
+  bool IsValuePinned() const override {
+    assert(valid_);
+    return iter_->IsValuePinned();
+  }
+
+  Status GetProperty(std::string prop_name, std::string* prop) override {
+    return iter_->GetProperty(prop_name, prop);
+  }
+
+ private:
+  void UpdateValid() {
+    assert(!iter_->Valid() || iter_->status().ok());
+
+    valid_ = iter_->Valid();
+  }
+
+  void EnforceUpperBoundImpl(IterBoundCheck bound_check_result) {
+    if (bound_check_result == IterBoundCheck::kInbound) {
+      return;
+    }
+
+    if (bound_check_result == IterBoundCheck::kOutOfBound) {
+      valid_ = false;
+      return;
+    }
+
+    assert(bound_check_result == IterBoundCheck::kUnknown);
+
+    if (cmp_->Compare(key(), *end_) >= 0) {
+      valid_ = false;
+    }
+  }
+
+  void EnforceUpperBound() {
+    if (!valid_) {
+      return;
+    }
+
+    if (!end_) {
+      return;
+    }
+
+    EnforceUpperBoundImpl(iter_->UpperBoundCheckResult());
+  }
+
+  void EnforceLowerBound() {
+    if (!valid_) {
+      return;
+    }
+
+    if (!start_) {
+      return;
+    }
+
+    if (!iter_->MayBeOutOfLowerBound()) {
+      return;
+    }
+
+    if (cmp_->Compare(key(), *start_) < 0) {
+      valid_ = false;
+    }
+  }
+
+  void AssertBounds() {
+    assert(!valid_ || !start_ || cmp_->Compare(key(), *start_) >= 0);
+    assert(!valid_ || !end_ || cmp_->Compare(key(), *end_) < 0);
+  }
+
+  void UpdateAndEnforceBounds() {
+    UpdateValid();
+    EnforceUpperBound();
+    EnforceLowerBound();
+    AssertBounds();
+  }
+
+  void UpdateAndEnforceUpperBound() {
+    UpdateValid();
+    EnforceUpperBound();
+    AssertBounds();
+  }
+
+  void UpdateAndEnforceLowerBound() {
+    UpdateValid();
+    EnforceLowerBound();
+    AssertBounds();
+  }
+
+  InternalIterator* iter_;
+  const Slice* start_;
+  const Slice* end_;
+  const Comparator* cmp_;
+  bool valid_;
+};
+
+}  // namespace ROCKSDB_NAMESPACE

db/compaction/clipping_iterator_test.cc

@@ -0,0 +1,256 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/compaction/clipping_iterator.h"
+
+#include <algorithm>
+#include <memory>
+#include <string>
+#include <vector>
+
+#include "rocksdb/comparator.h"
+#include "test_util/testharness.h"
+#include "test_util/testutil.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+// A vector iterator which does its own bounds checking. This is for testing the
+// optimizations in the clipping iterator where we bypass the bounds checking if
+// the input iterator has already performed it.
+class BoundsCheckingVectorIterator : public test::VectorIterator {
+ public:
+  BoundsCheckingVectorIterator(const std::vector<std::string>& keys,
+                               const std::vector<std::string>& values,
+                               const Slice* start, const Slice* end,
+                               const Comparator* cmp)
+      : VectorIterator(keys, values), start_(start), end_(end), cmp_(cmp) {
+    assert(cmp_);
+  }
+
+  bool NextAndGetResult(IterateResult* result) override {
+    assert(Valid());
+    assert(result);
+
+    Next();
+
+    if (!Valid()) {
+      return false;
+    }
+
+    result->key = key();
+    result->bound_check_result = UpperBoundCheckResult();
+    result->value_prepared = true;
+
+    return true;
+  }
+
+  bool MayBeOutOfLowerBound() override {
+    assert(Valid());
+
+    if (!start_) {
+      return false;
+    }
+
+    return cmp_->Compare(key(), *start_) < 0;
+  }
+
+  IterBoundCheck UpperBoundCheckResult() override {
+    assert(Valid());
+
+    if (!end_) {
+      return IterBoundCheck::kInbound;
+    }
+
+    return cmp_->Compare(key(), *end_) >= 0 ? IterBoundCheck::kOutOfBound
+                                            : IterBoundCheck::kInbound;
+  }
+
+ private:
+  const Slice* start_;
+  const Slice* end_;
+  const Comparator* cmp_;
+};
+
+class ClippingIteratorTest
+    : public ::testing::Test,
+      public ::testing::WithParamInterface<std::tuple<bool, size_t, size_t>> {};
+
+TEST_P(ClippingIteratorTest, Clip) {
+  const std::vector<std::string> keys{"key0", "key1", "key2", "key3", "key4",
+                                      "key5", "key6", "key7", "key8", "key9"};
+  const std::vector<std::string> values{
+      "unused0", "value1",  "value2",  "value3",  "unused4",
+      "unused5", "unused6", "unused7", "unused8", "unused9"};
+
+  assert(keys.size() == values.size());
+
+  // Note: the input always contains key1, key2, and key3; however, the clipping
+  // window is based on the test parameters: its left edge is a value in the
+  // range [0, 4], and its size is a value in the range [0, 5]
+  const std::vector<std::string> input_keys{keys[1], keys[2], keys[3]};
+  const std::vector<std::string> input_values{values[1], values[2], values[3]};
+
+  const bool use_bounds_checking_vec_it = std::get<0>(GetParam());
+
+  const size_t clip_start_idx = std::get<1>(GetParam());
+  const size_t clip_window_size = std::get<2>(GetParam());
+  const size_t clip_end_idx = clip_start_idx + clip_window_size;
+
+  const Slice start(keys[clip_start_idx]);
+  const Slice end(keys[clip_end_idx]);
+
+  std::unique_ptr<InternalIterator> input(
+      use_bounds_checking_vec_it
+          ? new BoundsCheckingVectorIterator(input_keys, input_values, &start,
+                                             &end, BytewiseComparator())
+          : new test::VectorIterator(input_keys, input_values));
+
+  ClippingIterator clip(input.get(), &start, &end, BytewiseComparator());
+
+  // The range the clipping iterator should return values from. This is
+  // essentially the intersection of the input range [1, 4) and the clipping
+  // window [clip_start_idx, clip_end_idx)
+  const size_t data_start_idx =
+      std::max(clip_start_idx, static_cast<size_t>(1));
+  const size_t data_end_idx = std::min(clip_end_idx, static_cast<size_t>(4));
+
+  // Range is empty; all Seeks should fail
+  if (data_start_idx >= data_end_idx) {
+    clip.SeekToFirst();
+    ASSERT_FALSE(clip.Valid());
+
+    clip.SeekToLast();
+    ASSERT_FALSE(clip.Valid());
+
+    for (size_t i = 0; i < keys.size(); ++i) {
+      clip.Seek(keys[i]);
+      ASSERT_FALSE(clip.Valid());
+
+      clip.SeekForPrev(keys[i]);
+      ASSERT_FALSE(clip.Valid());
+    }
+
+    return;
+  }
+
+  // Range is non-empty; call SeekToFirst and iterate forward
+  clip.SeekToFirst();
+  ASSERT_TRUE(clip.Valid());
+  ASSERT_EQ(clip.key(), keys[data_start_idx]);
+  ASSERT_EQ(clip.value(), values[data_start_idx]);
+  ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+  ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+
+  for (size_t i = data_start_idx + 1; i < data_end_idx; ++i) {
+    clip.Next();
+    ASSERT_TRUE(clip.Valid());
+    ASSERT_EQ(clip.key(), keys[i]);
+    ASSERT_EQ(clip.value(), values[i]);
+    ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+    ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+  }
+
+  clip.Next();
+  ASSERT_FALSE(clip.Valid());
+
+  // Do it again using NextAndGetResult
+  clip.SeekToFirst();
+  ASSERT_TRUE(clip.Valid());
+  ASSERT_EQ(clip.key(), keys[data_start_idx]);
+  ASSERT_EQ(clip.value(), values[data_start_idx]);
+  ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+  ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+
+  for (size_t i = data_start_idx + 1; i < data_end_idx; ++i) {
+    IterateResult result;
+    ASSERT_TRUE(clip.NextAndGetResult(&result));
+    ASSERT_EQ(result.key, keys[i]);
+    ASSERT_EQ(result.bound_check_result, IterBoundCheck::kInbound);
+    ASSERT_TRUE(clip.Valid());
+    ASSERT_EQ(clip.key(), keys[i]);
+    ASSERT_EQ(clip.value(), values[i]);
+    ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+    ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+  }
+
+  IterateResult result;
+  ASSERT_FALSE(clip.NextAndGetResult(&result));
+  ASSERT_FALSE(clip.Valid());
+
+  // Call SeekToLast and iterate backward
+  clip.SeekToLast();
+  ASSERT_TRUE(clip.Valid());
+  ASSERT_EQ(clip.key(), keys[data_end_idx - 1]);
+  ASSERT_EQ(clip.value(), values[data_end_idx - 1]);
+  ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+  ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+
+  for (size_t i = data_end_idx - 2; i >= data_start_idx; --i) {
+    clip.Prev();
+    ASSERT_TRUE(clip.Valid());
+    ASSERT_EQ(clip.key(), keys[i]);
+    ASSERT_EQ(clip.value(), values[i]);
+    ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+    ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+  }
+
+  clip.Prev();
+  ASSERT_FALSE(clip.Valid());
+
+  // Call Seek/SeekForPrev for all keys; Seek should return the smallest key
+  // which is >= the target; SeekForPrev should return the largest key which is
+  // <= the target
+  for (size_t i = 0; i < keys.size(); ++i) {
+    clip.Seek(keys[i]);
+
+    if (i < data_start_idx) {
+      ASSERT_TRUE(clip.Valid());
+      ASSERT_EQ(clip.key(), keys[data_start_idx]);
+      ASSERT_EQ(clip.value(), values[data_start_idx]);
+      ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+      ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+    } else if (i < data_end_idx) {
+      ASSERT_TRUE(clip.Valid());
+      ASSERT_EQ(clip.key(), keys[i]);
+      ASSERT_EQ(clip.value(), values[i]);
+      ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+      ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+    } else {
+      ASSERT_FALSE(clip.Valid());
+    }
+
+    clip.SeekForPrev(keys[i]);
+
+    if (i < data_start_idx) {
+      ASSERT_FALSE(clip.Valid());
+    } else if (i < data_end_idx) {
+      ASSERT_TRUE(clip.Valid());
+      ASSERT_EQ(clip.key(), keys[i]);
+      ASSERT_EQ(clip.value(), values[i]);
+      ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+      ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+    } else {
+      ASSERT_TRUE(clip.Valid());
+      ASSERT_EQ(clip.key(), keys[data_end_idx - 1]);
+      ASSERT_EQ(clip.value(), values[data_end_idx - 1]);
+      ASSERT_FALSE(clip.MayBeOutOfLowerBound());
+      ASSERT_EQ(clip.UpperBoundCheckResult(), IterBoundCheck::kInbound);
+    }
+  }
+}
+
+INSTANTIATE_TEST_CASE_P(
+    ClippingIteratorTest, ClippingIteratorTest,
+    ::testing::Combine(
+        ::testing::Bool(),
+        ::testing::Range(static_cast<size_t>(0), static_cast<size_t>(5)),
+        ::testing::Range(static_cast<size_t>(0), static_cast<size_t>(6))));
+
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/compaction/compaction.cc

@@ -211,9 +211,9 @@ Compaction::Compaction(
     std::vector<CompactionInputFiles> _inputs, int _output_level,
     uint64_t _target_file_size, uint64_t _max_compaction_bytes,
     uint32_t _output_path_id, CompressionType _compression,
-    CompressionOptions _compression_opts, uint32_t _max_subcompactions,
-    std::vector<FileMetaData*> _grandparents, bool _manual_compaction,
-    double _score, bool _deletion_compaction,
+    CompressionOptions _compression_opts, Temperature _output_temperature,
+    uint32_t _max_subcompactions, std::vector<FileMetaData*> _grandparents,
+    bool _manual_compaction, double _score, bool _deletion_compaction,
     CompactionReason _compaction_reason)
     : input_vstorage_(vstorage),
       start_level_(_inputs[0].level),
@@ -229,6 +229,7 @@ Compaction::Compaction(
       output_path_id_(_output_path_id),
       output_compression_(_compression),
       output_compression_opts_(_compression_opts),
+      output_temperature_(_output_temperature),
       deletion_compaction_(_deletion_compaction),
       inputs_(PopulateWithAtomicBoundaries(vstorage, std::move(_inputs))),
       grandparents_(std::move(_grandparents)),
@@ -237,7 +238,8 @@ Compaction::Compaction(
       is_full_compaction_(IsFullCompaction(vstorage, inputs_)),
       is_manual_compaction_(_manual_compaction),
       is_trivial_move_(false),
-      compaction_reason_(_compaction_reason) {
+      compaction_reason_(_compaction_reason),
+      notify_on_compaction_completion_(false) {
   MarkFilesBeingCompacted(true);
   if (is_manual_compaction_) {
     compaction_reason_ = CompactionReason::kManualCompaction;
@@ -307,6 +309,12 @@ bool Compaction::IsTrivialMove() const {
     return false;
   }
 
+  if (start_level_ == output_level_) {
+    // It doesn't make sense if compaction picker picks files just to trivial
+    // move to the same level.
+    return false;
+  }
+
   // Used in universal compaction, where trivial move can be done if the
   // input files are non overlapping
   if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
@@ -563,6 +571,14 @@ bool Compaction::ShouldFormSubcompactions() const {
   if (max_subcompactions_ <= 1 || cfd_ == nullptr) {
     return false;
   }
+
+  // Note: the subcompaction boundary picking logic does not currently guarantee
+  // that all user keys that differ only by timestamp get processed by the same
+  // subcompaction.
+  if (cfd_->user_comparator()->timestamp_size() > 0) {
+    return false;
+  }
+
   if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
     return (start_level_ == 0 || is_manual_compaction_) && output_level_ > 0 &&
            !IsOutputLevelEmpty();
@@ -573,6 +589,29 @@ bool Compaction::ShouldFormSubcompactions() const {
   }
 }
 
+bool Compaction::DoesInputReferenceBlobFiles() const {
+  assert(input_version_);
+
+  const VersionStorageInfo* storage_info = input_version_->storage_info();
+  assert(storage_info);
+
+  if (storage_info->GetBlobFiles().empty()) {
+    return false;
+  }
+
+  for (size_t i = 0; i < inputs_.size(); ++i) {
+    for (const FileMetaData* meta : inputs_[i].files) {
+      assert(meta);
+
+      if (meta->oldest_blob_file_number != kInvalidBlobFileNumber) {
+        return true;
+      }
+    }
+  }
+
+  return false;
+}
+
 uint64_t Compaction::MinInputFileOldestAncesterTime() const {
   uint64_t min_oldest_ancester_time = port::kMaxUint64;
   for (const auto& level_files : inputs_) {

db/compaction/compaction.h

@@ -76,7 +76,8 @@ class Compaction {
              std::vector<CompactionInputFiles> inputs, int output_level,
              uint64_t target_file_size, uint64_t max_compaction_bytes,
              uint32_t output_path_id, CompressionType compression,
-             CompressionOptions compression_opts, uint32_t max_subcompactions,
+             CompressionOptions compression_opts,
+             Temperature output_temperature, uint32_t max_subcompactions,
              std::vector<FileMetaData*> grandparents,
              bool manual_compaction = false, double score = -1,
              bool deletion_compaction = false,
@@ -223,9 +224,9 @@ class Compaction {
   // How many total levels are there?
   int number_levels() const { return number_levels_; }
 
-  // Return the ImmutableCFOptions that should be used throughout the compaction
+  // Return the ImmutableOptions that should be used throughout the compaction
   // procedure
-  const ImmutableOptions* immutable_cf_options() const {
+  const ImmutableOptions* immutable_options() const {
     return &immutable_options_;
   }
 
@@ -266,6 +267,11 @@ class Compaction {
   // Should this compaction be broken up into smaller ones run in parallel?
   bool ShouldFormSubcompactions() const;
 
+  // Returns true iff at least one input file references a blob file.
+  //
+  // PRE: input version has been set.
+  bool DoesInputReferenceBlobFiles() const;
+
   // test function to validate the functionality of IsBottommostLevel()
   // function -- determines if compaction with inputs and storage is bottommost
   static bool TEST_IsBottommostLevel(
@@ -294,10 +300,22 @@ class Compaction {
 
   uint64_t max_compaction_bytes() const { return max_compaction_bytes_; }
 
+  Temperature output_temperature() const { return output_temperature_; }
+
   uint32_t max_subcompactions() const { return max_subcompactions_; }
 
   uint64_t MinInputFileOldestAncesterTime() const;
 
+  // Called by DBImpl::NotifyOnCompactionCompleted to make sure number of
+  // compaction begin and compaction completion callbacks match.
+  void SetNotifyOnCompactionCompleted() {
+    notify_on_compaction_completion_ = true;
+  }
+
+  bool ShouldNotifyOnCompactionCompleted() const {
+    return notify_on_compaction_completion_;
+  }
+
  private:
   // mark (or clear) all files that are being compacted
   void MarkFilesBeingCompacted(bool mark_as_compacted);
@@ -341,6 +359,7 @@ class Compaction {
   const uint32_t output_path_id_;
   CompressionType output_compression_;
   CompressionOptions output_compression_opts_;
+  Temperature output_temperature_;
   // If true, then the compaction can be done by simply deleting input files.
   const bool deletion_compaction_;
 
@@ -381,6 +400,10 @@ class Compaction {
 
   // Reason for compaction
   CompactionReason compaction_reason_;
+
+  // Notify on compaction completion only if listener was notified on compaction
+  // begin.
+  bool notify_on_compaction_completion_;
 };
 
 // Return sum of sizes of all files in `files`.

db/compaction/compaction_iteration_stats.h

@@ -38,4 +38,6 @@ struct CompactionIterationStats {
   // Blob related statistics
   uint64_t num_blobs_read = 0;
   uint64_t total_blob_bytes_read = 0;
+  uint64_t num_blobs_relocated = 0;
+  uint64_t total_blob_bytes_relocated = 0;
 };

db/compaction/compaction_iterator.cc

@@ -16,22 +16,6 @@
 #include "table/internal_iterator.h"
 #include "test_util/sync_point.h"
 
-#define DEFINITELY_IN_SNAPSHOT(seq, snapshot)                       \
-  ((seq) <= (snapshot) &&                                           \
-   (snapshot_checker_ == nullptr ||                                 \
-    LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) == \
-           SnapshotCheckerResult::kInSnapshot)))
-
-#define DEFINITELY_NOT_IN_SNAPSHOT(seq, snapshot)                     \
-  ((seq) > (snapshot) ||                                              \
-   (snapshot_checker_ != nullptr &&                                   \
-    UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) == \
-             SnapshotCheckerResult::kNotInSnapshot)))
-
-#define IN_EARLIEST_SNAPSHOT(seq) \
-  ((seq) <= earliest_snapshot_ && \
-   (snapshot_checker_ == nullptr || LIKELY(IsInEarliestSnapshot(seq))))
-
 namespace ROCKSDB_NAMESPACE {
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -45,6 +29,7 @@ CompactionIterator::CompactionIterator(
     const std::atomic<bool>* shutting_down,
     const SequenceNumber preserve_deletes_seqnum,
     const std::atomic<int>* manual_compaction_paused,
+    const std::atomic<bool>* manual_compaction_canceled,
     const std::shared_ptr<Logger> info_log,
     const std::string* full_history_ts_low)
     : CompactionIterator(
@@ -55,7 +40,8 @@ CompactionIterator::CompactionIterator(
           std::unique_ptr<CompactionProxy>(
               compaction ? new RealCompaction(compaction) : nullptr),
           compaction_filter, shutting_down, preserve_deletes_seqnum,
-          manual_compaction_paused, info_log, full_history_ts_low) {}
+          manual_compaction_paused, manual_compaction_canceled, info_log,
+          full_history_ts_low) {}
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -70,12 +56,11 @@ CompactionIterator::CompactionIterator(
     const std::atomic<bool>* shutting_down,
     const SequenceNumber preserve_deletes_seqnum,
     const std::atomic<int>* manual_compaction_paused,
+    const std::atomic<bool>* manual_compaction_canceled,
     const std::shared_ptr<Logger> info_log,
     const std::string* full_history_ts_low)
-    : input_(
-          input, cmp,
-          compaction ==
-              nullptr),  // Now only need to count number of entries in flush.
+    : input_(input, cmp,
+             !compaction || compaction->DoesInputReferenceBlobFiles()),
       cmp_(cmp),
       merge_helper_(merge_helper),
       snapshots_(snapshots),
@@ -91,6 +76,7 @@ CompactionIterator::CompactionIterator(
       compaction_filter_(compaction_filter),
       shutting_down_(shutting_down),
       manual_compaction_paused_(manual_compaction_paused),
+      manual_compaction_canceled_(manual_compaction_canceled),
       preserve_deletes_seqnum_(preserve_deletes_seqnum),
       info_log_(info_log),
       allow_data_in_errors_(allow_data_in_errors),
@@ -509,11 +495,11 @@ void CompactionIterator::NextFromInput() {
                         "Unexpected key type %d for compaction output",
                         ikey_.type);
       }
-      assert(current_user_key_snapshot_ == last_snapshot);
-      if (current_user_key_snapshot_ != last_snapshot) {
+      assert(current_user_key_snapshot_ >= last_snapshot);
+      if (current_user_key_snapshot_ < last_snapshot) {
         ROCKS_LOG_FATAL(info_log_,
                         "current_user_key_snapshot_ (%" PRIu64
-                        ") != last_snapshot (%" PRIu64 ")",
+                        ") < last_snapshot (%" PRIu64 ")",
                         current_user_key_snapshot_, last_snapshot);
       }
 
@@ -569,10 +555,20 @@ void CompactionIterator::NextFromInput() {
           ParseInternalKey(input_.key(), &next_ikey, allow_data_in_errors_)
               .ok() &&
           cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
+#ifndef NDEBUG
+        const Compaction* c =
+            compaction_ ? compaction_->real_compaction() : nullptr;
+#endif
+        TEST_SYNC_POINT_CALLBACK(
+            "CompactionIterator::NextFromInput:SingleDelete:1",
+            const_cast<Compaction*>(c));
+
         // Check whether the next key belongs to the same snapshot as the
         // SingleDelete.
         if (prev_snapshot == 0 ||
-            DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot)) {
+            DefinitelyNotInSnapshot(next_ikey.sequence, prev_snapshot)) {
+          TEST_SYNC_POINT_CALLBACK(
+              "CompactionIterator::NextFromInput:SingleDelete:2", nullptr);
           if (next_ikey.type == kTypeSingleDeletion) {
             // We encountered two SingleDeletes in a row.  This could be due to
             // unexpected user input.
@@ -584,8 +580,8 @@ void CompactionIterator::NextFromInput() {
             ++iter_stats_.num_record_drop_obsolete;
             ++iter_stats_.num_single_del_mismatch;
           } else if (has_outputted_key_ ||
-                     DEFINITELY_IN_SNAPSHOT(
-                         ikey_.sequence, earliest_write_conflict_snapshot_)) {
+                     DefinitelyInSnapshot(ikey_.sequence,
+                                          earliest_write_conflict_snapshot_)) {
             // Found a matching value, we can drop the single delete and the
             // value.  It is safe to drop both records since we've already
             // outputted a key in this snapshot, or there is no earlier
@@ -618,6 +614,9 @@ void CompactionIterator::NextFromInput() {
             // Set up the Put to be outputted in the next iteration.
             // (Optimization 3).
             clear_and_output_next_key_ = true;
+            TEST_SYNC_POINT_CALLBACK(
+                "CompactionIterator::NextFromInput:KeepSDForWW",
+                /*arg=*/nullptr);
           }
         } else {
           // We hit the next snapshot without hitting a put, so the iterator
@@ -633,7 +632,8 @@ void CompactionIterator::NextFromInput() {
         // iteration. If the next key is corrupt, we return before the
         // comparison, so the value of has_current_user_key does not matter.
         has_current_user_key_ = false;
-        if (compaction_ != nullptr && IN_EARLIEST_SNAPSHOT(ikey_.sequence) &&
+        if (compaction_ != nullptr &&
+            DefinitelyInSnapshot(ikey_.sequence, earliest_snapshot_) &&
             compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                        &level_ptrs_)) {
           // Key doesn't exist outside of this range.
@@ -677,7 +677,7 @@ void CompactionIterator::NextFromInput() {
                (ikey_.type == kTypeDeletion ||
                 (ikey_.type == kTypeDeletionWithTimestamp &&
                  cmp_with_history_ts_low_ < 0)) &&
-               IN_EARLIEST_SNAPSHOT(ikey_.sequence) &&
+               DefinitelyInSnapshot(ikey_.sequence, earliest_snapshot_) &&
                ikeyNotNeededForIncrementalSnapshot() &&
                compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                           &level_ptrs_)) {
@@ -720,6 +720,13 @@ void CompactionIterator::NextFromInput() {
                                  ikey_.user_key, &level_ptrs_));
       ParsedInternalKey next_ikey;
       AdvanceInputIter();
+#ifndef NDEBUG
+      const Compaction* c =
+          compaction_ ? compaction_->real_compaction() : nullptr;
+#endif
+      TEST_SYNC_POINT_CALLBACK(
+          "CompactionIterator::NextFromInput:BottommostDelete:1",
+          const_cast<Compaction*>(c));
       // Skip over all versions of this key that happen to occur in the same
       // snapshot range as the delete.
       //
@@ -732,7 +739,7 @@ void CompactionIterator::NextFromInput() {
                   .ok()) &&
              cmp_->EqualWithoutTimestamp(ikey_.user_key, next_ikey.user_key) &&
              (prev_snapshot == 0 ||
-              DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot))) {
+              DefinitelyNotInSnapshot(next_ikey.sequence, prev_snapshot))) {
         AdvanceInputIter();
       }
       // If you find you still need to output a row with this key, we need to output the
@@ -752,13 +759,15 @@ void CompactionIterator::NextFromInput() {
       }
 
       pinned_iters_mgr_.StartPinning();
+      Version* version = compaction_ ? compaction_->input_version() : nullptr;
+
       // We know the merge type entry is not hidden, otherwise we would
       // have hit (A)
       // We encapsulate the merge related state machine in a different
       // object to minimize change to the existing flow.
-      Status s =
-          merge_helper_->MergeUntil(&input_, range_del_agg_, prev_snapshot,
-                                    bottommost_level_, allow_data_in_errors_);
+      Status s = merge_helper_->MergeUntil(&input_, range_del_agg_,
+                                           prev_snapshot, bottommost_level_,
+                                           allow_data_in_errors_, version);
       merge_out_iter_.SeekToFirst();
 
       if (!s.ok() && !s.IsMergeInProgress()) {
@@ -910,6 +919,9 @@ void CompactionIterator::GarbageCollectBlobIfNeeded() {
     ++iter_stats_.num_blobs_read;
     iter_stats_.total_blob_bytes_read += bytes_read;
 
+    ++iter_stats_.num_blobs_relocated;
+    iter_stats_.total_blob_bytes_relocated += blob_index.size();
+
     value_ = blob_value_;
 
     if (ExtractLargeValueIfNeededImpl()) {
@@ -973,7 +985,8 @@ void CompactionIterator::PrepareOutput() {
     if (valid_ && compaction_ != nullptr &&
         !compaction_->allow_ingest_behind() &&
         ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ &&
-        IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
+        DefinitelyInSnapshot(ikey_.sequence, earliest_snapshot_) &&
+        ikey_.type != kTypeMerge) {
       assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
       if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
         ROCKS_LOG_FATAL(info_log_,
@@ -1049,7 +1062,7 @@ inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
          (ikey_.sequence < preserve_deletes_seqnum_);
 }
 
-bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
+bool CompactionIterator::IsInCurrentEarliestSnapshot(SequenceNumber sequence) {
   assert(snapshot_checker_ != nullptr);
   bool pre_condition = (earliest_snapshot_ == kMaxSequenceNumber ||
                         (earliest_snapshot_iter_ != snapshots_->end() &&

db/compaction/compaction_iterator.h

@@ -30,7 +30,9 @@ class SequenceIterWrapper : public InternalIterator {
  public:
   SequenceIterWrapper(InternalIterator* iter, const Comparator* cmp,
                       bool need_count_entries)
-      : cmp_(cmp), inner_iter_(iter), need_count_entries_(need_count_entries) {}
+      : icmp_(cmp, /*named=*/false),
+        inner_iter_(iter),
+        need_count_entries_(need_count_entries) {}
   bool Valid() const override { return inner_iter_->Valid(); }
   Status status() const override { return inner_iter_->status(); }
   void Next() override {
@@ -44,7 +46,7 @@ class SequenceIterWrapper : public InternalIterator {
       // For flush cases, we need to count total number of entries, so we
       // do Next() rather than Seek().
       while (inner_iter_->Valid() &&
-             cmp_->Compare(inner_iter_->key(), target) < 0) {
+             icmp_.Compare(inner_iter_->key(), target) < 0) {
         Next();
       }
     }
@@ -61,7 +63,7 @@ class SequenceIterWrapper : public InternalIterator {
   uint64_t num_itered() const { return num_itered_; }
 
  private:
-  const Comparator* cmp_;         // not owned
+  InternalKeyComparator icmp_;
   InternalIterator* inner_iter_;  // not owned
   uint64_t num_itered_ = 0;
   bool need_count_entries_;
@@ -95,6 +97,10 @@ class CompactionIterator {
     virtual double blob_garbage_collection_age_cutoff() const = 0;
 
     virtual Version* input_version() const = 0;
+
+    virtual bool DoesInputReferenceBlobFiles() const = 0;
+
+    virtual const Compaction* real_compaction() const = 0;
   };
 
   class RealCompaction : public CompactionProxy {
@@ -102,7 +108,7 @@ class CompactionIterator {
     explicit RealCompaction(const Compaction* compaction)
         : compaction_(compaction) {
       assert(compaction_);
-      assert(compaction_->immutable_cf_options());
+      assert(compaction_->immutable_options());
       assert(compaction_->mutable_cf_options());
     }
 
@@ -124,11 +130,11 @@ class CompactionIterator {
     }
 
     bool allow_ingest_behind() const override {
-      return compaction_->immutable_cf_options()->allow_ingest_behind;
+      return compaction_->immutable_options()->allow_ingest_behind;
     }
 
     bool preserve_deletes() const override {
-      return compaction_->immutable_cf_options()->preserve_deletes;
+      return compaction_->immutable_options()->preserve_deletes;
     }
 
     bool enable_blob_garbage_collection() const override {
@@ -144,44 +150,50 @@ class CompactionIterator {
       return compaction_->input_version();
     }
 
+    bool DoesInputReferenceBlobFiles() const override {
+      return compaction_->DoesInputReferenceBlobFiles();
+    }
+
+    const Compaction* real_compaction() const override { return compaction_; }
+
    private:
     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,
-                     BlobFileBuilder* blob_file_builder,
-                     bool allow_data_in_errors,
-                     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<int>* manual_compaction_paused = nullptr,
-                     const std::shared_ptr<Logger> info_log = nullptr,
-                     const std::string* full_history_ts_low = 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,
+      BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
+      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<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
+      const std::shared_ptr<Logger> info_log = nullptr,
+      const std::string* full_history_ts_low = nullptr);
 
   // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(InternalIterator* input, const Comparator* cmp,
-                     MergeHelper* merge_helper, SequenceNumber last_sequence,
-                     std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
-                     bool report_detailed_time, bool expect_valid_internal_key,
-                     CompactionRangeDelAggregator* range_del_agg,
-                     BlobFileBuilder* blob_file_builder,
-                     bool allow_data_in_errors,
-                     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<int>* manual_compaction_paused = nullptr,
-                     const std::shared_ptr<Logger> info_log = nullptr,
-                     const std::string* full_history_ts_low = 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,
+      BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
+      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<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
+      const std::shared_ptr<Logger> info_log = nullptr,
+      const std::string* full_history_ts_low = nullptr);
 
   ~CompactionIterator();
 
@@ -259,7 +271,13 @@ class CompactionIterator {
                SnapshotCheckerResult::kInSnapshot;
   }
 
-  bool IsInEarliestSnapshot(SequenceNumber sequence);
+  bool IsInCurrentEarliestSnapshot(SequenceNumber sequence);
+
+  bool DefinitelyInSnapshot(SequenceNumber seq, SequenceNumber snapshot);
+
+  bool DefinitelyNotInSnapshot(SequenceNumber seq, SequenceNumber snapshot);
+
+  bool InCurrentEarliestSnapshot(SequenceNumber seq);
 
   // Extract user-defined timestamp from user key if possible and compare it
   // with *full_history_ts_low_ if applicable.
@@ -301,6 +319,7 @@ class CompactionIterator {
   const CompactionFilter* compaction_filter_;
   const std::atomic<bool>* shutting_down_;
   const std::atomic<int>* manual_compaction_paused_;
+  const std::atomic<bool>* manual_compaction_canceled_;
   const SequenceNumber preserve_deletes_seqnum_;
   bool bottommost_level_;
   bool valid_ = false;
@@ -397,8 +416,33 @@ class CompactionIterator {
 
   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) > 0;
+    return (manual_compaction_paused_ &&
+            manual_compaction_paused_->load(std::memory_order_relaxed) > 0) ||
+           (manual_compaction_canceled_ &&
+            manual_compaction_canceled_->load(std::memory_order_relaxed));
   }
 };
+
+inline bool CompactionIterator::DefinitelyInSnapshot(SequenceNumber seq,
+                                                     SequenceNumber snapshot) {
+  return ((seq) <= (snapshot) &&
+          (snapshot_checker_ == nullptr ||
+           LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                  SnapshotCheckerResult::kInSnapshot)));
+}
+
+inline bool CompactionIterator::DefinitelyNotInSnapshot(
+    SequenceNumber seq, SequenceNumber snapshot) {
+  return ((seq) > (snapshot) ||
+          (snapshot_checker_ != nullptr &&
+           UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                    SnapshotCheckerResult::kNotInSnapshot)));
+}
+
+inline bool CompactionIterator::InCurrentEarliestSnapshot(SequenceNumber seq) {
+  return ((seq) <= earliest_snapshot_ &&
+          (snapshot_checker_ == nullptr ||
+           LIKELY(IsInCurrentEarliestSnapshot(seq))));
+}
+
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_iterator_test.cc

@@ -182,6 +182,10 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
 
   Version* input_version() const override { return nullptr; }
 
+  bool DoesInputReferenceBlobFiles() const override { return false; }
+
+  const Compaction* real_compaction() const override { return nullptr; }
+
   bool key_not_exists_beyond_output_level = false;
 
   bool is_bottommost_level = false;
@@ -282,7 +286,8 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
         range_del_agg_.get(), nullptr /* blob_file_builder */,
         true /*allow_data_in_errors*/, std::move(compaction), filter,
         &shutting_down_, /*preserve_deletes_seqnum=*/0,
-        /*manual_compaction_paused=*/nullptr, /*info_log=*/nullptr,
+        /*manual_compaction_paused=*/nullptr,
+        /*manual_compaction_canceled=*/nullptr, /*info_log=*/nullptr,
         full_history_ts_low));
   }
 

db/compaction/compaction_job.cc

@@ -20,9 +20,12 @@
 #include <utility>
 #include <vector>
 
+#include "db/blob/blob_counting_iterator.h"
 #include "db/blob/blob_file_addition.h"
 #include "db/blob/blob_file_builder.h"
+#include "db/blob/blob_garbage_meter.h"
 #include "db/builder.h"
+#include "db/compaction/clipping_iterator.h"
 #include "db/db_impl/db_impl.h"
 #include "db/db_iter.h"
 #include "db/dbformat.h"
@@ -104,6 +107,8 @@ const char* GetCompactionReasonString(CompactionReason compaction_reason) {
       return "ExternalSstIngestion";
     case CompactionReason::kPeriodicCompaction:
       return "PeriodicCompaction";
+    case CompactionReason::kChangeTemperature:
+      return "ChangeTemperature";
     case CompactionReason::kNumOfReasons:
       // fall through
     default:
@@ -146,6 +151,7 @@ struct CompactionJob::SubcompactionState {
   // State kept for output being generated
   std::vector<Output> outputs;
   std::vector<BlobFileAddition> blob_file_additions;
+  std::unique_ptr<BlobGarbageMeter> blob_garbage_meter;
   std::unique_ptr<WritableFileWriter> outfile;
   std::unique_ptr<TableBuilder> builder;
 
@@ -176,9 +182,17 @@ struct CompactionJob::SubcompactionState {
   uint64_t overlapped_bytes = 0;
   // A flag determine whether the key has been seen in ShouldStopBefore()
   bool seen_key = false;
+  // sub compaction job id, which is used to identify different sub-compaction
+  // within the same compaction job.
+  const uint32_t sub_job_id;
 
-  SubcompactionState(Compaction* c, Slice* _start, Slice* _end, uint64_t size)
-      : compaction(c), start(_start), end(_end), approx_size(size) {
+  SubcompactionState(Compaction* c, Slice* _start, Slice* _end, uint64_t size,
+                     uint32_t _sub_job_id)
+      : compaction(c),
+        start(_start),
+        end(_end),
+        approx_size(size),
+        sub_job_id(_sub_job_id) {
     assert(compaction != nullptr);
   }
 
@@ -228,6 +242,14 @@ struct CompactionJob::SubcompactionState {
 
     return false;
   }
+
+  Status ProcessOutFlowIfNeeded(const Slice& key, const Slice& value) {
+    if (!blob_garbage_meter) {
+      return Status::OK();
+    }
+
+    return blob_garbage_meter->ProcessOutFlow(key, value);
+  }
 };
 
 // Maintains state for the entire compaction
@@ -313,9 +335,10 @@ CompactionJob::CompactionJob(
     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::shared_ptr<IOTracer>& io_tracer,
-    const std::atomic<int>* manual_compaction_paused, const std::string& db_id,
-    const std::string& db_session_id, std::string full_history_ts_low,
-    BlobFileCompletionCallback* blob_callback)
+    const std::atomic<int>* manual_compaction_paused,
+    const std::atomic<bool>* manual_compaction_canceled,
+    const std::string& db_id, const std::string& db_session_id,
+    std::string full_history_ts_low, BlobFileCompletionCallback* blob_callback)
     : compact_(new CompactionState(compaction)),
       compaction_stats_(compaction->compaction_reason(), 1),
       db_options_(db_options),
@@ -339,6 +362,7 @@ CompactionJob::CompactionJob(
       versions_(versions),
       shutting_down_(shutting_down),
       manual_compaction_paused_(manual_compaction_paused),
+      manual_compaction_canceled_(manual_compaction_canceled),
       preserve_deletes_seqnum_(preserve_deletes_seqnum),
       db_directory_(db_directory),
       blob_output_directory_(blob_output_directory),
@@ -435,7 +459,8 @@ void CompactionJob::Prepare() {
     for (size_t i = 0; i <= boundaries_.size(); i++) {
       Slice* start = i == 0 ? nullptr : &boundaries_[i - 1];
       Slice* end = i == boundaries_.size() ? nullptr : &boundaries_[i];
-      compact_->sub_compact_states.emplace_back(c, start, end, sizes_[i]);
+      compact_->sub_compact_states.emplace_back(c, start, end, sizes_[i],
+                                                static_cast<uint32_t>(i));
     }
     RecordInHistogram(stats_, NUM_SUBCOMPACTIONS_SCHEDULED,
                       compact_->sub_compact_states.size());
@@ -444,7 +469,8 @@ void CompactionJob::Prepare() {
     constexpr Slice* end = nullptr;
     constexpr uint64_t size = 0;
 
-    compact_->sub_compact_states.emplace_back(c, start, end, size);
+    compact_->sub_compact_states.emplace_back(c, start, end, size,
+                                              /*sub_job_id*/ 0);
   }
 }
 
@@ -550,9 +576,10 @@ void CompactionJob::GenSubcompactionBoundaries() {
   int base_level = v->storage_info()->base_level();
   uint64_t max_output_files = static_cast<uint64_t>(std::ceil(
       sum / min_file_fill_percent /
-      MaxFileSizeForLevel(*(c->mutable_cf_options()), out_lvl,
-          c->immutable_cf_options()->compaction_style, base_level,
-          c->immutable_cf_options()->level_compaction_dynamic_level_bytes)));
+      MaxFileSizeForLevel(
+          *(c->mutable_cf_options()), out_lvl,
+          c->immutable_options()->compaction_style, base_level,
+          c->immutable_options()->level_compaction_dynamic_level_bytes)));
   uint64_t subcompactions =
       std::min({static_cast<uint64_t>(ranges.size()),
                 static_cast<uint64_t>(c->max_subcompactions()),
@@ -751,7 +778,7 @@ Status CompactionJob::Run() {
   for (const auto& state : compact_->sub_compact_states) {
     for (const auto& output : state.outputs) {
       auto fn =
-          TableFileName(state.compaction->immutable_cf_options()->cf_paths,
+          TableFileName(state.compaction->immutable_options()->cf_paths,
                         output.meta.fd.GetNumber(), output.meta.fd.GetPathId());
       tp[fn] = output.table_properties;
     }
@@ -854,7 +881,7 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
 
   UpdateCompactionJobStats(stats);
 
-  auto stream = event_logger_->LogToBuffer(log_buffer_);
+  auto stream = event_logger_->LogToBuffer(log_buffer_, 8192);
   stream << "job" << job_id_ << "event"
          << "compaction_finished"
          << "compaction_time_micros" << stats.micros
@@ -958,7 +985,8 @@ void CompactionJob::ProcessKeyValueCompactionWithCompactionService(
       compaction_input.column_family.name.c_str(), job_id_,
       compaction_input.output_level, input_files_oss.str().c_str());
   CompactionServiceJobStatus compaction_status =
-      db_options_.compaction_service->Start(compaction_input_binary, job_id_);
+      db_options_.compaction_service->Start(compaction_input_binary,
+                                            GetCompactionId(sub_compact));
   if (compaction_status != CompactionServiceJobStatus::kSuccess) {
     sub_compact->status =
         Status::Incomplete("CompactionService failed to start compaction job.");
@@ -967,7 +995,7 @@ void CompactionJob::ProcessKeyValueCompactionWithCompactionService(
 
   std::string compaction_result_binary;
   compaction_status = db_options_.compaction_service->WaitForComplete(
-      job_id_, &compaction_result_binary);
+      GetCompactionId(sub_compact), &compaction_result_binary);
 
   CompactionServiceResult compaction_result;
   s = CompactionServiceResult::Read(compaction_result_binary,
@@ -1014,7 +1042,7 @@ void CompactionJob::ProcessKeyValueCompactionWithCompactionService(
   for (const auto& file : compaction_result.output_files) {
     uint64_t file_num = versions_->NewFileNumber();
     auto src_file = compaction_result.output_path + "/" + file.file_name;
-    auto tgt_file = TableFileName(compaction->immutable_cf_options()->cf_paths,
+    auto tgt_file = TableFileName(compaction->immutable_options()->cf_paths,
                                   file_num, compaction->output_path_id());
     s = fs_->RenameFile(src_file, tgt_file, IOOptions(), nullptr);
     if (!s.ok()) {
@@ -1084,6 +1112,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
 
   CompactionRangeDelAggregator range_del_agg(&cfd->internal_comparator(),
                                              existing_snapshots_);
+
+  const Slice* const start = sub_compact->start;
+  const Slice* const end = sub_compact->end;
+
   ReadOptions read_options;
   read_options.verify_checksums = true;
   read_options.fill_cache = false;
@@ -1093,11 +1125,51 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // (b) CompactionFilter::Decision::kRemoveAndSkipUntil.
   read_options.total_order_seek = true;
 
+  // Note: if we're going to support subcompactions for user-defined timestamps,
+  // the timestamp part will have to be stripped from the bounds here.
+  assert((!start && !end) || cfd->user_comparator()->timestamp_size() == 0);
+  read_options.iterate_lower_bound = start;
+  read_options.iterate_upper_bound = end;
+
   // 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(
+  std::unique_ptr<InternalIterator> raw_input(
       versions_->MakeInputIterator(read_options, sub_compact->compaction,
                                    &range_del_agg, file_options_for_read_));
+  InternalIterator* input = raw_input.get();
+
+  IterKey start_ikey;
+  IterKey end_ikey;
+  Slice start_slice;
+  Slice end_slice;
+
+  if (start) {
+    start_ikey.SetInternalKey(*start, kMaxSequenceNumber, kValueTypeForSeek);
+    start_slice = start_ikey.GetInternalKey();
+  }
+  if (end) {
+    end_ikey.SetInternalKey(*end, kMaxSequenceNumber, kValueTypeForSeek);
+    end_slice = end_ikey.GetInternalKey();
+  }
+
+  std::unique_ptr<InternalIterator> clip;
+  if (start || end) {
+    clip.reset(new ClippingIterator(
+        raw_input.get(), start ? &start_slice : nullptr,
+        end ? &end_slice : nullptr, &cfd->internal_comparator()));
+    input = clip.get();
+  }
+
+  std::unique_ptr<InternalIterator> blob_counter;
+
+  if (sub_compact->compaction->DoesInputReferenceBlobFiles()) {
+    sub_compact->blob_garbage_meter.reset(new BlobGarbageMeter);
+    blob_counter.reset(
+        new BlobCountingIterator(input, sub_compact->blob_garbage_meter.get()));
+    input = blob_counter.get();
+  }
+
+  input->SeekToFirst();
 
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -1138,7 +1210,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   std::unique_ptr<BlobFileBuilder> blob_file_builder(
       mutable_cf_options->enable_blob_files
           ? new BlobFileBuilder(versions_, fs_.get(),
-                                sub_compact->compaction->immutable_cf_options(),
+                                sub_compact->compaction->immutable_options(),
                                 mutable_cf_options, &file_options_, job_id_,
                                 cfd->GetID(), cfd->GetName(),
                                 Env::IOPriority::IO_LOW, write_hint_,
@@ -1152,28 +1224,18 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       reinterpret_cast<void*>(
           const_cast<std::atomic<int>*>(manual_compaction_paused_)));
 
-  Slice* start = sub_compact->start;
-  Slice* end = sub_compact->end;
-  if (start != nullptr) {
-    IterKey start_iter;
-    start_iter.SetInternalKey(*start, kMaxSequenceNumber, kValueTypeForSeek);
-    input->Seek(start_iter.GetInternalKey());
-  } else {
-    input->SeekToFirst();
-  }
-
   Status status;
   const std::string* const full_history_ts_low =
       full_history_ts_low_.empty() ? nullptr : &full_history_ts_low_;
   sub_compact->c_iter.reset(new CompactionIterator(
-      input.get(), cfd->user_comparator(), &merge, versions_->LastSequence(),
+      input, cfd->user_comparator(), &merge, versions_->LastSequence(),
       &existing_snapshots_, earliest_write_conflict_snapshot_,
       snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_),
       /*expect_valid_internal_key=*/true, &range_del_agg,
       blob_file_builder.get(), db_options_.allow_data_in_errors,
       sub_compact->compaction, compaction_filter, shutting_down_,
-      preserve_deletes_seqnum_, manual_compaction_paused_, db_options_.info_log,
-      full_history_ts_low));
+      preserve_deletes_seqnum_, manual_compaction_paused_,
+      manual_compaction_canceled_, db_options_.info_log, full_history_ts_low));
   auto c_iter = sub_compact->c_iter.get();
   c_iter->SeekToFirst();
   if (c_iter->Valid() && sub_compact->compaction->output_level() != 0) {
@@ -1197,12 +1259,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     const Slice& key = c_iter->key();
     const Slice& value = c_iter->value();
 
-    // If an end key (exclusive) is specified, check if the current key is
-    // >= than it and exit if it is because the iterator is out of its range
-    if (end != nullptr &&
-        cfd->user_comparator()->Compare(c_iter->user_key(), *end) >= 0) {
-      break;
-    }
+    assert(!end ||
+           cfd->user_comparator()->Compare(c_iter->user_key(), *end) < 0);
+
     if (c_iter_stats.num_input_records % kRecordStatsEvery ==
         kRecordStatsEvery - 1) {
       RecordDroppedKeys(c_iter_stats, &sub_compact->compaction_job_stats);
@@ -1222,6 +1281,11 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       break;
     }
 
+    status = sub_compact->ProcessOutFlowIfNeeded(key, value);
+    if (!status.ok()) {
+      break;
+    }
+
     sub_compact->current_output_file_size =
         sub_compact->builder->EstimatedFileSize();
     const ParsedInternalKey& ikey = c_iter->ikey();
@@ -1305,6 +1369,16 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
 
   RecordTick(stats_, FILTER_OPERATION_TOTAL_TIME,
              c_iter_stats.total_filter_time);
+
+  if (c_iter_stats.num_blobs_relocated > 0) {
+    RecordTick(stats_, BLOB_DB_GC_NUM_KEYS_RELOCATED,
+               c_iter_stats.num_blobs_relocated);
+  }
+  if (c_iter_stats.total_blob_bytes_relocated > 0) {
+    RecordTick(stats_, BLOB_DB_GC_BYTES_RELOCATED,
+               c_iter_stats.total_blob_bytes_relocated);
+  }
+
   RecordDroppedKeys(c_iter_stats, &sub_compact->compaction_job_stats);
   RecordCompactionIOStats();
 
@@ -1317,8 +1391,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     status = Status::ShutdownInProgress("Database shutdown");
   }
   if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      (manual_compaction_paused_ &&
-       manual_compaction_paused_->load(std::memory_order_relaxed) > 0)) {
+      ((manual_compaction_paused_ &&
+        manual_compaction_paused_->load(std::memory_order_relaxed) > 0) ||
+       (manual_compaction_canceled_ &&
+        manual_compaction_canceled_->load(std::memory_order_relaxed)))) {
     status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
   }
   if (status.ok()) {
@@ -1387,10 +1463,16 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
 #endif  // ROCKSDB_ASSERT_STATUS_CHECKED
 
   sub_compact->c_iter.reset();
-  input.reset();
+  blob_counter.reset();
+  clip.reset();
+  raw_input.reset();
   sub_compact->status = status;
 }
 
+uint64_t CompactionJob::GetCompactionId(SubcompactionState* sub_compact) {
+  return (uint64_t)job_id_ << 32 | sub_compact->sub_job_id;
+}
+
 void CompactionJob::RecordDroppedKeys(
     const CompactionIterationStats& c_iter_stats,
     CompactionJobStats* compaction_job_stats) {
@@ -1670,7 +1752,7 @@ Status CompactionJob::FinishCompactionOutputFile(
     // This happens when the output level is bottom level, at the same time
     // the sub_compact output nothing.
     std::string fname =
-        TableFileName(sub_compact->compaction->immutable_cf_options()->cf_paths,
+        TableFileName(sub_compact->compaction->immutable_options()->cf_paths,
                       meta->fd.GetNumber(), meta->fd.GetPathId());
 
     // TODO(AR) it is not clear if there are any larger implications if
@@ -1755,19 +1837,6 @@ Status CompactionJob::InstallCompactionResults(
   auto* compaction = compact_->compaction;
   assert(compaction);
 
-  // paranoia: verify that the files that we started with
-  // still exist in the current version and in the same original level.
-  // This ensures that a concurrent compaction did not erroneously
-  // pick the same files to compact_.
-  if (!versions_->VerifyCompactionFileConsistency(compaction)) {
-    Compaction::InputLevelSummaryBuffer inputs_summary;
-
-    ROCKS_LOG_ERROR(db_options_.info_log, "[%s] [JOB %d] Compaction %s aborted",
-                    compaction->column_family_data()->GetName().c_str(),
-                    job_id_, compaction->InputLevelSummary(&inputs_summary));
-    return Status::Corruption("Compaction input files inconsistent");
-  }
-
   {
     Compaction::InputLevelSummaryBuffer inputs_summary;
     ROCKS_LOG_INFO(db_options_.info_log,
@@ -1783,6 +1852,8 @@ Status CompactionJob::InstallCompactionResults(
   // Add compaction inputs
   compaction->AddInputDeletions(edit);
 
+  std::unordered_map<uint64_t, BlobGarbageMeter::BlobStats> blob_total_garbage;
+
   for (const auto& sub_compact : compact_->sub_compact_states) {
     for (const auto& out : sub_compact.outputs) {
       edit->AddFile(compaction->output_level(), out.meta);
@@ -1791,6 +1862,29 @@ Status CompactionJob::InstallCompactionResults(
     for (const auto& blob : sub_compact.blob_file_additions) {
       edit->AddBlobFile(blob);
     }
+
+    if (sub_compact.blob_garbage_meter) {
+      const auto& flows = sub_compact.blob_garbage_meter->flows();
+
+      for (const auto& pair : flows) {
+        const uint64_t blob_file_number = pair.first;
+        const BlobGarbageMeter::BlobInOutFlow& flow = pair.second;
+
+        assert(flow.IsValid());
+        if (flow.HasGarbage()) {
+          blob_total_garbage[blob_file_number].Add(flow.GetGarbageCount(),
+                                                   flow.GetGarbageBytes());
+        }
+      }
+    }
+  }
+
+  for (const auto& pair : blob_total_garbage) {
+    const uint64_t blob_file_number = pair.first;
+    const BlobGarbageMeter::BlobStats& stats = pair.second;
+
+    edit->AddBlobFileGarbage(blob_file_number, stats.GetCount(),
+                             stats.GetBytes());
   }
 
   return versions_->LogAndApply(compaction->column_family_data(),
@@ -1845,11 +1939,12 @@ Status CompactionJob::OpenCompactionOutputFile(
 
   // Pass temperature of botommost files to FileSystem.
   FileOptions fo_copy = file_options_;
-  Temperature temperature = Temperature::kUnknown;
-  if (bottommost_level_) {
-    fo_copy.temperature = temperature =
+  Temperature temperature = sub_compact->compaction->output_temperature();
+  if (temperature == Temperature::kUnknown && bottommost_level_) {
+    temperature =
         sub_compact->compaction->mutable_cf_options()->bottommost_temperature;
   }
+  fo_copy.temperature = temperature;
 
   Status s;
   IOStatus io_s = NewWritableFile(fs_.get(), fname, &writable_file, fo_copy);
@@ -1914,12 +2009,12 @@ Status CompactionJob::OpenCompactionOutputFile(
   writable_file->SetPreallocationBlockSize(static_cast<size_t>(
       sub_compact->compaction->OutputFilePreallocationSize()));
   const auto& listeners =
-      sub_compact->compaction->immutable_cf_options()->listeners;
+      sub_compact->compaction->immutable_options()->listeners;
   sub_compact->outfile.reset(new WritableFileWriter(
       std::move(writable_file), fname, file_options_, db_options_.clock,
       io_tracer_, db_options_.stats, listeners,
       db_options_.file_checksum_gen_factory.get(),
-      tmp_set.Contains(FileType::kTableFile)));
+      tmp_set.Contains(FileType::kTableFile), false));
 
   TableBuilderOptions tboptions(
       *cfd->ioptions(), *(sub_compact->compaction->mutable_cf_options()),
@@ -1929,7 +2024,8 @@ Status CompactionJob::OpenCompactionOutputFile(
       cfd->GetName(), sub_compact->compaction->output_level(),
       bottommost_level_, TableFileCreationReason::kCompaction,
       oldest_ancester_time, 0 /* oldest_key_time */, current_time, db_id_,
-      db_session_id_, sub_compact->compaction->max_output_file_size());
+      db_session_id_, sub_compact->compaction->max_output_file_size(),
+      file_number);
   sub_compact->builder.reset(
       NewTableBuilder(tboptions, sub_compact->outfile.get()));
   LogFlush(db_options_.info_log);
@@ -2095,7 +2191,7 @@ void CompactionJob::LogCompaction() {
 }
 
 std::string CompactionJob::GetTableFileName(uint64_t file_number) {
-  return TableFileName(compact_->compaction->immutable_cf_options()->cf_paths,
+  return TableFileName(compact_->compaction->immutable_options()->cf_paths,
                        file_number, compact_->compaction->output_path_id());
 }
 
@@ -2126,7 +2222,7 @@ CompactionServiceCompactionJob::CompactionServiceCompactionJob(
           compaction->mutable_cf_options()->paranoid_file_checks,
           compaction->mutable_cf_options()->report_bg_io_stats, dbname,
           &(compaction_service_result->stats), Env::Priority::USER, io_tracer,
-          nullptr, db_id, db_session_id,
+          nullptr, nullptr, db_id, db_session_id,
           compaction->column_family_data()->GetFullHistoryTsLow()),
       output_path_(output_path),
       compaction_input_(compaction_service_input),
@@ -2149,8 +2245,8 @@ Status CompactionServiceCompactionJob::Run() {
   Slice end = compaction_input_.end;
   compact_->sub_compact_states.emplace_back(
       c, compaction_input_.has_begin ? &begin : nullptr,
-      compaction_input_.has_end ? &end : nullptr,
-      compaction_input_.approx_size);
+      compaction_input_.has_end ? &end : nullptr, compaction_input_.approx_size,
+      /*sub_job_id*/ 0);
 
   log_buffer_->FlushBufferToLog();
   LogCompaction();
@@ -2189,7 +2285,7 @@ Status CompactionServiceCompactionJob::Run() {
     status = io_s;
   }
   if (status.ok()) {
-    // TODO: Add verify_table() and VerifyCompactionFileConsistency()
+    // TODO: Add verify_table()
   }
 
   // Finish up all book-keeping to unify the subcompaction results

db/compaction/compaction_job.h

@@ -81,6 +81,7 @@ class CompactionJob {
       const std::string& dbname, CompactionJobStats* compaction_job_stats,
       Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
       const std::atomic<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
       const std::string& db_id = "", const std::string& db_session_id = "",
       std::string full_history_ts_low = "",
       BlobFileCompletionCallback* blob_callback = nullptr);
@@ -167,7 +168,7 @@ class CompactionJob {
   void UpdateCompactionInputStatsHelper(
       int* num_files, uint64_t* bytes_read, int input_level);
 
-  int job_id_;
+  uint32_t job_id_;
 
   CompactionJobStats* compaction_job_stats_;
 
@@ -185,6 +186,7 @@ class CompactionJob {
   VersionSet* versions_;
   const std::atomic<bool>* shutting_down_;
   const std::atomic<int>* manual_compaction_paused_;
+  const std::atomic<bool>* manual_compaction_canceled_;
   const SequenceNumber preserve_deletes_seqnum_;
   FSDirectory* db_directory_;
   FSDirectory* blob_output_directory_;
@@ -217,6 +219,8 @@ class CompactionJob {
   std::string full_history_ts_low_;
   BlobFileCompletionCallback* blob_callback_;
 
+  uint64_t GetCompactionId(SubcompactionState* sub_compact);
+
   // Get table file name in where it's outputting to, which should also be in
   // `output_directory_`.
   virtual std::string GetTableFileName(uint64_t file_number);

db/compaction/compaction_job_test.cc

@@ -82,10 +82,11 @@ class CompactionJobTestBase : public testing::Test {
         mutable_db_options_(),
         table_cache_(NewLRUCache(50000, 16)),
         write_buffer_manager_(db_options_.db_write_buffer_size),
-        versions_(new VersionSet(
-            dbname_, &db_options_, env_options_, table_cache_.get(),
-            &write_buffer_manager_, &write_controller_,
-            /*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr)),
+        versions_(new VersionSet(dbname_, &db_options_, env_options_,
+                                 table_cache_.get(), &write_buffer_manager_,
+                                 &write_controller_,
+                                 /*block_cache_tracer=*/nullptr,
+                                 /*io_tracer=*/nullptr, /*db_session_id*/ "")),
         shutting_down_(false),
         preserve_deletes_seqnum_(0),
         mock_table_factory_(new mock::MockTableFactory()),
@@ -269,7 +270,8 @@ class CompactionJobTestBase : public testing::Test {
     versions_.reset(
         new VersionSet(dbname_, &db_options_, env_options_, table_cache_.get(),
                        &write_buffer_manager_, &write_controller_,
-                       /*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr));
+                       /*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr,
+                       /*db_session_id*/ ""));
     compaction_job_stats_.Reset();
     ASSERT_OK(SetIdentityFile(env_, dbname_));
 
@@ -332,8 +334,8 @@ class CompactionJobTestBase : public testing::Test {
         cfd->current()->storage_info(), *cfd->ioptions(),
         *cfd->GetLatestMutableCFOptions(), mutable_db_options_,
         compaction_input_files, output_level, 1024 * 1024, 10 * 1024 * 1024, 0,
-        kNoCompression, cfd->GetLatestMutableCFOptions()->compression_opts, 0,
-        {}, true);
+        kNoCompression, cfd->GetLatestMutableCFOptions()->compression_opts,
+        Temperature::kUnknown, 0, {}, true);
     compaction.SetInputVersion(cfd->current());
 
     LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
@@ -350,7 +352,8 @@ class CompactionJobTestBase : public testing::Test {
         earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
         &event_logger, false, false, dbname_, &compaction_job_stats_,
         Env::Priority::USER, nullptr /* IOTracer */,
-        /*manual_compaction_paused=*/nullptr, /*db_id=*/"",
+        /*manual_compaction_paused=*/nullptr,
+        /*manual_compaction_canceled=*/nullptr, /*db_id=*/"",
         /*db_session_id=*/"", full_history_ts_low_);
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 

db/compaction/compaction_picker.cc

@@ -358,7 +358,7 @@ Compaction* CompactionPicker::CompactFiles(
       output_level, compact_options.output_file_size_limit,
       mutable_cf_options.max_compaction_bytes, output_path_id, compression_type,
       GetCompressionOptions(mutable_cf_options, vstorage, output_level),
-      compact_options.max_subcompactions,
+      Temperature::kUnknown, compact_options.max_subcompactions,
       /* grandparents */ {}, true);
   RegisterCompaction(c);
   return c;
@@ -634,7 +634,8 @@ Compaction* CompactionPicker::CompactRange(
         GetCompressionType(ioptions_, vstorage, mutable_cf_options,
                            output_level, 1),
         GetCompressionOptions(mutable_cf_options, vstorage, output_level),
-        compact_range_options.max_subcompactions, /* grandparents */ {},
+        Temperature::kUnknown, compact_range_options.max_subcompactions,
+        /* grandparents */ {},
         /* is manual */ true);
     RegisterCompaction(c);
     vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
@@ -812,7 +813,8 @@ Compaction* CompactionPicker::CompactRange(
       GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                          vstorage->base_level()),
       GetCompressionOptions(mutable_cf_options, vstorage, output_level),
-      compact_range_options.max_subcompactions, std::move(grandparents),
+      Temperature::kUnknown, compact_range_options.max_subcompactions,
+      std::move(grandparents),
       /* is manual compaction */ true);
 
   TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);

db/compaction/compaction_picker_fifo.cc

@@ -111,7 +111,7 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
   Compaction* c = new Compaction(
       vstorage, ioptions_, mutable_cf_options, mutable_db_options,
       std::move(inputs), 0, 0, 0, 0, kNoCompression,
-      mutable_cf_options.compression_opts,
+      mutable_cf_options.compression_opts, Temperature::kUnknown,
       /* max_subcompactions */ 0, {}, /* is manual */ false,
       vstorage->CompactionScore(0),
       /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
@@ -154,7 +154,8 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
             {comp_inputs}, 0, 16 * 1024 * 1024 /* output file size limit */,
             0 /* max compaction bytes, not applicable */,
             0 /* output path ID */, mutable_cf_options.compression,
-            mutable_cf_options.compression_opts, 0 /* max_subcompactions */, {},
+            mutable_cf_options.compression_opts, Temperature::kUnknown,
+            0 /* max_subcompactions */, {},
             /* is manual */ false, vstorage->CompactionScore(0),
             /* is deletion compaction */ false,
             CompactionReason::kFIFOReduceNumFiles);
@@ -203,13 +204,119 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
   Compaction* c = new Compaction(
       vstorage, ioptions_, mutable_cf_options, mutable_db_options,
       std::move(inputs), 0, 0, 0, 0, kNoCompression,
-      mutable_cf_options.compression_opts,
+      mutable_cf_options.compression_opts, Temperature::kUnknown,
       /* max_subcompactions */ 0, {}, /* is manual */ false,
       vstorage->CompactionScore(0),
       /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
   return c;
 }
 
+Compaction* FIFOCompactionPicker::PickCompactionToWarm(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
+    LogBuffer* log_buffer) {
+  if (mutable_cf_options.compaction_options_fifo.age_for_warm == 0) {
+    return nullptr;
+  }
+
+  const int kLevel0 = 0;
+  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+
+  int64_t _current_time;
+  auto status = ioptions_.clock->GetCurrentTime(&_current_time);
+  if (!status.ok()) {
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: Couldn't get current time: %s. "
+                     "Not doing compactions based on warm threshold. ",
+                     cf_name.c_str(), status.ToString().c_str());
+    return nullptr;
+  }
+  const uint64_t current_time = static_cast<uint64_t>(_current_time);
+
+  if (!level0_compactions_in_progress_.empty()) {
+    ROCKS_LOG_BUFFER(
+        log_buffer,
+        "[%s] FIFO compaction: Already executing compaction. Parallel "
+        "compactions are not supported",
+        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.compaction_options_fifo.age_for_warm) {
+    uint64_t create_time_threshold =
+        current_time - mutable_cf_options.compaction_options_fifo.age_for_warm;
+    uint64_t compaction_size = 0;
+    // We will ideally identify a file qualifying for warm tier by knowing
+    // the timestamp for the youngest entry in the file. However, right now
+    // we don't have the information. We infer it by looking at timestamp
+    // of the next file's (which is just younger) oldest entry's timestamp.
+    FileMetaData* prev_file = nullptr;
+    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
+      FileMetaData* f = *ritr;
+      assert(f);
+      if (f->being_compacted) {
+        // Right now this probably won't happen as we never try to schedule
+        // two compactions in parallel, so here we just simply don't schedule
+        // anything.
+        return nullptr;
+      }
+      uint64_t oldest_ancester_time = f->TryGetOldestAncesterTime();
+      if (oldest_ancester_time == kUnknownOldestAncesterTime) {
+        // Older files might not have enough information. It is possible to
+        // handle these files by looking at newer files, but maintaining the
+        // logic isn't worth it.
+        break;
+      }
+      if (oldest_ancester_time > create_time_threshold) {
+        // The previous file (which has slightly older data) doesn't qualify
+        // for warm tier.
+        break;
+      }
+      if (prev_file != nullptr) {
+        compaction_size += prev_file->fd.GetFileSize();
+        if (compaction_size > mutable_cf_options.max_compaction_bytes) {
+          break;
+        }
+        inputs[0].files.push_back(prev_file);
+        ROCKS_LOG_BUFFER(log_buffer,
+                         "[%s] FIFO compaction: picking file %" PRIu64
+                         " with next file's oldest time %" PRIu64 " for warm",
+                         cf_name.c_str(), prev_file->fd.GetNumber(),
+                         oldest_ancester_time);
+      }
+      if (f->temperature == Temperature::kUnknown ||
+          f->temperature == Temperature::kHot) {
+        prev_file = f;
+      } else if (!inputs[0].files.empty()) {
+        // A warm file newer than files picked.
+        break;
+      } else {
+        assert(prev_file == nullptr);
+      }
+    }
+  }
+
+  if (inputs[0].files.empty()) {
+    return nullptr;
+  }
+
+  Compaction* c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, mutable_db_options,
+      std::move(inputs), 0, 0 /* output file size limit */,
+      0 /* max compaction bytes, not applicable */, 0 /* output path ID */,
+      mutable_cf_options.compression, mutable_cf_options.compression_opts,
+      Temperature::kWarm,
+      /* max_subcompactions */ 0, {}, /* is manual */ false,
+      vstorage->CompactionScore(0),
+      /* is deletion compaction */ false, CompactionReason::kChangeTemperature);
+  return c;
+}
+
 Compaction* FIFOCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
@@ -225,6 +332,10 @@ Compaction* FIFOCompactionPicker::PickCompaction(
     c = PickSizeCompaction(cf_name, mutable_cf_options, mutable_db_options,
                            vstorage, log_buffer);
   }
+  if (c == nullptr) {
+    c = PickCompactionToWarm(cf_name, mutable_cf_options, mutable_db_options,
+                             vstorage, log_buffer);
+  }
   RegisterCompaction(c);
   return c;
 }

db/compaction/compaction_picker_fifo.h

@@ -52,6 +52,12 @@ class FIFOCompactionPicker : public CompactionPicker {
                                  const MutableDBOptions& mutable_db_options,
                                  VersionStorageInfo* version,
                                  LogBuffer* log_buffer);
+
+  Compaction* PickCompactionToWarm(const std::string& cf_name,
+                                   const MutableCFOptions& mutable_cf_options,
+                                   const MutableDBOptions& mutable_db_options,
+                                   VersionStorageInfo* version,
+                                   LogBuffer* log_buffer);
 };
 }  // namespace ROCKSDB_NAMESPACE
 #endif  // !ROCKSDB_LITE

db/compaction/compaction_picker_level.cc

@@ -336,6 +336,7 @@ Compaction* LevelCompactionBuilder::GetCompaction() {
       GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
                          output_level_, vstorage_->base_level()),
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level_),
+      Temperature::kUnknown,
       /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
       start_level_score_, false /* deletion_compaction */, compaction_reason_);
 

db/compaction/compaction_picker_test.cc

@@ -98,7 +98,9 @@ class CompactionPickerTest : public testing::Test {
   void Add(int level, uint32_t file_number, const char* smallest,
            const char* largest, uint64_t file_size = 1, uint32_t path_id = 0,
            SequenceNumber smallest_seq = 100, SequenceNumber largest_seq = 100,
-           size_t compensated_file_size = 0, bool marked_for_compact = false) {
+           size_t compensated_file_size = 0, bool marked_for_compact = false,
+           Temperature temperature = Temperature::kUnknown,
+           uint64_t oldest_ancestor_time = kUnknownOldestAncesterTime) {
     VersionStorageInfo* vstorage;
     if (temp_vstorage_) {
       vstorage = temp_vstorage_.get();
@@ -115,6 +117,8 @@ class CompactionPickerTest : public testing::Test {
         kUnknownFileChecksum, kUnknownFileChecksumFuncName);
     f->compensated_file_size =
         (compensated_file_size != 0) ? compensated_file_size : file_size;
+    f->temperature = temperature;
+    f->oldest_ancester_time = oldest_ancestor_time;
     vstorage->AddFile(level, f);
     files_.emplace_back(f);
     file_map_.insert({file_number, {f, level}});
@@ -757,6 +761,245 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
               vstorage_->CompactionScore(0) >= 1);
   }
 }
+
+TEST_F(CompactionPickerTest, FIFOToWarm1) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  fifo_options_.age_for_warm = kWarmThreshold;
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, threshold_time - 2000);
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, threshold_time - 3000);
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_files(0));
+  ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, FIFOToWarm2) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  fifo_options_.age_for_warm = kWarmThreshold;
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, threshold_time - 2000);
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, threshold_time - 3000);
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, threshold_time - 4000);
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(2U, compaction->num_input_files(0));
+  ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, FIFOToWarmMaxSize) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  fifo_options_.age_for_warm = kWarmThreshold;
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 9;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, threshold_time - 2000);
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, threshold_time - 3000);
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, threshold_time - 4000);
+  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
+      Temperature::kUnknown, threshold_time - 5000);
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(2U, compaction->num_input_files(0));
+  ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, FIFOToWarmWithExistingWarm) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  fifo_options_.age_for_warm = kWarmThreshold;
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, threshold_time - 2000);
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, threshold_time - 3000);
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, threshold_time - 4000);
+  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
+      Temperature::kWarm, threshold_time - 5000);
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(2U, compaction->num_input_files(0));
+  ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, FIFOToWarmWithOngoing) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  fifo_options_.age_for_warm = kWarmThreshold;
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, threshold_time - 2000);
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, threshold_time - 3000);
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, threshold_time - 4000);
+  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
+      Temperature::kWarm, threshold_time - 5000);
+  file_map_[2].first->being_compacted = true;
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  // Stop if a file is being compacted
+  ASSERT_TRUE(compaction.get() == nullptr);
+}
+
+TEST_F(CompactionPickerTest, FIFOToWarmWithHotBetweenWarms) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  fifo_options_.age_for_warm = kWarmThreshold;
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, threshold_time - 2000);
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kWarm, threshold_time - 3000);
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, threshold_time - 4000);
+  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
+      Temperature::kWarm, threshold_time - 5000);
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  // Stop if a file is being compacted
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_files(0));
+  ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
+}
+
 #endif  // ROCKSDB_LITE
 
 TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {

db/compaction/compaction_picker_universal.cc

@@ -728,6 +728,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
                          1, enable_compression),
       GetCompressionOptions(mutable_cf_options_, vstorage_, start_level,
                             enable_compression),
+      Temperature::kUnknown,
       /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
       score_, false /* deletion_compaction */, compaction_reason);
 }
@@ -955,6 +956,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
       GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
                          output_level, 1),
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level),
+      Temperature::kUnknown,
       /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
       score_, false /* deletion_compaction */,
       CompactionReason::kFilesMarkedForCompaction);
@@ -1029,6 +1031,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToOldest(
                          output_level, 1, true /* enable_compression */),
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level,
                             true /* enable_compression */),
+      Temperature::kUnknown,
       /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
       score_, false /* deletion_compaction */, compaction_reason);
 }

db/compaction/compaction_service_test.cc

@@ -12,12 +12,16 @@ namespace ROCKSDB_NAMESPACE {
 
 class MyTestCompactionService : public CompactionService {
  public:
-  MyTestCompactionService(const std::string& db_path,
-                          std::shared_ptr<FileSystem> fs, Options& options)
-      : db_path_(db_path), fs_(fs), options_(options) {}
+  MyTestCompactionService(const std::string& db_path, Options& options,
+                          std::shared_ptr<Statistics> statistics = nullptr)
+      : db_path_(db_path), options_(options), statistics_(statistics) {}
+
+  static const char* kClassName() { return "MyTestCompactionService"; }
+
+  const char* Name() const override { return kClassName(); }
 
   CompactionServiceJobStatus Start(const std::string& compaction_service_input,
-                                   int job_id) override {
+                                   uint64_t job_id) override {
     InstrumentedMutexLock l(&mutex_);
     jobs_.emplace(job_id, compaction_service_input);
     CompactionServiceJobStatus s = CompactionServiceJobStatus::kSuccess;
@@ -26,7 +30,7 @@ class MyTestCompactionService : public CompactionService {
   }
 
   CompactionServiceJobStatus WaitForComplete(
-      int job_id, std::string* compaction_service_result) override {
+      uint64_t job_id, std::string* compaction_service_result) override {
     std::string compaction_input;
     {
       InstrumentedMutexLock l(&mutex_);
@@ -50,10 +54,11 @@ class MyTestCompactionService : public CompactionService {
     options_override.prefix_extractor = options_.prefix_extractor;
     options_override.table_factory = options_.table_factory;
     options_override.sst_partitioner_factory = options_.sst_partitioner_factory;
+    options_override.statistics = statistics_;
 
-    Status s = DB::OpenAndCompact(db_path_, db_path_ + "/" + ToString(job_id),
-                                  compaction_input, compaction_service_result,
-                                  options_override);
+    Status s = DB::OpenAndCompact(
+        db_path_, db_path_ + "/" + ROCKSDB_NAMESPACE::ToString(job_id),
+        compaction_input, compaction_service_result, options_override);
     TEST_SYNC_POINT_CALLBACK("MyTestCompactionService::WaitForComplete::End",
                              compaction_service_result);
     compaction_num_.fetch_add(1);
@@ -69,10 +74,10 @@ class MyTestCompactionService : public CompactionService {
  private:
   InstrumentedMutex mutex_;
   std::atomic_int compaction_num_{0};
-  std::map<int, std::string> jobs_;
+  std::map<uint64_t, std::string> jobs_;
   const std::string db_path_;
-  std::shared_ptr<FileSystem> fs_;
   Options options_;
+  std::shared_ptr<Statistics> statistics_;
 };
 
 class CompactionServiceTest : public DBTestBase {
@@ -119,8 +124,10 @@ class CompactionServiceTest : public DBTestBase {
 TEST_F(CompactionServiceTest, BasicCompactions) {
   Options options = CurrentOptions();
   options.env = env_;
+  options.statistics = CreateDBStatistics();
+  std::shared_ptr<Statistics> compactor_statistics = CreateDBStatistics();
   options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+      dbname_, options, compactor_statistics);
 
   DestroyAndReopen(options);
 
@@ -154,6 +161,12 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
       dynamic_cast<MyTestCompactionService*>(options.compaction_service.get());
   ASSERT_GE(my_cs->GetCompactionNum(), 1);
 
+  // make sure the compaction statistics is only recorded on remote side
+  ASSERT_GE(
+      compactor_statistics->getTickerCount(COMPACTION_KEY_DROP_NEWER_ENTRY), 1);
+  ASSERT_EQ(options.statistics->getTickerCount(COMPACTION_KEY_DROP_NEWER_ENTRY),
+            0);
+
   // Test failed compaction
   SyncPoint::GetInstance()->SetCallBack(
       "DBImplSecondary::CompactWithoutInstallation::End", [&](void* status) {
@@ -191,8 +204,8 @@ TEST_F(CompactionServiceTest, ManualCompaction) {
   Options options = CurrentOptions();
   options.env = env_;
   options.disable_auto_compactions = true;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
   DestroyAndReopen(options);
   GenerateTestData();
 
@@ -232,8 +245,8 @@ TEST_F(CompactionServiceTest, FailedToStart) {
   Options options = CurrentOptions();
   options.env = env_;
   options.disable_auto_compactions = true;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
   DestroyAndReopen(options);
   GenerateTestData();
 
@@ -257,8 +270,8 @@ TEST_F(CompactionServiceTest, InvalidResult) {
   Options options = CurrentOptions();
   options.env = env_;
   options.disable_auto_compactions = true;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
   DestroyAndReopen(options);
   GenerateTestData();
 
@@ -278,22 +291,31 @@ TEST_F(CompactionServiceTest, InvalidResult) {
   ASSERT_FALSE(s.ok());
 }
 
-// TODO: support sub-compaction
-TEST_F(CompactionServiceTest, DISABLED_SubCompaction) {
+TEST_F(CompactionServiceTest, SubCompaction) {
   Options options = CurrentOptions();
   options.env = env_;
   options.max_subcompactions = 10;
   options.target_file_size_base = 1 << 10;  // 1KB
   options.disable_auto_compactions = true;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
 
   DestroyAndReopen(options);
   GenerateTestData();
+  VerifyTestData();
+
+  auto my_cs =
+      dynamic_cast<MyTestCompactionService*>(options.compaction_service.get());
+  int compaction_num_before = my_cs->GetCompactionNum();
 
   auto cro = CompactRangeOptions();
   cro.max_subcompactions = 10;
-  db_->CompactRange(cro, nullptr, nullptr);
+  Status s = db_->CompactRange(cro, nullptr, nullptr);
+  ASSERT_OK(s);
+  VerifyTestData();
+  int compaction_num = my_cs->GetCompactionNum() - compaction_num_before;
+  // make sure there's sub-compaction by checking the compaction number
+  ASSERT_GE(compaction_num, 2);
 }
 
 class PartialDeleteCompactionFilter : public CompactionFilter {
@@ -315,10 +337,11 @@ class PartialDeleteCompactionFilter : public CompactionFilter {
 TEST_F(CompactionServiceTest, CompactionFilter) {
   Options options = CurrentOptions();
   options.env = env_;
-  auto delete_comp_filter = PartialDeleteCompactionFilter();
-  options.compaction_filter = &delete_comp_filter;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  std::unique_ptr<CompactionFilter> delete_comp_filter(
+      new PartialDeleteCompactionFilter());
+  options.compaction_filter = delete_comp_filter.get();
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
 
   DestroyAndReopen(options);
 
@@ -360,8 +383,8 @@ TEST_F(CompactionServiceTest, CompactionFilter) {
 TEST_F(CompactionServiceTest, Snapshot) {
   Options options = CurrentOptions();
   options.env = env_;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
 
   DestroyAndReopen(options);
 
@@ -387,8 +410,8 @@ TEST_F(CompactionServiceTest, ConcurrentCompaction) {
   Options options = CurrentOptions();
   options.level0_file_num_compaction_trigger = 100;
   options.env = env_;
-  options.compaction_service = std::make_shared<MyTestCompactionService>(
-      dbname_, env_->GetFileSystem(), options);
+  options.compaction_service =
+      std::make_shared<MyTestCompactionService>(dbname_, options);
   options.max_background_jobs = 20;
 
   DestroyAndReopen(options);

db/corruption_test.cc

@@ -55,14 +55,9 @@ class CorruptionTest : public testing::Test {
     // bug in recovery code. Keep it 4 for now to make the test passes.
     tiny_cache_ = NewLRUCache(100, 4);
     Env* base_env = Env::Default();
-#ifndef ROCKSDB_LITE
-    const char* test_env_uri = getenv("TEST_ENV_URI");
-    if (test_env_uri) {
-      Status s = Env::LoadEnv(test_env_uri, &base_env, &env_guard_);
-      EXPECT_OK(s);
-      EXPECT_NE(Env::Default(), base_env);
-    }
-#endif  //! ROCKSDB_LITE
+    EXPECT_OK(
+        test::CreateEnvFromSystem(ConfigOptions(), &base_env, &env_guard_));
+    EXPECT_NE(base_env, nullptr);
     env_ = new test::ErrorEnv(base_env);
     options_.wal_recovery_mode = WALRecoveryMode::kTolerateCorruptedTailRecords;
     options_.env = env_;

db/db_basic_test.cc

@@ -31,7 +31,7 @@ namespace ROCKSDB_NAMESPACE {
 
 class DBBasicTest : public DBTestBase {
  public:
-  DBBasicTest() : DBTestBase("/db_basic_test", /*env_do_fsync=*/false) {}
+  DBBasicTest() : DBTestBase("db_basic_test", /*env_do_fsync=*/false) {}
 };
 
 TEST_F(DBBasicTest, OpenWhenOpen) {
@@ -1362,6 +1362,28 @@ TEST_P(DBMultiGetTestWithParam, MultiGetMultiCFSnapshot) {
   }
 }
 
+TEST_P(DBMultiGetTestWithParam, MultiGetMultiCFUnsorted) {
+  Options options = CurrentOptions();
+  CreateAndReopenWithCF({"one", "two"}, options);
+
+  ASSERT_OK(Put(1, "foo", "bar"));
+  ASSERT_OK(Put(2, "baz", "xyz"));
+  ASSERT_OK(Put(1, "abc", "def"));
+
+  // Note: keys for the same CF do not form a consecutive range
+  std::vector<int> cfs{1, 2, 1};
+  std::vector<std::string> keys{"foo", "baz", "abc"};
+  std::vector<std::string> values;
+
+  values =
+      MultiGet(cfs, keys, /* snapshot */ nullptr, /* batched */ GetParam());
+
+  ASSERT_EQ(values.size(), 3);
+  ASSERT_EQ(values[0], "bar");
+  ASSERT_EQ(values[1], "xyz");
+  ASSERT_EQ(values[2], "def");
+}
+
 INSTANTIATE_TEST_CASE_P(DBMultiGetTestWithParam, DBMultiGetTestWithParam,
                         testing::Bool());
 
@@ -2576,7 +2598,7 @@ class DBBasicTestTrackWal : public DBTestBase,
                             public testing::WithParamInterface<bool> {
  public:
   DBBasicTestTrackWal()
-      : DBTestBase("/db_basic_test_track_wal", /*env_do_fsync=*/false) {}
+      : DBTestBase("db_basic_test_track_wal", /*env_do_fsync=*/false) {}
 
   int CountWalFiles() {
     VectorLogPtr log_files;
@@ -2734,6 +2756,11 @@ class DBBasicTestMultiGet : public DBTestBase {
         EXPECT_OK(dbfull()->Flush(FlushOptions(), handles_[cf]));
       }
     }
+    // Clear compressed cache, which is always pre-populated
+    if (compressed_cache_) {
+      compressed_cache_->SetCapacity(0);
+      compressed_cache_->SetCapacity(1048576);
+    }
   }
 
   bool CheckValue(int i, const std::string& value) {

db/db_block_cache_test.cc

@@ -7,15 +7,20 @@
 // 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 <cstdlib>
+#include <functional>
 #include <memory>
 
 #include "cache/cache_entry_roles.h"
 #include "cache/lru_cache.h"
+#include "db/column_family.h"
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
+#include "rocksdb/statistics.h"
 #include "rocksdb/table.h"
 #include "util/compression.h"
+#include "util/defer.h"
 #include "util/random.h"
+#include "utilities/fault_injection_fs.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -38,7 +43,7 @@ class DBBlockCacheTest : public DBTestBase {
   const size_t kValueSize = 100;
 
   DBBlockCacheTest()
-      : DBTestBase("/db_block_cache_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_block_cache_test", /*env_do_fsync=*/true) {}
 
   BlockBasedTableOptions GetTableOptions() {
     BlockBasedTableOptions table_options;
@@ -152,12 +157,15 @@ class DBBlockCacheTest : public DBTestBase {
   }
 
 #ifndef ROCKSDB_LITE
-  const std::array<size_t, kNumCacheEntryRoles>& GetCacheEntryRoleCounts() {
+  const std::array<size_t, kNumCacheEntryRoles> GetCacheEntryRoleCountsBg() {
     // Verify in cache entry role stats
     ColumnFamilyHandleImpl* cfh =
         static_cast<ColumnFamilyHandleImpl*>(dbfull()->DefaultColumnFamily());
     InternalStats* internal_stats_ptr = cfh->cfd()->internal_stats();
-    return internal_stats_ptr->TEST_GetCacheEntryRoleStats().entry_counts;
+    InternalStats::CacheEntryRoleStats stats;
+    internal_stats_ptr->TEST_GetCacheEntryRoleStats(&stats,
+                                                    /*foreground=*/false);
+    return stats.entry_counts;
   }
 #endif  // ROCKSDB_LITE
 };
@@ -169,7 +177,13 @@ TEST_F(DBBlockCacheTest, IteratorBlockCacheUsage) {
   auto options = GetOptions(table_options);
   InitTable(options);
 
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
+  LRUCacheOptions co;
+  co.capacity = 0;
+  co.num_shard_bits = 0;
+  co.strict_capacity_limit = false;
+  // Needed not to count entry stats collector
+  co.metadata_charge_policy = kDontChargeCacheMetadata;
+  std::shared_ptr<Cache> cache = NewLRUCache(co);
   table_options.block_cache = cache;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   Reopen(options);
@@ -193,7 +207,13 @@ TEST_F(DBBlockCacheTest, TestWithoutCompressedBlockCache) {
   auto options = GetOptions(table_options);
   InitTable(options);
 
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
+  LRUCacheOptions co;
+  co.capacity = 0;
+  co.num_shard_bits = 0;
+  co.strict_capacity_limit = false;
+  // Needed not to count entry stats collector
+  co.metadata_charge_policy = kDontChargeCacheMetadata;
+  std::shared_ptr<Cache> cache = NewLRUCache(co);
   table_options.block_cache = cache;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   Reopen(options);
@@ -241,34 +261,54 @@ TEST_F(DBBlockCacheTest, TestWithoutCompressedBlockCache) {
 
 #ifdef SNAPPY
 TEST_F(DBBlockCacheTest, TestWithCompressedBlockCache) {
-  ReadOptions read_options;
-  auto table_options = GetTableOptions();
-  auto options = GetOptions(table_options);
-  options.compression = CompressionType::kSnappyCompression;
-  InitTable(options);
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
 
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
+  BlockBasedTableOptions table_options;
+  table_options.no_block_cache = true;
+  table_options.block_cache_compressed = nullptr;
+  table_options.block_size = 1;
+  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
+  table_options.cache_index_and_filter_blocks = false;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  options.compression = CompressionType::kSnappyCompression;
+
+  DestroyAndReopen(options);
+
+  std::string value(kValueSize, 'a');
+  for (size_t i = 0; i < kNumBlocks; i++) {
+    ASSERT_OK(Put(ToString(i), value));
+    ASSERT_OK(Flush());
+  }
+
+  ReadOptions read_options;
   std::shared_ptr<Cache> compressed_cache = NewLRUCache(1 << 25, 0, false);
+  LRUCacheOptions co;
+  co.capacity = 0;
+  co.num_shard_bits = 0;
+  co.strict_capacity_limit = false;
+  // Needed not to count entry stats collector
+  co.metadata_charge_policy = kDontChargeCacheMetadata;
+  std::shared_ptr<Cache> cache = NewLRUCache(co);
   table_options.block_cache = cache;
+  table_options.no_block_cache = false;
   table_options.block_cache_compressed = compressed_cache;
+  table_options.max_auto_readahead_size = 0;
+  table_options.cache_index_and_filter_blocks = false;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   Reopen(options);
   RecordCacheCounters(options);
 
-  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
-  Iterator* iter = nullptr;
-
   // Load blocks into cache.
-  for (size_t i = 0; i + 1 < kNumBlocks; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
+  for (size_t i = 0; i < kNumBlocks - 1; i++) {
+    ASSERT_EQ(value, Get(ToString(i)));
     CheckCacheCounters(options, 1, 0, 1, 0);
     CheckCompressedCacheCounters(options, 1, 0, 1, 0);
-    iterators[i].reset(iter);
   }
+
   size_t usage = cache->GetUsage();
-  ASSERT_LT(0, usage);
+  ASSERT_EQ(0, usage);
   ASSERT_EQ(usage, cache->GetPinnedUsage());
   size_t compressed_usage = compressed_cache->GetUsage();
   ASSERT_LT(0, compressed_usage);
@@ -280,24 +320,21 @@ TEST_F(DBBlockCacheTest, TestWithCompressedBlockCache) {
   cache->SetCapacity(usage);
   cache->SetStrictCapacityLimit(true);
   ASSERT_EQ(usage, cache->GetPinnedUsage());
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_TRUE(iter->status().IsIncomplete());
+
+  // Load last key block.
+  ASSERT_EQ("Result incomplete: Insert failed due to LRU cache being full.",
+            Get(ToString(kNumBlocks - 1)));
+  // Failure will also record the miss counter.
   CheckCacheCounters(options, 1, 0, 0, 1);
   CheckCompressedCacheCounters(options, 1, 0, 1, 0);
-  delete iter;
-  iter = nullptr;
 
   // Clear strict capacity limit flag. This time we shall hit compressed block
-  // cache.
+  // cache and load into block cache.
   cache->SetStrictCapacityLimit(false);
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_OK(iter->status());
+  // Load last key block.
+  ASSERT_EQ(value, Get(ToString(kNumBlocks - 1)));
   CheckCacheCounters(options, 1, 0, 1, 0);
   CheckCompressedCacheCounters(options, 0, 1, 0, 0);
-  delete iter;
-  iter = nullptr;
 }
 #endif  // SNAPPY
 
@@ -445,6 +482,119 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
   //           filter_bytes_insert);
 }
 
+#if (defined OS_LINUX || defined OS_WIN)
+TEST_F(DBBlockCacheTest, WarmCacheWithDataBlocksDuringFlush) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+
+  BlockBasedTableOptions table_options;
+  table_options.block_cache = NewLRUCache(1 << 25, 0, false);
+  table_options.cache_index_and_filter_blocks = false;
+  table_options.prepopulate_block_cache =
+      BlockBasedTableOptions::PrepopulateBlockCache::kFlushOnly;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  DestroyAndReopen(options);
+
+  std::string value(kValueSize, 'a');
+  for (size_t i = 1; i <= kNumBlocks; i++) {
+    ASSERT_OK(Put(ToString(i), value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(i, options.statistics->getTickerCount(BLOCK_CACHE_DATA_ADD));
+    ASSERT_EQ(value, Get(ToString(i)));
+    ASSERT_EQ(0, options.statistics->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    ASSERT_EQ(i, options.statistics->getTickerCount(BLOCK_CACHE_DATA_HIT));
+  }
+}
+
+// This test cache data, index and filter blocks during flush.
+TEST_F(DBBlockCacheTest, WarmCacheWithBlocksDuringFlush) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+
+  BlockBasedTableOptions table_options;
+  table_options.block_cache = NewLRUCache(1 << 25, 0, false);
+  table_options.cache_index_and_filter_blocks = true;
+  table_options.prepopulate_block_cache =
+      BlockBasedTableOptions::PrepopulateBlockCache::kFlushOnly;
+  table_options.filter_policy.reset(NewBloomFilterPolicy(10, false));
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  DestroyAndReopen(options);
+
+  std::string value(kValueSize, 'a');
+  for (size_t i = 1; i <= kNumBlocks; i++) {
+    ASSERT_OK(Put(ToString(i), value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(i, options.statistics->getTickerCount(BLOCK_CACHE_DATA_ADD));
+    ASSERT_EQ(i, options.statistics->getTickerCount(BLOCK_CACHE_INDEX_ADD));
+    ASSERT_EQ(i, options.statistics->getTickerCount(BLOCK_CACHE_FILTER_ADD));
+
+    ASSERT_EQ(value, Get(ToString(i)));
+
+    ASSERT_EQ(0, options.statistics->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    ASSERT_EQ(i, options.statistics->getTickerCount(BLOCK_CACHE_DATA_HIT));
+
+    ASSERT_EQ(0, options.statistics->getTickerCount(BLOCK_CACHE_INDEX_MISS));
+    ASSERT_EQ(i * 3, options.statistics->getTickerCount(BLOCK_CACHE_INDEX_HIT));
+
+    ASSERT_EQ(0, options.statistics->getTickerCount(BLOCK_CACHE_FILTER_MISS));
+    ASSERT_EQ(i * 2,
+              options.statistics->getTickerCount(BLOCK_CACHE_FILTER_HIT));
+  }
+}
+
+TEST_F(DBBlockCacheTest, DynamicallyWarmCacheDuringFlush) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+
+  BlockBasedTableOptions table_options;
+  table_options.block_cache = NewLRUCache(1 << 25, 0, false);
+  table_options.cache_index_and_filter_blocks = false;
+  table_options.prepopulate_block_cache =
+      BlockBasedTableOptions::PrepopulateBlockCache::kFlushOnly;
+
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  DestroyAndReopen(options);
+
+  std::string value(kValueSize, 'a');
+
+  for (size_t i = 1; i <= 5; i++) {
+    ASSERT_OK(Put(ToString(i), value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(1,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+
+    ASSERT_EQ(value, Get(ToString(i)));
+    ASSERT_EQ(0,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+    ASSERT_EQ(
+        0, options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
+    ASSERT_EQ(1,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
+  }
+
+  ASSERT_OK(dbfull()->SetOptions(
+      {{"block_based_table_factory", "{prepopulate_block_cache=kDisable;}"}}));
+
+  for (size_t i = 6; i <= kNumBlocks; i++) {
+    ASSERT_OK(Put(ToString(i), value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(0,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+
+    ASSERT_EQ(value, Get(ToString(i)));
+    ASSERT_EQ(1,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+    ASSERT_EQ(
+        1, options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
+    ASSERT_EQ(0,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
+  }
+}
+#endif
+
 namespace {
 
 // A mock cache wraps LRUCache, and record how many entries have been
@@ -905,10 +1055,15 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
 }
 
 static void ClearCache(Cache* cache) {
+  auto roles = CopyCacheDeleterRoleMap();
   std::deque<std::string> keys;
   Cache::ApplyToAllEntriesOptions opts;
   auto callback = [&](const Slice& key, void* /*value*/, size_t /*charge*/,
-                      Cache::DeleterFn /*deleter*/) {
+                      Cache::DeleterFn deleter) {
+    if (roles.find(deleter) == roles.end()) {
+      // Keep the stats collector
+      return;
+    }
     keys.push_back(key.ToString());
   };
   cache->ApplyToAllEntries(callback, opts);
@@ -930,11 +1085,13 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
       ++iterations_tested;
 
       Options options = CurrentOptions();
+      SetTimeElapseOnlySleepOnReopen(&options);
       options.create_if_missing = true;
       options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-      options.stats_dump_period_sec = 0;
       options.max_open_files = 13;
       options.table_cache_numshardbits = 0;
+      // If this wakes up, it could interfere with test
+      options.stats_dump_period_sec = 0;
 
       BlockBasedTableOptions table_options;
       table_options.block_cache = cache;
@@ -970,7 +1127,9 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
       std::array<size_t, kNumCacheEntryRoles> expected{};
       // For CacheEntryStatsCollector
       expected[static_cast<size_t>(CacheEntryRole::kMisc)] = 1;
-      EXPECT_EQ(expected, GetCacheEntryRoleCounts());
+      EXPECT_EQ(expected, GetCacheEntryRoleCountsBg());
+
+      std::array<size_t, kNumCacheEntryRoles> prev_expected = expected;
 
       // First access only filters
       ASSERT_EQ("NOT_FOUND", Get("different from any key added"));
@@ -978,7 +1137,14 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
       if (partition) {
         expected[static_cast<size_t>(CacheEntryRole::kFilterMetaBlock)] += 2;
       }
-      EXPECT_EQ(expected, GetCacheEntryRoleCounts());
+      // Within some time window, we will get cached entry stats
+      EXPECT_EQ(prev_expected, GetCacheEntryRoleCountsBg());
+      // Not enough to force a miss
+      env_->MockSleepForSeconds(45);
+      EXPECT_EQ(prev_expected, GetCacheEntryRoleCountsBg());
+      // Enough to force a miss
+      env_->MockSleepForSeconds(601);
+      EXPECT_EQ(expected, GetCacheEntryRoleCountsBg());
 
       // Now access index and data block
       ASSERT_EQ("value", Get("foo"));
@@ -988,7 +1154,22 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
         expected[static_cast<size_t>(CacheEntryRole::kIndexBlock)]++;
       }
       expected[static_cast<size_t>(CacheEntryRole::kDataBlock)]++;
-      EXPECT_EQ(expected, GetCacheEntryRoleCounts());
+      // Enough to force a miss
+      env_->MockSleepForSeconds(601);
+      // But inject a simulated long scan so that we need a longer
+      // interval to force a miss next time.
+      SyncPoint::GetInstance()->SetCallBack(
+          "CacheEntryStatsCollector::GetStats:AfterApplyToAllEntries",
+          [this](void*) {
+            // To spend no more than 0.2% of time scanning, we would need
+            // interval of at least 10000s
+            env_->MockSleepForSeconds(20);
+          });
+      SyncPoint::GetInstance()->EnableProcessing();
+      EXPECT_EQ(expected, GetCacheEntryRoleCountsBg());
+      prev_expected = expected;
+      SyncPoint::GetInstance()->DisableProcessing();
+      SyncPoint::GetInstance()->ClearAllCallBacks();
 
       // The same for other file
       ASSERT_EQ("value", Get("zfoo"));
@@ -998,7 +1179,14 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
         expected[static_cast<size_t>(CacheEntryRole::kIndexBlock)]++;
       }
       expected[static_cast<size_t>(CacheEntryRole::kDataBlock)]++;
-      EXPECT_EQ(expected, GetCacheEntryRoleCounts());
+      // Because of the simulated long scan, this is not enough to force
+      // a miss
+      env_->MockSleepForSeconds(601);
+      EXPECT_EQ(prev_expected, GetCacheEntryRoleCountsBg());
+      // But this is enough
+      env_->MockSleepForSeconds(10000);
+      EXPECT_EQ(expected, GetCacheEntryRoleCountsBg());
+      prev_expected = expected;
 
       // Also check the GetProperty interface
       std::map<std::string, std::string> values;
@@ -1014,8 +1202,99 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
       EXPECT_EQ(
           ToString(expected[static_cast<size_t>(CacheEntryRole::kFilterBlock)]),
           values["count.filter-block"]);
+      EXPECT_EQ(
+          ToString(
+              prev_expected[static_cast<size_t>(CacheEntryRole::kWriteBuffer)]),
+          values["count.write-buffer"]);
       EXPECT_EQ(ToString(expected[static_cast<size_t>(CacheEntryRole::kMisc)]),
                 values["count.misc"]);
+
+      // Add one for kWriteBuffer
+      {
+        WriteBufferManager wbm(size_t{1} << 20, cache);
+        wbm.ReserveMem(1024);
+        expected[static_cast<size_t>(CacheEntryRole::kWriteBuffer)]++;
+        // Now we check that the GetProperty interface is more agressive about
+        // re-scanning stats, but not totally aggressive.
+        // Within some time window, we will get cached entry stats
+        env_->MockSleepForSeconds(1);
+        EXPECT_EQ(ToString(prev_expected[static_cast<size_t>(
+                      CacheEntryRole::kWriteBuffer)]),
+                  values["count.write-buffer"]);
+        // Not enough for a "background" miss but enough for a "foreground" miss
+        env_->MockSleepForSeconds(45);
+
+        ASSERT_TRUE(db_->GetMapProperty(DB::Properties::kBlockCacheEntryStats,
+                                        &values));
+        EXPECT_EQ(
+            ToString(
+                expected[static_cast<size_t>(CacheEntryRole::kWriteBuffer)]),
+            values["count.write-buffer"]);
+      }
+      prev_expected = expected;
+
+      // With collector pinned in cache, we should be able to hit
+      // even if the cache is full
+      ClearCache(cache.get());
+      Cache::Handle* h = nullptr;
+      ASSERT_OK(cache->Insert("Fill-it-up", nullptr, capacity + 1,
+                              GetNoopDeleterForRole<CacheEntryRole::kMisc>(),
+                              &h, Cache::Priority::HIGH));
+      ASSERT_GT(cache->GetUsage(), cache->GetCapacity());
+      expected = {};
+      // For CacheEntryStatsCollector
+      expected[static_cast<size_t>(CacheEntryRole::kMisc)] = 1;
+      // For Fill-it-up
+      expected[static_cast<size_t>(CacheEntryRole::kMisc)]++;
+      // Still able to hit on saved stats
+      EXPECT_EQ(prev_expected, GetCacheEntryRoleCountsBg());
+      // Enough to force a miss
+      env_->MockSleepForSeconds(1000);
+      EXPECT_EQ(expected, GetCacheEntryRoleCountsBg());
+
+      cache->Release(h);
+
+      // Now we test that the DB mutex is not held during scans, for the ways
+      // we know how to (possibly) trigger them. Without a better good way to
+      // check this, we simply inject an acquire & release of the DB mutex
+      // deep in the stat collection code. If we were already holding the
+      // mutex, that is UB that would at least be found by TSAN.
+      int scan_count = 0;
+      SyncPoint::GetInstance()->SetCallBack(
+          "CacheEntryStatsCollector::GetStats:AfterApplyToAllEntries",
+          [this, &scan_count](void*) {
+            dbfull()->TEST_LockMutex();
+            dbfull()->TEST_UnlockMutex();
+            ++scan_count;
+          });
+      SyncPoint::GetInstance()->EnableProcessing();
+
+      // Different things that might trigger a scan, with mock sleeps to
+      // force a miss.
+      env_->MockSleepForSeconds(10000);
+      dbfull()->DumpStats();
+      ASSERT_EQ(scan_count, 1);
+
+      env_->MockSleepForSeconds(10000);
+      ASSERT_TRUE(
+          db_->GetMapProperty(DB::Properties::kBlockCacheEntryStats, &values));
+      ASSERT_EQ(scan_count, 2);
+
+      env_->MockSleepForSeconds(10000);
+      std::string value_str;
+      ASSERT_TRUE(
+          db_->GetProperty(DB::Properties::kBlockCacheEntryStats, &value_str));
+      ASSERT_EQ(scan_count, 3);
+
+      env_->MockSleepForSeconds(10000);
+      ASSERT_TRUE(db_->GetProperty(DB::Properties::kCFStats, &value_str));
+      // To match historical speed, querying this property no longer triggers
+      // a scan, even if results are old. But periodic dump stats should keep
+      // things reasonably updated.
+      ASSERT_EQ(scan_count, /*unchanged*/ 3);
+
+      SyncPoint::GetInstance()->DisableProcessing();
+      SyncPoint::GetInstance()->ClearAllCallBacks();
     }
     EXPECT_GE(iterations_tested, 1);
   }
@@ -1023,13 +1302,238 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
 
 #endif  // ROCKSDB_LITE
 
+class DBBlockCacheKeyTest
+    : public DBTestBase,
+      public testing::WithParamInterface<std::tuple<bool, bool>> {
+ public:
+  DBBlockCacheKeyTest()
+      : DBTestBase("db_block_cache_test", /*env_do_fsync=*/false) {}
+
+  void SetUp() override {
+    use_compressed_cache_ = std::get<0>(GetParam());
+    exclude_file_numbers_ = std::get<1>(GetParam());
+  }
+
+  bool use_compressed_cache_;
+  bool exclude_file_numbers_;
+};
+
+// Disable LinkFile so that we can physically copy a DB using Checkpoint.
+// Disable file GetUniqueId to enable stable cache keys.
+class StableCacheKeyTestFS : public FaultInjectionTestFS {
+ public:
+  explicit StableCacheKeyTestFS(const std::shared_ptr<FileSystem>& base)
+      : FaultInjectionTestFS(base) {
+    SetFailGetUniqueId(true);
+  }
+
+  virtual ~StableCacheKeyTestFS() override {}
+
+  IOStatus LinkFile(const std::string&, const std::string&, const IOOptions&,
+                    IODebugContext*) override {
+    return IOStatus::NotSupported("Disabled");
+  }
+};
+
+TEST_P(DBBlockCacheKeyTest, StableCacheKeys) {
+  std::shared_ptr<StableCacheKeyTestFS> test_fs{
+      new StableCacheKeyTestFS(env_->GetFileSystem())};
+  std::unique_ptr<CompositeEnvWrapper> test_env{
+      new CompositeEnvWrapper(env_, test_fs)};
+
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.env = test_env.get();
+
+  BlockBasedTableOptions table_options;
+
+  int key_count = 0;
+  uint64_t expected_stat = 0;
+
+  std::function<void()> verify_stats;
+  if (use_compressed_cache_) {
+    if (!Snappy_Supported()) {
+      ROCKSDB_GTEST_SKIP("Compressed cache test requires snappy support");
+      return;
+    }
+    options.compression = CompressionType::kSnappyCompression;
+    table_options.no_block_cache = true;
+    table_options.block_cache_compressed = NewLRUCache(1 << 25, 0, false);
+    verify_stats = [&options, &expected_stat] {
+      // One for ordinary SST file and one for external SST file
+      ASSERT_EQ(expected_stat,
+                options.statistics->getTickerCount(BLOCK_CACHE_COMPRESSED_ADD));
+    };
+  } else {
+    table_options.cache_index_and_filter_blocks = true;
+    table_options.block_cache = NewLRUCache(1 << 25, 0, false);
+    verify_stats = [&options, &expected_stat] {
+      ASSERT_EQ(expected_stat,
+                options.statistics->getTickerCount(BLOCK_CACHE_DATA_ADD));
+      ASSERT_EQ(expected_stat,
+                options.statistics->getTickerCount(BLOCK_CACHE_INDEX_ADD));
+      ASSERT_EQ(expected_stat,
+                options.statistics->getTickerCount(BLOCK_CACHE_FILTER_ADD));
+    };
+  }
+
+  table_options.filter_policy.reset(NewBloomFilterPolicy(10, false));
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  CreateAndReopenWithCF({"koko"}, options);
+
+  if (exclude_file_numbers_) {
+    // Simulate something like old behavior without file numbers in properties.
+    // This is a "control" side of the test that also ensures safely degraded
+    // behavior on old files.
+    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+        "PropertyBlockBuilder::AddTableProperty:Start", [&](void* arg) {
+          TableProperties* props = reinterpret_cast<TableProperties*>(arg);
+          props->orig_file_number = 0;
+        });
+    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  }
+
+  std::function<void()> perform_gets = [&key_count, &expected_stat, this]() {
+    if (exclude_file_numbers_) {
+      // No cache key reuse should happen, because we can't rely on current
+      // file number being stable
+      expected_stat += key_count;
+    } else {
+      // Cache keys should be stable
+      expected_stat = key_count;
+    }
+    for (int i = 0; i < key_count; ++i) {
+      ASSERT_EQ(Get(1, Key(i)), "abc");
+    }
+  };
+
+  // Ordinary SST files with same session id
+  const std::string something_compressible(500U, 'x');
+  for (int i = 0; i < 2; ++i) {
+    ASSERT_OK(Put(1, Key(key_count), "abc"));
+    ASSERT_OK(Put(1, Key(key_count) + "a", something_compressible));
+    ASSERT_OK(Flush(1));
+    ++key_count;
+  }
+
+#ifndef ROCKSDB_LITE
+  // Save an export of those ordinary SST files for later
+  std::string export_files_dir = dbname_ + "/exported";
+  ExportImportFilesMetaData* metadata_ptr_ = nullptr;
+  Checkpoint* checkpoint;
+  ASSERT_OK(Checkpoint::Create(db_, &checkpoint));
+  ASSERT_OK(checkpoint->ExportColumnFamily(handles_[1], export_files_dir,
+                                           &metadata_ptr_));
+  ASSERT_NE(metadata_ptr_, nullptr);
+  delete checkpoint;
+  checkpoint = nullptr;
+
+  // External SST files with same session id
+  SstFileWriter sst_file_writer(EnvOptions(), options);
+  std::vector<std::string> external;
+  for (int i = 0; i < 2; ++i) {
+    std::string f = dbname_ + "/external" + ToString(i) + ".sst";
+    external.push_back(f);
+    ASSERT_OK(sst_file_writer.Open(f));
+    ASSERT_OK(sst_file_writer.Put(Key(key_count), "abc"));
+    ASSERT_OK(
+        sst_file_writer.Put(Key(key_count) + "a", something_compressible));
+    ++key_count;
+    ExternalSstFileInfo external_info;
+    ASSERT_OK(sst_file_writer.Finish(&external_info));
+    IngestExternalFileOptions ingest_opts;
+    ASSERT_OK(db_->IngestExternalFile(handles_[1], {f}, ingest_opts));
+  }
+
+  if (exclude_file_numbers_) {
+    // FIXME(peterd): figure out where these extra two ADDs are coming from
+    options.statistics->recordTick(BLOCK_CACHE_INDEX_ADD,
+                                   uint64_t{0} - uint64_t{2});
+    options.statistics->recordTick(BLOCK_CACHE_FILTER_ADD,
+                                   uint64_t{0} - uint64_t{2});
+    options.statistics->recordTick(BLOCK_CACHE_COMPRESSED_ADD,
+                                   uint64_t{0} - uint64_t{2});
+  }
+#endif
+
+  perform_gets();
+  verify_stats();
+
+  // Make sure we can cache hit after re-open
+  ReopenWithColumnFamilies({"default", "koko"}, options);
+
+  perform_gets();
+  verify_stats();
+
+  // Make sure we can cache hit even on a full copy of the DB. Using
+  // StableCacheKeyTestFS, Checkpoint will resort to full copy not hard link.
+  // (Checkpoint  not available in LITE mode to test this.)
+#ifndef ROCKSDB_LITE
+  auto db_copy_name = dbname_ + "-copy";
+  ASSERT_OK(Checkpoint::Create(db_, &checkpoint));
+  ASSERT_OK(checkpoint->CreateCheckpoint(db_copy_name));
+  delete checkpoint;
+
+  Close();
+  Destroy(options);
+
+  // Switch to the DB copy
+  SaveAndRestore<std::string> save_dbname(&dbname_, db_copy_name);
+  ReopenWithColumnFamilies({"default", "koko"}, options);
+
+  perform_gets();
+  verify_stats();
+
+  // And ensure that re-importing + ingesting the same files into a
+  // different DB uses same cache keys
+  DestroyAndReopen(options);
+
+  ColumnFamilyHandle* cfh = nullptr;
+  ASSERT_OK(db_->CreateColumnFamilyWithImport(ColumnFamilyOptions(), "yoyo",
+                                              ImportColumnFamilyOptions(),
+                                              *metadata_ptr_, &cfh));
+  ASSERT_NE(cfh, nullptr);
+  delete cfh;
+  cfh = nullptr;
+  delete metadata_ptr_;
+  metadata_ptr_ = nullptr;
+
+  DestroyDB(export_files_dir, options);
+
+  ReopenWithColumnFamilies({"default", "yoyo"}, options);
+
+  IngestExternalFileOptions ingest_opts;
+  ASSERT_OK(db_->IngestExternalFile(handles_[1], {external}, ingest_opts));
+
+  if (exclude_file_numbers_) {
+    // FIXME(peterd): figure out where these extra two ADDs are coming from
+    options.statistics->recordTick(BLOCK_CACHE_INDEX_ADD,
+                                   uint64_t{0} - uint64_t{2});
+    options.statistics->recordTick(BLOCK_CACHE_FILTER_ADD,
+                                   uint64_t{0} - uint64_t{2});
+  }
+
+  perform_gets();
+  verify_stats();
+#endif  // !ROCKSDB_LITE
+
+  Close();
+  Destroy(options);
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+}
+
+INSTANTIATE_TEST_CASE_P(DBBlockCacheKeyTest, DBBlockCacheKeyTest,
+                        ::testing::Combine(::testing::Bool(),
+                                           ::testing::Bool()));
+
 class DBBlockCachePinningTest
     : public DBTestBase,
       public testing::WithParamInterface<
           std::tuple<bool, PinningTier, PinningTier, PinningTier>> {
  public:
   DBBlockCachePinningTest()
-      : DBTestBase("/db_block_cache_test", /*env_do_fsync=*/false) {}
+      : DBTestBase("db_block_cache_test", /*env_do_fsync=*/false) {}
 
   void SetUp() override {
     partition_index_and_filters_ = std::get<0>(GetParam());

db/db_bloom_filter_test.cc

@@ -28,7 +28,7 @@ using BFP = BloomFilterPolicy;
 class DBBloomFilterTest : public DBTestBase {
  public:
   DBBloomFilterTest()
-      : DBTestBase("/db_bloom_filter_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_bloom_filter_test", /*env_do_fsync=*/true) {}
 };
 
 class DBBloomFilterTestWithParam : public DBTestBase,
@@ -42,7 +42,7 @@ class DBBloomFilterTestWithParam : public DBTestBase,
 
  public:
   DBBloomFilterTestWithParam()
-      : DBTestBase("/db_bloom_filter_tests", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_bloom_filter_tests", /*env_do_fsync=*/true) {}
 
   ~DBBloomFilterTestWithParam() override {}
 
@@ -527,7 +527,7 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
   } while (ChangeCompactOptions());
 }
 
-#ifndef ROCKSDB_VALGRIND_RUN
+#if !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 INSTANTIATE_TEST_CASE_P(
     FormatDef, DBBloomFilterTestDefFormatVersion,
     ::testing::Values(
@@ -551,7 +551,7 @@ INSTANTIATE_TEST_CASE_P(
                         test::kLatestFormatVersion),
         std::make_tuple(BFP::kAutoBloom, true, test::kLatestFormatVersion),
         std::make_tuple(BFP::kAutoBloom, false, test::kLatestFormatVersion)));
-#endif  // ROCKSDB_VALGRIND_RUN
+#endif  // !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 
 TEST_F(DBBloomFilterTest, BloomFilterRate) {
   while (ChangeFilterOptions()) {
@@ -1094,7 +1094,7 @@ class DBBloomFilterTestVaryPrefixAndFormatVer
 
  public:
   DBBloomFilterTestVaryPrefixAndFormatVer()
-      : DBTestBase("/db_bloom_filter_tests", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_bloom_filter_tests", /*env_do_fsync=*/true) {}
 
   ~DBBloomFilterTestVaryPrefixAndFormatVer() override {}
 

db/db_compaction_filter_test.cc

@@ -22,7 +22,7 @@ static std::string NEW_VALUE = "NewValue";
 class DBTestCompactionFilter : public DBTestBase {
  public:
   DBTestCompactionFilter()
-      : DBTestBase("/db_compaction_filter_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_compaction_filter_test", /*env_do_fsync=*/true) {}
 };
 
 // Param variant of DBTestBase::ChangeCompactOptions
@@ -46,7 +46,7 @@ class DBTestCompactionFilterWithCompactParam
   }
 };
 
-#ifndef ROCKSDB_VALGRIND_RUN
+#if !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 INSTANTIATE_TEST_CASE_P(
     CompactionFilterWithOption, DBTestCompactionFilterWithCompactParam,
     ::testing::Values(DBTestBase::OptionConfig::kDefault,
@@ -55,11 +55,11 @@ INSTANTIATE_TEST_CASE_P(
                       DBTestBase::OptionConfig::kLevelSubcompactions,
                       DBTestBase::OptionConfig::kUniversalSubcompactions));
 #else
-// Run fewer cases in valgrind
+// Run fewer cases in non-full valgrind to save time.
 INSTANTIATE_TEST_CASE_P(CompactionFilterWithOption,
                         DBTestCompactionFilterWithCompactParam,
                         ::testing::Values(DBTestBase::OptionConfig::kDefault));
-#endif  // ROCKSDB_VALGRIND_RUN
+#endif  // !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 
 class KeepFilter : public CompactionFilter {
  public:

db/db_compaction_test.cc

@@ -32,7 +32,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBCompactionTest : public DBTestBase {
  public:
   DBCompactionTest()
-      : DBTestBase("/db_compaction_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_compaction_test", /*env_do_fsync=*/true) {}
 };
 
 class DBCompactionTestWithParam
@@ -40,7 +40,7 @@ class DBCompactionTestWithParam
       public testing::WithParamInterface<std::tuple<uint32_t, bool>> {
  public:
   DBCompactionTestWithParam()
-      : DBTestBase("/db_compaction_test", /*env_do_fsync=*/true) {
+      : DBTestBase("db_compaction_test", /*env_do_fsync=*/true) {
     max_subcompactions_ = std::get<0>(GetParam());
     exclusive_manual_compaction_ = std::get<1>(GetParam());
   }
@@ -58,7 +58,7 @@ class DBCompactionTestWithBottommostParam
       public testing::WithParamInterface<BottommostLevelCompaction> {
  public:
   DBCompactionTestWithBottommostParam()
-      : DBTestBase("/db_compaction_test", /*env_do_fsync=*/true) {
+      : DBTestBase("db_compaction_test", /*env_do_fsync=*/true) {
     bottommost_level_compaction_ = GetParam();
   }
 
@@ -301,7 +301,7 @@ const SstFileMetaData* PickFileRandomly(
 }
 }  // anonymous namespace
 
-#ifndef ROCKSDB_VALGRIND_RUN
+#if !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 // All the TEST_P tests run once with sub_compactions disabled (i.e.
 // options.max_subcompactions = 1) and once with it enabled
 TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
@@ -366,7 +366,7 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
     }
   }
 }
-#endif  // ROCKSDB_VALGRIND_RUN
+#endif  // !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 
 TEST_P(DBCompactionTestWithParam, CompactionsPreserveDeletes) {
   //  For each options type we test following
@@ -2332,7 +2332,7 @@ TEST_P(DBCompactionTestWithParam, LevelCompactionCFPathUse) {
   option_vector.emplace_back(DBOptions(options), cf_opt1);
   CreateColumnFamilies({"one"},option_vector[1]);
 
-  // Configura CF2 specific paths.
+  // Configure CF2 specific paths.
   cf_opt2.cf_paths.emplace_back(dbname_ + "cf2", 500 * 1024);
   cf_opt2.cf_paths.emplace_back(dbname_ + "cf2_2", 4 * 1024 * 1024);
   cf_opt2.cf_paths.emplace_back(dbname_ + "cf2_3", 1024 * 1024 * 1024);
@@ -2387,13 +2387,16 @@ TEST_P(DBCompactionTestWithParam, LevelCompactionCFPathUse) {
   // Check that default column family uses db_paths.
   // And Column family "one" uses cf_paths.
 
-  // First three 110KB files are not going to second path.
-  // After that, (100K, 200K)
+  // The compaction in level0 outputs the sst files in level1.
+  // The first path cannot hold level1's data(400KB+400KB > 500KB),
+  // so every compaction move a sst file to second path. Please
+  // refer to LevelCompactionBuilder::GetPathId.
   for (int num = 0; num < 3; num++) {
     generate_file();
   }
+  check_sstfilecount(0, 1);
+  check_sstfilecount(1, 2);
 
-  // Another 110KB triggers a compaction to 400K file to fill up first path
   generate_file();
   check_sstfilecount(1, 3);
 
@@ -3600,6 +3603,41 @@ TEST_F(DBCompactionTest, CompactFilesOverlapInL0Bug) {
   ASSERT_EQ("new_val", Get(Key(0)));
 }
 
+TEST_F(DBCompactionTest, DeleteFilesInRangeConflictWithCompaction) {
+  Options options = CurrentOptions();
+  DestroyAndReopen(options);
+  const Snapshot* snapshot = nullptr;
+  const int kMaxKey = 10;
+
+  for (int i = 0; i < kMaxKey; i++) {
+    ASSERT_OK(Put(Key(i), Key(i)));
+    ASSERT_OK(Delete(Key(i)));
+    if (!snapshot) {
+      snapshot = db_->GetSnapshot();
+    }
+  }
+  ASSERT_OK(Flush());
+  MoveFilesToLevel(1);
+  ASSERT_OK(Put(Key(kMaxKey), Key(kMaxKey)));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  // test DeleteFilesInRange() deletes the files already picked for compaction
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"VersionSet::LogAndApply:WriteManifestStart",
+        "BackgroundCallCompaction:0"},
+       {"DBImpl::BackgroundCompaction:Finish",
+        "VersionSet::LogAndApply:WriteManifestDone"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  // release snapshot which mark bottommost file for compaction
+  db_->ReleaseSnapshot(snapshot);
+  std::string begin_string = Key(0);
+  std::string end_string = Key(kMaxKey + 1);
+  Slice begin(begin_string);
+  Slice end(end_string);
+  ASSERT_OK(DeleteFilesInRange(db_, db_->DefaultColumnFamily(), &begin, &end));
+  SyncPoint::GetInstance()->DisableProcessing();
+}
+
 TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
   // bottom-level files may contain deletions due to snapshots protecting the
   // deleted keys. Once the snapshot is released, we should see files with many
@@ -4970,7 +5008,7 @@ class CompactionPriTest : public DBTestBase,
                           public testing::WithParamInterface<uint32_t> {
  public:
   CompactionPriTest()
-      : DBTestBase("/compaction_pri_test", /*env_do_fsync=*/true) {
+      : DBTestBase("compaction_pri_test", /*env_do_fsync=*/true) {
     compaction_pri_ = GetParam();
   }
 
@@ -5208,11 +5246,12 @@ TEST_F(DBCompactionTest, ManualCompactionMax) {
   ASSERT_TRUE(num_compactions.load() == 1);
 
   // split the compaction to 5
-  uint64_t total = (l1_avg_size * 10) + (l2_avg_size * 100);
   int num_split = 5;
-  opts.max_compaction_bytes = total / num_split;
   DestroyAndReopen(opts);
   generate_sst_func();
+  uint64_t total_size = (l1_avg_size * 10) + (l2_avg_size * 100);
+  opts.max_compaction_bytes = total_size / num_split;
+  Reopen(opts);
   num_compactions.store(0);
   ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
   ASSERT_TRUE(num_compactions.load() == num_split);
@@ -5230,8 +5269,9 @@ TEST_F(DBCompactionTest, ManualCompactionMax) {
   opts.max_compaction_bytes = 0;
   DestroyAndReopen(opts);
   generate_sst_func();
+  total_size = (l1_avg_size * 10) + (l2_avg_size * 100);
   Status s = db_->SetOptions(
-      {{"max_compaction_bytes", std::to_string(total / num_split)}});
+      {{"max_compaction_bytes", std::to_string(total_size / num_split)}});
   ASSERT_OK(s);
 
   num_compactions.store(0);
@@ -6709,6 +6749,69 @@ TEST_F(DBCompactionTest, CompactionWithChecksumHandoffManifest2) {
   Destroy(options);
 }
 
+TEST_F(DBCompactionTest, FIFOWarm) {
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleFIFO;
+  options.num_levels = 1;
+  options.max_open_files = -1;
+  options.level0_file_num_compaction_trigger = 2;
+  options.create_if_missing = true;
+  CompactionOptionsFIFO fifo_options;
+  fifo_options.age_for_warm = 1000;
+  fifo_options.max_table_files_size = 100000000;
+  options.compaction_options_fifo = fifo_options;
+  env_->SetMockSleep();
+  Reopen(options);
+
+  int total_warm = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "NewWritableFile::FileOptions.temperature", [&](void* arg) {
+        Temperature temperature = *(static_cast<Temperature*>(arg));
+        if (temperature == Temperature::kWarm) {
+          total_warm++;
+        }
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  ASSERT_OK(Put(Key(0), "value1"));
+  env_->MockSleepForSeconds(800);
+  ASSERT_OK(Put(Key(2), "value2"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(Put(Key(0), "value1"));
+  env_->MockSleepForSeconds(800);
+  ASSERT_OK(Put(Key(2), "value2"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(Put(Key(0), "value1"));
+  env_->MockSleepForSeconds(800);
+  ASSERT_OK(Put(Key(2), "value2"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+  ASSERT_OK(Put(Key(0), "value1"));
+  env_->MockSleepForSeconds(800);
+  ASSERT_OK(Put(Key(2), "value2"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+
+  ColumnFamilyMetaData metadata;
+  db_->GetColumnFamilyMetaData(&metadata);
+  ASSERT_EQ(4, metadata.file_count);
+  ASSERT_EQ(Temperature::kUnknown, metadata.levels[0].files[0].temperature);
+  ASSERT_EQ(Temperature::kUnknown, metadata.levels[0].files[1].temperature);
+  ASSERT_EQ(Temperature::kWarm, metadata.levels[0].files[2].temperature);
+  ASSERT_EQ(Temperature::kWarm, metadata.levels[0].files[3].temperature);
+  ASSERT_EQ(2, total_warm);
+
+  Destroy(options);
+}
+
 #endif  // !defined(ROCKSDB_LITE)
 
 }  // namespace ROCKSDB_NAMESPACE

db/db_dynamic_level_test.cc

@@ -22,7 +22,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBTestDynamicLevel : public DBTestBase {
  public:
   DBTestDynamicLevel()
-      : DBTestBase("/db_dynamic_level_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_dynamic_level_test", /*env_do_fsync=*/true) {}
 };
 
 TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {

db/db_encryption_test.cc

@@ -17,7 +17,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBEncryptionTest : public DBTestBase {
  public:
   DBEncryptionTest()
-      : DBTestBase("/db_encryption_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_encryption_test", /*env_do_fsync=*/true) {}
   Env* GetTargetEnv() {
     if (encrypted_env_ != nullptr) {
       return (static_cast<EnvWrapper*>(encrypted_env_))->target();

db/db_filesnapshot.cc

@@ -127,7 +127,22 @@ Status DBImpl::GetSortedWalFiles(VectorLogPtr& files) {
       bg_cv_.Wait();
     }
   }
-  return wal_manager_.GetSortedWalFiles(files);
+
+  // Disable deletion in order to avoid the case where a file is deleted in
+  // the middle of the process so IO error is returned.
+  Status s = DisableFileDeletions();
+  bool file_deletion_supported = !s.IsNotSupported();
+  if (s.ok() || !file_deletion_supported) {
+    s = wal_manager_.GetSortedWalFiles(files);
+    if (file_deletion_supported) {
+      Status s2 = EnableFileDeletions(false);
+      if (!s2.ok() && s.ok()) {
+        s = s2;
+      }
+    }
+  }
+
+  return s;
 }
 
 Status DBImpl::GetCurrentWalFile(std::unique_ptr<LogFile>* current_log_file) {

db/db_impl/db_impl.cc

@@ -63,6 +63,7 @@
 #include "memtable/hash_linklist_rep.h"
 #include "memtable/hash_skiplist_rep.h"
 #include "monitoring/in_memory_stats_history.h"
+#include "monitoring/instrumented_mutex.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/persistent_stats_history.h"
@@ -93,14 +94,17 @@
 #include "table/table_builder.h"
 #include "table/two_level_iterator.h"
 #include "test_util/sync_point.h"
+#include "trace_replay/trace_replay.h"
 #include "util/autovector.h"
 #include "util/cast_util.h"
 #include "util/coding.h"
 #include "util/compression.h"
 #include "util/crc32c.h"
+#include "util/defer.h"
 #include "util/mutexlock.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
+#include "utilities/trace/replayer_impl.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -251,16 +255,17 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
   co.num_shard_bits = immutable_db_options_.table_cache_numshardbits;
   co.metadata_charge_policy = kDontChargeCacheMetadata;
   table_cache_ = NewLRUCache(co);
+  SetDbSessionId();
+  assert(!db_session_id_.empty());
 
   versions_.reset(new VersionSet(dbname_, &immutable_db_options_, file_options_,
                                  table_cache_.get(), write_buffer_manager_,
                                  &write_controller_, &block_cache_tracer_,
-                                 io_tracer_));
+                                 io_tracer_, db_session_id_));
   column_family_memtables_.reset(
       new ColumnFamilyMemTablesImpl(versions_->GetColumnFamilySet()));
 
   DumpRocksDBBuildVersion(immutable_db_options_.info_log.get());
-  SetDbSessionId();
   DumpDBFileSummary(immutable_db_options_, dbname_, db_session_id_);
   immutable_db_options_.Dump(immutable_db_options_.info_log.get());
   mutable_db_options_.Dump(immutable_db_options_.info_log.get());
@@ -547,12 +552,45 @@ Status DBImpl::CloseHelper() {
   flush_scheduler_.Clear();
   trim_history_scheduler_.Clear();
 
+  // For now, simply trigger a manual flush at close time
+  // on all the column families.
+  // TODO(bjlemaire): Check if this is needed. Also, in the
+  // future we can contemplate doing a more fine-grained
+  // flushing by first checking if there is a need for
+  // flushing (but need to implement something
+  // else than imm()->IsFlushPending() because the output
+  // memtables added to imm() dont trigger flushes).
+  if (immutable_db_options_.experimental_mempurge_threshold > 0.0) {
+    Status flush_ret;
+    mutex_.Unlock();
+    for (ColumnFamilyData* cf : *versions_->GetColumnFamilySet()) {
+      if (immutable_db_options_.atomic_flush) {
+        flush_ret = AtomicFlushMemTables({cf}, FlushOptions(),
+                                         FlushReason::kManualFlush);
+        if (!flush_ret.ok()) {
+          ROCKS_LOG_INFO(
+              immutable_db_options_.info_log,
+              "Atomic flush memtables failed upon closing (mempurge).");
+        }
+      } else {
+        flush_ret =
+            FlushMemTable(cf, FlushOptions(), FlushReason::kManualFlush);
+        if (!flush_ret.ok()) {
+          ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                         "Flush memtables failed upon closing (mempurge).");
+        }
+      }
+    }
+    mutex_.Lock();
+  }
+
   while (!flush_queue_.empty()) {
     const FlushRequest& flush_req = PopFirstFromFlushQueue();
     for (const auto& iter : flush_req) {
       iter.first->UnrefAndTryDelete();
     }
   }
+
   while (!compaction_queue_.empty()) {
     auto cfd = PopFirstFromCompactionQueue();
     cfd->UnrefAndTryDelete();
@@ -605,7 +643,7 @@ Status DBImpl::CloseHelper() {
       ROCKS_LOG_WARN(
           immutable_db_options_.info_log,
           "Unable to Sync WAL file %s with error -- %s",
-          LogFileName(immutable_db_options_.wal_dir, log_number).c_str(),
+          LogFileName(immutable_db_options_.GetWalDir(), log_number).c_str(),
           s.ToString().c_str());
       // Retain the first error
       if (ret.ok()) {
@@ -699,7 +737,8 @@ void DBImpl::MaybeIgnoreError(Status* s) const {
 const Status DBImpl::CreateArchivalDirectory() {
   if (immutable_db_options_.WAL_ttl_seconds > 0 ||
       immutable_db_options_.WAL_size_limit_MB > 0) {
-    std::string archivalPath = ArchivalDirectory(immutable_db_options_.wal_dir);
+    std::string archivalPath =
+        ArchivalDirectory(immutable_db_options_.GetWalDir());
     return env_->CreateDirIfMissing(archivalPath);
   }
   return Status::OK();
@@ -906,32 +945,50 @@ Status DBImpl::GetStatsHistory(
 void DBImpl::DumpStats() {
   TEST_SYNC_POINT("DBImpl::DumpStats:1");
 #ifndef ROCKSDB_LITE
-  const DBPropertyInfo* cf_property_info =
-      GetPropertyInfo(DB::Properties::kCFStats);
-  assert(cf_property_info != nullptr);
-  const DBPropertyInfo* db_property_info =
-      GetPropertyInfo(DB::Properties::kDBStats);
-  assert(db_property_info != nullptr);
-
   std::string stats;
   if (shutdown_initiated_) {
     return;
   }
+
   TEST_SYNC_POINT("DBImpl::DumpStats:StartRunning");
   {
     InstrumentedMutexLock l(&mutex_);
-    default_cf_internal_stats_->GetStringProperty(
-        *db_property_info, DB::Properties::kDBStats, &stats);
     for (auto cfd : *versions_->GetColumnFamilySet()) {
       if (cfd->initialized()) {
-        cfd->internal_stats()->GetStringProperty(
-            *cf_property_info, DB::Properties::kCFStatsNoFileHistogram, &stats);
+        // Release DB mutex for gathering cache entry stats. Pass over all
+        // column families for this first so that other stats are dumped
+        // near-atomically.
+        InstrumentedMutexUnlock u(&mutex_);
+        cfd->internal_stats()->CollectCacheEntryStats(/*foreground=*/false);
       }
     }
+
+    const std::string* property = &DB::Properties::kDBStats;
+    const DBPropertyInfo* property_info = GetPropertyInfo(*property);
+    assert(property_info != nullptr);
+    assert(!property_info->need_out_of_mutex);
+    default_cf_internal_stats_->GetStringProperty(*property_info, *property,
+                                                  &stats);
+
+    property = &DB::Properties::kCFStatsNoFileHistogram;
+    property_info = GetPropertyInfo(*property);
+    assert(property_info != nullptr);
+    assert(!property_info->need_out_of_mutex);
     for (auto cfd : *versions_->GetColumnFamilySet()) {
       if (cfd->initialized()) {
-        cfd->internal_stats()->GetStringProperty(
-            *cf_property_info, DB::Properties::kCFFileHistogram, &stats);
+        cfd->internal_stats()->GetStringProperty(*property_info, *property,
+                                                 &stats);
+      }
+    }
+
+    property = &DB::Properties::kCFFileHistogram;
+    property_info = GetPropertyInfo(*property);
+    assert(property_info != nullptr);
+    assert(!property_info->need_out_of_mutex);
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      if (cfd->initialized()) {
+        cfd->internal_stats()->GetStringProperty(*property_info, *property,
+                                                 &stats);
       }
     }
   }
@@ -1083,9 +1140,19 @@ Status DBImpl::SetDBOptions(
     InstrumentedMutexLock l(&mutex_);
     s = GetMutableDBOptionsFromStrings(mutable_db_options_, options_map,
                                        &new_options);
+
     if (new_options.bytes_per_sync == 0) {
       new_options.bytes_per_sync = 1024 * 1024;
     }
+
+    if (MutableDBOptionsAreEqual(mutable_db_options_, new_options)) {
+      ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                     "SetDBOptions(), input option value is not changed, "
+                     "skipping updating.");
+      persist_options_status.PermitUncheckedError();
+      return s;
+    }
+
     DBOptions new_db_options =
         BuildDBOptions(immutable_db_options_, new_options);
     if (s.ok()) {
@@ -1731,6 +1798,8 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
   }
   // If timestamp is used, we use read callback to ensure <key,t,s> is returned
   // only if t <= read_opts.timestamp and s <= snapshot.
+  // HACK: temporarily overwrite input struct field but restore
+  SaveAndRestore<ReadCallback*> restore_callback(&get_impl_options.callback);
   if (ts_sz > 0) {
     assert(!get_impl_options
                 .callback);  // timestamp with callback is not supported
@@ -1875,6 +1944,16 @@ std::vector<Status> DBImpl::MultiGet(
   }
 #endif  // NDEBUG
 
+  if (tracer_) {
+    // TODO: This mutex should be removed later, to improve performance when
+    // tracing is enabled.
+    InstrumentedMutexLock lock(&trace_mutex_);
+    if (tracer_) {
+      // TODO: maybe handle the tracing status?
+      tracer_->MultiGet(column_family, keys).PermitUncheckedError();
+    }
+  }
+
   SequenceNumber consistent_seqnum;
 
   std::unordered_map<uint32_t, MultiGetColumnFamilyData> multiget_cf_data(
@@ -2186,6 +2265,16 @@ void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
   }
 #endif  // NDEBUG
 
+  if (tracer_) {
+    // TODO: This mutex should be removed later, to improve performance when
+    // tracing is enabled.
+    InstrumentedMutexLock lock(&trace_mutex_);
+    if (tracer_) {
+      // TODO: maybe handle the tracing status?
+      tracer_->MultiGet(num_keys, column_families, keys).PermitUncheckedError();
+    }
+  }
+
   autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE> key_context;
   autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE> sorted_keys;
   sorted_keys.resize(num_keys);
@@ -2203,20 +2292,18 @@ void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
       multiget_cf_data;
   size_t cf_start = 0;
   ColumnFamilyHandle* cf = sorted_keys[0]->column_family;
+
   for (size_t i = 0; i < num_keys; ++i) {
     KeyContext* key_ctx = sorted_keys[i];
     if (key_ctx->column_family != cf) {
-      multiget_cf_data.emplace_back(
-          MultiGetColumnFamilyData(cf, cf_start, i - cf_start, nullptr));
+      multiget_cf_data.emplace_back(cf, cf_start, i - cf_start, nullptr);
       cf_start = i;
       cf = key_ctx->column_family;
     }
   }
-  {
-    // multiget_cf_data.emplace_back(
-    // MultiGetColumnFamilyData(cf, cf_start, num_keys - cf_start, nullptr));
-    multiget_cf_data.emplace_back(cf, cf_start, num_keys - cf_start, nullptr);
-  }
+
+  multiget_cf_data.emplace_back(cf, cf_start, num_keys - cf_start, nullptr);
+
   std::function<MultiGetColumnFamilyData*(
       autovector<MultiGetColumnFamilyData,
                  MultiGetContext::MAX_BATCH_SIZE>::iterator&)>
@@ -2276,7 +2363,7 @@ struct CompareKeyContext {
         static_cast<ColumnFamilyHandleImpl*>(lhs->column_family);
     uint32_t cfd_id1 = cfh->cfd()->GetID();
     const Comparator* comparator = cfh->cfd()->user_comparator();
-    cfh = static_cast<ColumnFamilyHandleImpl*>(lhs->column_family);
+    cfh = static_cast<ColumnFamilyHandleImpl*>(rhs->column_family);
     uint32_t cfd_id2 = cfh->cfd()->GetID();
 
     if (cfd_id1 < cfd_id2) {
@@ -2300,39 +2387,24 @@ struct CompareKeyContext {
 void DBImpl::PrepareMultiGetKeys(
     size_t num_keys, bool sorted_input,
     autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys) {
-#ifndef NDEBUG
   if (sorted_input) {
-    for (size_t index = 0; index < sorted_keys->size(); ++index) {
-      if (index > 0) {
-        KeyContext* lhs = (*sorted_keys)[index - 1];
-        KeyContext* rhs = (*sorted_keys)[index];
-        ColumnFamilyHandleImpl* cfh =
-            static_cast_with_check<ColumnFamilyHandleImpl>(lhs->column_family);
-        uint32_t cfd_id1 = cfh->cfd()->GetID();
-        const Comparator* comparator = cfh->cfd()->user_comparator();
-        cfh =
-            static_cast_with_check<ColumnFamilyHandleImpl>(lhs->column_family);
-        uint32_t cfd_id2 = cfh->cfd()->GetID();
+#ifndef NDEBUG
+    CompareKeyContext key_context_less;
 
-        assert(cfd_id1 <= cfd_id2);
-        if (cfd_id1 < cfd_id2) {
-          continue;
-        }
+    for (size_t index = 1; index < sorted_keys->size(); ++index) {
+      const KeyContext* const lhs = (*sorted_keys)[index - 1];
+      const KeyContext* const rhs = (*sorted_keys)[index];
 
-        // Both keys are from the same column family
-        int cmp = comparator->CompareWithoutTimestamp(
-            *(lhs->key), /*a_has_ts=*/false, *(rhs->key), /*b_has_ts=*/false);
-        assert(cmp <= 0);
-      }
-      index++;
+      // lhs should be <= rhs, or in other words, rhs should NOT be < lhs
+      assert(!key_context_less(rhs, lhs));
     }
-  }
 #endif
-  if (!sorted_input) {
-    CompareKeyContext sort_comparator;
-    std::sort(sorted_keys->begin(), sorted_keys->begin() + num_keys,
-              sort_comparator);
+
+    return;
   }
+
+  std::sort(sorted_keys->begin(), sorted_keys->begin() + num_keys,
+            CompareKeyContext());
 }
 
 void DBImpl::MultiGet(const ReadOptions& read_options,
@@ -2348,6 +2420,15 @@ void DBImpl::MultiGet(const ReadOptions& read_options,
                       const Slice* keys, PinnableSlice* values,
                       std::string* timestamps, Status* statuses,
                       const bool sorted_input) {
+  if (tracer_) {
+    // TODO: This mutex should be removed later, to improve performance when
+    // tracing is enabled.
+    InstrumentedMutexLock lock(&trace_mutex_);
+    if (tracer_) {
+      // TODO: maybe handle the tracing status?
+      tracer_->MultiGet(num_keys, column_family, keys).PermitUncheckedError();
+    }
+  }
   autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE> key_context;
   autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE> sorted_keys;
   sorted_keys.resize(num_keys);
@@ -3197,16 +3278,21 @@ bool DBImpl::GetProperty(ColumnFamilyHandle* column_family,
     }
     return ret_value;
   } else if (property_info->handle_string) {
-    InstrumentedMutexLock l(&mutex_);
-    return cfd->internal_stats()->GetStringProperty(*property_info, property,
-                                                    value);
-  } else if (property_info->handle_string_dbimpl) {
-    std::string tmp_value;
-    bool ret_value = (this->*(property_info->handle_string_dbimpl))(&tmp_value);
-    if (ret_value) {
-      *value = tmp_value;
+    if (property_info->need_out_of_mutex) {
+      return cfd->internal_stats()->GetStringProperty(*property_info, property,
+                                                      value);
+    } else {
+      InstrumentedMutexLock l(&mutex_);
+      return cfd->internal_stats()->GetStringProperty(*property_info, property,
+                                                      value);
+    }
+  } else if (property_info->handle_string_dbimpl) {
+    if (property_info->need_out_of_mutex) {
+      return (this->*(property_info->handle_string_dbimpl))(value);
+    } else {
+      InstrumentedMutexLock l(&mutex_);
+      return (this->*(property_info->handle_string_dbimpl))(value);
     }
-    return ret_value;
   }
   // Shouldn't reach here since exactly one of handle_string and handle_int
   // should be non-nullptr.
@@ -3224,9 +3310,14 @@ bool DBImpl::GetMapProperty(ColumnFamilyHandle* column_family,
   if (property_info == nullptr) {
     return false;
   } else if (property_info->handle_map) {
-    InstrumentedMutexLock l(&mutex_);
-    return cfd->internal_stats()->GetMapProperty(*property_info, property,
-                                                 value);
+    if (property_info->need_out_of_mutex) {
+      return cfd->internal_stats()->GetMapProperty(*property_info, property,
+                                                   value);
+    } else {
+      InstrumentedMutexLock l(&mutex_);
+      return cfd->internal_stats()->GetMapProperty(*property_info, property,
+                                                   value);
+    }
   }
   // If we reach this point it means that handle_map is not provided for the
   // requested property
@@ -3675,6 +3766,8 @@ Status DBImpl::DeleteFilesInRanges(ColumnFamilyHandle* column_family,
           deleted_files.insert(level_file);
           level_file->being_compacted = true;
         }
+        vstorage->ComputeCompactionScore(*cfd->ioptions(),
+                                         *cfd->GetLatestMutableCFOptions());
       }
     }
     if (edit.GetDeletedFiles().empty()) {
@@ -3738,6 +3831,17 @@ void DBImpl::GetColumnFamilyMetaData(ColumnFamilyHandle* column_family,
   ReturnAndCleanupSuperVersion(cfd, sv);
 }
 
+void DBImpl::GetAllColumnFamilyMetaData(
+    std::vector<ColumnFamilyMetaData>* metadata) {
+  InstrumentedMutexLock l(&mutex_);
+  for (auto cfd : *(versions_->GetColumnFamilySet())) {
+    {
+      metadata->emplace_back();
+      cfd->current()->GetColumnFamilyMetaData(&metadata->back());
+    }
+  }
+}
+
 #endif  // ROCKSDB_LITE
 
 Status DBImpl::CheckConsistency() {
@@ -3841,10 +3945,10 @@ Status DBImpl::GetDbSessionId(std::string& session_id) const {
   return Status::OK();
 }
 
-void DBImpl::SetDbSessionId() {
+std::string DBImpl::GenerateDbSessionId(Env* env) {
   // GenerateUniqueId() generates an identifier that has a negligible
   // probability of being duplicated, ~128 bits of entropy
-  std::string uuid = env_->GenerateUniqueId();
+  std::string uuid = env->GenerateUniqueId();
 
   // Hash and reformat that down to a more compact format, 20 characters
   // in base-36 ([0-9A-Z]), which is ~103 bits of entropy, which is enough
@@ -3855,15 +3959,21 @@ void DBImpl::SetDbSessionId() {
   // * Visually distinct from DB id format
   uint64_t a = NPHash64(uuid.data(), uuid.size(), 1234U);
   uint64_t b = NPHash64(uuid.data(), uuid.size(), 5678U);
-  db_session_id_.resize(20);
+  std::string db_session_id;
+  db_session_id.resize(20);
   static const char* const base36 = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
   size_t i = 0;
   for (; i < 10U; ++i, a /= 36U) {
-    db_session_id_[i] = base36[a % 36];
+    db_session_id[i] = base36[a % 36];
   }
   for (; i < 20U; ++i, b /= 36U) {
-    db_session_id_[i] = base36[b % 36];
+    db_session_id[i] = base36[b % 36];
   }
+  return db_session_id;
+}
+
+void DBImpl::SetDbSessionId() {
+  db_session_id_ = GenerateDbSessionId(env_);
   TEST_SYNC_POINT_CALLBACK("DBImpl::SetDbSessionId", &db_session_id_);
 }
 
@@ -3933,7 +4043,7 @@ Status DestroyDB(const std::string& dbname, const Options& options,
   ImmutableDBOptions soptions(SanitizeOptions(dbname, options));
   Env* env = soptions.env;
   std::vector<std::string> filenames;
-  bool wal_in_db_path = IsWalDirSameAsDBPath(&soptions);
+  bool wal_in_db_path = soptions.IsWalDirSameAsDBPath();
 
   // Reset the logger because it holds a handle to the
   // log file and prevents cleanup and directory removal
@@ -3999,7 +4109,7 @@ Status DestroyDB(const std::string& dbname, const Options& options,
     std::vector<std::string> walDirFiles;
     std::string archivedir = ArchivalDirectory(dbname);
     bool wal_dir_exists = false;
-    if (dbname != soptions.wal_dir) {
+    if (!soptions.IsWalDirSameAsDBPath(dbname)) {
       wal_dir_exists = env->GetChildren(soptions.wal_dir, &walDirFiles).ok();
       archivedir = ArchivalDirectory(soptions.wal_dir);
     }
@@ -4089,6 +4199,8 @@ Status DBImpl::WriteOptionsFile(bool need_mutex_lock,
 
   TEST_SYNC_POINT("DBImpl::WriteOptionsFile:1");
   TEST_SYNC_POINT("DBImpl::WriteOptionsFile:2");
+  TEST_SYNC_POINT_CALLBACK("DBImpl::WriteOptionsFile:PersistOptions",
+                           &db_options);
 
   std::string file_name =
       TempOptionsFileName(GetName(), versions_->NewFileNumber());
@@ -4255,9 +4367,7 @@ SequenceNumber DBImpl::GetEarliestMemTableSequenceNumber(SuperVersion* sv,
 
   return earliest_seq;
 }
-#endif  // ROCKSDB_LITE
 
-#ifndef ROCKSDB_LITE
 Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
                                        bool cache_only,
                                        SequenceNumber lower_bound_seq,
@@ -4999,11 +5109,19 @@ Status DBImpl::EndTrace() {
     s = tracer_->Close();
     tracer_.reset();
   } else {
-    return Status::IOError("No trace file to close");
+    s = Status::IOError("No trace file to close");
   }
   return s;
 }
 
+Status DBImpl::NewDefaultReplayer(
+    const std::vector<ColumnFamilyHandle*>& handles,
+    std::unique_ptr<TraceReader>&& reader,
+    std::unique_ptr<Replayer>* replayer) {
+  replayer->reset(new ReplayerImpl(this, handles, std::move(reader)));
+  return Status::OK();
+}
+
 Status DBImpl::StartBlockCacheTrace(
     const TraceOptions& trace_options,
     std::unique_ptr<TraceWriter>&& trace_writer) {

db/db_impl/db_impl.h

@@ -20,6 +20,7 @@
 #include <vector>
 
 #include "db/column_family.h"
+#include "db/compaction/compaction_iterator.h"
 #include "db/compaction/compaction_job.h"
 #include "db/dbformat.h"
 #include "db/error_handler.h"
@@ -50,9 +51,15 @@
 #include "rocksdb/env.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/status.h"
+#ifndef ROCKSDB_LITE
 #include "rocksdb/trace_reader_writer.h"
+#endif  // ROCKSDB_LITE
 #include "rocksdb/transaction_log.h"
+#ifndef ROCKSDB_LITE
+#include "rocksdb/utilities/replayer.h"
+#endif  // ROCKSDB_LITE
 #include "rocksdb/write_buffer_manager.h"
+#include "table/merging_iterator.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
 #include "util/hash.h"
@@ -400,12 +407,13 @@ class DBImpl : public DB {
       FileChecksumList* checksum_list) override;
 
   // Obtains the meta data of the specified column family of the DB.
-  // Status::NotFound() will be returned if the current DB does not have
-  // any column family match the specified name.
   // TODO(yhchiang): output parameter is placed in the end in this codebase.
   virtual void GetColumnFamilyMetaData(ColumnFamilyHandle* column_family,
                                        ColumnFamilyMetaData* metadata) override;
 
+  void GetAllColumnFamilyMetaData(
+      std::vector<ColumnFamilyMetaData>* metadata) override;
+
   Status SuggestCompactRange(ColumnFamilyHandle* column_family,
                              const Slice* begin, const Slice* end) override;
 
@@ -461,6 +469,12 @@ class DBImpl : public DB {
   using DB::EndTrace;
   virtual Status EndTrace() override;
 
+  using DB::NewDefaultReplayer;
+  virtual Status NewDefaultReplayer(
+      const std::vector<ColumnFamilyHandle*>& handles,
+      std::unique_ptr<TraceReader>&& reader,
+      std::unique_ptr<Replayer>* replayer) override;
+
   using DB::StartBlockCacheTrace;
   Status StartBlockCacheTrace(
       const TraceOptions& options,
@@ -962,7 +976,7 @@ class DBImpl : public DB {
 
   // Return the maximum overlapping data (in bytes) at next level for any
   // file at a level >= 1.
-  int64_t TEST_MaxNextLevelOverlappingBytes(
+  uint64_t TEST_MaxNextLevelOverlappingBytes(
       ColumnFamilyHandle* column_family = nullptr);
 
   // Return the current manifest file no.
@@ -974,8 +988,10 @@ class DBImpl : public DB {
   // get total level0 file size. Only for testing.
   uint64_t TEST_GetLevel0TotalSize();
 
-  void TEST_GetFilesMetaData(ColumnFamilyHandle* column_family,
-                             std::vector<std::vector<FileMetaData>>* metadata);
+  void TEST_GetFilesMetaData(
+      ColumnFamilyHandle* column_family,
+      std::vector<std::vector<FileMetaData>>* metadata,
+      std::vector<std::shared_ptr<BlobFileMetaData>>* blob_metadata = nullptr);
 
   void TEST_LockMutex();
 
@@ -1098,6 +1114,8 @@ class DBImpl : public DB {
     State state_;
   };
 
+  static std::string GenerateDbSessionId(Env* env);
+
  protected:
   const std::string dbname_;
   std::string db_id_;
@@ -1184,11 +1202,6 @@ class DBImpl : public DB {
                               ColumnFamilyHandle* column_family,
                               const Slice* begin, const Slice* end);
 
-  Status GetApproximateSizesInternal(const SizeApproximationOptions& options,
-                                     ColumnFamilyHandle* column_family,
-                                     const Range* range, int n,
-                                     uint64_t* sizes);
-
   // The following two functions can only be called when:
   // 1. WriteThread::Writer::EnterUnbatched() is used.
   // 2. db_mutex is NOT held
@@ -1454,15 +1467,16 @@ class DBImpl : public DB {
     uint32_t output_path_id;
     Status status;
     bool done;
-    bool in_progress;            // compaction request being processed?
-    bool incomplete;             // only part of requested range compacted
-    bool exclusive;              // current behavior of only one manual
-    bool disallow_trivial_move;  // Force actual compaction to run
-    const InternalKey* begin;    // nullptr means beginning of key range
-    const InternalKey* end;      // nullptr means end of key range
-    InternalKey* manual_end;     // how far we are compacting
-    InternalKey tmp_storage;     // Used to keep track of compaction progress
-    InternalKey tmp_storage1;    // Used to keep track of compaction progress
+    bool in_progress;             // compaction request being processed?
+    bool incomplete;              // only part of requested range compacted
+    bool exclusive;               // current behavior of only one manual
+    bool disallow_trivial_move;   // Force actual compaction to run
+    const InternalKey* begin;     // nullptr means beginning of key range
+    const InternalKey* end;       // nullptr means end of key range
+    InternalKey* manual_end;      // how far we are compacting
+    InternalKey tmp_storage;      // Used to keep track of compaction progress
+    InternalKey tmp_storage1;     // Used to keep track of compaction progress
+    std::atomic<bool>* canceled;  // Compaction canceled by the user?
   };
   struct PrepickedCompaction {
     // background compaction takes ownership of `compaction`.

db/db_impl/db_impl_compaction_flush.cc

@@ -7,6 +7,7 @@
 // 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 <deque>
 
 #include "db/builder.h"
 #include "db/db_impl/db_impl.h"
@@ -151,7 +152,6 @@ Status DBImpl::FlushMemTableToOutputFile(
   assert(cfd);
   assert(cfd->imm()->NumNotFlushed() != 0);
   assert(cfd->imm()->IsFlushPending());
-
   FlushJob flush_job(
       dbname_, cfd, immutable_db_options_, mutable_cf_options,
       port::kMaxUint64 /* memtable_id */, file_options_for_compaction_,
@@ -199,7 +199,7 @@ Status DBImpl::FlushMemTableToOutputFile(
     need_cancel = true;
   }
   TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:AfterPickMemtables");
-
+  bool switched_to_mempurge = false;
   // Within flush_job.Run, rocksdb may call event listener to notify
   // file creation and deletion.
   //
@@ -207,7 +207,8 @@ Status DBImpl::FlushMemTableToOutputFile(
   // and EventListener callback will be called when the db_mutex
   // is unlocked by the current thread.
   if (s.ok()) {
-    s = flush_job.Run(&logs_with_prep_tracker_, &file_meta);
+    s = flush_job.Run(&logs_with_prep_tracker_, &file_meta,
+                      &switched_to_mempurge);
     need_cancel = false;
   }
 
@@ -283,7 +284,9 @@ Status DBImpl::FlushMemTableToOutputFile(
     // from never needing it or ignoring the flush job status
     io_s.PermitUncheckedError();
   }
-  if (s.ok()) {
+  // If flush ran smoothly and no mempurge happened
+  // install new SST file path.
+  if (s.ok() && (!switched_to_mempurge)) {
 #ifndef ROCKSDB_LITE
     // may temporarily unlock and lock the mutex.
     NotifyOnFlushCompleted(cfd, mutable_cf_options,
@@ -408,10 +411,13 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
         stats_, &event_logger_, mutable_cf_options.report_bg_io_stats,
         false /* sync_output_directory */, false /* write_manifest */,
         thread_pri, io_tracer_, db_id_, db_session_id_,
-        cfd->GetFullHistoryTsLow()));
+        cfd->GetFullHistoryTsLow(), &blob_callback_));
   }
 
   std::vector<FileMetaData> file_meta(num_cfs);
+  // Use of deque<bool> because vector<bool>
+  // is specific and doesn't allow &v[i].
+  std::deque<bool> switched_to_mempurge(num_cfs, false);
   Status s;
   IOStatus log_io_s = IOStatus::OK();
   assert(num_cfs == static_cast<int>(jobs.size()));
@@ -461,10 +467,13 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
   }
 
   if (s.ok()) {
+    assert(switched_to_mempurge.size() ==
+           static_cast<long unsigned int>(num_cfs));
     // TODO (yanqin): parallelize jobs with threads.
     for (int i = 1; i != num_cfs; ++i) {
       exec_status[i].second =
-          jobs[i]->Run(&logs_with_prep_tracker_, &file_meta[i]);
+          jobs[i]->Run(&logs_with_prep_tracker_, &file_meta[i],
+                       &(switched_to_mempurge.at(i)));
       exec_status[i].first = true;
       io_status[i] = jobs[i]->io_status();
     }
@@ -476,8 +485,9 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     }
     assert(exec_status.size() > 0);
     assert(!file_meta.empty());
-    exec_status[0].second =
-        jobs[0]->Run(&logs_with_prep_tracker_, &file_meta[0]);
+    exec_status[0].second = jobs[0]->Run(
+        &logs_with_prep_tracker_, file_meta.data() /* &file_meta[0] */,
+        switched_to_mempurge.empty() ? nullptr : &(switched_to_mempurge.at(0)));
     exec_status[0].first = true;
     io_status[0] = jobs[0]->io_status();
 
@@ -591,6 +601,8 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     autovector<const autovector<MemTable*>*> mems_list;
     autovector<const MutableCFOptions*> mutable_cf_options_list;
     autovector<FileMetaData*> tmp_file_meta;
+    autovector<std::list<std::unique_ptr<FlushJobInfo>>*>
+        committed_flush_jobs_info;
     for (int i = 0; i != num_cfs; ++i) {
       const auto& mems = jobs[i]->GetMemTables();
       if (!cfds[i]->IsDropped() && !mems.empty()) {
@@ -598,13 +610,18 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
         mems_list.emplace_back(&mems);
         mutable_cf_options_list.emplace_back(&all_mutable_cf_options[i]);
         tmp_file_meta.emplace_back(&file_meta[i]);
+#ifndef ROCKSDB_LITE
+        committed_flush_jobs_info.emplace_back(
+            jobs[i]->GetCommittedFlushJobsInfo());
+#endif  //! ROCKSDB_LITE
       }
     }
 
     s = InstallMemtableAtomicFlushResults(
         nullptr /* imm_lists */, tmp_cfds, mutable_cf_options_list, mems_list,
         versions_.get(), &logs_with_prep_tracker_, &mutex_, tmp_file_meta,
-        &job_context->memtables_to_free, directories_.GetDbDir(), log_buffer);
+        committed_flush_jobs_info, &job_context->memtables_to_free,
+        directories_.GetDbDir(), log_buffer);
   }
 
   if (s.ok()) {
@@ -650,6 +667,11 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
         immutable_db_options_.sst_file_manager.get());
     assert(all_mutable_cf_options.size() == static_cast<size_t>(num_cfs));
     for (int i = 0; s.ok() && i != num_cfs; ++i) {
+      // If mempurge happened instead of Flush,
+      // no NotifyOnFlushCompleted call (no SST file created).
+      if (switched_to_mempurge[i]) {
+        continue;
+      }
       if (cfds[i]->IsDropped()) {
         continue;
       }
@@ -807,6 +829,10 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
     return Status::Incomplete(Status::SubCode::kManualCompactionPaused);
   }
 
+  if (options.canceled && options.canceled->load(std::memory_order_acquire)) {
+    return Status::Incomplete(Status::SubCode::kManualCompactionPaused);
+  }
+
   const Comparator* const ucmp = column_family->GetComparator();
   assert(ucmp);
   size_t ts_sz = ucmp->timestamp_size();
@@ -1253,8 +1279,8 @@ Status DBImpl::CompactFilesImpl(
       c->mutable_cf_options()->paranoid_file_checks,
       c->mutable_cf_options()->report_bg_io_stats, dbname_,
       &compaction_job_stats, Env::Priority::USER, io_tracer_,
-      &manual_compaction_paused_, db_id_, db_session_id_,
-      c->column_family_data()->GetFullHistoryTsLow());
+      &manual_compaction_paused_, nullptr, db_id_, db_session_id_,
+      c->column_family_data()->GetFullHistoryTsLow(), &blob_callback_);
 
   // Creating a compaction influences the compaction score because the score
   // takes running compactions into account (by skipping files that are already
@@ -1328,7 +1354,7 @@ Status DBImpl::CompactFilesImpl(
   if (output_file_names != nullptr) {
     for (const auto& newf : c->edit()->GetNewFiles()) {
       (*output_file_names)
-          .push_back(TableFileName(c->immutable_cf_options()->cf_paths,
+          .push_back(TableFileName(c->immutable_options()->cf_paths,
                                    newf.second.fd.GetNumber(),
                                    newf.second.fd.GetPathId()));
     }
@@ -1391,6 +1417,8 @@ void DBImpl::NotifyOnCompactionBegin(ColumnFamilyData* cfd, Compaction* c,
       manual_compaction_paused_.load(std::memory_order_acquire) > 0) {
     return;
   }
+
+  c->SetNotifyOnCompactionCompleted();
   Version* current = cfd->current();
   current->Ref();
   // release lock while notifying events
@@ -1426,10 +1454,11 @@ void DBImpl::NotifyOnCompactionCompleted(
   if (shutting_down_.load(std::memory_order_acquire)) {
     return;
   }
-  if (c->is_manual_compaction() &&
-      manual_compaction_paused_.load(std::memory_order_acquire) > 0) {
+
+  if (c->ShouldNotifyOnCompactionCompleted() == false) {
     return;
   }
+
   Version* current = cfd->current();
   current->Ref();
   // release lock while notifying events
@@ -1654,6 +1683,7 @@ Status DBImpl::RunManualCompaction(
   manual.incomplete = false;
   manual.exclusive = exclusive;
   manual.disallow_trivial_move = disallow_trivial_move;
+  manual.canceled = compact_range_options.canceled;
   // For universal compaction, we enforce every manual compaction to compact
   // all files.
   if (begin == nullptr ||
@@ -2390,6 +2420,17 @@ void DBImpl::SchedulePendingFlush(const FlushRequest& flush_req,
     assert(flush_req.size() == 1);
     ColumnFamilyData* cfd = flush_req[0].first;
     assert(cfd);
+    // Note: SchedulePendingFlush is always preceded
+    // with an imm()->FlushRequested() call. However,
+    // we want to make this code snipper more resilient to
+    // future changes. Therefore, we add the following if
+    // statement - note that calling it twice (or more)
+    // doesn't break anything.
+    if (immutable_db_options_.experimental_mempurge_threshold > 0.0) {
+      // If imm() contains silent memtables,
+      // requesting a flush will mark the imm_needed as true.
+      cfd->imm()->FlushRequested();
+    }
     if (!cfd->queued_for_flush() && cfd->imm()->IsFlushPending()) {
       cfd->Ref();
       cfd->set_queued_for_flush(true);
@@ -2531,6 +2572,11 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
 
     for (const auto& iter : flush_req) {
       ColumnFamilyData* cfd = iter.first;
+      if (immutable_db_options_.experimental_mempurge_threshold > 0.0) {
+        // If imm() contains silent memtables,
+        // requesting a flush will mark the imm_needed as true.
+        cfd->imm()->FlushRequested();
+      }
       if (cfd->IsDropped() || !cfd->imm()->IsFlushPending()) {
         // can't flush this CF, try next one
         column_families_not_to_flush.push_back(cfd);
@@ -2762,9 +2808,11 @@ void DBImpl::BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
 
     if (prepicked_compaction != nullptr &&
         prepicked_compaction->task_token != nullptr) {
-      // Releasing task tokens affects the DB state, so must be done before we
-      // potentially signal the DB close process to proceed below.
-      prepicked_compaction->task_token->ReleaseOnce();
+      // Releasing task tokens affects (and asserts on) the DB state, so
+      // must be done before we potentially signal the DB close process to
+      // proceed below.
+      prepicked_compaction->task_token.reset();
+      ;
     }
 
     if (made_progress ||
@@ -2819,6 +2867,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     } else if (is_manual &&
                manual_compaction_paused_.load(std::memory_order_acquire) > 0) {
       status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
+    } else if (is_manual && manual_compaction->canceled &&
+               manual_compaction->canceled->load(std::memory_order_acquire)) {
+      status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
     }
   } else {
     status = error_handler_.GetBGError();
@@ -2946,7 +2997,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
           c->column_family_data()
               ->current()
               ->storage_info()
-              ->ComputeCompactionScore(*(c->immutable_cf_options()),
+              ->ComputeCompactionScore(*(c->immutable_options()),
                                        *(c->mutable_cf_options()));
           AddToCompactionQueue(cfd);
           ++unscheduled_compactions_;
@@ -3140,8 +3191,10 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
         c->mutable_cf_options()->paranoid_file_checks,
         c->mutable_cf_options()->report_bg_io_stats, dbname_,
         &compaction_job_stats, thread_pri, io_tracer_,
-        is_manual ? &manual_compaction_paused_ : nullptr, db_id_,
-        db_session_id_, c->column_family_data()->GetFullHistoryTsLow());
+        is_manual ? &manual_compaction_paused_ : nullptr,
+        is_manual ? manual_compaction->canceled : nullptr, db_id_,
+        db_session_id_, c->column_family_data()->GetFullHistoryTsLow(),
+        &blob_callback_);
     compaction_job.Prepare();
 
     NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
@@ -3220,7 +3273,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       c->column_family_data()
           ->current()
           ->storage_info()
-          ->ComputeCompactionScore(*(c->immutable_cf_options()),
+          ->ComputeCompactionScore(*(c->immutable_options()),
                                    *(c->mutable_cf_options()));
       if (!cfd->queued_for_compaction()) {
         AddToCompactionQueue(cfd);
@@ -3385,7 +3438,7 @@ void DBImpl::BuildCompactionJobInfo(
     for (const auto fmd : *c->inputs(i)) {
       const FileDescriptor& desc = fmd->fd;
       const uint64_t file_number = desc.GetNumber();
-      auto fn = TableFileName(c->immutable_cf_options()->cf_paths, file_number,
+      auto fn = TableFileName(c->immutable_options()->cf_paths, file_number,
                               desc.GetPathId());
       compaction_job_info->input_files.push_back(fn);
       compaction_job_info->input_file_infos.push_back(CompactionFileInfo{
@@ -3404,7 +3457,7 @@ void DBImpl::BuildCompactionJobInfo(
     const FileDescriptor& desc = meta.fd;
     const uint64_t file_number = desc.GetNumber();
     compaction_job_info->output_files.push_back(TableFileName(
-        c->immutable_cf_options()->cf_paths, file_number, desc.GetPathId()));
+        c->immutable_options()->cf_paths, file_number, desc.GetPathId()));
     compaction_job_info->output_file_infos.push_back(CompactionFileInfo{
         newf.first, file_number, meta.oldest_blob_file_number});
   }
@@ -3440,7 +3493,7 @@ void DBImpl::InstallSuperVersionAndScheduleWork(
   if (UNLIKELY(sv_context->new_superversion == nullptr)) {
     sv_context->NewSuperVersion();
   }
-  cfd->InstallSuperVersion(sv_context, &mutex_, mutable_cf_options);
+  cfd->InstallSuperVersion(sv_context, mutable_cf_options);
 
   // There may be a small data race here. The snapshot tricking bottommost
   // compaction may already be released here. But assuming there will always be

db/db_impl/db_impl_debug.cc

@@ -43,7 +43,7 @@ bool DBImpl::TEST_WALBufferIsEmpty(bool lock) {
   return res;
 }
 
-int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
+uint64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
     ColumnFamilyHandle* column_family) {
   ColumnFamilyData* cfd;
   if (column_family == nullptr) {
@@ -58,7 +58,8 @@ int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
 
 void DBImpl::TEST_GetFilesMetaData(
     ColumnFamilyHandle* column_family,
-    std::vector<std::vector<FileMetaData>>* metadata) {
+    std::vector<std::vector<FileMetaData>>* metadata,
+    std::vector<std::shared_ptr<BlobFileMetaData>>* blob_metadata) {
   auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
   auto cfd = cfh->cfd();
   InstrumentedMutexLock l(&mutex_);
@@ -72,6 +73,12 @@ void DBImpl::TEST_GetFilesMetaData(
       (*metadata)[level].push_back(*f);
     }
   }
+  if (blob_metadata != nullptr) {
+    blob_metadata->clear();
+    for (const auto& blob : cfd->current()->storage_info()->GetBlobFiles()) {
+      blob_metadata->push_back(blob.second);
+    }
+  }
 }
 
 uint64_t DBImpl::TEST_Current_Manifest_FileNo() {

db/db_impl/db_impl_files.cc

@@ -38,20 +38,26 @@ uint64_t DBImpl::MinObsoleteSstNumberToKeep() {
 }
 
 Status DBImpl::DisableFileDeletions() {
-  InstrumentedMutexLock l(&mutex_);
-  return DisableFileDeletionsWithLock();
+  Status s;
+  int my_disable_delete_obsolete_files;
+  {
+    InstrumentedMutexLock l(&mutex_);
+    s = DisableFileDeletionsWithLock();
+    my_disable_delete_obsolete_files = disable_delete_obsolete_files_;
+  }
+  if (my_disable_delete_obsolete_files == 1) {
+    ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Disabled");
+  } else {
+    ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                   "File Deletions Disabled, but already disabled. Counter: %d",
+                   my_disable_delete_obsolete_files);
+  }
+  return s;
 }
 
 Status DBImpl::DisableFileDeletionsWithLock() {
   mutex_.AssertHeld();
   ++disable_delete_obsolete_files_;
-  if (disable_delete_obsolete_files_ == 1) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Disabled");
-  } else {
-    ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                   "File Deletions Disabled, but already disabled. Counter: %d",
-                   disable_delete_obsolete_files_);
-  }
   return Status::OK();
 }
 
@@ -215,7 +221,8 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     }
 
     // Add log files in wal_dir
-    if (immutable_db_options_.wal_dir != dbname_) {
+
+    if (!immutable_db_options_.IsWalDirSameAsDBPath(dbname_)) {
       std::vector<std::string> log_files;
       Status s = env_->GetChildren(immutable_db_options_.wal_dir, &log_files);
       s.PermitUncheckedError();  // TODO: What should we do on error?
@@ -395,10 +402,10 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
                                  blob_file.GetPath());
   }
 
+  auto wal_dir = immutable_db_options_.GetWalDir();
   for (auto file_num : state.log_delete_files) {
     if (file_num > 0) {
-      candidate_files.emplace_back(LogFileName(file_num),
-                                   immutable_db_options_.wal_dir);
+      candidate_files.emplace_back(LogFileName(file_num), wal_dir);
     }
   }
   for (const auto& filename : state.manifest_delete_files) {
@@ -517,12 +524,6 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
         break;
       case kOptionsFile:
         keep = (number >= optsfile_num2);
-        TEST_SYNC_POINT_CALLBACK(
-            "DBImpl::PurgeObsoleteFiles:CheckOptionsFiles:1",
-            reinterpret_cast<void*>(&number));
-        TEST_SYNC_POINT_CALLBACK(
-            "DBImpl::PurgeObsoleteFiles:CheckOptionsFiles:2",
-            reinterpret_cast<void*>(&keep));
         break;
       case kCurrentFile:
       case kDBLockFile:
@@ -547,8 +548,7 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
       fname = BlobFileName(candidate_file.file_path, number);
       dir_to_sync = candidate_file.file_path;
     } else {
-      dir_to_sync =
-          (type == kWalFile) ? immutable_db_options_.wal_dir : dbname_;
+      dir_to_sync = (type == kWalFile) ? wal_dir : dbname_;
       fname = dir_to_sync +
               ((!dir_to_sync.empty() && dir_to_sync.back() == '/') ||
                        (!to_delete.empty() && to_delete.front() == '/')

db/db_impl/db_impl_open.cc

@@ -111,16 +111,28 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src,
     result.recycle_log_file_num = 0;
   }
 
-  if (result.wal_dir.empty()) {
+  if (result.db_paths.size() == 0) {
+    result.db_paths.emplace_back(dbname, std::numeric_limits<uint64_t>::max());
+  } else if (result.wal_dir.empty()) {
     // Use dbname as default
     result.wal_dir = dbname;
   }
-  if (result.wal_dir.back() == '/') {
-    result.wal_dir = result.wal_dir.substr(0, result.wal_dir.size() - 1);
+  if (!result.wal_dir.empty()) {
+    // If there is a wal_dir already set, check to see if the wal_dir is the
+    // same as the dbname AND the same as the db_path[0] (which must exist from
+    // a few lines ago). If the wal_dir matches both of these values, then clear
+    // the wal_dir value, which will make wal_dir == dbname.  Most likely this
+    // condition was the result of reading an old options file where we forced
+    // wal_dir to be set (to dbname).
+    auto npath = NormalizePath(dbname + "/");
+    if (npath == NormalizePath(result.wal_dir + "/") &&
+        npath == NormalizePath(result.db_paths[0].path + "/")) {
+      result.wal_dir.clear();
+    }
   }
 
-  if (result.db_paths.size() == 0) {
-    result.db_paths.emplace_back(dbname, std::numeric_limits<uint64_t>::max());
+  if (!result.wal_dir.empty() && result.wal_dir.back() == '/') {
+    result.wal_dir = result.wal_dir.substr(0, result.wal_dir.size() - 1);
   }
 
   if (result.use_direct_reads && result.compaction_readahead_size == 0) {
@@ -141,7 +153,7 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src,
 
 #ifndef ROCKSDB_LITE
   ImmutableDBOptions immutable_db_options(result);
-  if (!IsWalDirSameAsDBPath(&immutable_db_options)) {
+  if (!immutable_db_options.IsWalDirSameAsDBPath()) {
     // Either the WAL dir and db_paths[0]/db_name are not the same, or we
     // cannot tell for sure. In either case, assume they're different and
     // explicitly cleanup the trash log files (bypass DeleteScheduler)
@@ -149,13 +161,14 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src,
     // DeleteScheduler::CleanupDirectory on the same dir later, it will be
     // safe
     std::vector<std::string> filenames;
-    Status s = result.env->GetChildren(result.wal_dir, &filenames);
+    auto wal_dir = immutable_db_options.GetWalDir();
+    Status s = result.env->GetChildren(wal_dir, &filenames);
     s.PermitUncheckedError();  //**TODO: What to do on error?
     for (std::string& filename : filenames) {
       if (filename.find(".log.trash", filename.length() -
                                           std::string(".log.trash").length()) !=
           std::string::npos) {
-        std::string trash_file = result.wal_dir + "/" + filename;
+        std::string trash_file = wal_dir + "/" + filename;
         result.env->DeleteFile(trash_file).PermitUncheckedError();
       }
     }
@@ -300,7 +313,8 @@ Status DBImpl::NewDB(std::vector<std::string>* new_filenames) {
     std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
         std::move(file), manifest, file_options, immutable_db_options_.clock,
         io_tracer_, nullptr /* stats */, immutable_db_options_.listeners,
-        nullptr, tmp_set.Contains(FileType::kDescriptorFile)));
+        nullptr, tmp_set.Contains(FileType::kDescriptorFile),
+        tmp_set.Contains(FileType::kDescriptorFile)));
     log::Writer log(std::move(file_writer), 0, false);
     std::string record;
     new_db.EncodeTo(&record);
@@ -542,12 +556,12 @@ Status DBImpl::Recover(
     // Note that prev_log_number() is no longer used, but we pay
     // attention to it in case we are recovering a database
     // produced by an older version of rocksdb.
+    auto wal_dir = immutable_db_options_.GetWalDir();
     if (!immutable_db_options_.best_efforts_recovery) {
-      s = env_->GetChildren(immutable_db_options_.wal_dir, &files_in_wal_dir);
+      s = env_->GetChildren(wal_dir, &files_in_wal_dir);
     }
     if (s.IsNotFound()) {
-      return Status::InvalidArgument("wal_dir not found",
-                                     immutable_db_options_.wal_dir);
+      return Status::InvalidArgument("wal_dir not found", wal_dir);
     } else if (!s.ok()) {
       return s;
     }
@@ -563,8 +577,7 @@ Status DBImpl::Recover(
               "existing log file: ",
               file);
         } else {
-          wal_files[number] =
-              LogFileName(immutable_db_options_.wal_dir, number);
+          wal_files[number] = LogFileName(wal_dir, number);
         }
       }
     }
@@ -644,7 +657,7 @@ Status DBImpl::Recover(
     if (s.ok()) {
       const std::string normalized_dbname = NormalizePath(dbname_);
       const std::string normalized_wal_dir =
-          NormalizePath(immutable_db_options_.wal_dir);
+          NormalizePath(immutable_db_options_.GetWalDir());
       if (immutable_db_options_.best_efforts_recovery) {
         filenames = std::move(files_in_dbname);
       } else if (normalized_dbname == normalized_wal_dir) {
@@ -849,7 +862,8 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
     // update the file number allocation counter in VersionSet.
     versions_->MarkFileNumberUsed(wal_number);
     // Open the log file
-    std::string fname = LogFileName(immutable_db_options_.wal_dir, wal_number);
+    std::string fname =
+        LogFileName(immutable_db_options_.GetWalDir(), wal_number);
 
     ROCKS_LOG_INFO(immutable_db_options_.info_log,
                    "Recovering log #%" PRIu64 " mode %d", wal_number,
@@ -1259,7 +1273,8 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
       // If there's no data in the WAL, or we flushed all the data, still
       // truncate the log file. If the process goes into a crash loop before
       // the file is deleted, the preallocated space will never get freed.
-      GetLogSizeAndMaybeTruncate(wal_numbers.back(), true, nullptr)
+      const bool truncate = !read_only;
+      GetLogSizeAndMaybeTruncate(wal_numbers.back(), truncate, nullptr)
           .PermitUncheckedError();
     }
   }
@@ -1273,7 +1288,8 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
 Status DBImpl::GetLogSizeAndMaybeTruncate(uint64_t wal_number, bool truncate,
                                           LogFileNumberSize* log_ptr) {
   LogFileNumberSize log(wal_number);
-  std::string fname = LogFileName(immutable_db_options_.wal_dir, wal_number);
+  std::string fname =
+      LogFileName(immutable_db_options_.GetWalDir(), wal_number);
   Status s;
   // This gets the appear size of the wals, not including preallocated space.
   s = env_->GetFileSize(fname, &log.size);
@@ -1292,7 +1308,7 @@ Status DBImpl::GetLogSizeAndMaybeTruncate(uint64_t wal_number, bool truncate,
       truncate_status = last_log->Close(IOOptions(), nullptr);
     }
     // Not a critical error if fail to truncate.
-    if (!truncate_status.ok()) {
+    if (!truncate_status.ok() && !truncate_status.IsNotSupported()) {
       ROCKS_LOG_WARN(immutable_db_options_.info_log,
                      "Failed to truncate log #%" PRIu64 ": %s", wal_number,
                      truncate_status.ToString().c_str());
@@ -1401,7 +1417,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
           0 /* level */, false /* is_bottommost */,
           TableFileCreationReason::kRecovery, current_time,
           0 /* oldest_key_time */, 0 /* file_creation_time */, db_id_,
-          db_session_id_, 0 /* target_file_size */);
+          db_session_id_, 0 /* target_file_size */, meta.fd.GetNumber());
       s = BuildTable(
           dbname_, versions_.get(), immutable_db_options_, tboptions,
           file_options_for_compaction_, cfd->table_cache(), iter.get(),
@@ -1418,8 +1434,10 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                       meta.fd.GetFileSize(), s.ToString().c_str());
       mutex_.Lock();
 
-      io_s.PermitUncheckedError();  // TODO(AR) is this correct, or should we
-                                    // return io_s if not ok()?
+      // TODO(AR) is this ok?
+      if (!io_s.ok() && s.ok()) {
+        s = io_s;
+      }
     }
   }
   ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
@@ -1513,15 +1531,14 @@ IOStatus DBImpl::CreateWAL(uint64_t log_file_num, uint64_t recycle_log_number,
       BuildDBOptions(immutable_db_options_, mutable_db_options_);
   FileOptions opt_file_options =
       fs_->OptimizeForLogWrite(file_options_, db_options);
-  std::string log_fname =
-      LogFileName(immutable_db_options_.wal_dir, log_file_num);
+  std::string wal_dir = immutable_db_options_.GetWalDir();
+  std::string log_fname = LogFileName(wal_dir, log_file_num);
 
   if (recycle_log_number) {
     ROCKS_LOG_INFO(immutable_db_options_.info_log,
                    "reusing log %" PRIu64 " from recycle list\n",
                    recycle_log_number);
-    std::string old_log_fname =
-        LogFileName(immutable_db_options_.wal_dir, recycle_log_number);
+    std::string old_log_fname = LogFileName(wal_dir, recycle_log_number);
     TEST_SYNC_POINT("DBImpl::CreateWAL:BeforeReuseWritableFile1");
     TEST_SYNC_POINT("DBImpl::CreateWAL:BeforeReuseWritableFile2");
     io_s = fs_->ReuseWritableFile(log_fname, old_log_fname, opt_file_options,
@@ -1539,7 +1556,8 @@ IOStatus DBImpl::CreateWAL(uint64_t log_file_num, uint64_t recycle_log_number,
     std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
         std::move(lfile), log_fname, opt_file_options,
         immutable_db_options_.clock, io_tracer_, nullptr /* stats */, listeners,
-        nullptr, tmp_set.Contains(FileType::kWalFile)));
+        nullptr, tmp_set.Contains(FileType::kWalFile),
+        tmp_set.Contains(FileType::kWalFile)));
     *new_log = new log::Writer(std::move(file_writer), log_file_num,
                                immutable_db_options_.recycle_log_file_num > 0,
                                immutable_db_options_.manual_wal_flush);
@@ -1571,7 +1589,7 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
   }
 
   DBImpl* impl = new DBImpl(db_options, dbname, seq_per_batch, batch_per_txn);
-  s = impl->env_->CreateDirIfMissing(impl->immutable_db_options_.wal_dir);
+  s = impl->env_->CreateDirIfMissing(impl->immutable_db_options_.GetWalDir());
   if (s.ok()) {
     std::vector<std::string> paths;
     for (auto& db_path : impl->immutable_db_options_.db_paths) {
@@ -1603,7 +1621,7 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
     return s;
   }
 
-  impl->wal_in_db_path_ = IsWalDirSameAsDBPath(&impl->immutable_db_options_);
+  impl->wal_in_db_path_ = impl->immutable_db_options_.IsWalDirSameAsDBPath();
 
   impl->mutex_.Lock();
   // Handles create_if_missing, error_if_exists
@@ -1670,6 +1688,7 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
 
       impl->DeleteObsoleteFiles();
       s = impl->directories_.GetDbDir()->Fsync(IOOptions(), nullptr);
+      TEST_SYNC_POINT("DBImpl::Open:AfterDeleteFilesAndSyncDir");
     }
     if (s.ok()) {
       // In WritePrepared there could be gap in sequence numbers. This breaks

db/db_impl/db_impl_secondary.cc

@@ -41,6 +41,9 @@ Status DBImplSecondary::Recover(
           ->Recover(column_families, &manifest_reader_, &manifest_reporter_,
                     &manifest_reader_status_);
   if (!s.ok()) {
+    if (manifest_reader_status_) {
+      manifest_reader_status_->PermitUncheckedError();
+    }
     return s;
   }
   if (immutable_db_options_.paranoid_checks && s.ok()) {
@@ -97,10 +100,10 @@ Status DBImplSecondary::FindNewLogNumbers(std::vector<uint64_t>* logs) {
   assert(logs != nullptr);
   std::vector<std::string> filenames;
   Status s;
-  s = env_->GetChildren(immutable_db_options_.wal_dir, &filenames);
+  s = env_->GetChildren(immutable_db_options_.GetWalDir(), &filenames);
   if (s.IsNotFound()) {
     return Status::InvalidArgument("Failed to open wal_dir",
-                                   immutable_db_options_.wal_dir);
+                                   immutable_db_options_.GetWalDir());
   } else if (!s.ok()) {
     return s;
   }
@@ -140,7 +143,8 @@ Status DBImplSecondary::MaybeInitLogReader(
     // initialize log reader from log_number
     // TODO: min_log_number_to_keep_2pc check needed?
     // Open the log file
-    std::string fname = LogFileName(immutable_db_options_.wal_dir, log_number);
+    std::string fname =
+        LogFileName(immutable_db_options_.GetWalDir(), log_number);
     ROCKS_LOG_INFO(immutable_db_options_.info_log,
                    "Recovering log #%" PRIu64 " mode %d", log_number,
                    static_cast<int>(immutable_db_options_.wal_recovery_mode));
@@ -627,7 +631,7 @@ Status DB::OpenAsSecondary(
       &impl->write_controller_, impl->io_tracer_));
   impl->column_family_memtables_.reset(
       new ColumnFamilyMemTablesImpl(impl->versions_->GetColumnFamilySet()));
-  impl->wal_in_db_path_ = IsWalDirSameAsDBPath(&impl->immutable_db_options_);
+  impl->wal_in_db_path_ = impl->immutable_db_options_.IsWalDirSameAsDBPath();
 
   impl->mutex_.Lock();
   s = impl->Recover(column_families, true, false, false);
@@ -767,6 +771,7 @@ Status DB::OpenAndCompact(
   compaction_input.db_options.env = override_options.env;
   compaction_input.db_options.file_checksum_gen_factory =
       override_options.file_checksum_gen_factory;
+  compaction_input.db_options.statistics = override_options.statistics;
   compaction_input.column_family.options.comparator =
       override_options.comparator;
   compaction_input.column_family.options.merge_operator =

db/db_impl/db_impl_secondary.h

@@ -278,6 +278,16 @@ class DBImplSecondary : public DBImpl {
       return AddColumnFamilyId(column_family_id);
     }
 
+    Status MarkBeginPrepare(bool) override { return Status::OK(); }
+
+    Status MarkEndPrepare(const Slice&) override { return Status::OK(); }
+
+    Status MarkRollback(const Slice&) override { return Status::OK(); }
+
+    Status MarkCommit(const Slice&) override { return Status::OK(); }
+
+    Status MarkNoop(bool) override { return Status::OK(); }
+
     const std::unordered_set<uint32_t>& column_families() const {
       return column_family_ids_;
     }

db/db_impl/db_impl_write.cc

@@ -220,7 +220,8 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
 
   bool need_log_sync = write_options.sync;
   bool need_log_dir_sync = need_log_sync && !log_dir_synced_;
-  if (!two_write_queues_ || !disable_memtable) {
+  assert(!two_write_queues_ || !disable_memtable);
+  {
     // With concurrent writes we do preprocess only in the write thread that
     // also does write to memtable to avoid sync issue on shared data structure
     // with the other thread
@@ -251,6 +252,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
       write_thread_.EnterAsBatchGroupLeader(&w, &write_group);
 
   IOStatus io_s;
+  Status pre_release_cb_status;
   if (status.ok()) {
     // Rules for when we can update the memtable concurrently
     // 1. supported by memtable
@@ -361,7 +363,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
               writer->sequence, disable_memtable, writer->log_used, index++,
               pre_release_callback_cnt);
           if (!ws.ok()) {
-            status = ws;
+            status = pre_release_cb_status = ws;
             break;
           }
         }
@@ -414,10 +416,13 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
 
   if (!w.CallbackFailed()) {
     if (!io_s.ok()) {
+      assert(pre_release_cb_status.ok());
       IOStatusCheck(io_s);
     } else {
-      WriteStatusCheck(status);
+      WriteStatusCheck(pre_release_cb_status);
     }
+  } else {
+    assert(io_s.ok() && pre_release_cb_status.ok());
   }
 
   if (need_log_sync) {
@@ -1647,12 +1652,7 @@ Status DBImpl::TrimMemtableHistory(WriteContext* context) {
   for (auto& cfd : cfds) {
     autovector<MemTable*> to_delete;
     bool trimmed = cfd->imm()->TrimHistory(
-        &to_delete, cfd->mem()->ApproximateMemoryUsage());
-    if (!to_delete.empty()) {
-      for (auto m : to_delete) {
-        delete m;
-      }
-    }
+        &context->memtables_to_free_, cfd->mem()->ApproximateMemoryUsage());
     if (trimmed) {
       context->superversion_context.NewSuperVersion();
       assert(context->superversion_context.new_superversion.get() != nullptr);
@@ -1911,6 +1911,8 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
       for (auto cf : empty_cfs) {
         if (cf->IsEmpty()) {
           cf->SetLogNumber(logfile_number_);
+          // MEMPURGE: No need to change this, because new adds
+          // should still receive new sequence numbers.
           cf->mem()->SetCreationSeq(versions_->LastSequence());
         }  // cf may become non-empty.
       }
@@ -1933,11 +1935,13 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
   }
 
   cfd->mem()->SetNextLogNumber(logfile_number_);
+  assert(new_mem != nullptr);
   cfd->imm()->Add(cfd->mem(), &context->memtables_to_free_);
   new_mem->Ref();
   cfd->SetMemtable(new_mem);
   InstallSuperVersionAndScheduleWork(cfd, &context->superversion_context,
                                      mutable_cf_options);
+
 #ifndef ROCKSDB_LITE
   mutex_.Unlock();
   // Notify client that memtable is sealed, now that we have successfully

db/db_info_dumper.cc

@@ -109,31 +109,30 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
   }
 
   // Get wal file in wal_dir
-  if (dbname.compare(options.wal_dir) != 0) {
-    if (!env->GetChildren(options.wal_dir, &files).ok()) {
-      Error(options.info_log,
-          "Error when reading %s dir\n",
-          options.wal_dir.c_str());
+  const auto& wal_dir = options.GetWalDir(dbname);
+  if (!options.IsWalDirSameAsDBPath(dbname)) {
+    if (!env->GetChildren(wal_dir, &files).ok()) {
+      Error(options.info_log, "Error when reading %s dir\n", wal_dir.c_str());
       return;
     }
     wal_info.clear();
     for (const std::string& file : files) {
       if (ParseFileName(file, &number, &type)) {
         if (type == kWalFile) {
-          if (env->GetFileSize(options.wal_dir + "/" + file, &file_size).ok()) {
+          if (env->GetFileSize(wal_dir + "/" + file, &file_size).ok()) {
             wal_info.append(file)
                 .append(" size: ")
                 .append(std::to_string(file_size))
                 .append(" ; ");
           } else {
             Error(options.info_log, "Error when reading LOG file %s/%s\n",
-                  options.wal_dir.c_str(), file.c_str());
+                  wal_dir.c_str(), file.c_str());
           }
         }
       }
     }
   }
-  Header(options.info_log, "Write Ahead Log file in %s: %s\n",
-         options.wal_dir.c_str(), wal_info.c_str());
+  Header(options.info_log, "Write Ahead Log file in %s: %s\n", wal_dir.c_str(),
+         wal_info.c_str());
 }
 }  // namespace ROCKSDB_NAMESPACE

db/db_inplace_update_test.cc

@@ -14,7 +14,7 @@ namespace ROCKSDB_NAMESPACE {
 class DBTestInPlaceUpdate : public DBTestBase {
  public:
   DBTestInPlaceUpdate()
-      : DBTestBase("/db_inplace_update_test", /*env_do_fsync=*/true) {}
+      : DBTestBase("db_inplace_update_test", /*env_do_fsync=*/true) {}
 };
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdate) {

db/db_io_failure_test.cc

@@ -15,8 +15,7 @@ namespace ROCKSDB_NAMESPACE {
 
 class DBIOFailureTest : public DBTestBase {
  public:
-  DBIOFailureTest()
-      : DBTestBase("/db_io_failure_test", /*env_do_fsync=*/true) {}
+  DBIOFailureTest() : DBTestBase("db_io_failure_test", /*env_do_fsync=*/true) {}
 };
 
 #ifndef ROCKSDB_LITE

db/db_iter.cc

@@ -36,7 +36,7 @@
 namespace ROCKSDB_NAMESPACE {
 
 DBIter::DBIter(Env* _env, const ReadOptions& read_options,
-               const ImmutableOptions& cf_options,
+               const ImmutableOptions& ioptions,
                const MutableCFOptions& mutable_cf_options,
                const Comparator* cmp, InternalIterator* iter,
                const Version* version, SequenceNumber s, bool arena_mode,
@@ -45,15 +45,15 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
                ColumnFamilyData* cfd, bool expose_blob_index)
     : prefix_extractor_(mutable_cf_options.prefix_extractor.get()),
       env_(_env),
-      clock_(cf_options.clock),
-      logger_(cf_options.logger),
+      clock_(ioptions.clock),
+      logger_(ioptions.logger),
       user_comparator_(cmp),
-      merge_operator_(cf_options.merge_operator.get()),
+      merge_operator_(ioptions.merge_operator.get()),
       iter_(iter),
       version_(version),
       read_callback_(read_callback),
       sequence_(s),
-      statistics_(cf_options.stats),
+      statistics_(ioptions.stats),
       max_skip_(max_sequential_skip_in_iterations),
       max_skippable_internal_keys_(read_options.max_skippable_internal_keys),
       num_internal_keys_skipped_(0),
@@ -75,7 +75,7 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
       expose_blob_index_(expose_blob_index),
       is_blob_(false),
       arena_mode_(arena_mode),
-      range_del_agg_(&cf_options.internal_comparator, s),
+      range_del_agg_(&ioptions.internal_comparator, s),
       db_impl_(db_impl),
       cfd_(cfd),
       start_seqnum_(read_options.iter_start_seqnum),
@@ -576,12 +576,8 @@ bool DBIter::MergeValuesNewToOld() {
       // hit a put, merge the put value with operands and store the
       // final result in saved_value_. We are done!
       const Slice val = iter_.value();
-      Status s = MergeHelper::TimedFullMerge(
-          merge_operator_, ikey.user_key, &val, merge_context_.GetOperands(),
-          &saved_value_, logger_, statistics_, clock_, &pinned_value_, true);
+      Status s = Merge(&val, ikey.user_key);
       if (!s.ok()) {
-        valid_ = false;
-        status_ = s;
         return false;
       }
       // iter_ is positioned after put
@@ -598,9 +594,31 @@ bool DBIter::MergeValuesNewToOld() {
           iter_.value(), iter_.iter()->IsValuePinned() /* operand_pinned */);
       PERF_COUNTER_ADD(internal_merge_count, 1);
     } else if (kTypeBlobIndex == ikey.type) {
-      status_ = Status::NotSupported("BlobDB does not support merge operator.");
-      valid_ = false;
-      return false;
+      if (expose_blob_index_) {
+        status_ =
+            Status::NotSupported("BlobDB does not support merge operator.");
+        valid_ = false;
+        return false;
+      }
+      // hit a put, merge the put value with operands and store the
+      // final result in saved_value_. We are done!
+      if (!SetBlobValueIfNeeded(ikey.user_key, iter_.value())) {
+        return false;
+      }
+      valid_ = true;
+      const Slice blob_value = value();
+      Status s = Merge(&blob_value, ikey.user_key);
+      if (!s.ok()) {
+        return false;
+      }
+      is_blob_ = false;
+      // iter_ is positioned after put
+      iter_.Next();
+      if (!iter_.status().ok()) {
+        valid_ = false;
+        return false;
+      }
+      return true;
     } else {
       valid_ = false;
       status_ = Status::Corruption(
@@ -619,16 +637,10 @@ bool DBIter::MergeValuesNewToOld() {
   // a deletion marker.
   // feed null as the existing value to the merge operator, such that
   // client can differentiate this scenario and do things accordingly.
-  Status s = MergeHelper::TimedFullMerge(
-      merge_operator_, saved_key_.GetUserKey(), nullptr,
-      merge_context_.GetOperands(), &saved_value_, logger_, statistics_, clock_,
-      &pinned_value_, true);
+  Status s = Merge(nullptr, saved_key_.GetUserKey());
   if (!s.ok()) {
-    valid_ = false;
-    status_ = s;
     return false;
   }
-
   assert(status_.ok());
   return true;
 }
@@ -931,21 +943,36 @@ bool DBIter::FindValueForCurrentKey() {
       if (last_not_merge_type == kTypeDeletion ||
           last_not_merge_type == kTypeSingleDeletion ||
           last_not_merge_type == kTypeRangeDeletion) {
-        s = MergeHelper::TimedFullMerge(
-            merge_operator_, saved_key_.GetUserKey(), nullptr,
-            merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
-            clock_, &pinned_value_, true);
+        s = Merge(nullptr, saved_key_.GetUserKey());
+        if (!s.ok()) {
+          return false;
+        }
+        return true;
       } else if (last_not_merge_type == kTypeBlobIndex) {
-        status_ =
-            Status::NotSupported("BlobDB does not support merge operator.");
-        valid_ = false;
-        return false;
+        if (expose_blob_index_) {
+          status_ =
+              Status::NotSupported("BlobDB does not support merge operator.");
+          valid_ = false;
+          return false;
+        }
+        if (!SetBlobValueIfNeeded(saved_key_.GetUserKey(), pinned_value_)) {
+          return false;
+        }
+        valid_ = true;
+        const Slice blob_value = value();
+        s = Merge(&blob_value, saved_key_.GetUserKey());
+        if (!s.ok()) {
+          return false;
+        }
+        is_blob_ = false;
+        return true;
       } else {
         assert(last_not_merge_type == kTypeValue);
-        s = MergeHelper::TimedFullMerge(
-            merge_operator_, saved_key_.GetUserKey(), &pinned_value_,
-            merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
-            clock_, &pinned_value_, true);
+        s = Merge(&pinned_value_, saved_key_.GetUserKey());
+        if (!s.ok()) {
+          return false;
+        }
+        return true;
       }
       break;
     case kTypeValue:
@@ -955,7 +982,6 @@ bool DBIter::FindValueForCurrentKey() {
       if (!SetBlobValueIfNeeded(saved_key_.GetUserKey(), pinned_value_)) {
         return false;
       }
-
       break;
     default:
       valid_ = false;
@@ -1095,25 +1121,33 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
 
     if (ikey.type == kTypeValue) {
       const Slice val = iter_.value();
-      Status s = MergeHelper::TimedFullMerge(
-          merge_operator_, saved_key_.GetUserKey(), &val,
-          merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
-          clock_, &pinned_value_, true);
+      Status s = Merge(&val, saved_key_.GetUserKey());
       if (!s.ok()) {
-        valid_ = false;
-        status_ = s;
         return false;
       }
-      valid_ = true;
       return true;
     } else if (ikey.type == kTypeMerge) {
       merge_context_.PushOperand(
           iter_.value(), iter_.iter()->IsValuePinned() /* operand_pinned */);
       PERF_COUNTER_ADD(internal_merge_count, 1);
     } else if (ikey.type == kTypeBlobIndex) {
-      status_ = Status::NotSupported("BlobDB does not support merge operator.");
-      valid_ = false;
-      return false;
+      if (expose_blob_index_) {
+        status_ =
+            Status::NotSupported("BlobDB does not support merge operator.");
+        valid_ = false;
+        return false;
+      }
+      if (!SetBlobValueIfNeeded(ikey.user_key, iter_.value())) {
+        return false;
+      }
+      valid_ = true;
+      const Slice blob_value = value();
+      Status s = Merge(&blob_value, saved_key_.GetUserKey());
+      if (!s.ok()) {
+        return false;
+      }
+      is_blob_ = false;
+      return true;
     } else {
       valid_ = false;
       status_ = Status::Corruption(
@@ -1123,13 +1157,8 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
     }
   }
 
-  Status s = MergeHelper::TimedFullMerge(
-      merge_operator_, saved_key_.GetUserKey(), nullptr,
-      merge_context_.GetOperands(), &saved_value_, logger_, statistics_, clock_,
-      &pinned_value_, true);
+  Status s = Merge(nullptr, saved_key_.GetUserKey());
   if (!s.ok()) {
-    valid_ = false;
-    status_ = s;
     return false;
   }
 
@@ -1152,6 +1181,19 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
   return true;
 }
 
+Status DBIter::Merge(const Slice* val, const Slice& user_key) {
+  Status s = MergeHelper::TimedFullMerge(
+      merge_operator_, user_key, val, merge_context_.GetOperands(),
+      &saved_value_, logger_, statistics_, clock_, &pinned_value_, true);
+  if (!s.ok()) {
+    valid_ = false;
+    status_ = s;
+    return s;
+  }
+  valid_ = true;
+  return s;
+}
+
 // Move backwards until the key smaller than saved_key_.
 // Changes valid_ only if return value is false.
 bool DBIter::FindUserKeyBeforeSavedKey() {
@@ -1536,7 +1578,7 @@ void DBIter::SeekToLast() {
 }
 
 Iterator* NewDBIterator(Env* env, const ReadOptions& read_options,
-                        const ImmutableOptions& cf_options,
+                        const ImmutableOptions& ioptions,
                         const MutableCFOptions& mutable_cf_options,
                         const Comparator* user_key_comparator,
                         InternalIterator* internal_iter, const Version* version,
@@ -1545,7 +1587,7 @@ Iterator* NewDBIterator(Env* env, const ReadOptions& read_options,
                         ReadCallback* read_callback, DBImpl* db_impl,
                         ColumnFamilyData* cfd, bool expose_blob_index) {
   DBIter* db_iter =
-      new DBIter(env, read_options, cf_options, mutable_cf_options,
+      new DBIter(env, read_options, ioptions, mutable_cf_options,
                  user_key_comparator, internal_iter, version, sequence, false,
                  max_sequential_skip_in_iterations, read_callback, db_impl, cfd,
                  expose_blob_index);

db/db_iter.h

@@ -114,7 +114,7 @@ class DBIter final : public Iterator {
   };
 
   DBIter(Env* _env, const ReadOptions& read_options,
-         const ImmutableOptions& cf_options,
+         const ImmutableOptions& ioptions,
          const MutableCFOptions& mutable_cf_options, const Comparator* cmp,
          InternalIterator* iter, const Version* version, SequenceNumber s,
          bool arena_mode, uint64_t max_sequential_skip_in_iterations,
@@ -299,6 +299,8 @@ class DBIter final : public Iterator {
   // index when using the integrated BlobDB implementation.
   bool SetBlobValueIfNeeded(const Slice& user_key, const Slice& blob_index);
 
+  Status Merge(const Slice* val, const Slice& user_key);
+
   const SliceTransform* prefix_extractor_;
   Env* const env_;
   SystemClock* clock_;
@@ -383,8 +385,7 @@ class DBIter final : public Iterator {
 // "*internal_iter") that were live at the specified `sequence` number
 // into appropriate user keys.
 extern Iterator* NewDBIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableOptions& cf_options,
+    Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options,
     const Comparator* user_key_comparator, InternalIterator* internal_iter,
     const Version* version, const SequenceNumber& sequence,

db/db_iter_test.cc

@@ -237,7 +237,7 @@ class DBIteratorTest : public testing::Test {
 
 TEST_F(DBIteratorTest, DBIteratorPrevNext) {
   Options options;
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
   {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
@@ -252,7 +252,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -286,7 +286,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -314,7 +314,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -348,7 +348,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -385,7 +385,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -417,7 +417,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 7 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -456,7 +456,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -483,7 +483,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -508,7 +508,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -545,7 +545,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 7 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -576,7 +576,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -621,7 +621,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -654,7 +654,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -677,7 +677,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
 TEST_F(DBIteratorTest, DBIteratorEmpty) {
   Options options;
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
   ReadOptions ro;
 
@@ -686,7 +686,7 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -700,7 +700,7 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -757,7 +757,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
   ReadOptions ro;
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
@@ -772,7 +772,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
 
       options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -810,7 +810,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -841,7 +841,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, 202 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -876,7 +876,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->AddPut("c", "200");
       internal_iter->Finish();
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -896,7 +896,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
     internal_iter->AddPut("c", "200");
     internal_iter->Finish();
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 200 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -934,7 +934,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -971,7 +971,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -1004,7 +1004,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
 
 TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
   Options options;
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
   ReadOptions ro;
 
@@ -1023,7 +1023,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 0;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1071,7 +1071,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1117,7 +1117,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1157,7 +1157,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1194,7 +1194,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1226,7 +1226,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1265,7 +1265,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1304,7 +1304,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
       ro.max_skippable_internal_keys = i;
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, 2 * i + 1 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -1359,7 +1359,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
       options.max_sequential_skip_in_iterations = 1000;
       ro.max_skippable_internal_keys = i;
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+          env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, 2 * i + 1 /* sequence */,
           options.max_sequential_skip_in_iterations,
           nullptr /* read_callback */));
@@ -1500,7 +1500,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
   ReadOptions ro;
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
@@ -1515,7 +1515,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1539,7 +1539,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 1 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1563,7 +1563,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1587,7 +1587,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 3 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1611,7 +1611,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1635,7 +1635,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 5 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1659,7 +1659,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 6 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1681,7 +1681,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->AddPut("b", "val_b");
     internal_iter->Finish();
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1698,7 +1698,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
   ReadOptions ro;
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
@@ -1713,7 +1713,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1737,7 +1737,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 1 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1761,7 +1761,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1785,7 +1785,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 3 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1805,7 +1805,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1829,7 +1829,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 5 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1853,7 +1853,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 6 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1870,7 +1870,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
   ReadOptions ro;
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
-  ImmutableOptions cf_options = ImmutableOptions(options);
+  ImmutableOptions ioptions = ImmutableOptions(options);
   MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
@@ -1897,7 +1897,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1933,7 +1933,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -1975,7 +1975,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -2017,7 +2017,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 5 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -2064,7 +2064,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 6 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -2112,7 +2112,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 7 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -2154,7 +2154,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 9 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -2202,7 +2202,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 13 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));
@@ -2251,7 +2251,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
+        env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 14 /* sequence */,
         options.max_sequential_skip_in_iterations,
         nullptr /* read_callback */));

db/db_iterator_test.cc

@@ -35,7 +35,7 @@ class DummyReadCallback : public ReadCallback {
 class DBIteratorTest : public DBTestBase,
                        public testing::WithParamInterface<bool> {
  public:
-  DBIteratorTest() : DBTestBase("/db_iterator_test", /*env_do_fsync=*/true) {}
+  DBIteratorTest() : DBTestBase("db_iterator_test", /*env_do_fsync=*/true) {}
 
   Iterator* NewIterator(const ReadOptions& read_options,
                         ColumnFamilyHandle* column_family = nullptr) {
@@ -1536,9 +1536,11 @@ class DBIteratorTestForPinnedData : public DBIteratorTest {
 }
 };
 
+#if !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 TEST_P(DBIteratorTestForPinnedData, PinnedDataIteratorRandomizedNormal) {
   PinnedDataIteratorRandomized(TestConfig::NORMAL);
 }
+#endif  // !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
 
 TEST_P(DBIteratorTestForPinnedData, PinnedDataIteratorRandomizedCLoseAndOpen) {
   PinnedDataIteratorRandomized(TestConfig::CLOSE_AND_OPEN);

db/db_kv_checksum_test.cc

@@ -29,7 +29,7 @@ class DbKvChecksumTest
       public ::testing::WithParamInterface<std::tuple<WriteBatchOpType, char>> {
  public:
   DbKvChecksumTest()
-      : DBTestBase("/db_kv_checksum_test", /*env_do_fsync=*/false) {
+      : DBTestBase("db_kv_checksum_test", /*env_do_fsync=*/false) {
     op_type_ = std::get<0>(GetParam());
     corrupt_byte_addend_ = std::get<1>(GetParam());
   }