Update history and version for 8.5.4

Summary:
**Context/Summary:**
https://github.com/facebook/rocksdb/pull/11631 introduced an undesired fallback behavior to RocksDB internal prefetching even when FS prefetching return non-OK status other than "Unsupported". We only want to fall back when FS prefetching is not supported.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11897

Test Plan: CI

Reviewed By: ajkr

Differential Revision: D49667055

Pulled By: hx235

fbshipit-source-id: fa36e4e5d6dc9507080217035f9d6ff8e4abda28

.github/workflows/sanity_check.yml

@@ -33,9 +33,7 @@ jobs:
       run: pip install argparse
 
     - name: Download clang-format-diff.py
-      uses: wei/wget@v1
-      with:
-        args: https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
+      run: wget https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
 
     - name: Check format
       run: VERBOSE_CHECK=1 make check-format

.gitignore

@@ -95,3 +95,5 @@ fuzz/crash-*
 
 cmake-build-*
 third-party/folly/
+.cache
+*.sublime-*

CMakeLists.txt

@@ -253,33 +253,10 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
   endif(HAS_LOONGARCH64)
 endif(CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
 
-option(PORTABLE "build a portable binary" OFF)
-option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
-option(FORCE_AVX "force building with AVX, even when PORTABLE=ON" OFF)
-option(FORCE_AVX2 "force building with AVX2, even when PORTABLE=ON" OFF)
-if(PORTABLE)
-  add_definitions(-DROCKSDB_PORTABLE)
-
-  # MSVC does not need a separate compiler flag to enable SSE4.2; if nmmintrin.h
-  # is available, it is available by default.
-  if(FORCE_SSE42 AND NOT MSVC)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.2 -mpclmul")
-  endif()
-  if(MSVC)
-    if(FORCE_AVX)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX")
-    endif()
-    # MSVC automatically enables BMI / lzcnt with AVX2.
-    if(FORCE_AVX2)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
-    endif()
-  else()
-    if(FORCE_AVX)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mavx")
-    endif()
-    if(FORCE_AVX2)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mavx2 -mbmi -mlzcnt")
-    endif()
+set(PORTABLE 0 CACHE STRING "Minimum CPU arch to support, or 0 = current CPU, 1 = baseline CPU")
+if(PORTABLE STREQUAL 1)
+  # Usually nothing to do; compiler default is typically the most general
+  if(NOT MSVC)
     if(CMAKE_SYSTEM_PROCESSOR MATCHES "^s390x")
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=z196")
     endif()
@@ -287,10 +264,21 @@ if(PORTABLE)
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=loongarch64")
     endif()
   endif()
+elseif(PORTABLE MATCHES [^0]+)
+  # Name of a CPU arch spec or feature set to require
+  if(MSVC)
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:${PORTABLE}")
+  else()
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=${PORTABLE}")
+  endif()
 else()
   if(MSVC)
+    # NOTE: No auto-detection of current CPU, but instead assume some useful
+    # level of optimization is supported
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
   else()
+    # Require instruction set from current CPU (with some legacy or opt-out
+    # exceptions)
     if(CMAKE_SYSTEM_PROCESSOR MATCHES "^s390x" AND NOT HAS_S390X_MARCH_NATIVE)
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=z196")
     elseif(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64" AND NOT HAS_ARMV8_CRC)
@@ -305,25 +293,6 @@ if(NOT MSVC)
   set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
 endif()
 
-CHECK_CXX_SOURCE_COMPILES("
-#include <cstdint>
-#include <nmmintrin.h>
-#include <wmmintrin.h>
-int main() {
-  volatile uint32_t x = _mm_crc32_u32(0, 0);
-  const auto a = _mm_set_epi64x(0, 0);
-  const auto b = _mm_set_epi64x(0, 0);
-  const auto c = _mm_clmulepi64_si128(a, b, 0x00);
-  auto d = _mm_cvtsi128_si64(c);
-}
-" HAVE_SSE42)
-if(HAVE_SSE42)
-  add_definitions(-DHAVE_SSE42)
-  add_definitions(-DHAVE_PCLMUL)
-elseif(FORCE_SSE42)
-  message(FATAL_ERROR "FORCE_SSE42=ON but unable to compile with SSE4.2 enabled")
-endif()
-
 # Check if -latomic is required or not
 if (NOT MSVC)
   set(CMAKE_REQUIRED_FLAGS "--std=c++17")
@@ -578,7 +547,7 @@ if(HAVE_SCHED_GETCPU)
   add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
 endif()
 
-check_cxx_symbol_exists(getauxval auvx.h HAVE_AUXV_GETAUXVAL)
+check_cxx_symbol_exists(getauxval "sys/auxv.h" HAVE_AUXV_GETAUXVAL)
 if(HAVE_AUXV_GETAUXVAL)
   add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
 endif()
@@ -896,6 +865,8 @@ set(SOURCES
         util/string_util.cc
         util/thread_local.cc
         util/threadpool_imp.cc
+        util/udt_util.cc
+        util/write_batch_util.cc
         util/xxhash.cc
         utilities/agg_merge/agg_merge.cc
         utilities/backup/backup_engine.cc
@@ -1010,12 +981,6 @@ if ( ROCKSDB_PLUGINS )
   endforeach()
 endif()
 
-if(HAVE_SSE42 AND NOT MSVC)
-  set_source_files_properties(
-    util/crc32c.cc
-    PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
-endif()
-
 if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
   list(APPEND SOURCES
     util/crc32c_ppc.c
@@ -1327,6 +1292,7 @@ if(WITH_TESTS)
         db/db_bloom_filter_test.cc
         db/db_compaction_filter_test.cc
         db/db_compaction_test.cc
+        db/db_clip_test.cc
         db/db_dynamic_level_test.cc
         db/db_encryption_test.cc
         db/db_flush_test.cc
@@ -1457,6 +1423,7 @@ if(WITH_TESTS)
         util/timer_test.cc
         util/thread_list_test.cc
         util/thread_local_test.cc
+        util/udt_util_test.cc
         util/work_queue_test.cc
         utilities/agg_merge/agg_merge_test.cc
         utilities/backup/backup_engine_test.cc
@@ -1625,3 +1592,6 @@ option(WITH_BENCHMARK "build benchmark tests" OFF)
 if(WITH_BENCHMARK)
   add_subdirectory(${PROJECT_SOURCE_DIR}/microbench/)
 endif()
+
+target_include_directories(${PROJECT_NAME} PUBLIC
+  $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>)

HISTORY.md

@@ -1,5 +1,122 @@
 # Rocksdb Change Log
-## Unreleased
+> NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
+
+## 8.5.4 (09/26/2023)
+### Bug Fixes
+* Fixed a bug where compaction read under non direct IO still falls back to RocksDB internal prefetching after file system's prefetching returns non-OK status other than `Status::NotSupported()`
+
+### Behavior Changes
+* For non direct IO, eliminate the file system prefetching attempt for compaction read when `Options::compaction_readahead_size` is 0
+
+## 8.5.3 (09/01/2023)
+### Bug Fixes
+* Fixed a race condition in `GenericRateLimiter` that could cause it to stop granting requests
+
+## 8.5.2 (08/31/2023)
+### Bug fixes
+* Fix a bug where iterator may return incorrect result for DeleteRange() users if there was an error reading from a file.
+
+## 8.5.1 (08/31/2023)
+### Bug fixes
+* Fix a bug where if there is an error reading from offset 0 of a file from L1+ and that the file is not the first file in the sorted run, data can be lost in compaction and read/scan can return incorrect results.
+
+## 8.5.0 (07/21/2023)
+### Public API Changes
+* Removed recently added APIs `GeneralCache` and `MakeSharedGeneralCache()` as our plan changed to stop exposing a general-purpose cache interface. The old forms of these APIs, `Cache` and `NewLRUCache()`, are still available, although general-purpose caching support will be dropped eventually.
+
+### Behavior Changes
+* Option `periodic_compaction_seconds` no longer supports FIFO compaction: setting it has no effect on FIFO compactions. FIFO compaction users should only set option `ttl` instead.
+* Move prefetching responsibility to page cache for compaction read for non directIO use case
+
+### Performance Improvements
+* In case of direct_io, if buffer passed by callee is already aligned, RandomAccessFileRead::Read will avoid realloacting a new buffer, reducing memcpy and use already passed aligned buffer.
+* Small efficiency improvement to HyperClockCache by reducing chance of compiler-generated heap allocations
+
+### Bug Fixes
+* Fix use_after_free bug in async_io MultiReads when underlying FS enabled kFSBuffer. kFSBuffer is when underlying FS pass their own buffer instead of using RocksDB scratch in FSReadRequest. Right now it's an experimental feature.
+* Fix a bug in FileTTLBooster that can cause users with a large number of levels (more than 65) to see errors like "runtime error: shift exponent .. is too large.." (#11673).
+
+## 8.4.0 (06/26/2023)
+### New Features
+* Add FSReadRequest::fs_scratch which is a data buffer allocated and provided by underlying FileSystem to RocksDB during reads, when FS wants to provide its own buffer with data instead of using RocksDB provided FSReadRequest::scratch. This can help in cpu optimization by avoiding copy from file system's buffer to RocksDB buffer. More details on how to use/enable it in file_system.h. Right now its supported only for MultiReads(async + sync) with non direct io.
+* Start logging non-zero user-defined timestamp sizes in WAL to signal user key format in subsequent records and use it during recovery. This change will break recovery from WAL files written by early versions that contain user-defined timestamps. The workaround is to ensure there are no WAL files to recover (i.e. by flushing before close) before upgrade.
+* Added new property "rocksdb.obsolete-sst-files-size-property" that reports the size of SST files that have become obsolete but have not yet been deleted or scheduled for deletion
+* Start to record the value of the flag `AdvancedColumnFamilyOptions.persist_user_defined_timestamps` in the Manifest and table properties for a SST file when it is created. And use the recorded flag when creating a table reader for the SST file. This flag is only explicitly record if it's false.
+* Add a new option OptimisticTransactionDBOptions::shared_lock_buckets that enables sharing mutexes for validating transactions between DB instances, for better balancing memory efficiency and validation contention across DB instances. Different column families and DBs also now use different hash seeds in this validation, so that the same set of key names will not contend across DBs or column families.
+* Add a new ticker `rocksdb.files.marked.trash.deleted` to track the number of trash files deleted by background thread from the trash queue.
+* Add an API NewTieredVolatileCache() in include/rocksdb/cache.h to allocate an instance of a block cache with a primary block cache tier and a compressed secondary cache tier. A cache of this type distributes memory reservations against the block cache, such as WriteBufferManager, table reader memory etc., proportionally across both the primary and compressed secondary cache.
+* Add `WaitForCompact()` to wait for all flush and compactions jobs to finish. Jobs to wait include the unscheduled (queued, but not scheduled yet).
+* Add `WriteBatch::Release()` that releases the batch's serialized data to the caller.
+
+### Public API Changes
+* Add C API `rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio`.
+* change the FileSystem::use_async_io() API to SupportedOps API in order to extend it to various operations supported by underlying FileSystem. Right now it contains FSSupportedOps::kAsyncIO and FSSupportedOps::kFSBuffer. More details about FSSupportedOps in filesystem.h
+* Add new tickers: `rocksdb.error.handler.bg.error.count`, `rocksdb.error.handler.bg.io.error.count`, `rocksdb.error.handler.bg.retryable.io.error.count` to replace the misspelled ones: `rocksdb.error.handler.bg.errro.count`, `rocksdb.error.handler.bg.io.errro.count`, `rocksdb.error.handler.bg.retryable.io.errro.count` ('error' instead of 'errro'). Users should switch to use the new tickers before 9.0 release as the misspelled old tickers will be completely removed then.
+* Overload the API CreateColumnFamilyWithImport() to support creating ColumnFamily by importing multiple ColumnFamilies It requires that CFs should not overlap in user key range.
+
+### Behavior Changes
+* Change the default value for option `level_compaction_dynamic_level_bytes` to true. This affects users who use leveled compaction and do not set this option explicitly. These users may see additional background compactions following DB open. These compactions help to shape the LSM according to `level_compaction_dynamic_level_bytes` such that the size of each level Ln is approximately size of Ln-1 * `max_bytes_for_level_multiplier`. Turning on this option has other benefits too: see more detail in wiki: https://github.com/facebook/rocksdb/wiki/Leveled-Compaction#option-level_compaction_dynamic_level_bytes-and-levels-target-size and in option comment in advanced_options.h (#11525).
+* For Leveled Compaction users, `CompactRange()` will now always try to compact to the last non-empty level. (#11468)
+For Leveled Compaction users, `CompactRange()` with `bottommost_level_compaction = BottommostLevelCompaction::kIfHaveCompactionFilter` will behave similar to `kForceOptimized` in that it will skip files created during this manual compaction when compacting files in the bottommost level. (#11468)
+* RocksDB will try to drop range tombstones during non-bottommost compaction when it is safe to do so. (#11459)
+* When a DB is openend with `allow_ingest_behind=true` (currently only Universal compaction is supported), files in the last level, i.e. the ingested files,  will not be included in any compaction. (#11489)
+* Statistics `rocksdb.sst.read.micros` scope is expanded to all SST reads except for file ingestion and column family import (some compaction reads were previously excluded).
+
+### Bug Fixes
+* Reduced cases of illegally using Env::Default() during static destruction by never destroying the internal PosixEnv itself (except for builds checking for memory leaks). (#11538)
+* Fix extra prefetching during seek in async_io when BlockBasedTableOptions.num_file_reads_for_auto_readahead is 1 leading to extra reads than required.
+* Fix a bug where compactions that are qualified to be run as 2 subcompactions were only run as one subcompaction.
+* Fix a use-after-move bug in block.cc.
+
+## 8.3.0 (05/19/2023)
+### New Features
+* Introduced a new option `block_protection_bytes_per_key`, which can be used to enable per key-value integrity protection for in-memory blocks in block cache (#11287).
+* Added `JemallocAllocatorOptions::num_arenas`. Setting `num_arenas > 1` may mitigate mutex contention in the allocator, particularly in scenarios where block allocations commonly bypass jemalloc tcache.
+* Improve the operational safety of publishing a DB or SST files to many hosts by using different block cache hash seeds on different hosts. The exact behavior is controlled by new option `ShardedCacheOptions::hash_seed`, which also documents the solved problem in more detail.
+* Introduced a new option `CompactionOptionsFIFO::file_temperature_age_thresholds` that allows FIFO compaction to compact files to different temperatures based on key age (#11428).
+* Added a new ticker stat to count how many times RocksDB detected a corruption while verifying a block checksum: `BLOCK_CHECKSUM_MISMATCH_COUNT`.
+* New statistics `rocksdb.file.read.db.open.micros` that measures read time of block-based SST tables or blob files during db open.
+* New statistics tickers for various iterator seek behaviors and relevant filtering, as \*`_LEVEL_SEEK_`\*. (#11460)
+
+### Public API Changes
+* EXPERIMENTAL: Add new API `DB::ClipColumnFamily` to clip the key in CF to a certain range. It will physically deletes all keys outside the range including tombstones.
+* Add `MakeSharedCache()` construction functions to various cache Options objects, and deprecated the `NewWhateverCache()` functions with long parameter lists.
+* Changed the meaning of various Bloom filter stats (prefix vs. whole key), with iterator-related filtering only being tracked in the new \*`_LEVEL_SEEK_`\*. stats. (#11460)
+
+### Behavior changes
+* For x86, CPU features are no longer detected at runtime nor in build scripts, but in source code using common preprocessor defines. This will likely unlock some small performance improvements on some newer hardware, but could hurt performance of the kCRC32c checksum, which is no longer the default, on some "portable" builds. See PR #11419 for details.
+
+### Bug Fixes
+* Delete an empty WAL file on DB open if the log number is less than the min log number to keep
+* Delete temp OPTIONS file on DB open if there is a failure to write it out or rename it
+
+### Performance Improvements
+* Improved the I/O efficiency of prefetching SST metadata by recording more information in the DB manifest. Opening files written with previous versions will still rely on heuristics for how much to prefetch (#11406).
+
+## 8.2.0 (04/24/2023)
+### Public API Changes
+* `SstFileWriter::DeleteRange()` now returns `Status::InvalidArgument` if the range's end key comes before its start key according to the user comparator. Previously the behavior was undefined.
+* Add `multi_get_for_update` to C API.
+* Remove unnecessary constructor for CompressionOptions.
+
+### Behavior changes
+* Changed default block cache size from an 8MB to 32MB LRUCache, which increases the default number of cache shards from 16 to 64. This change is intended to minimize cache mutex contention under stress conditions. See https://github.com/facebook/rocksdb/wiki/Block-Cache for more information.
+* For level compaction with `level_compaction_dynamic_level_bytes=true`, RocksDB now trivially moves levels down to fill LSM starting from bottommost level during DB open. See more in comments for option `level_compaction_dynamic_level_bytes` (#11321).
+* User-provided `ReadOptions` take effect for more reads of non-`CacheEntryRole::kDataBlock` blocks.
+* For level compaction with `level_compaction_dynamic_level_bytes=true`, RocksDB now drains unnecessary levels through background compaction automatically (#11340). This together with #11321 makes it automatic to migrate other compaction settings to level compaction with `level_compaction_dynamic_level_bytes=true`. In addition, a live DB that becomes smaller will now have unnecessary levels drained which can help to reduce read and space amp.
+* If `CompactRange()` is called with `CompactRangeOptions::bottommost_level_compaction=kForce*` to compact from L0 to L1, RocksDB now will try to do trivial move from L0 to L1 and then do an intra L1 compaction, instead of a L0 to L1 compaction with trivial move disabled (#11375)).
+
+### Bug Fixes
+* In the DB::VerifyFileChecksums API, ensure that file system reads of SST files are equal to the readahead_size in ReadOptions, if specified. Previously, each read was 2x the readahead_size.
+* In block cache tracing, fixed some cases of bad hit/miss information (and more) with MultiGet.
+
+### New Features
+* Add experimental `PerfContext` counters `iter_{next|prev|seek}_count` for db iterator, each counting the times of corresponding API being called.
+* Allow runtime changes to whether `WriteBufferManager` allows stall or not by calling `SetAllowStall()`
+* Added statistics tickers BYTES_COMPRESSED_FROM, BYTES_COMPRESSED_TO, BYTES_COMPRESSION_BYPASSED, BYTES_COMPRESSION_REJECTED, NUMBER_BLOCK_COMPRESSION_BYPASSED, and NUMBER_BLOCK_COMPRESSION_REJECTED. Disabled/deprecated histograms BYTES_COMPRESSED and BYTES_DECOMPRESSED, and ticker NUMBER_BLOCK_NOT_COMPRESSED. The new tickers offer more inight into compression ratios, rejected vs. disabled compression, etc. (#11388)
+* New statistics `rocksdb.file.read.{flush|compaction}.micros` that measure read time of block-based SST tables or blob files during flush or compaction.
+
+## 8.1.0 (03/18/2023)
 ### Behavior changes
 * Compaction output file cutting logic now considers range tombstone start keys. For example, SST partitioner now may receive ParitionRequest for range tombstone start keys.
 * If the async_io ReadOption is specified for MultiGet or NewIterator on a platform that doesn't support IO uring, the option is ignored and synchronous IO is used.

INSTALL.md

@@ -20,12 +20,15 @@ There are few options when compiling RocksDB:
 depend on gflags. You will need to have gflags installed to run `make all`. This will compile RocksDB in debug mode. Don't
 use binaries compiled by `make all` in production.
 
-* By default the binary we produce is optimized for the platform you're compiling on
-(`-march=native` or the equivalent). SSE4.2 will thus be enabled automatically if your
-CPU supports it. To print a warning if your CPU does not support SSE4.2, build with
-`USE_SSE=1 make static_lib` or, if using CMake, `cmake -DFORCE_SSE42=ON`. If you want
-to build a portable binary, add `PORTABLE=1` before your make commands, like this:
-`PORTABLE=1 make static_lib`.
+* By default the binary we produce is optimized for the CPU you're compiling on
+(`-march=native` or the equivalent). To build a binary compatible with the most
+general architecture supported by your CPU and compiler, set `PORTABLE=1` for
+the build, but performance will suffer as many operations benefit from newer
+and wider instructions. In addition to `PORTABLE=0` (default) and `PORTABLE=1`,
+it can be set to an architecture name recognized by your compiler. For example,
+on 64-bit x86, a reasonable compromise is `PORTABLE=haswell` which supports
+many or most of the available optimizations while still being compatible with
+most processors made since roughly 2013.
 
 ## Dependencies
 

Makefile

@@ -337,8 +337,8 @@ ifneq ($(MACHINE), arm64)
 # linking with jemalloc (as it won't be arm64-compatible) and remove some other options
 # set during platform detection
 DISABLE_JEMALLOC=1
-PLATFORM_CFLAGS := $(filter-out -march=native -DHAVE_SSE42 -DHAVE_AVX2, $(PLATFORM_CFLAGS))
-PLATFORM_CXXFLAGS := $(filter-out -march=native -DHAVE_SSE42 -DHAVE_AVX2, $(PLATFORM_CXXFLAGS))
+PLATFORM_CCFLAGS := $(filter-out -march=native, $(PLATFORM_CCFLAGS))
+PLATFORM_CXXFLAGS := $(filter-out -march=native, $(PLATFORM_CXXFLAGS))
 endif
 endif
 endif
@@ -539,7 +539,7 @@ endif
 
 ifdef USE_CLANG
 	# Used by some teams in Facebook
-	WARNING_FLAGS += -Wshift-sign-overflow
+	WARNING_FLAGS += -Wshift-sign-overflow -Wambiguous-reversed-operator
 endif
 
 ifeq ($(PLATFORM), OS_OPENBSD)
@@ -1417,6 +1417,9 @@ thread_local_test: $(OBJ_DIR)/util/thread_local_test.o $(TEST_LIBRARY) $(LIBRARY
 work_queue_test: $(OBJ_DIR)/util/work_queue_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+udt_util_test: $(OBJ_DIR)/util/udt_util_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 corruption_test: $(OBJ_DIR)/db/corruption_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1480,6 +1483,9 @@ db_compaction_filter_test: $(OBJ_DIR)/db/db_compaction_filter_test.o $(TEST_LIBR
 db_compaction_test: $(OBJ_DIR)/db/db_compaction_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+db_clip_test: $(OBJ_DIR)/db/db_clip_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 db_dynamic_level_test: $(OBJ_DIR)/db/db_dynamic_level_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -2435,6 +2441,8 @@ checkout_folly:
 	@# NOTE: this hack is required for gcc in some cases
 	perl -pi -e 's/(__has_include.<experimental.memory_resource>.)/__cpp_rtti && $$1/' third-party/folly/folly/memory/MemoryResource.h
 
+CXX_M_FLAGS = $(filter -m%, $(CXXFLAGS))
+
 build_folly:
 	FOLLY_INST_PATH=`cd third-party/folly; $(PYTHON) build/fbcode_builder/getdeps.py show-inst-dir`; \
 	if [ "$$FOLLY_INST_PATH" ]; then \
@@ -2445,8 +2453,8 @@ build_folly:
 	fi
 	# Restore the original version of Invoke.h with boost dependency
 	cd third-party/folly && ${GIT_COMMAND} checkout folly/functional/Invoke.h
-	cd third-party/folly && MAYBE_AVX2=`echo $(CXXFLAGS) | grep -o -- -DHAVE_AVX2 | sed 's/-DHAVE_AVX2/-mavx2/g' || true` && \
-		CXXFLAGS=" $$MAYBE_AVX2 -DHAVE_CXX11_ATOMIC " $(PYTHON) build/fbcode_builder/getdeps.py build --no-tests
+	cd third-party/folly && \
+		CXXFLAGS=" $(CXX_M_FLAGS) -DHAVE_CXX11_ATOMIC " $(PYTHON) build/fbcode_builder/getdeps.py build --no-tests
 
 # ---------------------------------------------------------------------------
 #   Build size testing

PLUGINS.md

@@ -5,3 +5,4 @@ This is the list of all known third-party plugins for RocksDB. If something is m
 * [ZenFS](https://github.com/westerndigitalcorporation/zenfs): a file system for zoned block devices
 * [RADOS](https://github.com/riversand963/rocksdb-rados-env): an Env used for interacting with RADOS. Migrated from RocksDB main repo.
 * [PMEM](https://github.com/pmem/pmem-rocksdb-plugin): a collection of plugins to enable Persistent Memory on RocksDB.
+* [IPPCP](https://github.com/intel/ippcp-plugin-rocksdb): a plugin to enable encryption on RocksDB based on Intel optimized open source IPP-Crypto library.

README.md

@@ -1,8 +1,6 @@
 ## RocksDB: A Persistent Key-Value Store for Flash and RAM Storage
 
 [![CircleCI Status](https://circleci.com/gh/facebook/rocksdb.svg?style=svg)](https://circleci.com/gh/facebook/rocksdb)
-[![Appveyor Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/main?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/main)
-[![PPC64le Build Status](http://140-211-168-68-openstack.osuosl.org:8080/buildStatus/icon?job=rocksdb&style=plastic)](http://140-211-168-68-openstack.osuosl.org:8080/job/rocksdb)
 
 RocksDB is developed and maintained by Facebook Database Engineering Team.
 It is built on earlier work on [LevelDB](https://github.com/google/leveldb) by Sanjay Ghemawat (sanjay@google.com)

TARGETS

@@ -264,6 +264,8 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "util/string_util.cc",
         "util/thread_local.cc",
         "util/threadpool_imp.cc",
+        "util/udt_util.cc",
+        "util/write_batch_util.cc",
         "util/xxhash.cc",
         "utilities/agg_merge/agg_merge.cc",
         "utilities/backup/backup_engine.cc",
@@ -354,351 +356,7 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "//folly/synchronization:distributed_mutex",
     ], headers=None, link_whole=False, extra_test_libs=False)
 
-cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[
-        "cache/cache.cc",
-        "cache/cache_entry_roles.cc",
-        "cache/cache_helpers.cc",
-        "cache/cache_key.cc",
-        "cache/cache_reservation_manager.cc",
-        "cache/charged_cache.cc",
-        "cache/clock_cache.cc",
-        "cache/compressed_secondary_cache.cc",
-        "cache/lru_cache.cc",
-        "cache/secondary_cache.cc",
-        "cache/secondary_cache_adapter.cc",
-        "cache/sharded_cache.cc",
-        "db/arena_wrapped_db_iter.cc",
-        "db/blob/blob_contents.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",
-        "db/blob/blob_source.cc",
-        "db/blob/prefetch_buffer_collection.cc",
-        "db/builder.cc",
-        "db/c.cc",
-        "db/column_family.cc",
-        "db/compaction/compaction.cc",
-        "db/compaction/compaction_iterator.cc",
-        "db/compaction/compaction_job.cc",
-        "db/compaction/compaction_outputs.cc",
-        "db/compaction/compaction_picker.cc",
-        "db/compaction/compaction_picker_fifo.cc",
-        "db/compaction/compaction_picker_level.cc",
-        "db/compaction/compaction_picker_universal.cc",
-        "db/compaction/compaction_service_job.cc",
-        "db/compaction/compaction_state.cc",
-        "db/compaction/sst_partitioner.cc",
-        "db/compaction/subcompaction_state.cc",
-        "db/convenience.cc",
-        "db/db_filesnapshot.cc",
-        "db/db_impl/compacted_db_impl.cc",
-        "db/db_impl/db_impl.cc",
-        "db/db_impl/db_impl_compaction_flush.cc",
-        "db/db_impl/db_impl_debug.cc",
-        "db/db_impl/db_impl_experimental.cc",
-        "db/db_impl/db_impl_files.cc",
-        "db/db_impl/db_impl_open.cc",
-        "db/db_impl/db_impl_readonly.cc",
-        "db/db_impl/db_impl_secondary.cc",
-        "db/db_impl/db_impl_write.cc",
-        "db/db_info_dumper.cc",
-        "db/db_iter.cc",
-        "db/dbformat.cc",
-        "db/error_handler.cc",
-        "db/event_helpers.cc",
-        "db/experimental.cc",
-        "db/external_sst_file_ingestion_job.cc",
-        "db/file_indexer.cc",
-        "db/flush_job.cc",
-        "db/flush_scheduler.cc",
-        "db/forward_iterator.cc",
-        "db/import_column_family_job.cc",
-        "db/internal_stats.cc",
-        "db/log_reader.cc",
-        "db/log_writer.cc",
-        "db/logs_with_prep_tracker.cc",
-        "db/malloc_stats.cc",
-        "db/memtable.cc",
-        "db/memtable_list.cc",
-        "db/merge_helper.cc",
-        "db/merge_operator.cc",
-        "db/output_validator.cc",
-        "db/periodic_task_scheduler.cc",
-        "db/range_del_aggregator.cc",
-        "db/range_tombstone_fragmenter.cc",
-        "db/repair.cc",
-        "db/seqno_to_time_mapping.cc",
-        "db/snapshot_impl.cc",
-        "db/table_cache.cc",
-        "db/table_properties_collector.cc",
-        "db/transaction_log_impl.cc",
-        "db/trim_history_scheduler.cc",
-        "db/version_builder.cc",
-        "db/version_edit.cc",
-        "db/version_edit_handler.cc",
-        "db/version_set.cc",
-        "db/wal_edit.cc",
-        "db/wal_manager.cc",
-        "db/wide/wide_column_serialization.cc",
-        "db/wide/wide_columns.cc",
-        "db/write_batch.cc",
-        "db/write_batch_base.cc",
-        "db/write_controller.cc",
-        "db/write_stall_stats.cc",
-        "db/write_thread.cc",
-        "env/composite_env.cc",
-        "env/env.cc",
-        "env/env_chroot.cc",
-        "env/env_encryption.cc",
-        "env/env_posix.cc",
-        "env/file_system.cc",
-        "env/file_system_tracer.cc",
-        "env/fs_posix.cc",
-        "env/fs_remap.cc",
-        "env/io_posix.cc",
-        "env/mock_env.cc",
-        "env/unique_id_gen.cc",
-        "file/delete_scheduler.cc",
-        "file/file_prefetch_buffer.cc",
-        "file/file_util.cc",
-        "file/filename.cc",
-        "file/line_file_reader.cc",
-        "file/random_access_file_reader.cc",
-        "file/read_write_util.cc",
-        "file/readahead_raf.cc",
-        "file/sequence_file_reader.cc",
-        "file/sst_file_manager_impl.cc",
-        "file/writable_file_writer.cc",
-        "logging/auto_roll_logger.cc",
-        "logging/event_logger.cc",
-        "logging/log_buffer.cc",
-        "memory/arena.cc",
-        "memory/concurrent_arena.cc",
-        "memory/jemalloc_nodump_allocator.cc",
-        "memory/memkind_kmem_allocator.cc",
-        "memory/memory_allocator.cc",
-        "memtable/alloc_tracker.cc",
-        "memtable/hash_linklist_rep.cc",
-        "memtable/hash_skiplist_rep.cc",
-        "memtable/skiplistrep.cc",
-        "memtable/vectorrep.cc",
-        "memtable/write_buffer_manager.cc",
-        "monitoring/histogram.cc",
-        "monitoring/histogram_windowing.cc",
-        "monitoring/in_memory_stats_history.cc",
-        "monitoring/instrumented_mutex.cc",
-        "monitoring/iostats_context.cc",
-        "monitoring/perf_context.cc",
-        "monitoring/perf_level.cc",
-        "monitoring/persistent_stats_history.cc",
-        "monitoring/statistics.cc",
-        "monitoring/thread_status_impl.cc",
-        "monitoring/thread_status_updater.cc",
-        "monitoring/thread_status_updater_debug.cc",
-        "monitoring/thread_status_util.cc",
-        "monitoring/thread_status_util_debug.cc",
-        "options/cf_options.cc",
-        "options/configurable.cc",
-        "options/customizable.cc",
-        "options/db_options.cc",
-        "options/options.cc",
-        "options/options_helper.cc",
-        "options/options_parser.cc",
-        "port/mmap.cc",
-        "port/port_posix.cc",
-        "port/stack_trace.cc",
-        "port/win/env_default.cc",
-        "port/win/env_win.cc",
-        "port/win/io_win.cc",
-        "port/win/port_win.cc",
-        "port/win/win_logger.cc",
-        "port/win/win_thread.cc",
-        "table/adaptive/adaptive_table_factory.cc",
-        "table/block_based/binary_search_index_reader.cc",
-        "table/block_based/block.cc",
-        "table/block_based/block_based_table_builder.cc",
-        "table/block_based/block_based_table_factory.cc",
-        "table/block_based/block_based_table_iterator.cc",
-        "table/block_based/block_based_table_reader.cc",
-        "table/block_based/block_builder.cc",
-        "table/block_based/block_cache.cc",
-        "table/block_based/block_prefetcher.cc",
-        "table/block_based/block_prefix_index.cc",
-        "table/block_based/data_block_footer.cc",
-        "table/block_based/data_block_hash_index.cc",
-        "table/block_based/filter_block_reader_common.cc",
-        "table/block_based/filter_policy.cc",
-        "table/block_based/flush_block_policy.cc",
-        "table/block_based/full_filter_block.cc",
-        "table/block_based/hash_index_reader.cc",
-        "table/block_based/index_builder.cc",
-        "table/block_based/index_reader_common.cc",
-        "table/block_based/parsed_full_filter_block.cc",
-        "table/block_based/partitioned_filter_block.cc",
-        "table/block_based/partitioned_index_iterator.cc",
-        "table/block_based/partitioned_index_reader.cc",
-        "table/block_based/reader_common.cc",
-        "table/block_based/uncompression_dict_reader.cc",
-        "table/block_fetcher.cc",
-        "table/compaction_merging_iterator.cc",
-        "table/cuckoo/cuckoo_table_builder.cc",
-        "table/cuckoo/cuckoo_table_factory.cc",
-        "table/cuckoo/cuckoo_table_reader.cc",
-        "table/format.cc",
-        "table/get_context.cc",
-        "table/iterator.cc",
-        "table/merging_iterator.cc",
-        "table/meta_blocks.cc",
-        "table/persistent_cache_helper.cc",
-        "table/plain/plain_table_bloom.cc",
-        "table/plain/plain_table_builder.cc",
-        "table/plain/plain_table_factory.cc",
-        "table/plain/plain_table_index.cc",
-        "table/plain/plain_table_key_coding.cc",
-        "table/plain/plain_table_reader.cc",
-        "table/sst_file_dumper.cc",
-        "table/sst_file_reader.cc",
-        "table/sst_file_writer.cc",
-        "table/table_factory.cc",
-        "table/table_properties.cc",
-        "table/two_level_iterator.cc",
-        "table/unique_id.cc",
-        "test_util/sync_point.cc",
-        "test_util/sync_point_impl.cc",
-        "test_util/transaction_test_util.cc",
-        "tools/dump/db_dump_tool.cc",
-        "tools/io_tracer_parser_tool.cc",
-        "tools/ldb_cmd.cc",
-        "tools/ldb_tool.cc",
-        "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/async_file_reader.cc",
-        "util/build_version.cc",
-        "util/cleanable.cc",
-        "util/coding.cc",
-        "util/compaction_job_stats_impl.cc",
-        "util/comparator.cc",
-        "util/compression.cc",
-        "util/compression_context_cache.cc",
-        "util/concurrent_task_limiter_impl.cc",
-        "util/crc32c.cc",
-        "util/crc32c_arm64.cc",
-        "util/data_structure.cc",
-        "util/dynamic_bloom.cc",
-        "util/file_checksum_helper.cc",
-        "util/hash.cc",
-        "util/murmurhash.cc",
-        "util/random.cc",
-        "util/rate_limiter.cc",
-        "util/ribbon_config.cc",
-        "util/slice.cc",
-        "util/status.cc",
-        "util/stderr_logger.cc",
-        "util/string_util.cc",
-        "util/thread_local.cc",
-        "util/threadpool_imp.cc",
-        "util/xxhash.cc",
-        "utilities/agg_merge/agg_merge.cc",
-        "utilities/backup/backup_engine.cc",
-        "utilities/blob_db/blob_compaction_filter.cc",
-        "utilities/blob_db/blob_db.cc",
-        "utilities/blob_db/blob_db_impl.cc",
-        "utilities/blob_db/blob_db_impl_filesnapshot.cc",
-        "utilities/blob_db/blob_dump_tool.cc",
-        "utilities/blob_db/blob_file.cc",
-        "utilities/cache_dump_load.cc",
-        "utilities/cache_dump_load_impl.cc",
-        "utilities/cassandra/cassandra_compaction_filter.cc",
-        "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/counted_fs.cc",
-        "utilities/debug.cc",
-        "utilities/env_mirror.cc",
-        "utilities/env_timed.cc",
-        "utilities/fault_injection_env.cc",
-        "utilities/fault_injection_fs.cc",
-        "utilities/fault_injection_secondary_cache.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",
-        "utilities/merge_operators/sortlist.cc",
-        "utilities/merge_operators/string_append/stringappend.cc",
-        "utilities/merge_operators/string_append/stringappend2.cc",
-        "utilities/merge_operators/uint64add.cc",
-        "utilities/object_registry.cc",
-        "utilities/option_change_migration/option_change_migration.cc",
-        "utilities/options/options_util.cc",
-        "utilities/persistent_cache/block_cache_tier.cc",
-        "utilities/persistent_cache/block_cache_tier_file.cc",
-        "utilities/persistent_cache/block_cache_tier_metadata.cc",
-        "utilities/persistent_cache/persistent_cache_tier.cc",
-        "utilities/persistent_cache/volatile_tier_impl.cc",
-        "utilities/simulator_cache/cache_simulator.cc",
-        "utilities/simulator_cache/sim_cache.cc",
-        "utilities/table_properties_collectors/compact_on_deletion_collector.cc",
-        "utilities/trace/file_trace_reader_writer.cc",
-        "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",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/keyrange.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/lock_request.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/locktree.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/manager.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/range_buffer.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/treenode.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/txnid_set.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/wfg.cc",
-        "utilities/transactions/lock/range/range_tree/lib/standalone_port.cc",
-        "utilities/transactions/lock/range/range_tree/lib/util/dbt.cc",
-        "utilities/transactions/lock/range/range_tree/lib/util/memarena.cc",
-        "utilities/transactions/lock/range/range_tree/range_tree_lock_manager.cc",
-        "utilities/transactions/lock/range/range_tree/range_tree_lock_tracker.cc",
-        "utilities/transactions/optimistic_transaction.cc",
-        "utilities/transactions/optimistic_transaction_db_impl.cc",
-        "utilities/transactions/pessimistic_transaction.cc",
-        "utilities/transactions/pessimistic_transaction_db.cc",
-        "utilities/transactions/snapshot_checker.cc",
-        "utilities/transactions/transaction_base.cc",
-        "utilities/transactions/transaction_db_mutex_impl.cc",
-        "utilities/transactions/transaction_util.cc",
-        "utilities/transactions/write_prepared_txn.cc",
-        "utilities/transactions/write_prepared_txn_db.cc",
-        "utilities/transactions/write_unprepared_txn.cc",
-        "utilities/transactions/write_unprepared_txn_db.cc",
-        "utilities/ttl/db_ttl_impl.cc",
-        "utilities/wal_filter.cc",
-        "utilities/write_batch_with_index/write_batch_with_index.cc",
-        "utilities/write_batch_with_index/write_batch_with_index_internal.cc",
-    ], deps=[
-        "//folly/container:f14_hash",
-        "//folly/experimental/coro:blocking_wait",
-        "//folly/experimental/coro:collect",
-        "//folly/experimental/coro:coroutine",
-        "//folly/experimental/coro:task",
-        "//folly/synchronization:distributed_mutex",
-    ], headers=None, link_whole=True, extra_test_libs=False)
+cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[], deps=[":rocksdb_lib"], headers=None, link_whole=True, extra_test_libs=False)
 
 cpp_library_wrapper(name="rocksdb_test_lib", srcs=[
         "db/db_test_util.cc",
@@ -736,6 +394,7 @@ rocks_cpp_library_wrapper(name="rocksdb_stress_lib", srcs=[
         "db_stress_tool/db_stress_test_base.cc",
         "db_stress_tool/db_stress_tool.cc",
         "db_stress_tool/expected_state.cc",
+        "db_stress_tool/expected_value.cc",
         "db_stress_tool/multi_ops_txns_stress.cc",
         "db_stress_tool/no_batched_ops_stress.cc",
         "test_util/testutil.cc",
@@ -5093,6 +4752,12 @@ cpp_unittest_wrapper(name="db_bloom_filter_test",
             extra_compiler_flags=[])
 
 
+cpp_unittest_wrapper(name="db_clip_test",
+            srcs=["db/db_clip_test.cc"],
+            deps=[":rocksdb_test_lib"],
+            extra_compiler_flags=[])
+
+
 cpp_unittest_wrapper(name="db_compaction_filter_test",
             srcs=["db/db_compaction_filter_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -5845,6 +5510,12 @@ cpp_unittest_wrapper(name="ttl_test",
             extra_compiler_flags=[])
 
 
+cpp_unittest_wrapper(name="udt_util_test",
+            srcs=["util/udt_util_test.cc"],
+            deps=[":rocksdb_test_lib"],
+            extra_compiler_flags=[])
+
+
 cpp_unittest_wrapper(name="util_merge_operators_test",
             srcs=["utilities/util_merge_operators_test.cc"],
             deps=[":rocksdb_test_lib"],

USERS.md

@@ -15,6 +15,25 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
 
 [2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/
 
+## Bilibili
+[Bilibili](bilibili.com) [uses](https://www.alluxio.io/blog/when-ai-meets-alluxio-at-bilibili-building-an-efficient-ai-platform-for-data-preprocessing-and-model-training/) Alluxio to speed up its ML training workloads, and Alluxio uses RocksDB to store its filesystem metadata, so Bilibili uses RocksDB.
+
+Bilibili's [real-time platform](https://www.alibabacloud.com/blog/architecture-and-practices-of-bilibilis-real-time-platform_596676) uses Flink, and uses RocksDB as Flink's state store.
+
+## TikTok
+TikTok, or its parent company ByteDance, uses RocksDB as the storage engine for some storage systems, such as its distributed graph database [ByteGraph](https://vldb.org/pvldb/vol15/p3306-li.pdf). 
+
+Also, TikTok uses [Alluxio](alluxio.io) to [speed up Presto queries](https://www.alluxio.io/resources/videos/improving-presto-performance-with-alluxio-at-tiktok/), and Alluxio stores the files' metadata in RocksDB.
+
+## FoundationDB
+[FoundationDB](https://www.foundationdb.org/) [uses](https://github.com/apple/foundationdb/blob/377f1f692da6ab2fe5bdac57035651db3e5fb66d/fdbserver/KeyValueStoreRocksDB.actor.cpp) RocksDB to implement a [key-value store interface](https://github.com/apple/foundationdb/blob/377f1f692da6ab2fe5bdac57035651db3e5fb66d/fdbserver/KeyValueStoreRocksDB.actor.cpp#L1127) in its server backend.
+
+## Apple
+Apple [uses](https://opensource.apple.com/projects/foundationdb/) FoundationDB, so it also uses RocksDB.
+
+## Snowflake
+Snowflake [uses](https://www.snowflake.com/blog/how-foundationdb-powers-snowflake-metadata-forward/) FoundationDB, so it also uses RocksDB.
+
 ## Microsoft
 The Bing search engine from Microsoft uses RocksDB as the storage engine for its web data platform: https://blogs.bing.com/Engineering-Blog/october-2021/RocksDB-in-Microsoft-Bing
 
@@ -29,6 +48,9 @@ Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasu
 ## Yahoo
 Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa. Learn more about it here: http://yahooeng.tumblr.com/post/120730204806/sherpa-scales-new-heights
 
+## Tencent
+[PaxosStore](https://github.com/Tencent/paxosstore) is a distributed database supporting WeChat. It uses RocksDB as its storage engine.
+
 ## Baidu
 [Apache Doris](http://doris.apache.org/master/en/) is a MPP analytical database engine released by Baidu. It [uses RocksDB](http://doris.apache.org/master/en/administrator-guide/operation/tablet-meta-tool.html) to manage its tablet's metadata.
 
@@ -82,9 +104,18 @@ quasardb uses a heavily tuned RocksDB as its persistence layer.
 ## TiKV
 [TiKV](https://github.com/pingcap/tikv) is a GEO-replicated, high-performance, distributed, transactional key-value database. TiKV is powered by Rust and Raft. TiKV uses RocksDB as its persistence layer.
 
+## TiDB
+[TiDB](https://github.com/pingcap/tidb) uses the TiKV distributed key-value database, so it uses RocksDB.
+
+## PingCAP
+[PingCAP](https://www.pingcap.com/) is the company behind TiDB, its cloud database service uses RocksDB.
+
 ## Apache Spark
 [Spark Structured Streaming](https://docs.databricks.com/structured-streaming/rocksdb-state-store.html) uses RocksDB as the local state store.
 
+## Databricks
+[Databricks](https://www.databricks.com/) [replaces AWS RDS with TiDB](https://www.pingcap.com/case-study/how-databricks-tackles-the-scalability-limit-with-a-mysql-alternative/) for scalability, so it uses RocksDB.
+
 ## Apache Flink
 [Apache Flink](https://flink.apache.org/news/2016/03/08/release-1.0.0.html) uses RocksDB to store state locally on a machine.
 

buckifier/buckify_rocksdb.py

@@ -154,16 +154,9 @@ def generate_targets(repo_path, deps_map):
     # rocksdb_whole_archive_lib
     TARGETS.add_library(
         "rocksdb_whole_archive_lib",
-        src_mk["LIB_SOURCES"] +
-        # always add range_tree, it's only excluded on ppc64, which we don't use internally
-        src_mk["RANGE_TREE_SOURCES"] + src_mk["TOOL_LIB_SOURCES"],
+        [],
         deps=[
-            "//folly/container:f14_hash",
-            "//folly/experimental/coro:blocking_wait",
-            "//folly/experimental/coro:collect",
-            "//folly/experimental/coro:coroutine",
-            "//folly/experimental/coro:task",
-            "//folly/synchronization:distributed_mutex",
+            ":rocksdb_lib",
         ],
         headers=None,
         extra_external_deps="",

build_tools/build_detect_platform

@@ -63,13 +63,7 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
     if [ "$LIB_MODE" == "shared" ]; then
       PIC_BUILD=1
     fi
-    if [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM010" ]; then
-      source "$PWD/build_tools/fbcode_config_platform010.sh"
-    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM009" ]; then
-      source "$PWD/build_tools/fbcode_config_platform009.sh"
-    else
-      source "$PWD/build_tools/fbcode_config_platform009.sh"
-    fi
+    source "$PWD/build_tools/fbcode_config_platform010.sh"
 fi
 
 # Delete existing output, if it exists
@@ -425,7 +419,7 @@ EOF
 
     if ! test $ROCKSDB_DISABLE_JEMALLOC; then
         # Test whether jemalloc is available
-        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o -ljemalloc \
+        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS $LDFLAGS -x c++ - -o test.o -ljemalloc \
           2>/dev/null; then
             # This will enable some preprocessor identifiers in the Makefile
             JEMALLOC=1
@@ -434,12 +428,19 @@ EOF
             WITH_JEMALLOC_FLAG=1
             # check for JEMALLOC installed with HomeBrew
             if [ "$PLATFORM" == "OS_MACOSX" ]; then
+                if [ "$TARGET_ARCHITECTURE" = "arm64" ]; then
+                    # on M1 Macs, homebrew installs here instead of /usr/local
+                    JEMALLOC_PREFIX="/opt/homebrew"
+                else
+                    JEMALLOC_PREFIX="/usr/local"
+                fi
                 if hash brew 2>/dev/null && brew ls --versions jemalloc > /dev/null; then
                     JEMALLOC_VER=$(brew ls --versions jemalloc | tail -n 1 | cut -f 2 -d ' ')
-                    JEMALLOC_INCLUDE="-I/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/include"
-                    JEMALLOC_LIB="/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/lib/libjemalloc_pic.a"
-                    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS $JEMALLOC_LIB"
-                    JAVA_STATIC_LDFLAGS="$JAVA_STATIC_LDFLAGS $JEMALLOC_LIB"
+                    JEMALLOC_INCLUDE="-I${JEMALLOC_PREFIX}/Cellar/jemalloc/${JEMALLOC_VER}/include"
+                    JEMALLOC_LIB="${JEMALLOC_PREFIX}/Cellar/jemalloc/${JEMALLOC_VER}/lib/libjemalloc_pic.a"
+                    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -L${JEMALLOC_PREFIX}/lib $JEMALLOC_LIB"
+                    JAVA_LDFLAGS="$JAVA_LDFLAGS -L${JEMALLOC_PREFIX}/lib $JEMALLOC_LIB"
+                    JAVA_STATIC_LDFLAGS="$JAVA_STATIC_LDFLAGS -L${JEMALLOC_PREFIX}/lib $JEMALLOC_LIB"
                 fi
             fi
         fi
@@ -627,7 +628,7 @@ EOF
   fi
 fi
 
-if test "0$PORTABLE" -eq 0; then
+if [ "$PORTABLE" == "" ] || [ "$PORTABLE" == 0 ]; then
   if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
     # Tune for this POWER processor, treating '+' models as base models
     POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
@@ -650,27 +651,26 @@ if test "0$PORTABLE" -eq 0; then
     COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
   elif [ "$TARGET_OS" == "IOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS"
-  elif [ "$TARGET_OS" == "AIX" ] || [ "$TARGET_OS" == "SunOS" ]; then
-    # TODO: Not sure why we don't use -march=native on these OSes
-    if test "$USE_SSE"; then
-      TRY_SSE_ETC="1"
-    fi
   else
     COMMON_FLAGS="$COMMON_FLAGS -march=native "
   fi
 else
-  # PORTABLE=1
-  if test "$USE_SSE"; then
-    TRY_SSE_ETC="1"
-  fi
-
-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
-    COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
-  fi
-
-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
-    RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
-    COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
+  # PORTABLE specified
+  if [ "$PORTABLE" == 1 ]; then
+    if test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
+      COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
+    elif test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
+      RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
+      COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
+    elif test "$USE_SSE"; then
+      # USE_SSE is DEPRECATED
+      # This is a rough approximation of the old USE_SSE behavior
+      COMMON_FLAGS="$COMMON_FLAGS -march=haswell"
+    fi
+    # Other than those cases, not setting -march= here.
+  else
+    # Assume PORTABLE is a minimum assumed cpu type, e.g. PORTABLE=haswell
+    COMMON_FLAGS="$COMMON_FLAGS -march=${PORTABLE}"
   fi
 
   if [[ "${PLATFORM}" == "OS_MACOSX" ]]; then
@@ -704,101 +704,6 @@ EOF
   fi
 fi
 
-if test "$TRY_SSE_ETC"; then
-  # The USE_SSE flag now means "attempt to compile with widely-available
-  # Intel architecture extensions utilized by specific optimizations in the
-  # source code." It's a qualifier on PORTABLE=1 that means "mostly portable."
-  # It doesn't even really check that your current CPU is compatible.
-  #
-  # SSE4.2 available since nehalem, ca. 2008-2010
-  # Includes POPCNT for BitsSetToOne, BitParity
-  TRY_SSE42="-msse4.2"
-  # PCLMUL available since westmere, ca. 2010-2011
-  TRY_PCLMUL="-mpclmul"
-  # AVX2 available since haswell, ca. 2013-2015
-  TRY_AVX2="-mavx2"
-  # BMI available since haswell, ca. 2013-2015
-  # Primarily for TZCNT for CountTrailingZeroBits
-  TRY_BMI="-mbmi"
-  # LZCNT available since haswell, ca. 2013-2015
-  # For FloorLog2
-  TRY_LZCNT="-mlzcnt"
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <nmmintrin.h>
-  int main() {
-    volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_SSE42 -DHAVE_SSE42"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <wmmintrin.h>
-  int main() {
-    const auto a = _mm_set_epi64x(0, 0);
-    const auto b = _mm_set_epi64x(0, 0);
-    const auto c = _mm_clmulepi64_si128(a, b, 0x00);
-    auto d = _mm_cvtsi128_si64(c);
-    (void)d;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_PCLMUL -DHAVE_PCLMUL"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main() {
-    const auto a = _mm256_setr_epi32(0, 1, 2, 3, 4, 7, 6, 5);
-    const auto b = _mm256_permutevar8x32_epi32(a, a);
-    (void)b;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_AVX2 -DHAVE_AVX2"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use AVX2 intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_BMI -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main(int argc, char *argv[]) {
-    (void)argv;
-    return (int)_tzcnt_u64((uint64_t)argc);
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_BMI -DHAVE_BMI"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use BMI intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_LZCNT -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main(int argc, char *argv[]) {
-    (void)argv;
-    return (int)_lzcnt_u64((uint64_t)argc);
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_LZCNT -DHAVE_LZCNT"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use LZCNT intrinsics, disabling" >&2
-fi
-
 $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o test.o 2>/dev/null <<EOF
   #include <cstdint>
   int main() {

build_tools/dependencies_platform009.sh

@@ -1,22 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/1795efe5f06778c15a92c8f9a2aba5dc496d9d4d/9.x/centos7-native/3bed279
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/7318eaac22659b6ff2fe43918e4b69fd0772a8a7/9.0.0/platform009/651ee30
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/4959b39cfbe5965a37c861c4c327fa7c5c759b87/9.x/platform009/9202ce7
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/45ce3375cdc77ecb2520bbf8f0ecddd3f98efd7a/2.30/platform009/f259413
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/be4de3205e029101b18aa8103daa696c2bef3b19/1.1.3/platform009/7f3b187
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/3c160ac5c67e257501e24c6c1d00ad5e01d73db6/1.2.8/platform009/7f3b187
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/73a237ac5bc0a5f5d67b39b8d253cfebaab88684/1.0.6/platform009/7f3b187
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/6ca38d3c390be2774d61a300f151464bbd632d62/1.9.1/platform009/7f3b187
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/64c58a207d2495e83abc57a500a956df09b79a7c/1.4.x/platform009/ba86d1f
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/824d0a8a5abb5b121afd1b35fc3896407ea50092/2.2.0/platform009/7f3b187
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b62912d333ef33f9760efa6219dbe3fe6abb3b0e/master/platform009/c305944
-NUMA_BASE=/mnt/gvfs/third-party2/numa/0af65f71e23a67bf65dc91b11f95caa39325c432/2.0.11/platform009/7f3b187
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/02486dac347645d31dce116f44e1de3177315be2/1.4/platform009/5191652
-TBB_BASE=/mnt/gvfs/third-party2/tbb/2e0ec671e550bfca347300bf3f789d9c0fff24ad/2018_U5/platform009/7f3b187
-LIBURING_BASE=/mnt/gvfs/third-party2/liburing/70dbd9cfee63a25611417d09433a86d7711b3990/20200729/platform009/7f3b187
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/32b8a2407b634df3f8f948ba373fc4acc6a18296/fb/platform009/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/08634589372fa5f237bfd374e8c644a8364e78c1/2.32/platform009/ba86d1f/
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/6ae525939ad02e5e676855082fbbc7828dbafeac/3.15.0/platform009/7f3b187
-LUA_BASE=/mnt/gvfs/third-party2/lua/162efd9561a3d21f6869f4814011e9cf1b3ff4dc/5.3.4/platform009/a6271c4
-BENCHMARK_BASE=/mnt/gvfs/third-party2/benchmark/30bf49ad6414325e17f3425b0edcb64239427ae3/1.6.1/platform009/7f3b187
-GLOG_BASE=/mnt/gvfs/third-party2/glog/32d751bd5673375b438158717ab6a57c1cc57e3d/0.3.2_fb/platform009/10a364d

build_tools/fbcode_config.sh

@@ -147,7 +147,7 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT"
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"

build_tools/fbcode_config_platform009.sh

@@ -1,170 +0,0 @@
-#!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-#
-# Set environment variables so that we can compile rocksdb using
-# fbcode settings.  It uses the latest g++ and clang compilers and also
-# uses jemalloc
-# Environment variables that change the behavior of this script:
-# PIC_BUILD -- if true, it will only take pic versions of libraries from fbcode. libraries that don't have pic variant will not be included
-
-
-BASEDIR=`dirname $BASH_SOURCE`
-source "$BASEDIR/dependencies_platform009.sh"
-
-CFLAGS=""
-
-# libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/9.3.0 -I $LIBGCC_BASE/include/c++/9.3.0/backward"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
-
-# glibc
-GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIBC_BASE/lib"
-
-if test -z $PIC_BUILD; then
-  MAYBE_PIC=
-else
-  MAYBE_PIC=_pic
-fi
-
-if ! test $ROCKSDB_DISABLE_SNAPPY; then
-  # snappy
-  SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy${MAYBE_PIC}.a"
-  CFLAGS+=" -DSNAPPY"
-fi
-
-if ! test $ROCKSDB_DISABLE_ZLIB; then
-  # location of zlib headers and libraries
-  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-  ZLIB_LIBS=" $ZLIB_BASE/lib/libz${MAYBE_PIC}.a"
-  CFLAGS+=" -DZLIB"
-fi
-
-if ! test $ROCKSDB_DISABLE_BZIP; then
-  # location of bzip headers and libraries
-  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2${MAYBE_PIC}.a"
-  CFLAGS+=" -DBZIP2"
-fi
-
-if ! test $ROCKSDB_DISABLE_LZ4; then
-  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-  LZ4_LIBS=" $LZ4_BASE/lib/liblz4${MAYBE_PIC}.a"
-  CFLAGS+=" -DLZ4"
-fi
-
-if ! test $ROCKSDB_DISABLE_ZSTD; then
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd${MAYBE_PIC}.a"
-  CFLAGS+=" -DZSTD"
-fi
-
-# location of gflags headers and libraries
-GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
-GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags${MAYBE_PIC}.a"
-CFLAGS+=" -DGFLAGS=gflags"
-
-BENCHMARK_INCLUDE=" -I $BENCHMARK_BASE/include/"
-BENCHMARK_LIBS=" $BENCHMARK_BASE/lib/libbenchmark${MAYBE_PIC}.a"
-
-GLOG_INCLUDE=" -I $GLOG_BASE/include/"
-GLOG_LIBS=" $GLOG_BASE/lib/libglog${MAYBE_PIC}.a"
-
-# location of jemalloc
-JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
-JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc${MAYBE_PIC}.a"
-
-# location of numa
-NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-NUMA_LIB=" $NUMA_BASE/lib/libnuma${MAYBE_PIC}.a"
-CFLAGS+=" -DNUMA"
-
-# location of libunwind
-LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind${MAYBE_PIC}.a"
-
-# location of TBB
-TBB_INCLUDE=" -isystem $TBB_BASE/include/"
-TBB_LIBS="$TBB_BASE/lib/libtbb${MAYBE_PIC}.a"
-CFLAGS+=" -DTBB"
-
-# location of LIBURING
-LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
-LIBURING_LIBS="$LIBURING_BASE/lib/liburing${MAYBE_PIC}.a"
-CFLAGS+=" -DLIBURING"
-
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-AS="$BINUTILS/as"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE $BENCHMARK_INCLUDE $GLOG_INCLUDE"
-
-STDLIBS="-L $GCC_BASE/lib64"
-
-CLANG_BIN="$CLANG_BASE/bin"
-CLANG_LIB="$CLANG_BASE/lib"
-CLANG_SRC="$CLANG_BASE/../../src"
-
-CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_SRC/llvm/clang/tools/scan-build/bin/scan-build"
-
-if [ -z "$USE_CLANG" ]; then
-  # gcc
-  CC="$GCC_BASE/bin/gcc"
-  CXX="$GCC_BASE/bin/g++"
-  AR="$GCC_BASE/bin/gcc-ar"
-
-  CFLAGS+=" -B$BINUTILS"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  JEMALLOC=1
-else
-  # clang
-  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
-  CC="$CLANG_BIN/clang"
-  CXX="$CLANG_BIN/clang++"
-  AR="$CLANG_BIN/llvm-ar"
-
-  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
-
-  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"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $CLANG_INCLUDE"
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
-  CFLAGS+=" -Wno-expansion-to-defined "
-  CXXFLAGS="-nostdinc++"
-fi
-
-CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
-CXXFLAGS+=" $CFLAGS"
-
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"
-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"
-
-PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
-PLATFORM_LDFLAGS+=" -B$BINUTILS"
-
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-# lua not supported because it's on track for deprecation, I think
-LUA_PATH=
-LUA_LIB=
-
-export CC CXX AR AS 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_platform010.sh

@@ -154,7 +154,7 @@ CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
 CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_IOURING_PRESENT"
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"

build_tools/regression_build_test.sh

@@ -360,7 +360,7 @@ function send_to_ods {
     echo >&2 "ERROR: Key $key doesn't have a value."
     return
   fi
-  curl --silent "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=$key&value=$value" \
+  curl --silent "https://www.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=$key&value=$value" \
     --connect-timeout 60
 }
 

build_tools/update_dependencies.sh

@@ -104,46 +104,3 @@ get_lib_base valgrind   LATEST platform010
 get_lib_base lua        5.3.4  platform010
 
 git diff $OUTPUT
-
-
-###########################################################
-#                platform009 dependencies                 #
-###########################################################
-
-OUTPUT="$BASEDIR/dependencies_platform009.sh"
-
-rm -f "$OUTPUT"
-touch "$OUTPUT"
-
-echo "Writing dependencies to $OUTPUT"
-
-# Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/9.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/9.0.0/platform009/*/`
-
-log_header
-log_variable GCC_BASE
-log_variable CLANG_BASE
-
-# Libraries locations
-get_lib_base libgcc     9.x     platform009
-get_lib_base glibc      2.30    platform009
-get_lib_base snappy     LATEST  platform009
-get_lib_base zlib       LATEST  platform009
-get_lib_base bzip2      LATEST  platform009
-get_lib_base lz4        LATEST  platform009
-get_lib_base zstd       LATEST  platform009
-get_lib_base gflags     LATEST  platform009
-get_lib_base jemalloc   LATEST  platform009
-get_lib_base numa       LATEST  platform009
-get_lib_base libunwind  LATEST  platform009
-get_lib_base tbb        2018_U5 platform009
-get_lib_base liburing   LATEST  platform009
-get_lib_base benchmark  LATEST  platform009
-
-get_lib_base kernel-headers fb platform009
-get_lib_base binutils   LATEST centos7-native
-get_lib_base valgrind   LATEST platform009
-get_lib_base lua        5.3.4  platform009
-
-git diff $OUTPUT

cache/cache_bench_tool.cc

@@ -77,6 +77,10 @@ DEFINE_bool(lean, false,
             "If true, no additional computation is performed besides cache "
             "operations.");
 
+DEFINE_bool(early_exit, false,
+            "Exit before deallocating most memory. Good for malloc stats, e.g."
+            "MALLOC_CONF=\"stats_print:true\"");
+
 DEFINE_string(secondary_cache_uri, "",
               "Full URI for creating a custom secondary cache object");
 static class std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache> secondary_cache;
@@ -593,6 +597,10 @@ class CacheBench {
       }
       thread->latency_ns_hist.Add(timer.ElapsedNanos());
     }
+    if (FLAGS_early_exit) {
+      MutexLock l(thread->shared->GetMutex());
+      exit(0);
+    }
     if (handle) {
       cache_->Release(handle);
       handle = nullptr;

cache/cache_test.cc

@@ -21,6 +21,7 @@
 #include "test_util/secondary_cache_test_util.h"
 #include "test_util/testharness.h"
 #include "util/coding.h"
+#include "util/hash_containers.h"
 #include "util/string_util.h"
 
 // HyperClockCache only supports 16-byte keys, so some of the tests
@@ -955,6 +956,97 @@ TEST_P(CacheTest, GetChargeAndDeleter) {
   cache_->Release(h1);
 }
 
+namespace {
+bool AreTwoCacheKeysOrdered(Cache* cache) {
+  std::vector<std::string> keys;
+  const auto callback = [&](const Slice& key, Cache::ObjectPtr /*value*/,
+                            size_t /*charge*/,
+                            const Cache::CacheItemHelper* /*helper*/) {
+    keys.push_back(key.ToString());
+  };
+  cache->ApplyToAllEntries(callback, /*opts*/ {});
+  EXPECT_EQ(keys.size(), 2U);
+  EXPECT_NE(keys[0], keys[1]);
+  return keys[0] < keys[1];
+}
+}  // namespace
+
+TEST_P(CacheTest, CacheUniqueSeeds) {
+  // kQuasiRandomHashSeed should generate unique seeds (up to 2 billion before
+  // repeating)
+  UnorderedSet<uint32_t> seeds_seen;
+  // Roughly sqrt(number of possible values) for a decent chance at detecting
+  // a random collision if it's possible (shouldn't be)
+  uint16_t kSamples = 20000;
+  seeds_seen.reserve(kSamples);
+
+  // Hash seed should affect ordering of entries in the table, so we should
+  // have extremely high chance of seeing two entries ordered both ways.
+  bool seen_forward_order = false;
+  bool seen_reverse_order = false;
+
+  for (int i = 0; i < kSamples; ++i) {
+    auto cache = NewCache(2, [=](ShardedCacheOptions& opts) {
+      opts.hash_seed = LRUCacheOptions::kQuasiRandomHashSeed;
+      opts.num_shard_bits = 0;
+      opts.metadata_charge_policy = kDontChargeCacheMetadata;
+    });
+    auto val = cache->GetHashSeed();
+    ASSERT_TRUE(seeds_seen.insert(val).second);
+
+    ASSERT_OK(cache->Insert(EncodeKey(1), nullptr, &kHelper, /*charge*/ 1));
+    ASSERT_OK(cache->Insert(EncodeKey(2), nullptr, &kHelper, /*charge*/ 1));
+
+    if (AreTwoCacheKeysOrdered(cache.get())) {
+      seen_forward_order = true;
+    } else {
+      seen_reverse_order = true;
+    }
+  }
+
+  ASSERT_TRUE(seen_forward_order);
+  ASSERT_TRUE(seen_reverse_order);
+}
+
+TEST_P(CacheTest, CacheHostSeed) {
+  // kHostHashSeed should generate a consistent seed within this process
+  // (and other processes on the same host, but not unit testing that).
+  // And we should be able to use that chosen seed as an explicit option
+  // (for debugging).
+  // And we should verify consistent ordering of entries.
+  uint32_t expected_seed = 0;
+  bool expected_order = false;
+  // 10 iterations -> chance of a random seed falsely appearing consistent
+  // should be low, just 1 in 2^9.
+  for (int i = 0; i < 10; ++i) {
+    auto cache = NewCache(2, [=](ShardedCacheOptions& opts) {
+      if (i != 5) {
+        opts.hash_seed = LRUCacheOptions::kHostHashSeed;
+      } else {
+        // Can be used as explicit seed
+        opts.hash_seed = static_cast<int32_t>(expected_seed);
+        ASSERT_GE(opts.hash_seed, 0);
+      }
+      opts.num_shard_bits = 0;
+      opts.metadata_charge_policy = kDontChargeCacheMetadata;
+    });
+    ASSERT_OK(cache->Insert(EncodeKey(1), nullptr, &kHelper, /*charge*/ 1));
+    ASSERT_OK(cache->Insert(EncodeKey(2), nullptr, &kHelper, /*charge*/ 1));
+    uint32_t val = cache->GetHashSeed();
+    bool order = AreTwoCacheKeysOrdered(cache.get());
+    if (i != 0) {
+      ASSERT_EQ(val, expected_seed);
+      ASSERT_EQ(order, expected_order);
+    } else {
+      expected_seed = val;
+      expected_order = order;
+    }
+  }
+  // Printed for reference in case it's needed to reproduce other unit test
+  // failures on another host
+  fprintf(stderr, "kHostHashSeed -> %u\n", (unsigned)expected_seed);
+}
+
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                         secondary_cache_test_util::GetTestingCacheTypes());
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest,

cache/clock_cache.h

@@ -371,14 +371,127 @@ struct ClockHandle : public ClockHandleBasicData {
   static constexpr uint8_t kMaxCountdown = kHighCountdown;
   // TODO: make these coundown values tuning parameters for eviction?
 
-  // See above
-  std::atomic<uint64_t> meta{};
+  // See above. Mutable for read reference counting.
+  mutable std::atomic<uint64_t> meta{};
 
-  // Anticipating use for SecondaryCache support
-  void* reserved_for_future_use = nullptr;
+  // Whether this is a "deteched" handle that is independently allocated
+  // with `new` (so must be deleted with `delete`).
+  // TODO: ideally this would be packed into some other data field, such
+  // as upper bits of total_charge, but that incurs a measurable performance
+  // regression.
+  bool standalone = false;
+
+  inline bool IsStandalone() const { return standalone; }
+
+  inline void SetStandalone() { standalone = true; }
 };  // struct ClockHandle
 
-class HyperClockTable {
+class BaseClockTable {
+ public:
+  BaseClockTable(CacheMetadataChargePolicy metadata_charge_policy,
+                 MemoryAllocator* allocator,
+                 const Cache::EvictionCallback* eviction_callback,
+                 const uint32_t* hash_seed)
+      : metadata_charge_policy_(metadata_charge_policy),
+        allocator_(allocator),
+        eviction_callback_(*eviction_callback),
+        hash_seed_(*hash_seed) {}
+
+  template <class Table>
+  typename Table::HandleImpl* CreateStandalone(ClockHandleBasicData& proto,
+                                               size_t capacity,
+                                               bool strict_capacity_limit,
+                                               bool allow_uncharged);
+
+  template <class Table>
+  Status Insert(const ClockHandleBasicData& proto,
+                typename Table::HandleImpl** handle, Cache::Priority priority,
+                size_t capacity, bool strict_capacity_limit);
+
+  void Ref(ClockHandle& handle);
+
+  size_t GetOccupancy() const {
+    return occupancy_.load(std::memory_order_relaxed);
+  }
+
+  size_t GetUsage() const { return usage_.load(std::memory_order_relaxed); }
+
+  size_t GetStandaloneUsage() const {
+    return standalone_usage_.load(std::memory_order_relaxed);
+  }
+
+  uint32_t GetHashSeed() const { return hash_seed_; }
+
+#ifndef NDEBUG
+  // Acquire N references
+  void TEST_RefN(ClockHandle& handle, size_t n);
+  // Helper for TEST_ReleaseN
+  void TEST_ReleaseNMinus1(ClockHandle* handle, size_t n);
+#endif
+
+ private:  // fns
+  // Creates a "standalone" handle for returning from an Insert operation that
+  // cannot be completed by actually inserting into the table.
+  // Updates `standalone_usage_` but not `usage_` nor `occupancy_`.
+  template <class HandleImpl>
+  HandleImpl* StandaloneInsert(const ClockHandleBasicData& proto);
+
+  // Helper for updating `usage_` for new entry with given `total_charge`
+  // and evicting if needed under strict_capacity_limit=true rules. This
+  // means the operation might fail with Status::MemoryLimit. If
+  // `need_evict_for_occupancy`, then eviction of at least one entry is
+  // required, and the operation should fail if not possible.
+  // NOTE: Otherwise, occupancy_ is not managed in this function
+  template <class Table>
+  Status ChargeUsageMaybeEvictStrict(size_t total_charge, size_t capacity,
+                                     bool need_evict_for_occupancy,
+                                     typename Table::InsertState& state);
+
+  // Helper for updating `usage_` for new entry with given `total_charge`
+  // and evicting if needed under strict_capacity_limit=false rules. This
+  // means that updating `usage_` always succeeds even if forced to exceed
+  // capacity. If `need_evict_for_occupancy`, then eviction of at least one
+  // entry is required, and the operation should return false if such eviction
+  // is not possible. `usage_` is not updated in that case. Otherwise, returns
+  // true, indicating success.
+  // NOTE: occupancy_ is not managed in this function
+  template <class Table>
+  bool ChargeUsageMaybeEvictNonStrict(size_t total_charge, size_t capacity,
+                                      bool need_evict_for_occupancy,
+                                      typename Table::InsertState& state);
+
+ protected:  // data
+  // We partition the following members into different cache lines
+  // to avoid false sharing among Lookup, Release, Erase and Insert
+  // operations in ClockCacheShard.
+
+  // Clock algorithm sweep pointer.
+  std::atomic<uint64_t> clock_pointer_{};
+
+  ALIGN_AS(CACHE_LINE_SIZE)
+  // Number of elements in the table.
+  std::atomic<size_t> occupancy_{};
+
+  // Memory usage by entries tracked by the cache (including standalone)
+  std::atomic<size_t> usage_{};
+
+  // Part of usage by standalone entries (not in table)
+  std::atomic<size_t> standalone_usage_{};
+
+  ALIGN_AS(CACHE_LINE_SIZE)
+  const CacheMetadataChargePolicy metadata_charge_policy_;
+
+  // From Cache, for deleter
+  MemoryAllocator* const allocator_;
+
+  // A reference to Cache::eviction_callback_
+  const Cache::EvictionCallback& eviction_callback_;
+
+  // A reference to ShardedCacheBase::hash_seed_
+  const uint32_t& hash_seed_;
+};
+
+class HyperClockTable : public BaseClockTable {
  public:
   // Target size to be exactly a common cache line size (see static_assert in
   // clock_cache.cc)
@@ -387,16 +500,6 @@ class HyperClockTable {
     // up in this slot or a higher one.
     std::atomic<uint32_t> displacements{};
 
-    // Whether this is a "deteched" handle that is independently allocated
-    // with `new` (so must be deleted with `delete`).
-    // TODO: ideally this would be packed into some other data field, such
-    // as upper bits of total_charge, but that incurs a measurable performance
-    // regression.
-    bool standalone = false;
-
-    inline bool IsStandalone() const { return standalone; }
-
-    inline void SetStandalone() { standalone = true; }
   };  // struct HandleImpl
 
   struct Opts {
@@ -407,50 +510,49 @@ class HyperClockTable {
                   CacheMetadataChargePolicy metadata_charge_policy,
                   MemoryAllocator* allocator,
                   const Cache::EvictionCallback* eviction_callback,
-                  const Opts& opts);
+                  const uint32_t* hash_seed, const Opts& opts);
   ~HyperClockTable();
 
-  Status Insert(const ClockHandleBasicData& proto, HandleImpl** handle,
-                Cache::Priority priority, size_t capacity,
-                bool strict_capacity_limit);
+  // For BaseClockTable::Insert
+  struct InsertState {};
 
-  HandleImpl* CreateStandalone(ClockHandleBasicData& proto, size_t capacity,
-                               bool strict_capacity_limit,
-                               bool allow_uncharged);
+  void StartInsert(InsertState& state);
+
+  // Returns true iff there is room for the proposed number of entries.
+  bool GrowIfNeeded(size_t new_occupancy, InsertState& state);
+
+  HandleImpl* DoInsert(const ClockHandleBasicData& proto,
+                       uint64_t initial_countdown, bool take_ref,
+                       InsertState& state);
+
+  // Runs the clock eviction algorithm trying to reclaim at least
+  // requested_charge. Returns how much is evicted, which could be less
+  // if it appears impossible to evict the requested amount without blocking.
+  void Evict(size_t requested_charge, size_t* freed_charge, size_t* freed_count,
+             InsertState& state);
 
   HandleImpl* Lookup(const UniqueId64x2& hashed_key);
 
   bool Release(HandleImpl* handle, bool useful, bool erase_if_last_ref);
 
-  void Ref(HandleImpl& handle);
-
   void Erase(const UniqueId64x2& hashed_key);
 
-  void ConstApplyToEntriesRange(std::function<void(const HandleImpl&)> func,
-                                size_t index_begin, size_t index_end,
-                                bool apply_if_will_be_deleted) const;
-
   void EraseUnRefEntries();
 
   size_t GetTableSize() const { return size_t{1} << length_bits_; }
 
-  int GetLengthBits() const { return length_bits_; }
-
-  size_t GetOccupancy() const {
-    return occupancy_.load(std::memory_order_relaxed);
-  }
-
   size_t GetOccupancyLimit() const { return occupancy_limit_; }
 
-  size_t GetUsage() const { return usage_.load(std::memory_order_relaxed); }
+  const HandleImpl* HandlePtr(size_t idx) const { return &array_[idx]; }
 
-  size_t GetStandaloneUsage() const {
-    return standalone_usage_.load(std::memory_order_relaxed);
+#ifndef NDEBUG
+  size_t& TEST_MutableOccupancyLimit() const {
+    return const_cast<size_t&>(occupancy_limit_);
   }
 
-  // Acquire/release N references
-  void TEST_RefN(HandleImpl& handle, size_t n);
+  // Release N references
   void TEST_ReleaseN(HandleImpl* handle, size_t n);
+#endif
 
  private:  // functions
   // Returns x mod 2^{length_bits_}.
@@ -458,28 +560,18 @@ class HyperClockTable {
     return static_cast<size_t>(x) & length_bits_mask_;
   }
 
-  // Runs the clock eviction algorithm trying to reclaim at least
-  // requested_charge. Returns how much is evicted, which could be less
-  // if it appears impossible to evict the requested amount without blocking.
-  inline void Evict(size_t requested_charge, size_t* freed_charge,
-                    size_t* freed_count);
-
-  // Returns the first slot in the probe sequence, starting from the given
-  // probe number, with a handle e such that match(e) is true. At every
-  // step, the function first tests whether match(e) holds. If this is false,
-  // it evaluates abort(e) to decide whether the search should be aborted,
-  // and in the affirmative returns -1. For every handle e probed except
-  // the last one, the function runs update(e).
-  // The probe parameter is modified as follows. We say a probe to a handle
-  // e is aborting if match(e) is false and abort(e) is true. Then the final
-  // value of probe is one more than the last non-aborting probe during the
-  // call. This is so that that the variable can be used to keep track of
-  // progress across consecutive calls to FindSlot.
-  inline HandleImpl* FindSlot(const UniqueId64x2& hashed_key,
-                              std::function<bool(HandleImpl*)> match,
-                              std::function<bool(HandleImpl*)> stop,
-                              std::function<void(HandleImpl*)> update,
-                              size_t& probe);
+  // Returns the first slot in the probe sequence with a handle e such that
+  // match_fn(e) is true. At every step, the function first tests whether
+  // match_fn(e) holds. If this is false, it evaluates abort_fn(e) to decide
+  // whether the search should be aborted, and if so, FindSlot immediately
+  // returns nullptr. For every handle e that is not a match and not aborted,
+  // FindSlot runs update_fn(e, is_last) where is_last is set to true iff that
+  // slot will be the last probed because the next would cycle back to the first
+  // slot probed. This function uses templates instead of std::function to
+  // minimize the risk of heap-allocated closures being created.
+  template <typename MatchFn, typename AbortFn, typename UpdateFn>
+  inline HandleImpl* FindSlot(const UniqueId64x2& hashed_key, MatchFn match_fn,
+                              AbortFn abort_fn, UpdateFn update_fn);
 
   // Re-decrement all displacements in probe path starting from beginning
   // until (not including) the given handle
@@ -492,33 +584,6 @@ class HyperClockTable {
   // before releasing it so that it can be provided to this function.
   inline void ReclaimEntryUsage(size_t total_charge);
 
-  // Helper for updating `usage_` for new entry with given `total_charge`
-  // and evicting if needed under strict_capacity_limit=true rules. This
-  // means the operation might fail with Status::MemoryLimit. If
-  // `need_evict_for_occupancy`, then eviction of at least one entry is
-  // required, and the operation should fail if not possible.
-  // NOTE: Otherwise, occupancy_ is not managed in this function
-  inline Status ChargeUsageMaybeEvictStrict(size_t total_charge,
-                                            size_t capacity,
-                                            bool need_evict_for_occupancy);
-
-  // Helper for updating `usage_` for new entry with given `total_charge`
-  // and evicting if needed under strict_capacity_limit=false rules. This
-  // means that updating `usage_` always succeeds even if forced to exceed
-  // capacity. If `need_evict_for_occupancy`, then eviction of at least one
-  // entry is required, and the operation should return false if such eviction
-  // is not possible. `usage_` is not updated in that case. Otherwise, returns
-  // true, indicating success.
-  // NOTE: occupancy_ is not managed in this function
-  inline bool ChargeUsageMaybeEvictNonStrict(size_t total_charge,
-                                             size_t capacity,
-                                             bool need_evict_for_occupancy);
-
-  // Creates a "standalone" handle for returning from an Insert operation that
-  // cannot be completed by actually inserting into the table.
-  // Updates `standalone_usage_` but not `usage_` nor `occupancy_`.
-  inline HandleImpl* StandaloneInsert(const ClockHandleBasicData& proto);
-
   MemoryAllocator* GetAllocator() const { return allocator_; }
 
   // Returns the number of bits used to hash an element in the hash
@@ -539,30 +604,6 @@ class HyperClockTable {
 
   // Array of slots comprising the hash table.
   const std::unique_ptr<HandleImpl[]> array_;
-
-  // From Cache, for deleter
-  MemoryAllocator* const allocator_;
-
-  // A reference to Cache::eviction_callback_
-  const Cache::EvictionCallback& eviction_callback_;
-
-  // We partition the following members into different cache lines
-  // to avoid false sharing among Lookup, Release, Erase and Insert
-  // operations in ClockCacheShard.
-
-  ALIGN_AS(CACHE_LINE_SIZE)
-  // Clock algorithm sweep pointer.
-  std::atomic<uint64_t> clock_pointer_{};
-
-  ALIGN_AS(CACHE_LINE_SIZE)
-  // Number of elements in the table.
-  std::atomic<size_t> occupancy_{};
-
-  // Memory usage by entries tracked by the cache (including standalone)
-  std::atomic<size_t> usage_{};
-
-  // Part of usage by standalone entries (not in table)
-  std::atomic<size_t> standalone_usage_{};
 };  // class HyperClockTable
 
 // A single shard of sharded cache.
@@ -573,7 +614,7 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
                   CacheMetadataChargePolicy metadata_charge_policy,
                   MemoryAllocator* allocator,
                   const Cache::EvictionCallback* eviction_callback,
-                  const typename Table::Opts& opts);
+                  const uint32_t* hash_seed, const typename Table::Opts& opts);
 
   // For CacheShard concept
   using HandleImpl = typename Table::HandleImpl;
@@ -583,22 +624,23 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
   static inline uint32_t HashPieceForSharding(HashCref hash) {
     return Upper32of64(hash[0]);
   }
-  static inline HashVal ComputeHash(const Slice& key) {
+  static inline HashVal ComputeHash(const Slice& key, uint32_t seed) {
     assert(key.size() == kCacheKeySize);
     HashVal in;
     HashVal out;
     // NOTE: endian dependence
     // TODO: use GetUnaligned?
     std::memcpy(&in, key.data(), kCacheKeySize);
-    BijectiveHash2x64(in[1], in[0], &out[1], &out[0]);
+    BijectiveHash2x64(in[1], in[0] ^ seed, &out[1], &out[0]);
     return out;
   }
 
   // For reconstructing key from hashed_key. Requires the caller to provide
   // backing storage for the Slice in `unhashed`
   static inline Slice ReverseHash(const UniqueId64x2& hashed,
-                                  UniqueId64x2* unhashed) {
+                                  UniqueId64x2* unhashed, uint32_t seed) {
     BijectiveUnhash2x64(hashed[1], hashed[0], &(*unhashed)[1], &(*unhashed)[0]);
+    (*unhashed)[0] ^= seed;
     // NOTE: endian dependence
     return Slice(reinterpret_cast<const char*>(unhashed), kCacheKeySize);
   }
@@ -660,9 +702,14 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
     return Lookup(key, hashed_key);
   }
 
+#ifndef NDEBUG
+  size_t& TEST_MutableOccupancyLimit() const {
+    return table_.TEST_MutableOccupancyLimit();
+  }
   // Acquire/release N references
   void TEST_RefN(HandleImpl* handle, size_t n);
   void TEST_ReleaseN(HandleImpl* handle, size_t n);
+#endif
 
  private:  // data
   Table table_;
@@ -682,10 +729,7 @@ class HyperClockCache
  public:
   using Shard = ClockCacheShard<HyperClockTable>;
 
-  HyperClockCache(size_t capacity, size_t estimated_value_size,
-                  int num_shard_bits, bool strict_capacity_limit,
-                  CacheMetadataChargePolicy metadata_charge_policy,
-                  std::shared_ptr<MemoryAllocator> memory_allocator);
+  explicit HyperClockCache(const HyperClockCacheOptions& opts);
 
   const char* Name() const override { return "HyperClockCache"; }
 

cache/compressed_secondary_cache.cc

@@ -9,7 +9,7 @@
 #include <cstdint>
 #include <memory>
 
-#include "memory/memory_allocator.h"
+#include "memory/memory_allocator_impl.h"
 #include "monitoring/perf_context_imp.h"
 #include "util/compression.h"
 #include "util/string_util.h"
@@ -17,25 +17,16 @@
 namespace ROCKSDB_NAMESPACE {
 
 CompressedSecondaryCache::CompressedSecondaryCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio, double low_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    CompressionType compression_type, uint32_t compress_format_version,
-    bool enable_custom_split_merge,
-    const CacheEntryRoleSet& do_not_compress_roles)
-    : cache_options_(capacity, num_shard_bits, strict_capacity_limit,
-                     high_pri_pool_ratio, low_pri_pool_ratio, memory_allocator,
-                     use_adaptive_mutex, metadata_charge_policy,
-                     compression_type, compress_format_version,
-                     enable_custom_split_merge, do_not_compress_roles) {
-  cache_ =
-      NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
-                  high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-                  metadata_charge_policy, low_pri_pool_ratio);
-}
+    const CompressedSecondaryCacheOptions& opts)
+    : cache_(opts.LRUCacheOptions::MakeSharedCache()),
+      cache_options_(opts),
+      cache_res_mgr_(std::make_shared<ConcurrentCacheReservationManager>(
+          std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
+              cache_))) {}
 
-CompressedSecondaryCache::~CompressedSecondaryCache() { cache_.reset(); }
+CompressedSecondaryCache::~CompressedSecondaryCache() {
+  assert(cache_res_mgr_->GetTotalReservedCacheSize() == 0);
+}
 
 std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
     const Slice& key, const Cache::CacheItemHelper* helper,
@@ -311,31 +302,17 @@ const Cache::CacheItemHelper* CompressedSecondaryCache::GetHelper(
   }
 }
 
-std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio, double low_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    CompressionType compression_type, uint32_t compress_format_version,
-    bool enable_custom_split_merge,
-    const CacheEntryRoleSet& do_not_compress_roles) {
-  return std::make_shared<CompressedSecondaryCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      low_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-      metadata_charge_policy, compression_type, compress_format_version,
-      enable_custom_split_merge, do_not_compress_roles);
+std::shared_ptr<SecondaryCache>
+CompressedSecondaryCacheOptions::MakeSharedSecondaryCache() const {
+  return std::make_shared<CompressedSecondaryCache>(*this);
 }
 
-std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
-    const CompressedSecondaryCacheOptions& opts) {
-  // The secondary_cache is disabled for this LRUCache instance.
-  assert(opts.secondary_cache == nullptr);
-  return NewCompressedSecondaryCache(
-      opts.capacity, opts.num_shard_bits, opts.strict_capacity_limit,
-      opts.high_pri_pool_ratio, opts.low_pri_pool_ratio, opts.memory_allocator,
-      opts.use_adaptive_mutex, opts.metadata_charge_policy,
-      opts.compression_type, opts.compress_format_version,
-      opts.enable_custom_split_merge, opts.do_not_compress_roles);
+Status CompressedSecondaryCache::Deflate(size_t decrease) {
+  return cache_res_mgr_->UpdateCacheReservation(decrease, /*increase=*/true);
+}
+
+Status CompressedSecondaryCache::Inflate(size_t increase) {
+  return cache_res_mgr_->UpdateCacheReservation(increase, /*increase=*/false);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

cache/compressed_secondary_cache.h

@@ -9,8 +9,9 @@
 #include <cstddef>
 #include <memory>
 
+#include "cache/cache_reservation_manager.h"
 #include "cache/lru_cache.h"
-#include "memory/memory_allocator.h"
+#include "memory/memory_allocator_impl.h"
 #include "rocksdb/secondary_cache.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/status.h"
@@ -69,18 +70,8 @@ class CompressedSecondaryCacheResultHandle : public SecondaryCacheResultHandle {
 
 class CompressedSecondaryCache : public SecondaryCache {
  public:
-  CompressedSecondaryCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      double high_pri_pool_ratio, double low_pri_pool_ratio,
-      std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-      bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-      CacheMetadataChargePolicy metadata_charge_policy =
-          kDefaultCacheMetadataChargePolicy,
-      CompressionType compression_type = CompressionType::kLZ4Compression,
-      uint32_t compress_format_version = 2,
-      bool enable_custom_split_merge = false,
-      const CacheEntryRoleSet& do_not_compress_roles = {
-          CacheEntryRole::kFilterBlock});
+  explicit CompressedSecondaryCache(
+      const CompressedSecondaryCacheOptions& opts);
   ~CompressedSecondaryCache() override;
 
   const char* Name() const override { return "CompressedSecondaryCache"; }
@@ -103,8 +94,14 @@ class CompressedSecondaryCache : public SecondaryCache {
 
   Status GetCapacity(size_t& capacity) override;
 
+  Status Deflate(size_t decrease) override;
+
+  Status Inflate(size_t increase) override;
+
   std::string GetPrintableOptions() const override;
 
+  size_t TEST_GetUsage() { return cache_->GetUsage(); }
+
  private:
   friend class CompressedSecondaryCacheTestBase;
   static constexpr std::array<uint16_t, 8> malloc_bin_sizes_{
@@ -137,6 +134,7 @@ class CompressedSecondaryCache : public SecondaryCache {
   std::shared_ptr<Cache> cache_;
   CompressedSecondaryCacheOptions cache_options_;
   mutable port::Mutex capacity_mutex_;
+  std::shared_ptr<ConcurrentCacheReservationManager> cache_res_mgr_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

cache/compressed_secondary_cache_test.cc

@@ -10,11 +10,13 @@
 #include <memory>
 #include <tuple>
 
+#include "cache/secondary_cache_adapter.h"
 #include "memory/jemalloc_nodump_allocator.h"
 #include "rocksdb/convenience.h"
 #include "test_util/secondary_cache_test_util.h"
 #include "test_util/testharness.h"
 #include "test_util/testutil.h"
+#include "util/cast_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -626,8 +628,9 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 
     using CacheValueChunk = CompressedSecondaryCache::CacheValueChunk;
     std::unique_ptr<CompressedSecondaryCache> sec_cache =
-        std::make_unique<CompressedSecondaryCache>(1000, 0, true, 0.5, 0.0,
-                                                   allocator);
+        std::make_unique<CompressedSecondaryCache>(
+            CompressedSecondaryCacheOptions(1000, 0, true, 0.5, 0.0,
+                                            allocator));
     Random rnd(301);
     // 8500 = 8169 + 233 + 98, so there should be 3 chunks after split.
     size_t str_size{8500};
@@ -678,7 +681,8 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     std::string str = str1 + str2 + str3;
 
     std::unique_ptr<CompressedSecondaryCache> sec_cache =
-        std::make_unique<CompressedSecondaryCache>(1000, 0, true, 0.5, 0.0);
+        std::make_unique<CompressedSecondaryCache>(
+            CompressedSecondaryCacheOptions(1000, 0, true, 0.5, 0.0));
     size_t charge{0};
     CacheAllocationPtr value =
         sec_cache->MergeChunksIntoValue(chunks_head, charge);
@@ -708,8 +712,9 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 
     using CacheValueChunk = CompressedSecondaryCache::CacheValueChunk;
     std::unique_ptr<CompressedSecondaryCache> sec_cache =
-        std::make_unique<CompressedSecondaryCache>(1000, 0, true, 0.5, 0.0,
-                                                   allocator);
+        std::make_unique<CompressedSecondaryCache>(
+            CompressedSecondaryCacheOptions(1000, 0, true, 0.5, 0.0,
+                                            allocator));
     Random rnd(301);
     // 8500 = 8169 + 233 + 98, so there should be 3 chunks after split.
     size_t str_size{8500};
@@ -971,6 +976,97 @@ TEST_P(CompressedSecondaryCacheTest, SplictValueAndMergeChunksTest) {
   SplictValueAndMergeChunksTest();
 }
 
+class CompressedSecCacheTestWithTiered : public ::testing::Test {
+ public:
+  CompressedSecCacheTestWithTiered() {
+    LRUCacheOptions lru_opts;
+    TieredVolatileCacheOptions opts;
+    lru_opts.capacity = 70 << 20;
+    opts.cache_opts = &lru_opts;
+    opts.cache_type = PrimaryCacheType::kCacheTypeLRU;
+    opts.comp_cache_opts.capacity = 30 << 20;
+    cache_ = NewTieredVolatileCache(opts);
+    cache_res_mgr_ =
+        std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
+            cache_);
+  }
+
+ protected:
+  CacheReservationManager* cache_res_mgr() { return cache_res_mgr_.get(); }
+
+  Cache* GetCache() {
+    return static_cast_with_check<CacheWithSecondaryAdapter, Cache>(
+               cache_.get())
+        ->TEST_GetCache();
+  }
+
+  SecondaryCache* GetSecondaryCache() {
+    return static_cast_with_check<CacheWithSecondaryAdapter, Cache>(
+               cache_.get())
+        ->TEST_GetSecondaryCache();
+  }
+
+  size_t GetPercent(size_t val, unsigned int percent) {
+    return static_cast<size_t>(val * percent / 100);
+  }
+
+ private:
+  std::shared_ptr<Cache> cache_;
+  std::shared_ptr<CacheReservationManager> cache_res_mgr_;
+};
+
+bool CacheUsageWithinBounds(size_t val1, size_t val2, size_t error) {
+  return ((val1 < (val2 + error)) && (val1 > (val2 - error)));
+}
+
+TEST_F(CompressedSecCacheTestWithTiered, CacheReservationManager) {
+  CompressedSecondaryCache* sec_cache =
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+
+  // Use EXPECT_PRED3 instead of EXPECT_NEAR to void too many size_t to
+  // double explicit casts
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+
+  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(10 << 20));
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (37 << 20),
+               GetPercent(37 << 20, 1));
+  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (3 << 20),
+               GetPercent(3 << 20, 1));
+
+  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(0));
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+}
+
+TEST_F(CompressedSecCacheTestWithTiered,
+       CacheReservationManagerMultipleUpdate) {
+  CompressedSecondaryCache* sec_cache =
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+
+  int i;
+  for (i = 0; i < 10; ++i) {
+    ASSERT_OK(cache_res_mgr()->UpdateCacheReservation((1 + i) << 20));
+  }
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (37 << 20),
+               GetPercent(37 << 20, 1));
+  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (3 << 20),
+               GetPercent(3 << 20, 1));
+
+  for (i = 10; i > 0; --i) {
+    ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(((i - 1) << 20)));
+  }
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

cache/lru_cache.cc

@@ -16,7 +16,7 @@
 
 #include "cache/secondary_cache_adapter.h"
 #include "monitoring/perf_context_imp.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "port/lang.h"
 #include "util/distributed_mutex.h"
 
@@ -646,23 +646,15 @@ void LRUCacheShard::AppendPrintableOptions(std::string& str) const {
   str.append(buffer);
 }
 
-LRUCache::LRUCache(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit, double high_pri_pool_ratio,
-                   double low_pri_pool_ratio,
-                   std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex,
-                   CacheMetadataChargePolicy metadata_charge_policy)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
-                   std::move(allocator)) {
+LRUCache::LRUCache(const LRUCacheOptions& opts) : ShardedCache(opts) {
   size_t per_shard = GetPerShardCapacity();
   MemoryAllocator* alloc = memory_allocator();
-  const EvictionCallback* eviction_callback = &eviction_callback_;
-  InitShards([=](LRUCacheShard* cs) {
-    new (cs) LRUCacheShard(per_shard, strict_capacity_limit,
-                           high_pri_pool_ratio, low_pri_pool_ratio,
-                           use_adaptive_mutex, metadata_charge_policy,
-                           /* max_upper_hash_bits */ 32 - num_shard_bits, alloc,
-                           eviction_callback);
+  InitShards([&](LRUCacheShard* cs) {
+    new (cs) LRUCacheShard(per_shard, opts.strict_capacity_limit,
+                           opts.high_pri_pool_ratio, opts.low_pri_pool_ratio,
+                           opts.use_adaptive_mutex, opts.metadata_charge_policy,
+                           /* max_upper_hash_bits */ 32 - opts.num_shard_bits,
+                           alloc, &eviction_callback_);
   });
 }
 
@@ -692,13 +684,7 @@ double LRUCache::GetHighPriPoolRatio() {
 
 }  // namespace lru_cache
 
-std::shared_ptr<Cache> NewLRUCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    const std::shared_ptr<SecondaryCache>& secondary_cache,
-    double low_pri_pool_ratio) {
+std::shared_ptr<Cache> LRUCacheOptions::MakeSharedCache() const {
   if (num_shard_bits >= 20) {
     return nullptr;  // The cache cannot be sharded into too many fine pieces.
   }
@@ -714,36 +700,24 @@ std::shared_ptr<Cache> NewLRUCache(
     // Invalid high_pri_pool_ratio and low_pri_pool_ratio combination
     return nullptr;
   }
-  if (num_shard_bits < 0) {
-    num_shard_bits = GetDefaultCacheShardBits(capacity);
+  // For sanitized options
+  LRUCacheOptions opts = *this;
+  if (opts.num_shard_bits < 0) {
+    opts.num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  std::shared_ptr<Cache> cache = std::make_shared<LRUCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      low_pri_pool_ratio, std::move(memory_allocator), use_adaptive_mutex,
-      metadata_charge_policy);
+  std::shared_ptr<Cache> cache = std::make_shared<LRUCache>(opts);
   if (secondary_cache) {
     cache = std::make_shared<CacheWithSecondaryAdapter>(cache, secondary_cache);
   }
   return cache;
 }
 
-std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
-  return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
-                     cache_opts.strict_capacity_limit,
-                     cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-                     cache_opts.metadata_charge_policy,
-                     cache_opts.secondary_cache, cache_opts.low_pri_pool_ratio);
-}
-
-std::shared_ptr<Cache> NewLRUCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    double low_pri_pool_ratio) {
-  return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
-                     high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-                     metadata_charge_policy, nullptr, low_pri_pool_ratio);
+std::shared_ptr<RowCache> LRUCacheOptions::MakeSharedRowCache() const {
+  if (secondary_cache) {
+    // Not allowed for a RowCache
+    return nullptr;
+  }
+  // Works while RowCache is an alias for Cache
+  return MakeSharedCache();
 }
 }  // namespace ROCKSDB_NAMESPACE

cache/lru_cache.h

@@ -279,8 +279,8 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShardBase {
   using HashCref = uint32_t;
 
  public:  // Function definitions expected as parameter to ShardedCache
-  static inline HashVal ComputeHash(const Slice& key) {
-    return Lower32of64(GetSliceNPHash64(key));
+  static inline HashVal ComputeHash(const Slice& key, uint32_t seed) {
+    return Lower32of64(GetSliceNPHash64(key, seed));
   }
 
   // Separate from constructor so caller can easily make an array of LRUCache
@@ -446,12 +446,7 @@ class LRUCache
 #endif
     : public ShardedCache<LRUCacheShard> {
  public:
-  LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-           double high_pri_pool_ratio, double low_pri_pool_ratio,
-           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
+  explicit LRUCache(const LRUCacheOptions& opts);
   const char* Name() const override { return "LRUCache"; }
   ObjectPtr Value(Handle* handle) override;
   size_t GetCharge(Handle* handle) const override;

cache/lru_cache_test.cc

@@ -397,7 +397,7 @@ class ClockCacheTest : public testing::Test {
     opts.estimated_value_size = 1;
     new (shard_)
         Shard(capacity, strict_capacity_limit, kDontChargeCacheMetadata,
-              /*allocator*/ nullptr, &eviction_callback_, opts);
+              /*allocator*/ nullptr, &eviction_callback_, &hash_seed_, opts);
   }
 
   Status Insert(const UniqueId64x2& hashed_key,
@@ -455,6 +455,7 @@ class ClockCacheTest : public testing::Test {
 
  private:
   Cache::EvictionCallback eviction_callback_;
+  uint32_t hash_seed_ = 0;
 };
 
 TEST_F(ClockCacheTest, Misc) {
@@ -714,6 +715,62 @@ TEST_F(ClockCacheTest, ClockCounterOverflowTest) {
   ASSERT_EQ(val.deleted, 1);
 }
 
+TEST_F(ClockCacheTest, ClockTableFull) {
+  // Force clock cache table to fill up (not usually allowed) in order
+  // to test full probe sequence that is theoretically possible due to
+  // parallel operations
+  NewShard(6, /*strict_capacity_limit*/ false);
+  size_t size = shard_->GetTableAddressCount();
+  ASSERT_LE(size + 3, 256);  // for using char keys
+  // Modify occupancy and capacity limits to attempt insert on full
+  shard_->TEST_MutableOccupancyLimit() = size + 100;
+  shard_->SetCapacity(size + 100);
+
+  DeleteCounter val;
+  std::vector<HandleImpl*> handles;
+  // NOTE: the three extra insertions should create standalone entries
+  for (size_t i = 0; i < size + 3; ++i) {
+    UniqueId64x2 hkey = TestHashedKey(static_cast<char>(i));
+    ASSERT_OK(shard_->Insert(TestKey(hkey), hkey, &val, &kDeleteCounterHelper,
+                             1, &handles.emplace_back(),
+                             Cache::Priority::HIGH));
+  }
+
+  for (size_t i = 0; i < size + 3; ++i) {
+    UniqueId64x2 hkey = TestHashedKey(static_cast<char>(i));
+    HandleImpl* h = shard_->Lookup(TestKey(hkey), hkey);
+    if (i < size) {
+      ASSERT_NE(h, nullptr);
+      shard_->Release(h);
+    } else {
+      // Standalone entries not visible by lookup
+      ASSERT_EQ(h, nullptr);
+    }
+  }
+
+  for (size_t i = 0; i < size + 3; ++i) {
+    ASSERT_NE(handles[i], nullptr);
+    shard_->Release(handles[i]);
+    if (i < size) {
+      // Everything still in cache
+      ASSERT_EQ(val.deleted, 0);
+    } else {
+      // Standalone entries freed on release
+      ASSERT_EQ(val.deleted, i + 1 - size);
+    }
+  }
+
+  for (size_t i = size + 3; i > 0; --i) {
+    UniqueId64x2 hkey = TestHashedKey(static_cast<char>(i - 1));
+    shard_->Erase(TestKey(hkey), hkey);
+    if (i - 1 > size) {
+      ASSERT_EQ(val.deleted, 3);
+    } else {
+      ASSERT_EQ(val.deleted, 3 + size - (i - 1));
+    }
+  }
+}
+
 // This test is mostly to exercise some corner case logic, by forcing two
 // keys to have the same hash, and more
 TEST_F(ClockCacheTest, CollidingInsertEraseTest) {

cache/secondary_cache_adapter.cc

@@ -6,6 +6,7 @@
 #include "cache/secondary_cache_adapter.h"
 
 #include "monitoring/perf_context_imp.h"
+#include "util/cast_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -18,20 +19,98 @@ const Dummy kDummy{};
 Cache::ObjectPtr const kDummyObj = const_cast<Dummy*>(&kDummy);
 }  // namespace
 
+// When CacheWithSecondaryAdapter is constructed with the distribute_cache_res
+// parameter set to true, it manages the entire memory budget across the
+// primary and secondary cache. The secondary cache is assumed to be in
+// memory, such as the CompressedSecondaryCache. When a placeholder entry
+// is inserted by a CacheReservationManager instance to reserve memory,
+// the CacheWithSecondaryAdapter ensures that the reservation is distributed
+// proportionally across the primary/secondary caches.
+//
+// The primary block cache is initially sized to the sum of the primary cache
+// budget + teh secondary cache budget, as follows -
+//   |---------    Primary Cache Configured Capacity  -----------|
+//   |---Secondary Cache Budget----|----Primary Cache Budget-----|
+//
+// A ConcurrentCacheReservationManager member in the CacheWithSecondaryAdapter,
+// pri_cache_res_,
+// is used to help with tracking the distribution of memory reservations.
+// Initially, it accounts for the entire secondary cache budget as a
+// reservation against the primary cache. This shrinks the usable capacity of
+// the primary cache to the budget that the user originally desired.
+//
+//   |--Reservation for Sec Cache--|-Pri Cache Usable Capacity---|
+//
+// When a reservation placeholder is inserted into the adapter, it is inserted
+// directly into the primary cache. This means the entire charge of the
+// placeholder is counted against the primary cache. To compensate and count
+// a portion of it against the secondary cache, the secondary cache Deflate()
+// method is called to shrink it. Since the Deflate() causes the secondary
+// actual usage to shrink, it is refelcted here by releasing an equal amount
+// from the pri_cache_res_ reservation. The Deflate() in the secondary cache
+// can be, but is not required to be, implemented using its own cache
+// reservation manager.
+//
+// For example, if the pri/sec ratio is 70/30, and the combined capacity is
+// 100MB, the intermediate and final  state after inserting a reservation
+// placeholder for 10MB would be as follows -
+//
+//   |-Reservation for Sec Cache-|-Pri Cache Usable Capacity-|---R---|
+// 1. After inserting the placeholder in primary
+//   |-------  30MB -------------|------- 60MB -------------|-10MB--|
+// 2. After deflating the secondary and adjusting the reservation for
+//    secondary against the primary
+//   |-------  27MB -------------|------- 63MB -------------|-10MB--|
+//
+// Likewise, when the user inserted placeholder is released, the secondary
+// cache Inflate() method is called to grow it, and the pri_cache_res_
+// reservation is increased by an equal amount.
+//
+// Another way of implementing this would have been to simply split the user
+// reservation into primary and seconary components. However, this would
+// require allocating a structure to track the associated secondary cache
+// reservation, which adds some complexity and overhead.
+//
 CacheWithSecondaryAdapter::CacheWithSecondaryAdapter(
     std::shared_ptr<Cache> target,
-    std::shared_ptr<SecondaryCache> secondary_cache)
+    std::shared_ptr<SecondaryCache> secondary_cache, bool distribute_cache_res)
     : CacheWrapper(std::move(target)),
-      secondary_cache_(std::move(secondary_cache)) {
+      secondary_cache_(std::move(secondary_cache)),
+      distribute_cache_res_(distribute_cache_res) {
   target_->SetEvictionCallback([this](const Slice& key, Handle* handle) {
     return EvictionHandler(key, handle);
   });
+  if (distribute_cache_res_) {
+    size_t sec_capacity = 0;
+    pri_cache_res_ = std::make_shared<ConcurrentCacheReservationManager>(
+        std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
+            target_));
+    Status s = secondary_cache_->GetCapacity(sec_capacity);
+    assert(s.ok());
+    // Initially, the primary cache is sized to uncompressed cache budget plsu
+    // compressed secondary cache budget. The secondary cache budget is then
+    // taken away from the primary cache through cache reservations. Later,
+    // when a placeholder entry is inserted by the caller, its inserted
+    // into the primary cache and the portion that should be assigned to the
+    // secondary cache is freed from the reservation.
+    s = pri_cache_res_->UpdateCacheReservation(sec_capacity);
+    assert(s.ok());
+    sec_cache_res_ratio_ = (double)sec_capacity / target_->GetCapacity();
+  }
 }
 
 CacheWithSecondaryAdapter::~CacheWithSecondaryAdapter() {
   // `*this` will be destroyed before `*target_`, so we have to prevent
   // use after free
   target_->SetEvictionCallback({});
+#ifndef NDEBUG
+  if (distribute_cache_res_) {
+    size_t sec_capacity = 0;
+    Status s = secondary_cache_->GetCapacity(sec_capacity);
+    assert(s.ok());
+    assert(pri_cache_res_->GetTotalReservedCacheSize() == sec_capacity);
+  }
+#endif  // NDEBUG
 }
 
 bool CacheWithSecondaryAdapter::EvictionHandler(const Slice& key,
@@ -95,8 +174,7 @@ Cache::Handle* CacheWithSecondaryAdapter::Promote(
   PERF_COUNTER_ADD(secondary_cache_hit_count, 1);
   RecordTick(stats, SECONDARY_CACHE_HITS);
 
-  // FIXME? using charge=Size() is suspicious but inherited from older
-  // implementation
+  // Note: SecondaryCache::Size() is really charge (from the CreateCallback)
   size_t charge = secondary_handle->Size();
   Handle* result = nullptr;
   // Insert into primary cache, possibly as a standalone+dummy entries.
@@ -137,6 +215,22 @@ Cache::Handle* CacheWithSecondaryAdapter::Promote(
   return result;
 }
 
+Status CacheWithSecondaryAdapter::Insert(const Slice& key, ObjectPtr value,
+                                         const CacheItemHelper* helper,
+                                         size_t charge, Handle** handle,
+                                         Priority priority) {
+  Status s = target_->Insert(key, value, helper, charge, handle, priority);
+  if (s.ok() && value == nullptr && distribute_cache_res_) {
+    size_t sec_charge = static_cast<size_t>(charge * (sec_cache_res_ratio_));
+    s = secondary_cache_->Deflate(sec_charge);
+    assert(s.ok());
+    s = pri_cache_res_->UpdateCacheReservation(sec_charge, /*increase=*/false);
+    assert(s.ok());
+  }
+
+  return s;
+}
+
 Cache::Handle* CacheWithSecondaryAdapter::Lookup(const Slice& key,
                                                  const CacheItemHelper* helper,
                                                  CreateContext* create_context,
@@ -163,6 +257,22 @@ Cache::Handle* CacheWithSecondaryAdapter::Lookup(const Slice& key,
   return result;
 }
 
+bool CacheWithSecondaryAdapter::Release(Handle* handle,
+                                        bool erase_if_last_ref) {
+  if (erase_if_last_ref) {
+    ObjectPtr v = target_->Value(handle);
+    if (v == nullptr && distribute_cache_res_) {
+      size_t charge = target_->GetCharge(handle);
+      size_t sec_charge = static_cast<size_t>(charge * (sec_cache_res_ratio_));
+      Status s = secondary_cache_->Inflate(sec_charge);
+      assert(s.ok());
+      s = pri_cache_res_->UpdateCacheReservation(sec_charge, /*increase=*/true);
+      assert(s.ok());
+    }
+  }
+  return target_->Release(handle, erase_if_last_ref);
+}
+
 Cache::ObjectPtr CacheWithSecondaryAdapter::Value(Handle* handle) {
   ObjectPtr v = target_->Value(handle);
   // TODO with stacked secondaries: might fail in EvictionHandler
@@ -266,7 +376,7 @@ void CacheWithSecondaryAdapter::WaitAll(AsyncLookupHandle* async_handles,
     for (AsyncLookupHandle* cur : my_pending) {
       my_secondary_handles.push_back(cur->pending_handle);
     }
-    secondary_cache_->WaitAll(my_secondary_handles);
+    secondary_cache_->WaitAll(std::move(my_secondary_handles));
   }
 
   // Process results
@@ -293,4 +403,31 @@ const char* CacheWithSecondaryAdapter::Name() const {
   // a secondary cache. So we pretend to be that cache
   return target_->Name();
 }
+
+std::shared_ptr<Cache> NewTieredVolatileCache(
+    TieredVolatileCacheOptions& opts) {
+  if (!opts.cache_opts) {
+    return nullptr;
+  }
+
+  std::shared_ptr<Cache> cache;
+  if (opts.cache_type == PrimaryCacheType::kCacheTypeLRU) {
+    LRUCacheOptions cache_opts =
+        *(static_cast_with_check<LRUCacheOptions, ShardedCacheOptions>(
+            opts.cache_opts));
+    cache_opts.capacity += opts.comp_cache_opts.capacity;
+    cache = cache_opts.MakeSharedCache();
+  } else if (opts.cache_type == PrimaryCacheType::kCacheTypeHCC) {
+    HyperClockCacheOptions cache_opts =
+        *(static_cast_with_check<HyperClockCacheOptions, ShardedCacheOptions>(
+            opts.cache_opts));
+    cache = cache_opts.MakeSharedCache();
+  } else {
+    return nullptr;
+  }
+  std::shared_ptr<SecondaryCache> sec_cache;
+  sec_cache = NewCompressedSecondaryCache(opts.comp_cache_opts);
+
+  return std::make_shared<CacheWithSecondaryAdapter>(cache, sec_cache, true);
+}
 }  // namespace ROCKSDB_NAMESPACE

cache/secondary_cache_adapter.h

@@ -5,6 +5,7 @@
 
 #pragma once
 
+#include "cache/cache_reservation_manager.h"
 #include "rocksdb/secondary_cache.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -13,15 +14,24 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
  public:
   explicit CacheWithSecondaryAdapter(
       std::shared_ptr<Cache> target,
-      std::shared_ptr<SecondaryCache> secondary_cache);
+      std::shared_ptr<SecondaryCache> secondary_cache,
+      bool distribute_cache_res = false);
 
   ~CacheWithSecondaryAdapter() override;
 
+  Status Insert(const Slice& key, ObjectPtr value,
+                const CacheItemHelper* helper, size_t charge,
+                Handle** handle = nullptr,
+                Priority priority = Priority::LOW) override;
+
   Handle* Lookup(const Slice& key, const CacheItemHelper* helper,
                  CreateContext* create_context,
                  Priority priority = Priority::LOW,
                  Statistics* stats = nullptr) override;
 
+  using Cache::Release;
+  bool Release(Handle* handle, bool erase_if_last_ref = false) override;
+
   ObjectPtr Value(Handle* handle) override;
 
   void StartAsyncLookup(AsyncLookupHandle& async_handle) override;
@@ -32,6 +42,10 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
 
   const char* Name() const override;
 
+  Cache* TEST_GetCache() { return target_.get(); }
+
+  SecondaryCache* TEST_GetSecondaryCache() { return secondary_cache_.get(); }
+
  private:
   bool EvictionHandler(const Slice& key, Handle* handle);
 
@@ -47,6 +61,16 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
   void CleanupCacheObject(ObjectPtr obj, const CacheItemHelper* helper);
 
   std::shared_ptr<SecondaryCache> secondary_cache_;
+  // Whether to proportionally distribute cache memory reservations, i.e
+  // placeholder entries with null value and a non-zero charge, across
+  // the primary and secondary caches.
+  bool distribute_cache_res_;
+  // A cache reservation manager to keep track of secondary cache memory
+  // usage by reserving equivalent capacity against the primary cache
+  std::shared_ptr<ConcurrentCacheReservationManager> pri_cache_res_;
+  // Fraction of a cache memory reservation to be assigned to the secondary
+  // cache
+  double sec_cache_res_ratio_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

cache/sharded_cache.cc

@@ -13,20 +13,57 @@
 #include <cstdint>
 #include <memory>
 
+#include "env/unique_id_gen.h"
+#include "rocksdb/env.h"
 #include "util/hash.h"
 #include "util/math.h"
 #include "util/mutexlock.h"
 
 namespace ROCKSDB_NAMESPACE {
+namespace {
+// The generated seeds must fit in 31 bits so that
+// ShardedCacheOptions::hash_seed can be set to it explicitly, for
+// diagnostic/debugging purposes.
+constexpr uint32_t kSeedMask = 0x7fffffff;
+uint32_t DetermineSeed(int32_t hash_seed_option) {
+  if (hash_seed_option >= 0) {
+    // User-specified exact seed
+    return static_cast<uint32_t>(hash_seed_option);
+  }
+  static SemiStructuredUniqueIdGen gen;
+  if (hash_seed_option == ShardedCacheOptions::kHostHashSeed) {
+    std::string hostname;
+    Status s = Env::Default()->GetHostNameString(&hostname);
+    if (s.ok()) {
+      return GetSliceHash(hostname) & kSeedMask;
+    } else {
+      // Fall back on something stable within the process.
+      return static_cast<uint32_t>(gen.GetBaseUpper()) & kSeedMask;
+    }
+  } else {
+    // for kQuasiRandomHashSeed and fallback
+    uint32_t val = gen.GenerateNext<uint32_t>() & kSeedMask;
+    // Perform some 31-bit bijective transformations so that we get
+    // quasirandom, not just incrementing. (An incrementing seed from a
+    // random starting point would be fine, but hard to describe in a name.)
+    // See https://en.wikipedia.org/wiki/Quasirandom and using a murmur-like
+    // transformation here for our bijection in the lower 31 bits.
+    // See https://en.wikipedia.org/wiki/MurmurHash
+    val *= /*31-bit prime*/ 1150630961;
+    val ^= (val & kSeedMask) >> 17;
+    val *= /*31-bit prime*/ 1320603883;
+    return val & kSeedMask;
+  }
+}
+}  // namespace
 
-ShardedCacheBase::ShardedCacheBase(size_t capacity, int num_shard_bits,
-                                   bool strict_capacity_limit,
-                                   std::shared_ptr<MemoryAllocator> allocator)
-    : Cache(std::move(allocator)),
+ShardedCacheBase::ShardedCacheBase(const ShardedCacheOptions& opts)
+    : Cache(opts.memory_allocator),
       last_id_(1),
-      shard_mask_((uint32_t{1} << num_shard_bits) - 1),
-      strict_capacity_limit_(strict_capacity_limit),
-      capacity_(capacity) {}
+      shard_mask_((uint32_t{1} << opts.num_shard_bits) - 1),
+      hash_seed_(DetermineSeed(opts.hash_seed)),
+      strict_capacity_limit_(opts.strict_capacity_limit),
+      capacity_(opts.capacity) {}
 
 size_t ShardedCacheBase::ComputePerShardCapacity(size_t capacity) const {
   uint32_t num_shards = GetNumShards();

cache/sharded_cache.h

@@ -34,8 +34,8 @@ class CacheShardBase {
   std::string GetPrintableOptions() const { return ""; }
   using HashVal = uint64_t;
   using HashCref = uint64_t;
-  static inline HashVal ComputeHash(const Slice& key) {
-    return GetSliceNPHash64(key);
+  static inline HashVal ComputeHash(const Slice& key, uint32_t seed) {
+    return GetSliceNPHash64(key, seed);
   }
   static inline uint32_t HashPieceForSharding(HashCref hash) {
     return Lower32of64(hash);
@@ -89,9 +89,7 @@ class CacheShardBase {
 // Portions of ShardedCache that do not depend on the template parameter
 class ShardedCacheBase : public Cache {
  public:
-  ShardedCacheBase(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit,
-                   std::shared_ptr<MemoryAllocator> memory_allocator);
+  explicit ShardedCacheBase(const ShardedCacheOptions& opts);
   virtual ~ShardedCacheBase() = default;
 
   int GetNumShardBits() const;
@@ -106,6 +104,8 @@ class ShardedCacheBase : public Cache {
   size_t GetUsage(Handle* handle) const override;
   std::string GetPrintableOptions() const override;
 
+  uint32_t GetHashSeed() const override { return hash_seed_; }
+
  protected:  // fns
   virtual void AppendPrintableOptions(std::string& str) const = 0;
   size_t GetPerShardCapacity() const;
@@ -114,6 +114,7 @@ class ShardedCacheBase : public Cache {
  protected:                        // data
   std::atomic<uint64_t> last_id_;  // For NewId
   const uint32_t shard_mask_;
+  const uint32_t hash_seed_;
 
   // Dynamic configuration parameters, guarded by config_mutex_
   bool strict_capacity_limit_;
@@ -134,10 +135,8 @@ class ShardedCache : public ShardedCacheBase {
   using HashCref = typename CacheShard::HashCref;
   using HandleImpl = typename CacheShard::HandleImpl;
 
-  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-               std::shared_ptr<MemoryAllocator> allocator)
-      : ShardedCacheBase(capacity, num_shard_bits, strict_capacity_limit,
-                         allocator),
+  explicit ShardedCache(const ShardedCacheOptions& opts)
+      : ShardedCacheBase(opts),
         shards_(reinterpret_cast<CacheShard*>(port::cacheline_aligned_alloc(
             sizeof(CacheShard) * GetNumShards()))),
         destroy_shards_in_dtor_(false) {}
@@ -175,7 +174,7 @@ class ShardedCache : public ShardedCacheBase {
                 size_t charge, Handle** handle = nullptr,
                 Priority priority = Priority::LOW) override {
     assert(helper);
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     auto h_out = reinterpret_cast<HandleImpl**>(handle);
     return GetShard(hash).Insert(key, hash, obj, helper, charge, h_out,
                                  priority);
@@ -185,7 +184,7 @@ class ShardedCache : public ShardedCacheBase {
                            const CacheItemHelper* helper, size_t charge,
                            bool allow_uncharged) override {
     assert(helper);
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     HandleImpl* result = GetShard(hash).CreateStandalone(
         key, hash, obj, helper, charge, allow_uncharged);
     return reinterpret_cast<Handle*>(result);
@@ -195,14 +194,14 @@ class ShardedCache : public ShardedCacheBase {
                  CreateContext* create_context = nullptr,
                  Priority priority = Priority::LOW,
                  Statistics* stats = nullptr) override {
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     HandleImpl* result = GetShard(hash).Lookup(key, hash, helper,
                                                create_context, priority, stats);
     return reinterpret_cast<Handle*>(result);
   }
 
   void Erase(const Slice& key) override {
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     GetShard(hash).Erase(key, hash);
   }
 
@@ -226,7 +225,7 @@ class ShardedCache : public ShardedCacheBase {
     return SumOverShards2(&CacheShard::GetPinnedUsage);
   }
   size_t GetOccupancyCount() const override {
-    return SumOverShards2(&CacheShard::GetPinnedUsage);
+    return SumOverShards2(&CacheShard::GetOccupancyCount);
   }
   size_t GetTableAddressCount() const override {
     return SumOverShards2(&CacheShard::GetTableAddressCount);

coverage/coverage_test.sh

@@ -12,7 +12,7 @@ fi
 ROOT=".."
 # Fetch right version of gcov
 if [ -d /mnt/gvfs/third-party -a -z "$CXX" ]; then
-  source $ROOT/build_tools/fbcode_config_platform009.sh
+  source $ROOT/build_tools/fbcode_config_platform010.sh
   GCOV=$GCC_BASE/bin/gcov
 else
   GCOV=$(which gcov)

crash_test.mk

@@ -21,6 +21,8 @@ CRASHTEST_PY=$(PYTHON) -u tools/db_crashtest.py --stress_cmd=$(DB_STRESS_CMD) --
 	blackbox_crash_test_with_multiops_wp_txn \
 	crash_test_with_tiered_storage blackbox_crash_test_with_tiered_storage \
 	whitebox_crash_test_with_tiered_storage \
+	whitebox_crash_test_with_optimistic_txn \
+	blackbox_crash_test_with_optimistic_txn \
 
 crash_test: $(DB_STRESS_CMD)
 # Do not parallelize
@@ -37,6 +39,11 @@ crash_test_with_txn: $(DB_STRESS_CMD)
 	$(CRASHTEST_MAKE) whitebox_crash_test_with_txn
 	$(CRASHTEST_MAKE) blackbox_crash_test_with_txn
 
+crash_test_with_optimistic_txn: $(DB_STRESS_CMD)
+# Do not parallelize
+	$(CRASHTEST_MAKE) whitebox_crash_test_with_optimistic_txn
+	$(CRASHTEST_MAKE) blackbox_crash_test_with_optimistic_txn
+
 crash_test_with_best_efforts_recovery: blackbox_crash_test_with_best_efforts_recovery
 
 crash_test_with_ts: $(DB_STRESS_CMD)
@@ -80,6 +87,9 @@ blackbox_crash_test_with_multiops_wp_txn: $(DB_STRESS_CMD)
 blackbox_crash_test_with_tiered_storage: $(DB_STRESS_CMD)
 	$(CRASHTEST_PY) --test_tiered_storage blackbox $(CRASH_TEST_EXT_ARGS)
 
+blackbox_crash_test_with_optimistic_txn: $(DB_STRESS_CMD)
+	$(CRASHTEST_PY) --optimistic_txn blackbox $(CRASH_TEST_EXT_ARGS)
+
 ifeq ($(CRASH_TEST_KILL_ODD),)
   CRASH_TEST_KILL_ODD=888887
 endif
@@ -105,3 +115,7 @@ whitebox_crash_test_with_ts: $(DB_STRESS_CMD)
 whitebox_crash_test_with_tiered_storage: $(DB_STRESS_CMD)
 	$(CRASHTEST_PY) --test_tiered_storage whitebox --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+
+whitebox_crash_test_with_optimistic_txn: $(DB_STRESS_CMD)
+	$(CRASHTEST_PY) --optimistic_txn whitebox --random_kill_odd \
+      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

db/arena_wrapped_db_iter.cc

@@ -47,7 +47,9 @@ void ArenaWrappedDBIter::Init(
   read_options_ = read_options;
   allow_refresh_ = allow_refresh;
   memtable_range_tombstone_iter_ = nullptr;
-  if (!env->GetFileSystem()->use_async_io()) {
+
+  if (!CheckFSFeatureSupport(env->GetFileSystem().get(),
+                             FSSupportedOps::kAsyncIO)) {
     read_options_.async_io = false;
   }
 }

db/blob/blob_contents.h

@@ -7,7 +7,7 @@
 
 #include <memory>
 
-#include "memory/memory_allocator.h"
+#include "memory/memory_allocator_impl.h"
 #include "rocksdb/advanced_cache.h"
 #include "rocksdb/rocksdb_namespace.h"
 #include "rocksdb/slice.h"

db/blob/blob_file_builder.cc

@@ -259,6 +259,7 @@ Status BlobFileBuilder::CompressBlobIfNeeded(
     return Status::OK();
   }
 
+  // TODO: allow user CompressionOptions, including max_compressed_bytes_per_kb
   CompressionOptions opts;
   CompressionContext context(blob_compression_type_);
   constexpr uint64_t sample_for_compression = 0;

db/blob/blob_file_cache.cc

@@ -25,7 +25,7 @@ BlobFileCache::BlobFileCache(Cache* cache,
                              HistogramImpl* blob_file_read_hist,
                              const std::shared_ptr<IOTracer>& io_tracer)
     : cache_(cache),
-      mutex_(kNumberOfMutexStripes, kGetSliceNPHash64UnseededFnPtr),
+      mutex_(kNumberOfMutexStripes),
       immutable_options_(immutable_options),
       file_options_(file_options),
       column_family_id_(column_family_id),
@@ -37,7 +37,7 @@ BlobFileCache::BlobFileCache(Cache* cache,
 }
 
 Status BlobFileCache::GetBlobFileReader(
-    uint64_t blob_file_number,
+    const ReadOptions& read_options, uint64_t blob_file_number,
     CacheHandleGuard<BlobFileReader>* blob_file_reader) {
   assert(blob_file_reader);
   assert(blob_file_reader->IsEmpty());
@@ -55,7 +55,7 @@ Status BlobFileCache::GetBlobFileReader(
   TEST_SYNC_POINT("BlobFileCache::GetBlobFileReader:DoubleCheck");
 
   // Check again while holding mutex
-  MutexLock lock(mutex_.get(key));
+  MutexLock lock(&mutex_.Get(key));
 
   handle = cache_.Lookup(key);
   if (handle) {
@@ -73,7 +73,7 @@ Status BlobFileCache::GetBlobFileReader(
   {
     assert(file_options_);
     const Status s = BlobFileReader::Create(
-        *immutable_options_, *file_options_, column_family_id_,
+        *immutable_options_, read_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

@@ -32,7 +32,8 @@ class BlobFileCache {
   BlobFileCache(const BlobFileCache&) = delete;
   BlobFileCache& operator=(const BlobFileCache&) = delete;
 
-  Status GetBlobFileReader(uint64_t blob_file_number,
+  Status GetBlobFileReader(const ReadOptions& read_options,
+                           uint64_t blob_file_number,
                            CacheHandleGuard<BlobFileReader>* blob_file_reader);
 
  private:
@@ -42,7 +43,7 @@ class BlobFileCache {
   CacheInterface cache_;
   // Note: mutex_ below is used to guard against multiple threads racing to open
   // the same file.
-  Striped<port::Mutex, Slice> mutex_;
+  Striped<CacheAlignedWrapper<port::Mutex>> mutex_;
   const ImmutableOptions* immutable_options_;
   const FileOptions* file_options_;
   uint32_t column_family_id_;

db/blob/blob_file_cache_test.cc

@@ -118,7 +118,9 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader) {
   // First try: reader should be opened and put in cache
   CacheHandleGuard<BlobFileReader> first;
 
-  ASSERT_OK(blob_file_cache.GetBlobFileReader(blob_file_number, &first));
+  const ReadOptions read_options;
+  ASSERT_OK(blob_file_cache.GetBlobFileReader(read_options, blob_file_number,
+                                              &first));
   ASSERT_NE(first.GetValue(), nullptr);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_OPENS), 1);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_ERRORS), 0);
@@ -126,7 +128,8 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader) {
   // Second try: reader should be served from cache
   CacheHandleGuard<BlobFileReader> second;
 
-  ASSERT_OK(blob_file_cache.GetBlobFileReader(blob_file_number, &second));
+  ASSERT_OK(blob_file_cache.GetBlobFileReader(read_options, blob_file_number,
+                                              &second));
   ASSERT_NE(second.GetValue(), nullptr);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_OPENS), 1);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_ERRORS), 0);
@@ -163,19 +166,21 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_Race) {
   CacheHandleGuard<BlobFileReader> first;
   CacheHandleGuard<BlobFileReader> second;
 
+  const ReadOptions read_options;
   SyncPoint::GetInstance()->SetCallBack(
       "BlobFileCache::GetBlobFileReader:DoubleCheck", [&](void* /* arg */) {
         // Disabling sync points to prevent infinite recursion
         SyncPoint::GetInstance()->DisableProcessing();
-
-        ASSERT_OK(blob_file_cache.GetBlobFileReader(blob_file_number, &second));
+        ASSERT_OK(blob_file_cache.GetBlobFileReader(read_options,
+                                                    blob_file_number, &second));
         ASSERT_NE(second.GetValue(), nullptr);
         ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_OPENS), 1);
         ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_ERRORS), 0);
       });
   SyncPoint::GetInstance()->EnableProcessing();
 
-  ASSERT_OK(blob_file_cache.GetBlobFileReader(blob_file_number, &first));
+  ASSERT_OK(blob_file_cache.GetBlobFileReader(read_options, blob_file_number,
+                                              &first));
   ASSERT_NE(first.GetValue(), nullptr);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_OPENS), 1);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_ERRORS), 0);
@@ -213,8 +218,10 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_IOError) {
 
   CacheHandleGuard<BlobFileReader> reader;
 
+  const ReadOptions read_options;
   ASSERT_TRUE(
-      blob_file_cache.GetBlobFileReader(blob_file_number, &reader).IsIOError());
+      blob_file_cache.GetBlobFileReader(read_options, blob_file_number, &reader)
+          .IsIOError());
   ASSERT_EQ(reader.GetValue(), nullptr);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_OPENS), 1);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_ERRORS), 1);
@@ -253,8 +260,10 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_CacheFull) {
   // strict_capacity_limit is set
   CacheHandleGuard<BlobFileReader> reader;
 
-  ASSERT_TRUE(blob_file_cache.GetBlobFileReader(blob_file_number, &reader)
-                  .IsMemoryLimit());
+  const ReadOptions read_options;
+  ASSERT_TRUE(
+      blob_file_cache.GetBlobFileReader(read_options, blob_file_number, &reader)
+          .IsMemoryLimit());
   ASSERT_EQ(reader.GetValue(), nullptr);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_OPENS), 1);
   ASSERT_EQ(options.statistics->getTickerCount(NO_FILE_ERRORS), 1);

db/blob/blob_file_reader.cc

@@ -12,7 +12,7 @@
 #include "db/blob/blob_log_format.h"
 #include "file/file_prefetch_buffer.h"
 #include "file/filename.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "options/cf_options.h"
 #include "rocksdb/file_system.h"
 #include "rocksdb/slice.h"
@@ -26,9 +26,10 @@
 namespace ROCKSDB_NAMESPACE {
 
 Status BlobFileReader::Create(
-    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,
+    const ImmutableOptions& immutable_options, const ReadOptions& read_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);
@@ -52,15 +53,17 @@ Status BlobFileReader::Create(
   CompressionType compression_type = kNoCompression;
 
   {
-    const Status s = ReadHeader(file_reader.get(), column_family_id, statistics,
-                                &compression_type);
+    const Status s =
+        ReadHeader(file_reader.get(), read_options, column_family_id,
+                   statistics, &compression_type);
     if (!s.ok()) {
       return s;
     }
   }
 
   {
-    const Status s = ReadFooter(file_reader.get(), file_size, statistics);
+    const Status s =
+        ReadFooter(file_reader.get(), read_options, file_size, statistics);
     if (!s.ok()) {
       return s;
     }
@@ -134,6 +137,7 @@ Status BlobFileReader::OpenFile(
 }
 
 Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
+                                  const ReadOptions& read_options,
                                   uint32_t column_family_id,
                                   Statistics* statistics,
                                   CompressionType* compression_type) {
@@ -151,9 +155,10 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
     constexpr size_t read_size = BlobLogHeader::kSize;
 
     // TODO: rate limit reading headers from blob files.
-    const Status s = ReadFromFile(file_reader, read_offset, read_size,
-                                  statistics, &header_slice, &buf, &aligned_buf,
-                                  Env::IO_TOTAL /* rate_limiter_priority */);
+    const Status s =
+        ReadFromFile(file_reader, read_options, read_offset, read_size,
+                     statistics, &header_slice, &buf, &aligned_buf,
+                     Env::IO_TOTAL /* rate_limiter_priority */);
     if (!s.ok()) {
       return s;
     }
@@ -187,6 +192,7 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
 }
 
 Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
+                                  const ReadOptions& read_options,
                                   uint64_t file_size, Statistics* statistics) {
   assert(file_size >= BlobLogHeader::kSize + BlobLogFooter::kSize);
   assert(file_reader);
@@ -202,9 +208,10 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
     constexpr size_t read_size = BlobLogFooter::kSize;
 
     // TODO: rate limit reading footers from blob files.
-    const Status s = ReadFromFile(file_reader, read_offset, read_size,
-                                  statistics, &footer_slice, &buf, &aligned_buf,
-                                  Env::IO_TOTAL /* rate_limiter_priority */);
+    const Status s =
+        ReadFromFile(file_reader, read_options, read_offset, read_size,
+                     statistics, &footer_slice, &buf, &aligned_buf,
+                     Env::IO_TOTAL /* rate_limiter_priority */);
     if (!s.ok()) {
       return s;
     }
@@ -232,6 +239,7 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
 }
 
 Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
+                                    const ReadOptions& read_options,
                                     uint64_t read_offset, size_t read_size,
                                     Statistics* statistics, Slice* slice,
                                     Buffer* buf, AlignedBuf* aligned_buf,
@@ -246,17 +254,23 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
 
   Status s;
 
+  IOOptions io_options;
+  s = file_reader->PrepareIOOptions(read_options, io_options);
+  if (!s.ok()) {
+    return s;
+  }
+
   if (file_reader->use_direct_io()) {
     constexpr char* scratch = nullptr;
 
-    s = file_reader->Read(IOOptions(), read_offset, read_size, slice, scratch,
+    s = file_reader->Read(io_options, read_offset, read_size, slice, scratch,
                           aligned_buf, rate_limiter_priority);
   } else {
     buf->reset(new char[read_size]);
     constexpr AlignedBuf* aligned_scratch = nullptr;
 
-    s = file_reader->Read(IOOptions(), read_offset, read_size, slice,
-                          buf->get(), aligned_scratch, rate_limiter_priority);
+    s = file_reader->Read(io_options, read_offset, read_size, slice, buf->get(),
+                          aligned_scratch, rate_limiter_priority);
   }
 
   if (!s.ok()) {
@@ -324,8 +338,13 @@ Status BlobFileReader::GetBlob(
     Status s;
     constexpr bool for_compaction = true;
 
+    IOOptions io_options;
+    s = file_reader_->PrepareIOOptions(read_options, io_options);
+    if (!s.ok()) {
+      return s;
+    }
     prefetched = prefetch_buffer->TryReadFromCache(
-        IOOptions(), file_reader_.get(), record_offset,
+        io_options, file_reader_.get(), record_offset,
         static_cast<size_t>(record_size), &record_slice, &s,
         read_options.rate_limiter_priority, for_compaction);
     if (!s.ok()) {
@@ -338,10 +357,10 @@ Status BlobFileReader::GetBlob(
     PERF_COUNTER_ADD(blob_read_count, 1);
     PERF_COUNTER_ADD(blob_read_byte, record_size);
     PERF_TIMER_GUARD(blob_read_time);
-    const Status s = ReadFromFile(file_reader_.get(), record_offset,
-                                  static_cast<size_t>(record_size), statistics_,
-                                  &record_slice, &buf, &aligned_buf,
-                                  read_options.rate_limiter_priority);
+    const Status s = ReadFromFile(
+        file_reader_.get(), read_options, record_offset,
+        static_cast<size_t>(record_size), statistics_, &record_slice, &buf,
+        &aligned_buf, read_options.rate_limiter_priority);
     if (!s.ok()) {
       return s;
     }
@@ -420,11 +439,11 @@ void BlobFileReader::MultiGetBlob(
     assert(req->offset >= adjustment);
     adjustments.push_back(adjustment);
 
-    FSReadRequest read_req = {};
+    FSReadRequest read_req;
     read_req.offset = req->offset - adjustment;
     read_req.len = req->len + adjustment;
-    read_reqs.emplace_back(read_req);
     total_len += read_req.len;
+    read_reqs.emplace_back(std::move(read_req));
   }
 
   RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_READ, total_len);

db/blob/blob_file_reader.h

@@ -29,6 +29,7 @@ class Statistics;
 class BlobFileReader {
  public:
   static Status Create(const ImmutableOptions& immutable_options,
+                       const ReadOptions& read_options,
                        const FileOptions& file_options,
                        uint32_t column_family_id,
                        HistogramImpl* blob_file_read_hist,
@@ -74,15 +75,18 @@ class BlobFileReader {
                          std::unique_ptr<RandomAccessFileReader>* file_reader);
 
   static Status ReadHeader(const RandomAccessFileReader* file_reader,
+                           const ReadOptions& read_options,
                            uint32_t column_family_id, Statistics* statistics,
                            CompressionType* compression_type);
 
   static Status ReadFooter(const RandomAccessFileReader* file_reader,
-                           uint64_t file_size, Statistics* statistics);
+                           const ReadOptions& read_options, uint64_t file_size,
+                           Statistics* statistics);
 
   using Buffer = std::unique_ptr<char[]>;
 
   static Status ReadFromFile(const RandomAccessFileReader* file_reader,
+                             const ReadOptions& read_options,
                              uint64_t read_offset, size_t read_size,
                              Statistics* statistics, Slice* slice, Buffer* buf,
                              AlignedBuf* aligned_buf,

db/blob/blob_file_reader_test.cc

@@ -172,12 +172,12 @@ TEST_F(BlobFileReaderTest, CreateReaderAndGetBlob) {
 
   std::unique_ptr<BlobFileReader> reader;
 
+  ReadOptions read_options;
   ASSERT_OK(BlobFileReader::Create(
-      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
-      blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, read_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;
   read_options.verify_checksums = false;
 
   constexpr FilePrefetchBuffer* prefetch_buffer = nullptr;
@@ -479,11 +479,11 @@ TEST_F(BlobFileReaderTest, Malformed) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
-  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
-                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, nullptr /*IOTracer*/,
-                                     &reader)
+  const ReadOptions read_options;
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, read_options,
+                                     FileOptions(), column_family_id,
+                                     blob_file_read_hist, blob_file_number,
+                                     nullptr /*IOTracer*/, &reader)
                   .IsCorruption());
 }
 
@@ -513,11 +513,11 @@ TEST_F(BlobFileReaderTest, TTL) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
-  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
-                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, nullptr /*IOTracer*/,
-                                     &reader)
+  const ReadOptions read_options;
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, read_options,
+                                     FileOptions(), column_family_id,
+                                     blob_file_read_hist, blob_file_number,
+                                     nullptr /*IOTracer*/, &reader)
                   .IsCorruption());
 }
 
@@ -552,11 +552,11 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInHeader) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
-  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
-                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, nullptr /*IOTracer*/,
-                                     &reader)
+  const ReadOptions read_options;
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, read_options,
+                                     FileOptions(), column_family_id,
+                                     blob_file_read_hist, blob_file_number,
+                                     nullptr /*IOTracer*/, &reader)
                   .IsCorruption());
 }
 
@@ -591,11 +591,11 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInFooter) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
-  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
-                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, nullptr /*IOTracer*/,
-                                     &reader)
+  const ReadOptions read_options;
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, read_options,
+                                     FileOptions(), column_family_id,
+                                     blob_file_read_hist, blob_file_number,
+                                     nullptr /*IOTracer*/, &reader)
                   .IsCorruption());
 }
 
@@ -629,9 +629,9 @@ TEST_F(BlobFileReaderTest, IncorrectColumnFamily) {
   std::unique_ptr<BlobFileReader> reader;
 
   constexpr uint32_t incorrect_column_family_id = 2;
-
-  ASSERT_TRUE(BlobFileReader::Create(immutable_options, FileOptions(),
-                                     incorrect_column_family_id,
+  const ReadOptions read_options;
+  ASSERT_TRUE(BlobFileReader::Create(immutable_options, read_options,
+                                     FileOptions(), incorrect_column_family_id,
                                      blob_file_read_hist, blob_file_number,
                                      nullptr /*IOTracer*/, &reader)
                   .IsCorruption());
@@ -664,10 +664,10 @@ TEST_F(BlobFileReaderTest, BlobCRCError) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
+  const ReadOptions read_options;
   ASSERT_OK(BlobFileReader::Create(
-      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
-      blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, read_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));
 
   SyncPoint::GetInstance()->SetCallBack(
       "BlobFileReader::VerifyBlob:CheckBlobCRC", [](void* arg) {
@@ -728,13 +728,12 @@ TEST_F(BlobFileReaderTest, Compression) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
+  ReadOptions read_options;
   ASSERT_OK(BlobFileReader::Create(
-      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
-      blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, read_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;
   read_options.verify_checksums = false;
 
   constexpr FilePrefetchBuffer* prefetch_buffer = nullptr;
@@ -803,10 +802,10 @@ TEST_F(BlobFileReaderTest, UncompressionError) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
+  const ReadOptions read_options;
   ASSERT_OK(BlobFileReader::Create(
-      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
-      blob_file_number, nullptr /*IOTracer*/, &reader));
+      immutable_options, read_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));
 
   SyncPoint::GetInstance()->SetCallBack(
       "BlobFileReader::UncompressBlobIfNeeded:TamperWithResult", [](void* arg) {
@@ -895,10 +894,10 @@ TEST_P(BlobFileReaderIOErrorTest, IOError) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
+  const ReadOptions read_options;
   const Status s = BlobFileReader::Create(
-      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
-      blob_file_number, nullptr /*IOTracer*/, &reader);
+      immutable_options, read_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");
@@ -983,10 +982,10 @@ TEST_P(BlobFileReaderDecodingErrorTest, DecodingError) {
   constexpr HistogramImpl* blob_file_read_hist = nullptr;
 
   std::unique_ptr<BlobFileReader> reader;
-
+  const ReadOptions read_options;
   const Status s = BlobFileReader::Create(
-      immutable_options, FileOptions(), column_family_id, blob_file_read_hist,
-      blob_file_number, nullptr /*IOTracer*/, &reader);
+      immutable_options, read_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_log_sequential_reader.cc

@@ -7,7 +7,7 @@
 #include "db/blob/blob_log_sequential_reader.h"
 
 #include "file/random_access_file_reader.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "util/stop_watch.h"
 
 namespace ROCKSDB_NAMESPACE {

db/blob/blob_log_writer.cc

@@ -10,7 +10,7 @@
 
 #include "db/blob/blob_log_format.h"
 #include "file/writable_file_writer.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "rocksdb/system_clock.h"
 #include "test_util/sync_point.h"
 #include "util/coding.h"

db/blob/blob_source.cc

@@ -13,7 +13,7 @@
 #include "db/blob/blob_contents.h"
 #include "db/blob/blob_file_reader.h"
 #include "db/blob/blob_log_format.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "options/cf_options.h"
 #include "table/get_context.h"
 #include "table/multiget_context.h"
@@ -209,7 +209,8 @@ Status BlobSource::GetBlob(const ReadOptions& read_options,
 
   {
     CacheHandleGuard<BlobFileReader> blob_file_reader;
-    s = blob_file_cache_->GetBlobFileReader(file_number, &blob_file_reader);
+    s = blob_file_cache_->GetBlobFileReader(read_options, file_number,
+                                            &blob_file_reader);
     if (!s.ok()) {
       return s;
     }
@@ -372,8 +373,8 @@ void BlobSource::MultiGetBlobFromOneFile(const ReadOptions& read_options,
     }
 
     CacheHandleGuard<BlobFileReader> blob_file_reader;
-    Status s =
-        blob_file_cache_->GetBlobFileReader(file_number, &blob_file_reader);
+    Status s = blob_file_cache_->GetBlobFileReader(read_options, file_number,
+                                                   &blob_file_reader);
     if (!s.ok()) {
       for (size_t i = 0; i < _blob_reqs.size(); ++i) {
         BlobReadRequest* const req = _blob_reqs[i].first;

db/blob/blob_source.h

@@ -95,9 +95,9 @@ class BlobSource {
                                uint64_t* bytes_read);
 
   inline Status GetBlobFileReader(
-      uint64_t blob_file_number,
+      const ReadOptions& read_options, uint64_t blob_file_number,
       CacheHandleGuard<BlobFileReader>* blob_file_reader) {
-    return blob_file_cache_->GetBlobFileReader(blob_file_number,
+    return blob_file_cache_->GetBlobFileReader(read_options, blob_file_number,
                                                blob_file_reader);
   }
 

db/blob/blob_source_test.cc

@@ -517,7 +517,8 @@ TEST_F(BlobSourceTest, GetCompressedBlobs) {
                   compression, blob_offsets, blob_sizes);
 
     CacheHandleGuard<BlobFileReader> blob_file_reader;
-    ASSERT_OK(blob_source.GetBlobFileReader(file_number, &blob_file_reader));
+    ASSERT_OK(blob_source.GetBlobFileReader(read_options, file_number,
+                                            &blob_file_reader));
     ASSERT_NE(blob_file_reader.GetValue(), nullptr);
 
     const uint64_t file_size = blob_file_reader.GetValue()->GetFileSize();
@@ -1139,12 +1140,13 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
                          blob_file_cache.get());
 
   CacheHandleGuard<BlobFileReader> file_reader;
-  ASSERT_OK(blob_source.GetBlobFileReader(file_number, &file_reader));
+  ReadOptions read_options;
+  ASSERT_OK(
+      blob_source.GetBlobFileReader(read_options, file_number, &file_reader));
   ASSERT_NE(file_reader.GetValue(), nullptr);
   const uint64_t file_size = file_reader.GetValue()->GetFileSize();
   ASSERT_EQ(file_reader.GetValue()->GetCompressionType(), kNoCompression);
 
-  ReadOptions read_options;
   read_options.verify_checksums = true;
 
   auto blob_cache = options_.blob_cache;

db/builder.cc

@@ -15,6 +15,7 @@
 
 #include "db/blob/blob_file_builder.h"
 #include "db/compaction/compaction_iterator.h"
+#include "db/dbformat.h"
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
@@ -56,8 +57,8 @@ TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
 Status BuildTable(
     const std::string& dbname, VersionSet* versions,
     const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
-    const FileOptions& file_options, TableCache* table_cache,
-    InternalIterator* iter,
+    const FileOptions& file_options, const ReadOptions& read_options,
+    TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
     FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
@@ -205,21 +206,38 @@ Status BuildTable(
         /*compaction=*/nullptr, compaction_filter.get(),
         /*shutting_down=*/nullptr, db_options.info_log, full_history_ts_low);
 
+    const size_t ts_sz = ucmp->timestamp_size();
+    const bool strip_timestamp =
+        ts_sz > 0 && !ioptions.persist_user_defined_timestamps;
+
+    std::string key_after_flush_buf;
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
       const ParsedInternalKey& ikey = c_iter.ikey();
-      // 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);
+      Slice key_after_flush = key;
+      // If user defined timestamps will be stripped from user key after flush,
+      // the in memory version of the key act logically the same as one with a
+      // minimum timestamp. We update the timestamp here so file boundary and
+      // output validator, block builder all see the effect of the stripping.
+      if (strip_timestamp) {
+        key_after_flush_buf.clear();
+        ReplaceInternalKeyWithMinTimestamp(&key_after_flush_buf, key, ts_sz);
+        key_after_flush = key_after_flush_buf;
+      }
+
+      //  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_after_flush, value);
       if (!s.ok()) {
         break;
       }
-      builder->Add(key, value);
+      builder->Add(key_after_flush, value);
 
-      s = meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
+      s = meta->UpdateBoundaries(key_after_flush, value, ikey.sequence,
+                                 ikey.type);
       if (!s.ok()) {
         break;
       }
@@ -244,6 +262,7 @@ Status BuildTable(
            range_del_it->Next()) {
         auto tombstone = range_del_it->Tombstone();
         auto kv = tombstone.Serialize();
+        // TODO(yuzhangyu): handle range deletion for UDT in memtables only.
         builder->Add(kv.first.Encode(), kv.second);
         InternalKey tombstone_end = tombstone.SerializeEndKey();
         meta->UpdateBoundariesForRange(kv.first, tombstone_end, tombstone.seq_,
@@ -255,8 +274,8 @@ Status BuildTable(
             SizeApproximationOptions approx_opts;
             approx_opts.files_size_error_margin = 0.1;
             meta->compensated_range_deletion_size += versions->ApproximateSize(
-                approx_opts, version, kv.first.Encode(), tombstone_end.Encode(),
-                0 /* start_level */, -1 /* end_level */,
+                approx_opts, read_options, version, kv.first.Encode(),
+                tombstone_end.Encode(), 0 /* start_level */, -1 /* end_level */,
                 TableReaderCaller::kFlush);
           }
           last_tombstone_start_user_key = range_del_it->start_key();
@@ -291,7 +310,10 @@ Status BuildTable(
     if (s.ok() && !empty) {
       uint64_t file_size = builder->FileSize();
       meta->fd.file_size = file_size;
+      meta->tail_size = builder->GetTailSize();
       meta->marked_for_compaction = builder->NeedCompact();
+      meta->user_defined_timestamps_persisted =
+          ioptions.persist_user_defined_timestamps;
       assert(meta->fd.GetFileSize() > 0);
       tp = builder
                ->GetTableProperties();  // refresh now that builder is finished
@@ -351,6 +373,8 @@ Status BuildTable(
       s = *io_status;
     }
 
+    // TODO(yuzhangyu): handle the key copy in the blob when ts should be
+    // stripped.
     if (blob_file_builder) {
       if (s.ok()) {
         s = blob_file_builder->Finish();
@@ -369,7 +393,6 @@ Status BuildTable(
       // here because this is a special case after we finish the table building.
       // No matter whether use_direct_io_for_flush_and_compaction is true,
       // the goal is to cache it here for further user reads.
-      ReadOptions read_options;
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
           read_options, file_options, tboptions.internal_comparator, *meta,
           nullptr /* range_del_agg */, mutable_cf_options.prefix_extractor,
@@ -381,7 +404,8 @@ Status BuildTable(
           MaxFileSizeForL0MetaPin(mutable_cf_options),
           /*smallest_compaction_key=*/nullptr,
           /*largest_compaction_key*/ nullptr,
-          /*allow_unprepared_value*/ false));
+          /*allow_unprepared_value*/ false,
+          mutable_cf_options.block_protection_bytes_per_key));
       s = it->status();
       if (s.ok() && paranoid_file_checks) {
         OutputValidator file_validator(tboptions.internal_comparator,

db/builder.h

@@ -53,8 +53,8 @@ TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
 extern Status BuildTable(
     const std::string& dbname, VersionSet* versions,
     const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
-    const FileOptions& file_options, TableCache* table_cache,
-    InternalIterator* iter,
+    const FileOptions& file_options, const ReadOptions& read_options,
+    TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
     FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,

db/c.cc

@@ -1057,6 +1057,36 @@ rocksdb_column_family_handle_t* rocksdb_create_column_family(
   return handle;
 }
 
+rocksdb_column_family_handle_t** rocksdb_create_column_families(
+    rocksdb_t* db, const rocksdb_options_t* column_family_options,
+    int num_column_families, const char* const* column_family_names,
+    size_t* lencfs, char** errptr) {
+  std::vector<ColumnFamilyHandle*> handles;
+  std::vector<std::string> names;
+  for (int i = 0; i != num_column_families; ++i) {
+    names.push_back(std::string(column_family_names[i]));
+  }
+  SaveError(errptr, db->rep->CreateColumnFamilies(
+                        ColumnFamilyOptions(column_family_options->rep), names,
+                        &handles));
+
+  *lencfs = handles.size();
+  rocksdb_column_family_handle_t** c_handles =
+      static_cast<rocksdb_column_family_handle_t**>(
+          malloc(sizeof(rocksdb_column_family_handle_t*) * handles.size()));
+  for (size_t i = 0; i != handles.size(); ++i) {
+    c_handles[i] = new rocksdb_column_family_handle_t;
+    c_handles[i]->rep = handles[i];
+  }
+
+  return c_handles;
+}
+
+void rocksdb_create_column_families_destroy(
+    rocksdb_column_family_handle_t** list) {
+  free(list);
+}
+
 rocksdb_column_family_handle_t* rocksdb_create_column_family_with_ttl(
     rocksdb_t* db, const rocksdb_options_t* column_family_options,
     const char* column_family_name, int ttl, char** errptr) {
@@ -3740,16 +3770,21 @@ void rocksdb_options_set_hash_link_list_rep(rocksdb_options_t* opt,
       ROCKSDB_NAMESPACE::NewHashLinkListRepFactory(bucket_count));
 }
 
-void rocksdb_options_set_plain_table_factory(rocksdb_options_t* opt,
-                                             uint32_t user_key_len,
-                                             int bloom_bits_per_key,
-                                             double hash_table_ratio,
-                                             size_t index_sparseness) {
+void rocksdb_options_set_plain_table_factory(
+    rocksdb_options_t* opt, uint32_t user_key_len, int bloom_bits_per_key,
+    double hash_table_ratio, size_t index_sparseness, size_t huge_page_tlb_size,
+    char encoding_type, unsigned char full_scan_mode,
+    unsigned char store_index_in_file) {
   ROCKSDB_NAMESPACE::PlainTableOptions options;
   options.user_key_len = user_key_len;
   options.bloom_bits_per_key = bloom_bits_per_key;
   options.hash_table_ratio = hash_table_ratio;
   options.index_sparseness = index_sparseness;
+  options.huge_page_tlb_size = huge_page_tlb_size;
+  options.encoding_type =
+      static_cast<ROCKSDB_NAMESPACE::EncodingType>(encoding_type);
+  options.full_scan_mode = full_scan_mode;
+  options.store_index_in_file = store_index_in_file;
 
   ROCKSDB_NAMESPACE::TableFactory* factory =
       ROCKSDB_NAMESPACE::NewPlainTableFactory(options);
@@ -3888,6 +3923,15 @@ void rocksdb_options_add_compact_on_deletion_collector_factory(
   opt->rep.table_properties_collector_factories.emplace_back(compact_on_del);
 }
 
+void rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio(
+    rocksdb_options_t* opt, size_t window_size, size_t num_dels_trigger,
+    double deletion_ratio) {
+  std::shared_ptr<ROCKSDB_NAMESPACE::TablePropertiesCollectorFactory>
+      compact_on_del = NewCompactOnDeletionCollectorFactory(
+          window_size, num_dels_trigger, deletion_ratio);
+  opt->rep.table_properties_collector_factories.emplace_back(compact_on_del);
+}
+
 void rocksdb_set_perf_level(int v) {
   PerfLevel level = static_cast<PerfLevel>(v);
   SetPerfLevel(level);
@@ -4064,6 +4108,8 @@ uint64_t rocksdb_perfcontext_metric(rocksdb_perfcontext_t* context,
       return rep->blob_decompress_time;
     case rocksdb_internal_range_del_reseek_count:
       return rep->internal_range_del_reseek_count;
+    case rocksdb_block_read_cpu_time:
+      return rep->block_read_cpu_time;
     default:
       break;
   }
@@ -4679,7 +4725,7 @@ rocksdb_cache_t* rocksdb_cache_create_lru_with_strict_capacity_limit(
 }
 
 rocksdb_cache_t* rocksdb_cache_create_lru_opts(
-    rocksdb_lru_cache_options_t* opt) {
+    const rocksdb_lru_cache_options_t* opt) {
   rocksdb_cache_t* c = new rocksdb_cache_t;
   c->rep = NewLRUCache(opt->rep);
   return c;
@@ -4726,7 +4772,7 @@ rocksdb_cache_t* rocksdb_cache_create_hyper_clock(
 }
 
 rocksdb_cache_t* rocksdb_cache_create_hyper_clock_opts(
-    rocksdb_hyper_clock_cache_options_t* opts) {
+    const rocksdb_hyper_clock_cache_options_t* opts) {
   rocksdb_cache_t* c = new rocksdb_cache_t;
   c->rep = opts->rep.MakeSharedCache();
   return c;
@@ -4742,18 +4788,26 @@ void rocksdb_cache_set_capacity(rocksdb_cache_t* cache, size_t capacity) {
   cache->rep->SetCapacity(capacity);
 }
 
-size_t rocksdb_cache_get_capacity(rocksdb_cache_t* cache) {
+size_t rocksdb_cache_get_capacity(const rocksdb_cache_t* cache) {
   return cache->rep->GetCapacity();
 }
 
-size_t rocksdb_cache_get_usage(rocksdb_cache_t* cache) {
+size_t rocksdb_cache_get_usage(const rocksdb_cache_t* cache) {
   return cache->rep->GetUsage();
 }
 
-size_t rocksdb_cache_get_pinned_usage(rocksdb_cache_t* cache) {
+size_t rocksdb_cache_get_pinned_usage(const rocksdb_cache_t* cache) {
   return cache->rep->GetPinnedUsage();
 }
 
+size_t rocksdb_cache_get_table_address_count(const rocksdb_cache_t* cache) {
+  return cache->rep->GetTableAddressCount();
+}
+
+size_t rocksdb_cache_get_occupancy_count(const rocksdb_cache_t* cache) {
+  return cache->rep->GetOccupancyCount();
+}
+
 rocksdb_dbpath_t* rocksdb_dbpath_create(const char* path,
                                         uint64_t target_size) {
   rocksdb_dbpath_t* result = new rocksdb_dbpath_t;
@@ -5569,6 +5623,23 @@ int rocksdb_transactiondb_property_int(rocksdb_transactiondb_t* db,
   }
 }
 
+rocksdb_t* rocksdb_transactiondb_get_base_db(
+    rocksdb_transactiondb_t* txn_db) {
+  DB* base_db = txn_db->rep->GetBaseDB();
+
+  if (base_db != nullptr) {
+    rocksdb_t* result = new rocksdb_t;
+    result->rep = base_db;
+    return result;
+  }
+
+  return nullptr;
+}
+
+void rocksdb_transactiondb_close_base_db(rocksdb_t* base_db) {
+  delete base_db;
+}
+
 rocksdb_transaction_t* rocksdb_transaction_begin(
     rocksdb_transactiondb_t* txn_db,
     const rocksdb_writeoptions_t* write_options,
@@ -5853,6 +5924,35 @@ void rocksdb_transaction_multi_get(rocksdb_transaction_t* txn,
   }
 }
 
+void rocksdb_transaction_multi_get_for_update(
+    rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
+    size_t num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes, char** values_list,
+    size_t* values_list_sizes, char** errs) {
+  std::vector<Slice> keys(num_keys);
+  for (size_t i = 0; i < num_keys; i++) {
+    keys[i] = Slice(keys_list[i], keys_list_sizes[i]);
+  }
+  std::vector<std::string> values(num_keys);
+  std::vector<Status> statuses =
+      txn->rep->MultiGetForUpdate(options->rep, keys, &values);
+  for (size_t i = 0; i < num_keys; i++) {
+    if (statuses[i].ok()) {
+      values_list[i] = CopyString(values[i]);
+      values_list_sizes[i] = values[i].size();
+      errs[i] = nullptr;
+    } else {
+      values_list[i] = nullptr;
+      values_list_sizes[i] = 0;
+      if (!statuses[i].IsNotFound()) {
+        errs[i] = strdup(statuses[i].ToString().c_str());
+      } else {
+        errs[i] = nullptr;
+      }
+    }
+  }
+}
+
 void rocksdb_transaction_multi_get_cf(
     rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
     const rocksdb_column_family_handle_t* const* column_families,
@@ -5885,6 +5985,38 @@ void rocksdb_transaction_multi_get_cf(
   }
 }
 
+void rocksdb_transaction_multi_get_for_update_cf(
+    rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
+    const rocksdb_column_family_handle_t* const* column_families,
+    size_t num_keys, const char* const* keys_list,
+    const size_t* keys_list_sizes, char** values_list,
+    size_t* values_list_sizes, char** errs) {
+  std::vector<Slice> keys(num_keys);
+  std::vector<ColumnFamilyHandle*> cfs(num_keys);
+  for (size_t i = 0; i < num_keys; i++) {
+    keys[i] = Slice(keys_list[i], keys_list_sizes[i]);
+    cfs[i] = column_families[i]->rep;
+  }
+  std::vector<std::string> values(num_keys);
+  std::vector<Status> statuses =
+      txn->rep->MultiGetForUpdate(options->rep, cfs, keys, &values);
+  for (size_t i = 0; i < num_keys; i++) {
+    if (statuses[i].ok()) {
+      values_list[i] = CopyString(values[i]);
+      values_list_sizes[i] = values[i].size();
+      errs[i] = nullptr;
+    } else {
+      values_list[i] = nullptr;
+      values_list_sizes[i] = 0;
+      if (!statuses[i].IsNotFound()) {
+        errs[i] = strdup(statuses[i].ToString().c_str());
+      } else {
+        errs[i] = nullptr;
+      }
+    }
+  }
+}
+
 // Read a key outside a transaction
 char* rocksdb_transactiondb_get(rocksdb_transactiondb_t* txn_db,
                                 const rocksdb_readoptions_t* options,

db/c_test.c

@@ -488,6 +488,19 @@ static void CheckTxnPinGetCF(rocksdb_transaction_t* txn,
   rocksdb_pinnableslice_destroy(p);
 }
 
+static void CheckTxnGetForUpdate(rocksdb_transaction_t* txn,
+                                 const rocksdb_readoptions_t* options,
+                                 const char* key, const char* expected) {
+  char* err = NULL;
+  size_t val_len;
+  char* val;
+  val = rocksdb_transaction_get_for_update(txn, options, key, strlen(key),
+                                           &val_len, true, &err);
+  CheckNoError(err);
+  CheckEqual(expected, val, val_len);
+  Free(&val);
+}
+
 static void CheckTxnDBGet(rocksdb_transactiondb_t* txn_db,
                           const rocksdb_readoptions_t* options, const char* key,
                           const char* expected) {
@@ -515,6 +528,20 @@ static void CheckTxnDBGetCF(rocksdb_transactiondb_t* txn_db,
   Free(&val);
 }
 
+static void CheckTxnGetForUpdateCF(
+    rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
+    rocksdb_column_family_handle_t* column_family, const char* key,
+    const char* expected) {
+  char* err = NULL;
+  size_t val_len;
+  char* val;
+  val = rocksdb_transaction_get_for_update_cf(
+      txn, options, column_family, key, strlen(key), &val_len, true, &err);
+  CheckNoError(err);
+  CheckEqual(expected, val, val_len);
+  Free(&val);
+}
+
 static void CheckTxnDBPinGet(rocksdb_transactiondb_t* txn_db,
                              const rocksdb_readoptions_t* options,
                              const char* key, const char* expected) {
@@ -694,6 +721,8 @@ int main(int argc, char** argv) {
 
   rocksdb_options_add_compact_on_deletion_collector_factory(options, 10000,
                                                             10001);
+  rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio(
+      options, 10000, 10001, 0.0);
 
   StartPhase("destroy");
   rocksdb_destroy_db(options, dbname, &err);
@@ -1645,7 +1674,8 @@ int main(int argc, char** argv) {
     rocksdb_options_set_prefix_extractor(
         options, rocksdb_slicetransform_create_fixed_prefix(3));
     rocksdb_options_set_hash_skip_list_rep(options, 5000, 4, 4);
-    rocksdb_options_set_plain_table_factory(options, 4, 10, 0.75, 16);
+    rocksdb_options_set_plain_table_factory(options, 4, 10, 0.75, 16, 0, 0, 0,
+                                            0);
     rocksdb_options_set_allow_concurrent_memtable_write(options, 0);
 
     db = rocksdb_open(options, dbname, &err);
@@ -3092,6 +3122,17 @@ int main(int argc, char** argv) {
     CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
     CheckTxnDBPinGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
 
+
+    //memory usage
+    rocksdb_t* base_db = rocksdb_transactiondb_get_base_db(txn_db);
+    rocksdb_memory_consumers_t* consumers = rocksdb_memory_consumers_create();
+    rocksdb_memory_consumers_add_db(consumers, base_db);
+    rocksdb_memory_usage_t* usage = rocksdb_approximate_memory_usage_create(consumers, &err);
+    CheckNoError(err);
+    rocksdb_approximate_memory_usage_destroy(usage);
+    rocksdb_memory_consumers_destroy(consumers);
+    rocksdb_transactiondb_close_base_db(base_db);
+
     // flush
     rocksdb_flushoptions_t* flush_options = rocksdb_flushoptions_create();
     rocksdb_flushoptions_set_wait(flush_options, 1);
@@ -3204,6 +3245,120 @@ int main(int argc, char** argv) {
     rocksdb_transactiondb_options_destroy(txn_db_options);
   }
 
+  StartPhase("transactions_multi_get_for_update");
+  {
+    // open a TransactionDB
+    txn_db_options = rocksdb_transactiondb_options_create();
+    rocksdb_transactiondb_options_set_transaction_lock_timeout(txn_db_options,
+                                                               0);
+    txn_options = rocksdb_transaction_options_create();
+    rocksdb_options_set_create_if_missing(options, 1);
+    txn_db = rocksdb_transactiondb_open(options, txn_db_options, dbname, &err);
+    CheckNoError(err);
+
+    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hey", 3, &err);
+    CheckNoError(err);
+    rocksdb_transactiondb_put(txn_db, woptions, "bar", 3, "hello", 5, &err);
+    CheckNoError(err);
+
+    // begin transactions
+    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
+    rocksdb_transaction_t* txn2 =
+        rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
+
+    // multi get
+    {
+      const char* keys[2] = {"foo", "bar"};
+      const size_t keys_sizes[2] = {3, 3};
+      char* vals[2];
+      size_t vals_sizes[2];
+      char* errs[2];
+      const char* expected[2] = {"hey", "hello"};
+      rocksdb_transaction_multi_get_for_update(
+          txn, roptions, 2, keys, keys_sizes, vals, vals_sizes, errs);
+      CheckMultiGetValues(2, vals, vals_sizes, errs, expected);
+    }
+
+    char* conflict_err = NULL;
+    size_t val_len;
+    rocksdb_transaction_get_for_update(txn2, roptions, "foo", 3, &val_len, true,
+                                       &conflict_err);
+    // get-for-update conflict
+    CheckCondition(conflict_err != NULL);
+    Free(&conflict_err);
+
+    // commit
+    rocksdb_transaction_commit(txn, &err);
+    CheckNoError(err);
+
+    // should work after first tx is commited
+    CheckTxnGetForUpdate(txn2, roptions, "foo", "hey");
+
+    // commit the second one
+    rocksdb_transaction_commit(txn2, &err);
+    CheckNoError(err);
+
+    // destroy txns
+    rocksdb_transaction_destroy(txn);
+    rocksdb_transaction_destroy(txn2);
+
+    // same for column families
+
+    rocksdb_column_family_handle_t* cfh;
+    cfh = rocksdb_transactiondb_create_column_family(txn_db, options,
+                                                     "txn_db_cf", &err);
+    CheckNoError(err);
+
+    rocksdb_transactiondb_put_cf(txn_db, woptions, cfh, "cf_foo", 6, "cf_hello",
+                                 8, &err);
+    CheckNoError(err);
+    rocksdb_transactiondb_put_cf(txn_db, woptions, cfh, "cf_bar", 6, "cf_hey",
+                                 6, &err);
+    CheckNoError(err);
+
+    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
+    txn2 = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
+
+    {
+      const rocksdb_column_family_handle_t* get_handles[2] = {cfh, cfh};
+      const char* keys[2] = {"cf_foo", "cf_bar"};
+      const size_t keys_sizes[2] = {6, 6};
+      char* vals[2];
+      size_t vals_sizes[2];
+      char* errs[2];
+      const char* expected[2] = {"cf_hello", "cf_hey"};
+      rocksdb_transaction_multi_get_for_update_cf(txn, roptions, get_handles, 2,
+                                                  keys, keys_sizes, vals,
+                                                  vals_sizes, errs);
+      CheckMultiGetValues(2, vals, vals_sizes, errs, expected);
+    }
+
+    char* conflict_err_cf = NULL;
+    size_t val_len_cf;
+    rocksdb_transaction_get_for_update_cf(txn2, roptions, cfh, "cf_foo", 6,
+                                          &val_len_cf, true, &conflict_err_cf);
+    CheckCondition(conflict_err_cf != NULL);
+    Free(&conflict_err_cf);
+
+    rocksdb_transaction_commit(txn, &err);
+    CheckNoError(err);
+
+    CheckTxnGetForUpdateCF(txn2, roptions, cfh, "cf_foo", "cf_hello");
+
+    rocksdb_transaction_commit(txn2, &err);
+    CheckNoError(err);
+
+    // close and destroy
+    rocksdb_column_family_handle_destroy(cfh);
+    rocksdb_transaction_destroy(txn);
+    rocksdb_transaction_destroy(txn2);
+    rocksdb_transactiondb_close(txn_db);
+    rocksdb_destroy_db(options, dbname, &err);
+    CheckNoError(err);
+    rocksdb_transaction_options_destroy(txn_options);
+    rocksdb_transactiondb_options_destroy(txn_db_options);
+  }
+
   StartPhase("optimistic_transactions");
   {
     rocksdb_options_t* db_options = rocksdb_options_create();
@@ -3233,8 +3388,19 @@ int main(int argc, char** argv) {
     rocksdb_put(db, woptions, "key", 3, "value", 5, &err);
     CheckNoError(err);
     rocksdb_column_family_handle_t *cfh1, *cfh2;
-    cfh1 = rocksdb_create_column_family(db, db_options, "txn_db_cf1", &err);
-    cfh2 = rocksdb_create_column_family(db, db_options, "txn_db_cf2", &err);
+    char** list_const_cf_names = (char**)malloc(2 * sizeof(char*));
+    list_const_cf_names[0] = "txn_db_cf1";
+    list_const_cf_names[1] = "txn_db_cf2";
+    size_t cflen;
+    rocksdb_column_family_handle_t** list_cfh = rocksdb_create_column_families(
+        db, db_options, 2, (const char* const*)list_const_cf_names, &cflen,
+        &err);
+    free(list_const_cf_names);
+    CheckNoError(err);
+    assert(cflen == 2);
+    cfh1 = list_cfh[0];
+    cfh2 = list_cfh[1];
+    rocksdb_create_column_families_destroy(list_cfh);
     txn = rocksdb_optimistictransaction_begin(otxn_db, woptions, otxn_options,
                                               NULL);
     rocksdb_transaction_put_cf(txn, cfh1, "key_cf1", 7, "val_cf1", 7, &err);

db/column_family.cc

@@ -382,8 +382,8 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
 
   const uint64_t kAdjustedTtl = 30 * 24 * 60 * 60;
   if (result.ttl == kDefaultTtl) {
-    if (is_block_based_table &&
-        result.compaction_style != kCompactionStyleFIFO) {
+    if (is_block_based_table) {
+      // For FIFO, max_open_files is checked in ValidateOptions().
       result.ttl = kAdjustedTtl;
     } else {
       result.ttl = 0;
@@ -403,16 +403,12 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
       result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
     }
   } else {
-    // result.compaction_style == kCompactionStyleFIFO
-    if (result.ttl == 0) {
-      if (is_block_based_table) {
-        if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-          result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-        }
-        result.ttl = result.periodic_compaction_seconds;
-      }
-    } else if (result.periodic_compaction_seconds != 0) {
-      result.ttl = std::min(result.ttl, result.periodic_compaction_seconds);
+    if (result.periodic_compaction_seconds != kDefaultPeriodicCompSecs &&
+        result.periodic_compaction_seconds > 0) {
+      ROCKS_LOG_WARN(
+          db_options.info_log.get(),
+          "periodic_compaction_seconds does not support FIFO compaction. You"
+          "may want to set option TTL instead.");
     }
   }
 
@@ -1141,6 +1137,7 @@ Status ColumnFamilyData::RangesOverlapWithMemtables(
   *overlap = false;
   // Create an InternalIterator over all unflushed memtables
   Arena arena;
+  // TODO: plumb Env::IOActivity
   ReadOptions read_opts;
   read_opts.total_order_seek = true;
   MergeIteratorBuilder merge_iter_builder(&internal_comparator_, &arena);
@@ -1244,30 +1241,11 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
   // (if no Scrape happens).
   assert(ptr != SuperVersion::kSVInUse);
   SuperVersion* sv = static_cast<SuperVersion*>(ptr);
-  if (sv == SuperVersion::kSVObsolete ||
-      sv->version_number != super_version_number_.load()) {
+  if (sv == SuperVersion::kSVObsolete) {
     RecordTick(ioptions_.stats, NUMBER_SUPERVERSION_ACQUIRES);
-    SuperVersion* sv_to_delete = nullptr;
-
-    if (sv && sv->Unref()) {
-      RecordTick(ioptions_.stats, NUMBER_SUPERVERSION_CLEANUPS);
-      db->mutex()->Lock();
-      // NOTE: underlying resources held by superversion (sst files) might
-      // not be released until the next background job.
-      sv->Cleanup();
-      if (db->immutable_db_options().avoid_unnecessary_blocking_io) {
-        db->AddSuperVersionsToFreeQueue(sv);
-        db->SchedulePurge();
-      } else {
-        sv_to_delete = sv;
-      }
-    } else {
-      db->mutex()->Lock();
-    }
+    db->mutex()->Lock();
     sv = super_version_->Ref();
     db->mutex()->Unlock();
-
-    delete sv_to_delete;
   }
   assert(sv != nullptr);
   return sv;
@@ -1427,6 +1405,37 @@ Status ColumnFamilyData::ValidateOptions(
         "Memtable per key-value checksum protection only supports 0, 1, 2, 4 "
         "or 8 bytes per key.");
   }
+  if (std::find(supported.begin(), supported.end(),
+                cf_options.block_protection_bytes_per_key) == supported.end()) {
+    return Status::NotSupported(
+        "Block per key-value checksum protection only supports 0, 1, 2, 4 "
+        "or 8 bytes per key.");
+  }
+
+  if (!cf_options.compaction_options_fifo.file_temperature_age_thresholds
+           .empty()) {
+    if (cf_options.compaction_style != kCompactionStyleFIFO) {
+      return Status::NotSupported(
+          "Option file_temperature_age_thresholds only supports FIFO "
+          "compaction.");
+    } else if (cf_options.num_levels > 1) {
+      return Status::NotSupported(
+          "Option file_temperature_age_thresholds is only supported when "
+          "num_levels = 1.");
+    } else {
+      const auto& ages =
+          cf_options.compaction_options_fifo.file_temperature_age_thresholds;
+      assert(ages.size() >= 1);
+      // check that age is sorted
+      for (size_t i = 0; i < ages.size() - 1; ++i) {
+        if (ages[i].age >= ages[i + 1].age) {
+          return Status::NotSupported(
+              "Option file_temperature_age_thresholds requires elements to be "
+              "sorted in increasing order with respect to `age` field.");
+        }
+      }
+    }
+  }
   return s;
 }
 
@@ -1608,6 +1617,13 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
       db_id_, db_session_id_);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
+  auto ucmp = new_cfd->user_comparator();
+  assert(ucmp);
+  size_t ts_sz = ucmp->timestamp_size();
+  running_ts_sz_.insert({id, ts_sz});
+  if (ts_sz > 0) {
+    ts_sz_for_record_.insert({id, ts_sz});
+  }
   max_column_family_ = std::max(max_column_family_, id);
   // add to linked list
   new_cfd->next_ = dummy_cfd_;
@@ -1623,10 +1639,13 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
 
 // under a DB mutex AND from a write thread
 void ColumnFamilySet::RemoveColumnFamily(ColumnFamilyData* cfd) {
-  auto cfd_iter = column_family_data_.find(cfd->GetID());
+  uint32_t cf_id = cfd->GetID();
+  auto cfd_iter = column_family_data_.find(cf_id);
   assert(cfd_iter != column_family_data_.end());
   column_family_data_.erase(cfd_iter);
   column_families_.erase(cfd->GetName());
+  running_ts_sz_.erase(cf_id);
+  ts_sz_for_record_.erase(cf_id);
 }
 
 // under a DB mutex OR from a write thread

db/column_family.h

@@ -705,6 +705,16 @@ class ColumnFamilySet {
                                        Version* dummy_version,
                                        const ColumnFamilyOptions& options);
 
+  const UnorderedMap<uint32_t, size_t>& GetRunningColumnFamiliesTimestampSize()
+      const {
+    return running_ts_sz_;
+  }
+
+  const UnorderedMap<uint32_t, size_t>&
+  GetColumnFamiliesTimestampSizeForRecord() const {
+    return ts_sz_for_record_;
+  }
+
   iterator begin() { return iterator(dummy_cfd_->next_); }
   iterator end() { return iterator(dummy_cfd_); }
 
@@ -730,6 +740,15 @@ class ColumnFamilySet {
   UnorderedMap<std::string, uint32_t> column_families_;
   UnorderedMap<uint32_t, ColumnFamilyData*> column_family_data_;
 
+  // Mutating / reading `running_ts_sz_` and `ts_sz_for_record_` follow
+  // the same requirements as `column_families_` and `column_family_data_`.
+  // Mapping from column family id to user-defined timestamp size for all
+  // running column families.
+  UnorderedMap<uint32_t, size_t> running_ts_sz_;
+  // Mapping from column family id to user-defined timestamp size for
+  // column families with non-zero user-defined timestamp size.
+  UnorderedMap<uint32_t, size_t> ts_sz_for_record_;
+
   uint32_t max_column_family_;
   const FileOptions file_options_;
 

db/column_family_test.cc

@@ -1255,6 +1255,7 @@ TEST_P(ColumnFamilyTest, DifferentCompactionStyles) {
   ColumnFamilyOptions default_cf, one, two;
   db_options_.max_open_files = 20;  // only 10 files in file cache
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
@@ -1272,6 +1273,7 @@ TEST_P(ColumnFamilyTest, DifferentCompactionStyles) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -1326,6 +1328,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
   db_options_.max_open_files = 20;  // only 10 files in file cache
   db_options_.max_background_compactions = 3;
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
@@ -1342,6 +1345,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -1424,13 +1428,14 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
   db_options_.max_open_files = 20;  // only 10 files in file cache
   db_options_.max_background_compactions = 3;
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
   default_cf.target_file_size_base = 30 << 10;
   default_cf.max_compaction_bytes = default_cf.target_file_size_base * 1100;
   BlockBasedTableOptions table_options = GetBlockBasedTableOptions();
-  ;
+
   table_options.no_block_cache = true;
   default_cf.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
@@ -1441,6 +1446,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -1519,13 +1525,14 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   db_options_.max_open_files = 20;  // only 10 files in file cache
   db_options_.max_background_compactions = 3;
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
   default_cf.target_file_size_base = 30 << 10;
   default_cf.max_compaction_bytes = default_cf.target_file_size_base * 1100;
   BlockBasedTableOptions table_options = GetBlockBasedTableOptions();
-  ;
+
   table_options.no_block_cache = true;
   default_cf.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
@@ -1536,6 +1543,7 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;

db/compact_files_test.cc

@@ -66,6 +66,7 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
   const int kWriteBufferSize = 10000;
   const int kLevel0Trigger = 2;
   options.create_if_missing = true;
+  options.level_compaction_dynamic_level_bytes = false;
   options.compaction_style = kCompactionStyleLevel;
   // Small slowdown and stop trigger for experimental purpose.
   options.level0_slowdown_writes_trigger = 20;
@@ -120,7 +121,9 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
 TEST_F(CompactFilesTest, MultipleLevel) {
   Options options;
   options.create_if_missing = true;
-  options.level_compaction_dynamic_level_bytes = true;
+  // Otherwise background compaction can happen to
+  // drain unnecessary level
+  options.level_compaction_dynamic_level_bytes = false;
   options.num_levels = 6;
   // Add listener
   FlushedFileCollector* collector = new FlushedFileCollector();
@@ -181,7 +184,6 @@ TEST_F(CompactFilesTest, MultipleLevel) {
   for (int invalid_output_level = 0; invalid_output_level < 5;
        invalid_output_level++) {
     s = db->CompactFiles(CompactionOptions(), files, invalid_output_level);
-    std::cout << s.ToString() << std::endl;
     ASSERT_TRUE(s.IsInvalidArgument());
   }
 
@@ -358,6 +360,7 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   std::shared_ptr<FilterWithGet> cf(new FilterWithGet());
 
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.create_if_missing = true;
   options.compaction_filter = cf.get();
 
@@ -400,6 +403,7 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
                                 CompactionStyle::kCompactionStyleNone}) {
     ASSERT_OK(DestroyDB(db_name_, Options()));
     Options options;
+    options.level_compaction_dynamic_level_bytes = false;
     options.compaction_style = compaction_style;
     // L0: Snappy, L1: ZSTD, L2: Snappy
     options.compression_per_level = {CompressionType::kSnappyCompression,

db/compaction/compaction.cc

@@ -23,14 +23,13 @@ namespace ROCKSDB_NAMESPACE {
 const uint64_t kRangeTombstoneSentinel =
     PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
 
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b) {
-  auto c = user_cmp->CompareWithoutTimestamp(a.user_key(), b.user_key());
+int sstableKeyCompare(const Comparator* uc, const Slice& a, const Slice& b) {
+  auto c = uc->CompareWithoutTimestamp(ExtractUserKey(a), ExtractUserKey(b));
   if (c != 0) {
     return c;
   }
-  auto a_footer = ExtractInternalKeyFooter(a.Encode());
-  auto b_footer = ExtractInternalKeyFooter(b.Encode());
+  auto a_footer = ExtractInternalKeyFooter(a);
+  auto b_footer = ExtractInternalKeyFooter(b);
   if (a_footer == kRangeTombstoneSentinel) {
     if (b_footer != kRangeTombstoneSentinel) {
       return -1;
@@ -465,6 +464,11 @@ bool Compaction::IsTrivialMove() const {
     return false;
   }
 
+  if (compaction_reason_ == CompactionReason::kChangeTemperature) {
+    // Changing temperature usually requires rewriting the file.
+    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) &&
@@ -481,26 +485,25 @@ bool Compaction::IsTrivialMove() const {
 
   // assert inputs_.size() == 1
 
-  std::unique_ptr<SstPartitioner> partitioner = CreateSstPartitioner();
-
-  for (const auto& file : inputs_.front().files) {
-    std::vector<FileMetaData*> file_grand_parents;
-    if (output_level_ + 1 >= number_levels_) {
-      continue;
-    }
-    input_vstorage_->GetOverlappingInputs(output_level_ + 1, &file->smallest,
-                                          &file->largest, &file_grand_parents);
-    const auto compaction_size =
-        file->fd.GetFileSize() + TotalFileSize(file_grand_parents);
-    if (compaction_size > max_compaction_bytes_) {
-      return false;
-    }
-
-    if (partitioner.get() != nullptr) {
-      if (!partitioner->CanDoTrivialMove(file->smallest.user_key(),
-                                         file->largest.user_key())) {
+  if (output_level_ + 1 < number_levels_) {
+    std::unique_ptr<SstPartitioner> partitioner = CreateSstPartitioner();
+    for (const auto& file : inputs_.front().files) {
+      std::vector<FileMetaData*> file_grand_parents;
+      input_vstorage_->GetOverlappingInputs(output_level_ + 1, &file->smallest,
+                                            &file->largest,
+                                            &file_grand_parents);
+      const auto compaction_size =
+          file->fd.GetFileSize() + TotalFileSize(file_grand_parents);
+      if (compaction_size > max_compaction_bytes_) {
         return false;
       }
+
+      if (partitioner.get() != nullptr) {
+        if (!partitioner->CanDoTrivialMove(file->smallest.user_key(),
+                                           file->largest.user_key())) {
+          return false;
+        }
+      }
     }
   }
 
@@ -558,6 +561,49 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   return false;
 }
 
+bool Compaction::KeyRangeNotExistsBeyondOutputLevel(
+    const Slice& begin_key, const Slice& end_key,
+    std::vector<size_t>* level_ptrs) const {
+  assert(input_version_ != nullptr);
+  assert(level_ptrs != nullptr);
+  assert(level_ptrs->size() == static_cast<size_t>(number_levels_));
+  assert(cfd_->user_comparator()->CompareWithoutTimestamp(begin_key, end_key) <
+         0);
+  if (bottommost_level_) {
+    return true /* does not overlap */;
+  } else if (output_level_ != 0 &&
+             cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
+    const Comparator* user_cmp = cfd_->user_comparator();
+    for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
+      const std::vector<FileMetaData*>& files =
+          input_vstorage_->LevelFiles(lvl);
+      for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
+        auto* f = files[level_ptrs->at(lvl)];
+        // Advance until the first file with begin_key <= f->largest.user_key()
+        if (user_cmp->CompareWithoutTimestamp(begin_key,
+                                              f->largest.user_key()) > 0) {
+          continue;
+        }
+        // We know that the previous file prev_f, if exists, has
+        // prev_f->largest.user_key() < begin_key.
+        if (user_cmp->CompareWithoutTimestamp(end_key,
+                                              f->smallest.user_key()) <= 0) {
+          // not overlapping with this level
+          break;
+        } else {
+          // We have:
+          // - begin_key < end_key,
+          // - begin_key <= f->largest.user_key(), and
+          // - end_key > f->smallest.user_key()
+          return false /* overlap */;
+        }
+      }
+    }
+    return true /* does not overlap */;
+  }
+  return false /* overlaps */;
+};
+
 // Mark (or clear) each file that is being compacted
 void Compaction::MarkFilesBeingCompacted(bool mark_as_compacted) {
   for (size_t i = 0; i < num_input_levels(); i++) {

db/compaction/compaction.h

@@ -31,8 +31,19 @@ namespace ROCKSDB_NAMESPACE {
 // that key never appears in the database. We don't want adjacent sstables to
 // be considered overlapping if they are separated by the range tombstone
 // sentinel.
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b);
+int sstableKeyCompare(const Comparator* user_cmp, const Slice&, const Slice&);
+inline int sstableKeyCompare(const Comparator* user_cmp, const Slice& a,
+                             const InternalKey& b) {
+  return sstableKeyCompare(user_cmp, a, b.Encode());
+}
+inline int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                             const Slice& b) {
+  return sstableKeyCompare(user_cmp, a.Encode(), b);
+}
+inline int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                             const InternalKey& b) {
+  return sstableKeyCompare(user_cmp, a.Encode(), b.Encode());
+}
 int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
                       const InternalKey& b);
 int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
@@ -203,10 +214,18 @@ class Compaction {
   void AddInputDeletions(VersionEdit* edit);
 
   // Returns true if the available information we have guarantees that
-  // the input "user_key" does not exist in any level beyond "output_level()".
+  // the input "user_key" does not exist in any level beyond `output_level()`.
   bool KeyNotExistsBeyondOutputLevel(const Slice& user_key,
                                      std::vector<size_t>* level_ptrs) const;
 
+  // Returns true if the user key range [begin_key, end_key) does not exist
+  // in any level beyond `output_level()`.
+  // Used for checking range tombstones, so we assume begin_key < end_key.
+  // begin_key and end_key should include timestamp if enabled.
+  bool KeyRangeNotExistsBeyondOutputLevel(
+      const Slice& begin_key, const Slice& end_key,
+      std::vector<size_t>* level_ptrs) const;
+
   // Clear all files to indicate that they are not being compacted
   // Delete this compaction from the list of running compactions.
   //
@@ -546,13 +565,16 @@ struct PerKeyPlacementContext {
   const Slice value;
   const SequenceNumber seq_num;
 
-  bool output_to_penultimate_level;
+  bool& output_to_penultimate_level;
 
   PerKeyPlacementContext(int _level, Slice _key, Slice _value,
-                         SequenceNumber _seq_num)
-      : level(_level), key(_key), value(_value), seq_num(_seq_num) {
-    output_to_penultimate_level = false;
-  }
+                         SequenceNumber _seq_num,
+                         bool& _output_to_penultimate_level)
+      : level(_level),
+        key(_key),
+        value(_value),
+        seq_num(_seq_num),
+        output_to_penultimate_level(_output_to_penultimate_level) {}
 };
 #endif /* !NDEBUG */
 

db/compaction/compaction_iterator.cc

@@ -1201,17 +1201,7 @@ void CompactionIterator::GarbageCollectBlobIfNeeded() {
 
 void CompactionIterator::DecideOutputLevel() {
   assert(compaction_->SupportsPerKeyPlacement());
-#ifndef NDEBUG
-  // Could be overridden by unittest
-  PerKeyPlacementContext context(level_, ikey_.user_key, value_,
-                                 ikey_.sequence);
-  TEST_SYNC_POINT_CALLBACK("CompactionIterator::PrepareOutput.context",
-                           &context);
-  output_to_penultimate_level_ = context.output_to_penultimate_level;
-#else
   output_to_penultimate_level_ = false;
-#endif  // NDEBUG
-
   // if the key is newer than the cutoff sequence or within the earliest
   // snapshot, it should output to the penultimate level.
   if (ikey_.sequence > preclude_last_level_min_seqno_ ||
@@ -1219,6 +1209,17 @@ void CompactionIterator::DecideOutputLevel() {
     output_to_penultimate_level_ = true;
   }
 
+#ifndef NDEBUG
+  // Could be overridden by unittest
+  PerKeyPlacementContext context(level_, ikey_.user_key, value_, ikey_.sequence,
+                                 output_to_penultimate_level_);
+  TEST_SYNC_POINT_CALLBACK("CompactionIterator::PrepareOutput.context",
+                           &context);
+  if (ikey_.sequence > earliest_snapshot_) {
+    output_to_penultimate_level_ = true;
+  }
+#endif  // NDEBUG
+
   if (output_to_penultimate_level_) {
     // If it's decided to output to the penultimate level, but unsafe to do so,
     // still output to the last level. For example, moving the data from a lower
@@ -1411,6 +1412,7 @@ std::unique_ptr<BlobFetcher> CompactionIterator::CreateBlobFetcherIfNeeded(
   }
 
   ReadOptions read_options;
+  read_options.io_activity = Env::IOActivity::kCompaction;
   read_options.fill_cache = false;
 
   return std::unique_ptr<BlobFetcher>(new BlobFetcher(version, read_options));

db/compaction/compaction_job.cc

@@ -192,8 +192,8 @@ CompactionJob::CompactionJob(
   assert(log_buffer_ != nullptr);
 
   const auto* cfd = compact_->compaction->column_family_data();
-  ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
-                                    db_options_.enable_thread_tracking);
+  ThreadStatusUtil::SetEnableTracking(db_options_.enable_thread_tracking);
+  ThreadStatusUtil::SetColumnFamily(cfd);
   ThreadStatusUtil::SetThreadOperation(ThreadStatus::OP_COMPACTION);
   ReportStartedCompaction(compaction);
 }
@@ -204,10 +204,6 @@ CompactionJob::~CompactionJob() {
 }
 
 void CompactionJob::ReportStartedCompaction(Compaction* compaction) {
-  const auto* cfd = compact_->compaction->column_family_data();
-  ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
-                                    db_options_.enable_thread_tracking);
-
   ThreadStatusUtil::SetThreadOperationProperty(ThreadStatus::COMPACTION_JOB_ID,
                                                job_id_);
 
@@ -264,7 +260,7 @@ void CompactionJob::Prepare() {
     StopWatch sw(db_options_.clock, stats_, SUBCOMPACTION_SETUP_TIME);
     GenSubcompactionBoundaries();
   }
-  if (boundaries_.size() > 1) {
+  if (boundaries_.size() >= 1) {
     for (size_t i = 0; i <= boundaries_.size(); i++) {
       compact_->sub_compact_states.emplace_back(
           c, (i != 0) ? std::optional<Slice>(boundaries_[i - 1]) : std::nullopt,
@@ -291,12 +287,14 @@ void CompactionJob::Prepare() {
                c->immutable_options()->preclude_last_level_data_seconds);
 
   if (preserve_time_duration > 0) {
+    const ReadOptions read_options(Env::IOActivity::kCompaction);
     // setup seqno_time_mapping_
     seqno_time_mapping_.SetMaxTimeDuration(preserve_time_duration);
     for (const auto& each_level : *c->inputs()) {
       for (const auto& fmd : each_level.files) {
         std::shared_ptr<const TableProperties> tp;
-        Status s = cfd->current()->GetTableProperties(&tp, fmd, nullptr);
+        Status s =
+            cfd->current()->GetTableProperties(read_options, &tp, fmd, nullptr);
         if (s.ok()) {
           seqno_time_mapping_.Add(tp->seqno_to_time_mapping)
               .PermitUncheckedError();
@@ -472,7 +470,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
   // overlap with N-1 other ranges. Since we requested a relatively large number
   // (128) of ranges from each input files, even N range overlapping would
   // cause relatively small inaccuracy.
-
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
   auto* c = compact_->compaction;
   if (c->max_subcompactions() <= 1 &&
       !(c->immutable_options()->compaction_pri == kRoundRobin &&
@@ -506,7 +504,9 @@ void CompactionJob::GenSubcompactionBoundaries() {
         FileMetaData* f = flevel->files[i].file_metadata;
         std::vector<TableReader::Anchor> my_anchors;
         Status s = cfd->table_cache()->ApproximateKeyAnchors(
-            ReadOptions(), icomp, *f, my_anchors);
+            read_options, icomp, *f,
+            c->mutable_cf_options()->block_protection_bytes_per_key,
+            my_anchors);
         if (!s.ok() || my_anchors.empty()) {
           my_anchors.emplace_back(f->largest.user_key(), f->fd.GetFileSize());
         }
@@ -722,11 +722,12 @@ Status CompactionJob::Run() {
         // use_direct_io_for_flush_and_compaction is true, we will regard this
         // verification as user reads since the goal is to cache it here for
         // further user reads
-        ReadOptions read_options;
+        const ReadOptions verify_table_read_options(
+            Env::IOActivity::kCompaction);
         InternalIterator* iter = cfd->table_cache()->NewIterator(
-            read_options, file_options_, cfd->internal_comparator(),
-            files_output[file_idx]->meta, /*range_del_agg=*/nullptr,
-            prefix_extractor,
+            verify_table_read_options, file_options_,
+            cfd->internal_comparator(), files_output[file_idx]->meta,
+            /*range_del_agg=*/nullptr, prefix_extractor,
             /*table_reader_ptr=*/nullptr,
             cfd->internal_stats()->GetFileReadHist(
                 compact_->compaction->output_level()),
@@ -736,7 +737,9 @@ Status CompactionJob::Run() {
                 *compact_->compaction->mutable_cf_options()),
             /*smallest_compaction_key=*/nullptr,
             /*largest_compaction_key=*/nullptr,
-            /*allow_unprepared_value=*/false);
+            /*allow_unprepared_value=*/false,
+            compact_->compaction->mutable_cf_options()
+                ->block_protection_bytes_per_key);
         auto s = iter->status();
 
         if (s.ok() && paranoid_file_checks_) {
@@ -805,8 +808,8 @@ Status CompactionJob::Run() {
   RecordCompactionIOStats();
   LogFlush(db_options_.info_log);
   TEST_SYNC_POINT("CompactionJob::Run():End");
-
   compact_->status = status;
+  TEST_SYNC_POINT_CALLBACK("CompactionJob::Run():EndStatusSet", &status);
   return status;
 }
 
@@ -1032,7 +1035,6 @@ void CompactionJob::NotifyOnSubcompactionCompleted(
 void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   assert(sub_compact);
   assert(sub_compact->compaction);
-
   if (db_options_.compaction_service) {
     CompactionServiceJobStatus comp_status =
         ProcessKeyValueCompactionWithCompactionService(sub_compact);
@@ -1083,6 +1085,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   read_options.verify_checksums = true;
   read_options.fill_cache = false;
   read_options.rate_limiter_priority = GetRateLimiterPriority();
+  read_options.io_activity = Env::IOActivity::kCompaction;
   // Compaction iterators shouldn't be confined to a single prefix.
   // Compactions use Seek() for
   // (a) concurrent compactions,
@@ -1093,17 +1096,17 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // GenSubcompactionBoundaries doesn't strip away the timestamp.
   size_t ts_sz = cfd->user_comparator()->timestamp_size();
   if (start.has_value()) {
-    read_options.iterate_lower_bound = &start.value();
+    read_options.iterate_lower_bound = &(*start);
     if (ts_sz > 0) {
-      start_without_ts = StripTimestampFromUserKey(start.value(), ts_sz);
-      read_options.iterate_lower_bound = &start_without_ts.value();
+      start_without_ts = StripTimestampFromUserKey(*start, ts_sz);
+      read_options.iterate_lower_bound = &(*start_without_ts);
     }
   }
   if (end.has_value()) {
-    read_options.iterate_upper_bound = &end.value();
+    read_options.iterate_upper_bound = &(*end);
     if (ts_sz > 0) {
-      end_without_ts = StripTimestampFromUserKey(end.value(), ts_sz);
-      read_options.iterate_upper_bound = &end_without_ts.value();
+      end_without_ts = StripTimestampFromUserKey(*end, ts_sz);
+      read_options.iterate_upper_bound = &(*end_without_ts);
     }
   }
 
@@ -1135,8 +1138,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   }
 
   if (start.has_value()) {
-    start_ikey.SetInternalKey(start.value(), kMaxSequenceNumber,
-                              kValueTypeForSeek);
+    start_ikey.SetInternalKey(*start, kMaxSequenceNumber, kValueTypeForSeek);
     if (ts_sz > 0) {
       start_ikey.UpdateInternalKey(kMaxSequenceNumber, kValueTypeForSeek,
                                    &ts_slice);
@@ -1145,7 +1147,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     start_user_key = start_ikey.GetUserKey();
   }
   if (end.has_value()) {
-    end_ikey.SetInternalKey(end.value(), kMaxSequenceNumber, kValueTypeForSeek);
+    end_ikey.SetInternalKey(*end, kMaxSequenceNumber, kValueTypeForSeek);
     if (ts_sz > 0) {
       end_ikey.UpdateInternalKey(kMaxSequenceNumber, kValueTypeForSeek,
                                  &ts_slice);
@@ -1286,8 +1288,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
     // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
     // returns true.
-    assert(!end.has_value() || cfd->user_comparator()->Compare(
-                                   c_iter->user_key(), end.value()) < 0);
+    assert(!end.has_value() ||
+           cfd->user_comparator()->Compare(c_iter->user_key(), *end) < 0);
 
     if (c_iter_stats.num_input_records % kRecordStatsEvery ==
         kRecordStatsEvery - 1) {
@@ -1640,6 +1642,7 @@ Status CompactionJob::InstallCompactionResults(
 
   db_mutex_->AssertHeld();
 
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
   auto* compaction = compact_->compaction;
   assert(compaction);
 
@@ -1717,8 +1720,8 @@ Status CompactionJob::InstallCompactionResults(
   }
 
   return versions_->LogAndApply(compaction->column_family_data(),
-                                mutable_cf_options, edit, db_mutex_,
-                                db_directory_);
+                                mutable_cf_options, read_options, edit,
+                                db_mutex_, db_directory_);
 }
 
 void CompactionJob::RecordCompactionIOStats() {
@@ -1814,10 +1817,10 @@ Status CompactionJob::OpenCompactionOutputFile(SubcompactionState* sub_compact,
   uint64_t current_time = static_cast<uint64_t>(temp_current_time);
   InternalKey tmp_start, tmp_end;
   if (sub_compact->start.has_value()) {
-    tmp_start.SetMinPossibleForUserKey(sub_compact->start.value());
+    tmp_start.SetMinPossibleForUserKey(*(sub_compact->start));
   }
   if (sub_compact->end.has_value()) {
-    tmp_end.SetMinPossibleForUserKey(sub_compact->end.value());
+    tmp_end.SetMinPossibleForUserKey(*(sub_compact->end));
   }
   uint64_t oldest_ancester_time =
       sub_compact->compaction->MinInputFileOldestAncesterTime(

db/compaction/compaction_job_stats_test.cc

@@ -24,7 +24,7 @@
 #include "db/write_batch_internal.h"
 #include "env/mock_env.h"
 #include "file/filename.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "monitoring/thread_status_util.h"
 #include "port/stack_trace.h"
 #include "rocksdb/cache.h"
@@ -54,7 +54,7 @@
 #include "util/compression.h"
 #include "util/hash.h"
 #include "util/mutexlock.h"
-#include "util/rate_limiter.h"
+#include "util/rate_limiter_impl.h"
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
@@ -616,6 +616,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
   // via AddExpectedStats().
   auto* stats_checker = new CompactionJobStatsChecker();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.listeners.emplace_back(stats_checker);
   options.create_if_missing = true;
   // just enough setting to hold off auto-compaction.
@@ -815,6 +816,7 @@ TEST_P(CompactionJobStatsTest, DeletionStatsTest) {
   // what we expect.
   auto* stats_checker = new CompactionJobDeletionStatsChecker();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.listeners.emplace_back(stats_checker);
   options.create_if_missing = true;
   options.level0_file_num_compaction_trigger = kTestScale + 1;

db/compaction/compaction_job_test.cc

@@ -373,7 +373,7 @@ class CompactionJobTestBase : public testing::Test {
     } else if (table_type_ == TableTypeForTest::kMockTable) {
       file_size = 10;
       EXPECT_OK(mock_table_factory_->CreateMockTable(
-          env_, GenerateFileName(file_number), std::move(contents)));
+          env_, GenerateFileName(file_number), contents));
     } else {
       assert(false);
     }
@@ -386,12 +386,13 @@ class CompactionJobTestBase : public testing::Test {
         kUnknownFileCreationTime,
         versions_->GetColumnFamilySet()->GetDefault()->NewEpochNumber(),
         kUnknownFileChecksum, kUnknownFileChecksumFuncName, kNullUniqueId64x2,
-        0);
+        /*compensated_range_deletion_size=*/0, /*tail_size=*/0,
+        /*user_defined_timestamps_persisted=*/true);
 
     mutex_.Lock();
-    EXPECT_OK(
-        versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
-                               mutable_cf_options_, &edit, &mutex_, nullptr));
+    EXPECT_OK(versions_->LogAndApply(
+        versions_->GetColumnFamilySet()->GetDefault(), mutable_cf_options_,
+        read_options_, &edit, &mutex_, nullptr));
     mutex_.Unlock();
   }
 
@@ -454,7 +455,8 @@ class CompactionJobTestBase : public testing::Test {
       Status s = cf_options_.table_factory->NewTableReader(
           read_opts,
           TableReaderOptions(*cfd->ioptions(), nullptr, FileOptions(),
-                             cfd_->internal_comparator()),
+                             cfd_->internal_comparator(),
+                             0 /* block_protection_bytes_per_key */),
           std::move(freader), file_size, &table_reader, false);
       ASSERT_OK(s);
       assert(table_reader);
@@ -727,6 +729,7 @@ class CompactionJobTestBase : public testing::Test {
   ColumnFamilyOptions cf_options_;
   MutableCFOptions mutable_cf_options_;
   MutableDBOptions mutable_db_options_;
+  const ReadOptions read_options_;
   std::shared_ptr<Cache> table_cache_;
   WriteController write_controller_;
   WriteBufferManager write_buffer_manager_;
@@ -2440,4 +2443,3 @@ int main(int argc, char** argv) {
   RegisterCustomObjects(argc, argv);
   return RUN_ALL_TESTS();
 }
-

db/compaction/compaction_outputs.cc

@@ -43,7 +43,10 @@ Status CompactionOutputs::Finish(const Status& intput_status,
   const uint64_t current_bytes = builder_->FileSize();
   if (s.ok()) {
     meta->fd.file_size = current_bytes;
+    meta->tail_size = builder_->GetTailSize();
     meta->marked_for_compaction = builder_->NeedCompact();
+    meta->user_defined_timestamps_persisted = static_cast<bool>(
+        builder_->GetTableProperties().user_defined_timestamps_persisted);
   }
   current_output().finished = true;
   stats_.bytes_written += current_bytes;
@@ -124,11 +127,6 @@ size_t CompactionOutputs::UpdateGrandparentBoundaryInfo(
   if (grandparents.empty()) {
     return curr_key_boundary_switched_num;
   }
-  assert(!internal_key.empty());
-  InternalKey ikey;
-  ikey.DecodeFrom(internal_key);
-  assert(ikey.Valid());
-
   const Comparator* ucmp = compaction_->column_family_data()->user_comparator();
 
   // Move the grandparent_index_ to the file containing the current user_key.
@@ -136,7 +134,7 @@ size_t CompactionOutputs::UpdateGrandparentBoundaryInfo(
   // index points to the last file containing the key.
   while (grandparent_index_ < grandparents.size()) {
     if (being_grandparent_gap_) {
-      if (sstableKeyCompare(ucmp, ikey,
+      if (sstableKeyCompare(ucmp, internal_key,
                             grandparents[grandparent_index_]->smallest) < 0) {
         break;
       }
@@ -149,13 +147,13 @@ size_t CompactionOutputs::UpdateGrandparentBoundaryInfo(
       being_grandparent_gap_ = false;
     } else {
       int cmp_result = sstableKeyCompare(
-          ucmp, ikey, grandparents[grandparent_index_]->largest);
+          ucmp, internal_key, grandparents[grandparent_index_]->largest);
       // If it's same key, make sure grandparent_index_ is pointing to the last
       // one.
       if (cmp_result < 0 ||
           (cmp_result == 0 &&
            (grandparent_index_ == grandparents.size() - 1 ||
-            sstableKeyCompare(ucmp, ikey,
+            sstableKeyCompare(ucmp, internal_key,
                               grandparents[grandparent_index_ + 1]->smallest) <
                 0))) {
         break;
@@ -574,6 +572,7 @@ Status CompactionOutputs::AddRangeDels(
   auto it = range_del_agg_->NewIterator(lower_bound, upper_bound);
   Slice last_tombstone_start_user_key{};
   bool reached_lower_bound = false;
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
   for (it->SeekToFirst(); it->Valid(); it->Next()) {
     auto tombstone = it->Tombstone();
     auto kv = tombstone.Serialize();
@@ -596,10 +595,12 @@ Status CompactionOutputs::AddRangeDels(
     // in any snapshot. trim_ts_ is passed to the constructor for
     // range_del_agg_, and range_del_agg_ internally drops tombstones above
     // trim_ts_.
-    if (bottommost_level && tombstone.seq_ <= earliest_snapshot &&
+    bool consider_drop =
+        tombstone.seq_ <= earliest_snapshot &&
         (ts_sz == 0 ||
          (!full_history_ts_low.empty() &&
-          ucmp->CompareTimestamp(tombstone.ts_, full_history_ts_low) < 0))) {
+          ucmp->CompareTimestamp(tombstone.ts_, full_history_ts_low) < 0));
+    if (consider_drop && bottommost_level) {
       // TODO(andrewkr): tombstones that span multiple output files are
       // counted for each compaction output file, so lots of double
       // counting.
@@ -633,6 +634,20 @@ Status CompactionOutputs::AddRangeDels(
         icmp.Compare(*upper_bound, tombstone_start.Encode()) < 0) {
       break;
     }
+    if (lower_bound &&
+        icmp.Compare(tombstone_start.Encode(), *lower_bound) < 0) {
+      tombstone_start.DecodeFrom(*lower_bound);
+    }
+    if (upper_bound && icmp.Compare(*upper_bound, tombstone_end.Encode()) < 0) {
+      tombstone_end.DecodeFrom(*upper_bound);
+    }
+    if (consider_drop && compaction_->KeyRangeNotExistsBeyondOutputLevel(
+                             tombstone_start.user_key(),
+                             tombstone_end.user_key(), &level_ptrs_)) {
+      range_del_out_stats.num_range_del_drop_obsolete++;
+      range_del_out_stats.num_record_drop_obsolete++;
+      continue;
+    }
     // Here we show that *only* range tombstones that overlap with
     // [lower_bound, upper_bound] are added to the current file, and
     // sanity checking invariants that should hold:
@@ -686,13 +701,6 @@ Status CompactionOutputs::AddRangeDels(
 
     // Range tombstone is not supported by output validator yet.
     builder_->Add(kv.first.Encode(), kv.second);
-    if (lower_bound &&
-        icmp.Compare(tombstone_start.Encode(), *lower_bound) < 0) {
-      tombstone_start.DecodeFrom(*lower_bound);
-    }
-    if (upper_bound && icmp.Compare(*upper_bound, tombstone_end.Encode()) < 0) {
-      tombstone_end.DecodeFrom(*upper_bound);
-    }
     assert(icmp.Compare(tombstone_start, tombstone_end) <= 0);
     meta.UpdateBoundariesForRange(tombstone_start, tombstone_end,
                                   tombstone.seq_, icmp);
@@ -713,7 +721,7 @@ Status CompactionOutputs::AddRangeDels(
           approx_opts.files_size_error_margin = 0.1;
           auto approximate_covered_size =
               compaction_->input_version()->version_set()->ApproximateSize(
-                  approx_opts, compaction_->input_version(),
+                  approx_opts, read_options, compaction_->input_version(),
                   tombstone_start.Encode(), tombstone_end.Encode(),
                   compaction_->output_level() + 1 /* start_level */,
                   -1 /* end_level */, kCompaction);
@@ -777,6 +785,8 @@ CompactionOutputs::CompactionOutputs(const Compaction* compaction,
   if (compaction->output_level() != 0) {
     FillFilesToCutForTtl();
   }
+
+  level_ptrs_ = std::vector<size_t>(compaction_->number_levels(), 0);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_outputs.h

@@ -206,10 +206,10 @@ class CompactionOutputs {
       // We may only split the output when the cursor is in the range. Split
       if ((!end.has_value() ||
            icmp->user_comparator()->Compare(
-               ExtractUserKey(output_split_key->Encode()), end.value()) < 0) &&
-          (!start.has_value() || icmp->user_comparator()->Compare(
-                                     ExtractUserKey(output_split_key->Encode()),
-                                     start.value()) > 0)) {
+               ExtractUserKey(output_split_key->Encode()), *end) < 0) &&
+          (!start.has_value() ||
+           icmp->user_comparator()->Compare(
+               ExtractUserKey(output_split_key->Encode()), *start) > 0)) {
         local_output_split_key_ = output_split_key;
       }
     }
@@ -356,6 +356,15 @@ class CompactionOutputs {
   // The smallest key of the current output file, this is set when current
   // output file's smallest key is a range tombstone start key.
   InternalKey range_tombstone_lower_bound_;
+
+  // Used for calls to compaction->KeyRangeNotExistsBeyondOutputLevel() in
+  // CompactionOutputs::AddRangeDels().
+  // level_ptrs_[i] holds index of the file that was checked during the last
+  // call to compaction->KeyRangeNotExistsBeyondOutputLevel(). This allows
+  // future calls to the function to pick up where it left off, since each
+  // range tombstone added to output file within each subcompaction is in
+  // increasing key range.
+  std::vector<size_t> level_ptrs_;
 };
 
 // helper struct to concatenate the last level and penultimate level outputs

db/compaction/compaction_picker.cc

@@ -20,7 +20,7 @@
 #include "file/filename.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "test_util/sync_point.h"
 #include "util/random.h"
 #include "util/string_util.h"
@@ -611,23 +611,21 @@ Compaction* CompactionPicker::CompactRange(
     // Universal compaction with more than one level always compacts all the
     // files together to the last level.
     assert(vstorage->num_levels() > 1);
+    int max_output_level =
+        vstorage->MaxOutputLevel(ioptions_.allow_ingest_behind);
     // DBImpl::CompactRange() set output level to be the last level
-    if (ioptions_.allow_ingest_behind) {
-      assert(output_level == vstorage->num_levels() - 2);
-    } else {
-      assert(output_level == vstorage->num_levels() - 1);
-    }
+    assert(output_level == max_output_level);
     // DBImpl::RunManualCompaction will make full range for universal compaction
     assert(begin == nullptr);
     assert(end == nullptr);
     *compaction_end = nullptr;
 
     int start_level = 0;
-    for (; start_level < vstorage->num_levels() &&
+    for (; start_level <= max_output_level &&
            vstorage->NumLevelFiles(start_level) == 0;
          start_level++) {
     }
-    if (start_level == vstorage->num_levels()) {
+    if (start_level > max_output_level) {
       return nullptr;
     }
 
@@ -637,9 +635,9 @@ Compaction* CompactionPicker::CompactRange(
       return nullptr;
     }
 
-    std::vector<CompactionInputFiles> inputs(vstorage->num_levels() -
+    std::vector<CompactionInputFiles> inputs(max_output_level + 1 -
                                              start_level);
-    for (int level = start_level; level < vstorage->num_levels(); level++) {
+    for (int level = start_level; level <= max_output_level; level++) {
       inputs[level - start_level].level = level;
       auto& files = inputs[level - start_level].files;
       for (FileMetaData* f : vstorage->LevelFiles(level)) {
@@ -753,8 +751,10 @@ Compaction* CompactionPicker::CompactRange(
 
   // for BOTTOM LEVEL compaction only, use max_file_num_to_ignore to filter out
   // files that are created during the current compaction.
-  if (compact_range_options.bottommost_level_compaction ==
-          BottommostLevelCompaction::kForceOptimized &&
+  if ((compact_range_options.bottommost_level_compaction ==
+           BottommostLevelCompaction::kForceOptimized ||
+       compact_range_options.bottommost_level_compaction ==
+           BottommostLevelCompaction::kIfHaveCompactionFilter) &&
       max_file_num_to_ignore != std::numeric_limits<uint64_t>::max()) {
     assert(input_level == output_level);
     // inputs_shrunk holds a continuous subset of input files which were all

db/compaction/compaction_picker_fifo.cc

@@ -16,6 +16,7 @@
 #include "db/column_family.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
+#include "options/options_helper.h"
 #include "util/string_util.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -284,31 +285,36 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
   return c;
 }
 
-Compaction* FIFOCompactionPicker::PickCompactionToWarm(
+Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
     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) {
+  const std::vector<FileTemperatureAge>& ages =
+      mutable_cf_options.compaction_options_fifo
+          .file_temperature_age_thresholds;
+  if (ages.empty()) {
     return nullptr;
   }
 
-  // PickCompactionToWarm is only triggered if there is no non-L0 files.
-  for (int level = 1; level < vstorage->num_levels(); ++level) {
-    if (GetTotalFilesSize(vstorage->LevelFiles(level)) > 0) {
-      return nullptr;
-    }
+  // Does not apply to multi-level FIFO.
+  if (vstorage->num_levels() > 1) {
+    return nullptr;
   }
 
   const int kLevel0 = 0;
   const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  if (level_files.empty()) {
+    return nullptr;
+  }
 
   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());
+    ROCKS_LOG_BUFFER(
+        log_buffer,
+        "[%s] FIFO compaction: Couldn't get current time: %s. "
+        "Not doing compactions based on file temperature-age threshold. ",
+        cf_name.c_str(), status.ToString().c_str());
     return nullptr;
   }
   const uint64_t current_time = static_cast<uint64_t>(_current_time);
@@ -327,56 +333,77 @@ Compaction* FIFOCompactionPicker::PickCompactionToWarm(
   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 min_age = ages[0].age;
+  // kLastTemperature means target temperature is to be determined.
+  Temperature compaction_target_temp = Temperature::kLastTemperature;
+  if (current_time > min_age) {
+    uint64_t create_time_threshold = current_time - min_age;
     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.
+    // We will ideally identify a file qualifying for temperature change 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 previous file's (which is just younger) oldest entry's timestamp.
+    Temperature cur_target_temp;
+    // avoid index underflow
+    assert(level_files.size() >= 1);
+    for (size_t index = level_files.size() - 1; index >= 1; --index) {
+      // Try to add cur_file to compaction inputs.
+      FileMetaData* cur_file = level_files[index];
+      // prev_file is just younger than cur_file
+      FileMetaData* prev_file = level_files[index - 1];
+      if (cur_file->being_compacted) {
+        // Should not happen since we check for
+        // `level0_compactions_in_progress_` above. Here we simply just don't
+        // schedule anything.
         return nullptr;
       }
-      uint64_t oldest_ancester_time = f->TryGetOldestAncesterTime();
-      if (oldest_ancester_time == kUnknownOldestAncesterTime) {
+      uint64_t oldest_ancestor_time = prev_file->TryGetOldestAncesterTime();
+      if (oldest_ancestor_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.
+      if (oldest_ancestor_time > create_time_threshold) {
+        // cur_file is too fresh
         break;
       }
-      if (prev_file != nullptr) {
-        compaction_size += prev_file->fd.GetFileSize();
-        if (compaction_size > mutable_cf_options.max_compaction_bytes) {
+      cur_target_temp = ages[0].temperature;
+      for (size_t i = 1; i < ages.size(); ++i) {
+        if (current_time >= ages[i].age &&
+            oldest_ancestor_time <= current_time - ages[i].age) {
+          cur_target_temp = ages[i].temperature;
+        }
+      }
+      if (cur_file->temperature == cur_target_temp) {
+        if (inputs[0].empty()) {
+          continue;
+        } else {
           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.
+
+      // cur_file needs to change temperature
+      if (compaction_target_temp == Temperature::kLastTemperature) {
+        assert(inputs[0].empty());
+        compaction_target_temp = cur_target_temp;
+      } else if (cur_target_temp != compaction_target_temp) {
+        assert(!inputs[0].empty());
+        break;
+      }
+      if (inputs[0].empty() || compaction_size + cur_file->fd.GetFileSize() <=
+                                   mutable_cf_options.max_compaction_bytes) {
+        inputs[0].files.push_back(cur_file);
+        compaction_size += cur_file->fd.GetFileSize();
+        ROCKS_LOG_BUFFER(
+            log_buffer,
+            "[%s] FIFO compaction: picking file %" PRIu64
+            " with next file's oldest time %" PRIu64 " for temperature %s.",
+            cf_name.c_str(), cur_file->fd.GetNumber(), oldest_ancestor_time,
+            temperature_to_string[cur_target_temp].c_str());
+      }
+      if (compaction_size > mutable_cf_options.max_compaction_bytes) {
         break;
-      } else {
-        assert(prev_file == nullptr);
       }
     }
   }
@@ -390,7 +417,7 @@ Compaction* FIFOCompactionPicker::PickCompactionToWarm(
       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,
+      compaction_target_temp,
       /* max_subcompactions */ 0, {}, /* is manual */ false, /* trim_ts */ "",
       vstorage->CompactionScore(0),
       /* is deletion compaction */ false, /* l0_files_might_overlap */ true,
@@ -412,8 +439,8 @@ Compaction* FIFOCompactionPicker::PickCompaction(
                            vstorage, log_buffer);
   }
   if (c == nullptr) {
-    c = PickCompactionToWarm(cf_name, mutable_cf_options, mutable_db_options,
-                             vstorage, log_buffer);
+    c = PickTemperatureChangeCompaction(
+        cf_name, mutable_cf_options, mutable_db_options, vstorage, log_buffer);
   }
   RegisterCompaction(c);
   return c;

db/compaction/compaction_picker_fifo.h

@@ -52,10 +52,9 @@ class FIFOCompactionPicker : public CompactionPicker {
                                  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);
+  Compaction* PickTemperatureChangeCompaction(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
+      LogBuffer* log_buffer);
 };
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_picker_level.cc

@@ -83,7 +83,7 @@ class LevelCompactionBuilder {
 
   Compaction* GetCompaction();
 
-  // For the specfied level, pick a file that we want to compact.
+  // From `start_level_`, pick files to compact to `output_level_`.
   // Returns false if there is no file to compact.
   // If it returns true, inputs->files.size() will be exactly one for
   // all compaction priorities except round-robin. For round-robin,
@@ -107,8 +107,9 @@ class LevelCompactionBuilder {
   bool PickIntraL0Compaction();
 
   // Return true if TrivialMove is extended. `start_index` is the index of
-  // the intiial file picked, which should already be in `start_level_inputs_`.
-  bool TryExtendNonL0TrivialMove(int start_index);
+  // the initial file picked, which should already be in `start_level_inputs_`.
+  bool TryExtendNonL0TrivialMove(int start_index,
+                                 bool only_expand_right = false);
 
   // Picks a file from level_files to compact.
   // level_files is a vector of (level, file metadata) in ascending order of
@@ -355,7 +356,8 @@ void LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion() {
   vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
                                   &output_level_inputs.files);
   if (output_level_inputs.empty()) {
-    if (TryExtendNonL0TrivialMove((int)start_index)) {
+    if (TryExtendNonL0TrivialMove((int)start_index,
+                                  true /* only_expand_right */)) {
       return;
     }
   }
@@ -501,6 +503,16 @@ Compaction* LevelCompactionBuilder::PickCompaction() {
 }
 
 Compaction* LevelCompactionBuilder::GetCompaction() {
+  // TryPickL0TrivialMove() does not apply to the case when compacting L0 to an
+  // empty output level. So L0 files is picked in PickFileToCompact() by
+  // compaction score. We may still be able to do trivial move when this file
+  // does not overlap with other L0s. This happens when
+  // compaction_inputs_[0].size() == 1 since SetupOtherL0FilesIfNeeded() did not
+  // pull in more L0s.
+  assert(!compaction_inputs_.empty());
+  bool l0_files_might_overlap =
+      start_level_ == 0 && !is_l0_trivial_move_ &&
+      (compaction_inputs_.size() > 1 || compaction_inputs_[0].size() > 1);
   auto c = new Compaction(
       vstorage_, ioptions_, mutable_cf_options_, mutable_db_options_,
       std::move(compaction_inputs_), output_level_,
@@ -515,8 +527,7 @@ Compaction* LevelCompactionBuilder::GetCompaction() {
       Temperature::kUnknown,
       /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
       /* trim_ts */ "", start_level_score_, false /* deletion_compaction */,
-      /* l0_files_might_overlap */ start_level_ == 0 && !is_l0_trivial_move_,
-      compaction_reason_);
+      l0_files_might_overlap, compaction_reason_);
 
   // If it's level 0 compaction, make sure we don't execute any other level 0
   // compactions in parallel
@@ -653,7 +664,8 @@ bool LevelCompactionBuilder::TryPickL0TrivialMove() {
   return false;
 }
 
-bool LevelCompactionBuilder::TryExtendNonL0TrivialMove(int start_index) {
+bool LevelCompactionBuilder::TryExtendNonL0TrivialMove(int start_index,
+                                                       bool only_expand_right) {
   if (start_level_inputs_.size() == 1 &&
       (ioptions_.db_paths.empty() || ioptions_.db_paths.size() == 1) &&
       (mutable_cf_options_.compression_per_level.empty())) {
@@ -670,6 +682,7 @@ bool LevelCompactionBuilder::TryExtendNonL0TrivialMove(int start_index) {
     size_t total_size = initial_file->fd.GetFileSize();
     CompactionInputFiles output_level_inputs;
     output_level_inputs.level = output_level_;
+    // Expand towards right
     for (int i = start_index + 1;
          i < static_cast<int>(level_files.size()) &&
          start_level_inputs_.size() < kMaxMultiTrivialMove;
@@ -702,6 +715,37 @@ bool LevelCompactionBuilder::TryExtendNonL0TrivialMove(int start_index) {
       }
       start_level_inputs_.files.push_back(next_file);
     }
+    // Expand towards left
+    if (!only_expand_right) {
+      for (int i = start_index - 1;
+           i >= 0 && start_level_inputs_.size() < kMaxMultiTrivialMove; i--) {
+        FileMetaData* next_file = level_files[i];
+        if (next_file->being_compacted) {
+          break;
+        }
+        vstorage_->GetOverlappingInputs(output_level_, &(next_file->smallest),
+                                        &(initial_file->largest),
+                                        &output_level_inputs.files);
+        if (!output_level_inputs.empty()) {
+          break;
+        }
+        if (i > 0 && compaction_picker_->icmp()
+                             ->user_comparator()
+                             ->CompareWithoutTimestamp(
+                                 next_file->smallest.user_key(),
+                                 level_files[i - 1]->largest.user_key()) == 0) {
+          // Not a clean up after adding the next file. Skip.
+          break;
+        }
+        total_size += next_file->fd.GetFileSize();
+        if (total_size > mutable_cf_options_.max_compaction_bytes) {
+          break;
+        }
+        // keep `files` sorted in increasing order by key range
+        start_level_inputs_.files.insert(start_level_inputs_.files.begin(),
+                                         next_file);
+      }
+    }
     return start_level_inputs_.size() > 1;
   }
   return false;
@@ -785,7 +829,10 @@ bool LevelCompactionBuilder::PickFileToCompact() {
     vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
                                     &output_level_inputs.files);
     if (output_level_inputs.empty()) {
-      if (TryExtendNonL0TrivialMove(index)) {
+      if (start_level_ > 0 &&
+          TryExtendNonL0TrivialMove(index,
+                                    ioptions_.compaction_pri ==
+                                        kRoundRobin /* only_expand_right */)) {
         break;
       }
     } else {

db/compaction/compaction_picker_test.cc

@@ -70,6 +70,11 @@ class CompactionPickerTestBase : public testing::Test {
     mutable_cf_options_.RefreshDerivedOptions(ioptions_);
     ioptions_.cf_paths.emplace_back("dummy",
                                     std::numeric_limits<uint64_t>::max());
+    // When the default value of this option is true, universal compaction
+    // tests can encounter assertion failure since SanitizeOption() is
+    // not run to set this option to false. So we do the sanitization
+    // here. Tests that test this option set this option to true explicitly.
+    ioptions_.level_compaction_dynamic_level_bytes = false;
   }
 
   ~CompactionPickerTestBase() override {}
@@ -148,7 +153,8 @@ class CompactionPickerTestBase : public testing::Test {
         smallest_seq, largest_seq, marked_for_compact, temperature,
         kInvalidBlobFileNumber, kUnknownOldestAncesterTime,
         kUnknownFileCreationTime, epoch_number, kUnknownFileChecksum,
-        kUnknownFileChecksumFuncName, kNullUniqueId64x2, 0);
+        kUnknownFileChecksumFuncName, kNullUniqueId64x2, 0, 0,
+        true /* user_defined_timestamps_persisted */);
     f->compensated_file_size =
         (compensated_file_size != 0) ? compensated_file_size : file_size;
     f->oldest_ancester_time = oldest_ancestor_time;
@@ -505,7 +511,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
 
 TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
   const uint64_t kFileSize = 100000;
-  NewVersionStorage(1, kCompactionStyleUniversal);
+  NewVersionStorage(3 /* num_levels */, kCompactionStyleUniversal);
   ioptions_.allow_ingest_behind = true;
   ioptions_.num_levels = 3;
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
@@ -532,6 +538,14 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
 
   // output level should be the one above the bottom-most
   ASSERT_EQ(1, compaction->output_level());
+
+  // input should not include the reserved level
+  const std::vector<CompactionInputFiles>* inputs = compaction->inputs();
+  for (const auto& compaction_input : *inputs) {
+    if (!compaction_input.empty()) {
+      ASSERT_LT(compaction_input.level, 2);
+    }
+  }
 }
 // Tests if the files can be trivially moved in multi level
 // universal compaction when allow_trivial_move option is set
@@ -1005,29 +1019,28 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   }
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarm1) {
+TEST_F(CompactionPickerTest, FIFOToCold1) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   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);
+      static_cast<uint64_t>(current_time) - kColdThreshold;
+  Add(0 /* level */, 4U /* file_number */, "260", "300", 1 * kFileSize, 0, 2500,
+      2600, 0, true, Temperature::kUnknown,
+      threshold_time - 2000 /* oldest_ancestor_time */);
+  // Qualifies for compaction to kCold.
   Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
       Temperature::kUnknown, threshold_time - 3000);
   UpdateVersionStorageInfo();
@@ -1037,33 +1050,36 @@ TEST_F(CompactionPickerTest, FIFOToWarm1) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(1U, compaction->num_input_files(0));
   ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarm2) {
+TEST_F(CompactionPickerTest, FIFOToCold2) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   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;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   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);
+      Temperature::kUnknown, threshold_time);
+  // The following two files qualify for compaction to kCold.
   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,
@@ -1075,34 +1091,40 @@ TEST_F(CompactionPickerTest, FIFOToWarm2) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   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) {
+TEST_F(CompactionPickerTest, FIFOToColdMaxCompactionSize) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   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;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   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);
+  // The following two files qualify for compaction to kCold.
+  // But only the last two should be included to respect `max_compaction_bytes`.
   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,
@@ -1116,40 +1138,45 @@ TEST_F(CompactionPickerTest, FIFOToWarmMaxSize) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   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) {
+TEST_F(CompactionPickerTest, FIFOToColdWithExistingCold) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   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;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   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);
+  // The following two files qualify for compaction to kCold.
   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);
+      Temperature::kCold, threshold_time - 5000);
   UpdateVersionStorageInfo();
 
   ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
@@ -1157,28 +1184,32 @@ TEST_F(CompactionPickerTest, FIFOToWarmWithExistingWarm) {
       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(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->num_input_files(0));
   ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarmWithOngoing) {
+TEST_F(CompactionPickerTest, FIFOToColdWithHotBetweenCold) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   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;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   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,
@@ -1186,63 +1217,77 @@ TEST_F(CompactionPickerTest, FIFOToWarmWithOngoing) {
   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);
+      Temperature::kCold, threshold_time - 3000);
+  // Qualifies for compaction to kCold.
   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;
+      Temperature::kCold, 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);
-}
-
-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(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(1U, compaction->num_input_files(0));
   ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
 }
 
+TEST_F(CompactionPickerTest, FIFOToColdAndWarm) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 10000;
+  uint64_t kHotThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  // Test that multiple threshold works.
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kHot, kHotThreshold}, {Temperature::kWarm, kWarmThreshold}};
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
+  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 hot_threshold_time =
+      static_cast<uint64_t>(current_time) - kHotThreshold;
+  uint64_t warm_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, hot_threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, hot_threshold_time - 200);
+  // Qualifies for Hot
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, warm_threshold_time - 100);
+  // Qualifies for Warm
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, warm_threshold_time - 4000);
+  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
+      Temperature::kUnknown, warm_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(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  // Assumes compaction picker picks older files first.
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kWarm);
+  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, CompactionPriMinOverlapping1) {
   NewVersionStorage(6, kCompactionStyleLevel);
@@ -1923,6 +1968,15 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys11) {
   ASSERT_EQ(7U, compaction->input(1, 0)->fd.GetNumber());
 }
 
+TEST_F(CompactionPickerTest, FileTtlBoosterLargeNumLevels) {
+  const uint64_t kCurrentTime = 1000000;
+  FileTtlBooster booster(kCurrentTime, /*ttl=*/2048,
+                         /*num_non_empty_levels=*/100, /*level=*/1);
+  FileMetaData meta;
+  meta.oldest_ancester_time = kCurrentTime - 1023;
+  ASSERT_EQ(1, booster.GetBoostScore(&meta));
+}
+
 TEST_F(CompactionPickerTest, FileTtlBooster) {
   // Set TTL to 2048
   // TTL boosting for all levels starts at 1024,
@@ -2520,6 +2574,61 @@ TEST_F(CompactionPickerTest, L0TrivialMoveWholeL0) {
   ASSERT_TRUE(compaction->IsTrivialMove());
 }
 
+TEST_F(CompactionPickerTest, NonL0TrivialMoveExtendBothDirection) {
+  mutable_cf_options_.max_bytes_for_level_base = 5000;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 4;
+  mutable_cf_options_.max_compaction_bytes = 10000000u;
+  ioptions_.level_compaction_dynamic_level_bytes = false;
+  NewVersionStorage(6, kCompactionStyleLevel);
+
+  Add(1, 1U, "300", "350", 3000U, 0, 710, 800, 3000U);
+  Add(1, 2U, "600", "651", 3001U, 0, 610, 700, 3001U);
+  Add(1, 3U, "700", "750", 3000U, 0, 500, 550, 3000U);
+  Add(2, 4U, "800", "850", 4000U, 0, 150, 200, 4000U);
+
+  UpdateVersionStorageInfo();
+  // File #2 should be picked first, and expand both directions to include
+  // files #1 and #3.
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1, compaction->num_input_levels());
+  ASSERT_EQ(3, compaction->num_input_files(0));
+  ASSERT_EQ(1, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2, compaction->input(0, 1)->fd.GetNumber());
+  ASSERT_EQ(3, compaction->input(0, 2)->fd.GetNumber());
+  ASSERT_TRUE(compaction->IsTrivialMove());
+}
+
+TEST_F(CompactionPickerTest, L0TrivialMoveToEmptyLevel) {
+  mutable_cf_options_.max_bytes_for_level_base = 5000;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 4;
+  mutable_cf_options_.max_compaction_bytes = 10000000u;
+  ioptions_.level_compaction_dynamic_level_bytes = false;
+  NewVersionStorage(6, kCompactionStyleLevel);
+
+  // File 2 will be picked first, which by itself is trivial movable.
+  // There was a bug before where compaction also picks file 3 and 4,
+  // (and then file 1 since it overlaps with the key range),
+  // which makes the compaction not trivial movable.
+  Add(0, 1U, "450", "599", 3000U, 0, 710, 800, 3000U);
+  Add(0, 2U, "600", "651", 3001U, 0, 610, 700, 3001U);
+  Add(0, 3U, "300", "350", 3000U, 0, 500, 550, 3000U);
+  Add(0, 4U, "500", "550", 2999U, 0, 300, 350, 2999U);
+
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1, compaction->num_input_levels());
+  ASSERT_EQ(1, compaction->num_input_files(0));
+  ASSERT_EQ(2, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_TRUE(compaction->IsTrivialMove());
+}
+
 TEST_F(CompactionPickerTest, IsTrivialMoveOffSstPartitioned) {
   mutable_cf_options_.max_bytes_for_level_base = 10000u;
   mutable_cf_options_.max_compaction_bytes = 10001u;

db/compaction/compaction_picker_universal.cc

@@ -19,7 +19,7 @@
 #include "file/filename.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "test_util/sync_point.h"
 #include "util/random.h"
 #include "util/string_util.h"
@@ -133,8 +133,8 @@ class UniversalCompactionBuilder {
   UniversalCompactionPicker* picker_;
   LogBuffer* log_buffer_;
 
-  static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage);
+  static std::vector<UniversalCompactionBuilder::SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, int last_level);
 
   // Pick a path ID to place a newly generated file, with its estimated file
   // size.
@@ -339,13 +339,13 @@ void UniversalCompactionBuilder::SortedRun::DumpSizeInfo(
 
 std::vector<UniversalCompactionBuilder::SortedRun>
 UniversalCompactionBuilder::CalculateSortedRuns(
-    const VersionStorageInfo& vstorage) {
+    const VersionStorageInfo& vstorage, int last_level) {
   std::vector<UniversalCompactionBuilder::SortedRun> ret;
   for (FileMetaData* f : vstorage.LevelFiles(0)) {
     ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
                      f->being_compacted);
   }
-  for (int level = 1; level < vstorage.num_levels(); level++) {
+  for (int level = 1; level <= last_level; level++) {
     uint64_t total_compensated_size = 0U;
     uint64_t total_size = 0U;
     bool being_compacted = false;
@@ -374,7 +374,9 @@ UniversalCompactionBuilder::CalculateSortedRuns(
 Compaction* UniversalCompactionBuilder::PickCompaction() {
   const int kLevel0 = 0;
   score_ = vstorage_->CompactionScore(kLevel0);
-  sorted_runs_ = CalculateSortedRuns(*vstorage_);
+  int max_output_level =
+      vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
+  sorted_runs_ = CalculateSortedRuns(*vstorage_, max_output_level);
 
   if (sorted_runs_.size() == 0 ||
       (vstorage_->FilesMarkedForPeriodicCompaction().empty() &&
@@ -471,6 +473,8 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
         "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
     return nullptr;
   }
+  assert(c->output_level() <=
+         vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind));
 
   if (mutable_cf_options_.compaction_options_universal.allow_trivial_move ==
           true &&
@@ -698,22 +702,18 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
   int start_level = sorted_runs_[start_index].level;
   int output_level;
+  // last level is reserved for the files ingested behind
+  int max_output_level =
+      vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
   if (first_index_after == sorted_runs_.size()) {
-    output_level = vstorage_->num_levels() - 1;
+    output_level = max_output_level;
   } else if (sorted_runs_[first_index_after].level == 0) {
     output_level = 0;
   } else {
     output_level = sorted_runs_[first_index_after].level - 1;
   }
 
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind &&
-      (output_level == vstorage_->num_levels() - 1)) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  std::vector<CompactionInputFiles> inputs(max_output_level + 1);
   for (size_t i = 0; i < inputs.size(); ++i) {
     inputs[i].level = start_level + static_cast<int>(i);
   }
@@ -1192,8 +1192,10 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
       return nullptr;
     }
 
+    int max_output_level =
+        vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
     // Pick the first non-empty level after the start_level
-    for (output_level = start_level + 1; output_level < vstorage_->num_levels();
+    for (output_level = start_level + 1; output_level <= max_output_level;
          output_level++) {
       if (vstorage_->NumLevelFiles(output_level) != 0) {
         break;
@@ -1201,9 +1203,9 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
     }
 
     // If all higher levels are empty, pick the highest level as output level
-    if (output_level == vstorage_->num_levels()) {
+    if (output_level > max_output_level) {
       if (start_level == 0) {
-        output_level = vstorage_->num_levels() - 1;
+        output_level = max_output_level;
       } else {
         // If start level is non-zero and all higher levels are empty, this
         // compaction will translate into a trivial move. Since the idea is
@@ -1212,11 +1214,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
         return nullptr;
       }
     }
-    if (ioptions_.allow_ingest_behind &&
-        output_level == vstorage_->num_levels() - 1) {
-      assert(output_level > 1);
-      output_level--;
-    }
+    assert(output_level <= max_output_level);
 
     if (output_level != 0) {
       if (start_level == 0) {
@@ -1293,8 +1291,9 @@ Compaction* UniversalCompactionBuilder::PickCompactionWithSortedRunRange(
   uint32_t path_id =
       GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
   int start_level = sorted_runs_[start_index].level;
-
-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  int max_output_level =
+      vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
+  std::vector<CompactionInputFiles> inputs(max_output_level + 1);
   for (size_t i = 0; i < inputs.size(); ++i) {
     inputs[i].level = start_level + static_cast<int>(i);
   }
@@ -1331,13 +1330,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionWithSortedRunRange(
 
   int output_level;
   if (end_index == sorted_runs_.size() - 1) {
-    // output files at the last level, unless it's reserved
-    output_level = vstorage_->num_levels() - 1;
-    // last level is reserved for the files ingested behind
-    if (ioptions_.allow_ingest_behind) {
-      assert(output_level > 1);
-      output_level--;
-    }
+    output_level = max_output_level;
   } else {
     // if it's not including all sorted_runs, it can only output to the level
     // above the `end_index + 1` sorted_run.

db/compaction/compaction_service_test.cc

@@ -928,7 +928,7 @@ TEST_F(CompactionServiceTest, TablePropertiesCollector) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   ASSERT_OK(db_->GetPropertiesOfAllTables(&fname_to_props));
 
@@ -952,4 +952,3 @@ int main(int argc, char** argv) {
   RegisterCustomObjects(argc, argv);
   return RUN_ALL_TESTS();
 }
-

db/compaction/file_pri.h

@@ -53,8 +53,10 @@ class FileTtlBooster {
       enabled_ = true;
       uint64_t all_boost_start_age = ttl / 2;
       uint64_t all_boost_age_range = (ttl / 32) * 31 - all_boost_start_age;
+      // TODO(cbi): more reasonable algorithm that gives different values
+      //   when num_non_empty_levels - level - 1 > 63.
       uint64_t boost_age_range =
-          all_boost_age_range >> (num_non_empty_levels - level - 1);
+          all_boost_age_range >> std::min(63, num_non_empty_levels - level - 1);
       boost_age_start_ = all_boost_start_age + boost_age_range;
       const uint64_t kBoostRatio = 16;
       // prevent 0 value to avoid divide 0 error.

db/compaction/tiered_compaction_test.cc

@@ -209,7 +209,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageUniversal) {
     seq_history.emplace_back(dbfull()->GetLatestSequenceNumber());
     expect_stats[0].Add(kBasicFlushStats);
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // the penultimate level file temperature is not cold, all data are output to
   // the penultimate level.
@@ -374,7 +374,7 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageUniversal) {
     ASSERT_OK(Flush());
     expect_stats[0].Add(kBasicFlushStats);
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,1,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -445,8 +445,8 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageUniversal) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(
-      true));  // make sure the compaction is able to finish
+  // make sure the compaction is able to finish
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,1,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -911,7 +911,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     ASSERT_OK(Flush());
     expect_stats[0].Add(kBasicFlushStats);
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // non last level is hot
   ASSERT_EQ("0,1", FilesPerLevel());
@@ -954,7 +954,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     ASSERT_OK(Flush());
     seq_history.emplace_back(dbfull()->GetLatestSequenceNumber());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,1,0,0,0,0,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -1005,7 +1005,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     ASSERT_OK(Flush());
     seq_history.emplace_back(dbfull()->GetLatestSequenceNumber());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   latest_cold_seq = seq_history[0];
   ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
@@ -1111,6 +1111,7 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageLevel) {
   options.num_levels = kNumLevels;
   options.statistics = CreateDBStatistics();
   options.max_subcompactions = 10;
+  options.preclude_last_level_data_seconds = 10000;
   DestroyAndReopen(options);
   auto cmp = options.comparator;
 
@@ -1134,7 +1135,7 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageLevel) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,1,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -1264,7 +1265,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimeManualCompaction) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1326,7 +1327,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimeAutoCompaction) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1359,7 +1360,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimeAutoCompaction) {
       });
     }
     ASSERT_OK(Flush());
-    ASSERT_OK(dbfull()->WaitForCompact(true));
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
   }
 
   // all data is moved up to the penultimate level
@@ -1402,7 +1403,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimePartial) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1529,7 +1530,7 @@ TEST_F(PrecludeLastLevelTest, LastLevelOnlyCompactionPartial) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1608,7 +1609,7 @@ TEST_P(PrecludeLastLevelTestWithParms, LastLevelOnlyCompactionNoPreclude) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1704,7 +1705,7 @@ TEST_P(PrecludeLastLevelTestWithParms, LastLevelOnlyCompactionNoPreclude) {
 
   manual_compaction_thread.join();
 
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   if (enable_preclude_last_level) {
     ASSERT_NE("0,0,0,0,0,1,1", FilesPerLevel());
@@ -1840,7 +1841,7 @@ TEST_P(PrecludeLastLevelTestWithParms, PeriodicCompactionToPenultimateLevel) {
   }
   ASSERT_OK(Flush());
 
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   stop_token.reset();
 
@@ -1939,7 +1940,7 @@ TEST_F(PrecludeLastLevelTest, PartialPenultimateLevelCompaction) {
     ASSERT_OK(Flush());
   }
 
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // L5: [0,19] [20,39] [40,299]
   // L6: [0,                299]
@@ -2105,7 +2106,7 @@ TEST_F(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   Slice begin_key(begin_key_buf), end_key(end_key_buf);
   ASSERT_OK(db_->SuggestCompactRange(db_->DefaultColumnFamily(), &begin_key,
                                      &end_key));
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,3,3", FilesPerLevel());
   ASSERT_EQ(1, per_key_comp_num);
   verify_db();
@@ -2115,7 +2116,7 @@ TEST_F(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   db_->ReleaseSnapshot(snap2);
   ASSERT_OK(db_->SuggestCompactRange(db_->DefaultColumnFamily(), &begin_key,
                                      &end_key));
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,3,3", FilesPerLevel());
   ASSERT_EQ(2, per_key_comp_num);
   verify_db();
@@ -2125,7 +2126,7 @@ TEST_F(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   db_->ReleaseSnapshot(snap1);
   ASSERT_OK(db_->SuggestCompactRange(db_->DefaultColumnFamily(), &begin_key,
                                      &end_key));
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,2,3", FilesPerLevel());
   ASSERT_EQ(3, per_key_comp_num);
   verify_db();

db/convenience.cc

@@ -33,7 +33,9 @@ Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
 Status VerifySstFileChecksum(const Options& options,
                              const EnvOptions& env_options,
                              const std::string& file_path) {
-  return VerifySstFileChecksum(options, env_options, ReadOptions(), file_path);
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
+  return VerifySstFileChecksum(options, env_options, read_options, file_path);
 }
 Status VerifySstFileChecksum(const Options& options,
                              const EnvOptions& env_options,
@@ -56,13 +58,14 @@ Status VerifySstFileChecksum(const Options& options,
   std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(
           std::move(file), file_path, ioptions.clock, nullptr /* io_tracer */,
-          nullptr /* stats */, 0 /* hist_type */, nullptr /* file_read_hist */,
-          ioptions.rate_limiter.get()));
+          ioptions.stats /* stats */,
+          Histograms::SST_READ_MICROS /* hist_type */,
+          nullptr /* file_read_hist */, ioptions.rate_limiter.get()));
   const bool kImmortal = true;
   auto reader_options = TableReaderOptions(
       ioptions, options.prefix_extractor, env_options, internal_comparator,
-      false /* skip_filters */, !kImmortal, false /* force_direct_prefetch */,
-      -1 /* level */);
+      options.block_protection_bytes_per_key, false /* skip_filters */,
+      !kImmortal, false /* force_direct_prefetch */, -1 /* level */);
   reader_options.largest_seqno = largest_seqno;
   s = ioptions.table_factory->NewTableReader(
       reader_options, std::move(file_reader), file_size, &table_reader,
@@ -76,4 +79,3 @@ Status VerifySstFileChecksum(const Options& options,
 }
 
 }  // namespace ROCKSDB_NAMESPACE
-

db/corruption_test.cc

@@ -450,6 +450,7 @@ TEST_F(CorruptionTest, TableFile) {
 
 TEST_F(CorruptionTest, VerifyChecksumReadahead) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   SpecialEnv senv(base_env_);
   options.env = &senv;
   // Disable block cache as we are going to check checksum for
@@ -503,6 +504,7 @@ TEST_F(CorruptionTest, VerifyChecksumReadahead) {
 
 TEST_F(CorruptionTest, TableFileIndexData) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   // very big, we'll trigger flushes manually
   options.write_buffer_size = 100 * 1024 * 1024;
   Reopen(&options);
@@ -659,6 +661,7 @@ TEST_F(CorruptionTest, CorruptedDescriptor) {
 
 TEST_F(CorruptionTest, CompactionInputError) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   Reopen(&options);
   Build(10);
@@ -680,6 +683,7 @@ TEST_F(CorruptionTest, CompactionInputError) {
 
 TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_checks = true;
   options.write_buffer_size = 131072;
@@ -762,9 +766,11 @@ TEST_F(CorruptionTest, RangeDeletionCorrupted) {
       fs->GetFileSize(filename, file_opts.io_options, &file_size, nullptr));
 
   BlockHandle range_del_handle;
-  ASSERT_OK(FindMetaBlockInFile(
-      file_reader.get(), file_size, kBlockBasedTableMagicNumber,
-      ImmutableOptions(options_), kRangeDelBlockName, &range_del_handle));
+  const ReadOptions read_options;
+  ASSERT_OK(FindMetaBlockInFile(file_reader.get(), file_size,
+                                kBlockBasedTableMagicNumber,
+                                ImmutableOptions(options_), read_options,
+                                kRangeDelBlockName, &range_del_handle));
 
   ASSERT_OK(TryReopen());
   ASSERT_OK(test::CorruptFile(env_.get(), filename,
@@ -775,6 +781,7 @@ TEST_F(CorruptionTest, RangeDeletionCorrupted) {
 TEST_F(CorruptionTest, FileSystemStateCorrupted) {
   for (int iter = 0; iter < 2; ++iter) {
     Options options;
+    options.level_compaction_dynamic_level_bytes = false;
     options.env = env_.get();
     options.paranoid_checks = true;
     options.create_if_missing = true;
@@ -814,6 +821,7 @@ static const auto& corruption_modes = {
 
 TEST_F(CorruptionTest, ParanoidFileChecksOnFlush) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -842,6 +850,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksOnFlush) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksOnCompact) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_file_checks = true;
   options.create_if_missing = true;
@@ -875,6 +884,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksOnCompact) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeFirst) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -911,6 +921,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeFirst) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRange) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -950,6 +961,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRange) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeLast) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -986,6 +998,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeLast) {
 
 TEST_F(CorruptionTest, LogCorruptionErrorsInCompactionIterator) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.create_if_missing = true;
   options.allow_data_in_errors = true;
@@ -1015,6 +1028,7 @@ TEST_F(CorruptionTest, LogCorruptionErrorsInCompactionIterator) {
 
 TEST_F(CorruptionTest, CompactionKeyOrderCheck) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_file_checks = false;
   options.create_if_missing = true;
@@ -1042,6 +1056,7 @@ TEST_F(CorruptionTest, CompactionKeyOrderCheck) {
 
 TEST_F(CorruptionTest, FlushKeyOrderCheck) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_file_checks = false;
   options.create_if_missing = true;
@@ -1095,6 +1110,7 @@ TEST_F(CorruptionTest, DisableKeyOrderCheck) {
 TEST_F(CorruptionTest, VerifyWholeTableChecksum) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   ASSERT_OK(DestroyDB(dbname_, options));
   options.create_if_missing = true;
@@ -1180,6 +1196,7 @@ INSTANTIATE_TEST_CASE_P(CorruptionTest, CrashDuringRecoveryWithCorruptionTest,
 TEST_P(CrashDuringRecoveryWithCorruptionTest, CrashDuringRecovery) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.track_and_verify_wals_in_manifest =
       track_and_verify_wals_in_manifest_;
   options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
@@ -1352,6 +1369,7 @@ TEST_P(CrashDuringRecoveryWithCorruptionTest, CrashDuringRecovery) {
 TEST_P(CrashDuringRecoveryWithCorruptionTest, TxnDbCrashDuringRecovery) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
   options.track_and_verify_wals_in_manifest =
       track_and_verify_wals_in_manifest_;
@@ -1549,6 +1567,7 @@ TEST_P(CrashDuringRecoveryWithCorruptionTest, TxnDbCrashDuringRecovery) {
 TEST_P(CrashDuringRecoveryWithCorruptionTest, CrashDuringRecoveryWithFlush) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
   options.avoid_flush_during_recovery = false;
   options.env = env_.get();
@@ -1666,4 +1685,3 @@ int main(int argc, char** argv) {
   RegisterCustomObjects(argc, argv);
   return RUN_ALL_TESTS();
 }
-

db/cuckoo_table_db_test.cc

@@ -39,6 +39,7 @@ class CuckooTableDBTest : public testing::Test {
 
   Options CurrentOptions() {
     Options options;
+    options.level_compaction_dynamic_level_bytes = false;
     options.table_factory.reset(NewCuckooTableFactory());
     options.memtable_factory.reset(NewHashLinkListRepFactory(4, 0, 3, true));
     options.allow_mmap_reads = true;

db/db_basic_test.cc

@@ -4494,6 +4494,63 @@ TEST_F(DBBasicTest, VerifyFileChecksums) {
   ASSERT_TRUE(db_->VerifyFileChecksums(ReadOptions()).IsInvalidArgument());
 }
 
+TEST_F(DBBasicTest, VerifyFileChecksumsReadahead) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.env = env_;
+  options.file_checksum_gen_factory = GetFileChecksumGenCrc32cFactory();
+  DestroyAndReopen(options);
+
+  Random rnd(301);
+  int alignment = 256 * 1024;
+  for (int i = 0; i < 16; ++i) {
+    ASSERT_OK(Put("key" + std::to_string(i), rnd.RandomString(alignment)));
+  }
+  ASSERT_OK(Flush());
+
+  std::vector<std::string> filenames;
+  int sst_cnt = 0;
+  std::string sst_name;
+  uint64_t sst_size;
+  uint64_t number;
+  FileType type;
+  ASSERT_OK(env_->GetChildren(dbname_, &filenames));
+  for (auto name : filenames) {
+    if (ParseFileName(name, &number, &type)) {
+      if (type == kTableFile) {
+        sst_cnt++;
+        sst_name = name;
+      }
+    }
+  }
+  ASSERT_EQ(sst_cnt, 1);
+  ASSERT_OK(env_->GetFileSize(dbname_ + '/' + sst_name, &sst_size));
+
+  bool last_read = false;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "GenerateOneFileChecksum::Chunk:0", [&](void* /*arg*/) {
+        if (env_->random_read_bytes_counter_.load() == sst_size) {
+          EXPECT_FALSE(last_read);
+          last_read = true;
+        } else {
+          ASSERT_EQ(env_->random_read_bytes_counter_.load() & (alignment - 1),
+                    0);
+        }
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  env_->count_random_reads_ = true;
+  env_->random_read_bytes_counter_ = 0;
+  env_->random_read_counter_.Reset();
+
+  ReadOptions ro;
+  ro.readahead_size = alignment;
+  ASSERT_OK(db_->VerifyFileChecksums(ro));
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ASSERT_TRUE(last_read);
+  ASSERT_EQ(env_->random_read_counter_.Read(),
+            (sst_size + alignment - 1) / (alignment));
+}
+
 // TODO: re-enable after we provide finer-grained control for WAL tracking to
 // meet the needs of different use cases, durability levels and recovery modes.
 TEST_F(DBBasicTest, DISABLED_ManualWalSync) {

db/db_block_cache_test.cc

@@ -620,9 +620,9 @@ class MockCache : public LRUCache {
   static uint32_t low_pri_insert_count;
 
   MockCache()
-      : LRUCache((size_t)1 << 25 /*capacity*/, 0 /*num_shard_bits*/,
-                 false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/,
-                 0.0 /*low_pri_pool_ratio*/) {}
+      : LRUCache(LRUCacheOptions(
+            size_t{1} << 25 /*capacity*/, 0 /*num_shard_bits*/,
+            false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/)) {}
 
   using ShardedCache::Insert;
 
@@ -979,12 +979,14 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
   const size_t capacity = size_t{1} << 25;
   int iterations_tested = 0;
   for (bool partition : {false, true}) {
+    SCOPED_TRACE("Partition? " + std::to_string(partition));
     for (std::shared_ptr<Cache> cache :
          {NewLRUCache(capacity),
           HyperClockCacheOptions(
               capacity,
               BlockBasedTableOptions().block_size /*estimated_value_size*/)
               .MakeSharedCache()}) {
+      SCOPED_TRACE(std::string("Cache: ") + cache->Name());
       ++iterations_tested;
 
       Options options = CurrentOptions();
@@ -1278,6 +1280,7 @@ TEST_F(DBBlockCacheTest, HyperClockCacheReportProblems) {
   HyperClockCacheOptions hcc_opts{capacity, value_size_est};
   hcc_opts.num_shard_bits = 2;  // 4 shards
   hcc_opts.metadata_charge_policy = kDontChargeCacheMetadata;
+  hcc_opts.hash_seed = 0;  // deterministic hashing
   std::shared_ptr<Cache> cache = hcc_opts.MakeSharedCache();
   std::shared_ptr<CountingLogger> logger = std::make_shared<CountingLogger>();
 

db/db_bloom_filter_test.cc

@@ -43,6 +43,16 @@ const std::string kStandard128Ribbon =
     test::Standard128RibbonFilterPolicy::kClassName();
 const std::string kAutoBloom = BloomFilterPolicy::kClassName();
 const std::string kAutoRibbon = RibbonFilterPolicy::kClassName();
+
+template <typename T>
+T Pop(T& var) {
+  auto rv = var;
+  var = 0;
+  return rv;
+}
+PerfContextByLevel& GetLevelPerfContext(uint32_t level) {
+  return (*(get_perf_context()->level_to_perf_context))[level];
+}
 }  // anonymous namespace
 
 // DB tests related to bloom filter.
@@ -209,57 +219,43 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloomCustomPrefixExtractor) {
     ASSERT_OK(dbfull()->Flush(fo));
 
     ASSERT_EQ("foo", Get("barbarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ(
-        0,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
+
     ASSERT_EQ("foo2", Get("barbarbar2"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ(
-        0,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
+
     ASSERT_EQ("NOT_FOUND", Get("barbarbar3"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ(
-        0,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
 
     ASSERT_EQ("NOT_FOUND", Get("barfoofoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ(
-        1,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 1);
 
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
-    ASSERT_EQ(
-        2,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 1);
 
     ro.total_order_seek = true;
     // NOTE: total_order_seek no longer affects Get()
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
-    ASSERT_EQ(
-        3,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 1);
 
     // No bloom on extractor changed
     ASSERT_OK(db_->SetOptions({{"prefix_extractor", "capped:10"}}));
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
-    ASSERT_EQ(
-        3,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
 
     // No bloom on extractor changed, after re-open
     options.prefix_extractor.reset(NewCappedPrefixTransform(10));
     Reopen(options);
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
-    ASSERT_EQ(
-        3,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
 
     get_perf_context()->Reset();
   }
@@ -294,33 +290,32 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
     ASSERT_OK(dbfull()->Flush(fo));
 
     ASSERT_EQ("foo", Get("barbarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     ASSERT_EQ("foo2", Get("barbarbar2"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("barbarbar3"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
 
     ASSERT_EQ("NOT_FOUND", Get("barfoofoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 1);
 
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 1);
 
     ro.total_order_seek = true;
     // NOTE: total_order_seek no longer affects Get()
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
-    ASSERT_EQ(
-        3,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 1);
 
     // No bloom on extractor changed
     ASSERT_OK(db_->SetOptions({{"prefix_extractor", "capped:10"}}));
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
-    ASSERT_EQ(
-        3,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(Pop(GetLevelPerfContext(0).bloom_filter_useful), 0);
 
     get_perf_context()->Reset();
   }
@@ -357,12 +352,17 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
     ASSERT_OK(dbfull()->Flush(fo));
 
     Reopen(options);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
 
     // Reopen with whole key filtering enabled and prefix extractor
     // NULL. Bloom filter should be off for both of whole key and
@@ -372,13 +372,17 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
     options.prefix_extractor.reset();
     Reopen(options);
 
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     // Write DB with only full key filtering.
     ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
     // Needs insert some keys to make sure files are not filtered out by key
@@ -394,13 +398,17 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
     options.table_factory.reset(NewBlockBasedTableFactory(bbto));
     Reopen(options);
 
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
 
     // Try to create a DB with mixed files:
     ASSERT_OK(dbfull()->Put(wo, "foobar", "foo"));
@@ -424,61 +432,81 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
     ASSERT_OK(Flush());
 
     // Now we have two files:
-    // File 1: An older file with prefix bloom.
+    // File 1: An older file with prefix bloom (disabled)
     // File 2: A newer file with whole bloom filter.
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 3);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
 
     // Reopen with the same setting: only whole key is used
     Reopen(options);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 4);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 5);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 6);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
 
     // Restart with both filters are allowed
     options.prefix_extractor.reset(NewFixedPrefixTransform(3));
     bbto.whole_key_filtering = true;
     options.table_factory.reset(NewBlockBasedTableFactory(bbto));
     Reopen(options);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 7);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     // File 1 will has it filtered out.
     // File 2 will not, as prefix `foo` exists in the file.
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 8);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 10);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
 
     // Restart with only prefix bloom is allowed.
     options.prefix_extractor.reset(NewFixedPrefixTransform(3));
     bbto.whole_key_filtering = false;
     options.table_factory.reset(NewBlockBasedTableFactory(bbto));
     Reopen(options);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("foo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 11);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("NOT_FOUND", Get("bar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("foo", Get("foobar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     ASSERT_EQ("bar", Get("barfoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 0);
     uint64_t bloom_filter_useful_all_levels = 0;
     for (auto& kv : (*(get_perf_context()->level_to_perf_context))) {
       if (kv.second.bloom_filter_useful > 0) {
@@ -696,11 +724,8 @@ TEST_P(DBBloomFilterTestWithParam, SkipFilterOnEssentiallyZeroBpk) {
   PutAndGetFn();
 
   // Verify filter is accessed (and constructed)
-  EXPECT_EQ(TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_POSITIVE),
-            maxKey * 2);
-  EXPECT_EQ(
-      TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE),
-      maxKey);
+  EXPECT_EQ(PopTicker(options, BLOOM_FILTER_FULL_POSITIVE), maxKey * 2);
+  EXPECT_EQ(PopTicker(options, BLOOM_FILTER_FULL_TRUE_POSITIVE), maxKey);
   props.clear();
   ASSERT_TRUE(db_->GetMapProperty(kAggTableProps, &props));
   EXPECT_NE(props["filter_size"], "0");
@@ -715,11 +740,8 @@ TEST_P(DBBloomFilterTestWithParam, SkipFilterOnEssentiallyZeroBpk) {
   GetFn();
 
   // Verify filter is accessed
-  EXPECT_EQ(TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_POSITIVE),
-            maxKey * 2);
-  EXPECT_EQ(
-      TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE),
-      maxKey);
+  EXPECT_EQ(PopTicker(options, BLOOM_FILTER_FULL_POSITIVE), maxKey * 2);
+  EXPECT_EQ(PopTicker(options, BLOOM_FILTER_FULL_TRUE_POSITIVE), maxKey);
 
   // But new filters are not generated (configuration details unknown)
   DestroyAndReopen(options);
@@ -783,9 +805,7 @@ TEST_F(DBBloomFilterTest, BloomFilterRate) {
       ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
     }
     ASSERT_GE(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), maxKey * 0.98);
-    ASSERT_GE(
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful,
-        maxKey * 0.98);
+    ASSERT_GE(GetLevelPerfContext(0).bloom_filter_useful, maxKey * 0.98);
     get_perf_context()->Reset();
   }
 }
@@ -864,9 +884,8 @@ TEST_F(DBBloomFilterTest, BloomFilterCompatibility) {
       ASSERT_EQ("val", Get(prefix + "Z"));  // Filter positive
       // Filter negative, with high probability
       ASSERT_EQ("NOT_FOUND", Get(prefix + "Q"));
-      EXPECT_EQ(TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_POSITIVE),
-                2);
-      EXPECT_EQ(TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+      EXPECT_EQ(PopTicker(options, BLOOM_FILTER_FULL_POSITIVE), 2);
+      EXPECT_EQ(PopTicker(options, BLOOM_FILTER_USEFUL), 1);
     }
   }
 }
@@ -1705,7 +1724,7 @@ TEST_F(DBBloomFilterTest, ContextCustomFilterPolicy) {
     }
     // Since we have two tables / two filters, we might have Bloom checks on
     // our queries, but no more than one "useful" per query on a found key.
-    EXPECT_LE(TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL), maxKey);
+    EXPECT_LE(PopTicker(options, BLOOM_FILTER_USEFUL), maxKey);
 
     // Check that we have two filters, each about
     // fifo: 0.12% FP rate (15 bits per key)
@@ -1714,8 +1733,7 @@ TEST_F(DBBloomFilterTest, ContextCustomFilterPolicy) {
       ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
     }
     {
-      auto useful_count =
-          TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL);
+      auto useful_count = PopTicker(options, BLOOM_FILTER_USEFUL);
       EXPECT_GE(useful_count, maxKey * 2 * (fifo ? 0.9980 : 0.975));
       EXPECT_LE(useful_count, maxKey * 2 * (fifo ? 0.9995 : 0.98));
     }
@@ -1732,8 +1750,7 @@ TEST_F(DBBloomFilterTest, ContextCustomFilterPolicy) {
         ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
       }
       {
-        auto useful_count =
-            TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL);
+        auto useful_count = PopTicker(options, BLOOM_FILTER_USEFUL);
         EXPECT_GE(useful_count, maxKey * 0.90);
         EXPECT_LE(useful_count, maxKey * 0.91);
       }
@@ -2027,13 +2044,14 @@ TEST_P(DBBloomFilterTestVaryPrefixAndFormatVer, PartitionedMultiGet) {
   std::array<Status, Q> statuses;
   std::array<PinnableSlice, Q> values;
 
-  TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_HIT);
-  TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_MISS);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_POSITIVE);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE);
+  PopTicker(options, BLOCK_CACHE_FILTER_HIT);
+  PopTicker(options, BLOCK_CACHE_FILTER_MISS);
+  PopTicker(options, BLOOM_FILTER_PREFIX_USEFUL);
+  PopTicker(options, BLOOM_FILTER_USEFUL);
+  PopTicker(options, BLOOM_FILTER_PREFIX_CHECKED);
+  PopTicker(options, BLOOM_FILTER_FULL_POSITIVE);
+  PopTicker(options, BLOOM_FILTER_FULL_TRUE_POSITIVE);
+  PopTicker(options, BLOOM_FILTER_PREFIX_TRUE_POSITIVE);
 
   // Check that initial clump of keys only loads one partition filter from
   // block cache.
@@ -2063,26 +2081,22 @@ TEST_P(DBBloomFilterTestVaryPrefixAndFormatVer, PartitionedMultiGet) {
     }
 
     // Confirm correct Bloom stats (no FPs)
-    uint64_t filter_useful = TestGetAndResetTickerCount(
-        options,
-        use_prefix_ ? BLOOM_FILTER_PREFIX_USEFUL : BLOOM_FILTER_USEFUL);
+    uint64_t filter_useful =
+        PopTicker(options, use_prefix_ ? BLOOM_FILTER_PREFIX_USEFUL
+                                       : BLOOM_FILTER_USEFUL);
     uint64_t filter_checked =
-        TestGetAndResetTickerCount(options, use_prefix_
-                                                ? BLOOM_FILTER_PREFIX_CHECKED
-                                                : BLOOM_FILTER_FULL_POSITIVE) +
+        PopTicker(options, use_prefix_ ? BLOOM_FILTER_PREFIX_CHECKED
+                                       : BLOOM_FILTER_FULL_POSITIVE) +
         (use_prefix_ ? 0 : filter_useful);
     EXPECT_EQ(filter_useful, number_not_found);
     EXPECT_EQ(filter_checked, Q);
-    if (!use_prefix_) {
-      EXPECT_EQ(
-          TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE),
-          Q - number_not_found);
-    }
+    EXPECT_EQ(PopTicker(options, use_prefix_ ? BLOOM_FILTER_PREFIX_TRUE_POSITIVE
+                                             : BLOOM_FILTER_FULL_TRUE_POSITIVE),
+              Q - number_not_found);
 
     // Confirm no duplicate loading same filter partition
-    uint64_t filter_accesses =
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_HIT) +
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_MISS);
+    uint64_t filter_accesses = PopTicker(options, BLOCK_CACHE_FILTER_HIT) +
+                               PopTicker(options, BLOCK_CACHE_FILTER_MISS);
     if (stride == 1) {
       EXPECT_EQ(filter_accesses, 1);
     } else {
@@ -2118,26 +2132,22 @@ TEST_P(DBBloomFilterTestVaryPrefixAndFormatVer, PartitionedMultiGet) {
     }
 
     // Confirm correct Bloom stats (might see some FPs)
-    uint64_t filter_useful = TestGetAndResetTickerCount(
-        options,
-        use_prefix_ ? BLOOM_FILTER_PREFIX_USEFUL : BLOOM_FILTER_USEFUL);
+    uint64_t filter_useful =
+        PopTicker(options, use_prefix_ ? BLOOM_FILTER_PREFIX_USEFUL
+                                       : BLOOM_FILTER_USEFUL);
     uint64_t filter_checked =
-        TestGetAndResetTickerCount(options, use_prefix_
-                                                ? BLOOM_FILTER_PREFIX_CHECKED
-                                                : BLOOM_FILTER_FULL_POSITIVE) +
+        PopTicker(options, use_prefix_ ? BLOOM_FILTER_PREFIX_CHECKED
+                                       : BLOOM_FILTER_FULL_POSITIVE) +
         (use_prefix_ ? 0 : filter_useful);
     EXPECT_GE(filter_useful, number_not_found - 2);  // possible FP
     EXPECT_EQ(filter_checked, Q);
-    if (!use_prefix_) {
-      EXPECT_EQ(
-          TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE),
-          Q - number_not_found);
-    }
+    EXPECT_EQ(PopTicker(options, use_prefix_ ? BLOOM_FILTER_PREFIX_TRUE_POSITIVE
+                                             : BLOOM_FILTER_FULL_TRUE_POSITIVE),
+              Q - number_not_found);
 
     // Confirm no duplicate loading of same filter partition
-    uint64_t filter_accesses =
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_HIT) +
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_MISS);
+    uint64_t filter_accesses = PopTicker(options, BLOCK_CACHE_FILTER_HIT) +
+                               PopTicker(options, BLOCK_CACHE_FILTER_MISS);
     if (filter_accesses == 2) {
       // Spanned across partitions.
       ++found_spanning;
@@ -2437,9 +2447,11 @@ TEST_F(DBBloomFilterTest, PrefixScan) {
 }
 
 TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
+  const int kNumKeysPerFlush = 1000;
+
   Options options = CurrentOptions();
-  options.write_buffer_size = 64 * 1024;
-  options.arena_block_size = 4 * 1024;
+  options.memtable_factory.reset(
+      test::NewSpecialSkipListFactory(kNumKeysPerFlush));
   options.target_file_size_base = 64 * 1024;
   options.level0_file_num_compaction_trigger = 2;
   options.level0_slowdown_writes_trigger = 2;
@@ -2475,8 +2487,13 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
   int num_inserted = 0;
   for (int key : keys) {
     ASSERT_OK(Put(1, Key(key), "val"));
-    if (++num_inserted % 1000 == 0) {
-      ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+    num_inserted++;
+    // The write after each `kNumKeysPerFlush` keys triggers a flush. Always
+    // wait for that flush and any follow-on compactions for deterministic LSM
+    // shape.
+    if (num_inserted > kNumKeysPerFlush &&
+        num_inserted % kNumKeysPerFlush == 1) {
+      ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable(handles_[1]));
       ASSERT_OK(dbfull()->TEST_WaitForCompact());
     }
   }
@@ -2597,7 +2614,7 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
   compact_options.target_level = 7;
   ASSERT_OK(db_->CompactRange(compact_options, handles_[1], nullptr, nullptr));
 
-  ASSERT_EQ(trivial_move, 1);
+  ASSERT_GE(trivial_move, 1);
   ASSERT_EQ(non_trivial_move, 0);
 
   prev_cache_filter_hits = TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT);
@@ -2629,6 +2646,9 @@ int CountIter(std::unique_ptr<Iterator>& iter, const Slice& key) {
   int count = 0;
   for (iter->Seek(key); iter->Valid(); iter->Next()) {
     count++;
+    // Access key & value as if we were using them
+    (void)iter->key();
+    (void)iter->value();
   }
   EXPECT_OK(iter->status());
   return count;
@@ -2668,6 +2688,12 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       read_options.iterate_upper_bound = &upper_bound;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abcd0000"), 4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                1);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      ASSERT_EQ(TestGetTickerCount(
+                    options, NON_LAST_LEVEL_SEEK_DATA_USEFUL_FILTER_MATCH),
+                1);
     }
     {
       Slice upper_bound("abcdzzzz");
@@ -2676,8 +2702,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       read_options.iterate_upper_bound = &upper_bound;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abcd0000"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                2);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:5"}}));
     ASSERT_EQ(dbfull()->GetOptions().prefix_extractor->AsString(),
@@ -2691,8 +2718,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abcdxx00"), 4);
       // should check bloom filter since upper bound meets requirement
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                3);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     {
       // [abcdxx01, abcey) is not valid bound since upper bound is too long for
@@ -2704,8 +2732,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abcdxx01"), 4);
       // should skip bloom filter since upper bound is too long
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                3);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     {
       // [abcdxx02, abcdy) is a valid bound since the prefix is the same
@@ -2717,8 +2746,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       ASSERT_EQ(CountIter(iter, "abcdxx02"), 4);
       // should check bloom filter since upper bound matches transformed seek
       // key
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     {
       // [aaaaaaaa, abce) is not a valid bound since 1) they don't share the
@@ -2730,8 +2760,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "aaaaaaaa"), 0);
       // should skip bloom filter since mismatch is found
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:3"}}));
     {
@@ -2743,8 +2774,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       read_options.iterate_upper_bound = &upper_bound;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abc"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     // Same with re-open
     options.prefix_extractor.reset(NewFixedPrefixTransform(3));
@@ -2756,8 +2788,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       read_options.iterate_upper_bound = &upper_bound;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abc"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
     }
     // Set back to capped:4 and verify BF is always read
     options.prefix_extractor.reset(NewCappedPrefixTransform(4));
@@ -2769,8 +2802,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       read_options.iterate_upper_bound = &upper_bound;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abc"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 5);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 1);
     }
     // Same if there's a problem initally loading prefix transform
     SyncPoint::GetInstance()->SetCallBack(
@@ -2785,8 +2819,9 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       read_options.iterate_upper_bound = &upper_bound;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abc"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 6);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+                4);
+      ASSERT_EQ(TestGetTickerCount(options, NON_LAST_LEVEL_SEEK_FILTERED), 2);
     }
     SyncPoint::GetInstance()->DisableProcessing();
   }
@@ -2821,7 +2856,8 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
     dbfull()->Flush(FlushOptions());
     std::unique_ptr<Iterator> iter_old(db_->NewIterator(read_options));
     ASSERT_EQ(CountIter(iter_old, "foo"), 4);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 1);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 1);
 
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
     ASSERT_EQ(dbfull()->GetOptions().prefix_extractor->AsString(),
@@ -2829,10 +2865,11 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
     read_options.iterate_upper_bound = &upper_bound;
     std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
     ASSERT_EQ(CountIter(iter, "foo"), 2);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 2);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 1);
     ASSERT_EQ(CountIter(iter, "gpk"), 0);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 2);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
 
     // second SST with capped:3 BF
     ASSERT_OK(Put("foo3", "bar3"));
@@ -2844,13 +2881,13 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       // BF is cappped:3 now
       std::unique_ptr<Iterator> iter_tmp(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter_tmp, "foo"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 2);
       ASSERT_EQ(CountIter(iter_tmp, "gpk"), 0);
       // both counters are incremented because BF is "not changed" for 1 of the
       // 2 SST files, so filter is checked once and found no match.
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 5);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 1);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
     }
 
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:2"}}));
@@ -2867,33 +2904,34 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       std::unique_ptr<Iterator> iter_tmp(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter_tmp, "foo"), 9);
       // the first and last BF are checked
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 7);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 2);
       ASSERT_EQ(CountIter(iter_tmp, "gpk"), 0);
       // only last BF is checked and not found
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 8);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 1);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
     }
 
-    // iter_old can only see the first SST, so checked plus 1
+    // iter_old can only see the first SST
     ASSERT_EQ(CountIter(iter_old, "foo"), 4);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 9);
-    // iter was created after the first setoptions call so only full filter
-    // will check the filter
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 1);
+    // same with iter, but different prefix extractor
     ASSERT_EQ(CountIter(iter, "foo"), 2);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 10);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 1);
 
     {
       // keys in all three SSTs are visible to iterator
       // The range of [foo, foz90000] is compatible with (fixed:1) and (fixed:2)
-      // so +2 for checked counter
       std::unique_ptr<Iterator> iter_all(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter_all, "foo"), 9);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 12);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 2);
       ASSERT_EQ(CountIter(iter_all, "gpk"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 13);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
+      // FIXME? isn't seek key out of SST range?
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 1);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
     }
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
     ASSERT_EQ(dbfull()->GetOptions().prefix_extractor->AsString(),
@@ -2903,11 +2941,12 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       ASSERT_EQ(CountIter(iter_all, "foo"), 6);
       // all three SST are checked because the current options has the same as
       // the remaining SST (capped:3)
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 16);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 3);
       ASSERT_EQ(CountIter(iter_all, "gpk"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 17);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 4);
+      // FIXME? isn't seek key out of SST range?
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 1);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
     }
     // TODO(Zhongyi): Maybe also need to add Get calls to test point look up?
   }
@@ -3009,13 +3048,13 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
     {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "foo"), 12);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 3);
     }
     std::unique_ptr<Iterator> iter_old(db_->NewIterator(read_options));
     ASSERT_EQ(CountIter(iter_old, "foo"), 12);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 6);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 3);
 
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
     ASSERT_EQ(dbfull()->GetOptions().prefix_extractor->AsString(),
@@ -3024,17 +3063,18 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       // "fp*" should be skipped
       ASSERT_EQ(CountIter(iter, "foo"), 9);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 6);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+      EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
     }
 
     // iterator created before should not be affected and see all keys
     ASSERT_EQ(CountIter(iter_old, "foo"), 12);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 9);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 0);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 3);
     ASSERT_EQ(CountIter(iter_old, "abc"), 0);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 12);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
+    // FIXME? isn't seek key out of SST range?
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTERED), 3);
+    EXPECT_EQ(PopTicker(options, NON_LAST_LEVEL_SEEK_FILTER_MATCH), 0);
   }
 }
 
@@ -3129,19 +3169,19 @@ class FixedSuffix4Transform : public SliceTransform {
 
 std::pair<uint64_t, uint64_t> GetBloomStat(const Options& options, bool sst) {
   if (sst) {
-    return {
-        options.statistics->getAndResetTickerCount(BLOOM_FILTER_PREFIX_CHECKED),
-        options.statistics->getAndResetTickerCount(BLOOM_FILTER_PREFIX_USEFUL)};
+    return {options.statistics->getAndResetTickerCount(
+                NON_LAST_LEVEL_SEEK_FILTER_MATCH),
+            options.statistics->getAndResetTickerCount(
+                NON_LAST_LEVEL_SEEK_FILTERED)};
   } else {
     auto hit = std::exchange(get_perf_context()->bloom_memtable_hit_count, 0);
     auto miss = std::exchange(get_perf_context()->bloom_memtable_miss_count, 0);
-    return {hit + miss, miss};
+    return {hit, miss};
   }
 }
 
-std::pair<uint64_t, uint64_t> CheckedAndUseful(uint64_t checked,
-                                               uint64_t useful) {
-  return {checked, useful};
+std::pair<uint64_t, uint64_t> HitAndMiss(uint64_t hits, uint64_t misses) {
+  return {hits, misses};
 }
 }  // anonymous namespace
 
@@ -3179,27 +3219,27 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter1) {
     if (flushed) {  // TODO: support auto_prefix_mode in memtable?
       read_options.auto_prefix_mode = true;
     }
-    EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+    EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
     {
       Slice ub("999aaaa");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "aaaa"), 3);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
     {
       Slice ub("999abaa");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "abaa"), 1);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
     {
       Slice ub("999acaa");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "acaa"), 0);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 1));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 1));
     }
     {
       Slice ub("zzzz");
@@ -3207,7 +3247,7 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter1) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "baa"), 3);
       if (flushed) {  // TODO: fix memtable case
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
       }
     }
   }
@@ -3253,13 +3293,13 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter2) {
       get_perf_context()->bloom_memtable_hit_count = 0;
       get_perf_context()->bloom_memtable_miss_count = 0;
     }
-    EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+    EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
     {
       Slice ub("aaaa000");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "aaaa999"), 3);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
     {
       // Note: prefix does work as upper bound
@@ -3267,7 +3307,7 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter2) {
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "aaaa999"), 3);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
     {
       // Note: prefix does not work here as seek key
@@ -3275,28 +3315,28 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter2) {
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "aaaa"), 0);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
     {
       Slice ub("aaba000");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "aaba999"), 1);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
     {
       Slice ub("aaca000");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "aaca999"), 0);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 1));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 1));
     }
     {
       Slice ub("aaaz");
       read_options.iterate_upper_bound = &ub;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "zzz"), 5);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
     }
     {
       // Note: prefix does work here as seek key, but only finds key equal
@@ -3306,7 +3346,7 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter2) {
       read_options.prefix_same_as_start = true;
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       EXPECT_EQ(CountIter(iter, "qqqq"), 1);
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
     }
   }
 }
@@ -3397,13 +3437,13 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter3) {
         get_perf_context()->bloom_memtable_hit_count = 0;
         get_perf_context()->bloom_memtable_miss_count = 0;
       }
-      EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+      EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
       {
         Slice ub("aaaa999");
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "aaaa000"), 3);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
       }
       {
         // Note: prefix as seek key is not bloom-optimized
@@ -3413,28 +3453,28 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter3) {
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "aaaa"), 3);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
       }
       {
         Slice ub("aaba9");
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "aaba0"), 1);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
       }
       {
         Slice ub("aaca9");
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "aaca0"), 0);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 1));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 1));
       }
       {
         Slice ub("qqqq9");
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "qqqq0"), 1);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(1, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(1, 0));
       }
       {
         // Note: prefix as seek key is not bloom-optimized
@@ -3442,7 +3482,7 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter3) {
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "qqqq"), weird_comparator ? 7 : 2);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
       }
       {
         // Note: prefix as seek key is not bloom-optimized
@@ -3450,14 +3490,14 @@ TEST_F(DBBloomFilterTest, WeirdPrefixExtractorWithFilter3) {
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "zzzz"), weird_comparator ? 8 : 1);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
       }
       {
         Slice ub("zzzz9");
         read_options.iterate_upper_bound = &ub;
         std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
         EXPECT_EQ(CountIter(iter, "aab"), weird_comparator ? 6 : 5);
-        EXPECT_EQ(GetBloomStat(options, flushed), CheckedAndUseful(0, 0));
+        EXPECT_EQ(GetBloomStat(options, flushed), HitAndMiss(0, 0));
       }
     }
   }

db/db_clip_test.cc

@@ -0,0 +1,142 @@
+//  Copyright (c) Meta Platforms, Inc. and affiliates.
+//  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/db_test_util.h"
+#include "port/port.h"
+#include "util/random.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class DBClipTest : public DBTestBase {
+ public:
+  DBClipTest() : DBTestBase("db_clip_test", /*env_do_fsync=*/true) {}
+};
+
+TEST_F(DBClipTest, TestClipRange) {
+  Options options = CurrentOptions();
+  options.write_buffer_size = 10 * 1024 * 1024;
+  options.max_bytes_for_level_multiplier = 2;
+  options.num_levels = 3;
+  options.max_background_compactions = 3;
+  options.disable_auto_compactions = true;
+  options.statistics = CreateDBStatistics();
+
+  DestroyAndReopen(options);
+  int32_t value_size = 10 * 1024;  // 10 KB
+
+  Random rnd(301);
+  std::map<int32_t, std::string> values;
+
+  // file [0 => 100), [100 => 200), ... [900, 1000)
+  for (auto i = 0; i < 10; i++) {
+    for (auto j = 0; j < 100; j++) {
+      auto k = i * 100 + j;
+      values[k] = rnd.RandomString(value_size);
+      ASSERT_OK(Put(Key(k), values[k]));
+    }
+    ASSERT_OK(Flush());
+  }
+  ASSERT_EQ("10", FilesPerLevel(0));
+  auto begin_key = Key(251), end_key = Key(751);
+  ASSERT_OK(
+      db_->ClipColumnFamily(db_->DefaultColumnFamily(), begin_key, end_key));
+
+  for (auto i = 0; i < 251; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+  for (auto i = 251; i < 751; i++) {
+    ASSERT_EQ(Get(Key(i)), values[i]);
+  }
+  for (auto i = 751; i < 1000; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+
+  std::vector<LiveFileMetaData> all_metadata;
+  db_->GetLiveFilesMetaData(&all_metadata);
+  for (auto& md : all_metadata) {
+    // make sure clip_begin_key <= file_smallestkey <= file_largestkey <=
+    // clip_end_key
+    bool in_range = false;
+
+    if (options.comparator->Compare(begin_key, md.smallestkey) <= 0 &&
+        options.comparator->Compare(end_key, md.largestkey) > 0) {
+      in_range = true;
+    }
+    ASSERT_TRUE(in_range);
+  }
+
+  CompactRangeOptions compact_options;
+  compact_options.change_level = true;
+  compact_options.target_level = 2;
+  ASSERT_OK(db_->CompactRange(compact_options, nullptr, nullptr));
+  ASSERT_EQ("0,0,3", FilesPerLevel(0));
+
+  for (auto i = 0; i < 10; i += 2) {
+    for (auto j = 0; j < 100; j++) {
+      auto k = i * 100 + j;
+      ASSERT_OK(Put(Key(k), values[k]));
+    }
+    ASSERT_OK(Flush());
+  }
+  ASSERT_EQ("5,0,3", FilesPerLevel(0));
+  ASSERT_OK(dbfull()->TEST_CompactRange(0, nullptr, nullptr));
+  ASSERT_EQ("0,5,3", FilesPerLevel(0));
+
+  for (auto i = 1; i < 10; i += 2) {
+    for (auto j = 0; j < 100; j++) {
+      auto k = i * 100 + j;
+      ASSERT_OK(Put(Key(k), values[k]));
+    }
+    ASSERT_OK(Flush());
+  }
+  ASSERT_EQ("5,5,3", FilesPerLevel(0));
+
+  auto begin_key_2 = Key(222), end_key_2 = Key(888);
+
+  ASSERT_OK(db_->ClipColumnFamily(db_->DefaultColumnFamily(), begin_key_2,
+                                  end_key_2));
+
+  for (auto i = 0; i < 222; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+  for (auto i = 222; i < 888; i++) {
+    ASSERT_EQ(Get(Key(i)), values[i]);
+  }
+  for (auto i = 888; i < 1000; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+
+  std::vector<LiveFileMetaData> all_metadata_2;
+  db_->GetLiveFilesMetaData(&all_metadata_2);
+  for (auto& md : all_metadata_2) {
+    // make sure clip_begin_key <= file_smallestkey <= file_largestkey <=
+    // clip_end_key
+    bool in_range = false;
+    if (begin_key_2.compare(md.smallestkey) <= 0 &&
+        end_key_2.compare(md.largestkey) > 0) {
+      in_range = true;
+    }
+    ASSERT_TRUE(in_range);
+  }
+}
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/db_compaction_filter_test.cc

@@ -742,7 +742,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextCfId) {
   ASSERT_TRUE(filter->compaction_filter_created());
 }
 
-// Compaction filters aplies to all records, regardless snapshots.
+// Compaction filters applies to all records, regardless snapshots.
 TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
   std::string five = std::to_string(5);
   Options options = CurrentOptions();

db/db_filesnapshot.cc

@@ -29,35 +29,8 @@
 namespace ROCKSDB_NAMESPACE {
 
 Status DBImpl::FlushForGetLiveFiles() {
-  mutex_.AssertHeld();
-
-  // flush all dirty data to disk.
-  Status status;
-  if (immutable_db_options_.atomic_flush) {
-    mutex_.Unlock();
-    status = AtomicFlushMemTables(FlushOptions(), FlushReason::kGetLiveFiles);
-    if (status.IsColumnFamilyDropped()) {
-      status = Status::OK();
-    }
-    mutex_.Lock();
-  } else {
-    for (auto cfd : versions_->GetRefedColumnFamilySet()) {
-      if (cfd->IsDropped()) {
-        continue;
-      }
-      mutex_.Unlock();
-      status = FlushMemTable(cfd, FlushOptions(), FlushReason::kGetLiveFiles);
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
-      mutex_.Lock();
-      if (!status.ok() && !status.IsColumnFamilyDropped()) {
-        break;
-      } else if (status.IsColumnFamilyDropped()) {
-        status = Status::OK();
-      }
-    }
-  }
-  return status;
+  return DBImpl::FlushAllColumnFamilies(FlushOptions(),
+                                        FlushReason::kGetLiveFiles);
 }
 
 Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,

db/db_impl/compacted_db_impl.cc

@@ -46,6 +46,11 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
 Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                             const Slice& key, PinnableSlice* value,
                             std::string* timestamp) {
+  if (options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call Get with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
   assert(user_comparator_);
   if (options.timestamp) {
     const Status s = FailIfTsMismatchCf(

db/db_impl/compacted_db_impl.h

@@ -118,16 +118,24 @@ class CompactedDBImpl : public DBImpl {
       const IngestExternalFileOptions& /*ingestion_options*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
+
   using DB::CreateColumnFamilyWithImport;
   virtual Status CreateColumnFamilyWithImport(
       const ColumnFamilyOptions& /*options*/,
       const std::string& /*column_family_name*/,
       const ImportColumnFamilyOptions& /*import_options*/,
-      const ExportImportFilesMetaData& /*metadata*/,
+      const std::vector<const ExportImportFilesMetaData*>& /*metadatas*/,
       ColumnFamilyHandle** /*handle*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
 
+  using DB::ClipColumnFamily;
+  virtual Status ClipColumnFamily(ColumnFamilyHandle* /*column_family*/,
+                                  const Slice& /*begin*/,
+                                  const Slice& /*end*/) override {
+    return Status::NotSupported("Not supported in compacted db mode.");
+  }
+
   // FIXME: some missing overrides for more "write" functions
   // Share with DBImplReadOnly?
 

db/db_impl/db_impl.cc

@@ -258,6 +258,9 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
   co.capacity = table_cache_size;
   co.num_shard_bits = immutable_db_options_.table_cache_numshardbits;
   co.metadata_charge_policy = kDontChargeCacheMetadata;
+  // TODO: Consider a non-fixed seed once test fallout (prefetch_test) is
+  // dealt with
+  co.hash_seed = 0;
   table_cache_ = NewLRUCache(co);
   SetDbSessionId();
   assert(!db_session_id_.empty());
@@ -327,6 +330,9 @@ Status DBImpl::Resume() {
 //    means a new super version wouldn't have been installed
 Status DBImpl::ResumeImpl(DBRecoverContext context) {
   mutex_.AssertHeld();
+
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   WaitForBackgroundWork();
 
   Status s;
@@ -368,7 +374,7 @@ Status DBImpl::ResumeImpl(DBRecoverContext context) {
       assert(cfh);
       ColumnFamilyData* cfd = cfh->cfd();
       const MutableCFOptions& cf_opts = *cfd->GetLatestMutableCFOptions();
-      s = versions_->LogAndApply(cfd, cf_opts, &edit, &mutex_,
+      s = versions_->LogAndApply(cfd, cf_opts, read_options, &edit, &mutex_,
                                  directories_.GetDbDir());
       if (!s.ok()) {
         io_s = versions_->io_status();
@@ -1147,6 +1153,8 @@ FSDirectory* DBImpl::GetDataDir(ColumnFamilyData* cfd, size_t path_id) const {
 Status DBImpl::SetOptions(
     ColumnFamilyHandle* column_family,
     const std::unordered_map<std::string, std::string>& options_map) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   auto* cfd =
       static_cast_with_check<ColumnFamilyHandleImpl>(column_family)->cfd();
   if (options_map.empty()) {
@@ -1168,8 +1176,8 @@ Status DBImpl::SetOptions(
       new_options = *cfd->GetLatestMutableCFOptions();
       // Append new version to recompute compaction score.
       VersionEdit dummy_edit;
-      s = versions_->LogAndApply(cfd, new_options, &dummy_edit, &mutex_,
-                                 directories_.GetDbDir());
+      s = versions_->LogAndApply(cfd, new_options, read_options, &dummy_edit,
+                                 &mutex_, directories_.GetDbDir());
       // Trigger possible flush/compactions. This has to be before we persist
       // options to file, otherwise there will be a deadlock with writer
       // thread.
@@ -1507,7 +1515,9 @@ Status DBImpl::SyncWAL() {
   }
   if (status.ok() && synced_wals.IsWalAddition()) {
     InstrumentedMutexLock l(&mutex_);
-    status = ApplyWALToManifest(&synced_wals);
+    // TODO: plumb Env::IOActivity
+    const ReadOptions read_options;
+    status = ApplyWALToManifest(read_options, &synced_wals);
   }
 
   TEST_SYNC_POINT("DBImpl::SyncWAL:BeforeMarkLogsSynced:2");
@@ -1515,11 +1525,13 @@ Status DBImpl::SyncWAL() {
   return status;
 }
 
-Status DBImpl::ApplyWALToManifest(VersionEdit* synced_wals) {
+Status DBImpl::ApplyWALToManifest(const ReadOptions& read_options,
+                                  VersionEdit* synced_wals) {
   // not empty, write to MANIFEST.
   mutex_.AssertHeld();
+
   Status status = versions_->LogAndApplyToDefaultColumnFamily(
-      synced_wals, &mutex_, directories_.GetDbDir());
+      read_options, synced_wals, &mutex_, directories_.GetDbDir());
   if (!status.ok() && versions_->io_status().IsIOError()) {
     status = error_handler_.SetBGError(versions_->io_status(),
                                        BackgroundErrorReason::kManifestWrite);
@@ -1936,6 +1948,12 @@ Status DBImpl::GetEntity(const ReadOptions& read_options,
         "Cannot call GetEntity without a PinnableWideColumns object");
   }
 
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call GetEntity with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
+
   columns->Reset();
 
   GetImplOptions get_impl_options;
@@ -1981,6 +1999,12 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
 
   assert(get_impl_options.column_family);
 
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call Get with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
+
   if (read_options.timestamp) {
     const Status s = FailIfTsMismatchCf(get_impl_options.column_family,
                                         *(read_options.timestamp),
@@ -2454,7 +2478,6 @@ std::vector<Status> DBImpl::MultiGet(
 
   // Post processing (decrement reference counts and record statistics)
   PERF_TIMER_GUARD(get_post_process_time);
-  autovector<SuperVersion*> superversions_to_delete;
 
   for (auto mgd_iter : multiget_cf_data) {
     auto mgd = mgd_iter.second;
@@ -2931,6 +2954,11 @@ Status DBImpl::MultiGetImpl(
     autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys,
     SuperVersion* super_version, SequenceNumber snapshot,
     ReadCallback* callback) {
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call MultiGet with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
   PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
   StopWatch sw(immutable_db_options_.clock, stats_, DB_MULTIGET);
 
@@ -3129,6 +3157,8 @@ Status DBImpl::CreateColumnFamilies(
 Status DBImpl::CreateColumnFamilyImpl(const ColumnFamilyOptions& cf_options,
                                       const std::string& column_family_name,
                                       ColumnFamilyHandle** handle) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   Status s;
   *handle = nullptr;
 
@@ -3169,9 +3199,9 @@ Status DBImpl::CreateColumnFamilyImpl(const ColumnFamilyOptions& cf_options,
       write_thread_.EnterUnbatched(&w, &mutex_);
       // LogAndApply will both write the creation in MANIFEST and create
       // ColumnFamilyData object
-      s = versions_->LogAndApply(nullptr, MutableCFOptions(cf_options), &edit,
-                                 &mutex_, directories_.GetDbDir(), false,
-                                 &cf_options);
+      s = versions_->LogAndApply(nullptr, MutableCFOptions(cf_options),
+                                 read_options, &edit, &mutex_,
+                                 directories_.GetDbDir(), false, &cf_options);
       write_thread_.ExitUnbatched(&w);
     }
     if (s.ok()) {
@@ -3250,6 +3280,8 @@ Status DBImpl::DropColumnFamilies(
 }
 
 Status DBImpl::DropColumnFamilyImpl(ColumnFamilyHandle* column_family) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
   auto cfd = cfh->cfd();
   if (cfd->GetID() == 0) {
@@ -3272,8 +3304,9 @@ Status DBImpl::DropColumnFamilyImpl(ColumnFamilyHandle* column_family) {
       // we drop column family from a single write thread
       WriteThread::Writer w;
       write_thread_.EnterUnbatched(&w, &mutex_);
-      s = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(), &edit,
-                                 &mutex_, directories_.GetDbDir());
+      s = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
+                                 read_options, &edit, &mutex_,
+                                 directories_.GetDbDir());
       write_thread_.ExitUnbatched(&w);
     }
     if (s.ok()) {
@@ -3324,10 +3357,13 @@ bool DBImpl::KeyMayExist(const ReadOptions& read_options,
                          std::string* value, std::string* timestamp,
                          bool* value_found) {
   assert(value != nullptr);
+  assert(read_options.io_activity == Env::IOActivity::kUnknown);
+
   if (value_found != nullptr) {
     // falsify later if key-may-exist but can't fetch value
     *value_found = true;
   }
+  // TODO: plumb Env::IOActivity
   ReadOptions roptions = read_options;
   roptions.read_tier = kBlockCacheTier;  // read from block cache only
   PinnableSlice pinnable_val;
@@ -3356,6 +3392,11 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
     return NewErrorIterator(Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators."));
   }
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return NewErrorIterator(Status::InvalidArgument(
+        "Cannot call NewIterator with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`"));
+  }
 
   assert(column_family);
 
@@ -3491,6 +3532,11 @@ Status DBImpl::NewIterators(
     return Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators.");
   }
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call NewIterators with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
 
   if (read_options.timestamp) {
     for (auto* cf : column_families) {
@@ -3808,7 +3854,9 @@ Status DBImpl::GetPropertiesOfAllTables(ColumnFamilyHandle* column_family,
   version->Ref();
   mutex_.Unlock();
 
-  auto s = version->GetPropertiesOfAllTables(props);
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
+  auto s = version->GetPropertiesOfAllTables(read_options, props);
 
   // Decrement the ref count
   mutex_.Lock();
@@ -3830,7 +3878,9 @@ Status DBImpl::GetPropertiesOfTablesInRange(ColumnFamilyHandle* column_family,
   version->Ref();
   mutex_.Unlock();
 
-  auto s = version->GetPropertiesOfTablesInRange(range, n, props);
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
+  auto s = version->GetPropertiesOfTablesInRange(read_options, range, n, props);
 
   // Decrement the ref count
   mutex_.Lock();
@@ -4163,6 +4213,8 @@ Status DBImpl::GetApproximateSizes(const SizeApproximationOptions& options,
   SuperVersion* sv = GetAndRefSuperVersion(cfd);
   v = sv->current;
 
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   for (int i = 0; i < n; i++) {
     Slice start = range[i].start;
     Slice limit = range[i].limit;
@@ -4184,7 +4236,7 @@ Status DBImpl::GetApproximateSizes(const SizeApproximationOptions& options,
     sizes[i] = 0;
     if (options.include_files) {
       sizes[i] += versions_->ApproximateSize(
-          options, v, k1.Encode(), k2.Encode(), /*start_level=*/0,
+          options, read_options, v, k1.Encode(), k2.Encode(), /*start_level=*/0,
           /*end_level=*/-1, TableReaderCaller::kUserApproximateSize);
     }
     if (options.include_memtables) {
@@ -4232,6 +4284,8 @@ Status DBImpl::GetUpdatesSince(
 }
 
 Status DBImpl::DeleteFile(std::string name) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   uint64_t number;
   FileType type;
   WalFileType log_type;
@@ -4311,7 +4365,8 @@ Status DBImpl::DeleteFile(std::string name) {
     edit.SetColumnFamily(cfd->GetID());
     edit.DeleteFile(level, number);
     status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
-                                    &edit, &mutex_, directories_.GetDbDir());
+                                    read_options, &edit, &mutex_,
+                                    directories_.GetDbDir());
     if (status.ok()) {
       InstallSuperVersionAndScheduleWork(cfd,
                                          &job_context.superversion_contexts[0],
@@ -4333,6 +4388,8 @@ Status DBImpl::DeleteFile(std::string name) {
 Status DBImpl::DeleteFilesInRanges(ColumnFamilyHandle* column_family,
                                    const RangePtr* ranges, size_t n,
                                    bool include_end) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   Status status = Status::OK();
   auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
   ColumnFamilyData* cfd = cfh->cfd();
@@ -4398,7 +4455,8 @@ Status DBImpl::DeleteFilesInRanges(ColumnFamilyHandle* column_family,
     }
     input_version->Ref();
     status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
-                                    &edit, &mutex_, directories_.GetDbDir());
+                                    read_options, &edit, &mutex_,
+                                    directories_.GetDbDir());
     if (status.ok()) {
       InstallSuperVersionAndScheduleWork(cfd,
                                          &job_context.superversion_contexts[0],
@@ -4464,7 +4522,6 @@ void DBImpl::GetAllColumnFamilyMetaData(
   }
 }
 
-
 Status DBImpl::CheckConsistency() {
   mutex_.AssertHeld();
   std::vector<LiveFileMetaData> metadata;
@@ -4855,6 +4912,15 @@ Status DBImpl::WriteOptionsFile(bool need_mutex_lock,
   if (s.ok()) {
     s = RenameTempFileToOptionsFile(file_name);
   }
+
+  if (!s.ok() && GetEnv()->FileExists(file_name).ok()) {
+    if (!GetEnv()->DeleteFile(file_name).ok()) {
+      ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                     "Unable to delete temp options file %s",
+                     file_name.c_str());
+    }
+  }
+
   // restore lock
   if (!need_mutex_lock) {
     mutex_.Lock();
@@ -5034,6 +5100,7 @@ Status DBImpl::GetLatestSequenceForKey(
   MergeContext merge_context;
   SequenceNumber max_covering_tombstone_seq = 0;
 
+  // TODO: plumb Env::IOActivity
   ReadOptions read_options;
   SequenceNumber current_seq = versions_->LastSequence();
 
@@ -5189,6 +5256,8 @@ Status DBImpl::IngestExternalFile(
 
 Status DBImpl::IngestExternalFiles(
     const std::vector<IngestExternalFileArg>& args) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   if (args.empty()) {
     return Status::InvalidArgument("ingestion arg list is empty");
   }
@@ -5406,9 +5475,9 @@ Status DBImpl::IngestExternalFiles(
         }
         assert(0 == num_entries);
       }
-      status =
-          versions_->LogAndApply(cfds_to_commit, mutable_cf_options_list,
-                                 edit_lists, &mutex_, directories_.GetDbDir());
+      status = versions_->LogAndApply(cfds_to_commit, mutable_cf_options_list,
+                                      read_options, edit_lists, &mutex_,
+                                      directories_.GetDbDir());
       // It is safe to update VersionSet last seqno here after LogAndApply since
       // LogAndApply persists last sequence number from VersionEdits,
       // which are from file's largest seqno and not from VersionSet.
@@ -5506,12 +5575,24 @@ Status DBImpl::IngestExternalFiles(
 Status DBImpl::CreateColumnFamilyWithImport(
     const ColumnFamilyOptions& options, const std::string& column_family_name,
     const ImportColumnFamilyOptions& import_options,
-    const ExportImportFilesMetaData& metadata, ColumnFamilyHandle** handle) {
+    const std::vector<const ExportImportFilesMetaData*>& metadatas,
+    ColumnFamilyHandle** handle) {
   assert(handle != nullptr);
   assert(*handle == nullptr);
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   std::string cf_comparator_name = options.comparator->Name();
-  if (cf_comparator_name != metadata.db_comparator_name) {
-    return Status::InvalidArgument("Comparator name mismatch");
+
+  size_t total_file_num = 0;
+  std::vector<std::vector<LiveFileMetaData*>> metadata_files(metadatas.size());
+  for (size_t i = 0; i < metadatas.size(); i++) {
+    if (cf_comparator_name != metadatas[i]->db_comparator_name) {
+      return Status::InvalidArgument("Comparator name mismatch");
+    }
+    for (auto& file : metadatas[i]->files) {
+      metadata_files[i].push_back((LiveFileMetaData*)&file);
+    }
+    total_file_num += metadatas[i]->files.size();
   }
 
   // Create column family.
@@ -5525,7 +5606,7 @@ Status DBImpl::CreateColumnFamilyWithImport(
   auto cfd = cfh->cfd();
   ImportColumnFamilyJob import_job(versions_.get(), cfd, immutable_db_options_,
                                    file_options_, import_options,
-                                   metadata.files, io_tracer_);
+                                   metadata_files, io_tracer_);
 
   SuperVersionContext dummy_sv_ctx(/* create_superversion */ true);
   VersionEdit dummy_edit;
@@ -5548,10 +5629,11 @@ Status DBImpl::CreateColumnFamilyWithImport(
       // reuse the file number that has already assigned to the internal file,
       // and this will overwrite the external file. To protect the external
       // file, we have to make sure the file number will never being reused.
-      next_file_number = versions_->FetchAddFileNumber(metadata.files.size());
+      next_file_number = versions_->FetchAddFileNumber(total_file_num);
       auto cf_options = cfd->GetLatestMutableCFOptions();
-      status = versions_->LogAndApply(cfd, *cf_options, &dummy_edit, &mutex_,
-                                      directories_.GetDbDir());
+      status =
+          versions_->LogAndApply(cfd, *cf_options, read_options, &dummy_edit,
+                                 &mutex_, directories_.GetDbDir());
       if (status.ok()) {
         InstallSuperVersionAndScheduleWork(cfd, &dummy_sv_ctx, *cf_options);
       }
@@ -5587,8 +5669,9 @@ Status DBImpl::CreateColumnFamilyWithImport(
       // Install job edit [Mutex will be unlocked here]
       if (status.ok()) {
         auto cf_options = cfd->GetLatestMutableCFOptions();
-        status = versions_->LogAndApply(cfd, *cf_options, import_job.edit(),
-                                        &mutex_, directories_.GetDbDir());
+        status = versions_->LogAndApply(cfd, *cf_options, read_options,
+                                        import_job.edit(), &mutex_,
+                                        directories_.GetDbDir());
         if (status.ok()) {
           InstallSuperVersionAndScheduleWork(cfd, &sv_context, *cf_options);
         }
@@ -5631,6 +5714,81 @@ Status DBImpl::CreateColumnFamilyWithImport(
   return status;
 }
 
+Status DBImpl::ClipColumnFamily(ColumnFamilyHandle* column_family,
+                                const Slice& begin_key, const Slice& end_key) {
+  assert(column_family);
+  Status status;
+  // Flush memtable
+  FlushOptions flush_opts;
+  flush_opts.allow_write_stall = true;
+  auto* cfd =
+      static_cast_with_check<ColumnFamilyHandleImpl>(column_family)->cfd();
+  if (immutable_db_options_.atomic_flush) {
+    status = AtomicFlushMemTables(flush_opts, FlushReason::kDeleteFiles,
+                                  {} /* provided_candidate_cfds */,
+                                  false /* entered_write_thread */);
+  } else {
+    status = FlushMemTable(cfd, flush_opts, FlushReason::kDeleteFiles,
+                           false /* entered_write_thread */);
+  }
+
+  if (status.ok()) {
+    // DeleteFilesInRanges non-overlap files except L0
+    std::vector<RangePtr> ranges;
+    ranges.push_back(RangePtr(nullptr, &begin_key));
+    ranges.push_back(RangePtr(&end_key, nullptr));
+    status = DeleteFilesInRanges(column_family, ranges.data(), ranges.size());
+  }
+
+  // DeleteRange the remaining overlapping keys
+  bool empty_after_delete = false;
+  if (status.ok()) {
+    Slice smallest_user_key, largest_user_key;
+    {
+      // Lock db mutex
+      InstrumentedMutexLock l(&mutex_);
+      cfd->current()->GetSstFilesBoundaryKeys(&smallest_user_key,
+                                              &largest_user_key);
+    }
+    // all the files has been deleted after DeleteFilesInRanges;
+    if (smallest_user_key.empty() && largest_user_key.empty()) {
+      empty_after_delete = true;
+    } else {
+      const Comparator* const ucmp = column_family->GetComparator();
+      WriteOptions wo;
+      // Delete [smallest_user_key, clip_begin_key)
+      if (ucmp->Compare(smallest_user_key, begin_key) < 0) {
+        status = DeleteRange(wo, column_family, smallest_user_key, begin_key);
+      }
+
+      if (status.ok()) {
+        // Delete [clip_end_key, largest_use_key]
+        if (ucmp->Compare(end_key, largest_user_key) < 0) {
+          status = DeleteRange(wo, column_family, end_key, largest_user_key);
+          if (status.ok()) {
+            status = Delete(wo, column_family, largest_user_key);
+          }
+        }
+      }
+    }
+  }
+
+  if (status.ok() && !empty_after_delete) {
+    // CompactRange delete all the tombstones
+    CompactRangeOptions compact_options;
+    compact_options.exclusive_manual_compaction = true;
+    compact_options.bottommost_level_compaction =
+        BottommostLevelCompaction::kForceOptimized;
+    // We could just compact the ranges [null, clip_begin_key] and
+    // [clip_end_key, null]. But due to how manual compaction calculates the
+    // last level to compact to and that range tombstones are not dropped
+    // during non-bottommost compactions, calling CompactRange() on these two
+    // ranges may not clear all range tombstones.
+    status = CompactRange(compact_options, nullptr, nullptr);
+  }
+  return status;
+}
+
 Status DBImpl::VerifyFileChecksums(const ReadOptions& read_options) {
   return VerifyChecksumInternal(read_options, /*use_file_checksum=*/true);
 }
@@ -5648,6 +5806,12 @@ Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
 
   Status s;
 
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    s = Status::InvalidArgument(
+        "Cannot verify file checksum with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+    return s;
+  }
   if (use_file_checksum) {
     FileChecksumGenFactory* const file_checksum_gen_factory =
         immutable_db_options_.file_checksum_gen_factory.get();
@@ -5761,6 +5925,12 @@ Status DBImpl::VerifyFullFileChecksum(const std::string& file_checksum_expected,
                                       const std::string& func_name_expected,
                                       const std::string& fname,
                                       const ReadOptions& read_options) {
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call VerifyChecksum with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
+
   Status s;
   if (file_checksum_expected == kUnknownFileChecksum) {
     return s;
@@ -5893,6 +6063,8 @@ Status DBImpl::ReserveFileNumbersBeforeIngestion(
     ColumnFamilyData* cfd, uint64_t num,
     std::unique_ptr<std::list<uint64_t>::iterator>& pending_output_elem,
     uint64_t* next_file_number) {
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   Status s;
   SuperVersionContext dummy_sv_ctx(true /* create_superversion */);
   assert(nullptr != next_file_number);
@@ -5910,8 +6082,8 @@ Status DBImpl::ReserveFileNumbersBeforeIngestion(
   // reuse the file number that has already assigned to the internal file,
   // and this will overwrite the external file. To protect the external
   // file, we have to make sure the file number will never being reused.
-  s = versions_->LogAndApply(cfd, *cf_options, &dummy_edit, &mutex_,
-                             directories_.GetDbDir());
+  s = versions_->LogAndApply(cfd, *cf_options, read_options, &dummy_edit,
+                             &mutex_, directories_.GetDbDir());
   if (s.ok()) {
     InstallSuperVersionAndScheduleWork(cfd, &dummy_sv_ctx, *cf_options);
   }

db/db_impl/db_impl.h

@@ -531,9 +531,14 @@ class DBImpl : public DB {
   virtual Status CreateColumnFamilyWithImport(
       const ColumnFamilyOptions& options, const std::string& column_family_name,
       const ImportColumnFamilyOptions& import_options,
-      const ExportImportFilesMetaData& metadata,
+      const std::vector<const ExportImportFilesMetaData*>& metadatas,
       ColumnFamilyHandle** handle) override;
 
+  using DB::ClipColumnFamily;
+  virtual Status ClipColumnFamily(ColumnFamilyHandle* column_family,
+                                  const Slice& begin_key,
+                                  const Slice& end_key) override;
+
   using DB::VerifyFileChecksums;
   Status VerifyFileChecksums(const ReadOptions& read_options) override;
 
@@ -734,13 +739,17 @@ class DBImpl : public DB {
   // max_file_num_to_ignore allows bottom level compaction to filter out newly
   // compacted SST files. Setting max_file_num_to_ignore to kMaxUint64 will
   // disable the filtering
+  // If `final_output_level` is not nullptr, it is set to manual compaction's
+  // output level if returned status is OK, and it may or may not be set to
+  // manual compaction's output level if returned status is not OK.
   Status RunManualCompaction(ColumnFamilyData* cfd, int input_level,
                              int output_level,
                              const CompactRangeOptions& compact_range_options,
                              const Slice* begin, const Slice* end,
                              bool exclusive, bool disallow_trivial_move,
                              uint64_t max_file_num_to_ignore,
-                             const std::string& trim_ts);
+                             const std::string& trim_ts,
+                             int* final_output_level = nullptr);
 
   // Return an internal iterator over the current state of the database.
   // The keys of this iterator are internal keys (see format.h).
@@ -802,6 +811,8 @@ class DBImpl : public DB {
   // being deleted.
   uint64_t MinObsoleteSstNumberToKeep();
 
+  uint64_t GetObsoleteSstFilesSize();
+
   // Returns the list of live files in 'live' and the list
   // of all files in the filesystem in 'candidate_files'.
   // If force == false and the last call was less than
@@ -1049,10 +1060,8 @@ class DBImpl : public DB {
 
   VersionSet* GetVersionSet() const { return versions_.get(); }
 
-  // Wait for any compaction
-  // We add a bool parameter to wait for unscheduledCompactions_ == 0, but this
-  // is only for the special test of CancelledCompactions
-  Status WaitForCompact(bool waitUnscheduled = false);
+  Status WaitForCompact(
+      const WaitForCompactOptions& wait_for_compact_options) override;
 
 #ifndef NDEBUG
   // Compact any files in the named level that overlap [*begin, *end]
@@ -1091,10 +1100,9 @@ class DBImpl : public DB {
   // Wait for memtable compaction
   Status TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family = nullptr);
 
-  // Wait for any compaction
-  // We add a bool parameter to wait for unscheduledCompactions_ == 0, but this
-  // is only for the special test of CancelledCompactions
-  Status TEST_WaitForCompact(bool waitUnscheduled = false);
+  Status TEST_WaitForCompact();
+  Status TEST_WaitForCompact(
+      const WaitForCompactOptions& wait_for_compact_options);
 
   // Wait for any background purge
   Status TEST_WaitForPurge();
@@ -1404,6 +1412,9 @@ class DBImpl : public DB {
   void NotifyOnExternalFileIngested(
       ColumnFamilyData* cfd, const ExternalSstFileIngestionJob& ingestion_job);
 
+  Status FlushAllColumnFamilies(const FlushOptions& flush_options,
+                                FlushReason flush_reason);
+
   virtual Status FlushForGetLiveFiles();
 
   void NewThreadStatusCfInfo(ColumnFamilyData* cfd) const;
@@ -2123,7 +2134,7 @@ class DBImpl : public DB {
 
   // helper function to call after some of the logs_ were synced
   void MarkLogsSynced(uint64_t up_to, bool synced_dir, VersionEdit* edit);
-  Status ApplyWALToManifest(VersionEdit* edit);
+  Status ApplyWALToManifest(const ReadOptions& read_options, VersionEdit* edit);
   // WALs with log number up to up_to are not synced successfully.
   void MarkLogsNotSynced(uint64_t up_to);
 
@@ -2306,7 +2317,7 @@ class DBImpl : public DB {
   // logfile_number_. With two_write_queues it also protects alive_log_files_,
   // and log_empty_. Refer to the definition of each variable below for more
   // details.
-  // Note: to avoid dealock, if needed to acquire both log_write_mutex_ and
+  // Note: to avoid deadlock, if needed to acquire both log_write_mutex_ and
   // mutex_, the order should be first mutex_ and then log_write_mutex_.
   InstrumentedMutex log_write_mutex_;
 

db/db_impl/db_impl_compaction_flush.cc

@@ -229,7 +229,9 @@ Status DBImpl::FlushMemTableToOutputFile(
     log_io_s = SyncClosedLogs(job_context, &synced_wals);
     mutex_.Lock();
     if (log_io_s.ok() && synced_wals.IsWalAddition()) {
-      log_io_s = status_to_io_status(ApplyWALToManifest(&synced_wals));
+      const ReadOptions read_options(Env::IOActivity::kFlush);
+      log_io_s =
+          status_to_io_status(ApplyWALToManifest(read_options, &synced_wals));
       TEST_SYNC_POINT_CALLBACK("DBImpl::FlushMemTableToOutputFile:CommitWal:1",
                                nullptr);
     }
@@ -492,7 +494,9 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     log_io_s = SyncClosedLogs(job_context, &synced_wals);
     mutex_.Lock();
     if (log_io_s.ok() && synced_wals.IsWalAddition()) {
-      log_io_s = status_to_io_status(ApplyWALToManifest(&synced_wals));
+      const ReadOptions read_options(Env::IOActivity::kFlush);
+      log_io_s =
+          status_to_io_status(ApplyWALToManifest(read_options, &synced_wals));
     }
 
     if (!log_io_s.ok() && !log_io_s.IsShutdownInProgress() &&
@@ -848,8 +852,8 @@ void DBImpl::NotifyOnFlushBegin(ColumnFamilyData* cfd, FileMetaData* file_meta,
     }
   }
   mutex_.Lock();
-// no need to signal bg_cv_ as it will be signaled at the end of the
-// flush process.
+  // no need to signal bg_cv_ as it will be signaled at the end of the
+  // flush process.
 }
 
 void DBImpl::NotifyOnFlushCompleted(
@@ -956,6 +960,9 @@ Status DBImpl::IncreaseFullHistoryTsLowImpl(ColumnFamilyData* cfd,
   VersionEdit edit;
   edit.SetColumnFamily(cfd->GetID());
   edit.SetFullHistoryTsLow(ts_low);
+
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   TEST_SYNC_POINT_CALLBACK("DBImpl::IncreaseFullHistoryTsLowImpl:BeforeEdit",
                            &edit);
 
@@ -969,7 +976,8 @@ Status DBImpl::IncreaseFullHistoryTsLowImpl(ColumnFamilyData* cfd,
   }
 
   Status s = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
-                                    &edit, &mutex_, directories_.GetDbDir());
+                                    read_options, &edit, &mutex_,
+                                    directories_.GetDbDir());
   if (!s.ok()) {
     return s;
   }
@@ -1054,11 +1062,10 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
     }
     s = RunManualCompaction(cfd, ColumnFamilyData::kCompactAllLevels,
                             final_output_level, options, begin, end, exclusive,
-                            false, std::numeric_limits<uint64_t>::max(),
-                            trim_ts);
+                            false /* disable_trivial_move */,
+                            std::numeric_limits<uint64_t>::max(), trim_ts);
   } else {
     int first_overlapped_level = kInvalidLevel;
-    int max_overlapped_level = kInvalidLevel;
     {
       SuperVersion* super_version = cfd->GetReferencedSuperVersion(this);
       Version* current_version = super_version->current;
@@ -1080,6 +1087,7 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
 
       ReadOptions ro;
       ro.total_order_seek = true;
+      ro.io_activity = Env::IOActivity::kCompaction;
       bool overlap;
       for (int level = 0;
            level < current_version->storage_info()->num_non_empty_levels();
@@ -1133,83 +1141,104 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
                                                                     begin, end);
         }
         if (overlap) {
-          if (first_overlapped_level == kInvalidLevel) {
-            first_overlapped_level = level;
-          }
-          max_overlapped_level = level;
+          first_overlapped_level = level;
+          break;
         }
       }
       CleanupSuperVersion(super_version);
     }
     if (s.ok() && first_overlapped_level != kInvalidLevel) {
-      // max_file_num_to_ignore can be used to filter out newly created SST
-      // files, useful for bottom level compaction in a manual compaction
-      uint64_t max_file_num_to_ignore = std::numeric_limits<uint64_t>::max();
-      uint64_t next_file_number = versions_->current_next_file_number();
-      final_output_level = max_overlapped_level;
-      int output_level;
-      for (int level = first_overlapped_level; level <= max_overlapped_level;
-           level++) {
-        bool disallow_trivial_move = false;
-        // in case the compaction is universal or if we're compacting the
-        // bottom-most level, the output level will be the same as input one.
-        // level 0 can never be the bottommost level (i.e. if all files are in
-        // level 0, we will compact to level 1)
-        if (cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
-            cfd->ioptions()->compaction_style == kCompactionStyleFIFO) {
-          output_level = level;
-        } else if (level == max_overlapped_level && level > 0) {
-          if (options.bottommost_level_compaction ==
-              BottommostLevelCompaction::kSkip) {
-            // Skip bottommost level compaction
-            continue;
-          } else if (options.bottommost_level_compaction ==
-                         BottommostLevelCompaction::kIfHaveCompactionFilter &&
-                     cfd->ioptions()->compaction_filter == nullptr &&
-                     cfd->ioptions()->compaction_filter_factory == nullptr) {
-            // Skip bottommost level compaction since we don't have a compaction
-            // filter
-            continue;
+      if (cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
+          cfd->ioptions()->compaction_style == kCompactionStyleFIFO) {
+        assert(first_overlapped_level == 0);
+        s = RunManualCompaction(
+            cfd, first_overlapped_level, first_overlapped_level, options, begin,
+            end, exclusive, true /* disallow_trivial_move */,
+            std::numeric_limits<uint64_t>::max() /* max_file_num_to_ignore */,
+            trim_ts);
+        final_output_level = first_overlapped_level;
+      } else {
+        assert(cfd->ioptions()->compaction_style == kCompactionStyleLevel);
+        uint64_t next_file_number = versions_->current_next_file_number();
+        // Start compaction from `first_overlapped_level`, one level down at a
+        // time, until output level >= max_overlapped_level.
+        // When max_overlapped_level == 0, we will still compact from L0 -> L1
+        // (or LBase), and followed by a bottommost level intra-level compaction
+        // at L1 (or LBase), if applicable.
+        int level = first_overlapped_level;
+        final_output_level = level;
+        int output_level = 0, base_level = 0;
+        for (;;) {
+          // Always allow L0 -> L1 compaction
+          if (level > 0) {
+            if (cfd->ioptions()->level_compaction_dynamic_level_bytes) {
+              assert(final_output_level < cfd->ioptions()->num_levels);
+              if (final_output_level + 1 == cfd->ioptions()->num_levels) {
+                break;
+              }
+            } else {
+              // TODO(cbi): there is still a race condition here where
+              //  if a background compaction compacts some file beyond
+              //  current()->storage_info()->num_non_empty_levels() right after
+              //  the check here.This should happen very infrequently and should
+              //  not happen once a user populates the last level of the LSM.
+              InstrumentedMutexLock l(&mutex_);
+              // num_non_empty_levels may be lower after a compaction, so
+              // we check for >= here.
+              if (final_output_level + 1 >=
+                  cfd->current()->storage_info()->num_non_empty_levels()) {
+                break;
+              }
+            }
           }
-          output_level = level;
-          // update max_file_num_to_ignore only for bottom level compaction
-          // because data in newly compacted files in middle levels may still
-          // need to be pushed down
-          max_file_num_to_ignore = next_file_number;
-        } else {
           output_level = level + 1;
-          if (cfd->ioptions()->compaction_style == kCompactionStyleLevel &&
-              cfd->ioptions()->level_compaction_dynamic_level_bytes &&
+          if (cfd->ioptions()->level_compaction_dynamic_level_bytes &&
               level == 0) {
             output_level = ColumnFamilyData::kCompactToBaseLevel;
           }
-          // if it's a BottommostLevel compaction and `kForce*` compaction is
-          // set, disallow trivial move
-          if (level == max_overlapped_level &&
-              (options.bottommost_level_compaction ==
-                   BottommostLevelCompaction::kForce ||
-               options.bottommost_level_compaction ==
-                   BottommostLevelCompaction::kForceOptimized)) {
-            disallow_trivial_move = true;
+          // Use max value for `max_file_num_to_ignore` to always compact
+          // files down.
+          s = RunManualCompaction(
+              cfd, level, output_level, options, begin, end, exclusive,
+              !trim_ts.empty() /* disallow_trivial_move */,
+              std::numeric_limits<uint64_t>::max() /* max_file_num_to_ignore */,
+              trim_ts,
+              output_level == ColumnFamilyData::kCompactToBaseLevel
+                  ? &base_level
+                  : nullptr);
+          if (!s.ok()) {
+            break;
+          }
+          if (output_level == ColumnFamilyData::kCompactToBaseLevel) {
+            assert(base_level > 0);
+            level = base_level;
+          } else {
+            ++level;
+          }
+          final_output_level = level;
+          TEST_SYNC_POINT("DBImpl::RunManualCompaction()::1");
+          TEST_SYNC_POINT("DBImpl::RunManualCompaction()::2");
+        }
+        if (s.ok()) {
+          assert(final_output_level > 0);
+          // bottommost level intra-level compaction
+          if ((options.bottommost_level_compaction ==
+                   BottommostLevelCompaction::kIfHaveCompactionFilter &&
+               (cfd->ioptions()->compaction_filter != nullptr ||
+                cfd->ioptions()->compaction_filter_factory != nullptr)) ||
+              options.bottommost_level_compaction ==
+                  BottommostLevelCompaction::kForceOptimized ||
+              options.bottommost_level_compaction ==
+                  BottommostLevelCompaction::kForce) {
+            // Use `next_file_number` as `max_file_num_to_ignore` to avoid
+            // rewriting newly compacted files when it is kForceOptimized
+            // or kIfHaveCompactionFilter with compaction filter set.
+            s = RunManualCompaction(
+                cfd, final_output_level, final_output_level, options, begin,
+                end, exclusive, true /* disallow_trivial_move */,
+                next_file_number /* max_file_num_to_ignore */, trim_ts);
           }
         }
-        // trim_ts need real compaction to remove latest record
-        if (!trim_ts.empty()) {
-          disallow_trivial_move = true;
-        }
-        s = RunManualCompaction(cfd, level, output_level, options, begin, end,
-                                exclusive, disallow_trivial_move,
-                                max_file_num_to_ignore, trim_ts);
-        if (!s.ok()) {
-          break;
-        }
-        if (output_level == ColumnFamilyData::kCompactToBaseLevel) {
-          final_output_level = cfd->NumberLevels() - 1;
-        } else if (output_level > final_output_level) {
-          final_output_level = output_level;
-        }
-        TEST_SYNC_POINT("DBImpl::RunManualCompaction()::1");
-        TEST_SYNC_POINT("DBImpl::RunManualCompaction()::2");
       }
     }
   }
@@ -1357,6 +1386,14 @@ Status DBImpl::CompactFilesImpl(
     }
   }
 
+  if (cfd->ioptions()->allow_ingest_behind &&
+      output_level >= cfd->ioptions()->num_levels - 1) {
+    return Status::InvalidArgument(
+        "Exceed the maximum output level defined by "
+        "the current compaction algorithm with ingest_behind --- " +
+        std::to_string(cfd->ioptions()->num_levels - 1));
+  }
+
   Status s = cfd->compaction_picker()->SanitizeCompactionInputFiles(
       &input_set, cf_meta, output_level);
   TEST_SYNC_POINT("DBImpl::CompactFilesImpl::PostSanitizeCompactionInputFiles");
@@ -1630,6 +1667,8 @@ Status DBImpl::ReFitLevel(ColumnFamilyData* cfd, int level, int target_level) {
     return Status::InvalidArgument("Target level exceeds number of levels");
   }
 
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
+
   SuperVersionContext sv_context(/* create_superversion */ true);
 
   InstrumentedMutexLock guard_lock(&mutex_);
@@ -1738,14 +1777,16 @@ Status DBImpl::ReFitLevel(ColumnFamilyData* cfd, int level, int target_level) {
           f->marked_for_compaction, f->temperature, f->oldest_blob_file_number,
           f->oldest_ancester_time, f->file_creation_time, f->epoch_number,
           f->file_checksum, f->file_checksum_func_name, f->unique_id,
-          f->compensated_range_deletion_size);
+          f->compensated_range_deletion_size, f->tail_size,
+          f->user_defined_timestamps_persisted);
     }
     ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
                     "[%s] Apply version edit:\n%s", cfd->GetName().c_str(),
                     edit.DebugString().data());
 
-    Status status = versions_->LogAndApply(cfd, mutable_cf_options, &edit,
-                                           &mutex_, directories_.GetDbDir());
+    Status status =
+        versions_->LogAndApply(cfd, mutable_cf_options, read_options, &edit,
+                               &mutex_, directories_.GetDbDir());
 
     cfd->compaction_picker()->UnregisterCompaction(c.get());
     c.reset();
@@ -1787,6 +1828,37 @@ int DBImpl::Level0StopWriteTrigger(ColumnFamilyHandle* column_family) {
       ->mutable_cf_options.level0_stop_writes_trigger;
 }
 
+Status DBImpl::FlushAllColumnFamilies(const FlushOptions& flush_options,
+                                      FlushReason flush_reason) {
+  mutex_.AssertHeld();
+  Status status;
+  if (immutable_db_options_.atomic_flush) {
+    mutex_.Unlock();
+    status = AtomicFlushMemTables(flush_options, flush_reason);
+    if (status.IsColumnFamilyDropped()) {
+      status = Status::OK();
+    }
+    mutex_.Lock();
+  } else {
+    for (auto cfd : versions_->GetRefedColumnFamilySet()) {
+      if (cfd->IsDropped()) {
+        continue;
+      }
+      mutex_.Unlock();
+      status = FlushMemTable(cfd, flush_options, flush_reason);
+      TEST_SYNC_POINT("DBImpl::FlushAllColumnFamilies:1");
+      TEST_SYNC_POINT("DBImpl::FlushAllColumnFamilies:2");
+      mutex_.Lock();
+      if (!status.ok() && !status.IsColumnFamilyDropped()) {
+        break;
+      } else if (status.IsColumnFamilyDropped()) {
+        status = Status::OK();
+      }
+    }
+  }
+  return status;
+}
+
 Status DBImpl::Flush(const FlushOptions& flush_options,
                      ColumnFamilyHandle* column_family) {
   auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
@@ -1853,7 +1925,8 @@ Status DBImpl::RunManualCompaction(
     ColumnFamilyData* cfd, int input_level, int output_level,
     const CompactRangeOptions& compact_range_options, const Slice* begin,
     const Slice* end, bool exclusive, bool disallow_trivial_move,
-    uint64_t max_file_num_to_ignore, const std::string& trim_ts) {
+    uint64_t max_file_num_to_ignore, const std::string& trim_ts,
+    int* final_output_level) {
   assert(input_level == ColumnFamilyData::kCompactAllLevels ||
          input_level >= 0);
 
@@ -2004,6 +2077,15 @@ Status DBImpl::RunManualCompaction(
     } else if (!scheduled) {
       if (compaction == nullptr) {
         manual.done = true;
+        if (final_output_level) {
+          // No compaction needed or there is a conflicting compaction.
+          // Still set `final_output_level` to the level where we would
+          // have compacted to.
+          *final_output_level = output_level;
+          if (output_level == ColumnFamilyData::kCompactToBaseLevel) {
+            *final_output_level = cfd->current()->storage_info()->base_level();
+          }
+        }
         bg_cv_.SignalAll();
         continue;
       }
@@ -2037,6 +2119,9 @@ Status DBImpl::RunManualCompaction(
       }
       scheduled = true;
       TEST_SYNC_POINT("DBImpl::RunManualCompaction:Scheduled");
+      if (final_output_level) {
+        *final_output_level = compaction->output_level();
+      }
     }
   }
 
@@ -2578,6 +2663,9 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
       env_->GetBackgroundThreads(Env::Priority::HIGH) == 0;
   while (!is_flush_pool_empty && unscheduled_flushes_ > 0 &&
          bg_flush_scheduled_ < bg_job_limits.max_flushes) {
+    TEST_SYNC_POINT_CALLBACK(
+        "DBImpl::MaybeScheduleFlushOrCompaction:BeforeSchedule",
+        &unscheduled_flushes_);
     bg_flush_scheduled_++;
     FlushThreadArg* fta = new FlushThreadArg;
     fta->db_ = this;
@@ -2687,7 +2775,7 @@ ColumnFamilyData* DBImpl::PopFirstFromCompactionQueue() {
 
 DBImpl::FlushRequest DBImpl::PopFirstFromFlushQueue() {
   assert(!flush_queue_.empty());
-  FlushRequest flush_req = flush_queue_.front();
+  FlushRequest flush_req = std::move(flush_queue_.front());
   flush_queue_.pop_front();
   if (!immutable_db_options_.atomic_flush) {
     assert(flush_req.cfd_to_max_mem_id_to_persist.size() == 1);
@@ -2882,14 +2970,12 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
   autovector<ColumnFamilyData*> column_families_not_to_flush;
   while (!flush_queue_.empty()) {
     // This cfd is already referenced
-    const FlushRequest& flush_req = PopFirstFromFlushQueue();
-    FlushReason flush_reason = flush_req.flush_reason;
+    auto [flush_reason, cfd_to_max_mem_id_to_persist] =
+        PopFirstFromFlushQueue();
     superversion_contexts.clear();
-    superversion_contexts.reserve(
-        flush_req.cfd_to_max_mem_id_to_persist.size());
+    superversion_contexts.reserve(cfd_to_max_mem_id_to_persist.size());
 
-    for (const auto& iter : flush_req.cfd_to_max_mem_id_to_persist) {
-      ColumnFamilyData* cfd = iter.first;
+    for (const auto& [cfd, max_memtable_id] : cfd_to_max_mem_id_to_persist) {
       if (cfd->GetMempurgeUsed()) {
         // If imm() contains silent memtables (e.g.: because
         // MemPurge was activated), requesting a flush will
@@ -2903,7 +2989,7 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
         continue;
       }
       superversion_contexts.emplace_back(SuperVersionContext(true));
-      bg_flush_args.emplace_back(cfd, iter.second,
+      bg_flush_args.emplace_back(cfd, max_memtable_id,
                                  &(superversion_contexts.back()), flush_reason);
     }
     if (!bg_flush_args.empty()) {
@@ -3167,6 +3253,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
   mutex_.AssertHeld();
   TEST_SYNC_POINT("DBImpl::BackgroundCompaction:Start");
 
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
+
   bool is_manual = (manual_compaction != nullptr);
   std::unique_ptr<Compaction> c;
   if (prepicked_compaction != nullptr &&
@@ -3377,9 +3465,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     for (const auto& f : *c->inputs(0)) {
       c->edit()->DeleteFile(c->level(), f->fd.GetNumber());
     }
-    status = versions_->LogAndApply(c->column_family_data(),
-                                    *c->mutable_cf_options(), c->edit(),
-                                    &mutex_, directories_.GetDbDir());
+    status = versions_->LogAndApply(
+        c->column_family_data(), *c->mutable_cf_options(), read_options,
+        c->edit(), &mutex_, directories_.GetDbDir());
     io_s = versions_->io_status();
     InstallSuperVersionAndScheduleWork(c->column_family_data(),
                                        &job_context->superversion_contexts[0],
@@ -3396,9 +3484,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
                              c->column_family_data());
     // Instrument for event update
     // TODO(yhchiang): add op details for showing trivial-move.
-    ThreadStatusUtil::SetColumnFamily(
-        c->column_family_data(), c->column_family_data()->ioptions()->env,
-        immutable_db_options_.enable_thread_tracking);
+    ThreadStatusUtil::SetColumnFamily(c->column_family_data());
     ThreadStatusUtil::SetThreadOperation(ThreadStatus::OP_COMPACTION);
 
     compaction_job_stats.num_input_files = c->num_input_files(0);
@@ -3423,7 +3509,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
             f->oldest_blob_file_number, f->oldest_ancester_time,
             f->file_creation_time, f->epoch_number, f->file_checksum,
             f->file_checksum_func_name, f->unique_id,
-            f->compensated_range_deletion_size);
+            f->compensated_range_deletion_size, f->tail_size,
+            f->user_defined_timestamps_persisted);
 
         ROCKS_LOG_BUFFER(
             log_buffer,
@@ -3444,9 +3531,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
             vstorage->GetNextCompactCursor(start_level, c->num_input_files(0)));
       }
     }
-    status = versions_->LogAndApply(c->column_family_data(),
-                                    *c->mutable_cf_options(), c->edit(),
-                                    &mutex_, directories_.GetDbDir());
+    status = versions_->LogAndApply(
+        c->column_family_data(), *c->mutable_cf_options(), read_options,
+        c->edit(), &mutex_, directories_.GetDbDir());
     io_s = versions_->io_status();
     // Use latest MutableCFOptions
     InstallSuperVersionAndScheduleWork(c->column_family_data(),
@@ -3535,7 +3622,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     mutex_.Unlock();
     TEST_SYNC_POINT_CALLBACK(
         "DBImpl::BackgroundCompaction:NonTrivial:BeforeRun", nullptr);
-    // Should handle erorr?
+    // Should handle error?
     compaction_job.Run().PermitUncheckedError();
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
     mutex_.Lock();
@@ -3760,6 +3847,8 @@ void DBImpl::BuildCompactionJobInfo(
   compaction_job_info->table_properties = c->GetOutputTableProperties();
   compaction_job_info->compaction_reason = c->compaction_reason();
   compaction_job_info->compression = c->output_compression();
+
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
   for (size_t i = 0; i < c->num_input_levels(); ++i) {
     for (const auto fmd : *c->inputs(i)) {
       const FileDescriptor& desc = fmd->fd;
@@ -3771,7 +3860,7 @@ void DBImpl::BuildCompactionJobInfo(
           static_cast<int>(i), file_number, fmd->oldest_blob_file_number});
       if (compaction_job_info->table_properties.count(fn) == 0) {
         std::shared_ptr<const TableProperties> tp;
-        auto s = current->GetTableProperties(&tp, fmd, &fn);
+        auto s = current->GetTableProperties(read_options, &tp, fmd, &fn);
         if (s.ok()) {
           compaction_job_info->table_properties[fn] = tp;
         }
@@ -3921,16 +4010,33 @@ void DBImpl::GetSnapshotContext(
   *snapshot_seqs = snapshots_.GetAll(earliest_write_conflict_snapshot);
 }
 
-Status DBImpl::WaitForCompact(bool wait_unscheduled) {
-  // Wait until the compaction completes
+Status DBImpl::WaitForCompact(
+    const WaitForCompactOptions& wait_for_compact_options) {
   InstrumentedMutexLock l(&mutex_);
-  while ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
-          bg_flush_scheduled_ ||
-          (wait_unscheduled && unscheduled_compactions_)) &&
-         (error_handler_.GetBGError().ok())) {
-    bg_cv_.Wait();
+  if (wait_for_compact_options.flush) {
+    Status s = DBImpl::FlushAllColumnFamilies(FlushOptions(),
+                                              FlushReason::kManualFlush);
+    if (!s.ok()) {
+      return s;
+    }
+  }
+  TEST_SYNC_POINT("DBImpl::WaitForCompact:StartWaiting");
+  for (;;) {
+    if (shutting_down_.load(std::memory_order_acquire)) {
+      return Status::ShutdownInProgress();
+    }
+    if (bg_work_paused_ && wait_for_compact_options.abort_on_pause) {
+      return Status::Aborted();
+    }
+    if ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
+         bg_flush_scheduled_ || unscheduled_compactions_ ||
+         unscheduled_flushes_) &&
+        (error_handler_.GetBGError().ok())) {
+      bg_cv_.Wait();
+    } else {
+      return error_handler_.GetBGError();
+    }
   }
-  return error_handler_.GetBGError();
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db/db_impl/db_impl_debug.cc

@@ -178,9 +178,12 @@ Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
   return WaitForFlushMemTable(cfd, nullptr, false);
 }
 
-Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
-  // Wait until the compaction completes
-  return WaitForCompact(wait_unscheduled);
+Status DBImpl::TEST_WaitForCompact() {
+  return WaitForCompact(WaitForCompactOptions());
+}
+Status DBImpl::TEST_WaitForCompact(
+    const WaitForCompactOptions& wait_for_compact_options) {
+  return WaitForCompact(wait_for_compact_options);
 }
 
 Status DBImpl::TEST_WaitForPurge() {

db/db_impl/db_impl_experimental.cc

@@ -61,7 +61,8 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
                    "PromoteL0 FAILED. Invalid target level %d\n", target_level);
     return Status::InvalidArgument("Invalid target level");
   }
-
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   Status status;
   VersionEdit edit;
   JobContext job_context(next_job_id_.fetch_add(1), true);
@@ -137,11 +138,13 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
                    f->oldest_blob_file_number, f->oldest_ancester_time,
                    f->file_creation_time, f->epoch_number, f->file_checksum,
                    f->file_checksum_func_name, f->unique_id,
-                   f->compensated_range_deletion_size);
+                   f->compensated_range_deletion_size, f->tail_size,
+                   f->user_defined_timestamps_persisted);
     }
 
     status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
-                                    &edit, &mutex_, directories_.GetDbDir());
+                                    read_options, &edit, &mutex_,
+                                    directories_.GetDbDir());
     if (status.ok()) {
       InstallSuperVersionAndScheduleWork(cfd,
                                          &job_context.superversion_contexts[0],

db/db_impl/db_impl_files.cc

@@ -35,6 +35,11 @@ uint64_t DBImpl::MinObsoleteSstNumberToKeep() {
   return std::numeric_limits<uint64_t>::max();
 }
 
+uint64_t DBImpl::GetObsoleteSstFilesSize() {
+  mutex_.AssertHeld();
+  return versions_->GetObsoleteSstFilesSize();
+}
+
 Status DBImpl::DisableFileDeletions() {
   Status s;
   int my_disable_delete_obsolete_files;
@@ -286,6 +291,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     return;
   }
 
+  bool mutex_unlocked = false;
   if (!alive_log_files_.empty() && !logs_.empty()) {
     uint64_t min_log_number = job_context->log_number;
     size_t num_alive_log_files = alive_log_files_.size();
@@ -315,6 +321,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     }
     log_write_mutex_.Unlock();
     mutex_.Unlock();
+    mutex_unlocked = true;
     TEST_SYNC_POINT_CALLBACK("FindObsoleteFiles::PostMutexUnlock", nullptr);
     log_write_mutex_.Lock();
     while (!logs_.empty() && logs_.front().number < min_log_number) {
@@ -337,7 +344,9 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
 
   logs_to_free_.clear();
   log_write_mutex_.Unlock();
-  mutex_.Lock();
+  if (mutex_unlocked) {
+    mutex_.Lock();
+  }
   job_context->log_recycle_files.assign(log_recycle_files_.begin(),
                                         log_recycle_files_.end());
 }

db/db_impl/db_impl_open.cc

@@ -19,11 +19,13 @@
 #include "file/writable_file_writer.h"
 #include "logging/logging.h"
 #include "monitoring/persistent_stats_history.h"
+#include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
 #include "rocksdb/table.h"
 #include "rocksdb/wal_filter.h"
 #include "test_util/sync_point.h"
-#include "util/rate_limiter.h"
+#include "util/rate_limiter_impl.h"
+#include "util/udt_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 Options SanitizeOptions(const std::string& dbname, const Options& src,
@@ -533,6 +535,104 @@ Status DBImpl::Recover(
   if (!s.ok()) {
     return s;
   }
+  if (s.ok() && !read_only) {
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      // Try to trivially move files down the LSM tree to start from bottommost
+      // level when level_compaction_dynamic_level_bytes is enabled. This should
+      // only be useful when user is migrating to turning on this option.
+      // If a user is migrating from Level Compaction with a smaller level
+      // multiplier or from Universal Compaction, there may be too many
+      // non-empty levels and the trivial moves here are not sufficed for
+      // migration. Additional compactions are needed to drain unnecessary
+      // levels.
+      //
+      // Note that this step moves files down LSM without consulting
+      // SSTPartitioner. Further compactions are still needed if
+      // the user wants to partition SST files.
+      // Note that files moved in this step may not respect the compression
+      // option in target level.
+      if (cfd->ioptions()->compaction_style ==
+              CompactionStyle::kCompactionStyleLevel &&
+          cfd->ioptions()->level_compaction_dynamic_level_bytes &&
+          !cfd->GetLatestMutableCFOptions()->disable_auto_compactions) {
+        int to_level = cfd->ioptions()->num_levels - 1;
+        // last level is reserved
+        // allow_ingest_behind does not support Level Compaction,
+        // and per_key_placement can have infinite compaction loop for Level
+        // Compaction. Adjust to_level here just to be safe.
+        if (cfd->ioptions()->allow_ingest_behind ||
+            cfd->ioptions()->preclude_last_level_data_seconds > 0) {
+          to_level -= 1;
+        }
+        // Whether this column family has a level trivially moved
+        bool moved = false;
+        // Fill the LSM starting from to_level and going up one level at a time.
+        // Some loop invariants (when last level is not reserved):
+        // - levels in (from_level, to_level] are empty, and
+        // - levels in (to_level, last_level] are non-empty.
+        for (int from_level = to_level; from_level >= 0; --from_level) {
+          const std::vector<FileMetaData*>& level_files =
+              cfd->current()->storage_info()->LevelFiles(from_level);
+          if (level_files.empty() || from_level == 0) {
+            continue;
+          }
+          assert(from_level <= to_level);
+          // Trivial move files from `from_level` to `to_level`
+          if (from_level < to_level) {
+            if (!moved) {
+              // lsm_state will look like "[1,2,3,4,5,6,0]" for an LSM with
+              // 7 levels
+              std::string lsm_state = "[";
+              for (int i = 0; i < cfd->ioptions()->num_levels; ++i) {
+                lsm_state += std::to_string(
+                    cfd->current()->storage_info()->NumLevelFiles(i));
+                if (i < cfd->ioptions()->num_levels - 1) {
+                  lsm_state += ",";
+                }
+              }
+              lsm_state += "]";
+              ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                             "[%s] Trivially move files down the LSM when open "
+                             "with level_compaction_dynamic_level_bytes=true,"
+                             " lsm_state: %s (Files are moved only if DB "
+                             "Recovery is successful).",
+                             cfd->GetName().c_str(), lsm_state.c_str());
+              moved = true;
+            }
+            ROCKS_LOG_WARN(
+                immutable_db_options_.info_log,
+                "[%s] Moving %zu files from from_level-%d to from_level-%d",
+                cfd->GetName().c_str(), level_files.size(), from_level,
+                to_level);
+            VersionEdit edit;
+            edit.SetColumnFamily(cfd->GetID());
+            for (const FileMetaData* f : level_files) {
+              edit.DeleteFile(from_level, f->fd.GetNumber());
+              edit.AddFile(to_level, f->fd.GetNumber(), f->fd.GetPathId(),
+                           f->fd.GetFileSize(), f->smallest, f->largest,
+                           f->fd.smallest_seqno, f->fd.largest_seqno,
+                           f->marked_for_compaction,
+                           f->temperature,  // this can be different from
+                                            // `last_level_temperature`
+                           f->oldest_blob_file_number, f->oldest_ancester_time,
+                           f->file_creation_time, f->epoch_number,
+                           f->file_checksum, f->file_checksum_func_name,
+                           f->unique_id, f->compensated_range_deletion_size,
+                           f->tail_size, f->user_defined_timestamps_persisted);
+              ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                             "[%s] Moving #%" PRIu64
+                             " from from_level-%d to from_level-%d %" PRIu64
+                             " bytes\n",
+                             cfd->GetName().c_str(), f->fd.GetNumber(),
+                             from_level, to_level, f->fd.GetFileSize());
+            }
+            recovery_ctx->UpdateVersionEdits(cfd, edit);
+          }
+          --to_level;
+        }
+      }
+    }
+  }
   s = SetupDBId(read_only, recovery_ctx);
   ROCKS_LOG_INFO(immutable_db_options_.info_log, "DB ID: %s\n", db_id_.c_str());
   if (s.ok() && !read_only) {
@@ -826,8 +926,9 @@ Status DBImpl::InitPersistStatsColumnFamily() {
 Status DBImpl::LogAndApplyForRecovery(const RecoveryContext& recovery_ctx) {
   mutex_.AssertHeld();
   assert(versions_->descriptor_log_ == nullptr);
+  const ReadOptions read_options(Env::IOActivity::kDBOpen);
   Status s = versions_->LogAndApply(
-      recovery_ctx.cfds_, recovery_ctx.mutable_cf_opts_,
+      recovery_ctx.cfds_, recovery_ctx.mutable_cf_opts_, read_options,
       recovery_ctx.edit_lists_, &mutex_, directories_.GetDbDir());
   if (s.ok() && !(recovery_ctx.files_to_delete_.empty())) {
     mutex_.Unlock();
@@ -1086,6 +1187,9 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
     std::string scratch;
     Slice record;
 
+    const UnorderedMap<uint32_t, size_t>& running_ts_sz =
+        versions_->GetRunningColumnFamiliesTimestampSize();
+
     TEST_SYNC_POINT_CALLBACK("DBImpl::RecoverLogFiles:BeforeReadWal",
                              /*arg=*/nullptr);
     uint64_t record_checksum;
@@ -1108,6 +1212,17 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
       if (!status.ok()) {
         return status;
       }
+
+      const UnorderedMap<uint32_t, size_t>& record_ts_sz =
+          reader.GetRecordedTimestampSize();
+      // TODO(yuzhangyu): update mode to kReconcileInconsistency when user
+      // comparator can be changed.
+      status = HandleWriteBatchTimestampSizeDifference(
+          &batch, running_ts_sz, record_ts_sz,
+          TimestampSizeConsistencyMode::kVerifyConsistency);
+      if (!status.ok()) {
+        return status;
+      }
       TEST_SYNC_POINT_CALLBACK(
           "DBImpl::RecoverLogFiles:BeforeUpdateProtectionInfo:batch", &batch);
       TEST_SYNC_POINT_CALLBACK(
@@ -1354,7 +1469,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
         recovery_ctx->UpdateVersionEdits(cfd, iter->second);
       }
 
-      if (flushed) {
+      if (flushed || !data_seen) {
         VersionEdit wal_deletion;
         if (immutable_db_options_.track_and_verify_wals_in_manifest) {
           wal_deletion.DeleteWalsBefore(max_wal_number + 1);
@@ -1480,6 +1595,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
   meta.fd = FileDescriptor(versions_->NewFileNumber(), 0, 0);
   ReadOptions ro;
   ro.total_order_seek = true;
+  ro.io_activity = Env::IOActivity::kDBOpen;
   Arena arena;
   Status s;
   TableProperties table_properties;
@@ -1538,16 +1654,19 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       SeqnoToTimeMapping empty_seqno_time_mapping;
       Version* version = cfd->current();
       version->Ref();
+      const ReadOptions read_option(Env::IOActivity::kDBOpen);
+      uint64_t num_input_entries = 0;
       s = BuildTable(
           dbname_, versions_.get(), immutable_db_options_, tboptions,
-          file_options_for_compaction_, cfd->table_cache(), iter.get(),
-          std::move(range_del_iters), &meta, &blob_file_additions,
+          file_options_for_compaction_, read_option, cfd->table_cache(),
+          iter.get(), std::move(range_del_iters), &meta, &blob_file_additions,
           snapshot_seqs, earliest_write_conflict_snapshot, kMaxSequenceNumber,
           snapshot_checker, paranoid_file_checks, cfd->internal_stats(), &io_s,
           io_tracer_, BlobFileCreationReason::kRecovery,
           empty_seqno_time_mapping, &event_logger_, job_id, Env::IO_HIGH,
           nullptr /* table_properties */, write_hint,
-          nullptr /*full_history_ts_low*/, &blob_callback_, version);
+          nullptr /*full_history_ts_low*/, &blob_callback_, version,
+          &num_input_entries);
       version->Unref();
       LogFlush(immutable_db_options_.info_log);
       ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
@@ -1561,6 +1680,19 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       if (!io_s.ok() && s.ok()) {
         s = io_s;
       }
+
+      uint64_t total_num_entries = mem->num_entries();
+      if (s.ok() && total_num_entries != num_input_entries) {
+        std::string msg = "Expected " + std::to_string(total_num_entries) +
+                          " entries in memtable, but read " +
+                          std::to_string(num_input_entries);
+        ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                       "[%s] [JOB %d] Level-0 flush during recover: %s",
+                       cfd->GetName().c_str(), job_id, msg.c_str());
+        if (immutable_db_options_.flush_verify_memtable_count) {
+          s = Status::Corruption(msg);
+        }
+      }
     }
   }
   ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
@@ -1579,7 +1711,8 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                   meta.oldest_blob_file_number, meta.oldest_ancester_time,
                   meta.file_creation_time, meta.epoch_number,
                   meta.file_checksum, meta.file_checksum_func_name,
-                  meta.unique_id, meta.compensated_range_deletion_size);
+                  meta.unique_id, meta.compensated_range_deletion_size,
+                  meta.tail_size, meta.user_defined_timestamps_persisted);
 
     for (const auto& blob : blob_file_additions) {
       edit->AddBlobFile(blob);
@@ -1642,8 +1775,12 @@ Status DB::Open(const DBOptions& db_options, const std::string& dbname,
                 std::vector<ColumnFamilyHandle*>* handles, DB** dbptr) {
   const bool kSeqPerBatch = true;
   const bool kBatchPerTxn = true;
-  return DBImpl::Open(db_options, dbname, column_families, handles, dbptr,
-                      !kSeqPerBatch, kBatchPerTxn);
+  ThreadStatusUtil::SetEnableTracking(db_options.enable_thread_tracking);
+  ThreadStatusUtil::SetThreadOperation(ThreadStatus::OperationType::OP_DBOPEN);
+  Status s = DBImpl::Open(db_options, dbname, column_families, handles, dbptr,
+                          !kSeqPerBatch, kBatchPerTxn);
+  ThreadStatusUtil::ResetThreadStatus();
+  return s;
 }
 
 // TODO: Implement the trimming in flush code path.
@@ -1828,7 +1965,9 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
 
   // Handles create_if_missing, error_if_exists
   uint64_t recovered_seq(kMaxSequenceNumber);
-  s = impl->Recover(column_families, false, false, false, &recovered_seq,
+  s = impl->Recover(column_families, false /* read_only */,
+                    false /* error_if_wal_file_exists */,
+                    false /* error_if_data_exists_in_wals */, &recovered_seq,
                     &recovery_ctx);
   if (s.ok()) {
     uint64_t new_log_number = impl->versions_->NewFileNumber();

db/db_impl/db_impl_readonly.cc

@@ -40,8 +40,14 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
                            ColumnFamilyHandle* column_family, const Slice& key,
                            PinnableSlice* pinnable_val,
                            std::string* timestamp) {
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call Get with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
   assert(pinnable_val != nullptr);
-  // TODO: stopwatch DB_GET needed?, perf timer needed?
+  PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
+  StopWatch sw(immutable_db_options_.clock, stats_, DB_GET);
   PERF_TIMER_GUARD(get_snapshot_time);
 
   assert(column_family);
@@ -112,6 +118,11 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
 
 Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
                                       ColumnFamilyHandle* column_family) {
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return NewErrorIterator(Status::InvalidArgument(
+        "Cannot call NewIterator with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`"));
+  }
   assert(column_family);
   if (read_options.timestamp) {
     const Status s = FailIfTsMismatchCf(

db/db_impl/db_impl_readonly.h

@@ -142,6 +142,22 @@ class DBImplReadOnly : public DBImpl {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
 
+  virtual Status CreateColumnFamilyWithImport(
+      const ColumnFamilyOptions& /*options*/,
+      const std::string& /*column_family_name*/,
+      const ImportColumnFamilyOptions& /*import_options*/,
+      const std::vector<const ExportImportFilesMetaData*>& /*metadatas*/,
+      ColumnFamilyHandle** /*handle*/) override {
+    return Status::NotSupported("Not supported operation in read only mode.");
+  }
+
+  using DB::ClipColumnFamily;
+  virtual Status ClipColumnFamily(ColumnFamilyHandle* /*column_family*/,
+                                  const Slice& /*begin*/,
+                                  const Slice& /*end*/) override {
+    return Status::NotSupported("Not supported operation in read only mode.");
+  }
+
   // FIXME: some missing overrides for more "write" functions
 
  protected:

db/db_impl/db_impl_secondary.cc

@@ -14,6 +14,7 @@
 #include "monitoring/perf_context_imp.h"
 #include "rocksdb/configurable.h"
 #include "util/cast_util.h"
+#include "util/write_batch_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -197,6 +198,9 @@ Status DBImplSecondary::RecoverLogFiles(
     }
     assert(reader != nullptr);
   }
+
+  const UnorderedMap<uint32_t, size_t>& running_ts_sz =
+      versions_->GetRunningColumnFamiliesTimestampSize();
   for (auto log_number : log_numbers) {
     auto it = log_readers_.find(log_number);
     assert(it != log_readers_.end());
@@ -224,6 +228,14 @@ Status DBImplSecondary::RecoverLogFiles(
       if (!status.ok()) {
         break;
       }
+      const UnorderedMap<uint32_t, size_t>& record_ts_sz =
+          reader->GetRecordedTimestampSize();
+      status = HandleWriteBatchTimestampSizeDifference(
+          &batch, running_ts_sz, record_ts_sz,
+          TimestampSizeConsistencyMode::kVerifyConsistency);
+      if (!status.ok()) {
+        break;
+      }
       SequenceNumber seq_of_batch = WriteBatchInternal::Sequence(&batch);
       std::vector<uint32_t> column_family_ids;
       status = CollectColumnFamilyIdsFromWriteBatch(batch, &column_family_ids);
@@ -345,6 +357,11 @@ Status DBImplSecondary::GetImpl(const ReadOptions& read_options,
                                 ColumnFamilyHandle* column_family,
                                 const Slice& key, PinnableSlice* pinnable_val,
                                 std::string* timestamp) {
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call Get with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
   assert(pinnable_val != nullptr);
   PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
   StopWatch sw(immutable_db_options_.clock, stats_, DB_GET);
@@ -445,6 +462,11 @@ Iterator* DBImplSecondary::NewIterator(const ReadOptions& read_options,
     return NewErrorIterator(Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators."));
   }
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return NewErrorIterator(Status::InvalidArgument(
+        "Cannot call NewIterator with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`"));
+  }
 
   assert(column_family);
   if (read_options.timestamp) {
@@ -511,6 +533,11 @@ Status DBImplSecondary::NewIterators(
     return Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators.");
   }
+  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Cannot call NewIterators with `ReadOptions::io_activity` != "
+        "`Env::IOActivity::kUnknown`");
+  }
   ReadCallback* read_callback = nullptr;  // No read callback provided.
   if (iterators == nullptr) {
     return Status::InvalidArgument("iterators not allowed to be nullptr");

db/db_impl/db_impl_secondary.h

@@ -273,85 +273,6 @@ class DBImplSecondary : public DBImpl {
     return Status::OK();
   }
 
-  // ColumnFamilyCollector is a write batch handler which does nothing
-  // except recording unique column family IDs
-  class ColumnFamilyCollector : public WriteBatch::Handler {
-    std::unordered_set<uint32_t> column_family_ids_;
-
-    Status AddColumnFamilyId(uint32_t column_family_id) {
-      if (column_family_ids_.find(column_family_id) ==
-          column_family_ids_.end()) {
-        column_family_ids_.insert(column_family_id);
-      }
-      return Status::OK();
-    }
-
-   public:
-    explicit ColumnFamilyCollector() {}
-
-    ~ColumnFamilyCollector() override {}
-
-    Status PutCF(uint32_t column_family_id, const Slice&,
-                 const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status DeleteCF(uint32_t column_family_id, const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status SingleDeleteCF(uint32_t column_family_id, const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status DeleteRangeCF(uint32_t column_family_id, const Slice&,
-                         const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status MergeCF(uint32_t column_family_id, const Slice&,
-                   const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status PutBlobIndexCF(uint32_t column_family_id, const Slice&,
-                          const Slice&) override {
-      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 MarkCommitWithTimestamp(const Slice&, 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_;
-    }
-  };
-
-  Status CollectColumnFamilyIdsFromWriteBatch(
-      const WriteBatch& batch, std::vector<uint32_t>* column_family_ids) {
-    assert(column_family_ids != nullptr);
-    column_family_ids->clear();
-    ColumnFamilyCollector handler;
-    Status s = batch.Iterate(&handler);
-    if (s.ok()) {
-      for (const auto& cf : handler.column_families()) {
-        column_family_ids->push_back(cf);
-      }
-    }
-    return s;
-  }
-
   bool OwnTablesAndLogs() const override {
     // Currently, the secondary instance does not own the database files. It
     // simply opens the files of the primary instance and tracks their file

db/db_impl/db_impl_write.cc

@@ -606,7 +606,9 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
     log_write_mutex_.Unlock();
     if (status.ok() && synced_wals.IsWalAddition()) {
       InstrumentedMutexLock l(&mutex_);
-      status = ApplyWALToManifest(&synced_wals);
+      // TODO: plumb Env::IOActivity
+      const ReadOptions read_options;
+      status = ApplyWALToManifest(read_options, &synced_wals);
     }
 
     // Requesting sync with two_write_queues_ is expected to be very rare. We
@@ -767,7 +769,9 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
     }
     if (w.status.ok() && synced_wals.IsWalAddition()) {
       InstrumentedMutexLock l(&mutex_);
-      w.status = ApplyWALToManifest(&synced_wals);
+      // TODO: plumb Env::IOActivity
+      const ReadOptions read_options;
+      w.status = ApplyWALToManifest(read_options, &synced_wals);
     }
     write_thread_.ExitAsBatchGroupLeader(wal_write_group, w.status);
   }
@@ -1324,7 +1328,13 @@ IOStatus DBImpl::WriteToWAL(const WriteBatch& merged_batch,
   if (UNLIKELY(needs_locking)) {
     log_write_mutex_.Lock();
   }
-  IOStatus io_s = log_writer->AddRecord(log_entry, rate_limiter_priority);
+  IOStatus io_s = log_writer->MaybeAddUserDefinedTimestampSizeRecord(
+      versions_->GetColumnFamiliesTimestampSizeForRecord(),
+      rate_limiter_priority);
+  if (!io_s.ok()) {
+    return io_s;
+  }
+  io_s = log_writer->AddRecord(log_entry, rate_limiter_priority);
 
   if (UNLIKELY(needs_locking)) {
     log_write_mutex_.Unlock();
@@ -1805,7 +1815,7 @@ Status DBImpl::DelayWrite(uint64_t num_bytes, WriteThread& write_thread,
   bool delayed = false;
   {
     StopWatch sw(immutable_db_options_.clock, stats_, WRITE_STALL,
-                 &time_delayed);
+                 Histograms::HISTOGRAM_ENUM_MAX, &time_delayed);
     // To avoid parallel timed delays (bad throttling), only support them
     // on the primary write queue.
     uint64_t delay;
@@ -2086,6 +2096,8 @@ void DBImpl::NotifyOnMemTableSealed(ColumnFamilyData* /*cfd*/,
 // two_write_queues_ is true (This is to simplify the reasoning.)
 Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
   mutex_.AssertHeld();
+  // TODO: plumb Env::IOActivity
+  const ReadOptions read_options;
   log::Writer* new_log = nullptr;
   MemTable* new_mem = nullptr;
   IOStatus io_s;
@@ -2237,8 +2249,8 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
 
       VersionEdit wal_deletion;
       wal_deletion.DeleteWalsBefore(min_wal_number_to_keep);
-      s = versions_->LogAndApplyToDefaultColumnFamily(&wal_deletion, &mutex_,
-                                                      directories_.GetDbDir());
+      s = versions_->LogAndApplyToDefaultColumnFamily(
+          read_options, &wal_deletion, &mutex_, directories_.GetDbDir());
       if (!s.ok() && versions_->io_status().IsIOError()) {
         s = error_handler_.SetBGError(versions_->io_status(),
                                       BackgroundErrorReason::kManifestWrite);

db/db_iter.cc

@@ -131,6 +131,7 @@ void DBIter::Next() {
   assert(valid_);
   assert(status_.ok());
 
+  PERF_COUNTER_ADD(iter_next_count, 1);
   PERF_CPU_TIMER_GUARD(iter_next_cpu_nanos, clock_);
   // Release temporarily pinned blocks from last operation
   ReleaseTempPinnedData();
@@ -195,6 +196,7 @@ bool DBIter::SetBlobValueIfNeeded(const Slice& user_key,
 
   // TODO: consider moving ReadOptions from ArenaWrappedDBIter to DBIter to
   // avoid having to copy options back and forth.
+  // TODO: plumb Env::IOActivity
   ReadOptions read_options;
   read_options.read_tier = read_tier_;
   read_options.fill_cache = fill_cache_;
@@ -637,6 +639,7 @@ void DBIter::Prev() {
   assert(valid_);
   assert(status_.ok());
 
+  PERF_COUNTER_ADD(iter_prev_count, 1);
   PERF_CPU_TIMER_GUARD(iter_prev_cpu_nanos, clock_);
   ReleaseTempPinnedData();
   ResetBlobValue();
@@ -961,9 +964,6 @@ bool DBIter::FindValueForCurrentKey() {
     assert(last_key_entry_type == ikey_.type);
   }
 
-  Status s;
-  s.PermitUncheckedError();
-
   switch (last_key_entry_type) {
     case kTypeDeletion:
     case kTypeDeletionWithTimestamp:
@@ -1040,11 +1040,6 @@ bool DBIter::FindValueForCurrentKey() {
           std::to_string(static_cast<unsigned int>(last_key_entry_type)));
       return false;
   }
-  if (!s.ok()) {
-    valid_ = false;
-    status_ = s;
-    return false;
-  }
   valid_ = true;
   return true;
 }
@@ -1444,6 +1439,7 @@ void DBIter::SetSavedKeyToSeekForPrevTarget(const Slice& target) {
 }
 
 void DBIter::Seek(const Slice& target) {
+  PERF_COUNTER_ADD(iter_seek_count, 1);
   PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
   StopWatch sw(clock_, statistics_, DB_SEEK);
 
@@ -1517,6 +1513,7 @@ void DBIter::Seek(const Slice& target) {
 }
 
 void DBIter::SeekForPrev(const Slice& target) {
+  PERF_COUNTER_ADD(iter_seek_count, 1);
   PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
   StopWatch sw(clock_, statistics_, DB_SEEK);
 
@@ -1590,6 +1587,7 @@ void DBIter::SeekToFirst() {
     Seek(*iterate_lower_bound_);
     return;
   }
+  PERF_COUNTER_ADD(iter_seek_count, 1);
   PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
   // Don't use iter_::Seek() if we set a prefix extractor
   // because prefix seek will be used.
@@ -1652,6 +1650,7 @@ void DBIter::SeekToLast() {
     return;
   }
 
+  PERF_COUNTER_ADD(iter_seek_count, 1);
   PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
   // Don't use iter_::Seek() if we set a prefix extractor
   // because prefix seek will be used.

db/db_iterator_test.cc

@@ -16,7 +16,7 @@
 #include "port/stack_trace.h"
 #include "rocksdb/iostats_context.h"
 #include "rocksdb/perf_context.h"
-#include "table/block_based/flush_block_policy.h"
+#include "table/block_based/flush_block_policy_impl.h"
 #include "util/random.h"
 #include "utilities/merge_operators/string_append/stringappend2.h"
 
@@ -30,12 +30,63 @@ class DummyReadCallback : public ReadCallback {
   void SetSnapshot(SequenceNumber seq) { max_visible_seq_ = seq; }
 };
 
+class DBIteratorBaseTest : public DBTestBase {
+ public:
+  DBIteratorBaseTest()
+      : DBTestBase("db_iterator_test", /*env_do_fsync=*/true) {}
+};
+
+TEST_F(DBIteratorBaseTest, APICallsWithPerfContext) {
+  // Set up the DB
+  Options options = CurrentOptions();
+  DestroyAndReopen(options);
+  Random rnd(301);
+  for (int i = 1; i <= 3; i++) {
+    ASSERT_OK(Put(std::to_string(i), std::to_string(i)));
+  }
+
+  // Setup iterator and PerfContext
+  Iterator* iter = db_->NewIterator(ReadOptions());
+  std::string key_str = std::to_string(2);
+  Slice key(key_str);
+  SetPerfLevel(kEnableCount);
+  get_perf_context()->Reset();
+
+  // Initial PerfContext counters
+  ASSERT_EQ(0, get_perf_context()->iter_seek_count);
+  ASSERT_EQ(0, get_perf_context()->iter_next_count);
+  ASSERT_EQ(0, get_perf_context()->iter_prev_count);
+
+  // Test Seek-related API calls PerfContext counter
+  iter->Seek(key);
+  iter->SeekToFirst();
+  iter->SeekToLast();
+  iter->SeekForPrev(key);
+  ASSERT_EQ(4, get_perf_context()->iter_seek_count);
+  ASSERT_EQ(0, get_perf_context()->iter_next_count);
+  ASSERT_EQ(0, get_perf_context()->iter_prev_count);
+
+  // Test Next() calls PerfContext counter
+  iter->Next();
+  ASSERT_EQ(4, get_perf_context()->iter_seek_count);
+  ASSERT_EQ(1, get_perf_context()->iter_next_count);
+  ASSERT_EQ(0, get_perf_context()->iter_prev_count);
+
+  // Test Prev() calls PerfContext counter
+  iter->Prev();
+  ASSERT_EQ(4, get_perf_context()->iter_seek_count);
+  ASSERT_EQ(1, get_perf_context()->iter_next_count);
+  ASSERT_EQ(1, get_perf_context()->iter_prev_count);
+
+  delete iter;
+}
+
 // Test param:
 //   bool: whether to pass read_callback to NewIterator().
-class DBIteratorTest : public DBTestBase,
+class DBIteratorTest : public DBIteratorBaseTest,
                        public testing::WithParamInterface<bool> {
  public:
-  DBIteratorTest() : DBTestBase("db_iterator_test", /*env_do_fsync=*/true) {}
+  DBIteratorTest() {}
 
   Iterator* NewIterator(const ReadOptions& read_options,
                         ColumnFamilyHandle* column_family = nullptr) {

db/db_merge_operand_test.cc

@@ -49,10 +49,8 @@ TEST_F(DBMergeOperandTest, CacheEvictedMergeOperandReadAfterFreeBug) {
   // There was a bug of reading merge operands after they are mistakely freed
   // in DB::GetMergeOperands, which is surfaced by cache full.
   // See PR#9507 for more.
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   options.merge_operator = MergeOperators::CreateStringAppendOperator();
-  options.env = env_;
   BlockBasedTableOptions table_options;
 
   // Small cache to simulate cache full
@@ -121,11 +119,9 @@ TEST_F(DBMergeOperandTest, FlushedMergeOperandReadAfterFreeBug) {
 }
 
 TEST_F(DBMergeOperandTest, GetMergeOperandsBasic) {
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   // Use only the latest two merge operands.
   options.merge_operator = std::make_shared<LimitedStringAppendMergeOp>(2, ',');
-  options.env = env_;
   Reopen(options);
   int num_records = 4;
   int number_of_operands = 0;
@@ -309,13 +305,11 @@ TEST_F(DBMergeOperandTest, GetMergeOperandsBasic) {
 }
 
 TEST_F(DBMergeOperandTest, BlobDBGetMergeOperandsBasic) {
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   options.enable_blob_files = true;
   options.min_blob_size = 0;
   // Use only the latest two merge operands.
   options.merge_operator = std::make_shared<LimitedStringAppendMergeOp>(2, ',');
-  options.env = env_;
   Reopen(options);
   int num_records = 4;
   int number_of_operands = 0;
@@ -401,8 +395,7 @@ TEST_F(DBMergeOperandTest, GetMergeOperandsLargeResultOptimization) {
   const int kNumOperands = 1024;
   const int kOperandLen = 1024;
 
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   options.merge_operator = MergeOperators::CreateStringAppendOperator();
   DestroyAndReopen(options);