Update history and version for 10.2.3

Summary:
Remove the dependency on `allow_db_generated_files` option in `IngestExternalFile` to be set for ingesting external tables. The files are created by SstFileWriter, and we should be able to ingest them. We could make it work by having the external table implementation provide the version and global sequence number related properties, but its safer to have RocksDB generate the table properties block and store it as is in the file.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/13608

Test Plan: Add unit test to test basic ingestion and ingestion with atomic_replace_range

Reviewed By: pdillinger

Differential Revision: D74830707

Pulled By: anand1976

fbshipit-source-id: 4a9bea4a4f38f7c24c584262095c5c98cd771ddc

.github/actions/install-maven/action.yml

@@ -4,8 +4,8 @@ runs:
   steps:
   - name: Install Maven
     run: |
-      wget --no-check-certificate https://dlcdn.apache.org/maven/maven-3/3.9.10/binaries/apache-maven-3.9.10-bin.tar.gz
-      tar zxf apache-maven-3.9.10-bin.tar.gz
-      echo "export M2_HOME=$(pwd)/apache-maven-3.9.10" >> $GITHUB_ENV
-      echo "$(pwd)/apache-maven-3.9.10/bin" >> $GITHUB_PATH
+      wget --no-check-certificate https://dlcdn.apache.org/maven/maven-3/3.9.6/binaries/apache-maven-3.9.6-bin.tar.gz
+      tar zxf apache-maven-3.9.6-bin.tar.gz
+      echo "export M2_HOME=$(pwd)/apache-maven-3.9.6" >> $GITHUB_ENV
+      echo "$(pwd)/apache-maven-3.9.6/bin" >> $GITHUB_PATH
     shell: bash

.github/actions/windows-build-steps/action.yml

@@ -38,7 +38,7 @@ runs:
       $env:Path = $env:JAVA_HOME + ";" + $env:Path
       mkdir build
       cd build
-      & cmake -G "$Env:CMAKE_GENERATOR" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE="$Env:CMAKE_PORTABLE" -DSNAPPY=1 -DXPRESS=1 -DJNI=1 ..
+      & cmake -G "$Env:CMAKE_GENERATOR" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE="$Env:CMAKE_PORTABLE" -DSNAPPY=1 -DJNI=1 ..
       if(!$?) { Exit $LASTEXITCODE }
       cd ..
       echo "Building with VS version: $Env:CMAKE_GENERATOR"

.github/workflows/pr-jobs.yml

@@ -52,14 +52,6 @@ jobs:
       run: make check-buck-targets
     - name: Simple source code checks
       run: make check-sources
-    - name: Sanity check check_format_compatible.sh
-      run: |-
-        export TEST_TMPDIR=/dev/shm/rocksdb
-        rm -rf /dev/shm/rocksdb
-        mkdir /dev/shm/rocksdb
-        git reset --hard
-        git config --global --add safe.directory /__w/rocksdb/rocksdb
-        SANITY_CHECK=1 LONG_TEST=1 tools/check_format_compatible.sh
   # ========================= Linux With Tests ======================== #
   build-linux:
     if: ${{ github.repository_owner == 'facebook' }}

BUCK

@@ -249,7 +249,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "trace_replay/trace_record_result.cc",
         "trace_replay/trace_replay.cc",
         "util/async_file_reader.cc",
-        "util/auto_skip_compressor.cc",
         "util/build_version.cc",
         "util/cleanable.cc",
         "util/coding.cc",
@@ -268,7 +267,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "util/random.cc",
         "util/rate_limiter.cc",
         "util/ribbon_config.cc",
-        "util/simple_mixed_compressor.cc",
         "util/slice.cc",
         "util/status.cc",
         "util/stderr_logger.cc",
@@ -4711,12 +4709,6 @@ cpp_unittest_wrapper(name="compressed_secondary_cache_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="compression_test",
-            srcs=["util/compression_test.cc"],
-            deps=[":rocksdb_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="configurable_test",
             srcs=["options/configurable_test.cc"],
             deps=[":rocksdb_test_lib"],

CMakeLists.txt

@@ -874,13 +874,11 @@ set(SOURCES
         trace_replay/trace_record.cc
         trace_replay/trace_replay.cc
         util/async_file_reader.cc
-        util/auto_skip_compressor.cc
         util/cleanable.cc
         util/coding.cc
         util/compaction_job_stats_impl.cc
         util/comparator.cc
         util/compression.cc
-        util/simple_mixed_compressor.cc
         util/compression_context_cache.cc
         util/concurrent_task_limiter_impl.cc
         util/crc32c.cc
@@ -1458,7 +1456,6 @@ if(WITH_TESTS)
         util/autovector_test.cc
         util/bloom_test.cc
         util/coding_test.cc
-        util/compression_test.cc
         util/crc32c_test.cc
         util/defer_test.cc
         util/dynamic_bloom_test.cc

HISTORY.md

@@ -1,37 +1,16 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
-## 10.4.0 (06/20/2025)
-### New Features
-* Add a new CF option `memtable_avg_op_scan_flush_trigger` that supports triggering memtable flush when an iterator scans through an expensive range of keys, with the average number of skipped keys from the active memtable exceeding the threshold.
-* Vector based memtable now supports concurrent writers (DBOptions::allow_concurrent_memtable_write) #13675.
-* Add new experimental `TransactionOptions::large_txn_commit_optimize_byte_threshold` to enable optimizations for large transaction commit by transaction batch data size.
-* Add a new option `CompactionOptionsUniversal::reduce_file_locking` and if it's true, auto universal compaction picking will adjust to minimize locking of input files when bottom priority compactions are waiting to run. This can increase the likelihood of existing L0s being selected for compaction, thereby improving write stall and reducing read regression.
-
-### Public API Changes
-* Change NewExternalTableFactory to return a unique_ptr instead of shared_ptr.
-* Add an optional min file size requirement for deletion triggered compaction. It can be specified when creating `CompactOnDeletionCollectorFactory`.
-
-### Behavior Changes
-* `TransactionOptions::large_txn_commit_optimize_threshold` now has default value 0 for disabled. `TransactionDBOptions::txn_commit_bypass_memtable_threshold` now has no effect on transactions.
+## 10.2.3 (05/19/2025)
+* Fix a failure in IngestExternalFiles() when ingesting an external table with the allow_db_generated_files option set to false.
 
+## 10.2.2 (05/08/2025)
 ### Bug Fixes
-* Fix a bug where CreateColumnFamilyWithImport() could miss the SST file for the memtable flush it triggered. The exported CF then may not contain the updates in the memtable when CreateColumnFamilyWithImport() is called.
-* Fix iterator operations returning NotImplemented status if disallow_memtable_writes and paranoid_memory_checks CF options are both set.
-* Fixed handling of file checksums in IngestExternalFile() to allow providing checksums using recognized but not necessarily the DB's preferred checksum function, to ease migration between checksum functions.
-
-## 10.3.0 (05/17/2025)
-### New Features
-* Add new experimental `CompactionOptionsFIFO::allow_trivial_copy_when_change_temperature` along with `CompactionOptionsFIFO::trivial_copy_buffer_size` to allow optimizing FIFO compactions with tiering when kChangeTemperature to move files from source tier FileSystem to another tier FileSystem via trivial and direct copying raw sst file instead of reading thru the content of the SST file then rebuilding the table files.
-* Add a new field to Compaction Stats in LOG files for the pre-compression size written to each level.
-* Add new experimental `TransactionOptions::large_txn_commit_optimize_threshold` to enable optimizations for large transaction commit with per transaction threshold. `TransactionDBOptions::txn_commit_bypass_memtable_threshold` is deprecated in favor of this transaction option.
-* [internal team use only] Allow an application-defined `request_id` to be passed to RocksDB and propagated to the filesystem via IODebugContext
-
-### Bug Fixes
-* Fix a bug where transaction lock upgrade can incorrectly fail with a Deadlock status. This happens when a transaction has a non-zero timeout and tries to upgrade a shared lock that is also held by another transaction.
 * Pass wrapped WritableFileWriter pointer to ExternalTableBuilder so that the file checksum can be correctly calculated and returned by SstFileWriter for external table files.
-* Fix an infinite-loop bug in transaction locking. This can happen if a transaction reaches lock limit and its time out expires before it attempts to wait for it.
-* Fixed a potential data race with `CompressionOptions::parallel_threads > 1` and a `TablePropertiesCollector` overriding `BlockAdd()`.
+
+## 10.2.1 (04/24/2025)
+### Bug Fixes
+* Fix improper initialization of ExternalTableOptions
 
 ## 10.2.0 (04/21/2025)
 ### New Features

Makefile

@@ -1491,9 +1491,6 @@ db_test: $(OBJ_DIR)/db/db_test.o $(TEST_LIBRARY) $(LIBRARY)
 db_test2: $(OBJ_DIR)/db/db_test2.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-compression_test: $(OBJ_DIR)/util/compression_test.o $(TEST_LIBRARY) $(LIBRARY)
-	$(AM_LINK)
-
 db_logical_block_size_cache_test: $(OBJ_DIR)/db/db_logical_block_size_cache_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -2492,13 +2489,11 @@ checkout_folly:
 	fi
 	@# Pin to a particular version for public CI, so that PR authors don't
 	@# need to worry about folly breaking our integration. Update periodically
-	cd third-party/folly && git reset --hard d17bf897cb5bbf8f07b122a614e8cffdc38edcde
-	@# Apparently missing include
-	perl -pi -e 's/(#include <atomic>)/$$1\n#include <cstring>/' third-party/folly/folly/lang/Exception.h
-	@# Warning-as-error on memcpy
-	perl -pi -e 's/memcpy.&ptr/memcpy((void*)&ptr/' third-party/folly/folly/lang/Exception.cpp
-	@# const mismatch
-	perl -pi -e 's/: environ/: (const char**)(environ)/' third-party/folly/folly/Subprocess.cpp
+	cd third-party/folly && git reset --hard 78286282478e1ae05b2e8cbcf0e2139eab283bea
+	@# NOTE: this hack is required for clang in some cases
+	perl -pi -e 's/int rv = syscall/int rv = (int)syscall/' third-party/folly/folly/detail/Futex.cpp
+	@# NOTE: this hack is required for gcc in some cases
+	perl -pi -e 's/(__has_include.<experimental.memory_resource>.)/__cpp_rtti && $$1/' third-party/folly/folly/memory/MemoryResource.h
 	@# NOTE: boost source will be needed for any build including `USE_FOLLY_LITE` builds as those depend on boost headers
 	cd third-party/folly && $(PYTHON) build/fbcode_builder/getdeps.py fetch boost
 

build_tools/format-diff.sh

@@ -118,9 +118,6 @@ fi
 # fi
 set -e
 
-# Exclude third-party from formatting
-EXCLUDE=':!third-party/'
-
 uncommitted_code=`git diff HEAD`
 
 # If there's no uncommitted changes, we assume user are doing post-commit
@@ -140,11 +137,11 @@ then
   # should be relevant for formatting fixes.
   FORMAT_UPSTREAM_MERGE_BASE="$(git merge-base "$FORMAT_UPSTREAM" HEAD)"
   # Get the differences
-  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" -- $EXCLUDE | $CLANG_FORMAT_DIFF -p 1) || true
+  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1) || true
   echo "Checking format of changes not yet in $FORMAT_UPSTREAM..."
 else
   # Check the format of uncommitted lines,
-  diffs=$(git diff -U0 HEAD -- $EXCLUDE | $CLANG_FORMAT_DIFF -p 1) || true
+  diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1) || true
   echo "Checking format of uncommitted changes..."
 fi
 
@@ -190,9 +187,9 @@ fi
 # Do in-place format adjustment.
 if [ -z "$uncommitted_code" ]
 then
-  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" -- $EXCLUDE | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -i -p 1
 else
-  git diff -U0 HEAD -- $EXCLUDE | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 HEAD | $CLANG_FORMAT_DIFF -i -p 1
 fi
 echo "Files reformatted!"
 

cache/compressed_secondary_cache.cc

@@ -24,14 +24,7 @@ CompressedSecondaryCache::CompressedSecondaryCache(
       cache_res_mgr_(std::make_shared<ConcurrentCacheReservationManager>(
           std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
               cache_))),
-      disable_cache_(opts.capacity == 0) {
-  auto mgr =
-      GetBuiltinCompressionManager(cache_options_.compress_format_version);
-  compressor_ = mgr->GetCompressor(cache_options_.compression_opts,
-                                   cache_options_.compression_type);
-  decompressor_ =
-      mgr->GetDecompressorOptimizeFor(cache_options_.compression_type);
-}
+      disable_cache_(opts.capacity == 0) {}
 
 CompressedSecondaryCache::~CompressedSecondaryCache() = default;
 
@@ -104,24 +97,25 @@ std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
                             kNoCompression, CacheTier::kVolatileTier,
                             create_context, allocator, &value, &charge);
     } else {
-      // TODO: can we work some magic with create_cb, which might be based on
-      // custom compression, to decompress without an extra copy in create_cb?
-      Decompressor::Args args;
-      args.compressed_data = Slice(data_ptr, handle_value_charge);
-      args.compression_type = cache_options_.compression_type;
-      s = decompressor_->ExtractUncompressedSize(args);
-      assert(s.ok());
-      if (s.ok()) {
-        auto uncompressed = std::make_unique<char[]>(args.uncompressed_size);
-        s = decompressor_->DecompressBlock(args, uncompressed.get());
-        assert(s.ok());
-        if (s.ok()) {
-          s = helper->create_cb(
-              Slice(uncompressed.get(), args.uncompressed_size), kNoCompression,
-              CacheTier::kVolatileTier, create_context, allocator, &value,
-              &charge);
-        }
+      UncompressionContext uncompression_context(
+          cache_options_.compression_type);
+      UncompressionInfo uncompression_info(uncompression_context,
+                                           UncompressionDict::GetEmptyDict(),
+                                           cache_options_.compression_type);
+
+      size_t uncompressed_size{0};
+      CacheAllocationPtr uncompressed =
+          UncompressData(uncompression_info, (char*)data_ptr,
+                         handle_value_charge, &uncompressed_size,
+                         cache_options_.compress_format_version, allocator);
+
+      if (!uncompressed) {
+        cache_->Release(lru_handle, /*erase_if_last_ref=*/true);
+        return nullptr;
       }
+      s = helper->create_cb(Slice(uncompressed.get(), uncompressed_size),
+                            kNoCompression, CacheTier::kVolatileTier,
+                            create_context, allocator, &value, &charge);
     }
   } else {
     // The item was not compressed by us. Let the helper create_cb
@@ -204,17 +198,20 @@ Status CompressedSecondaryCache::InsertInternal(
       type == kNoCompression &&
       !cache_options_.do_not_compress_roles.Contains(helper->role)) {
     PERF_COUNTER_ADD(compressed_sec_cache_uncompressed_bytes, data_size);
+    CompressionContext compression_context(cache_options_.compression_type,
+                                           cache_options_.compression_opts);
+    uint64_t sample_for_compression{0};
+    CompressionInfo compression_info(
+        cache_options_.compression_opts, compression_context,
+        CompressionDict::GetEmptyDict(), cache_options_.compression_type,
+        sample_for_compression);
 
-    CompressionType to_type = kNoCompression;
-    s = compressor_->CompressBlock(val, &compressed_val, &to_type,
-                                   nullptr /*working_area*/);
-    if (!s.ok()) {
-      return s;
-    }
-    // TODO: allow values not compressed when there's no size savings?
-    assert(to_type == cache_options_.compression_type);
-    if (to_type != cache_options_.compression_type) {
-      return Status::Corruption("Failed to compress value.");
+    bool success =
+        CompressData(val, compression_info,
+                     cache_options_.compress_format_version, &compressed_val);
+
+    if (!success) {
+      return Status::Corruption("Error compressing value.");
     }
 
     val = Slice(compressed_val);

cache/compressed_secondary_cache.h

@@ -145,8 +145,6 @@ class CompressedSecondaryCache : public SecondaryCache {
   const Cache::CacheItemHelper* GetHelper(bool enable_custom_split_merge) const;
   std::shared_ptr<Cache> cache_;
   CompressedSecondaryCacheOptions cache_options_;
-  std::unique_ptr<Compressor> compressor_;
-  std::shared_ptr<Decompressor> decompressor_;
   mutable port::Mutex capacity_mutex_;
   std::shared_ptr<ConcurrentCacheReservationManager> cache_res_mgr_;
   bool disable_cache_;

cache/secondary_cache_adapter.cc

@@ -121,17 +121,7 @@ CacheWithSecondaryAdapter::~CacheWithSecondaryAdapter() {
     assert(s.ok());
     assert(placeholder_usage_ == 0);
     assert(reserved_usage_ == 0);
-    bool pri_cache_res_mismatch =
-        pri_cache_res_->GetTotalMemoryUsed() != sec_capacity;
-    if (pri_cache_res_mismatch) {
-      fprintf(stderr,
-              "~CacheWithSecondaryAdapter: Primary cache reservation: "
-              "%zu, Secondary cache capacity: %zu, "
-              "Secondary cache reserved: %zu\n",
-              pri_cache_res_->GetTotalMemoryUsed(), sec_capacity,
-              sec_reserved_);
-      assert(pri_cache_res_mismatch);
-    }
+    assert(pri_cache_res_->GetTotalMemoryUsed() == sec_capacity);
   }
 #endif  // NDEBUG
 }

db/arena_wrapped_db_iter.cc

@@ -55,7 +55,7 @@ void ArenaWrappedDBIter::Init(
   db_iter_ = DBIter::NewIter(
       env, read_options_, ioptions, mutable_cf_options,
       ioptions.user_comparator, /*internal_iter=*/nullptr, version, sequence,
-      read_callback, active_mem, cfh, expose_blob_index, &arena_);
+      read_callback, cfh, expose_blob_index, active_mem, &arena_);
 
   sv_number_ = version_number;
   allow_refresh_ = allow_refresh;

db/blob/blob_file_builder.cc

@@ -267,9 +267,10 @@ Status BlobFileBuilder::CompressBlobIfNeeded(
   // TODO: allow user CompressionOptions, including max_compressed_bytes_per_kb
   CompressionOptions opts;
   CompressionContext context(blob_compression_type_, opts);
+  constexpr uint64_t sample_for_compression = 0;
 
   CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
-                       blob_compression_type_);
+                       blob_compression_type_, sample_for_compression);
 
   constexpr uint32_t compression_format_version = 2;
 
@@ -278,8 +279,8 @@ Status BlobFileBuilder::CompressBlobIfNeeded(
   {
     StopWatch stop_watch(immutable_options_->clock, immutable_options_->stats,
                          BLOB_DB_COMPRESSION_MICROS);
-    success = OLD_CompressData(*blob, info, compression_format_version,
-                               compressed_blob);
+    success =
+        CompressData(*blob, info, compression_format_version, compressed_blob);
   }
 
   if (!success) {

db/blob/blob_file_builder_test.cc

@@ -405,9 +405,10 @@ TEST_F(BlobFileBuilderTest, Compression) {
 
   CompressionOptions opts;
   CompressionContext context(kSnappyCompression, opts);
+  constexpr uint64_t sample_for_compression = 0;
 
   CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
-                       kSnappyCompression);
+                       kSnappyCompression, sample_for_compression);
 
   std::string compressed_value;
   ASSERT_TRUE(Snappy_Compress(info, uncompressed_value.data(),

db/blob/blob_file_meta.h

@@ -6,7 +6,6 @@
 #pragma once
 
 #include <cassert>
-#include <cstdint>
 #include <iosfwd>
 #include <memory>
 #include <string>

db/blob/blob_file_reader.cc

@@ -250,8 +250,7 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
   Status s;
 
   IOOptions io_options;
-  IODebugContext dbg;
-  s = file_reader->PrepareIOOptions(read_options, io_options, &dbg);
+  s = file_reader->PrepareIOOptions(read_options, io_options);
   if (!s.ok()) {
     return s;
   }
@@ -260,13 +259,13 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
     constexpr char* scratch = nullptr;
 
     s = file_reader->Read(io_options, read_offset, read_size, slice, scratch,
-                          aligned_buf, &dbg);
+                          aligned_buf);
   } else {
     buf->reset(new char[read_size]);
     constexpr AlignedBuf* aligned_scratch = nullptr;
 
     s = file_reader->Read(io_options, read_offset, read_size, slice, buf->get(),
-                          aligned_scratch, &dbg);
+                          aligned_scratch);
   }
 
   if (!s.ok()) {
@@ -335,8 +334,7 @@ Status BlobFileReader::GetBlob(
     constexpr bool for_compaction = true;
 
     IOOptions io_options;
-    IODebugContext dbg;
-    s = file_reader_->PrepareIOOptions(read_options, io_options, &dbg);
+    s = file_reader_->PrepareIOOptions(read_options, io_options);
     if (!s.ok()) {
       return s;
     }
@@ -465,11 +463,10 @@ void BlobFileReader::MultiGetBlob(
   PERF_COUNTER_ADD(blob_read_count, num_blobs);
   PERF_COUNTER_ADD(blob_read_byte, total_len);
   IOOptions opts;
-  IODebugContext dbg;
-  s = file_reader_->PrepareIOOptions(read_options, opts, &dbg);
+  s = file_reader_->PrepareIOOptions(read_options, opts);
   if (s.ok()) {
     s = file_reader_->MultiRead(opts, read_reqs.data(), read_reqs.size(),
-                                direct_io ? &aligned_buf : nullptr, &dbg);
+                                direct_io ? &aligned_buf : nullptr);
   }
   if (!s.ok()) {
     for (auto& req : read_reqs) {
@@ -605,9 +602,9 @@ Status BlobFileReader::UncompressBlobIfNeeded(
   {
     PERF_TIMER_GUARD(blob_decompress_time);
     StopWatch stop_watch(clock, statistics, BLOB_DB_DECOMPRESSION_MICROS);
-    output = OLD_UncompressData(info, value_slice.data(), value_slice.size(),
-                                &uncompressed_size, compression_format_version,
-                                allocator);
+    output = UncompressData(info, value_slice.data(), value_slice.size(),
+                            &uncompressed_size, compression_format_version,
+                            allocator);
   }
 
   TEST_SYNC_POINT_CALLBACK(

db/blob/blob_file_reader_test.cc

@@ -75,14 +75,15 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
   } else {
     CompressionOptions opts;
     CompressionContext context(compression, opts);
+    constexpr uint64_t sample_for_compression = 0;
     CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
-                         compression);
+                         compression, sample_for_compression);
 
     constexpr uint32_t compression_format_version = 2;
 
     for (size_t i = 0; i < num; ++i) {
-      ASSERT_TRUE(OLD_CompressData(blobs[i], info, compression_format_version,
-                                   &compressed_blobs[i]));
+      ASSERT_TRUE(CompressData(blobs[i], info, compression_format_version,
+                               &compressed_blobs[i]));
       blobs_to_write[i] = compressed_blobs[i];
       blob_sizes[i] = compressed_blobs[i].size();
     }

db/blob/blob_source_test.cc

@@ -77,14 +77,15 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
   } else {
     CompressionOptions opts;
     CompressionContext context(compression, opts);
+    constexpr uint64_t sample_for_compression = 0;
     CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
-                         compression);
+                         compression, sample_for_compression);
 
     constexpr uint32_t compression_format_version = 2;
 
     for (size_t i = 0; i < num; ++i) {
-      ASSERT_TRUE(OLD_CompressData(blobs[i], info, compression_format_version,
-                                   &compressed_blobs[i]));
+      ASSERT_TRUE(CompressData(blobs[i], info, compression_format_version,
+                               &compressed_blobs[i]));
       blobs_to_write[i] = compressed_blobs[i];
       blob_sizes[i] = compressed_blobs[i].size();
     }

db/builder.cc

@@ -74,8 +74,8 @@ Status BuildTable(
     EventLogger* event_logger, int job_id, TableProperties* table_properties,
     Env::WriteLifeTimeHint write_hint, const std::string* full_history_ts_low,
     BlobFileCompletionCallback* blob_callback, Version* version,
-    uint64_t* memtable_payload_bytes, uint64_t* memtable_garbage_bytes,
-    InternalStats::CompactionStats* flush_stats) {
+    uint64_t* num_input_entries, uint64_t* memtable_payload_bytes,
+    uint64_t* memtable_garbage_bytes) {
   assert((tboptions.column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          tboptions.column_family_name.empty());
@@ -218,7 +218,8 @@ Status BuildTable(
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
       ParsedInternalKey ikey = c_iter.ikey();
-      Slice key_after_flush = key;
+      key_after_flush_buf.assign(key.data(), key.size());
+      Slice key_after_flush = key_after_flush_buf;
       Slice value_after_flush = value;
 
       if (ikey.type == kTypeValuePreferredSeqno) {
@@ -236,7 +237,6 @@ Status BuildTable(
               std::min(smallest_preferred_seqno, preferred_seqno);
         } else {
           // Cannot get a useful preferred seqno, convert it to a kTypeValue.
-          key_after_flush_buf.assign(key.data(), key.size());
           UpdateInternalKey(&key_after_flush_buf, ikey.sequence, kTypeValue);
           ikey = ParsedInternalKey(ikey.user_key, ikey.sequence, kTypeValue);
           key_after_flush = key_after_flush_buf;
@@ -253,10 +253,6 @@ Status BuildTable(
       }
       builder->Add(key_after_flush, value_after_flush);
 
-      if (flush_stats) {
-        flush_stats->num_output_records++;
-      }
-
       s = meta->UpdateBoundaries(key_after_flush, value_after_flush,
                                  ikey.sequence, ikey.type);
       if (!s.ok()) {
@@ -288,9 +284,6 @@ Status BuildTable(
         auto tombstone = range_del_it->Tombstone();
         std::pair<InternalKey, Slice> kv = tombstone.Serialize();
         builder->Add(kv.first.Encode(), kv.second);
-        if (flush_stats) {
-          flush_stats->num_output_records++;
-        }
         InternalKey tombstone_end = tombstone.SerializeEndKey();
         meta->UpdateBoundariesForRange(kv.first, tombstone_end, tombstone.seq_,
                                        tboptions.internal_comparator);
@@ -312,9 +305,9 @@ Status BuildTable(
 
     TEST_SYNC_POINT("BuildTable:BeforeFinishBuildTable");
     const bool empty = builder->IsEmpty();
-    if (flush_stats) {
+    if (num_input_entries != nullptr) {
       assert(c_iter.HasNumInputEntryScanned());
-      flush_stats->num_input_records =
+      *num_input_entries =
           c_iter.NumInputEntryScanned() + num_unfragmented_tombstones;
     }
     if (!s.ok() || empty) {
@@ -341,9 +334,6 @@ Status BuildTable(
     }
 
     if (s.ok() && !empty) {
-      if (flush_stats) {
-        flush_stats->bytes_written_pre_comp = builder->PreCompressionSize();
-      }
       uint64_t file_size = builder->FileSize();
       meta->fd.file_size = file_size;
       meta->tail_size = builder->GetTailSize();

db/builder.h

@@ -10,7 +10,6 @@
 #include <utility>
 #include <vector>
 
-#include "db/internal_stats.h"
 #include "db/range_tombstone_fragmenter.h"
 #include "db/seqno_to_time_mapping.h"
 #include "db/table_properties_collector.h"
@@ -35,6 +34,7 @@ class SnapshotChecker;
 class TableCache;
 class TableBuilder;
 class WritableFileWriter;
+class InternalStats;
 class BlobFileCompletionCallback;
 
 // Convenience function for NewTableBuilder on the embedded table_factory.
@@ -49,7 +49,6 @@ TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
 //
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown.
-// @param flush_stats treat flush as level 0 compaction in internal stats
 Status BuildTable(
     const std::string& dbname, VersionSet* versions,
     const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
@@ -70,8 +69,8 @@ Status BuildTable(
     Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
     const std::string* full_history_ts_low = nullptr,
     BlobFileCompletionCallback* blob_callback = nullptr,
-    Version* version = nullptr, uint64_t* memtable_payload_bytes = nullptr,
-    uint64_t* memtable_garbage_bytes = nullptr,
-    InternalStats::CompactionStats* flush_stats = nullptr);
+    Version* version = nullptr, uint64_t* num_input_entries = nullptr,
+    uint64_t* memtable_payload_bytes = nullptr,
+    uint64_t* memtable_garbage_bytes = nullptr);
 
 }  // namespace ROCKSDB_NAMESPACE

db/c.cc

@@ -24,14 +24,12 @@
 #include "rocksdb/experimental.h"
 #include "rocksdb/filter_policy.h"
 #include "rocksdb/iterator.h"
-#include "rocksdb/listener.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/merge_operator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/perf_context.h"
 #include "rocksdb/rate_limiter.h"
 #include "rocksdb/slice_transform.h"
-#include "rocksdb/sst_file_manager.h"
 #include "rocksdb/statistics.h"
 #include "rocksdb/status.h"
 #include "rocksdb/table.h"
@@ -51,7 +49,6 @@
 #include "util/stderr_logger.h"
 #include "utilities/merge_operators.h"
 
-using ROCKSDB_NAMESPACE::BackgroundErrorReason;
 using ROCKSDB_NAMESPACE::BackupEngine;
 using ROCKSDB_NAMESPACE::BackupEngineOptions;
 using ROCKSDB_NAMESPACE::BackupID;
@@ -68,9 +65,7 @@ using ROCKSDB_NAMESPACE::ColumnFamilyMetaData;
 using ROCKSDB_NAMESPACE::ColumnFamilyOptions;
 using ROCKSDB_NAMESPACE::CompactionFilter;
 using ROCKSDB_NAMESPACE::CompactionFilterFactory;
-using ROCKSDB_NAMESPACE::CompactionJobInfo;
 using ROCKSDB_NAMESPACE::CompactionOptionsFIFO;
-using ROCKSDB_NAMESPACE::CompactionReason;
 using ROCKSDB_NAMESPACE::CompactRangeOptions;
 using ROCKSDB_NAMESPACE::Comparator;
 using ROCKSDB_NAMESPACE::CompressionType;
@@ -81,11 +76,8 @@ using ROCKSDB_NAMESPACE::DBOptions;
 using ROCKSDB_NAMESPACE::DbPath;
 using ROCKSDB_NAMESPACE::Env;
 using ROCKSDB_NAMESPACE::EnvOptions;
-using ROCKSDB_NAMESPACE::EventListener;
-using ROCKSDB_NAMESPACE::ExternalFileIngestionInfo;
 using ROCKSDB_NAMESPACE::FileLock;
 using ROCKSDB_NAMESPACE::FilterPolicy;
-using ROCKSDB_NAMESPACE::FlushJobInfo;
 using ROCKSDB_NAMESPACE::FlushOptions;
 using ROCKSDB_NAMESPACE::HistogramData;
 using ROCKSDB_NAMESPACE::HyperClockCacheOptions;
@@ -98,7 +90,6 @@ using ROCKSDB_NAMESPACE::Logger;
 using ROCKSDB_NAMESPACE::LRUCacheOptions;
 using ROCKSDB_NAMESPACE::MemoryAllocator;
 using ROCKSDB_NAMESPACE::MemoryUtil;
-using ROCKSDB_NAMESPACE::MemTableInfo;
 using ROCKSDB_NAMESPACE::MergeOperator;
 using ROCKSDB_NAMESPACE::NewBloomFilterPolicy;
 using ROCKSDB_NAMESPACE::NewCompactOnDeletionCollectorFactory;
@@ -122,12 +113,10 @@ using ROCKSDB_NAMESPACE::Slice;
 using ROCKSDB_NAMESPACE::SliceParts;
 using ROCKSDB_NAMESPACE::SliceTransform;
 using ROCKSDB_NAMESPACE::Snapshot;
-using ROCKSDB_NAMESPACE::SstFileManager;
 using ROCKSDB_NAMESPACE::SstFileMetaData;
 using ROCKSDB_NAMESPACE::SstFileWriter;
 using ROCKSDB_NAMESPACE::Status;
 using ROCKSDB_NAMESPACE::StderrLogger;
-using ROCKSDB_NAMESPACE::SubcompactionJobInfo;
 using ROCKSDB_NAMESPACE::TablePropertiesCollectorFactory;
 using ROCKSDB_NAMESPACE::Transaction;
 using ROCKSDB_NAMESPACE::TransactionDB;
@@ -141,8 +130,6 @@ using ROCKSDB_NAMESPACE::WriteBatch;
 using ROCKSDB_NAMESPACE::WriteBatchWithIndex;
 using ROCKSDB_NAMESPACE::WriteBufferManager;
 using ROCKSDB_NAMESPACE::WriteOptions;
-using ROCKSDB_NAMESPACE::WriteStallCondition;
-using ROCKSDB_NAMESPACE::WriteStallInfo;
 
 using std::unordered_set;
 using std::vector;
@@ -152,9 +139,6 @@ extern "C" {
 struct rocksdb_t {
   DB* rep;
 };
-struct rocksdb_status_ptr_t {
-  Status* rep;
-};
 struct rocksdb_backup_engine_t {
   BackupEngine* rep;
 };
@@ -242,9 +226,6 @@ struct rocksdb_cache_t {
 struct rocksdb_write_buffer_manager_t {
   std::shared_ptr<WriteBufferManager> rep;
 };
-struct rocksdb_sst_file_manager_t {
-  std::shared_ptr<SstFileManager> rep;
-};
 struct rocksdb_livefiles_t {
   std::vector<LiveFileMetaData> rep;
 };
@@ -311,28 +292,6 @@ struct rocksdb_compactionfiltercontext_t {
   CompactionFilter::Context rep;
 };
 
-struct rocksdb_flushjobinfo_t {
-  FlushJobInfo rep;
-};
-struct rocksdb_writestallcondition_t {
-  WriteStallCondition rep;
-};
-struct rocksdb_writestallinfo_t {
-  WriteStallInfo rep;
-};
-struct rocksdb_memtableinfo_t {
-  MemTableInfo rep;
-};
-struct rocksdb_compactionjobinfo_t {
-  CompactionJobInfo rep;
-};
-struct rocksdb_subcompactionjobinfo_t {
-  SubcompactionJobInfo rep;
-};
-struct rocksdb_externalfileingestioninfo_t {
-  ExternalFileIngestionInfo rep;
-};
-
 struct rocksdb_statistics_histogram_data_t {
   rocksdb_statistics_histogram_data_t() : rep() {}
   HistogramData rep;
@@ -2668,16 +2627,6 @@ rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base(
   return result;
 }
 
-rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base_readopts(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
-    const rocksdb_readoptions_t* options) {
-  rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep =
-      wbwi->rep->NewIteratorWithBase(base_iterator->rep, &options->rep);
-  delete base_iterator;
-  return result;
-}
-
 rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base_cf(
     rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
     rocksdb_column_family_handle_t* column_family) {
@@ -2688,17 +2637,6 @@ rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base_cf(
   return result;
 }
 
-rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base_cf_readopts(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
-    rocksdb_column_family_handle_t* column_family,
-    const rocksdb_readoptions_t* options) {
-  rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep = wbwi->rep->NewIteratorWithBase(
-      column_family->rep, base_iterator->rep, &options->rep);
-  delete base_iterator;
-  return result;
-}
-
 char* rocksdb_writebatch_wi_get_from_batch(rocksdb_writebatch_wi_t* wbwi,
                                            const rocksdb_options_t* options,
                                            const char* key, size_t keylen,
@@ -2758,23 +2696,6 @@ char* rocksdb_writebatch_wi_get_from_batch_and_db(
   return result;
 }
 
-rocksdb_pinnableslice_t* rocksdb_writebatch_wi_get_pinned_from_batch_and_db(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
-    const rocksdb_readoptions_t* options, const char* key, size_t keylen,
-    char** errptr) {
-  rocksdb_pinnableslice_t* v = new (rocksdb_pinnableslice_t);
-  Status s = wbwi->rep->GetFromBatchAndDB(db->rep, options->rep,
-                                          Slice(key, keylen), &v->rep);
-  if (!s.ok()) {
-    delete (v);
-    if (!s.IsNotFound()) {
-      SaveError(errptr, s);
-    }
-    return nullptr;
-  }
-  return v;
-}
-
 char* rocksdb_writebatch_wi_get_from_batch_and_db_cf(
     rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
     const rocksdb_readoptions_t* options,
@@ -2796,24 +2717,6 @@ char* rocksdb_writebatch_wi_get_from_batch_and_db_cf(
   return result;
 }
 
-rocksdb_pinnableslice_t* rocksdb_writebatch_wi_get_pinned_from_batch_and_db_cf(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
-    const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key,
-    size_t keylen, char** errptr) {
-  rocksdb_pinnableslice_t* v = new (rocksdb_pinnableslice_t);
-  Status s = wbwi->rep->GetFromBatchAndDB(
-      db->rep, options->rep, column_family->rep, Slice(key, keylen), &v->rep);
-  if (!s.ok()) {
-    delete (v);
-    if (!s.IsNotFound()) {
-      SaveError(errptr, s);
-    }
-    return nullptr;
-  }
-  return v;
-}
-
 void rocksdb_write_writebatch_wi(rocksdb_t* db,
                                  const rocksdb_writeoptions_t* options,
                                  rocksdb_writebatch_wi_t* wbwi, char** errptr) {
@@ -3027,352 +2930,6 @@ void rocksdb_block_based_options_set_unpartitioned_pinning_tier(
       static_cast<ROCKSDB_NAMESPACE::PinningTier>(v);
 }
 
-/* FlushJobInfo */
-
-const char* rocksdb_flushjobinfo_cf_name(const rocksdb_flushjobinfo_t* info,
-                                         size_t* size) {
-  *size = info->rep.cf_name.size();
-  return info->rep.cf_name.data();
-}
-
-const char* rocksdb_flushjobinfo_file_path(const rocksdb_flushjobinfo_t* info,
-                                           size_t* size) {
-  *size = info->rep.file_path.size();
-  return info->rep.file_path.data();
-}
-
-unsigned char rocksdb_flushjobinfo_triggered_writes_slowdown(
-    const rocksdb_flushjobinfo_t* info) {
-  return info->rep.triggered_writes_slowdown;
-}
-
-unsigned char rocksdb_flushjobinfo_triggered_writes_stop(
-    const rocksdb_flushjobinfo_t* info) {
-  return info->rep.triggered_writes_stop;
-}
-
-uint64_t rocksdb_flushjobinfo_largest_seqno(
-    const rocksdb_flushjobinfo_t* info) {
-  return info->rep.largest_seqno;
-}
-
-uint64_t rocksdb_flushjobinfo_smallest_seqno(
-    const rocksdb_flushjobinfo_t* info) {
-  return info->rep.smallest_seqno;
-}
-
-void rocksdb_reset_status(rocksdb_status_ptr_t* status_ptr) {
-  auto ptr = status_ptr->rep;
-  *ptr = Status::OK();
-}
-
-/* CompactionJobInfo */
-
-void rocksdb_compactionjobinfo_status(const rocksdb_compactionjobinfo_t* info,
-                                      char** errptr) {
-  SaveError(errptr, info->rep.status);
-}
-
-const char* rocksdb_compactionjobinfo_cf_name(
-    const rocksdb_compactionjobinfo_t* info, size_t* size) {
-  *size = info->rep.cf_name.size();
-  return info->rep.cf_name.data();
-}
-
-size_t rocksdb_compactionjobinfo_input_files_count(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.input_files.size();
-}
-
-const char* rocksdb_compactionjobinfo_input_file_at(
-    const rocksdb_compactionjobinfo_t* info, size_t pos, size_t* size) {
-  assert(info != nullptr);
-  assert(pos < info->rep.input_files.size());
-
-  const std::string& path = info->rep.input_files[pos];
-  *size = path.size();
-  return path.data();
-}
-
-size_t rocksdb_compactionjobinfo_output_files_count(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.output_files.size();
-}
-
-const char* rocksdb_compactionjobinfo_output_file_at(
-    const rocksdb_compactionjobinfo_t* info, size_t pos, size_t* size) {
-  assert(info != nullptr);
-  assert(pos < info->rep.output_files.size());
-
-  const std::string& path = info->rep.output_files[pos];
-  *size = path.size();
-  return path.data();
-}
-
-uint64_t rocksdb_compactionjobinfo_elapsed_micros(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.elapsed_micros;
-}
-
-uint64_t rocksdb_compactionjobinfo_num_corrupt_keys(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.num_corrupt_keys;
-}
-
-int rocksdb_compactionjobinfo_base_input_level(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.base_input_level;
-}
-
-int rocksdb_compactionjobinfo_output_level(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.output_level;
-}
-
-size_t rocksdb_compactionjobinfo_num_input_files(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.num_input_files;
-}
-
-size_t rocksdb_compactionjobinfo_num_input_files_at_output_level(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.num_input_files_at_output_level;
-}
-
-uint64_t rocksdb_compactionjobinfo_input_records(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.num_input_records;
-}
-
-uint64_t rocksdb_compactionjobinfo_output_records(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.num_output_records;
-}
-
-uint64_t rocksdb_compactionjobinfo_total_input_bytes(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.total_input_bytes;
-}
-
-uint64_t rocksdb_compactionjobinfo_total_output_bytes(
-    const rocksdb_compactionjobinfo_t* info) {
-  return info->rep.stats.total_output_bytes;
-}
-
-uint32_t rocksdb_compactionjobinfo_compaction_reason(
-    const rocksdb_compactionjobinfo_t* info) {
-  return static_cast<uint32_t>(info->rep.compaction_reason);
-}
-
-/* SubcompactionJobInfo */
-
-void rocksdb_subcompactionjobinfo_status(
-    const rocksdb_subcompactionjobinfo_t* info, char** errptr) {
-  SaveError(errptr, info->rep.status);
-}
-
-const char* rocksdb_subcompactionjobinfo_cf_name(
-    const rocksdb_subcompactionjobinfo_t* info, size_t* size) {
-  *size = info->rep.cf_name.size();
-  return info->rep.cf_name.data();
-}
-
-uint64_t rocksdb_subcompactionjobinfo_thread_id(
-    const rocksdb_subcompactionjobinfo_t* info) {
-  return info->rep.thread_id;
-}
-
-int rocksdb_subcompactionjobinfo_base_input_level(
-    const rocksdb_subcompactionjobinfo_t* info) {
-  return info->rep.base_input_level;
-}
-
-int rocksdb_subcompactionjobinfo_output_level(
-    const rocksdb_subcompactionjobinfo_t* info) {
-  return info->rep.output_level;
-}
-
-/* ExternalFileIngestionInfo */
-
-const char* rocksdb_externalfileingestioninfo_cf_name(
-    const rocksdb_externalfileingestioninfo_t* info, size_t* size) {
-  *size = info->rep.cf_name.size();
-  return info->rep.cf_name.data();
-}
-
-const char* rocksdb_externalfileingestioninfo_internal_file_path(
-    const rocksdb_externalfileingestioninfo_t* info, size_t* size) {
-  *size = info->rep.internal_file_path.size();
-  return info->rep.internal_file_path.data();
-}
-
-/* External write stall info */
-extern ROCKSDB_LIBRARY_API const char* rocksdb_writestallinfo_cf_name(
-    const rocksdb_writestallinfo_t* info, size_t* size) {
-  *size = info->rep.cf_name.size();
-  return info->rep.cf_name.data();
-}
-
-const rocksdb_writestallcondition_t* rocksdb_writestallinfo_cur(
-    const rocksdb_writestallinfo_t* info) {
-  return reinterpret_cast<const rocksdb_writestallcondition_t*>(
-      &info->rep.condition.cur);
-}
-
-const rocksdb_writestallcondition_t* rocksdb_writestallinfo_prev(
-    const rocksdb_writestallinfo_t* info) {
-  return reinterpret_cast<const rocksdb_writestallcondition_t*>(
-      &info->rep.condition.prev);
-}
-
-const char* rocksdb_memtableinfo_cf_name(const rocksdb_memtableinfo_t* info,
-                                         size_t* size) {
-  *size = info->rep.cf_name.size();
-  return info->rep.cf_name.data();
-}
-
-uint64_t rocksdb_memtableinfo_first_seqno(const rocksdb_memtableinfo_t* info) {
-  return info->rep.first_seqno;
-}
-uint64_t rocksdb_memtableinfo_earliest_seqno(
-    const rocksdb_memtableinfo_t* info) {
-  return info->rep.earliest_seqno;
-}
-uint64_t rocksdb_memtableinfo_num_entries(const rocksdb_memtableinfo_t* info) {
-  return info->rep.num_entries;
-}
-uint64_t rocksdb_memtableinfo_num_deletes(const rocksdb_memtableinfo_t* info) {
-  return info->rep.num_deletes;
-}
-
-/* event listener */
-
-struct rocksdb_eventlistener_t : public EventListener {
-  void* state_{};
-  void (*destructor_)(void*){};
-  void (*on_flush_begin)(void*, rocksdb_t*, const rocksdb_flushjobinfo_t*){};
-  void (*on_flush_completed)(void*, rocksdb_t*,
-                             const rocksdb_flushjobinfo_t*){};
-  void (*on_compaction_begin)(void*, rocksdb_t*,
-                              const rocksdb_compactionjobinfo_t*){};
-  void (*on_compaction_completed)(void*, rocksdb_t*,
-                                  const rocksdb_compactionjobinfo_t*){};
-  void (*on_subcompaction_begin)(void*,
-                                 const rocksdb_subcompactionjobinfo_t*){};
-  void (*on_subcompaction_completed)(void*,
-                                     const rocksdb_subcompactionjobinfo_t*){};
-  void (*on_external_file_ingested)(
-      void*, rocksdb_t*, const rocksdb_externalfileingestioninfo_t*){};
-  void (*on_background_error)(void*, uint32_t, rocksdb_status_ptr_t*){};
-  void (*on_stall_conditions_changed)(void*, const rocksdb_writestallinfo_t*){};
-  void (*on_memtable_sealed)(void*, const rocksdb_memtableinfo_t*){};
-
-  rocksdb_eventlistener_t() = default;
-
-  rocksdb_eventlistener_t(const rocksdb_eventlistener_t&) = delete;
-  rocksdb_eventlistener_t& operator=(const rocksdb_eventlistener_t&) = delete;
-  rocksdb_eventlistener_t(rocksdb_eventlistener_t&&) = delete;
-  rocksdb_eventlistener_t& operator=(rocksdb_eventlistener_t&&) = delete;
-
-  void OnFlushBegin(DB* db, const FlushJobInfo& info) override {
-    rocksdb_t c_db = {db};
-    on_flush_begin(state_, &c_db,
-                   reinterpret_cast<const rocksdb_flushjobinfo_t*>(&info));
-  }
-
-  void OnFlushCompleted(DB* db, const FlushJobInfo& info) override {
-    rocksdb_t c_db = {db};
-    on_flush_completed(state_, &c_db,
-                       reinterpret_cast<const rocksdb_flushjobinfo_t*>(&info));
-  }
-
-  void OnCompactionBegin(DB* db, const CompactionJobInfo& info) override {
-    rocksdb_t c_db = {db};
-    on_compaction_begin(
-        state_, &c_db,
-        reinterpret_cast<const rocksdb_compactionjobinfo_t*>(&info));
-  }
-
-  void OnCompactionCompleted(DB* db, const CompactionJobInfo& info) override {
-    rocksdb_t c_db = {db};
-    on_compaction_completed(
-        state_, &c_db,
-        reinterpret_cast<const rocksdb_compactionjobinfo_t*>(&info));
-  }
-
-  void OnSubcompactionBegin(const SubcompactionJobInfo& info) override {
-    on_subcompaction_begin(
-        state_, reinterpret_cast<const rocksdb_subcompactionjobinfo_t*>(&info));
-  }
-
-  void OnSubcompactionCompleted(const SubcompactionJobInfo& info) override {
-    on_subcompaction_completed(
-        state_, reinterpret_cast<const rocksdb_subcompactionjobinfo_t*>(&info));
-  }
-
-  void OnExternalFileIngested(DB* db,
-                              const ExternalFileIngestionInfo& info) override {
-    rocksdb_t c_db = {db};
-    on_external_file_ingested(
-        state_, &c_db,
-        reinterpret_cast<const rocksdb_externalfileingestioninfo_t*>(&info));
-  }
-
-  void OnBackgroundError(BackgroundErrorReason reason,
-                         Status* status) override {
-    rocksdb_status_ptr_t* s = new rocksdb_status_ptr_t;
-    s->rep = status;
-    on_background_error(state_, static_cast<uint32_t>(reason), s);
-    delete s;
-  }
-
-  void OnStallConditionsChanged(const WriteStallInfo& info) override {
-    on_stall_conditions_changed(
-        state_, reinterpret_cast<const rocksdb_writestallinfo_t*>(&info));
-  }
-
-  void OnMemTableSealed(const MemTableInfo& info) override {
-    on_memtable_sealed(state_,
-                       reinterpret_cast<const rocksdb_memtableinfo_t*>(&info));
-  }
-
-  ~rocksdb_eventlistener_t() override { destructor_(state_); }
-};
-
-rocksdb_eventlistener_t* rocksdb_eventlistener_create(
-    void* state_, void (*destructor_)(void*), on_flush_begin_cb on_flush_begin,
-    on_flush_completed_cb on_flush_completed,
-    on_compaction_begin_cb on_compaction_begin,
-    on_compaction_completed_cb on_compaction_completed,
-    on_subcompaction_begin_cb on_subcompaction_begin,
-    on_subcompaction_completed_cb on_subcompaction_completed,
-    on_external_file_ingested_cb on_external_file_ingested,
-    on_background_error_cb on_background_error,
-    on_stall_conditions_changed_cb on_stall_conditions_changed,
-    on_memtable_sealed_cb on_memtable_sealed) {
-  rocksdb_eventlistener_t* et = new rocksdb_eventlistener_t;
-  et->state_ = state_;
-  et->destructor_ = destructor_;
-  et->on_flush_begin = on_flush_begin;
-  et->on_flush_completed = on_flush_completed;
-  et->on_compaction_begin = on_compaction_begin;
-  et->on_compaction_completed = on_compaction_completed;
-  et->on_subcompaction_begin = on_subcompaction_begin;
-  et->on_subcompaction_completed = on_subcompaction_completed;
-  et->on_external_file_ingested = on_external_file_ingested;
-  et->on_background_error = on_background_error;
-  et->on_stall_conditions_changed = on_stall_conditions_changed;
-  et->on_memtable_sealed = on_memtable_sealed;
-  return et;
-}
-
-void rocksdb_eventlistener_destroy(rocksdb_eventlistener_t* t) { delete t; }
-
-void rocksdb_options_add_eventlistener(rocksdb_options_t* opt,
-                                       rocksdb_eventlistener_t* t) {
-  opt->rep.listeners.emplace_back(std::shared_ptr<EventListener>(t));
-}
-
 rocksdb_cuckoo_table_options_t* rocksdb_cuckoo_options_create() {
   return new rocksdb_cuckoo_table_options_t;
 }
@@ -3748,16 +3305,6 @@ uint32_t rocksdb_options_get_memtable_op_scan_flush_trigger(
   return opt->rep.memtable_op_scan_flush_trigger;
 }
 
-void rocksdb_options_set_memtable_avg_op_scan_flush_trigger(
-    rocksdb_options_t* opt, uint32_t n) {
-  opt->rep.memtable_avg_op_scan_flush_trigger = n;
-}
-
-uint32_t rocksdb_options_get_memtable_avg_op_scan_flush_trigger(
-    rocksdb_options_t* opt) {
-  return opt->rep.memtable_avg_op_scan_flush_trigger;
-}
-
 void rocksdb_options_enable_statistics(rocksdb_options_t* opt) {
   opt->rep.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
 }
@@ -4785,8 +4332,6 @@ uint64_t rocksdb_perfcontext_metric(rocksdb_perfcontext_t* context,
       return rep->internal_recent_skipped_count;
     case rocksdb_internal_merge_count:
       return rep->internal_merge_count;
-    case rocksdb_internal_merge_point_lookup_count:
-      return rep->internal_merge_point_lookup_count;
     case rocksdb_get_snapshot_time:
       return rep->get_snapshot_time;
     case rocksdb_get_from_memtable_time:
@@ -5694,67 +5239,6 @@ ROCKSDB_LIBRARY_API void rocksdb_write_buffer_manager_set_allow_stall(
   wbm->rep->SetAllowStall(new_allow_stall);
 }
 
-rocksdb_sst_file_manager_t* rocksdb_sst_file_manager_create(
-    rocksdb_env_t* env) {
-  rocksdb_sst_file_manager_t* sfm = new rocksdb_sst_file_manager_t;
-  sfm->rep.reset(ROCKSDB_NAMESPACE::NewSstFileManager(env->rep));
-  return sfm;
-}
-
-void rocksdb_sst_file_manager_destroy(rocksdb_sst_file_manager_t* sfm) {
-  delete sfm;
-}
-
-void rocksdb_sst_file_manager_set_max_allowed_space_usage(
-    rocksdb_sst_file_manager_t* sfm, uint64_t max_allowed_space) {
-  sfm->rep->SetMaxAllowedSpaceUsage(max_allowed_space);
-}
-
-void rocksdb_sst_file_manager_set_compaction_buffer_size(
-    rocksdb_sst_file_manager_t* sfm, uint64_t compaction_buffer_size) {
-  sfm->rep->SetCompactionBufferSize(compaction_buffer_size);
-}
-
-bool rocksdb_sst_file_manager_is_max_allowed_space_reached(
-    rocksdb_sst_file_manager_t* sfm) {
-  return sfm->rep->IsMaxAllowedSpaceReached();
-}
-
-bool rocksdb_sst_file_manager_is_max_allowed_space_reached_including_compactions(
-    rocksdb_sst_file_manager_t* sfm) {
-  return sfm->rep->IsMaxAllowedSpaceReachedIncludingCompactions();
-}
-
-uint64_t rocksdb_sst_file_manager_get_total_size(
-    rocksdb_sst_file_manager_t* sfm) {
-  return sfm->rep->GetTotalSize();
-}
-
-int64_t rocksdb_sst_file_manager_get_delete_rate_bytes_per_second(
-    rocksdb_sst_file_manager_t* sfm) {
-  return sfm->rep->GetDeleteRateBytesPerSecond();
-}
-
-void rocksdb_sst_file_manager_set_delete_rate_bytes_per_second(
-    rocksdb_sst_file_manager_t* sfm, int64_t delete_rate) {
-  return sfm->rep->SetDeleteRateBytesPerSecond(delete_rate);
-}
-
-double rocksdb_sst_file_manager_get_max_trash_db_ratio(
-    rocksdb_sst_file_manager_t* sfm) {
-  return sfm->rep->GetMaxTrashDBRatio();
-}
-
-void rocksdb_sst_file_manager_set_max_trash_db_ratio(
-    rocksdb_sst_file_manager_t* sfm, double ratio) {
-  return sfm->rep->SetMaxTrashDBRatio(ratio);
-}
-
-uint64_t rocksdb_sst_file_manager_get_total_trash_size(
-    rocksdb_sst_file_manager_t* sfm) {
-  return sfm->rep->GetTotalTrashSize();
-}
-
 rocksdb_dbpath_t* rocksdb_dbpath_create(const char* path,
                                         uint64_t target_size) {
   rocksdb_dbpath_t* result = new rocksdb_dbpath_t;

db/c_test.c

@@ -103,12 +103,6 @@ static void CheckValue(char* err, const char* expected, char** actual,
   Free(actual);
 }
 
-static void CheckPinnedValue(char* err, const char* expected,
-                             const char** actual, size_t actual_length) {
-  CheckNoError(err);
-  CheckEqual(expected, *actual, actual_length);
-}
-
 static void CheckGet(rocksdb_t* db, const rocksdb_readoptions_t* options,
                      const char* key, const char* expected) {
   char* err = NULL;
@@ -1251,8 +1245,6 @@ int main(int argc, char** argv) {
     CheckCondition(count == 3);
     size_t size;
     char* value;
-    const char* pinned_value;
-    rocksdb_pinnableslice_t* p;
     value = rocksdb_writebatch_wi_get_from_batch(wbi, options, "box", 3, &size,
                                                  &err);
     CheckValue(err, "c", &value, size);
@@ -1262,19 +1254,9 @@ int main(int argc, char** argv) {
     value = rocksdb_writebatch_wi_get_from_batch_and_db(wbi, db, roptions,
                                                         "foo", 3, &size, &err);
     CheckValue(err, "hello", &value, size);
-    p = rocksdb_writebatch_wi_get_pinned_from_batch_and_db(wbi, db, roptions,
-                                                           "foo", 3, &err);
-    pinned_value = rocksdb_pinnableslice_value(p, &size);
-    CheckPinnedValue(err, "hello", &pinned_value, size);
-    rocksdb_pinnableslice_destroy(p);
     value = rocksdb_writebatch_wi_get_from_batch_and_db(wbi, db, roptions,
                                                         "box", 3, &size, &err);
     CheckValue(err, "c", &value, size);
-    p = rocksdb_writebatch_wi_get_pinned_from_batch_and_db(wbi, db, roptions,
-                                                           "box", 3, &err);
-    pinned_value = rocksdb_pinnableslice_value(p, &size);
-    CheckPinnedValue(err, "c", &pinned_value, size);
-    rocksdb_pinnableslice_destroy(p);
     rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
     CheckNoError(err);
     CheckGet(db, roptions, "foo", "hello");
@@ -1380,46 +1362,6 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_wi_destroy(wbi);
   }
 
-  StartPhase("wbwi_iter_readoptions");
-  {
-    rocksdb_readoptions_t* iter_roptions = rocksdb_readoptions_create();
-    rocksdb_readoptions_set_iterate_lower_bound(iter_roptions, "boy", 3);
-    rocksdb_readoptions_set_iterate_upper_bound(iter_roptions, "fool", 4);
-    rocksdb_iterator_t* base_iter = rocksdb_create_iterator(db, iter_roptions);
-    rocksdb_writebatch_wi_t* wbi = rocksdb_writebatch_wi_create(0, 1);
-    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b",
-                              1);  // should get filtered out
-    rocksdb_writebatch_wi_put(wbi, "cat", 3, "miau", 4);
-    rocksdb_writebatch_wi_put(wbi, "gnu", 3, "muh",
-                              3);  // should get filtered out
-    rocksdb_iterator_t* iter =
-        rocksdb_writebatch_wi_create_iterator_with_base_readopts(wbi, base_iter,
-                                                                 iter_roptions);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-    CheckIter(iter, "cat", "miau");
-    rocksdb_iter_next(iter);
-    CheckIter(iter, "foo", "hello");
-    rocksdb_iter_prev(iter);
-    CheckIter(iter, "cat", "miau");
-    rocksdb_iter_prev(iter);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_last(iter);
-    CheckIter(iter, "foo", "hello");
-    rocksdb_iter_seek(iter, "b", 1);
-    CheckIter(iter, "cat", "miau");
-    rocksdb_iter_seek_for_prev(iter, "d", 1);
-    CheckIter(iter, "cat", "miau");
-    rocksdb_iter_seek_for_prev(iter, "fool", 3);
-    CheckIter(iter, "foo", "hello");
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-    rocksdb_writebatch_wi_destroy(wbi);
-    rocksdb_readoptions_destroy(iter_roptions);
-  }
-
   StartPhase("multiget");
   {
     const char* keys[3] = {"box", "foo", "notfound"};
@@ -1850,35 +1792,6 @@ int main(int argc, char** argv) {
     rocksdb_flush_wal(db, 1, &err);
     CheckNoError(err);
 
-    // Test WriteBatchWithIndex iteration with Column Family
-    rocksdb_writebatch_wi_t* wbwi = rocksdb_writebatch_wi_create(0, true);
-    rocksdb_writebatch_wi_put_cf(wbwi, handles[1], "boat", 4, "row",
-                                 3);  // should be filtered out
-    rocksdb_writebatch_wi_put_cf(wbwi, handles[1], "buffy", 5, "charmed", 7);
-    rocksdb_writebatch_wi_put_cf(wbwi, handles[1], "bus", 3, "yellow",
-                                 6);  // should be filtered out
-    rocksdb_readoptions_t* iter_roptions = rocksdb_readoptions_create();
-    rocksdb_readoptions_set_iterate_lower_bound(iter_roptions, "bu", 2);
-    rocksdb_readoptions_set_iterate_upper_bound(iter_roptions, "buffz", 5);
-    rocksdb_iterator_t* base_iter =
-        rocksdb_create_iterator_cf(db, iter_roptions, handles[1]);
-    rocksdb_iterator_t* wbwi_iter =
-        rocksdb_writebatch_wi_create_iterator_with_base_cf_readopts(
-            wbwi, base_iter, handles[1], iter_roptions);
-
-    CheckCondition(!rocksdb_iter_valid(wbwi_iter));
-    rocksdb_iter_seek_to_first(wbwi_iter);
-    CheckCondition(rocksdb_iter_valid(wbwi_iter));
-    CheckIter(wbwi_iter, "buff", "rocksdb");
-    rocksdb_iter_next(wbwi_iter);
-    CheckIter(wbwi_iter, "buffy", "charmed");
-    rocksdb_iter_next(wbwi_iter);
-    CheckCondition(!rocksdb_iter_valid(wbwi_iter));
-
-    rocksdb_iter_destroy(wbwi_iter);
-    rocksdb_writebatch_wi_destroy(wbwi);
-    rocksdb_readoptions_destroy(iter_roptions);
-
     const char* keys[3] = {"box", "box", "barfooxx"};
     const rocksdb_column_family_handle_t* get_handles[3] = {
         handles[0], handles[1], handles[1]};
@@ -2220,10 +2133,6 @@ int main(int argc, char** argv) {
     CheckCondition(100 ==
                    rocksdb_options_get_memtable_op_scan_flush_trigger(o));
 
-    rocksdb_options_set_memtable_avg_op_scan_flush_trigger(o, 150);
-    CheckCondition(150 ==
-                   rocksdb_options_get_memtable_avg_op_scan_flush_trigger(o));
-
     rocksdb_options_set_ttl(o, 5000);
     CheckCondition(5000 == rocksdb_options_get_ttl(o));
 
@@ -2667,12 +2576,6 @@ int main(int argc, char** argv) {
     CheckCondition(100 ==
                    rocksdb_options_get_memtable_op_scan_flush_trigger(o));
 
-    rocksdb_options_set_memtable_avg_op_scan_flush_trigger(copy, 900);
-    CheckCondition(
-        900 == rocksdb_options_get_memtable_avg_op_scan_flush_trigger(copy));
-    CheckCondition(150 ==
-                   rocksdb_options_get_memtable_avg_op_scan_flush_trigger(o));
-
     rocksdb_options_set_ttl(copy, 8000);
     CheckCondition(8000 == rocksdb_options_get_ttl(copy));
     CheckCondition(5000 == rocksdb_options_get_ttl(o));
@@ -4147,23 +4050,6 @@ int main(int argc, char** argv) {
     rocksdb_cache_destroy(lru);
   }
 
-  StartPhase("sst_file_manager");
-  {
-    rocksdb_sst_file_manager_t* sst_file_manager;
-    sst_file_manager = rocksdb_sst_file_manager_create(env);
-    rocksdb_sst_file_manager_set_delete_rate_bytes_per_second(sst_file_manager,
-                                                              1);
-    rocksdb_sst_file_manager_set_max_trash_db_ratio(sst_file_manager, 0.75);
-
-    CheckCondition(1 ==
-                   rocksdb_sst_file_manager_get_delete_rate_bytes_per_second(
-                       sst_file_manager));
-    CheckCondition(0.75 == rocksdb_sst_file_manager_get_max_trash_db_ratio(
-                               sst_file_manager));
-
-    rocksdb_sst_file_manager_destroy(sst_file_manager);
-  }
-
   StartPhase("cancel_all_background_work");
   rocksdb_cancel_all_background_work(db, 1);
 

db/column_family.cc

@@ -110,19 +110,11 @@ void GetInternalTblPropCollFactory(
   }
 }
 
-bool CompressionSupportedWithManager(CompressionType type,
-                                     UnownedPtr<CompressionManager> mgr) {
-  return mgr ? mgr->SupportsCompressionType(type)
-             : CompressionTypeSupported(type);
-}
-
 Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
   if (!cf_options.compression_per_level.empty()) {
     for (size_t level = 0; level < cf_options.compression_per_level.size();
          ++level) {
-      if (!CompressionSupportedWithManager(
-              cf_options.compression_per_level[level],
-              cf_options.compression_manager.get())) {
+      if (!CompressionTypeSupported(cf_options.compression_per_level[level])) {
         return Status::InvalidArgument(
             "Compression type " +
             CompressionTypeToString(cf_options.compression_per_level[level]) +
@@ -130,8 +122,7 @@ Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
       }
     }
   } else {
-    if (!CompressionSupportedWithManager(
-            cf_options.compression, cf_options.compression_manager.get())) {
+    if (!CompressionTypeSupported(cf_options.compression)) {
       return Status::InvalidArgument(
           "Compression type " +
           CompressionTypeToString(cf_options.compression) +
@@ -457,21 +448,13 @@ ColumnFamilyOptions SanitizeCfOptions(const ImmutableDBOptions& db_options,
     result.preclude_last_level_data_seconds = 0;
   }
 
-  if (read_only) {
-    if (result.memtable_op_scan_flush_trigger) {
-      ROCKS_LOG_WARN(db_options.info_log.get(),
-                     "option memtable_op_scan_flush_trigger is sanitized to "
-                     "0(disabled) for read only DB.");
-      result.memtable_op_scan_flush_trigger = 0;
-    }
-    if (result.memtable_avg_op_scan_flush_trigger) {
-      ROCKS_LOG_WARN(
-          db_options.info_log.get(),
-          "option memtable_avg_op_scan_flush_trigger is sanitized to "
-          "0(disabled) for read only DB.");
-      result.memtable_avg_op_scan_flush_trigger = 0;
-    }
+  if (read_only && result.memtable_op_scan_flush_trigger != 0) {
+    ROCKS_LOG_WARN(db_options.info_log.get(),
+                   "option memtable_op_scan_flush_trigger is sanitized to "
+                   "0(disabled) for read only DB.");
+    result.memtable_op_scan_flush_trigger = 0;
   }
+
   return result;
 }
 
@@ -1226,12 +1209,10 @@ Compaction* ColumnFamilyData::PickCompaction(
     const MutableCFOptions& mutable_options,
     const MutableDBOptions& mutable_db_options,
     const std::vector<SequenceNumber>& existing_snapshots,
-    const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer,
-    bool require_max_output_level) {
+    const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer) {
   auto* result = compaction_picker_->PickCompaction(
       GetName(), mutable_options, mutable_db_options, existing_snapshots,
-      snapshot_checker, current_->storage_info(), log_buffer,
-      require_max_output_level);
+      snapshot_checker, current_->storage_info(), log_buffer);
   if (result != nullptr) {
     result->FinalizeInputInfo(current_);
   }

db/column_family.h

@@ -424,8 +424,7 @@ class ColumnFamilyData {
       const MutableCFOptions& mutable_options,
       const MutableDBOptions& mutable_db_options,
       const std::vector<SequenceNumber>& existing_snapshots,
-      const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer,
-      bool require_max_output_level = false);
+      const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer);
 
   // Check if the passed range overlap with any running compactions.
   // REQUIRES: DB mutex held

db/compaction/compaction.h

@@ -283,13 +283,6 @@ class Compaction {
   // are non-overlapping and can be trivially moved.
   bool is_trivial_move() const { return is_trivial_move_; }
 
-  bool is_trivial_copy_compaction() const {
-    return immutable_options_.compaction_style == kCompactionStyleFIFO &&
-           compaction_reason_ == CompactionReason::kChangeTemperature &&
-           mutable_cf_options_.compaction_options_fifo
-               .allow_trivial_copy_when_change_temperature;
-  }
-
   // How many total levels are there?
   int number_levels() const { return number_levels_; }
 
@@ -463,11 +456,6 @@ class Compaction {
                                    const int start_level,
                                    const int output_level);
 
-  static bool OutputToNonZeroMaxOutputLevel(int output_level,
-                                            int max_output_level) {
-    return output_level > 0 && output_level == max_output_level;
-  }
-
   // If some data cannot be safely migrated "up" the LSM tree due to a change
   // in the preclude_last_level_data_seconds setting, this indicates a sequence
   // number for the newest data that must be kept in the last level.

db/compaction/compaction_job.cc

@@ -133,7 +133,10 @@ CompactionJob::CompactionJob(
     LogBuffer* log_buffer, FSDirectory* db_directory,
     FSDirectory* output_directory, FSDirectory* blob_output_directory,
     Statistics* stats, InstrumentedMutex* db_mutex,
-    ErrorHandler* db_error_handler, JobContext* job_context,
+    ErrorHandler* db_error_handler,
+    std::vector<SequenceNumber> existing_snapshots,
+    SequenceNumber earliest_write_conflict_snapshot,
+    const SnapshotChecker* snapshot_checker, JobContext* job_context,
     std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
     bool paranoid_file_checks, bool measure_io_stats, const std::string& dbname,
     CompactionJobStats* compaction_job_stats, Env::Priority thread_pri,
@@ -170,7 +173,12 @@ CompactionJob::CompactionJob(
       blob_output_directory_(blob_output_directory),
       db_mutex_(db_mutex),
       db_error_handler_(db_error_handler),
-      earliest_snapshot_(job_context->GetEarliestSnapshotSequence()),
+      existing_snapshots_(std::move(existing_snapshots)),
+      earliest_snapshot_(existing_snapshots_.empty()
+                             ? kMaxSequenceNumber
+                             : existing_snapshots_.at(0)),
+      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
+      snapshot_checker_(snapshot_checker),
       job_context_(job_context),
       table_cache_(std::move(table_cache)),
       event_logger_(event_logger),
@@ -185,7 +193,6 @@ CompactionJob::CompactionJob(
       bg_bottom_compaction_scheduled_(bg_bottom_compaction_scheduled) {
   assert(job_stats_ != nullptr);
   assert(log_buffer_ != nullptr);
-  assert(job_context->snapshot_context_initialized);
 
   const auto* cfd = compact_->compaction->column_family_data();
   ThreadStatusUtil::SetEnableTracking(db_options_.enable_thread_tracking);
@@ -217,9 +224,10 @@ void CompactionJob::ReportStartedCompaction(Compaction* compaction) {
       ThreadStatus::COMPACTION_PROP_FLAGS,
       compaction->is_manual_compaction() +
           (compaction->deletion_compaction() << 1));
-  auto total_input_bytes = compaction->CalculateTotalInputSize();
+
   ThreadStatusUtil::SetThreadOperationProperty(
-      ThreadStatus::COMPACTION_TOTAL_INPUT_BYTES, total_input_bytes);
+      ThreadStatus::COMPACTION_TOTAL_INPUT_BYTES,
+      compaction->CalculateTotalInputSize());
 
   IOSTATS_RESET(bytes_written);
   IOSTATS_RESET(bytes_read);
@@ -234,16 +242,6 @@ void CompactionJob::ReportStartedCompaction(Compaction* compaction) {
 
   job_stats_->is_manual_compaction = compaction->is_manual_compaction();
   job_stats_->is_full_compaction = compaction->is_full_compaction();
-  // populate compaction stats num_input_files and total_num_of_bytes
-  size_t num_input_files = 0;
-  for (int input_level = 0;
-       input_level < static_cast<int>(compaction->num_input_levels());
-       ++input_level) {
-    const LevelFilesBrief* flevel = compaction->input_levels(input_level);
-    num_input_files += flevel->num_files;
-  }
-  job_stats_->CompactionJobStats::num_input_files = num_input_files;
-  job_stats_->total_input_bytes = total_input_bytes;
 }
 
 void CompactionJob::Prepare(
@@ -839,7 +837,8 @@ Status CompactionJob::Run() {
   }
 
   ReleaseSubcompactionResources();
-  TEST_SYNC_POINT("CompactionJob::ReleaseSubcompactionResources");
+  TEST_SYNC_POINT("CompactionJob::ReleaseSubcompactionResources:0");
+  TEST_SYNC_POINT("CompactionJob::ReleaseSubcompactionResources:1");
 
   for (const auto& state : compact_->sub_compact_states) {
     for (const auto& output : state.GetOutputs()) {
@@ -879,14 +878,7 @@ Status CompactionJob::Run() {
   UpdateCompactionJobOutputStats(internal_stats_);
 
   // Verify number of output records
-  // Only verify on table with format collects table properties
-  const auto& mutable_cf_options = compact_->compaction->mutable_cf_options();
-  if (status.ok() &&
-      (mutable_cf_options.table_factory->IsInstanceOf(
-           TableFactory::kBlockBasedTableName()) ||
-       mutable_cf_options.table_factory->IsInstanceOf(
-           TableFactory::kPlainTableName())) &&
-      db_options_.compaction_verify_record_count) {
+  if (status.ok() && db_options_.compaction_verify_record_count) {
     uint64_t total_output_num = 0;
     for (const auto& state : compact_->sub_compact_states) {
       for (const auto& output : state.GetOutputs()) {
@@ -1184,7 +1176,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // creation across both CompactionJob and CompactionServiceCompactionJob
   sub_compact->AssignRangeDelAggregator(
       std::make_unique<CompactionRangeDelAggregator>(
-          &cfd->internal_comparator(), job_context_->snapshot_seqs,
+          &cfd->internal_comparator(), existing_snapshots_,
           &full_history_ts_low_, &trim_ts_));
 
   // TODO: since we already use C++17, should use
@@ -1325,8 +1317,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       env_, cfd->user_comparator(), cfd->ioptions().merge_operator.get(),
       compaction_filter, db_options_.info_log.get(),
       false /* internal key corruption is expected */,
-      job_context_->GetLatestSnapshotSequence(), job_context_->snapshot_checker,
-      compact_->compaction->level(), db_options_.stats);
+      existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
+      snapshot_checker_, compact_->compaction->level(), db_options_.stats);
 
   const auto& mutable_cf_options =
       sub_compact->compaction->mutable_cf_options();
@@ -1362,10 +1354,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
 
   auto c_iter = std::make_unique<CompactionIterator>(
       input, cfd->user_comparator(), &merge, versions_->LastSequence(),
-      &(job_context_->snapshot_seqs), earliest_snapshot_,
-      job_context_->earliest_write_conflict_snapshot, job_snapshot_seq,
-      job_context_->snapshot_checker, env_,
-      ShouldReportDetailedTime(env_, stats_),
+      &existing_snapshots_, earliest_snapshot_,
+      earliest_write_conflict_snapshot_, job_snapshot_seq, snapshot_checker_,
+      env_, ShouldReportDetailedTime(env_, stats_),
       /*expect_valid_internal_key=*/true, sub_compact->RangeDelAgg(),
       blob_file_builder.get(), db_options_.allow_data_in_errors,
       db_options_.enforce_single_del_contracts, manual_compaction_canceled_,
@@ -1654,6 +1645,10 @@ Status CompactionJob::FinishCompactionOutputFile(
   Status s = input_status;
 
   // Add range tombstones
+  auto earliest_snapshot = kMaxSequenceNumber;
+  if (existing_snapshots_.size() > 0) {
+    earliest_snapshot = existing_snapshots_[0];
+  }
   if (s.ok()) {
     // Inclusive lower bound, exclusive upper bound
     std::pair<SequenceNumber, SequenceNumber> keep_seqno_range{
@@ -1679,7 +1674,7 @@ Status CompactionJob::FinishCompactionOutputFile(
       s = outputs.AddRangeDels(*sub_compact->RangeDelAgg(), comp_start_user_key,
                                comp_end_user_key, range_del_out_stats,
                                bottommost_level_, cfd->internal_comparator(),
-                               earliest_snapshot_, keep_seqno_range,
+                               earliest_snapshot, keep_seqno_range,
                                next_table_min_key, full_history_ts_low_);
     }
     RecordDroppedKeys(range_del_out_stats, &sub_compact->compaction_job_stats);
@@ -2298,8 +2293,8 @@ void CompactionJob::LogCompaction() {
                    cfd->GetName().c_str(), scratch);
     // build event logger report
     auto stream = event_logger_->Log();
-    stream << "job" << job_id_ << "event" << "compaction_started" << "cf_name"
-           << cfd->GetName() << "compaction_reason"
+    stream << "job" << job_id_ << "event" << "compaction_started"
+           << "compaction_reason"
            << GetCompactionReasonString(compaction->compaction_reason());
     for (size_t i = 0; i < compaction->num_input_levels(); ++i) {
       stream << ("files_L" + std::to_string(compaction->level(i)));
@@ -2311,10 +2306,9 @@ void CompactionJob::LogCompaction() {
     }
     stream << "score" << compaction->score() << "input_data_size"
            << compaction->CalculateTotalInputSize() << "oldest_snapshot_seqno"
-           << (job_context_->snapshot_seqs.empty()
+           << (existing_snapshots_.empty()
                    ? int64_t{-1}  // Use -1 for "none"
-                   : static_cast<int64_t>(
-                         job_context_->GetEarliestSnapshotSequence()));
+                   : static_cast<int64_t>(existing_snapshots_[0]));
     if (compaction->SupportsPerKeyPlacement()) {
       stream << "proximal_after_seqno" << proximal_after_seqno_;
       stream << "preserve_seqno_after" << preserve_seqno_after_;

db/compaction/compaction_job.h

@@ -142,27 +142,27 @@ class SubcompactionState;
 
 class CompactionJob {
  public:
-  CompactionJob(int job_id, Compaction* compaction,
-                const ImmutableDBOptions& db_options,
-                const MutableDBOptions& mutable_db_options,
-                const FileOptions& file_options, VersionSet* versions,
-                const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
-                FSDirectory* db_directory, FSDirectory* output_directory,
-                FSDirectory* blob_output_directory, Statistics* stats,
-                InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
-                JobContext* job_context, std::shared_ptr<Cache> table_cache,
-                EventLogger* event_logger, bool paranoid_file_checks,
-                bool measure_io_stats, const std::string& dbname,
-                CompactionJobStats* compaction_job_stats,
-                Env::Priority thread_pri,
-                const std::shared_ptr<IOTracer>& io_tracer,
-                const std::atomic<bool>& manual_compaction_canceled,
-                const std::string& db_id = "",
-                const std::string& db_session_id = "",
-                std::string full_history_ts_low = "", std::string trim_ts = "",
-                BlobFileCompletionCallback* blob_callback = nullptr,
-                int* bg_compaction_scheduled = nullptr,
-                int* bg_bottom_compaction_scheduled = nullptr);
+  CompactionJob(
+      int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
+      const MutableDBOptions& mutable_db_options,
+      const FileOptions& file_options, VersionSet* versions,
+      const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
+      FSDirectory* db_directory, FSDirectory* output_directory,
+      FSDirectory* blob_output_directory, Statistics* stats,
+      InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
+      std::vector<SequenceNumber> existing_snapshots,
+      SequenceNumber earliest_write_conflict_snapshot,
+      const SnapshotChecker* snapshot_checker, JobContext* job_context,
+      std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
+      bool paranoid_file_checks, bool measure_io_stats,
+      const std::string& dbname, CompactionJobStats* compaction_job_stats,
+      Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
+      const std::atomic<bool>& manual_compaction_canceled,
+      const std::string& db_id = "", const std::string& db_session_id = "",
+      std::string full_history_ts_low = "", std::string trim_ts = "",
+      BlobFileCompletionCallback* blob_callback = nullptr,
+      int* bg_compaction_scheduled = nullptr,
+      int* bg_bottom_compaction_scheduled = nullptr);
 
   virtual ~CompactionJob();
 
@@ -321,8 +321,21 @@ class CompactionJob {
   FSDirectory* blob_output_directory_;
   InstrumentedMutex* db_mutex_;
   ErrorHandler* db_error_handler_;
+  // If there were two snapshots with seq numbers s1 and
+  // s2 and s1 < s2, and if we find two instances of a key k1 then lies
+  // entirely within s1 and s2, then the earlier version of k1 can be safely
+  // deleted because that version is not visible in any snapshot.
+  std::vector<SequenceNumber> existing_snapshots_;
 
   SequenceNumber earliest_snapshot_;
+
+  // This is the earliest snapshot that could be used for write-conflict
+  // checking by a transaction.  For any user-key newer than this snapshot, we
+  // should make sure not to remove evidence that a write occurred.
+  SequenceNumber earliest_write_conflict_snapshot_;
+
+  const SnapshotChecker* const snapshot_checker_;
+
   JobContext* job_context_;
 
   std::shared_ptr<Cache> table_cache_;
@@ -414,9 +427,8 @@ struct CompactionServiceInput {
 // CompactionServiceOutputFile is the metadata for the output SST file
 struct CompactionServiceOutputFile {
   std::string file_name;
-  uint64_t file_size{};
-  SequenceNumber smallest_seqno{};
-  SequenceNumber largest_seqno{};
+  SequenceNumber smallest_seqno;
+  SequenceNumber largest_seqno;
   std::string smallest_internal_key;
   std::string largest_internal_key;
   uint64_t oldest_ancester_time = kUnknownOldestAncesterTime;
@@ -424,26 +436,24 @@ struct CompactionServiceOutputFile {
   uint64_t epoch_number = kUnknownEpochNumber;
   std::string file_checksum = kUnknownFileChecksum;
   std::string file_checksum_func_name = kUnknownFileChecksumFuncName;
-  uint64_t paranoid_hash{};
+  uint64_t paranoid_hash;
   bool marked_for_compaction;
   UniqueId64x2 unique_id{};
   TableProperties table_properties;
   bool is_proximal_level_output;
-  Temperature file_temperature = Temperature::kUnknown;
+  Temperature file_temperature;
 
   CompactionServiceOutputFile() = default;
   CompactionServiceOutputFile(
-      const std::string& name, uint64_t size, SequenceNumber smallest,
-      SequenceNumber largest, std::string _smallest_internal_key,
-      std::string _largest_internal_key, uint64_t _oldest_ancester_time,
-      uint64_t _file_creation_time, uint64_t _epoch_number,
-      const std::string& _file_checksum,
+      const std::string& name, SequenceNumber smallest, SequenceNumber largest,
+      std::string _smallest_internal_key, std::string _largest_internal_key,
+      uint64_t _oldest_ancester_time, uint64_t _file_creation_time,
+      uint64_t _epoch_number, const std::string& _file_checksum,
       const std::string& _file_checksum_func_name, uint64_t _paranoid_hash,
       bool _marked_for_compaction, UniqueId64x2 _unique_id,
       const TableProperties& _table_properties, bool _is_proximal_level_output,
       Temperature _file_temperature)
       : file_name(name),
-        file_size(size),
         smallest_seqno(smallest),
         largest_seqno(largest),
         smallest_internal_key(std::move(_smallest_internal_key)),
@@ -511,9 +521,9 @@ class CompactionServiceCompactionJob : private CompactionJob {
       const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
       FSDirectory* output_directory, Statistics* stats,
       InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
-      JobContext* job_context, std::shared_ptr<Cache> table_cache,
-      EventLogger* event_logger, const std::string& dbname,
-      const std::shared_ptr<IOTracer>& io_tracer,
+      std::vector<SequenceNumber> existing_snapshots,
+      std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
+      const std::string& dbname, const std::shared_ptr<IOTracer>& io_tracer,
       const std::atomic<bool>& manual_compaction_canceled,
       const std::string& db_id, const std::string& db_session_id,
       std::string output_path,

db/compaction/compaction_job_test.cc

@@ -43,6 +43,7 @@ void VerifyInitializationOfCompactionJobStats(
   ASSERT_EQ(compaction_job_stats.elapsed_micros, 0U);
 
   ASSERT_EQ(compaction_job_stats.num_input_records, 0U);
+  ASSERT_EQ(compaction_job_stats.num_input_files, 0U);
   ASSERT_EQ(compaction_job_stats.num_input_files_at_output_level, 0U);
 
   ASSERT_EQ(compaction_job_stats.num_output_records, 0U);
@@ -51,6 +52,7 @@ void VerifyInitializationOfCompactionJobStats(
   ASSERT_TRUE(compaction_job_stats.is_manual_compaction);
   ASSERT_FALSE(compaction_job_stats.is_remote_compaction);
 
+  ASSERT_EQ(compaction_job_stats.total_input_bytes, 0U);
   ASSERT_EQ(compaction_job_stats.total_output_bytes, 0U);
 
   ASSERT_EQ(compaction_job_stats.total_input_raw_key_bytes, 0U);
@@ -230,6 +232,11 @@ class CompactionJobTestBase : public testing::Test {
     // set default for the tests
     mutable_cf_options_.target_file_size_base = 1024 * 1024;
     mutable_cf_options_.max_compaction_bytes = 10 * 1024 * 1024;
+
+    // Turn off compaction_verify_record_count MockTables
+    if (table_type == TableTypeForTest::kMockTable) {
+      db_options_.compaction_verify_record_count = false;
+    }
   }
 
   void SetUp() override {
@@ -458,10 +465,9 @@ class CompactionJobTestBase : public testing::Test {
       ReadOptions read_opts;
       Status s = cf_options_.table_factory->NewTableReader(
           read_opts,
-          TableReaderOptions(cfd->ioptions(), /*prefix_extractor=*/nullptr,
-                             /*compression_manager=*/nullptr, FileOptions(),
+          TableReaderOptions(cfd->ioptions(), nullptr, FileOptions(),
                              cfd_->internal_comparator(),
-                             /*block_protection_bytes_per_key=*/0),
+                             0 /* block_protection_bytes_per_key */),
           std::move(freader), file_size, &table_reader, false);
       ASSERT_OK(s);
       assert(table_reader);
@@ -594,11 +600,11 @@ class CompactionJobTestBase : public testing::Test {
       const std::vector<std::vector<FileMetaData*>>& input_files,
       const std::vector<int> input_levels,
       std::function<void(Compaction& comp)>&& verify_func,
-      std::vector<SequenceNumber>&& snapshots = {}) {
+      const std::vector<SequenceNumber>& snapshots = {}) {
     const int kLastLevel = cf_options_.num_levels - 1;
     verify_per_key_placement_ = std::move(verify_func);
     mock::KVVector empty_map;
-    RunCompaction(input_files, input_levels, {empty_map}, std::move(snapshots),
+    RunCompaction(input_files, input_levels, {empty_map}, snapshots,
                   kMaxSequenceNumber, kLastLevel, false);
   }
 
@@ -607,7 +613,7 @@ class CompactionJobTestBase : public testing::Test {
       const std::vector<std::vector<FileMetaData*>>& input_files,
       const std::vector<int>& input_levels,
       const std::vector<mock::KVVector>& expected_results,
-      std::vector<SequenceNumber>&& snapshots = {},
+      const std::vector<SequenceNumber>& snapshots = {},
       SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber,
       int output_level = 1, bool verify = true,
       std::vector<uint64_t> expected_oldest_blob_file_numbers = {},
@@ -664,15 +670,13 @@ class CompactionJobTestBase : public testing::Test {
                 ucmp_->timestamp_size() == full_history_ts_low_.size());
     const std::atomic<bool> kManualCompactionCanceledFalse{false};
     JobContext job_context(1, false /* create_superversion */);
-    job_context.InitSnapshotContext(snapshot_checker, nullptr,
-                                    earliest_write_conflict_snapshot,
-                                    std::move(snapshots));
     CompactionJob compaction_job(
         0, &compaction, db_options_, mutable_db_options_, env_options_,
         versions_.get(), &shutting_down_, &log_buffer, nullptr, nullptr,
-        nullptr, nullptr, &mutex_, &error_handler_, &job_context, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_,
-        Env::Priority::USER, nullptr /* IOTracer */,
+        nullptr, nullptr, &mutex_, &error_handler_, snapshots,
+        earliest_write_conflict_snapshot, snapshot_checker, &job_context,
+        table_cache_, &event_logger, false, false, dbname_,
+        &compaction_job_stats_, Env::Priority::USER, nullptr /* IOTracer */,
         /*manual_compaction_canceled=*/kManualCompactionCanceledFalse,
         env_->GenerateUniqueId(), DBImpl::GenerateDbSessionId(nullptr),
         full_history_ts_low_);
@@ -1670,7 +1674,6 @@ TEST_F(CompactionJobTest, ResultSerialization) {
     UniqueId64x2 id{rnd64.Uniform(UINT64_MAX), rnd64.Uniform(UINT64_MAX)};
     result.output_files.emplace_back(
         rnd.RandomString(rnd.Uniform(kStrMaxLen)) /* file_name */,
-        rnd64.Uniform(UINT64_MAX) /* file_size */,
         rnd64.Uniform(UINT64_MAX) /* smallest_seqno */,
         rnd64.Uniform(UINT64_MAX) /* largest_seqno */,
         rnd.RandomBinaryString(
@@ -2037,7 +2040,7 @@ TEST_F(CompactionJobTest, CutToAlignGrandparentBoundarySameKey) {
     snapshots.emplace_back(i);
   }
   RunCompaction({lvl0_files, lvl1_files}, input_levels,
-                {expected_file1, expected_file2}, std::move(snapshots));
+                {expected_file1, expected_file2}, snapshots);
 }
 
 TEST_F(CompactionJobTest, CutForMaxCompactionBytesSameKey) {
@@ -2096,8 +2099,7 @@ TEST_F(CompactionJobTest, CutForMaxCompactionBytesSameKey) {
     snapshots.emplace_back(i);
   }
   RunCompaction({lvl0_files, lvl1_files}, input_levels,
-                {expected_file1, expected_file2, expected_file3},
-                std::move(snapshots));
+                {expected_file1, expected_file2, expected_file3}, snapshots);
 }
 
 class CompactionJobTimestampTest : public CompactionJobTestBase {

db/compaction/compaction_outputs.cc

@@ -54,7 +54,6 @@ Status CompactionOutputs::Finish(
   }
   current_output().finished = true;
   stats_.bytes_written += current_bytes;
-  stats_.bytes_written_pre_comp += builder_->PreCompressionSize();
   stats_.num_output_files = static_cast<int>(outputs_.size());
 
   return s;

db/compaction/compaction_picker.h

@@ -65,7 +65,7 @@ class CompactionPicker {
       const MutableDBOptions& mutable_db_options,
       const std::vector<SequenceNumber>& existing_snapshots,
       const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
-      LogBuffer* log_buffer, bool require_max_output_level) = 0;
+      LogBuffer* log_buffer) = 0;
 
   // The returned Compaction might not include the whole requested range.
   // In that case, compaction_end will be set to the next key that needs
@@ -272,8 +272,7 @@ class NullCompactionPicker : public CompactionPicker {
       const MutableDBOptions& /*mutable_db_options*/,
       const std::vector<SequenceNumber>& /*existing_snapshots*/,
       const SnapshotChecker* /*snapshot_checker*/,
-      VersionStorageInfo* /*vstorage*/, LogBuffer* /* log_buffer */,
-      bool /*require_max_output_level*/ = false) override {
+      VersionStorageInfo* /*vstorage*/, LogBuffer* /* log_buffer */) override {
     return nullptr;
   }
 

db/compaction/compaction_picker_fifo.cc

@@ -428,7 +428,7 @@ Compaction* FIFOCompactionPicker::PickCompaction(
     const MutableDBOptions& mutable_db_options,
     const std::vector<SequenceNumber>& /* existing_snapshots */,
     const SnapshotChecker* /* snapshot_checker */, VersionStorageInfo* vstorage,
-    LogBuffer* log_buffer, bool /* require_max_output_level*/) {
+    LogBuffer* log_buffer) {
   Compaction* c = nullptr;
   if (mutable_cf_options.ttl > 0) {
     c = PickTTLCompaction(cf_name, mutable_cf_options, mutable_db_options,

db/compaction/compaction_picker_fifo.h

@@ -23,8 +23,7 @@ class FIFOCompactionPicker : public CompactionPicker {
       const MutableDBOptions& mutable_db_options,
       const std::vector<SequenceNumber>& /* existing_snapshots */,
       const SnapshotChecker* /* snapshot_checker */,
-      VersionStorageInfo* version, LogBuffer* log_buffer,
-      bool /* require_max_output_level*/ = false) override;
+      VersionStorageInfo* version, LogBuffer* log_buffer) override;
 
   Compaction* CompactRange(const std::string& cf_name,
                            const MutableCFOptions& mutable_cf_options,

db/compaction/compaction_picker_level.cc

@@ -978,7 +978,7 @@ Compaction* LevelCompactionPicker::PickCompaction(
     const MutableDBOptions& mutable_db_options,
     const std::vector<SequenceNumber>& /*existing_snapshots */,
     const SnapshotChecker* /*snapshot_checker*/, VersionStorageInfo* vstorage,
-    LogBuffer* log_buffer, bool /* require_max_output_level*/) {
+    LogBuffer* log_buffer) {
   LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
                                  mutable_cf_options, ioptions_,
                                  mutable_db_options);

db/compaction/compaction_picker_level.h

@@ -25,8 +25,7 @@ class LevelCompactionPicker : public CompactionPicker {
       const MutableDBOptions& mutable_db_options,
       const std::vector<SequenceNumber>& /* existing_snapshots */,
       const SnapshotChecker* /* snapshot_checker */,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      bool /*require_max_output_level*/ = false) override;
+      VersionStorageInfo* vstorage, LogBuffer* log_buffer) override;
 
   bool NeedsCompaction(const VersionStorageInfo* vstorage) const override;
 };

db/compaction/compaction_picker_test.cc

@@ -1134,15 +1134,10 @@ TEST_F(CompactionPickerTest, FIFOToCold1) {
     fifo_options_.max_table_files_size = kMaxSize;
     fifo_options_.file_temperature_age_thresholds = {
         {Temperature::kCold, kColdThreshold}};
-    fifo_options_.allow_trivial_copy_when_change_temperature = true;
-    fifo_options_.trivial_copy_buffer_size = 16 * 1024 * 1024;
     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;
-
-    auto copiedIOptions = ioptions_;
-    copiedIOptions.compaction_style = kCompactionStyleFIFO;
-    FIFOCompactionPicker fifo_compaction_picker(copiedIOptions, &icmp_);
+    FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
     int64_t current_time = 0;
     ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
@@ -1191,10 +1186,7 @@ TEST_F(CompactionPickerTest, FIFOToColdMaxCompactionSize) {
     mutable_cf_options_.compaction_options_fifo = fifo_options_;
     mutable_cf_options_.level0_file_num_compaction_trigger = 100;
     mutable_cf_options_.max_compaction_bytes = kFileSize * 9;
-
-    auto copiedIOptions = ioptions_;
-    copiedIOptions.compaction_style = kCompactionStyleFIFO;
-    FIFOCompactionPicker fifo_compaction_picker(copiedIOptions, &icmp_);
+    FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
     int64_t current_time = 0;
     ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
@@ -1261,10 +1253,7 @@ TEST_F(CompactionPickerTest, FIFOToColdWithExistingCold) {
     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;
-
-    auto copiedIOptions = ioptions_;
-    copiedIOptions.compaction_style = kCompactionStyleFIFO;
-    FIFOCompactionPicker fifo_compaction_picker(copiedIOptions, &icmp_);
+    FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
     int64_t current_time = 0;
     ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
@@ -1329,10 +1318,7 @@ TEST_F(CompactionPickerTest, FIFOToColdWithHotBetweenCold) {
     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;
-
-    auto copiedIOptions = ioptions_;
-    copiedIOptions.compaction_style = kCompactionStyleFIFO;
-    FIFOCompactionPicker fifo_compaction_picker(copiedIOptions, &icmp_);
+    FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
     int64_t current_time = 0;
     ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
@@ -1399,10 +1385,7 @@ TEST_F(CompactionPickerTest, FIFOToHotAndWarm) {
     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;
-
-    auto copiedIOptions = ioptions_;
-    copiedIOptions.compaction_style = kCompactionStyleFIFO;
-    FIFOCompactionPicker fifo_compaction_picker(copiedIOptions, &icmp_);
+    FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
     int64_t current_time = 0;
     ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));

db/compaction/compaction_picker_universal.cc

@@ -38,8 +38,7 @@ class UniversalCompactionBuilder {
       const MutableDBOptions& mutable_db_options,
       const std::vector<SequenceNumber>& existing_snapshots,
       const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
-      UniversalCompactionPicker* picker, LogBuffer* log_buffer,
-      bool require_max_output_level)
+      UniversalCompactionPicker* picker, LogBuffer* log_buffer)
       : ioptions_(ioptions),
         icmp_(icmp),
         cf_name_(cf_name),
@@ -47,8 +46,7 @@ class UniversalCompactionBuilder {
         mutable_db_options_(mutable_db_options),
         vstorage_(vstorage),
         picker_(picker),
-        log_buffer_(log_buffer),
-        require_max_output_level_(require_max_output_level) {
+        log_buffer_(log_buffer) {
     assert(icmp_);
     const auto* ucmp = icmp_->user_comparator();
     assert(ucmp);
@@ -104,174 +102,6 @@ class UniversalCompactionBuilder {
     bool level_has_marked_standalone_rangedel;
   };
 
-  unsigned int GetMaxNumFilesToCompactBasedOnMaxReadAmp(
-      const int file_num_compaction_trigger, const unsigned int ratio,
-      int* num_sr_not_compacted_output, int* max_num_runs_output) const {
-    assert(num_sr_not_compacted_output);
-    assert(max_num_runs_output);
-    int max_num_runs =
-        mutable_cf_options_.compaction_options_universal.max_read_amp;
-    if (max_num_runs < 0) {
-      // any value < -1 is not valid
-      assert(max_num_runs == -1);
-      // By default, fall back to `level0_file_num_compaction_trigger`
-      max_num_runs = file_num_compaction_trigger;
-    } else if (max_num_runs == 0) {
-      if (mutable_cf_options_.compaction_options_universal.stop_style ==
-          kCompactionStopStyleTotalSize) {
-        // 0 means auto-tuning by RocksDB. We estimate max num run based on
-        // max_run_size, size_ratio and write buffer size:
-        // Assume the size of the lowest level size is equal to
-        // write_buffer_size. Each subsequent level is the max size without
-        // triggering size_ratio compaction. `max_num_runs` is the minimum
-        // number of levels required such that the target size of the
-        // largest level is at least `max_run_size_`.
-        max_num_runs = 1;
-        double cur_level_max_size =
-            static_cast<double>(mutable_cf_options_.write_buffer_size);
-        double total_run_size = 0;
-        while (cur_level_max_size < static_cast<double>(max_run_size_)) {
-          // This loop should not take too many iterations since
-          // cur_level_max_size at least doubles each iteration.
-          total_run_size += cur_level_max_size;
-          cur_level_max_size = (100.0 + ratio) / 100.0 * total_run_size;
-          ++max_num_runs;
-        }
-      } else {
-        // TODO: implement the auto-tune logic for this stop style
-        max_num_runs = file_num_compaction_trigger;
-      }
-    } else {
-      // max_num_runs > 0, it's the limit on the number of sorted run
-    }
-
-    // Get the total number of sorted runs that are not being compacted
-    int num_sr_not_compacted = 0;
-    for (size_t i = 0; i < sorted_runs_.size(); i++) {
-      if (sorted_runs_[i].being_compacted == false &&
-          !sorted_runs_[i].level_has_marked_standalone_rangedel) {
-        num_sr_not_compacted++;
-      }
-    }
-
-    *num_sr_not_compacted_output = num_sr_not_compacted;
-    *max_num_runs_output = max_num_runs;
-
-    if (num_sr_not_compacted > max_num_runs) {
-      return num_sr_not_compacted - max_num_runs + 1;
-    } else {
-      return 0;
-    }
-  }
-
-  Compaction* MaybePickPeriodicCompaction(Compaction* const prev_picked_c) {
-    if (prev_picked_c != nullptr ||
-        vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
-      return prev_picked_c;
-    }
-    // Always need to do a full compaction for periodic compaction.
-    Compaction* c = PickPeriodicCompaction();
-    TEST_SYNC_POINT_CALLBACK("PostPickPeriodicCompaction", c);
-    if (c != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: picked for periodic compaction\n",
-                       cf_name_.c_str());
-    }
-    return c;
-  }
-
-  Compaction* MaybePickSizeAmpCompaction(Compaction* const prev_picked_c,
-                                         int file_num_compaction_trigger) {
-    if (prev_picked_c != nullptr ||
-        sorted_runs_.size() <
-            static_cast<size_t>(file_num_compaction_trigger)) {
-      return prev_picked_c;
-    }
-    Compaction* c = PickCompactionToReduceSizeAmp();
-    if (c != nullptr) {
-      TEST_SYNC_POINT("PickCompactionToReduceSizeAmpReturnNonnullptr");
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: picked for size amp compaction \n",
-                       cf_name_.c_str());
-    }
-    return c;
-  }
-
-  Compaction* MaybePickCompactionToReduceSortedRunsBasedFileRatio(
-      Compaction* const prev_picked_c, int file_num_compaction_trigger,
-      unsigned int ratio) {
-    if (prev_picked_c != nullptr ||
-        sorted_runs_.size() <
-            static_cast<size_t>(file_num_compaction_trigger)) {
-      return prev_picked_c;
-    }
-    Compaction* c = PickCompactionToReduceSortedRuns(ratio, UINT_MAX);
-    if (c != nullptr) {
-      TEST_SYNC_POINT("PickCompactionToReduceSortedRunsReturnNonnullptr");
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: picked for size ratio compaction to "
-                       "reduce sorted run\n",
-                       cf_name_.c_str());
-    }
-    return c;
-  }
-
-  Compaction* MaybePickCompactionToReduceSortedRuns(
-      Compaction* const prev_picked_c, int file_num_compaction_trigger,
-      unsigned int ratio) {
-    if (prev_picked_c != nullptr ||
-        sorted_runs_.size() <
-            static_cast<size_t>(file_num_compaction_trigger)) {
-      return prev_picked_c;
-    }
-
-    int num_sr_not_compacted = 0;
-    int max_num_runs = 0;
-    const unsigned int max_num_files_to_compact =
-        GetMaxNumFilesToCompactBasedOnMaxReadAmp(file_num_compaction_trigger,
-                                                 ratio, &num_sr_not_compacted,
-                                                 &max_num_runs);
-    if (max_num_files_to_compact == 0) {
-      ROCKS_LOG_BUFFER(
-          log_buffer_,
-          "[%s] Universal: skipping compaction to reduce sorted run, num "
-          "sorted runs not "
-          "being compacted -- %u, max num runs allowed -- %d, max_run_size "
-          "-- %" PRIu64 "\n",
-          cf_name_.c_str(), num_sr_not_compacted, max_num_runs, max_run_size_);
-      return nullptr;
-    }
-
-    Compaction* c =
-        PickCompactionToReduceSortedRuns(UINT_MAX, max_num_files_to_compact);
-    if (c != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: picked for sorted run num compaction "
-                       "to reduce sorted run, to "
-                       "compact file num -- %u, max num runs allowed"
-                       "-- %d, max_run_size -- %" PRIu64 "\n",
-                       cf_name_.c_str(), max_num_files_to_compact, max_num_runs,
-                       max_run_size_);
-    }
-    return c;
-  }
-
-  Compaction* MaybePickDeleteTriggeredCompaction(
-      Compaction* const prev_picked_c) {
-    if (prev_picked_c != nullptr) {
-      return prev_picked_c;
-    }
-    Compaction* c = PickDeleteTriggeredCompaction();
-    if (c != nullptr) {
-      TEST_SYNC_POINT("PickDeleteTriggeredCompactionReturnNonnullptr");
-      ROCKS_LOG_BUFFER(
-          log_buffer_,
-          "[%s] Universal: picked for delete triggered compaction\n",
-          cf_name_.c_str());
-    }
-    return c;
-  }
-
   // Pick Universal compaction to limit read amplification
   Compaction* PickCompactionToReduceSortedRuns(
       unsigned int ratio, unsigned int max_number_of_files_to_compact);
@@ -419,13 +249,6 @@ class UniversalCompactionBuilder {
     return num_l0_to_exclude;
   }
 
-  bool MeetsOutputLevelRequirements(int output_level) const {
-    return !require_max_output_level_ ||
-           Compaction::OutputToNonZeroMaxOutputLevel(
-               output_level,
-               vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind));
-  }
-
   const ImmutableOptions& ioptions_;
   const InternalKeyComparator* icmp_;
   double score_;
@@ -437,7 +260,6 @@ class UniversalCompactionBuilder {
   VersionStorageInfo* vstorage_;
   UniversalCompactionPicker* picker_;
   LogBuffer* log_buffer_;
-  bool require_max_output_level_;
   // Optional earliest snapshot at time of compaction picking. This is only
   // provided if the column family doesn't enable user-defined timestamps.
   // And this information is only passed to `Compaction` picked by deletion
@@ -598,11 +420,10 @@ Compaction* UniversalCompactionPicker::PickCompaction(
     const MutableDBOptions& mutable_db_options,
     const std::vector<SequenceNumber>& existing_snapshots,
     const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
-    LogBuffer* log_buffer, bool require_max_output_level) {
+    LogBuffer* log_buffer) {
   UniversalCompactionBuilder builder(
       ioptions_, icmp_, cf_name, mutable_cf_options, mutable_db_options,
-      existing_snapshots, snapshot_checker, vstorage, this, log_buffer,
-      require_max_output_level);
+      existing_snapshots, snapshot_checker, vstorage, this, log_buffer);
   return builder.PickCompaction();
 }
 
@@ -733,21 +554,13 @@ bool UniversalCompactionBuilder::ShouldSkipMarkedFile(
 Compaction* UniversalCompactionBuilder::PickCompaction() {
   const int kLevel0 = 0;
   score_ = vstorage_->CompactionScore(kLevel0);
-  const int max_output_level =
+  int max_output_level =
       vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
-  const int file_num_compaction_trigger =
-      mutable_cf_options_.level0_file_num_compaction_trigger;
-  const unsigned int ratio =
-      mutable_cf_options_.compaction_options_universal.size_ratio;
-
-  if (max_output_level == 0 &&
-      !MeetsOutputLevelRequirements(0 /* output_level */)) {
-    return nullptr;
-  }
-
   max_run_size_ = 0;
   sorted_runs_ =
       CalculateSortedRuns(*vstorage_, max_output_level, &max_run_size_);
+  int file_num_compaction_trigger =
+      mutable_cf_options_.level0_file_num_compaction_trigger;
 
   if (sorted_runs_.size() == 0 ||
       (vstorage_->FilesMarkedForPeriodicCompaction().empty() &&
@@ -759,7 +572,6 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
         "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
     return nullptr;
   }
-
   VersionStorageInfo::LevelSummaryStorage tmp;
   ROCKS_LOG_BUFFER_MAX_SZ(
       log_buffer_, 3072,
@@ -767,14 +579,119 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
       cf_name_.c_str(), sorted_runs_.size(), vstorage_->LevelSummary(&tmp));
 
   Compaction* c = nullptr;
+  // Periodic compaction has higher priority than other type of compaction
+  // because it's a hard requirement.
+  if (!vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
+    // Always need to do a full compaction for periodic compaction.
+    c = PickPeriodicCompaction();
+    TEST_SYNC_POINT_CALLBACK("PostPickPeriodicCompaction", c);
+  }
 
-  c = MaybePickPeriodicCompaction(c);
-  c = MaybePickSizeAmpCompaction(c, file_num_compaction_trigger);
-  c = MaybePickCompactionToReduceSortedRunsBasedFileRatio(
-      c, file_num_compaction_trigger, ratio);
-  c = MaybePickCompactionToReduceSortedRuns(c, file_num_compaction_trigger,
-                                            ratio);
-  c = MaybePickDeleteTriggeredCompaction(c);
+  if (c == nullptr &&
+      sorted_runs_.size() >= static_cast<size_t>(file_num_compaction_trigger)) {
+    // Check for size amplification.
+    if ((c = PickCompactionToReduceSizeAmp()) != nullptr) {
+      TEST_SYNC_POINT("PickCompactionToReduceSizeAmpReturnNonnullptr");
+      ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: compacting for size amp\n",
+                       cf_name_.c_str());
+    } else {
+      // Size amplification is within limits. Try reducing read
+      // amplification while maintaining file size ratios.
+      unsigned int ratio =
+          mutable_cf_options_.compaction_options_universal.size_ratio;
+
+      if ((c = PickCompactionToReduceSortedRuns(ratio, UINT_MAX)) != nullptr) {
+        TEST_SYNC_POINT("PickCompactionToReduceSortedRunsReturnNonnullptr");
+        ROCKS_LOG_BUFFER(log_buffer_,
+                         "[%s] Universal: compacting for size ratio\n",
+                         cf_name_.c_str());
+      } else {
+        // Size amplification and file size ratios are within configured limits.
+        // If max read amplification exceeds configured limits, then force
+        // compaction to reduce the number sorted runs without looking at file
+        // size ratios.
+
+        // This is guaranteed by NeedsCompaction()
+        assert(sorted_runs_.size() >=
+               static_cast<size_t>(file_num_compaction_trigger));
+        int max_num_runs =
+            mutable_cf_options_.compaction_options_universal.max_read_amp;
+        if (max_num_runs < 0) {
+          // any value < -1 is not valid
+          assert(max_num_runs == -1);
+          // By default, fall back to `level0_file_num_compaction_trigger`
+          max_num_runs = file_num_compaction_trigger;
+        } else if (max_num_runs == 0) {
+          if (mutable_cf_options_.compaction_options_universal.stop_style ==
+              kCompactionStopStyleTotalSize) {
+            // 0 means auto-tuning by RocksDB. We estimate max num run based on
+            // max_run_size, size_ratio and write buffer size:
+            // Assume the size of the lowest level size is equal to
+            // write_buffer_size. Each subsequent level is the max size without
+            // triggering size_ratio compaction. `max_num_runs` is the minimum
+            // number of levels required such that the target size of the
+            // largest level is at least `max_run_size_`.
+            max_num_runs = 1;
+            double cur_level_max_size =
+                static_cast<double>(mutable_cf_options_.write_buffer_size);
+            double total_run_size = 0;
+            while (cur_level_max_size < static_cast<double>(max_run_size_)) {
+              // This loop should not take too many iterations since
+              // cur_level_max_size at least doubles each iteration.
+              total_run_size += cur_level_max_size;
+              cur_level_max_size = (100.0 + ratio) / 100.0 * total_run_size;
+              ++max_num_runs;
+            }
+          } else {
+            // TODO: implement the auto-tune logic for this stop style
+            max_num_runs = file_num_compaction_trigger;
+          }
+        } else {
+          // max_num_runs > 0, it's the limit on the number of sorted run
+        }
+        // Get the total number of sorted runs that are not being compacted
+        int num_sr_not_compacted = 0;
+        for (size_t i = 0; i < sorted_runs_.size(); i++) {
+          if (sorted_runs_[i].being_compacted == false &&
+              !sorted_runs_[i].level_has_marked_standalone_rangedel) {
+            num_sr_not_compacted++;
+          }
+        }
+
+        // The number of sorted runs that are not being compacted is greater
+        // than the maximum allowed number of sorted runs
+        if (num_sr_not_compacted > max_num_runs) {
+          unsigned int num_files = num_sr_not_compacted - max_num_runs + 1;
+          if ((c = PickCompactionToReduceSortedRuns(UINT_MAX, num_files)) !=
+              nullptr) {
+            ROCKS_LOG_BUFFER(log_buffer_,
+                             "[%s] Universal: compacting for file num, to "
+                             "compact file num -- %u, max num runs allowed"
+                             "-- %d, max_run_size -- %" PRIu64 "\n",
+                             cf_name_.c_str(), num_files, max_num_runs,
+                             max_run_size_);
+          }
+        } else {
+          ROCKS_LOG_BUFFER(
+              log_buffer_,
+              "[%s] Universal: skipping compaction for file num, num runs not "
+              "being compacted -- %u, max num runs allowed -- %d, max_run_size "
+              "-- %" PRIu64 "\n",
+              cf_name_.c_str(), num_sr_not_compacted, max_num_runs,
+              max_run_size_);
+        }
+      }
+    }
+  }
+
+  if (c == nullptr) {
+    if ((c = PickDeleteTriggeredCompaction()) != nullptr) {
+      TEST_SYNC_POINT("PickDeleteTriggeredCompactionReturnNonnullptr");
+      ROCKS_LOG_BUFFER(log_buffer_,
+                       "[%s] Universal: delete triggered compaction\n",
+                       cf_name_.c_str());
+    }
+  }
 
   if (c == nullptr) {
     TEST_SYNC_POINT_CALLBACK(
@@ -783,7 +700,6 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
   }
   assert(c->output_level() <=
          vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind));
-  assert(MeetsOutputLevelRequirements(c->output_level()));
 
   if (mutable_cf_options_.compaction_options_universal.allow_trivial_move ==
           true &&
@@ -909,16 +825,14 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       if (sr->being_compacted) {
         ROCKS_LOG_BUFFER(log_buffer_,
                          "[%s] Universal: %s"
-                         "[%d] being compacted, skipping for compaction to "
-                         "reduce sorted runs",
+                         "[%d] being compacted, skipping",
                          cf_name_.c_str(), file_num_buf, loop);
       } else if (sr->level_has_marked_standalone_rangedel) {
-        ROCKS_LOG_BUFFER(
-            log_buffer_,
-            "[%s] Universal: %s"
-            "[%d] has standalone range tombstone files marked for "
-            "compaction, skipping for compaction to reduce sorted runs",
-            cf_name_.c_str(), file_num_buf, loop);
+        ROCKS_LOG_BUFFER(log_buffer_,
+                         "[%s] Universal: %s"
+                         "[%d] has standalone range tombstone files marked for "
+                         "compaction, skipping",
+                         cf_name_.c_str(), file_num_buf, loop);
       }
 
       sr = nullptr;
@@ -931,8 +845,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf), true);
       ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: Possible candidate for compaction to "
-                       "reduce sorted runs %s[%d].",
+                       "[%s] Universal: Possible candidate %s[%d].",
                        cf_name_.c_str(), file_num_buf, loop);
     }
 
@@ -1034,10 +947,6 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
     output_level = sorted_runs_[first_index_after].level - 1;
   }
 
-  if (!MeetsOutputLevelRequirements(output_level)) {
-    return nullptr;
-  }
-
   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);
@@ -1130,19 +1039,18 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf), true);
       if (sr->being_compacted) {
-        ROCKS_LOG_BUFFER(log_buffer_,
-                         "[%s] Universal: stopping for size amp compaction at "
-                         "sorted run undergoing compaction: "
-                         "%s[%" ROCKSDB_PRIszt "]",
-                         cf_name_.c_str(), file_num_buf, start_index - 1);
+        ROCKS_LOG_BUFFER(
+            log_buffer_,
+            "[%s] Universal: stopping at sorted run undergoing compaction: "
+            "%s[%" ROCKSDB_PRIszt "]",
+            cf_name_.c_str(), file_num_buf, start_index - 1);
       } else if (sr->level_has_marked_standalone_rangedel) {
-        ROCKS_LOG_BUFFER(log_buffer_,
-                         "[%s] Universal: stopping for size amp compaction at "
-                         "sorted run that has "
-                         "standalone range "
-                         "tombstone files marked for compaction: "
-                         "%s[%" ROCKSDB_PRIszt "]",
-                         cf_name_.c_str(), file_num_buf, start_index - 1);
+        ROCKS_LOG_BUFFER(
+            log_buffer_,
+            "[%s] Universal: stopping at sorted run that has standalone range "
+            "tombstone files marked for compaction: "
+            "%s[%" ROCKSDB_PRIszt "]",
+            cf_name_.c_str(), file_num_buf, start_index - 1);
       }
       break;
     }
@@ -1158,12 +1066,11 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
   {
     const size_t num_l0_to_exclude = MightExcludeNewL0sToReduceWriteStop(
         num_l0_files, end_index, start_index, candidate_size);
-    ROCKS_LOG_BUFFER(
-        log_buffer_,
-        "[%s] Universal: Excluding for size amp compaction %" ROCKSDB_PRIszt
-        " latest L0 files to reduce potential write stop "
-        "triggered by `level0_stop_writes_trigger`",
-        cf_name_.c_str(), num_l0_to_exclude);
+    ROCKS_LOG_BUFFER(log_buffer_,
+                     "[%s] Universal: Excluding %" ROCKSDB_PRIszt
+                     " latest L0 files to reduce potential write stop "
+                     "triggered by `level0_stop_writes_trigger`",
+                     cf_name_.c_str(), num_l0_to_exclude);
   }
 
   {
@@ -1181,18 +1088,18 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
 
   // size amplification = percentage of additional size
   if (candidate_size * 100 < ratio * base_sr_size) {
-    ROCKS_LOG_BUFFER(log_buffer_,
-                     "[%s] Universal: size amp compction not needed. "
-                     "newer-files-total-size %" PRIu64
-                     " earliest-file-size %" PRIu64,
-                     cf_name_.c_str(), candidate_size, base_sr_size);
+    ROCKS_LOG_BUFFER(
+        log_buffer_,
+        "[%s] Universal: size amp not needed. newer-files-total-size %" PRIu64
+        " earliest-file-size %" PRIu64,
+        cf_name_.c_str(), candidate_size, base_sr_size);
     return nullptr;
   } else {
-    ROCKS_LOG_BUFFER(log_buffer_,
-                     "[%s] Universal: size amp compaction needed. "
-                     "newer-files-total-size %" PRIu64
-                     " earliest-file-size %" PRIu64,
-                     cf_name_.c_str(), candidate_size, base_sr_size);
+    ROCKS_LOG_BUFFER(
+        log_buffer_,
+        "[%s] Universal: size amp needed. newer-files-total-size %" PRIu64
+        " earliest-file-size %" PRIu64,
+        cf_name_.c_str(), candidate_size, base_sr_size);
   }
   // Since incremental compaction can't include more than second last
   // level, it can introduce penalty, compared to full compaction. We
@@ -1543,10 +1450,6 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
     }
     assert(output_level <= max_output_level);
 
-    if (!MeetsOutputLevelRequirements(output_level)) {
-      return nullptr;
-    }
-
     if (output_level != 0) {
       if (start_level == 0) {
         if (!picker_->GetOverlappingL0Files(vstorage_, &start_level_inputs,
@@ -1671,10 +1574,6 @@ Compaction* UniversalCompactionBuilder::PickCompactionWithSortedRunRange(
     output_level = sorted_runs_[end_index + 1].level - 1;
   }
 
-  if (!MeetsOutputLevelRequirements(output_level)) {
-    return nullptr;
-  }
-
   // intra L0 compactions outputs could have overlap
   if (output_level != 0 && picker_->FilesRangeOverlapWithCompaction(
                                inputs, output_level,

db/compaction/compaction_picker_universal.h

@@ -18,15 +18,12 @@ class UniversalCompactionPicker : public CompactionPicker {
   UniversalCompactionPicker(const ImmutableOptions& ioptions,
                             const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
-
-  // If `require_max_output_level` is true, only pick compaction
-  // with max output level or return nullptr if no such compaction exists.
   Compaction* PickCompaction(
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
       const MutableDBOptions& mutable_db_options,
       const std::vector<SequenceNumber>& existing_snapshots,
       const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
-      LogBuffer* log_buffer, bool require_max_output_level = false) override;
+      LogBuffer* log_buffer) override;
   int MaxOutputLevel() const override { return NumberLevels() - 1; }
 
   bool NeedsCompaction(const VersionStorageInfo* vstorage) const override;

db/compaction/compaction_service_job.cc

@@ -41,7 +41,7 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
   }
 
   compaction_input.cf_name = compaction->column_family_data()->GetName();
-  compaction_input.snapshots = job_context_->snapshot_seqs;
+  compaction_input.snapshots = existing_snapshots_;
   compaction_input.has_begin = sub_compact->start.has_value();
   compaction_input.begin =
       compaction_input.has_begin ? sub_compact->start->ToString() : "";
@@ -74,9 +74,7 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
       compaction->column_family_data()->GetName().c_str(), job_id_,
       compaction_input.output_level, input_files_oss.str().c_str());
   CompactionServiceJobInfo info(
-      dbname_, db_id_, db_session_id_,
-      compaction->column_family_data()->GetID(),
-      compaction->column_family_data()->GetName(), GetCompactionId(sub_compact),
+      dbname_, db_id_, db_session_id_, GetCompactionId(sub_compact),
       thread_pri_, compaction->compaction_reason(),
       compaction->is_full_compaction(), compaction->is_manual_compaction(),
       compaction->bottommost_level(), compaction->start_level(),
@@ -115,7 +113,7 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
   }
 
   std::string debug_str_before_wait =
-      compaction->input_version()->DebugString(/*hex=*/true);
+      compaction->input_version()->DebugString();
 
   ROCKS_LOG_INFO(db_options_.info_log,
                  "[%s] [JOB %d] Waiting for remote compaction...",
@@ -126,14 +124,13 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
                                            &compaction_result_binary);
 
   if (compaction_status != CompactionServiceJobStatus::kSuccess) {
-    ROCKS_LOG_ERROR(
-        db_options_.info_log,
-        "[%s] [JOB %d] Wait() status is not kSuccess. "
-        "\nDebugString Before Wait():\n%s"
-        "\nDebugString After Wait():\n%s",
-        compaction->column_family_data()->GetName().c_str(), job_id_,
-        debug_str_before_wait.c_str(),
-        compaction->input_version()->DebugString(/*hex=*/true).c_str());
+    ROCKS_LOG_ERROR(db_options_.info_log,
+                    "[%s] [JOB %d] Wait() status is not kSuccess. "
+                    "\nDebugString Before Wait():\n%s"
+                    "\nDebugString After Wait():\n%s",
+                    compaction->column_family_data()->GetName().c_str(),
+                    job_id_, debug_str_before_wait.c_str(),
+                    compaction->input_version()->DebugString().c_str());
   }
 
   if (compaction_status == CompactionServiceJobStatus::kUseLocal) {
@@ -221,24 +218,18 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     }
 
     FileMetaData meta;
-    uint64_t file_size = file.file_size;
-
-    // TODO - Clean this up in the next release.
-    // For backward compatibility - in case the remote worker does not populate
-    // the file_size yet. If missing, continue to populate this from the file
-    // system.
-    if (file_size == 0) {
-      s = fs_->GetFileSize(tgt_file, IOOptions(), &file_size, nullptr);
-    }
-
+    uint64_t file_size;
+    // FIXME: file_size should be part of CompactionServiceOutputFile so that
+    // we don't get DB corruption if the full file size has not been propagated
+    // back to the caller through the file system (which could have metadata
+    // lag or caching bugs).
+    s = fs_->GetFileSize(tgt_file, IOOptions(), &file_size, nullptr);
     if (!s.ok()) {
       sub_compact->status = s;
       db_options_.compaction_service->OnInstallation(
           response.scheduled_job_id, CompactionServiceJobStatus::kFailure);
       return CompactionServiceJobStatus::kFailure;
     }
-    assert(file_size > 0);
-
     meta.fd = FileDescriptor(file_num, compaction->output_path_id(), file_size,
                              file.smallest_seqno, file.largest_seqno);
     meta.smallest.DecodeFrom(file.smallest_internal_key);
@@ -304,9 +295,9 @@ CompactionServiceCompactionJob::CompactionServiceCompactionJob(
     VersionSet* versions, const std::atomic<bool>* shutting_down,
     LogBuffer* log_buffer, FSDirectory* output_directory, Statistics* stats,
     InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
-    JobContext* job_context, std::shared_ptr<Cache> table_cache,
-    EventLogger* event_logger, const std::string& dbname,
-    const std::shared_ptr<IOTracer>& io_tracer,
+    std::vector<SequenceNumber> existing_snapshots,
+    std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
+    const std::string& dbname, const std::shared_ptr<IOTracer>& io_tracer,
     const std::atomic<bool>& manual_compaction_canceled,
     const std::string& db_id, const std::string& db_session_id,
     std::string output_path,
@@ -315,8 +306,9 @@ CompactionServiceCompactionJob::CompactionServiceCompactionJob(
     : CompactionJob(job_id, compaction, db_options, mutable_db_options,
                     file_options, versions, shutting_down, log_buffer, nullptr,
                     output_directory, nullptr, stats, db_mutex,
-                    db_error_handler, job_context, std::move(table_cache),
-                    event_logger,
+                    db_error_handler, std::move(existing_snapshots),
+                    kMaxSequenceNumber, nullptr, nullptr,
+                    std::move(table_cache), event_logger,
                     compaction->mutable_cf_options().paranoid_file_checks,
                     compaction->mutable_cf_options().report_bg_io_stats, dbname,
                     &(compaction_service_result->stats), Env::Priority::USER,
@@ -426,14 +418,14 @@ Status CompactionServiceCompactionJob::Run() {
     for (const auto& output_file : sub_compact->GetOutputs()) {
       auto& meta = output_file.meta;
       compaction_result_->output_files.emplace_back(
-          MakeTableFileName(meta.fd.GetNumber()), meta.fd.GetFileSize(),
-          meta.fd.smallest_seqno, meta.fd.largest_seqno,
-          meta.smallest.Encode().ToString(), meta.largest.Encode().ToString(),
-          meta.oldest_ancester_time, meta.file_creation_time, meta.epoch_number,
-          meta.file_checksum, meta.file_checksum_func_name,
-          output_file.validator.GetHash(), meta.marked_for_compaction,
-          meta.unique_id, *output_file.table_properties,
-          output_file.is_proximal_level, meta.temperature);
+          MakeTableFileName(meta.fd.GetNumber()), meta.fd.smallest_seqno,
+          meta.fd.largest_seqno, meta.smallest.Encode().ToString(),
+          meta.largest.Encode().ToString(), meta.oldest_ancester_time,
+          meta.file_creation_time, meta.epoch_number, meta.file_checksum,
+          meta.file_checksum_func_name, output_file.validator.GetHash(),
+          meta.marked_for_compaction, meta.unique_id,
+          *output_file.table_properties, output_file.is_proximal_level,
+          meta.temperature);
     }
   }
 
@@ -533,10 +525,6 @@ static std::unordered_map<std::string, OptionTypeInfo>
          {offsetof(struct CompactionServiceOutputFile, file_name),
           OptionType::kEncodedString, OptionVerificationType::kNormal,
           OptionTypeFlags::kNone}},
-        {"file_size",
-         {offsetof(struct CompactionServiceOutputFile, file_size),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
         {"smallest_seqno",
          {offsetof(struct CompactionServiceOutputFile, smallest_seqno),
           OptionType::kUInt64T, OptionVerificationType::kNormal,

db/compaction/compaction_service_test.cc

@@ -7,7 +7,6 @@
 #include "port/stack_trace.h"
 #include "rocksdb/utilities/options_util.h"
 #include "table/unique_id_impl.h"
-#include "utilities/merge_operators/string_append/stringappend.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -22,10 +21,10 @@ class MyTestCompactionService : public CompactionService {
       : db_path_(std::move(db_path)),
         options_(options),
         statistics_(statistics),
-        start_info_("na", "na", "na", 0, "na", 0, Env::TOTAL,
-                    CompactionReason::kUnknown, false, false, false, -1, -1),
-        wait_info_("na", "na", "na", 0, "na", 0, Env::TOTAL,
-                   CompactionReason::kUnknown, false, false, false, -1, -1),
+        start_info_("na", "na", "na", 0, Env::TOTAL, CompactionReason::kUnknown,
+                    false, false, false, -1, -1),
+        wait_info_("na", "na", "na", 0, Env::TOTAL, CompactionReason::kUnknown,
+                   false, false, false, -1, -1),
         listeners_(listeners),
         table_properties_collector_factories_(
             std::move(table_properties_collector_factories)) {}
@@ -435,30 +434,6 @@ TEST_F(CompactionServiceTest, ManualCompaction) {
   ASSERT_OK(result.status);
   ASSERT_TRUE(result.stats.is_manual_compaction);
   ASSERT_TRUE(result.stats.is_remote_compaction);
-
-  auto info = my_cs->GetCompactionInfoForStart();
-  ASSERT_EQ(0, info.cf_id);
-  ASSERT_EQ(kDefaultColumnFamilyName, info.cf_name);
-
-  info = my_cs->GetCompactionInfoForWait();
-  ASSERT_EQ(0, info.cf_id);
-  ASSERT_EQ(kDefaultColumnFamilyName, info.cf_name);
-
-  // Test non-default CF
-  ASSERT_OK(
-      db_->CompactRange(CompactRangeOptions(), handles_[1], nullptr, nullptr));
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-
-  info = my_cs->GetCompactionInfoForStart();
-  ASSERT_EQ(handles_[1]->GetID(), info.cf_id);
-  ASSERT_EQ(handles_[1]->GetName(), info.cf_name);
-
-  info = my_cs->GetCompactionInfoForWait();
-  ASSERT_EQ(handles_[1]->GetID(), info.cf_id);
-  ASSERT_EQ(handles_[1]->GetName(), info.cf_name);
 }
 
 TEST_F(CompactionServiceTest, CompactionOutputFileIOError) {
@@ -1223,32 +1198,6 @@ TEST_F(CompactionServiceTest, CompactionFilter) {
   ASSERT_GE(my_cs->GetCompactionNum(), 1);
 }
 
-TEST_F(CompactionServiceTest, MergeOperator) {
-  Options options = CurrentOptions();
-  options.merge_operator.reset(new StringAppendOperator(','));
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  for (int i = 0; i < 200; i++) {
-    ASSERT_OK(db_->Merge(WriteOptions(), Key(i),
-                         "merge_op_append_" + std::to_string(i)));
-  }
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  // verify result
-  for (int i = 0; i < 200; i++) {
-    auto result = Get(Key(i));
-    if (i % 2) {
-      ASSERT_EQ(result, "value" + std::to_string(i) + ",merge_op_append_" +
-                            std::to_string(i));
-    } else {
-      ASSERT_EQ(result, "value_new" + std::to_string(i) + ",merge_op_append_" +
-                            std::to_string(i));
-    }
-  }
-  auto my_cs = GetCompactionService();
-  ASSERT_GE(my_cs->GetCompactionNum(), 1);
-}
-
 TEST_F(CompactionServiceTest, Snapshot) {
   Options options = CurrentOptions();
   ReopenWithCompactionService(&options);
@@ -1422,7 +1371,6 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
   ASSERT_EQ(true, info.bottommost_level);
   ASSERT_EQ(1, info.base_input_level);
   ASSERT_EQ(2, info.output_level);
-  ASSERT_EQ(kDefaultColumnFamilyName, info.cf_name);
 
   // Test priority BOTTOM
   env_->SetBackgroundThreads(1, Env::BOTTOM);

db/compaction/subcompaction_state.h

@@ -106,11 +106,7 @@ class SubcompactionState {
     subcompaction_job_info.subcompaction_job_id = static_cast<int>(sub_job_id);
     subcompaction_job_info.base_input_level = c->start_level();
     subcompaction_job_info.output_level = c->output_level();
-    subcompaction_job_info.compaction_reason = c->compaction_reason();
-    subcompaction_job_info.compression = c->output_compression();
     subcompaction_job_info.stats = compaction_job_stats;
-    subcompaction_job_info.blob_compression_type =
-        c->mutable_cf_options().blob_compression_type;
   }
 
   SubcompactionState() = delete;

db/compaction/tiered_compaction_test.cc

@@ -225,8 +225,6 @@ TEST_F(TieredCompactionTest, SequenceBasedTieredStorageUniversal) {
     flush_stats.micros = 1;
     flush_stats.bytes_written = bytes_per_file;
     flush_stats.num_output_files = 1;
-    flush_stats.num_input_records = kNumKeys;
-    flush_stats.num_output_records = kNumKeys;
     expect_stats[0].Add(flush_stats);
   }
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
@@ -1082,8 +1080,6 @@ TEST_F(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     flush_stats.micros = 1;
     flush_stats.bytes_written = bytes_per_file;
     flush_stats.num_output_files = 1;
-    flush_stats.num_input_records = kNumKeys;
-    flush_stats.num_output_records = kNumKeys;
     expect_stats[0].Add(flush_stats);
   }
   ASSERT_OK(dbfull()->TEST_WaitForCompact());

db/convenience.cc

@@ -93,10 +93,9 @@ Status VerifySstFileChecksumInternal(const Options& options,
           nullptr /* file_read_hist */, ioptions.rate_limiter.get()));
   const bool kImmortal = true;
   auto reader_options = TableReaderOptions(
-      ioptions, options.prefix_extractor, options.compression_manager.get(),
-      env_options, internal_comparator, options.block_protection_bytes_per_key,
-      false /* skip_filters */, !kImmortal, false /* force_direct_prefetch */,
-      -1 /* level */);
+      ioptions, options.prefix_extractor, env_options, internal_comparator,
+      options.block_protection_bytes_per_key, false /* skip_filters */,
+      !kImmortal, false /* force_direct_prefetch */, -1 /* level */);
   reader_options.largest_seqno = largest_seqno;
   s = options.table_factory->NewTableReader(
       read_options, reader_options, std::move(file_reader), file_size,

db/corruption_test.cc

@@ -851,6 +851,9 @@ TEST_F(CorruptionTest, ParanoidFileChecksOnCompact) {
   options.env = env_.get();
   options.paranoid_file_checks = true;
   options.create_if_missing = true;
+  // Skip verifying record count against TableProperties for
+  // MockTables
+  options.compaction_verify_record_count = false;
   Status s;
   for (const auto& mode : corruption_modes) {
     delete db_;

db/db_basic_test.cc

@@ -5086,7 +5086,6 @@ TEST_F(DBBasicTest, DisallowMemtableWrite) {
   options_allow.create_if_missing = true;
   Options options_disallow = options_allow;
   options_disallow.disallow_memtable_writes = true;
-  options_disallow.paranoid_memory_checks = true;
 
   DestroyAndReopen(options_allow);
   // CFs allowing and disallowing memtable write
@@ -5126,11 +5125,6 @@ TEST_F(DBBasicTest, DisallowMemtableWrite) {
   EXPECT_EQ(Get(2, "b2"), "2");
   EXPECT_EQ(Get(3, "b3"), "NOT_FOUND");
 
-  std::unique_ptr<Iterator> iter(
-      dbfull()->NewIterator(ReadOptions(), handles_[3]));
-  iter->Seek("a3");
-  ASSERT_OK(iter->status());
-  iter.reset();
   // When the DB is re-opened with WAL entries for a CF that is newly setting
   // disallow_memtable_writes, we detect that and fail the open gracefully.
   ASSERT_EQ(TryReopenWithColumnFamilies(

db/db_block_cache_test.cc

@@ -506,8 +506,6 @@ TEST_P(DBBlockCacheTest1, WarmCacheWithBlocksDuringFlush) {
   table_options.prepopulate_block_cache =
       BlockBasedTableOptions::PrepopulateBlockCache::kFlushOnly;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  // Include a compression dictionary block
-  options.compression_opts.max_dict_bytes = 123;
   DestroyAndReopen(options);
 
   std::string value(kValueSize, 'a');
@@ -539,9 +537,6 @@ TEST_P(DBBlockCacheTest1, WarmCacheWithBlocksDuringFlush) {
                 options.statistics->getTickerCount(BLOCK_CACHE_FILTER_HIT));
     }
     ASSERT_EQ(0, options.statistics->getTickerCount(BLOCK_CACHE_FILTER_MISS));
-
-    // Including compression dict
-    ASSERT_EQ(0, options.statistics->getTickerCount(BLOCK_CACHE_MISS));
   }
 
   // Verify compaction not counted
@@ -829,79 +824,68 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
   const int kNumEntriesPerFile = 128;
   const int kNumBytesPerEntry = 1024;
 
-  std::vector<CompressionType> dict_compressions =
-      GetSupportedDictCompressions();
+  // Try all the available libraries that support dictionary compression
+  std::vector<CompressionType> compression_types;
+  if (Zlib_Supported()) {
+    compression_types.push_back(kZlibCompression);
+  }
+  if (LZ4_Supported()) {
+    compression_types.push_back(kLZ4Compression);
+    compression_types.push_back(kLZ4HCCompression);
+  }
+  if (ZSTD_Supported()) {
+    compression_types.push_back(kZSTD);
+  }
   Random rnd(301);
-  // Format version before and after compression handling changes
-  TEST_AllowUnsupportedFormatVersion() = true;
-  for (int format_version : {6, 7}) {
-    // Test all supported compression types because (at least historically)
-    // dictionary compression could be enabled and a dictionary block saved
-    // but ignored by some compression types. Ensure we at least don't crash
-    // or return corruption for those.
-    for (auto compression_type : GetSupportedCompressions()) {
-      // Extra handling checks only for types actually supporting dictionary
-      // compression.
-      bool dict_supported =
-          std::count(dict_compressions.begin(), dict_compressions.end(),
-                     compression_type) > 0;
+  for (auto compression_type : compression_types) {
+    Options options = CurrentOptions();
+    options.bottommost_compression = compression_type;
+    options.bottommost_compression_opts.max_dict_bytes = 4096;
+    options.bottommost_compression_opts.enabled = true;
+    options.create_if_missing = true;
+    options.num_levels = 2;
+    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.target_file_size_base = kNumEntriesPerFile * kNumBytesPerEntry;
+    BlockBasedTableOptions table_options;
+    table_options.cache_index_and_filter_blocks = true;
+    table_options.block_cache.reset(new MockCache());
+    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+    DestroyAndReopen(options);
 
-      Options options = CurrentOptions();
-      options.bottommost_compression = compression_type;
-      options.bottommost_compression_opts.max_dict_bytes = 4096;
-      options.bottommost_compression_opts.enabled = true;
-      options.create_if_missing = true;
-      options.num_levels = 2;
-      options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-      options.target_file_size_base = kNumEntriesPerFile * kNumBytesPerEntry;
-      BlockBasedTableOptions table_options;
-      table_options.cache_index_and_filter_blocks = true;
-      table_options.block_cache.reset(new MockCache());
-      table_options.format_version = format_version;
-      options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-      DestroyAndReopen(options);
+    RecordCacheCountersForCompressionDict(options);
 
-      RecordCacheCountersForCompressionDict(options);
-
-      for (int i = 0; i < kNumFiles; ++i) {
-        ASSERT_EQ(i, NumTableFilesAtLevel(0, 0));
-        for (int j = 0; j < kNumEntriesPerFile; ++j) {
-          std::string value = rnd.RandomString(kNumBytesPerEntry);
-          ASSERT_OK(Put(Key(j * kNumFiles + i), value.c_str()));
-        }
-        ASSERT_OK(Flush());
-      }
-      ASSERT_OK(dbfull()->TEST_WaitForCompact());
-      ASSERT_EQ(0, NumTableFilesAtLevel(0));
-      ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(1));
-
-      if (dict_supported) {
-        // Compression dictionary blocks are preloaded.
-        CheckCacheCountersForCompressionDict(
-            options, kNumFiles /* expected_compression_dict_misses */,
-            0 /* expected_compression_dict_hits */,
-            kNumFiles /* expected_compression_dict_inserts */);
-      }
-
-      // Seek to a key in a file. It should cause the SST's dictionary
-      // meta-block to be read.
-      RecordCacheCounters(options);
-      RecordCacheCountersForCompressionDict(options);
-      ReadOptions read_options;
-      ASSERT_NE("NOT_FOUND", Get(Key(kNumFiles * kNumEntriesPerFile - 1)));
-
-      if (dict_supported) {
-        // Two block hits: index and dictionary since they are prefetched
-        // One block missed/added: data block
-        CheckCacheCounters(options, 1 /* expected_misses */,
-                           2 /* expected_hits */, 1 /* expected_inserts */,
-                           0 /* expected_failures */);
-        CheckCacheCountersForCompressionDict(
-            options, 0 /* expected_compression_dict_misses */,
-            1 /* expected_compression_dict_hits */,
-            0 /* expected_compression_dict_inserts */);
+    for (int i = 0; i < kNumFiles; ++i) {
+      ASSERT_EQ(i, NumTableFilesAtLevel(0, 0));
+      for (int j = 0; j < kNumEntriesPerFile; ++j) {
+        std::string value = rnd.RandomString(kNumBytesPerEntry);
+        ASSERT_OK(Put(Key(j * kNumFiles + i), value.c_str()));
       }
+      ASSERT_OK(Flush());
     }
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    ASSERT_EQ(0, NumTableFilesAtLevel(0));
+    ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(1));
+
+    // Compression dictionary blocks are preloaded.
+    CheckCacheCountersForCompressionDict(
+        options, kNumFiles /* expected_compression_dict_misses */,
+        0 /* expected_compression_dict_hits */,
+        kNumFiles /* expected_compression_dict_inserts */);
+
+    // Seek to a key in a file. It should cause the SST's dictionary meta-block
+    // to be read.
+    RecordCacheCounters(options);
+    RecordCacheCountersForCompressionDict(options);
+    ReadOptions read_options;
+    ASSERT_NE("NOT_FOUND", Get(Key(kNumFiles * kNumEntriesPerFile - 1)));
+    // Two block hits: index and dictionary since they are prefetched
+    // One block missed/added: data block
+    CheckCacheCounters(options, 1 /* expected_misses */, 2 /* expected_hits */,
+                       1 /* expected_inserts */, 0 /* expected_failures */);
+    CheckCacheCountersForCompressionDict(
+        options, 0 /* expected_compression_dict_misses */,
+        1 /* expected_compression_dict_hits */,
+        0 /* expected_compression_dict_inserts */);
   }
 }
 

db/db_compaction_test.cc

@@ -455,72 +455,6 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
   }
 }
 #endif  // !defined(ROCKSDB_VALGRIND_RUN) || defined(ROCKSDB_FULL_VALGRIND_RUN)
-TEST_F(DBCompactionTest, UniversalReduceFileLockingRepickNothing) {
-  const int kFileNumCompactionTrigger = 3;
-
-  Options options = CurrentOptions();
-  options.compaction_options_universal.reduce_file_locking = true;
-  // Set `max_background_jobs` to be 3 to allow low and bottom priority thread
-  // to run compaction together
-  options.max_background_jobs = 3;
-  Env::Default()->SetBackgroundThreads(1, Env::Priority::BOTTOM);
-  options.num_levels = 3;
-  options.compaction_style = kCompactionStyleUniversal;
-  options.level0_file_num_compaction_trigger = kFileNumCompactionTrigger;
-  options.compaction_options_universal.max_size_amplification_percent = 1;
-
-  DestroyAndReopen(options);
-
-  // Need to get a token to enable compaction parallelism up to
-  // `max_background_compactions` jobs.
-  auto pressure_token =
-      dbfull()->TEST_write_controler().GetCompactionPressureToken();
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {// Wait for the full (bottom-priority) compaction to be pre-picked as an
-       // intent (that is allowing files to be picked by other compactions and
-       // will pick later when the bottom-priority thread is available to
-       // execute the compaction) before triggering the low-priority compaction.
-       {"DBImpl::BackgroundCompaction:ForwardToBottomPriPool",
-        "LowPriCompaction"},
-       // Wait for low-priority compaction to start before
-       // repicking for the full compaction intent (bottom-priority), enabling
-       // them to run in parallel.
-       {"DBImpl::BackgroundCompaction:NonTrivial",
-        "DBImpl::BGWorkBottomCompaction"}});
-
-  bool bottom_pri_compaction_attempt_repick = false;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::BackgroundCompaction():AfterPickCompactionBottomPri",
-      [&](void* arg) {
-        bottom_pri_compaction_attempt_repick = true;
-        Compaction* c = static_cast<Compaction*>(arg);
-        // Verify the intended full compaction for bottom priority thread does
-        // not get to run (i.e, output to bottommost level) since when it
-        // repicks its files, some of the the intended input files are already
-        // compacted by the low priority thread
-        assert(c == nullptr);
-      });
-
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  for (int i = 0; i < kFileNumCompactionTrigger; ++i) {
-    if (i == 0) {
-      ASSERT_OK(Put("file_locked_for_bottom_pri_compaction", "value"));
-    } else {
-      ASSERT_OK(
-          Put("file_not_locked_for_bottom_pri_compaction" + std::to_string(i),
-              "value"));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  TEST_SYNC_POINT("LowPriCompaction");
-  ASSERT_OK(Put("a_new_file_to_pick_for_low_pri_compaction", "value"));
-  ASSERT_OK(Flush());
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  ASSERT_TRUE(bottom_pri_compaction_attempt_repick);
-}
 
 TEST_F(DBCompactionTest, SkipStatsUpdateTest) {
   // This test verify UpdateAccumulatedStats is not on
@@ -2890,99 +2824,46 @@ TEST_F(DBCompactionTest, L0_CompactionBug_Issue44_b) {
 }
 
 TEST_F(DBCompactionTest, ManualAutoRace) {
-  const int kNumL0FilesTrigger = 4;
-  // Verify that the auto compaction is retried after the conflicting exclusive
-  // manual compaction finishes for:
-  // 1. Non-bottom-priority compactions (tested with level compaction)
-  // 2. Bottom-priority compactions (tested with universal compaction)
-  for (auto compaction_style :
-       {kCompactionStyleLevel, kCompactionStyleUniversal}) {
-    Env::Default()->SetBackgroundThreads(
-        compaction_style == kCompactionStyleUniversal ? 2 : 0,
-        Env::Priority::BOTTOM);
-    for (auto universal_reduce_file_locking : {false, true}) {
-      if (compaction_style != kCompactionStyleUniversal &&
-          universal_reduce_file_locking) {
-        continue;
-      }
+  CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::BGWorkCompaction", "DBCompactionTest::ManualAutoRace:1"},
+       {"DBImpl::RunManualCompaction:WaitScheduled",
+        "BackgroundCallCompaction:0"}});
 
-      Options options = CurrentOptions();
-      options.num_levels = 3;
-      options.level0_file_num_compaction_trigger = kNumL0FilesTrigger;
-      options.compaction_style = compaction_style;
-      options.compaction_options_universal.reduce_file_locking =
-          universal_reduce_file_locking;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
-      DestroyAndReopen(options);
-      CreateAndReopenWithCF({"exclusive_manual_compaction_cf"}, options);
+  ASSERT_OK(Put(1, "foo", ""));
+  ASSERT_OK(Put(1, "bar", ""));
+  ASSERT_OK(Flush(1));
+  ASSERT_OK(Put(1, "foo", ""));
+  ASSERT_OK(Put(1, "bar", ""));
+  // Generate four files in CF 0, which should trigger an auto compaction
+  ASSERT_OK(Put("foo", ""));
+  ASSERT_OK(Put("bar", ""));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("foo", ""));
+  ASSERT_OK(Put("bar", ""));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("foo", ""));
+  ASSERT_OK(Put("bar", ""));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("foo", ""));
+  ASSERT_OK(Put("bar", ""));
+  ASSERT_OK(Flush());
 
-      // Set up sync points to ensure that the auto compaction
-      // encounters a conflict from exclusive manual compaction before the auto
-      // compaction gets to pick files, This will trigger a retry later.
-      //
-      // Specifically, the sync points are set up as following:
-      // 1. Wait until background low-pri scheduled (not picking files yet) or
-      // bottom-pri scheduled (not repicking files yet) for
-      // `universal_reduce_file_locking = true` before triggering
-      // CompactRange()
-      //
-      // 2. Wait until the triggered CompactRange()
-      // registers its compaction and creates conflict before the auto
-      // compaction picks or repicks files for the background compaction.
-      if (compaction_style == kCompactionStyleLevel ||
-          !universal_reduce_file_locking) {
-        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-            {{"DBImpl::BGWorkCompaction", "DBCompactionTest::ManualAutoRace:1"},
-             {"DBImpl::RunManualCompaction:WaitScheduled",
-              "BackgroundCallCompaction:0"}});
-      } else {
-        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-            {{"DBImpl::BackgroundCompaction:ForwardToBottomPriPool",
-              "DBCompactionTest::ManualAutoRace:1"},
-             {"DBImpl::RunManualCompaction:WaitScheduled",
-              "BackgroundCallCompaction:0:BottomPri"}});
-      }
+  // The auto compaction is scheduled but waited until here
+  TEST_SYNC_POINT("DBCompactionTest::ManualAutoRace:1");
+  // The auto compaction will wait until the manual compaction is registerd
+  // before processing so that it will be cancelled.
+  CompactRangeOptions cro;
+  cro.exclusive_manual_compaction = true;
+  ASSERT_OK(dbfull()->CompactRange(cro, handles_[1], nullptr, nullptr));
+  ASSERT_EQ("0,1", FilesPerLevel(1));
 
-      bool encounter_conflict = false;
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-          "DBImpl::BackgroundCompaction()::Conflict",
-          [&](void* /*arg*/) { encounter_conflict = true; });
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-      // Generate files in CF 1 for exclusive CompactRange()
-      ASSERT_OK(Put(1, "foo", ""));
-      ASSERT_OK(Put(1, "bar", ""));
-      ASSERT_OK(Flush(1));
-      ASSERT_OK(Put(1, "foo", ""));
-      ASSERT_OK(Put(1, "bar", ""));
-      // Generate files in CF0 to trigger full compaction
-      for (int i = 0; i < kNumL0FilesTrigger; ++i) {
-        ASSERT_OK(Put("foo", ""));
-        ASSERT_OK(Put("bar", ""));
-        ASSERT_OK(Flush());
-      }
-
-      TEST_SYNC_POINT("DBCompactionTest::ManualAutoRace:1");
-      CompactRangeOptions cro;
-      cro.exclusive_manual_compaction = true;
-      ASSERT_OK(dbfull()->CompactRange(cro, handles_[1], nullptr, nullptr));
-      ASSERT_EQ(compaction_style == kCompactionStyleLevel ? "0,1" : "0,0,1",
-                FilesPerLevel(1));
-
-      ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-      ASSERT_TRUE(encounter_conflict);
-
-      // Verify that the auto compaction is eventually executed after the
-      // exclusive CompactRange() finishes.
-      ASSERT_EQ(compaction_style == kCompactionStyleLevel ? "0,1" : "0,0,1",
-                FilesPerLevel(0));
-
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-    }
-    Env::Default()->SetBackgroundThreads(0, Env::Priority::BOTTOM);
-  }
+  // Eventually the cancelled compaction will be rescheduled and executed.
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  ASSERT_EQ("0,1", FilesPerLevel(0));
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
 }
 
 TEST_P(DBCompactionTestWithParam, ManualCompaction) {
@@ -4105,51 +3986,41 @@ TEST_P(DBCompactionTestWithParam, IntraL0CompactionDoesNotObsoleteDeletions) {
 TEST_P(DBCompactionTestWithParam, FullCompactionInBottomPriThreadPool) {
   const int kNumFilesTrigger = 3;
   Env::Default()->SetBackgroundThreads(1, Env::Priority::BOTTOM);
-  for (auto compaction_style :
-       {kCompactionStyleLevel, kCompactionStyleUniversal}) {
-    for (auto universal_reduce_file_locking : {false, true}) {
-      if (compaction_style != kCompactionStyleUniversal &&
-          universal_reduce_file_locking) {
-        continue;
-      }
-      Options options = CurrentOptions();
-      options.compaction_style = compaction_style;
-      if (compaction_style == kCompactionStyleLevel) {
-        options.level_compaction_dynamic_level_bytes = true;
-      } else {
-        options.compaction_options_universal.reduce_file_locking =
-            universal_reduce_file_locking;
-        // Trigger compaction if size amplification exceeds 110%
-        options.compaction_options_universal.max_size_amplification_percent =
-            110;
-      }
-      options.num_levels = 4;
-      options.write_buffer_size = 100 << 10;     // 100KB
-      options.target_file_size_base = 32 << 10;  // 32KB
-      options.level0_file_num_compaction_trigger = kNumFilesTrigger;
-
-      DestroyAndReopen(options);
-
-      int num_bottom_pri_compactions = 0;
-      SyncPoint::GetInstance()->SetCallBack(
-          "DBImpl::BGWorkBottomCompaction",
-          [&](void* /*arg*/) { ++num_bottom_pri_compactions; });
-      SyncPoint::GetInstance()->EnableProcessing();
-
-      Random rnd(301);
-      for (int num = 0; num < kNumFilesTrigger; num++) {
-        ASSERT_EQ(NumSortedRuns(), num);
-        int key_idx = 0;
-        GenerateNewFile(&rnd, &key_idx);
-      }
-      ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-      ASSERT_EQ(1, num_bottom_pri_compactions);
-
-      // Verify that size amplification did occur
-      ASSERT_EQ(NumSortedRuns(), 1);
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  for (bool use_universal_compaction : {false, true}) {
+    Options options = CurrentOptions();
+    if (use_universal_compaction) {
+      options.compaction_style = kCompactionStyleUniversal;
+    } else {
+      options.compaction_style = kCompactionStyleLevel;
+      options.level_compaction_dynamic_level_bytes = true;
     }
+    options.num_levels = 4;
+    options.write_buffer_size = 100 << 10;     // 100KB
+    options.target_file_size_base = 32 << 10;  // 32KB
+    options.level0_file_num_compaction_trigger = kNumFilesTrigger;
+    // Trigger compaction if size amplification exceeds 110%
+    options.compaction_options_universal.max_size_amplification_percent = 110;
+    DestroyAndReopen(options);
+
+    int num_bottom_pri_compactions = 0;
+    SyncPoint::GetInstance()->SetCallBack(
+        "DBImpl::BGWorkBottomCompaction",
+        [&](void* /*arg*/) { ++num_bottom_pri_compactions; });
+    SyncPoint::GetInstance()->EnableProcessing();
+
+    Random rnd(301);
+    for (int num = 0; num < kNumFilesTrigger; num++) {
+      ASSERT_EQ(NumSortedRuns(), num);
+      int key_idx = 0;
+      GenerateNewFile(&rnd, &key_idx);
+    }
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+    ASSERT_EQ(1, num_bottom_pri_compactions);
+
+    // Verify that size amplification did occur
+    ASSERT_EQ(NumSortedRuns(), 1);
+    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
   }
   Env::Default()->SetBackgroundThreads(0, Env::Priority::BOTTOM);
 }
@@ -6763,7 +6634,7 @@ TEST_P(RoundRobinSubcompactionsAgainstResources, SubcompactionsUsingResources) {
   // compaction is enough to make post-compaction L1 size less than
   // the maximum size (this test assumes only one round-robin compaction
   // is triggered by kLevelMaxLevelSize)
-  options.max_compaction_bytes = std::numeric_limits<uint64_t>::max();
+  options.max_compaction_bytes = 100000000;
 
   DestroyAndReopen(options);
   env_->SetBackgroundThreads(total_low_pri_threads_, Env::LOW);
@@ -6796,33 +6667,41 @@ TEST_P(RoundRobinSubcompactionsAgainstResources, SubcompactionsUsingResources) {
         // More than 10 files are selected for round-robin under auto
         // compaction. The number of planned subcompaction is restricted by
         // the minimum number between available threads and compaction limits
-        auto actual_reserved_threads =
-            num_planned_subcompactions - options.max_subcompactions;
-        auto expected_reserved_threads =
-            std::min(total_low_pri_threads_, max_compaction_limits_) - 1;
-        ASSERT_EQ(actual_reserved_threads, expected_reserved_threads);
+        ASSERT_EQ(num_planned_subcompactions - options.max_subcompactions,
+                  std::min(total_low_pri_threads_, max_compaction_limits_) - 1);
         num_planned_subcompactions_verified = true;
       });
-
-  int acquire_count = 0;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::AcquireSubcompactionResources:0",
-      [&](void* /*arg*/) { acquire_count++; });
-  int release_count = 0;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::ReleaseSubcompactionResources",
-      [&](void* /*arg*/) { release_count++; });
-
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"RoundRobinSubcompactionsAgainstResources:0",
+        "BackgroundCallCompaction:0"},
+       {"CompactionJob::AcquireSubcompactionResources:0",
+        "RoundRobinSubcompactionsAgainstResources:1"},
+       {"RoundRobinSubcompactionsAgainstResources:2",
+        "CompactionJob::AcquireSubcompactionResources:1"},
+       {"CompactionJob::ReleaseSubcompactionResources:0",
+        "RoundRobinSubcompactionsAgainstResources:3"},
+       {"RoundRobinSubcompactionsAgainstResources:4",
+        "CompactionJob::ReleaseSubcompactionResources:1"}});
   SyncPoint::GetInstance()->EnableProcessing();
 
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  ASSERT_OK(dbfull()->EnableAutoCompaction({dbfull()->DefaultColumnFamily()}));
+  TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:0");
+  TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:1");
   auto pressure_token =
       dbfull()->TEST_write_controler().GetCompactionPressureToken();
-  ASSERT_OK(dbfull()->EnableAutoCompaction({dbfull()->DefaultColumnFamily()}));
+
+  TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:2");
+  TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:3");
+  // We can reserve more threads now except one is being used
+  ASSERT_EQ(total_low_pri_threads_ - 1,
+            env_->ReserveThreads(total_low_pri_threads_, Env::Priority::LOW));
+  ASSERT_EQ(
+      total_low_pri_threads_ - 1,
+      env_->ReleaseThreads(total_low_pri_threads_ - 1, Env::Priority::LOW));
+  TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:4");
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
   ASSERT_TRUE(num_planned_subcompactions_verified);
-  ASSERT_EQ(acquire_count, release_count);
-
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
@@ -9555,134 +9434,104 @@ TEST_F(DBCompactionTest, CompactionWithChecksumHandoffManifest2) {
 }
 
 TEST_F(DBCompactionTest, FIFOChangeTemperature) {
-  for (bool should_allow_trivial_copy : {false, true}) {
-    for (bool write_time_default : {false, true}) {
-      int32_t before_compaction_calls = 0;
-      int32_t after_compaction_calls = 0;
-      if (should_allow_trivial_copy) {
-        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-            "DBImpl::BackgroundCompaction:TriviaCopyBeforeCompaction",
-            [&](void*) { ++before_compaction_calls; });
-        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-            "DBImpl::BackgroundCompaction:TriviaCopyAfterCompaction",
-            [&](void*) { ++after_compaction_calls; });
-      } else {
-        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-            "DBImpl::BackgroundCompaction:BeforeCompaction",
-            [&](void*) { ++before_compaction_calls; });
+  for (bool write_time_default : {false, true}) {
+    SCOPED_TRACE("write time default? " + std::to_string(write_time_default));
 
-        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-            "DBImpl::BackgroundCompaction:AfterCompaction",
-            [&](void*) { ++after_compaction_calls; });
-      }
-
-      SCOPED_TRACE("write time default? " + std::to_string(write_time_default));
-
-      Options options = CurrentOptions();
-      options.compaction_style = kCompactionStyleFIFO;
-      options.num_levels = 1;
-      options.max_open_files = -1;
-      options.level0_file_num_compaction_trigger = 2;
-      options.create_if_missing = true;
-      CompactionOptionsFIFO fifo_options;
-      fifo_options.file_temperature_age_thresholds = {
-          {Temperature::kCold, 1000}};
-      fifo_options.max_table_files_size = 100000000;
-      fifo_options.allow_trivial_copy_when_change_temperature =
-          should_allow_trivial_copy;
-      fifo_options.trivial_copy_buffer_size = 4096;
-      options.compaction_options_fifo = fifo_options;
-      env_->SetMockSleep();
-      if (write_time_default) {
-        options.default_write_temperature = Temperature::kWarm;
-      }
-      // Should be ignored (TODO: fail?)
-      options.last_level_temperature = Temperature::kHot;
-      Reopen(options);
-
-      int total_cold = 0;
-      int total_warm = 0;
-      int total_hot = 0;
-      int total_unknown = 0;
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-          "NewWritableFile::FileOptions.temperature", [&](void* arg) {
-            Temperature temperature = *(static_cast<Temperature*>(arg));
-            if (temperature == Temperature::kCold) {
-              total_cold++;
-            } else if (temperature == Temperature::kWarm) {
-              total_warm++;
-            } else if (temperature == Temperature::kHot) {
-              total_hot++;
-            } else {
-              assert(temperature == Temperature::kUnknown);
-              total_unknown++;
-            }
-          });
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-      // The file system does not support checksum handoff. The check
-      // will be ignored.
-      ASSERT_OK(Put(Key(0), "value1"));
-      env_->MockSleepForSeconds(800);
-      ASSERT_OK(Put(Key(2), "value2"));
-      ASSERT_OK(Flush());
-
-      ASSERT_OK(Put(Key(0), "value1"));
-      ASSERT_OK(Put(Key(2), "value2"));
-      ASSERT_OK(Flush());
-
-      // First two L0 files both become eligible for temperature change
-      // compaction They should be compacted one-by-one.
-      ASSERT_OK(Put(Key(0), "value1"));
-      env_->MockSleepForSeconds(1200);
-      ASSERT_OK(Put(Key(2), "value2"));
-      ASSERT_OK(Flush());
-      ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-      if (write_time_default) {
-        // Also test dynamic option change
-        ASSERT_OK(db_->SetOptions({{"default_write_temperature", "kHot"}}));
-      }
-
-      ASSERT_OK(Put(Key(0), "value1"));
-      env_->MockSleepForSeconds(800);
-      ASSERT_OK(Put(Key(2), "value2"));
-      ASSERT_OK(Flush());
-
-      ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-
-      ColumnFamilyMetaData metadata;
-      db_->GetColumnFamilyMetaData(&metadata);
-      ASSERT_EQ(4, metadata.file_count);
-      if (write_time_default) {
-        ASSERT_EQ(Temperature::kHot, metadata.levels[0].files[0].temperature);
-        ASSERT_EQ(Temperature::kWarm, metadata.levels[0].files[1].temperature);
-        // Includes obsolete/deleted files moved to cold
-        ASSERT_EQ(total_warm, 3);
-        ASSERT_EQ(total_hot, 1);
-        // Includes non-SST DB files
-        ASSERT_GT(total_unknown, 0);
-      } else {
-        ASSERT_EQ(Temperature::kUnknown,
-                  metadata.levels[0].files[0].temperature);
-        ASSERT_EQ(Temperature::kUnknown,
-                  metadata.levels[0].files[1].temperature);
-        ASSERT_EQ(total_warm, 0);
-        ASSERT_EQ(total_hot, 0);
-        // Includes non-SST DB files
-        ASSERT_GT(total_unknown, 4);
-      }
-      ASSERT_EQ(Temperature::kCold, metadata.levels[0].files[2].temperature);
-      ASSERT_EQ(Temperature::kCold, metadata.levels[0].files[3].temperature);
-      ASSERT_EQ(2, total_cold);
-
-      ASSERT_EQ(2, before_compaction_calls);
-      ASSERT_EQ(2, after_compaction_calls);
-
-      Destroy(options);
+    Options options = CurrentOptions();
+    options.compaction_style = kCompactionStyleFIFO;
+    options.num_levels = 1;
+    options.max_open_files = -1;
+    options.level0_file_num_compaction_trigger = 2;
+    options.create_if_missing = true;
+    CompactionOptionsFIFO fifo_options;
+    fifo_options.file_temperature_age_thresholds = {{Temperature::kCold, 1000}};
+    fifo_options.max_table_files_size = 100000000;
+    options.compaction_options_fifo = fifo_options;
+    env_->SetMockSleep();
+    if (write_time_default) {
+      options.default_write_temperature = Temperature::kWarm;
     }
+    // Should be ignored (TODO: fail?)
+    options.last_level_temperature = Temperature::kHot;
+    Reopen(options);
+
+    int total_cold = 0;
+    int total_warm = 0;
+    int total_hot = 0;
+    int total_unknown = 0;
+    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+        "NewWritableFile::FileOptions.temperature", [&](void* arg) {
+          Temperature temperature = *(static_cast<Temperature*>(arg));
+          if (temperature == Temperature::kCold) {
+            total_cold++;
+          } else if (temperature == Temperature::kWarm) {
+            total_warm++;
+          } else if (temperature == Temperature::kHot) {
+            total_hot++;
+          } else {
+            assert(temperature == Temperature::kUnknown);
+            total_unknown++;
+          }
+        });
+    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+    // The file system does not support checksum handoff. The check
+    // will be ignored.
+    ASSERT_OK(Put(Key(0), "value1"));
+    env_->MockSleepForSeconds(800);
+    ASSERT_OK(Put(Key(2), "value2"));
+    ASSERT_OK(Flush());
+
+    ASSERT_OK(Put(Key(0), "value1"));
+    ASSERT_OK(Put(Key(2), "value2"));
+    ASSERT_OK(Flush());
+
+    // First two L0 files both become eligible for temperature change compaction
+    // They should be compacted one-by-one.
+    ASSERT_OK(Put(Key(0), "value1"));
+    env_->MockSleepForSeconds(1200);
+    ASSERT_OK(Put(Key(2), "value2"));
+    ASSERT_OK(Flush());
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+    if (write_time_default) {
+      // Also test dynamic option change
+      ASSERT_OK(db_->SetOptions({{"default_write_temperature", "kHot"}}));
+    }
+
+    ASSERT_OK(Put(Key(0), "value1"));
+    env_->MockSleepForSeconds(800);
+    ASSERT_OK(Put(Key(2), "value2"));
+    ASSERT_OK(Flush());
+
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+
+    ColumnFamilyMetaData metadata;
+    db_->GetColumnFamilyMetaData(&metadata);
+    ASSERT_EQ(4, metadata.file_count);
+    if (write_time_default) {
+      ASSERT_EQ(Temperature::kHot, metadata.levels[0].files[0].temperature);
+      ASSERT_EQ(Temperature::kWarm, metadata.levels[0].files[1].temperature);
+      // Includes obsolete/deleted files moved to cold
+      ASSERT_EQ(total_warm, 3);
+      ASSERT_EQ(total_hot, 1);
+      // Includes non-SST DB files
+      ASSERT_GT(total_unknown, 0);
+    } else {
+      ASSERT_EQ(Temperature::kUnknown, metadata.levels[0].files[0].temperature);
+      ASSERT_EQ(Temperature::kUnknown, metadata.levels[0].files[1].temperature);
+      ASSERT_EQ(total_warm, 0);
+      ASSERT_EQ(total_hot, 0);
+      // Includes non-SST DB files
+      ASSERT_GT(total_unknown, 4);
+    }
+    ASSERT_EQ(Temperature::kCold, metadata.levels[0].files[2].temperature);
+    ASSERT_EQ(Temperature::kCold, metadata.levels[0].files[3].temperature);
+    ASSERT_EQ(2, total_cold);
+
+    Destroy(options);
   }
 }
 
@@ -10127,60 +9976,55 @@ TEST_F(DBCompactionTest, BottomPriCompactionCountsTowardConcurrencyLimit) {
 
   env_->SetBackgroundThreads(1, Env::Priority::BOTTOM);
 
-  for (bool universal_reduce_file_locking : {false, true}) {
-    Options options = CurrentOptions();
-    options.level0_file_num_compaction_trigger = kNumL0Files;
-    options.num_levels = kNumLevels;
-    options.compaction_style = kCompactionStyleUniversal;
-    options.compaction_options_universal.reduce_file_locking =
-        universal_reduce_file_locking;
-    DestroyAndReopen(options);
+  Options options = CurrentOptions();
+  options.level0_file_num_compaction_trigger = kNumL0Files;
+  options.num_levels = kNumLevels;
+  DestroyAndReopen(options);
 
-    // Setup last level to be non-empty since it's a bit unclear whether
-    // compaction to an empty level would be considered "bottommost".
+  // Setup last level to be non-empty since it's a bit unclear whether
+  // compaction to an empty level would be considered "bottommost".
+  ASSERT_OK(Put(Key(0), "val"));
+  ASSERT_OK(Flush());
+  MoveFilesToLevel(kNumLevels - 1);
+
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::BGWorkBottomCompaction",
+        "DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
+        "PreTriggerCompaction"},
+       {"DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
+        "PostTriggerCompaction",
+        "BackgroundCallCompaction:0"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  port::Thread compact_range_thread([&] {
+    CompactRangeOptions cro;
+    cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
+    cro.exclusive_manual_compaction = false;
+    ASSERT_OK(dbfull()->CompactRange(cro, nullptr, nullptr));
+  });
+
+  // Sleep in the low-pri thread so any newly scheduled compaction will be
+  // queued. Otherwise it might finish before we check its existence.
+  test::SleepingBackgroundTask sleeping_task_low;
+  env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask, &sleeping_task_low,
+                 Env::Priority::LOW);
+  sleeping_task_low.WaitUntilSleeping();
+
+  TEST_SYNC_POINT(
+      "DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
+      "PreTriggerCompaction");
+  for (int i = 0; i < kNumL0Files; ++i) {
     ASSERT_OK(Put(Key(0), "val"));
     ASSERT_OK(Flush());
-    MoveFilesToLevel(kNumLevels - 1);
-
-    SyncPoint::GetInstance()->LoadDependency(
-        {{"DBImpl::BGWorkBottomCompaction",
-          "DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
-          "PreTriggerCompaction"},
-         {"DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
-          "PostTriggerCompaction",
-          "BackgroundCallCompaction:0"}});
-    SyncPoint::GetInstance()->EnableProcessing();
-
-    port::Thread compact_range_thread([&] {
-      CompactRangeOptions cro;
-      cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
-      cro.exclusive_manual_compaction = false;
-      ASSERT_OK(dbfull()->CompactRange(cro, nullptr, nullptr));
-    });
-
-    // Sleep in the low-pri thread so any newly scheduled compaction will be
-    // queued. Otherwise it might finish before we check its existence.
-    test::SleepingBackgroundTask sleeping_task_low;
-    env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask,
-                   &sleeping_task_low, Env::Priority::LOW);
-    sleeping_task_low.WaitUntilSleeping();
-
-    TEST_SYNC_POINT(
-        "DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
-        "PreTriggerCompaction");
-    for (int i = 0; i < kNumL0Files; ++i) {
-      ASSERT_OK(Put(Key(0), "val"));
-      ASSERT_OK(Flush());
-    }
-    ASSERT_EQ(0u, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
-    TEST_SYNC_POINT(
-        "DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
-        "PostTriggerCompaction");
-
-    sleeping_task_low.WakeUp();
-    sleeping_task_low.WaitUntilDone();
-    compact_range_thread.join();
   }
+  ASSERT_EQ(0u, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
+  TEST_SYNC_POINT(
+      "DBCompactionTest::BottomPriCompactionCountsTowardConcurrencyLimit:"
+      "PostTriggerCompaction");
+
+  sleeping_task_low.WakeUp();
+  sleeping_task_low.WaitUntilDone();
+  compact_range_thread.join();
 }
 
 TEST_F(DBCompactionTest, BottommostFileCompactionAllowIngestBehind) {

db/db_flush_test.cc

@@ -3504,63 +3504,6 @@ TEST_F(DBFlushTest, DBStuckAfterAtomicFlushError) {
   ASSERT_OK(dbfull()->TEST_WaitForBackgroundWork());
   ASSERT_EQ(1, NumTableFilesAtLevel(0));
 }
-
-TEST_F(DBFlushTest, VerifyOutputRecordCount) {
-  for (bool use_plain_table : {false, true}) {
-    Options options = CurrentOptions();
-    options.flush_verify_memtable_count = true;
-    options.merge_operator = MergeOperators::CreateStringAppendOperator();
-    DestroyAndReopen(options);
-    // Verify flush output record count verification in different table
-    // formats
-    if (use_plain_table) {
-      options.table_factory.reset(NewPlainTableFactory());
-    }
-
-    // Verify that flush output record count verification does not produce false
-    // positives.
-    ASSERT_OK(Merge("k0", "v1"));
-    ASSERT_OK(Put("k1", "v1"));
-    ASSERT_OK(Put("k2", "v1"));
-    ASSERT_OK(SingleDelete("k2"));
-    ASSERT_OK(Delete("k2"));
-    ASSERT_OK(Delete("k3"));
-    ASSERT_OK(db_->DeleteRange(WriteOptions(), "k1", "k3"));
-    ASSERT_OK(Flush());
-
-    // Verify that flush output record count verification catch corruption
-    DestroyAndReopen(options);
-    if (use_plain_table) {
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-          "PlainTableBuilder::Add::skip",
-          [&](void* skip) { *(bool*)skip = true; });
-
-    } else {
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-          "BlockBasedTableBuilder::Add::skip",
-          [&](void* skip) { *(bool*)skip = true; });
-    }
-    SyncPoint::GetInstance()->EnableProcessing();
-    const char* expect =
-        "Number of keys in flush output SST files does not match";
-
-    // 1. During DB open flush
-    ASSERT_OK(Put("k1", "v1"));
-    ASSERT_OK(Put("k2", "v1"));
-    Status s = TryReopen(options);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), expect));
-
-    // 2. During regular flush
-    DestroyAndReopen(options);
-    ASSERT_OK(Put("k1", "v1"));
-    ASSERT_OK(Put("k2", "v1"));
-    s = Flush();
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), expect));
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  }
-}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_impl/db_impl.cc

@@ -3886,14 +3886,12 @@ Iterator* DBImpl::NewIterator(const ReadOptions& _read_options,
 
     auto iter = new ForwardIterator(this, read_options, cfd, sv,
                                     /* allow_unprepared_value */ true);
-    // TODO(cbi): Add support for `memtable_op_scan_flush_trigger` for tailing
-    // iterator. This requires refreshing DBIter's pointer to active_mem when
-    // tailing iterator refreshes to new memtable internally.
     result = DBIter::NewIter(env_, read_options, cfd->ioptions(),
                              sv->mutable_cf_options, cfd->user_comparator(),
                              iter, sv->current, kMaxSequenceNumber,
-                             /*read_callback=*/nullptr, /*active_mem=*/nullptr,
-                             cfh, /*expose_blob_index=*/false);
+                             /*read_callback=*/nullptr, cfh,
+                             /*expose_blob_index=*/false,
+                             /*active_mem=*/sv->mem);
   } else {
     // Note: no need to consider the special case of
     // last_seq_same_as_publish_seq_==false since NewIterator is overridden in
@@ -4097,12 +4095,12 @@ Status DBImpl::NewIterators(
       auto iter = new ForwardIterator(this, read_options, cf_sv_pair.cfd,
                                       cf_sv_pair.super_version,
                                       /* allow_unprepared_value */ true);
-      iterators->push_back(DBIter::NewIter(
-          env_, read_options, cf_sv_pair.cfd->ioptions(),
-          cf_sv_pair.super_version->mutable_cf_options,
-          cf_sv_pair.cfd->user_comparator(), iter,
-          cf_sv_pair.super_version->current, kMaxSequenceNumber,
-          nullptr /*read_callback*/, /*active_mem=*/nullptr, cf_sv_pair.cfh));
+      iterators->push_back(
+          DBIter::NewIter(env_, read_options, cf_sv_pair.cfd->ioptions(),
+                          cf_sv_pair.super_version->mutable_cf_options,
+                          cf_sv_pair.cfd->user_comparator(), iter,
+                          cf_sv_pair.super_version->current, kMaxSequenceNumber,
+                          nullptr /*read_callback*/, cf_sv_pair.cfh));
     }
   } else {
     for (const auto& cf_sv_pair : cf_sv_pairs) {
@@ -5018,6 +5016,7 @@ void DBImpl::GetColumnFamilyMetaData(ColumnFamilyHandle* column_family,
   assert(column_family);
   auto* cfd =
       static_cast_with_check<ColumnFamilyHandleImpl>(column_family)->cfd();
+  auto* sv = GetAndRefSuperVersion(cfd);
   {
     // Without mutex, Version::GetColumnFamilyMetaData will have data race
     // with Compaction::MarkFilesBeingCompacted. One solution is to use mutex,
@@ -5029,8 +5028,9 @@ void DBImpl::GetColumnFamilyMetaData(ColumnFamilyHandle* column_family,
     // DB::GetColumnFamilyMetaData is not called frequently, the regression
     // should not be big. We still need to keep an eye on it.
     InstrumentedMutexLock l(&mutex_);
-    cfd->current()->GetColumnFamilyMetaData(cf_meta);
+    sv->current->GetColumnFamilyMetaData(cf_meta);
   }
+  ReturnAndCleanupSuperVersion(cfd, sv);
 }
 
 void DBImpl::GetAllColumnFamilyMetaData(

db/db_impl/db_impl.h

@@ -1090,7 +1090,10 @@ class DBImpl : public DB {
   void SetSnapshotChecker(SnapshotChecker* snapshot_checker);
 
   // Fill JobContext with snapshot information needed by flush and compaction.
-  void InitSnapshotContext(JobContext* job_context);
+  void GetSnapshotContext(JobContext* job_context,
+                          std::vector<SequenceNumber>* snapshot_seqs,
+                          SequenceNumber* earliest_write_conflict_snapshot,
+                          SnapshotChecker** snapshot_checker);
 
   // Not thread-safe.
   void SetRecoverableStatePreReleaseCallback(PreReleaseCallback* callback);
@@ -1952,19 +1955,12 @@ class DBImpl : public DB {
   };
   struct PrepickedCompaction {
     // background compaction takes ownership of `compaction`.
-    // TODO(hx235): consider using std::shared_ptr for easier ownership
-    // management
     Compaction* compaction;
     // caller retains ownership of `manual_compaction_state` as it is reused
     // across background compactions.
     ManualCompactionState* manual_compaction_state;  // nullptr if non-manual
     // task limiter token is requested during compaction picking.
     std::unique_ptr<TaskLimiterToken> task_token;
-    // If true, `compaction` is picked temporarily to express compaction intent
-    // and will be released before re-picking a real compaction based on the
-    // updated LSM shape when thread associated with `compaction` is ready to
-    // run
-    bool need_repick;
   };
 
   struct CompactionArg {
@@ -2055,13 +2051,14 @@ class DBImpl : public DB {
   // Flush the in-memory write buffer to storage.  Switches to a new
   // log-file/memtable and writes a new descriptor iff successful. Then
   // installs a new super version for the column family.
-  Status FlushMemTableToOutputFile(ColumnFamilyData* cfd,
-                                   const MutableCFOptions& mutable_cf_options,
-                                   bool* madeProgress, JobContext* job_context,
-                                   FlushReason flush_reason,
-                                   SuperVersionContext* superversion_context,
-                                   LogBuffer* log_buffer,
-                                   Env::Priority thread_pri);
+  Status FlushMemTableToOutputFile(
+      ColumnFamilyData* cfd, const MutableCFOptions& mutable_cf_options,
+      bool* madeProgress, JobContext* job_context, FlushReason flush_reason,
+      SuperVersionContext* superversion_context,
+      std::vector<SequenceNumber>& snapshot_seqs,
+      SequenceNumber earliest_write_conflict_snapshot,
+      SnapshotChecker* snapshot_checker, LogBuffer* log_buffer,
+      Env::Priority thread_pri);
 
   // Flush the memtables of (multiple) column families to multiple files on
   // persistent storage.
@@ -2463,8 +2460,6 @@ class DBImpl : public DB {
                          bool* flush_rescheduled_to_retain_udt,
                          Env::Priority thread_pri);
 
-  Compaction* CreateIntendedCompactionForwardedToBottomPriorityPool(
-      Compaction* c);
   bool EnoughRoomForCompaction(ColumnFamilyData* cfd,
                                const std::vector<CompactionInputFiles>& inputs,
                                bool* sfm_bookkeeping, LogBuffer* log_buffer);
@@ -2582,7 +2577,7 @@ class DBImpl : public DB {
   bool ShouldntRunManualCompaction(ManualCompactionState* m);
   bool HaveManualCompaction(ColumnFamilyData* cfd);
   bool MCOverlap(ManualCompactionState* m, ManualCompactionState* m1);
-  void UpdateFIFOCompactionStatus(const std::unique_ptr<Compaction>& c);
+  void UpdateDeletionCompactionStats(const std::unique_ptr<Compaction>& c);
 
   // May open and read table files for table property.
   // Should not be called while holding mutex_.
@@ -2732,11 +2727,6 @@ class DBImpl : public DB {
       const std::vector<ColumnFamilyHandle*>& column_families,
       ErrorIteratorFuncType error_iterator_func);
 
-  bool ShouldPickCompaction(bool is_prepicked,
-                            const PrepickedCompaction* prepicked_compaction);
-
-  void ResetBottomPriCompactionIntent(ColumnFamilyData* cfd,
-                                      std::unique_ptr<Compaction>& c);
   // Lock over the persistent DB state.  Non-nullptr iff successfully acquired.
   FileLock* db_lock_ = nullptr;
 

db/db_impl/db_impl_compaction_flush.cc

@@ -13,14 +13,12 @@
 #include "db/db_impl/db_impl.h"
 #include "db/error_handler.h"
 #include "db/event_helpers.h"
-#include "file/file_util.h"
 #include "file/sst_file_manager_impl.h"
 #include "logging/logging.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/thread_status_updater.h"
 #include "monitoring/thread_status_util.h"
-#include "options/options_helper.h"
 #include "rocksdb/file_system.h"
 #include "rocksdb/io_status.h"
 #include "rocksdb/options.h"
@@ -145,7 +143,10 @@ IOStatus DBImpl::SyncClosedWals(const WriteOptions& write_options,
 Status DBImpl::FlushMemTableToOutputFile(
     ColumnFamilyData* cfd, const MutableCFOptions& mutable_cf_options,
     bool* made_progress, JobContext* job_context, FlushReason flush_reason,
-    SuperVersionContext* superversion_context, LogBuffer* log_buffer,
+    SuperVersionContext* superversion_context,
+    std::vector<SequenceNumber>& snapshot_seqs,
+    SequenceNumber earliest_write_conflict_snapshot,
+    SnapshotChecker* snapshot_checker, LogBuffer* log_buffer,
     Env::Priority thread_pri) {
   mutex_.AssertHeld();
   assert(cfd);
@@ -209,6 +210,7 @@ Status DBImpl::FlushMemTableToOutputFile(
   FlushJob flush_job(
       dbname_, cfd, immutable_db_options_, mutable_cf_options, max_memtable_id,
       file_options_for_compaction_, versions_.get(), &mutex_, &shutting_down_,
+      snapshot_seqs, earliest_write_conflict_snapshot, snapshot_checker,
       job_context, flush_reason, log_buffer, directories_.GetDbDir(),
       GetDataDir(cfd, 0U),
       GetCompressionFlush(cfd->ioptions(), mutable_cf_options), stats_,
@@ -393,8 +395,11 @@ Status DBImpl::FlushMemTablesToOutputFiles(
         bg_flush_args, made_progress, job_context, log_buffer, thread_pri);
   }
   assert(bg_flush_args.size() == 1);
-  InitSnapshotContext(job_context);
-
+  std::vector<SequenceNumber> snapshot_seqs;
+  SequenceNumber earliest_write_conflict_snapshot;
+  SnapshotChecker* snapshot_checker;
+  GetSnapshotContext(job_context, &snapshot_seqs,
+                     &earliest_write_conflict_snapshot, &snapshot_checker);
   const auto& bg_flush_arg = bg_flush_args[0];
   ColumnFamilyData* cfd = bg_flush_arg.cfd_;
   // intentional infrequent copy for each flush
@@ -405,7 +410,8 @@ Status DBImpl::FlushMemTablesToOutputFiles(
   FlushReason flush_reason = bg_flush_arg.flush_reason_;
   Status s = FlushMemTableToOutputFile(
       cfd, mutable_cf_options_copy, made_progress, job_context, flush_reason,
-      superversion_context, log_buffer, thread_pri);
+      superversion_context, snapshot_seqs, earliest_write_conflict_snapshot,
+      snapshot_checker, log_buffer, thread_pri);
   return s;
 }
 
@@ -440,7 +446,12 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
   }
 #endif /* !NDEBUG */
 
-  InitSnapshotContext(job_context);
+  std::vector<SequenceNumber> snapshot_seqs;
+  SequenceNumber earliest_write_conflict_snapshot;
+  SnapshotChecker* snapshot_checker;
+  GetSnapshotContext(job_context, &snapshot_seqs,
+                     &earliest_write_conflict_snapshot, &snapshot_checker);
+
   autovector<FSDirectory*> distinct_output_dirs;
   autovector<std::string> distinct_output_dir_paths;
   std::vector<std::unique_ptr<FlushJob>> jobs;
@@ -474,7 +485,8 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     jobs.emplace_back(new FlushJob(
         dbname_, cfd, immutable_db_options_, mutable_cf_options,
         max_memtable_id, file_options_for_compaction_, versions_.get(), &mutex_,
-        &shutting_down_, job_context, flush_reason, log_buffer,
+        &shutting_down_, snapshot_seqs, earliest_write_conflict_snapshot,
+        snapshot_checker, job_context, flush_reason, log_buffer,
         directories_.GetDbDir(), data_dir,
         GetCompressionFlush(cfd->ioptions(), mutable_cf_options), stats_,
         &event_logger_, mutable_cf_options.report_bg_io_stats,
@@ -1381,9 +1393,6 @@ Status DBImpl::CompactFiles(const CompactionOptions& compact_options,
   TEST_SYNC_POINT_CALLBACK("TestCompactFiles:PausingManualCompaction:3",
                            static_cast<void*>(const_cast<std::atomic<int>*>(
                                &manual_compaction_paused_)));
-  TEST_SYNC_POINT_CALLBACK("TestCancelCompactFiles:SuccessfulCompaction",
-                           static_cast<void*>(const_cast<std::atomic<int>*>(
-                               &manual_compaction_paused_)));
   {
     InstrumentedMutexLock l(&mutex_);
     auto* current = cfd->current();
@@ -1436,12 +1445,7 @@ Status DBImpl::CompactFilesImpl(
   if (shutting_down_.load(std::memory_order_acquire)) {
     return Status::ShutdownInProgress();
   }
-
-  // triggered by DisableManualCompactions or by user-set canceled flag in
-  // CompactionOptions
-  if (manual_compaction_paused_.load(std::memory_order_acquire) > 0 ||
-      (compact_options.canceled &&
-       compact_options.canceled->load(std::memory_order_acquire))) {
+  if (manual_compaction_paused_.load(std::memory_order_acquire) > 0) {
     return Status::Incomplete(Status::SubCode::kManualCompactionPaused);
   }
 
@@ -1512,7 +1516,11 @@ Status DBImpl::CompactFilesImpl(
   // deletion compaction currently not allowed in CompactFiles.
   assert(!c->deletion_compaction());
 
-  InitSnapshotContext(job_context);
+  std::vector<SequenceNumber> snapshot_seqs;
+  SequenceNumber earliest_write_conflict_snapshot;
+  SnapshotChecker* snapshot_checker;
+  GetSnapshotContext(job_context, &snapshot_seqs,
+                     &earliest_write_conflict_snapshot, &snapshot_checker);
 
   std::unique_ptr<std::list<uint64_t>::iterator> pending_outputs_inserted_elem(
       new std::list<uint64_t>::iterator(
@@ -1526,6 +1534,7 @@ Status DBImpl::CompactFilesImpl(
       log_buffer, directories_.GetDbDir(),
       GetDataDir(c->column_family_data(), c->output_path_id()),
       GetDataDir(c->column_family_data(), 0), stats_, &mutex_, &error_handler_,
+      snapshot_seqs, earliest_write_conflict_snapshot, snapshot_checker,
       job_context, table_cache_, &event_logger_,
       c->mutable_cf_options().paranoid_file_checks,
       c->mutable_cf_options().report_bg_io_stats, dbname_,
@@ -2178,7 +2187,6 @@ Status DBImpl::RunManualCompaction(
         // Don't throttle manual compaction, only count outstanding tasks.
         assert(false);
       }
-      ca->prepicked_compaction->need_repick = false;
       manual.incomplete = false;
       if (compaction->bottommost_level() &&
           env_->GetBackgroundThreads(Env::Priority::BOTTOM) > 0) {
@@ -2708,10 +2716,6 @@ Status DBImpl::WaitUntilFlushWouldNotStallWrites(ColumnFamilyData* cfd,
 // Finish waiting when ALL column families finish flushing memtables.
 // resuming_from_bg_err indicates whether the caller is trying to resume from
 // background error or in normal processing.
-// Note that the wait finishes when the flush result is installed to column
-// families' Versions and persisted in MANIFEST. It doesn't wait until
-// SuperVersion to reflect the flush result, except for the case when
-// flush_reason is `kExternalFileIngestion`.
 Status DBImpl::WaitForFlushMemTables(
     const autovector<ColumnFamilyData*>& cfds,
     const autovector<const uint64_t*>& flush_memtable_ids,
@@ -3405,10 +3409,6 @@ void DBImpl::BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
   bool made_progress = false;
   JobContext job_context(next_job_id_.fetch_add(1), true);
   TEST_SYNC_POINT("BackgroundCallCompaction:0");
-  if (bg_thread_pri == Env::Priority::BOTTOM) {
-    TEST_SYNC_POINT("BackgroundCallCompaction:0:BottomPri");
-  }
-
   LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL,
                        immutable_db_options_.info_log.get());
   {
@@ -3644,54 +3644,34 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
                  : m->manual_end->DebugString(true).c_str()));
       }
     }
-  } else if (ShouldPickCompaction(is_prepicked, prepicked_compaction)) {
-    bool need_repick = is_prepicked && prepicked_compaction->need_repick;
+  } else if (!is_prepicked && !compaction_queue_.empty()) {
     if (HasExclusiveManualCompaction()) {
+      // Can't compact right now, but try again later
       TEST_SYNC_POINT("DBImpl::BackgroundCompaction()::Conflict");
 
-      // TODO(hx235): Resolve conflict between intended
-      // bottom-priority compaction (requiring repick, i.e., need_repick = true)
-      // and exclusive manual compaction by releasing the intended
-      // bottom-priority compaction.
-      if (!need_repick) {
-        // Can't compact right now, but try again later
-        //
-        // Increase `unscheduled_compactions_` directly so we
-        // don't need to
-        // dequeue and enqueue the CFD again in the compaction queue and thus
-        // keep the CFD's position in the queue
-        unscheduled_compactions_++;
+      // Stay in the compaction queue.
+      unscheduled_compactions_++;
 
-        return Status::OK();
-      }
+      return Status::OK();
     }
 
-    ColumnFamilyData* cfd = nullptr;
+    auto cfd = PickCompactionFromQueue(&task_token, log_buffer);
+    if (cfd == nullptr) {
+      // Can't find any executable task from the compaction queue.
+      // All tasks have been throttled by compaction thread limiter.
+      ++unscheduled_compactions_;
+      return Status::Busy();
+    }
 
-    if (!need_repick) {
-      cfd = PickCompactionFromQueue(&task_token, log_buffer);
-      if (cfd == nullptr) {
-        // Can't find any executable task from the compaction queue.
-        // All tasks have been throttled by compaction thread limiter.
-        ++unscheduled_compactions_;
-        return Status::Busy();
-      }
-
-      // We unreference here because the following code will take a Ref() on
-      // this cfd if it is going to use it (Compaction class holds a
-      // reference).
-      // This will all happen under a mutex so we don't have to be afraid of
-      // somebody else deleting it.
-      if (cfd->UnrefAndTryDelete()) {
-        // This was the last reference of the column family, so no need to
-        // compact.
-        return Status::OK();
-      }
-    } else {
-      cfd = c->column_family_data();
-      assert(cfd);
-      ResetBottomPriCompactionIntent(cfd, c);
-      assert(c == nullptr);
+    // We unreference here because the following code will take a Ref() on
+    // this cfd if it is going to use it (Compaction class holds a
+    // reference).
+    // This will all happen under a mutex so we don't have to be afraid of
+    // somebody else deleting it.
+    if (cfd->UnrefAndTryDelete()) {
+      // This was the last reference of the column family, so no need to
+      // compact.
+      return Status::OK();
     }
 
     // Pick up latest mutable CF Options and use it throughout the
@@ -3705,24 +3685,21 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       // compaction is not necessary. Need to make sure mutex is held
       // until we make a copy in the following code
       TEST_SYNC_POINT("DBImpl::BackgroundCompaction():BeforePickCompaction");
+      SnapshotChecker* snapshot_checker = nullptr;
+      std::vector<SequenceNumber> snapshot_seqs;
       // This info is not useful for other scenarios, so save querying existing
       // snapshots for those cases.
       if (cfd->ioptions().compaction_style == kCompactionStyleUniversal &&
           cfd->user_comparator()->timestamp_size() == 0) {
-        InitSnapshotContext(job_context);
+        SequenceNumber earliest_write_conflict_snapshot;
+        GetSnapshotContext(job_context, &snapshot_seqs,
+                           &earliest_write_conflict_snapshot,
+                           &snapshot_checker);
         assert(is_snapshot_supported_ || snapshots_.empty());
       }
-      c.reset(cfd->PickCompaction(
-          mutable_cf_options, mutable_db_options_, job_context->snapshot_seqs,
-          job_context->snapshot_checker, log_buffer,
-          thread_pri == Env::Priority::BOTTOM /* require_max_output_level */));
-      if (thread_pri == Env::Priority::LOW) {
-        TEST_SYNC_POINT("DBImpl::BackgroundCompaction():AfterPickCompaction");
-      } else if (thread_pri == Env::Priority::BOTTOM) {
-        TEST_SYNC_POINT_CALLBACK(
-            "DBImpl::BackgroundCompaction():AfterPickCompactionBottomPri",
-            c.get());
-      }
+      c.reset(cfd->PickCompaction(mutable_cf_options, mutable_db_options_,
+                                  snapshot_seqs, snapshot_checker, log_buffer));
+      TEST_SYNC_POINT("DBImpl::BackgroundCompaction():AfterPickCompaction");
 
       if (c != nullptr) {
         bool enough_room = EnoughRoomForCompaction(
@@ -3736,7 +3713,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
               ->storage_info()
               ->ComputeCompactionScore(c->immutable_options(),
                                        c->mutable_cf_options());
-          EnqueuePendingCompaction(cfd);
+          AddToCompactionQueue(cfd);
 
           c.reset();
           // Don't need to sleep here, because BackgroundCallCompaction
@@ -3758,21 +3735,16 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
           // options take effect.
           // 3) When we Pick a new compaction, we "remove" those files being
           // compacted from the calculation, which then influences compaction
-          // score. Inside EnqueuePendingCompaction(),  we check if we need
-          // the new compaction even without the files that are currently being
-          // compacted. If we need another compaction, we might be able to
-          // execute it in parallel, so we add it to the queue and schedule a
-          // new thread.
-          EnqueuePendingCompaction(cfd);
-          MaybeScheduleFlushOrCompaction();
+          // score. Here we check if we need the new compaction even without the
+          // files that are currently being compacted. If we need another
+          // compaction, we might be able to execute it in parallel, so we add
+          // it to the queue and schedule a new thread.
+          if (cfd->NeedsCompaction()) {
+            // Yes, we need more compactions!
+            AddToCompactionQueue(cfd);
+            MaybeScheduleFlushOrCompaction();
+          }
         }
-      } else if (is_prepicked) {
-        ROCKS_LOG_BUFFER(
-            log_buffer,
-            "[%s] Pre-picked compaction repicked files for compaction as "
-            "required, "
-            "but upon re-evaluation, no compaction was found necessary \n",
-            cfd->GetName().c_str());
       }
     }
   }
@@ -3814,251 +3786,11 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
                      c->column_family_data()->GetName().c_str(),
                      c->num_input_files(0));
     if (status.ok() && io_s.ok()) {
-      UpdateFIFOCompactionStatus(c);
+      UpdateDeletionCompactionStats(c);
     }
     *made_progress = true;
     TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
                              c->column_family_data());
-  } else if (c->is_trivial_copy_compaction()) {
-    TEST_SYNC_POINT_CALLBACK(
-        "DBImpl::BackgroundCompaction:TriviaCopyBeforeCompaction",
-        c->column_family_data());
-    assert(c->num_input_files(1) == 0);
-    assert(c->column_family_data()->ioptions().compaction_style ==
-           kCompactionStyleFIFO);
-    assert(c->compaction_reason() == CompactionReason::kChangeTemperature);
-
-    compaction_job_stats.num_input_files = c->num_input_files(0);
-
-    NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
-                            compaction_job_stats, job_context->job_id);
-
-    std::vector<FileMetaData> out_files;
-    for (const auto& in_file : *c->inputs(0)) {
-      const uint64_t out_file_number = versions_->NewFileNumber();
-      const std::string in_fname =
-          TableFileName(c->immutable_options().cf_paths,
-                        in_file->fd.GetNumber(), in_file->fd.GetPathId());
-      const std::string out_fname =
-          TableFileName(c->immutable_options().cf_paths, out_file_number,
-                        c->output_path_id());
-
-      // TODO (mikechuang): Currently skip calling
-      // EventHelpers::NotifyTableFileCreationStarted for the trivial copy.
-      // Since it's a trivial copy we should ideally use the exact
-      // TableProperties from the input file but that will break some existing
-      // stress tests. For now skip the listener call for the FIFO
-      // kChangeTemperature trivial copy move.
-
-      int64_t tmp_current_time = 0;
-      auto get_time_status =
-          immutable_db_options_.clock->GetCurrentTime(&tmp_current_time);
-      if (!get_time_status.ok()) {
-        ROCKS_LOG_BUFFER(log_buffer,
-                         "[%s] WARNING: Failed to get current time %s "
-                         "status=%s",
-                         c->column_family_data()->GetName().c_str(),
-                         get_time_status.ToString().c_str());
-      }
-      uint64_t out_file_creation_time = static_cast<uint64_t>(tmp_current_time);
-
-      FileOptions copied_file_options = file_options_;
-      copied_file_options.temperature = c->output_temperature();
-      std::unique_ptr<WritableFileWriter> dest_writer;
-      {
-        std::unique_ptr<FSWritableFile> dest_file;
-        IOStatus writable_file_io_status =
-            immutable_db_options_.fs.get()->NewWritableFile(
-                out_fname, copied_file_options, &dest_file, nullptr /* dbg */);
-        TEST_SYNC_POINT_CALLBACK(
-            "NewWritableFile::FileOptions.temperature",
-            const_cast<Temperature*>(&copied_file_options.temperature));
-        if (!writable_file_io_status.ok()) {
-          io_s = writable_file_io_status;
-          ROCKS_LOG_BUFFER(
-              log_buffer,
-              "[%s] Error: Abort trivial copy compaction, failed to open "
-              "NewWritableFile %s\n"
-              " out_fname=%s, temperature=%s, io_status=%s",
-              c->column_family_data()->GetName().c_str(), out_fname.c_str(),
-              temperature_to_string[c->output_temperature()].c_str(),
-              io_s.ToString().c_str());
-          break;
-        }
-
-        FileTypeSet tmp_set = immutable_db_options_.checksum_handoff_file_types;
-        dest_writer.reset(new WritableFileWriter(
-            std::move(dest_file), out_fname, copied_file_options,
-            immutable_db_options_.clock, io_tracer_,
-            immutable_db_options_.stats, Histograms::SST_WRITE_MICROS,
-            c->immutable_options().listeners,
-            immutable_db_options_.file_checksum_gen_factory.get(),
-            tmp_set.Contains(FileType::kTableFile), false));
-      }
-
-      ROCKS_LOG_BUFFER(
-          log_buffer,
-          "[%s] Started copying from: %s\n"
-          " temperature=%s, to: %s, temperature=%s, buffer_size=%" PRIu64,
-          c->column_family_data()->GetName().c_str(), in_fname.c_str(),
-          temperature_to_string[in_file->temperature].c_str(),
-          out_fname.c_str(),
-          temperature_to_string[c->output_temperature()].c_str(),
-          c->mutable_cf_options()
-              .compaction_options_fifo.trivial_copy_buffer_size);
-      // Add IO_LOW HINT for compaction
-      IOOptions copy_files_compaction_io_options;
-      copy_files_compaction_io_options.rate_limiter_priority =
-          Env::IOPriority::IO_LOW;
-      copy_files_compaction_io_options.type = IOType::kData;
-      copy_files_compaction_io_options.io_activity =
-          Env::IOActivity::kCompaction;
-
-      IOStatus copy_file_io_status = CopyFile(
-          immutable_db_options_.fs.get() /* fileSystem */,
-          in_fname /* source */, in_file->temperature /* src_temp_hint */,
-          dest_writer /* dest_writer */, 0 /* size */, true /* use_fsync */,
-          io_tracer_ /* io_tracer*/,
-          c->mutable_cf_options()
-              .compaction_options_fifo
-              .trivial_copy_buffer_size /* max_read_buffer_size
-                                         */
-          ,
-          copy_files_compaction_io_options /* readIOOptions */,
-          copy_files_compaction_io_options /* writeIOOptions */);
-      if (dest_writer) {
-        IOOptions close_files_compaction_io_options;
-        close_files_compaction_io_options.rate_limiter_priority =
-            Env::IOPriority::IO_LOW;
-        close_files_compaction_io_options.type = IOType::kData;
-        close_files_compaction_io_options.io_activity =
-            Env::IOActivity::kCompaction;
-        // Close the dest_write
-        io_s = dest_writer->Close(close_files_compaction_io_options);
-        if (!io_s.ok()) {
-          ROCKS_LOG_BUFFER(
-              log_buffer,
-              "[%s] Failed to close the writer. Failed to copy from: %s\n"
-              " temperature=%s, to=%s, temperature=%s, io_status=%s",
-              c->column_family_data()->GetName().c_str(), in_fname.c_str(),
-              temperature_to_string[in_file->temperature].c_str(),
-              out_fname.c_str(),
-              temperature_to_string[c->output_temperature()].c_str(),
-              io_s.ToString().c_str());
-          break;
-        }
-      }
-
-      io_s = copy_file_io_status;
-
-      if (!io_s.ok()) {
-        ROCKS_LOG_BUFFER(log_buffer,
-                         "[%s] Failed to copy from: %s\n"
-                         " temperature=%s, to=%s, temperature=%s, io_status=%s",
-                         c->column_family_data()->GetName().c_str(),
-                         in_fname.c_str(),
-                         temperature_to_string[in_file->temperature].c_str(),
-                         out_fname.c_str(),
-                         temperature_to_string[c->output_temperature()].c_str(),
-                         io_s.ToString().c_str());
-        break;
-      }
-      ROCKS_LOG_BUFFER(log_buffer,
-                       "[%s] Successfully copying from: %s\n"
-                       " temperature=%s, to=%s, temperature=%s, io_status=%s",
-                       c->column_family_data()->GetName().c_str(),
-                       in_fname.c_str(),
-                       temperature_to_string[in_file->temperature].c_str(),
-                       out_fname.c_str(),
-                       temperature_to_string[c->output_temperature()].c_str(),
-                       io_s.ToString().c_str());
-
-      FileMetaData out_file_metadata{
-          out_file_number,
-          c->output_path_id(),
-          in_file->fd.GetFileSize(),
-          in_file->smallest,
-          in_file->largest,
-          in_file->fd.smallest_seqno,
-          in_file->fd.largest_seqno,
-          false /* marked_for_compact */,
-          c->output_temperature() /* temperature */,
-          in_file->oldest_blob_file_number,
-          in_file->oldest_ancester_time,
-          out_file_creation_time,
-          c->MinInputFileEpochNumber(),
-          dest_writer->GetFileChecksum(),
-          dest_writer->GetFileChecksumFuncName(),
-          in_file->unique_id,
-          in_file->compensated_range_deletion_size,
-          in_file->tail_size,
-          in_file->user_defined_timestamps_persisted};
-
-      out_files.push_back(std::move(out_file_metadata));
-    }
-
-    // Update version set
-    if (status.ok() && io_s.ok()) {
-      // NOTE: ChangeTemperature should only copy one file at one file
-      // hence *c->inputs(0) == out_files.size() == 1 if copy succeeded
-      assert(c->inputs(0)->size() == 1);
-      assert(out_files.size() == 1);
-
-      auto out_file_metadata_it = out_files.begin();
-      for (const auto& in_file : *c->inputs(0)) {
-        if (out_file_metadata_it == out_files.end()) {
-          break;
-        }
-
-        c->edit()->DeleteFile(c->level(), in_file->fd.GetNumber());
-        c->edit()->AddFile(c->level(), *out_file_metadata_it);
-        ++out_file_metadata_it;
-      }
-
-      status = versions_->LogAndApply(
-          c->column_family_data(), read_options, write_options, c->edit(),
-          &mutex_, directories_.GetDbDir(),
-          /*new_descriptor_log=*/false, /*column_family_options=*/nullptr,
-          [&c, &compaction_released](const Status& s) {
-            c->ReleaseCompactionFiles(s);
-            compaction_released = true;
-          });
-    }
-
-    // TODO (mikechuang): Currently skip calling
-    // EventHelper::LogAndNotifyTableFileCreationFinished for the trivial copy.
-    // Since it's a trivial copy we should ideally use the exact TableProperties
-    // from the input file but that will break some existing stress tests. For
-    // now skip the listener call for the FIFO kChangeTemperature trivial copy
-    // move.
-
-    if (io_s.ok()) {
-      io_s = versions_->io_status();
-    }
-
-    InstallSuperVersionAndScheduleWork(
-        c->column_family_data(), job_context->superversion_contexts.data());
-    if (status.ok() && io_s.ok()) {
-      UpdateFIFOCompactionStatus(c);
-    } else {
-      for (const auto& in_file : *c->inputs(0)) {
-        const std::string in_fname =
-            TableFileName(c->immutable_options().cf_paths,
-                          in_file->fd.GetNumber(), in_file->fd.GetPathId());
-        ROCKS_LOG_BUFFER(
-            log_buffer,
-            "[%s] Failed to do trvial copy compaction: %s"
-            " temperature=%s, to temperature=%s, status=%s, io_status=%s",
-            c->column_family_data()->GetName().c_str(), in_fname.c_str(),
-            temperature_to_string[in_file->temperature].c_str(),
-            temperature_to_string[c->output_temperature()].c_str(),
-            status.ToString().c_str(), io_s.ToString().c_str());
-      }
-    }
-    *made_progress = true;
-    TEST_SYNC_POINT_CALLBACK(
-        "DBImpl::BackgroundCompaction:TriviaCopyAfterCompaction",
-        c->column_family_data());
   } else if (!trivial_move_disallowed && c->IsTrivialMove()) {
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:TrivialMove");
     TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:BeforeCompaction",
@@ -4149,16 +3881,14 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     ThreadStatusUtil::ResetThreadStatus();
     TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
                              c->column_family_data());
-  } else if (!is_prepicked &&
-             Compaction::OutputToNonZeroMaxOutputLevel(
-                 c->output_level(),
+  } else if (!is_prepicked && c->output_level() > 0 &&
+             c->output_level() ==
                  c->column_family_data()
                      ->current()
                      ->storage_info()
                      ->MaxOutputLevel(
-                         immutable_db_options_.allow_ingest_behind)) &&
+                         immutable_db_options_.allow_ingest_behind) &&
              env_->GetBackgroundThreads(Env::Priority::BOTTOM) > 0) {
-    assert(thread_pri == Env::Priority::LOW);
     // Forward compactions involving last level to the bottom pool if it exists,
     // such that compactions unlikely to contribute to write stalls can be
     // delayed or deprioritized.
@@ -4167,23 +3897,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     ca->db = this;
     ca->compaction_pri_ = Env::Priority::BOTTOM;
     ca->prepicked_compaction = new PrepickedCompaction;
-
-    // If `universal_reduce_file_locking` is true, we only lock a limited set of
-    // input files by creating an intended compaction to forward to bottom
-    // priority pool and repicking files when bottom priority thread
-    // gets to execute this intended compaction
-    const bool need_repick =
-        c->mutable_cf_options()
-            .compaction_options_universal.reduce_file_locking;
-    if (need_repick) {
-      ca->prepicked_compaction->compaction =
-          CreateIntendedCompactionForwardedToBottomPriorityPool(c.get());
-      c.reset();
-      ca->prepicked_compaction->need_repick = true;
-    } else {
-      ca->prepicked_compaction->compaction = c.release();
-      ca->prepicked_compaction->need_repick = false;
-    }
+    ca->prepicked_compaction->compaction = c.release();
     ca->prepicked_compaction->manual_compaction_state = nullptr;
     // Transfer requested token, so it doesn't need to do it again.
     ca->prepicked_compaction->task_token = std::move(task_token);
@@ -4198,7 +3912,11 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     output_level = c->output_level();
     TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:NonTrivial",
                              &output_level);
-    InitSnapshotContext(job_context);
+    std::vector<SequenceNumber> snapshot_seqs;
+    SequenceNumber earliest_write_conflict_snapshot;
+    SnapshotChecker* snapshot_checker;
+    GetSnapshotContext(job_context, &snapshot_seqs,
+                       &earliest_write_conflict_snapshot, &snapshot_checker);
     assert(is_snapshot_supported_ || snapshots_.empty());
 
     CompactionJob compaction_job(
@@ -4207,7 +3925,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
         &shutting_down_, log_buffer, directories_.GetDbDir(),
         GetDataDir(c->column_family_data(), c->output_path_id()),
         GetDataDir(c->column_family_data(), 0), stats_, &mutex_,
-        &error_handler_, job_context, table_cache_, &event_logger_,
+        &error_handler_, snapshot_seqs, earliest_write_conflict_snapshot,
+        snapshot_checker, job_context, table_cache_, &event_logger_,
         c->mutable_cf_options().paranoid_file_checks,
         c->mutable_cf_options().report_bg_io_stats, dbname_,
         &compaction_job_stats, thread_pri, io_tracer_,
@@ -4227,15 +3946,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
                             compaction_job_stats, job_context->job_id);
     mutex_.Unlock();
-    if (thread_pri == Env::Priority::LOW) {
-      TEST_SYNC_POINT_CALLBACK(
-          "DBImpl::BackgroundCompaction:NonTrivial:BeforeRun", nullptr);
-    } else {
-      assert(thread_pri == Env::Priority::BOTTOM);
-      TEST_SYNC_POINT(
-          "DBImpl::BackgroundCompaction:NonTrivial:BeforeRunBottomPri");
-    }
-
+    TEST_SYNC_POINT_CALLBACK(
+        "DBImpl::BackgroundCompaction:NonTrivial:BeforeRun", nullptr);
     // Should handle error?
     compaction_job.Run().PermitUncheckedError();
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
@@ -4329,7 +4041,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
           ->storage_info()
           ->ComputeCompactionScore(c->immutable_options(),
                                    c->mutable_cf_options());
-      EnqueuePendingCompaction(cfd);
+      if (!cfd->queued_for_compaction()) {
+        AddToCompactionQueue(cfd);
+      }
     }
   }
   // this will unref its input_version and column_family_data
@@ -4374,71 +4088,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
   return status;
 }
 
-// Create an intended compaction to forward based on the original picked
-// compaction. It serves two purposes while it is waiting
-// for a bottom-priority thread becomes available to run:
-// - Prevent the last input file (or sorted run if non-L0) from
-// being included in compaction score calculations unnecessarily since the
-// intended compaction is already scheduled to compact it
-// - Allow other input files to be picked by low-priority compactions that can
-// run right away
-//
-// Once a bottom-priority available to run this intended compaction, it will
-// repick files to consider the LSM updates that occurred during the waiting
-// period.
-Compaction* DBImpl::CreateIntendedCompactionForwardedToBottomPriorityPool(
-    Compaction* c) {
-  auto* cfd = c->column_family_data();
-  const auto& io = c->immutable_options();
-  const auto& mo = c->mutable_cf_options();
-  auto* vstorage = c->input_version()->storage_info();
-
-  std::vector<CompactionInputFiles> inputs(1);
-
-  const std::vector<FileMetaData*>* max_intput_level_files = nullptr;
-  int max_intput_level = 0;
-
-  for (size_t i = c->num_input_levels(); i >= 1; --i) {
-    size_t level = i - 1;
-    if (c->num_input_files(level) > 0) {
-      max_intput_level = static_cast<int>(level);
-      max_intput_level_files = c->inputs(level);
-      break;
-    }
-  }
-
-  assert(max_intput_level_files);
-  assert(!max_intput_level_files->empty());
-  inputs[0].level = max_intput_level;
-
-  if (max_intput_level == 0) {
-    // The last input file
-    inputs[0].files.push_back(
-        (*max_intput_level_files)[max_intput_level_files->size() - 1]);
-  } else {
-    // The last input sorted run
-    for (FileMetaData* f : (*max_intput_level_files)) {
-      inputs[0].files.push_back(f);
-    }
-  }
-
-  c->ReleaseCompactionFiles(Status::OK());
-
-  Compaction* intended_compaction = new Compaction(
-      vstorage, io, mo, mutable_db_options_, std::move(inputs),
-      c->output_level(), c->target_output_file_size(),
-      c->max_compaction_bytes(), c->output_path_id(), c->output_compression(),
-      c->output_compression_opts(), c->output_temperature(),
-      c->max_subcompactions(), c->grandparents(),
-      std::nullopt /* earliest_snapshot */, nullptr /* snapshot_checker */);
-
-  cfd->compaction_picker()->RegisterCompaction(intended_compaction);
-  vstorage->ComputeCompactionScore(io, mo);
-  intended_compaction->FinalizeInputInfo(cfd->current());
-
-  return intended_compaction;
-}
-
 bool DBImpl::HasPendingManualCompaction() {
   return (!manual_compaction_dequeue_.empty());
 }
@@ -4527,7 +4176,8 @@ bool DBImpl::MCOverlap(ManualCompactionState* m, ManualCompactionState* m1) {
   return false;
 }
 
-void DBImpl::UpdateFIFOCompactionStatus(const std::unique_ptr<Compaction>& c) {
+void DBImpl::UpdateDeletionCompactionStats(
+    const std::unique_ptr<Compaction>& c) {
   if (c == nullptr) {
     return;
   }
@@ -4541,9 +4191,6 @@ void DBImpl::UpdateFIFOCompactionStatus(const std::unique_ptr<Compaction>& c) {
     case CompactionReason::kFIFOTtl:
       RecordTick(stats_, FIFO_TTL_COMPACTIONS);
       break;
-    case CompactionReason::kChangeTemperature:
-      RecordTick(stats_, FIFO_CHANGE_TEMPERATURE_COMPACTIONS);
-      break;
     default:
       assert(false);
       break;
@@ -4710,33 +4357,31 @@ void DBImpl::SetSnapshotChecker(SnapshotChecker* snapshot_checker) {
   snapshot_checker_.reset(snapshot_checker);
 }
 
-void DBImpl::InitSnapshotContext(JobContext* job_context) {
+void DBImpl::GetSnapshotContext(
+    JobContext* job_context, std::vector<SequenceNumber>* snapshot_seqs,
+    SequenceNumber* earliest_write_conflict_snapshot,
+    SnapshotChecker** snapshot_checker_ptr) {
   mutex_.AssertHeld();
   assert(job_context != nullptr);
-  if (job_context->snapshot_context_initialized) {
-    return;
+  assert(snapshot_seqs != nullptr);
+  assert(earliest_write_conflict_snapshot != nullptr);
+  assert(snapshot_checker_ptr != nullptr);
+
+  *snapshot_checker_ptr = snapshot_checker_.get();
+  if (use_custom_gc_ && *snapshot_checker_ptr == nullptr) {
+    *snapshot_checker_ptr = DisableGCSnapshotChecker::Instance();
   }
-  SnapshotChecker* snapshot_checker = snapshot_checker_.get();
-  if (use_custom_gc_ && !snapshot_checker) {
-    snapshot_checker = DisableGCSnapshotChecker::Instance();
-  }
-  std::unique_ptr<ManagedSnapshot> managed_snapshot = nullptr;
-  if (snapshot_checker) {
+  if (*snapshot_checker_ptr != nullptr) {
     // If snapshot_checker is used, that means the flush/compaction may
     // contain values not visible to snapshot taken after
     // flush/compaction job starts. Take a snapshot and it will appear
     // in snapshot_seqs and force compaction iterator to consider such
     // snapshots.
-    const Snapshot* snapshot =
-        GetSnapshotImpl(/*is_write_conflict_boundary=*/false, /*lock=*/false);
-    managed_snapshot.reset(new ManagedSnapshot(this, snapshot));
+    const Snapshot* job_snapshot =
+        GetSnapshotImpl(false /*write_conflict_boundary*/, false /*lock*/);
+    job_context->job_snapshot.reset(new ManagedSnapshot(this, job_snapshot));
   }
-  SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber;
-  std::vector<SequenceNumber> snapshot_seqs =
-      snapshots_.GetAll(&earliest_write_conflict_snapshot);
-  job_context->InitSnapshotContext(
-      snapshot_checker, std::move(managed_snapshot),
-      earliest_write_conflict_snapshot, std::move(snapshot_seqs));
+  *snapshot_seqs = snapshots_.GetAll(earliest_write_conflict_snapshot);
 }
 
 Status DBImpl::WaitForCompact(
@@ -4795,18 +4440,4 @@ Status DBImpl::WaitForCompact(
   }
 }
 
-bool DBImpl::ShouldPickCompaction(
-    bool is_prepicked, const PrepickedCompaction* prepicked_compaction) {
-  return (!is_prepicked && !compaction_queue_.empty()) ||
-         (is_prepicked && prepicked_compaction->need_repick);
-}
-
-void DBImpl::ResetBottomPriCompactionIntent(ColumnFamilyData* cfd,
-                                            std::unique_ptr<Compaction>& c) {
-  c->ReleaseCompactionFiles(Status::OK());
-  cfd->current()->storage_info()->ComputeCompactionScore(
-      c->immutable_options(), c->mutable_cf_options());
-  c.reset();
-}
-
 }  // namespace ROCKSDB_NAMESPACE

db/db_impl/db_impl_debug.cc

@@ -84,7 +84,6 @@ void DBImpl::TEST_GetFilesMetaData(
 }
 
 uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
-  InstrumentedMutexLock l(&mutex_);
   return versions_->manifest_file_number();
 }
 

db/db_impl/db_impl_open.cc

@@ -2000,9 +2000,6 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
   const size_t ts_sz = ucmp->timestamp_size();
   const bool logical_strip_timestamp =
       ts_sz > 0 && !cfd->ioptions().persist_user_defined_timestamps;
-  // Note that here we treat flush as level 0 compaction in internal stats
-  InternalStats::CompactionStats flush_stats(CompactionReason::kFlush,
-                                             1 /* count */);
   {
     ScopedArenaPtr<InternalIterator> iter(
         logical_strip_timestamp
@@ -2075,20 +2072,19 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
           kMaxSequenceNumber);
       Version* version = cfd->current();
       version->Ref();
-      TableProperties temp_table_proerties;
-      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,
-          snapshot_seqs, earliest_snapshot, earliest_write_conflict_snapshot,
-          kMaxSequenceNumber, snapshot_checker, paranoid_file_checks,
-          cfd->internal_stats(), &io_s, io_tracer_,
-          BlobFileCreationReason::kRecovery,
-          nullptr /* seqno_to_time_mapping */, &event_logger_, job_id,
-          &temp_table_proerties /* table_properties */, write_hint,
-          nullptr /*full_history_ts_low*/, &blob_callback_, version,
-          nullptr /* memtable_payload_bytes */,
-          nullptr /* memtable_garbage_bytes */, &flush_stats);
+      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, snapshot_seqs, earliest_snapshot,
+                     earliest_write_conflict_snapshot, kMaxSequenceNumber,
+                     snapshot_checker, paranoid_file_checks,
+                     cfd->internal_stats(), &io_s, io_tracer_,
+                     BlobFileCreationReason::kRecovery,
+                     nullptr /* seqno_to_time_mapping */, &event_logger_,
+                     job_id, nullptr /* table_properties */, write_hint,
+                     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,
@@ -2104,31 +2100,10 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       }
 
       uint64_t total_num_entries = mem->NumEntries();
-      if (s.ok() && total_num_entries != flush_stats.num_input_records) {
+      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(flush_stats.num_input_records);
-        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);
-        }
-      }
-      // Only verify on table with format collects table properties
-      const auto& mutable_cf_options = cfd->GetLatestMutableCFOptions();
-      if (s.ok() &&
-          (mutable_cf_options.table_factory->IsInstanceOf(
-               TableFactory::kBlockBasedTableName()) ||
-           mutable_cf_options.table_factory->IsInstanceOf(
-               TableFactory::kPlainTableName())) &&
-          flush_stats.num_output_records != temp_table_proerties.num_entries) {
-        std::string msg =
-            "Number of keys in flush output SST files does not match "
-            "number of keys added to the table. Expected " +
-            std::to_string(flush_stats.num_output_records) + " but there are " +
-            std::to_string(temp_table_proerties.num_entries) +
-            " in output SST files";
+                          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());
@@ -2176,25 +2151,25 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
     }
   }
 
-  flush_stats.micros = immutable_db_options_.clock->NowMicros() - start_micros;
+  InternalStats::CompactionStats stats(CompactionReason::kFlush, 1);
+  stats.micros = immutable_db_options_.clock->NowMicros() - start_micros;
 
   if (has_output) {
-    flush_stats.bytes_written = meta.fd.GetFileSize();
-    flush_stats.num_output_files = 1;
+    stats.bytes_written = meta.fd.GetFileSize();
+    stats.num_output_files = 1;
   }
 
   const auto& blobs = edit->GetBlobFileAdditions();
   for (const auto& blob : blobs) {
-    flush_stats.bytes_written_blob += blob.GetTotalBlobBytes();
+    stats.bytes_written_blob += blob.GetTotalBlobBytes();
   }
 
-  flush_stats.num_output_files_blob = static_cast<int>(blobs.size());
+  stats.num_output_files_blob = static_cast<int>(blobs.size());
 
-  cfd->internal_stats()->AddCompactionStats(level, Env::Priority::USER,
-                                            flush_stats);
+  cfd->internal_stats()->AddCompactionStats(level, Env::Priority::USER, stats);
   cfd->internal_stats()->AddCFStats(
       InternalStats::BYTES_FLUSHED,
-      flush_stats.bytes_written + flush_stats.bytes_written_blob);
+      stats.bytes_written + stats.bytes_written_blob);
   RecordTick(stats_, COMPACT_WRITE_BYTES, meta.fd.GetFileSize());
   return s;
 }

db/db_impl/db_impl_secondary.cc

@@ -728,13 +728,13 @@ Status DBImplSecondary::TryCatchUpWithPrimary() {
     // instance
     if (s.ok()) {
       s = FindAndRecoverLogFiles(&cfds_changed, &job_context);
-      if (s.IsPathNotFound()) {
-        ROCKS_LOG_INFO(
-            immutable_db_options_.info_log,
-            "Secondary tries to read WAL, but WAL file(s) have already "
-            "been purged by primary.");
-        s = Status::OK();
-      }
+    }
+    if (s.IsPathNotFound()) {
+      ROCKS_LOG_INFO(
+          immutable_db_options_.info_log,
+          "Secondary tries to read WAL, but WAL file(s) have already "
+          "been purged by primary.");
+      s = Status::OK();
     }
     if (s.ok()) {
       for (auto cfd : cfds_changed) {
@@ -909,7 +909,7 @@ Status DBImplSecondary::CompactWithoutInstallation(
     ROCKS_LOG_ERROR(
         immutable_db_options_.info_log,
         "GetCompactionInputsFromFileNumbers() failed - %s.\n DebugString: %s",
-        s.ToString().c_str(), version->DebugString(/*hex=*/true).c_str());
+        s.ToString().c_str(), version->DebugString().c_str());
     return s;
   }
 
@@ -933,10 +933,7 @@ Status DBImplSecondary::CompactWithoutInstallation(
                        immutable_db_options_.info_log.get());
 
   const int job_id = next_job_id_.fetch_add(1);
-  JobContext job_context(0, true /*create_superversion*/);
-  std::vector<SequenceNumber> snapshots = input.snapshots;
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber,
-                                  std::move(snapshots));
+
   // use primary host's db_id for running the compaction, but db_session_id is
   // using the local one, which is to make sure the unique id is unique from
   // the remote compactors. Because the id is generated from db_id,
@@ -947,7 +944,7 @@ Status DBImplSecondary::CompactWithoutInstallation(
       job_id, c.get(), immutable_db_options_, mutable_db_options_,
       file_options_for_compaction_, versions_.get(), &shutting_down_,
       &log_buffer, output_dir.get(), stats_, &mutex_, &error_handler_,
-      &job_context, table_cache_, &event_logger_, dbname_, io_tracer_,
+      input.snapshots, table_cache_, &event_logger_, dbname_, io_tracer_,
       options.canceled ? *options.canceled : kManualCompactionCanceledFalse_,
       input.db_id, db_session_id_, secondary_path_, input, result);
 

db/db_impl/db_impl_write.cc

@@ -856,7 +856,8 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
             write_group, current_sequence, column_family_memtables_.get(),
             &flush_scheduler_, &trim_history_scheduler_,
             write_options.ignore_missing_column_families,
-            0 /*recovery_log_number*/, this, seq_per_batch_, batch_per_txn_);
+            0 /*recovery_log_number*/, this, parallel, seq_per_batch_,
+            batch_per_txn_);
       } else {
         write_group.last_sequence = last_sequence;
         write_thread_.LaunchParallelMemTableWriters(&write_group);
@@ -928,7 +929,6 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
                                /*min_prep_log=*/log_ref, last_sequence,
                                /*memtable_updated=*/memtable_update_count > 0,
                                write_options.ignore_missing_column_families);
-      RecordTick(stats_, NUMBER_WBWI_INGEST);
     }
   }
 
@@ -1114,7 +1114,7 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
           memtable_write_group, w.sequence, column_family_memtables_.get(),
           &flush_scheduler_, &trim_history_scheduler_,
           write_options.ignore_missing_column_families, 0 /*log_number*/, this,
-          seq_per_batch_, batch_per_txn_);
+          false /*concurrent_memtable_writes*/, seq_per_batch_, batch_per_txn_);
       if (memtable_write_group.status
               .ok()) {  // Don't publish a partial batch write
         versions_->SetLastSequence(memtable_write_group.last_sequence);

db/db_io_failure_test.cc

@@ -7,8 +7,6 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#include <iomanip>
-
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
 #include "test_util/testutil.h"

db/db_iter.cc

@@ -66,11 +66,11 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
       timestamp_lb_(read_options.iter_start_ts),
       timestamp_size_(timestamp_ub_ ? timestamp_ub_->size() : 0),
       active_mem_(active_mem),
-      memtable_seqno_lb_(kMaxSequenceNumber),
-      memtable_op_scan_flush_trigger_(0),
-      avg_op_scan_flush_trigger_(0),
-      iter_step_since_seek_(1),
-      mem_hidden_op_scanned_since_seek_(0),
+      memtable_seqno_lb_((active_mem_ && !active_mem_->IsEmpty())
+                             ? active_mem_->GetFirstSequenceNumber()
+                             : kMaxSequenceNumber),
+      memtable_op_scan_flush_trigger_(
+          mutable_cf_options.memtable_op_scan_flush_trigger),
       direction_(kForward),
       valid_(false),
       current_entry_is_merged_(false),
@@ -98,25 +98,6 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
   // prefix_seek_opt_in_only should force total_order_seek whereever the caller
   // is duplicating the original ReadOptions
   assert(!ioptions.prefix_seek_opt_in_only || read_options.total_order_seek);
-  if (active_mem_) {
-    // FIXME: GetEarliestSequenceNumber() may return a seqno that is one smaller
-    // than the smallest seqno in the memtable. This violates its comment and
-    // entries with that seqno may not be in the active memtable. Before it's
-    // fixed, we use GetFirstSequenceNumber() for more accurate result.
-    memtable_seqno_lb_ = active_mem_->IsEmpty()
-                             ? active_mem_->GetEarliestSequenceNumber()
-                             : active_mem_->GetFirstSequenceNumber();
-    memtable_op_scan_flush_trigger_ =
-        mutable_cf_options.memtable_op_scan_flush_trigger;
-    if (memtable_op_scan_flush_trigger_) {
-      // avg_op_scan_flush_trigger_ requires memtable_op_scan_flush_trigger_ > 0
-      avg_op_scan_flush_trigger_ =
-          mutable_cf_options.memtable_avg_op_scan_flush_trigger;
-    }
-  } else {
-    // memtable_op_scan_flush_trigger_ and avg_op_scan_flush_trigger_ are
-    // initialized to 0(disabled) as default.
-  }
 }
 
 Status DBIter::GetProperty(std::string prop_name, std::string* prop) {
@@ -178,7 +159,6 @@ void DBIter::Next() {
   local_stats_.skip_count_ += num_internal_keys_skipped_;
   local_stats_.skip_count_--;
   num_internal_keys_skipped_ = 0;
-  iter_step_since_seek_++;
   bool ok = true;
   if (direction_ == kReverse) {
     is_key_seqnum_zero_ = false;
@@ -393,7 +373,8 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
   // to one.
   bool reseek_done = false;
 
-  uint64_t mem_hidden_op_scanned = 0;
+  uint64_t mem_ops_scanned = 0;
+  bool marked_for_flush = false;
   do {
     // Will update is_key_seqnum_zero_ as soon as we parsed the current key
     // but we need to save the previous value to be used in the loop.
@@ -450,7 +431,12 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
           CompareKeyForSkip(ikey_.user_key, saved_key_.GetUserKey()) <= 0) {
         num_skipped++;  // skip this entry
         PERF_COUNTER_ADD(internal_key_skipped_count, 1);
-        MarkMemtableForFlushForPerOpTrigger(mem_hidden_op_scanned);
+        if (memtable_op_scan_flush_trigger_ && active_mem_ &&
+            ikey_.sequence >= memtable_seqno_lb_ && !marked_for_flush &&
+            ++mem_ops_scanned >= memtable_op_scan_flush_trigger_) {
+          active_mem_->MarkForFlush();
+          marked_for_flush = true;
+        }
       } else {
         assert(!skipping_saved_key ||
                CompareKeyForSkip(ikey_.user_key, saved_key_.GetUserKey()) > 0);
@@ -472,7 +458,12 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
                                       !iter_.iter()->IsKeyPinned() /* copy */);
               skipping_saved_key = true;
               PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
-              MarkMemtableForFlushForPerOpTrigger(mem_hidden_op_scanned);
+              if (memtable_op_scan_flush_trigger_ && active_mem_ &&
+                  ikey_.sequence >= memtable_seqno_lb_ && !marked_for_flush &&
+                  ++mem_ops_scanned >= memtable_op_scan_flush_trigger_) {
+                active_mem_->MarkForFlush();
+                marked_for_flush = true;
+              }
             }
             break;
           case kTypeValue:
@@ -1597,7 +1588,6 @@ void DBIter::Seek(const Slice& target) {
   ResetBlobData();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
-  MarkMemtableForFlushForAvgTrigger();
 
   // Seek the inner iterator based on the target key.
   {
@@ -1674,7 +1664,6 @@ void DBIter::SeekForPrev(const Slice& target) {
   ResetBlobData();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
-  MarkMemtableForFlushForAvgTrigger();
 
   // Seek the inner iterator based on the target key.
   {
@@ -1736,7 +1725,6 @@ void DBIter::SeekToFirst() {
   ResetBlobData();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
-  MarkMemtableForFlushForAvgTrigger();
   ClearSavedValue();
   is_key_seqnum_zero_ = false;
 
@@ -1800,7 +1788,6 @@ void DBIter::SeekToLast() {
   ResetBlobData();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
-  MarkMemtableForFlushForAvgTrigger();
   ClearSavedValue();
   is_key_seqnum_zero_ = false;
 

db/db_iter.h

@@ -12,6 +12,7 @@
 #include <string>
 
 #include "db/db_impl/db_impl.h"
+#include "db/range_del_aggregator.h"
 #include "memory/arena.h"
 #include "options/cf_options.h"
 #include "rocksdb/db.h"
@@ -61,8 +62,7 @@ class DBIter final : public Iterator {
   //
   // @param active_mem Pointer to the active memtable that `internal_iter`
   // is reading from. If not null, the memtable can be marked for flush
-  // according to options mutable_cf_options.memtable_op_scan_flush_trigger
-  // and mutable_cf_options.memtable_avg_op_scan_flush_trigger.
+  // according to option mutable_cf_options.memtable_op_scan_flush_trigger.
   // @param arena_mode If true, the DBIter will be allocated from the arena.
   static DBIter* NewIter(Env* env, const ReadOptions& read_options,
                          const ImmutableOptions& ioptions,
@@ -71,9 +71,9 @@ class DBIter final : public Iterator {
                          InternalIterator* internal_iter,
                          const Version* version, const SequenceNumber& sequence,
                          ReadCallback* read_callback,
-                         ReadOnlyMemTable* active_mem,
                          ColumnFamilyHandleImpl* cfh = nullptr,
                          bool expose_blob_index = false,
+                         ReadOnlyMemTable* active_mem = nullptr,
                          Arena* arena = nullptr) {
     void* mem = arena ? arena->AllocateAligned(sizeof(DBIter))
                       : operator new(sizeof(DBIter));
@@ -145,7 +145,6 @@ class DBIter final : public Iterator {
   void operator=(const DBIter&) = delete;
 
   ~DBIter() override {
-    MarkMemtableForFlushForAvgTrigger();
     ThreadStatus::OperationType cur_op_type =
         ThreadStatusUtil::GetThreadOperation();
     ThreadStatusUtil::SetThreadOperation(
@@ -418,36 +417,6 @@ class DBIter final : public Iterator {
     return true;
   }
 
-  void MarkMemtableForFlushForAvgTrigger() {
-    if (avg_op_scan_flush_trigger_ &&
-        mem_hidden_op_scanned_since_seek_ >= memtable_op_scan_flush_trigger_ &&
-        mem_hidden_op_scanned_since_seek_ >=
-            static_cast<uint64_t>(iter_step_since_seek_) *
-                avg_op_scan_flush_trigger_) {
-      assert(memtable_op_scan_flush_trigger_ > 0);
-      active_mem_->MarkForFlush();
-      avg_op_scan_flush_trigger_ = 0;
-      memtable_op_scan_flush_trigger_ = 0;
-    }
-    iter_step_since_seek_ = 1;
-    mem_hidden_op_scanned_since_seek_ = 0;
-  }
-
-  void MarkMemtableForFlushForPerOpTrigger(uint64_t& mem_hidden_op_scanned) {
-    if (memtable_op_scan_flush_trigger_ &&
-        ikey_.sequence >= memtable_seqno_lb_) {
-      if (++mem_hidden_op_scanned >= memtable_op_scan_flush_trigger_) {
-        active_mem_->MarkForFlush();
-        // Turn off the flush trigger checks.
-        memtable_op_scan_flush_trigger_ = 0;
-        avg_op_scan_flush_trigger_ = 0;
-      }
-      if (avg_op_scan_flush_trigger_) {
-        ++mem_hidden_op_scanned_since_seek_;
-      }
-    }
-  }
-
   const SliceTransform* prefix_extractor_;
   Env* const env_;
   SystemClock* clock_;
@@ -506,12 +475,9 @@ class DBIter final : public Iterator {
   const size_t timestamp_size_;
   std::string saved_timestamp_;
   std::optional<std::vector<ScanOptions>> scan_opts_;
-  ReadOnlyMemTable* const active_mem_;
+  ReadOnlyMemTable* active_mem_;
   SequenceNumber memtable_seqno_lb_;
   uint32_t memtable_op_scan_flush_trigger_;
-  uint32_t avg_op_scan_flush_trigger_;
-  uint32_t iter_step_since_seek_;
-  uint32_t mem_hidden_op_scanned_since_seek_;
   Direction direction_;
   bool valid_;
   bool current_entry_is_merged_;

db/db_iter_stress_test.cc

@@ -532,7 +532,7 @@ TEST_F(DBIteratorStressTest, StressTest) {
                       env_, ropt, ImmutableOptions(options),
                       MutableCFOptions(options), BytewiseComparator(),
                       internal_iter, /*version=*/nullptr, sequence,
-                      nullptr /*read_callback*/, /*active_mem=*/nullptr));
+                      nullptr /*read_callback*/));
                 }
 
                 // Do a random operation. It's important to do it on ref_it

db/db_iter_test.cc

@@ -262,7 +262,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -296,7 +296,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -323,7 +323,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -356,7 +356,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -392,7 +392,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
@@ -423,7 +423,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 7 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     SetPerfLevel(kEnableCount);
     ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -462,7 +462,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -488,7 +488,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
@@ -512,7 +512,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -548,7 +548,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 7 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     SetPerfLevel(kEnableCount);
     ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -579,7 +579,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -623,7 +623,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -655,7 +655,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -686,7 +686,7 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
     ASSERT_OK(db_iter->status());
@@ -699,7 +699,7 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToFirst();
     ASSERT_TRUE(!db_iter->Valid());
     ASSERT_OK(db_iter->status());
@@ -723,7 +723,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkipCountSkips) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      2 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      2 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -770,7 +770,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
 
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -808,7 +808,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
 
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -838,7 +838,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, 202 /* sequence */,
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+
+          nullptr /* read_callback */));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -873,7 +874,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i /* sequence */,
 
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
       db_iter->SeekToLast();
       ASSERT_TRUE(!db_iter->Valid());
       ASSERT_OK(db_iter->status());
@@ -892,7 +893,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 200 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -930,7 +931,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
 
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -967,7 +968,7 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, i + 2 /* sequence */,
 
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -1018,7 +1019,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1065,7 +1066,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1110,7 +1111,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1149,7 +1150,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1185,7 +1186,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -1216,7 +1217,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1254,7 +1255,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1293,7 +1294,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
           env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
           internal_iter, nullptr /* version */, 2 * i + 1 /* sequence */,
 
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
 
       db_iter->SeekToFirst();
       ASSERT_TRUE(db_iter->Valid());
@@ -1347,7 +1348,7 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
       std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
           env_, ro, ioptions, MutableCFOptions(options), BytewiseComparator(),
           internal_iter, nullptr /* version */, 2 * i + 1 /* sequence */,
-          nullptr /* read_callback */, /*active_mem=*/nullptr));
+          nullptr /* read_callback */));
 
       db_iter->SeekToFirst();
       ASSERT_TRUE(db_iter->Valid());
@@ -1390,7 +1391,7 @@ TEST_F(DBIteratorTest, DBIteratorTimedPutBasic) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      7 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      7 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1440,7 +1441,7 @@ TEST_F(DBIteratorTest, DBIterator1) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      1 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      1 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1469,7 +1470,7 @@ TEST_F(DBIteratorTest, DBIterator2) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      0 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      0 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1494,7 +1495,7 @@ TEST_F(DBIteratorTest, DBIterator3) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      2 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      2 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1519,7 +1520,7 @@ TEST_F(DBIteratorTest, DBIterator4) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      4 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      4 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1553,7 +1554,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1577,7 +1578,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 1 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1601,7 +1602,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1625,7 +1626,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 3 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1649,7 +1650,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1673,7 +1674,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 5 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1697,7 +1698,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 6 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1719,7 +1720,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 10 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->Seek("b");
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -1750,7 +1751,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1774,7 +1775,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 1 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1798,7 +1799,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1822,7 +1823,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 3 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
     ASSERT_OK(db_iter->status());
@@ -1842,7 +1843,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1866,7 +1867,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 5 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1890,7 +1891,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 6 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1934,7 +1935,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 0 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1970,7 +1971,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 2 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2012,7 +2013,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 4 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2054,7 +2055,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 5 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2101,7 +2102,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 6 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2149,7 +2150,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 7 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2191,7 +2192,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 9 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2239,7 +2240,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 13 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2288,7 +2289,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
         env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
         internal_iter, nullptr /* version */, 14 /* sequence */,
-        nullptr /* read_callback */, /*active_mem=*/nullptr));
+        nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2320,7 +2321,7 @@ TEST_F(DBIteratorTest, DBIterator8) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -2348,11 +2349,10 @@ TEST_F(DBIteratorTest, DBIterator9) {
     internal_iter->AddMerge("d", "merge_6");
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(
-        DBIter::NewIter(env_, ro, ImmutableOptions(options),
-                        MutableCFOptions(options), BytewiseComparator(),
-                        internal_iter, nullptr /* version */, 10 /* sequence */,
-                        nullptr /* read_callback */, /*active_mem=*/nullptr));
+    std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
+        env_, ro, ImmutableOptions(options), MutableCFOptions(options),
+        BytewiseComparator(), internal_iter, nullptr /* version */,
+        10 /* sequence */, nullptr /* read_callback */));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -2419,7 +2419,7 @@ TEST_F(DBIteratorTest, DBIterator10) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, nullptr /* read_callback */));
 
   db_iter->Seek("c");
   ASSERT_TRUE(db_iter->Valid());
@@ -2459,7 +2459,7 @@ TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, 0 /* force seek */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -2489,7 +2489,7 @@ TEST_F(DBIteratorTest, DBIterator11) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      1 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      1 /* sequence */, nullptr /* read_callback */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -2517,7 +2517,7 @@ TEST_F(DBIteratorTest, DBIterator12) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, 0 /* force seek */, nullptr /* read_callback */));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -2557,7 +2557,7 @@ TEST_F(DBIteratorTest, DBIterator13) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      2 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      2 /* sequence */, nullptr /* read_callback */));
   db_iter->Seek("b");
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), key);
@@ -2587,7 +2587,7 @@ TEST_F(DBIteratorTest, DBIterator14) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      4 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      4 /* sequence */, nullptr /* read_callback */));
   db_iter->Seek("b");
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -2627,8 +2627,7 @@ class DBIterWithMergeIterTest : public testing::Test {
     db_iter_.reset(DBIter::NewIter(
         env_, ro_, ImmutableOptions(options_), MutableCFOptions(options_),
         BytewiseComparator(), merge_iter, nullptr /* version */,
-        8 /* read data earlier than seqId 8 */, nullptr /* read_callback */,
-        /*active_mem=*/nullptr));
+        8 /* read data earlier than seqId 8 */, nullptr /* read_callback */));
   }
 
   Env* env_;
@@ -3067,7 +3066,7 @@ TEST_F(DBIteratorTest, SeekPrefixTombstones) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, nullptr /* read_callback */));
 
   int skipped_keys = 0;
 
@@ -3100,11 +3099,10 @@ TEST_F(DBIteratorTest, SeekToFirstLowerBound) {
     Slice lower_bound(lower_bound_str);
     ro.iterate_lower_bound = &lower_bound;
     Options options;
-    std::unique_ptr<Iterator> db_iter(
-        DBIter::NewIter(env_, ro, ImmutableOptions(options),
-                        MutableCFOptions(options), BytewiseComparator(),
-                        internal_iter, nullptr /* version */, 10 /* sequence */,
-                        nullptr /* read_callback */, /*active_mem=*/nullptr));
+    std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
+        env_, ro, ImmutableOptions(options), MutableCFOptions(options),
+        BytewiseComparator(), internal_iter, nullptr /* version */,
+        10 /* sequence */, nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     if (i == kNumKeys + 1) {
@@ -3143,7 +3141,7 @@ TEST_F(DBIteratorTest, PrevLowerBound) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, nullptr /* read_callback */));
 
   db_iter->SeekToLast();
   for (int i = kNumKeys; i >= kLowerBound; --i) {
@@ -3171,7 +3169,7 @@ TEST_F(DBIteratorTest, SeekLessLowerBound) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ro, ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, nullptr /* read_callback */));
 
   auto before_lower_bound_str = std::to_string(kLowerBound - 1);
   Slice before_lower_bound(lower_bound_str);
@@ -3196,7 +3194,7 @@ TEST_F(DBIteratorTest, ReverseToForwardWithDisappearingKeys) {
   std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
       env_, ReadOptions(), ImmutableOptions(options), MutableCFOptions(options),
       BytewiseComparator(), internal_iter, nullptr /* version */,
-      10 /* sequence */, nullptr /* read_callback */, /*active_mem=*/nullptr));
+      10 /* sequence */, nullptr /* read_callback */));
 
   db_iter->SeekForPrev("a");
   ASSERT_TRUE(db_iter->Valid());

db/db_iterator_test.cc

@@ -3890,7 +3890,6 @@ TEST_P(DBIteratorTest, MemtableOpsScanFlushTriggerWithSeek) {
             db_->GetIntProperty("rocksdb.num-deletes-active-mem-table", &val));
         ASSERT_EQ(0, val);
       } else {
-        ASSERT_EQ(0, NumTableFilesAtLevel(0));
         uint64_t val = 0;
         ASSERT_TRUE(
             db_->GetIntProperty("rocksdb.num-deletes-active-mem-table", &val));
@@ -3985,160 +3984,6 @@ TEST_P(DBIteratorTest, MemtableOpsScanFlushTriggerWithNext) {
     }
   }
 }
-
-TEST_P(DBIteratorTest, AverageMemtableOpsScanFlushTrigger) {
-  // Tests option memtable_avg_op_scan_flush_trigger with
-  // long tombstone sequences.
-  Random* r = Random::GetTLSInstance();
-
-  const int kAvgTrigger = 10;
-  const int kMaxTrigger = 500;
-  Options options;
-  options.create_if_missing = true;
-  options.memtable_op_scan_flush_trigger = kMaxTrigger;
-  options.memtable_avg_op_scan_flush_trigger = kAvgTrigger;
-  options.level_compaction_dynamic_level_bytes = true;
-  DestroyAndReopen(options);
-
-  const int kNumKeys = 1000;
-  // Base data that will be covered by a consecutive sequence of tombstones.
-  for (int i = 0; i < kNumKeys; ++i) {
-    ASSERT_OK(Put(Key(i), r->RandomString(50)));
-  }
-  ASSERT_OK(Flush());
-  ASSERT_OK(db_->CompactRange({}, nullptr, nullptr));
-  ASSERT_EQ(1, NumTableFilesAtLevel(6));
-
-  for (int i = 0; i < kNumKeys; ++i) {
-    // We issue slightly more deletions than kAvgTrigger between visible keys
-    // to ensure avg skipped entries exceed kAvgTrigger.
-    if (i % (kAvgTrigger + 2) != 0) {
-      ASSERT_OK(SingleDelete(Key(i)));
-    }
-  }
-
-  // Each operation, except the first Seek, is expected to see kAvgTrigger + 1
-  // tombstones (from the active memtable) before it finds the next visible key.
-  SetPerfLevel(PerfLevel::kEnableCount);
-  get_perf_context()->Reset();
-  std::unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
-  iter->Seek(Key(1));
-  ASSERT_EQ(get_perf_context()->next_on_memtable_count, kAvgTrigger + 1);
-  iter.reset();
-  // Should not flush since total entries skipped is below
-  // memtable_op_scan_flush_trigger
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  ASSERT_OK(db_->WaitForCompact({}));
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-
-  get_perf_context()->Reset();
-  iter.reset(db_->NewIterator(ReadOptions()));
-  int num_ops = 1;
-  uint64_t num_skipped = 0;
-  iter->Seek(Key(0));
-  ASSERT_EQ(iter->key(), Key(0));
-  uint64_t last_memtable_next_count =
-      get_perf_context()->next_on_memtable_count;
-  iter->Next();
-  num_ops++;
-  while (iter->Valid()) {
-    ASSERT_OK(iter->status());
-    uint64_t num_skipped_in_op =
-        get_perf_context()->next_on_memtable_count - last_memtable_next_count;
-    ASSERT_GE(num_skipped_in_op, kAvgTrigger + 1);
-    last_memtable_next_count = get_perf_context()->next_on_memtable_count;
-    num_skipped += num_skipped_in_op;
-    iter->Next();
-    num_ops++;
-  }
-  // During iterator destruction we mark memtable for flush
-  iter.reset();
-
-  // avg trigger
-  ASSERT_GE(num_skipped, kAvgTrigger * num_ops);
-  // memtable_op_scan_flush_trigger
-  ASSERT_GE(num_skipped, kMaxTrigger);
-  // Average hidden entries scanned from memtable per operation is more than
-  // kAvgTrigger and the total skipped is more than
-  // memtable_op_scan_flush_trigger, the current memtable should be marked for
-  // flush. The following two writes will trigger the flush.
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  // Before a write, we schedule memtables for flush if requested.
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  ASSERT_OK(db_->WaitForCompact({}));
-  ASSERT_EQ(1, NumTableFilesAtLevel(0));
-}
-
-TEST_P(DBIteratorTest, AverageMemtableOpsScanFlushTriggerByOverwrites) {
-  // Tests option memtable_avg_op_scan_flush_trigger with overwrites to keys.
-  Random* r = Random::GetTLSInstance();
-
-  const int kAvgTrigger = 25;
-  Options options;
-  options.create_if_missing = true;
-  options.memtable_op_scan_flush_trigger = 250;
-  options.memtable_avg_op_scan_flush_trigger = kAvgTrigger;
-  options.level_compaction_dynamic_level_bytes = true;
-  DestroyAndReopen(options);
-
-  const int kNumKeys = 100;
-  // Base data that will be covered by a consecutive sequence of tombstones.
-  for (int i = 0; i < kNumKeys; ++i) {
-    ASSERT_OK(Put(Key(i), r->RandomString(50)));
-  }
-  ASSERT_OK(Flush());
-  ASSERT_OK(db_->CompactRange({}, nullptr, nullptr));
-  ASSERT_EQ(1, NumTableFilesAtLevel(6));
-
-  // One visible key every 10 keys.
-  // Each non-visible user key has 3 non-visible entries in the active memtable.
-  for (int i = 0; i < kNumKeys; ++i) {
-    if (i % 10 != 0) {
-      ASSERT_OK(Put(Key(i), r->RandomString(50)));
-      ASSERT_OK(Put(Key(i), r->RandomString(50)));
-      ASSERT_OK(Delete(Key(i)));
-    }
-  }
-
-  SetPerfLevel(PerfLevel::kEnableCount);
-  get_perf_context()->Reset();
-  ReadOptions ro;
-  std::unique_ptr<Iterator> iter(db_->NewIterator(ro));
-  iter->Seek(Key(1));
-  ASSERT_GT(get_perf_context()->next_on_memtable_count, kAvgTrigger);
-  // Re-seek to trigger check for flush trigger
-  iter->Seek(Key(1));
-  // Should not flush since total entries skipped is below
-  // memtable_op_scan_flush_trigger
-  ASSERT_FALSE(static_cast<ColumnFamilyHandleImpl*>(db_->DefaultColumnFamily())
-                   ->cfd()
-                   ->mem()
-                   ->IsMarkedForFlush());
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  ASSERT_OK(db_->WaitForCompact({}));
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-  get_perf_context()->Reset();
-
-  int num_ops = 1;
-  iter->Seek(Key(1));
-  while (iter->Valid()) {
-    num_ops++;
-    iter->Next();
-  }
-  ASSERT_GT(get_perf_context()->next_on_memtable_count, num_ops * kAvgTrigger);
-
-  // Re-seek should check conditions for marking memtable for flush
-  iter->Seek(Key(80));
-
-  // Average hidden entries scanned from memtable per operation is 2.
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  // Before a write, we schedule memtables for flush if requested.
-  ASSERT_OK(Put(Key(0), "dummy write"));
-  ASSERT_OK(db_->WaitForCompact({}));
-  ASSERT_EQ(1, NumTableFilesAtLevel(0));
-}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_memtable_test.cc

@@ -424,96 +424,6 @@ TEST_F(DBMemTableTest, IntegrityChecks) {
     ASSERT_FALSE(iter->Valid());
   }
 }
-
-TEST_F(DBMemTableTest, VectorConcurrentInsert) {
-  Options options;
-  options.create_if_missing = true;
-  options.create_missing_column_families = true;
-  options.allow_concurrent_memtable_write = true;
-  options.memtable_factory.reset(new VectorRepFactory());
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"cf1"}, options);
-
-  // Multi-threaded writes
-  {
-    WriteOptions write_options;
-    std::vector<port::Thread> threads;
-    for (int i = 0; i < 10; ++i) {
-      threads.emplace_back([&, i]() {
-        int start = i * 100;
-        int end = start + 100;
-        WriteBatch batch;
-        for (int j = start; j < end; ++j) {
-          ASSERT_OK(
-              batch.Put(handles_[0], Key(j), "value" + std::to_string(j)));
-        }
-        ASSERT_OK(db_->Write(write_options, &batch));
-      });
-    }
-    for (auto& t : threads) {
-      t.join();
-    }
-
-    std::unique_ptr<Iterator> iter(
-        db_->NewIterator(ReadOptions(), handles_[0]));
-    iter->SeekToFirst();
-    for (int i = 0; i < 1000; ++i) {
-      ASSERT_TRUE(iter->Valid());
-      ASSERT_EQ(iter->key().ToString(), Key(i));
-      ASSERT_EQ(iter->value().ToString(), "value" + std::to_string(i));
-      iter->Next();
-    }
-    ASSERT_FALSE(iter->Valid());
-    ASSERT_OK(iter->status());
-  }
-
-  // Multi-threaded writes, multi CF
-  {
-    WriteOptions write_options;
-    std::vector<port::Thread> threads;
-    for (int i = 0; i < 10; ++i) {
-      threads.emplace_back([&, i]() {
-        int start = i * 100;
-        int end = start + 100;
-        WriteBatch batch;
-        for (int j = start; j < end; ++j) {
-          ASSERT_OK(batch.Put(handles_[0], Key(j), "CF0" + std::to_string(j)));
-          ASSERT_OK(batch.Put(handles_[1], Key(j), "CF1" + std::to_string(j)));
-        }
-        ASSERT_OK(db_->Write(write_options, &batch));
-      });
-    }
-
-    for (auto& t : threads) {
-      t.join();
-    }
-
-    std::unique_ptr<Iterator> iter0(
-        db_->NewIterator(ReadOptions(), handles_[0]));
-    std::unique_ptr<Iterator> iter1(
-        db_->NewIterator(ReadOptions(), handles_[1]));
-    iter0->SeekToFirst();
-    iter1->SeekToFirst();
-    for (int i = 0; i < 1000; ++i) {
-      ASSERT_TRUE(iter0->Valid());
-      ASSERT_EQ(iter0->key().ToString(), Key(i));
-      ASSERT_EQ(iter0->value().ToString(), "CF0" + std::to_string(i));
-      iter0->Next();
-
-      ASSERT_TRUE(iter1->Valid());
-      ASSERT_EQ(iter1->key().ToString(), Key(i));
-      ASSERT_EQ(iter1->value().ToString(), "CF1" + std::to_string(i));
-      iter1->Next();
-    }
-    ASSERT_FALSE(iter0->Valid());
-    ASSERT_OK(iter0->status());
-    ASSERT_FALSE(iter1->Valid());
-    ASSERT_OK(iter1->status());
-  }
-
-  ASSERT_OK(Flush(0));
-  ASSERT_OK(Flush(1));
-}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_properties_test.cc

@@ -377,8 +377,6 @@ TEST_F(DBPropertiesTest, AggregatedTableProperties) {
         NewBloomFilterPolicy(kBloomBitsPerKey, false));
     table_options.block_size = 1024;
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    // The checks assume kTableCount number of files
-    options.disable_auto_compactions = true;
 
     DestroyAndReopen(options);
 
@@ -569,7 +567,7 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
   options.target_file_size_base = 8192;
   options.max_bytes_for_level_base = 10000;
   options.max_bytes_for_level_multiplier = 2;
-  // The checks assume kTableCount number of files
+  // This ensures there no compaction happening when we call GetProperty().
   options.disable_auto_compactions = true;
   options.merge_operator.reset(new TestPutOperator());
 

db/db_test.cc

@@ -144,121 +144,6 @@ TEST_F(DBTest, MockEnvTest) {
   delete db;
 }
 
-TEST_F(DBTest, RequestIdPlumbingTest) {
-  // test that request_id is passed to the filesystem, from
-  // ReadOptions to IODebugContext
-  Options options = CurrentOptions();
-  options.env = env_;
-
-  // Create a mock environment to capture IODebugContext during reads
-  IODebugContext dbgCopy;
-  const std::string* captured_request_id_dbg;
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "RandomAccessFileReader::Read:IODebugContext", [&](void* arg) {
-        IODebugContext* dbg = static_cast<IODebugContext*>(arg);
-        if (dbg == nullptr) {
-          captured_request_id_dbg = nullptr;
-        } else {
-          captured_request_id_dbg = dbg->request_id;
-          // Test IODebugContext assignment operator
-          dbgCopy = *dbg;
-        }
-      });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("k1", "v1"));
-  ASSERT_OK(Flush());
-
-  // test request_id plumbing during a get
-  {
-    const std::string test_request_id = "test_request_id_123";
-    ReadOptions read_opts;
-    read_opts.request_id = &test_request_id;
-    std::string value;
-    ASSERT_OK(db_->Get(read_opts, "k1", &value));
-
-    // Verify the request_id was propagated to the file system
-    ASSERT_NE(captured_request_id_dbg, nullptr);
-    ASSERT_EQ(*captured_request_id_dbg, test_request_id);
-
-    ASSERT_NE(dbgCopy.request_id, nullptr);
-    ASSERT_NE(dbgCopy.request_id, captured_request_id_dbg);
-    ASSERT_EQ(*dbgCopy.request_id, test_request_id);
-  }
-
-  captured_request_id_dbg = nullptr;
-
-  // test request_id plumbing during iterator seek
-  ASSERT_OK(Put("k2", "v2"));
-  ASSERT_OK(Flush());
-  {
-    ReadOptions read_opts;
-    const std::string request_id = "test_request_id_456";
-    read_opts.request_id = &request_id;
-
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
-    iter->Seek("k2");
-    ASSERT_TRUE(iter->Valid());
-
-    // Verify the request_id was propagated to the file system
-    ASSERT_NE(captured_request_id_dbg, nullptr);
-    ASSERT_EQ(*captured_request_id_dbg, request_id);
-
-    ASSERT_NE(dbgCopy.request_id, nullptr);
-    ASSERT_NE(dbgCopy.request_id, captured_request_id_dbg);
-    ASSERT_EQ(*dbgCopy.request_id, request_id);
-
-    // Test IODebugContext copy constructor
-    IODebugContext dbgCopy2(dbgCopy);
-    ASSERT_NE(dbgCopy2.request_id, nullptr);
-    ASSERT_NE(dbgCopy2.request_id, captured_request_id_dbg);
-    ASSERT_NE(dbgCopy2.request_id, dbgCopy.request_id);
-    ASSERT_EQ(*dbgCopy2.request_id, request_id);
-  }
-
-  // test request_id plumbing during multiget
-  captured_request_id_dbg = nullptr;
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "RandomAccessFileReader::MultiRead:IODebugContext", [&](void* arg) {
-        IODebugContext* dbg = static_cast<IODebugContext*>(arg);
-        if (dbg == nullptr) {
-          captured_request_id_dbg = nullptr;
-        } else {
-          captured_request_id_dbg = dbg->request_id;
-        }
-      });
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("k3", "v3"));
-  ASSERT_OK(Put("k4", "v4"));
-  ASSERT_OK(Flush());
-
-  {
-    ReadOptions read_opts;
-    const std::string multiget_request_id = "test_request_id_789";
-    read_opts.request_id = &multiget_request_id;
-
-    std::vector<std::string> values;
-    std::vector<Slice> keys = {Slice("k3"), Slice("k4")};
-
-    values.resize(keys.size());
-
-    std::vector<ColumnFamilyHandle*> cfhs(keys.size(),
-                                          db_->DefaultColumnFamily());
-    db_->MultiGet(read_opts, cfhs, keys, &values);
-
-    ASSERT_NE(captured_request_id_dbg, nullptr);
-    ASSERT_EQ(*captured_request_id_dbg, multiget_request_id);
-  }
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 TEST_F(DBTest, MemEnvTest) {
   std::unique_ptr<Env> env{NewMemEnv(Env::Default())};
   Options options;
@@ -5578,6 +5463,7 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel2) {
   options.max_bytes_for_level_multiplier = 8;
   options.max_background_compactions = 1;
   options.num_levels = 5;
+  options.compaction_verify_record_count = false;
   std::shared_ptr<mock::MockTableFactory> mtf(new mock::MockTableFactory);
   options.table_factory = mtf;
 
@@ -6209,7 +6095,8 @@ TEST_F(DBTest, L0L1L2AndUpHitCounter) {
 }
 
 TEST_F(DBTest, EncodeDecompressedBlockSizeTest) {
-  bool& allow_unsupported_fv = TEST_AllowUnsupportedFormatVersion();
+  bool& allow_unsupported_fv =
+      BlockBasedTableFactory::AllowUnsupportedFormatVersion();
   SaveAndRestore guard(&allow_unsupported_fv);
   ASSERT_FALSE(allow_unsupported_fv);
 

db/db_test2.cc

@@ -10,6 +10,7 @@
 #include <atomic>
 #include <cstdlib>
 #include <functional>
+#include <iostream>
 #include <memory>
 
 #include "db/db_test_util.h"
@@ -29,7 +30,6 @@
 #include "test_util/testutil.h"
 #include "util/defer.h"
 #include "util/random.h"
-#include "util/simple_mixed_compressor.h"
 #include "utilities/fault_injection_env.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -1722,14 +1722,16 @@ TEST_P(CompressionFailuresTest, CompressionFailures) {
         });
   } else if (compression_failure_type_ == kTestDecompressionFail) {
     ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-        "DecompressBlockData:TamperWithReturnValue", [](void* arg) {
+        "UncompressBlockData:TamperWithReturnValue", [](void* arg) {
           Status* ret = static_cast<Status*>(arg);
           ASSERT_OK(*ret);
           *ret = Status::Corruption("kTestDecompressionFail");
         });
   } else if (compression_failure_type_ == kTestDecompressionCorruption) {
     ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-        "DecompressBlockData:TamperWithDecompressionOutput", [](void* arg) {
+        "UncompressBlockData:"
+        "TamperWithDecompressionOutput",
+        [](void* arg) {
           BlockContents* contents = static_cast<BlockContents*>(arg);
           // Ensure uncompressed data != original data
           const size_t len = contents->data.size() + 1;
@@ -1883,495 +1885,6 @@ TEST_F(DBTest2, CompressionOptions) {
   }
 }
 
-TEST_F(DBTest2, RoundRobinManager) {
-  if (ZSTD_Supported()) {
-    auto mgr = std::make_shared<RoundRobinManager>(
-        GetDefaultBuiltinCompressionManager());
-
-    std::vector<std::string> values;
-    for (bool use_wrapper : {true}) {
-      SCOPED_TRACE((use_wrapper ? "With " : "No ") + std::string("wrapper"));
-
-      Options options = CurrentOptions();
-      options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-      options.statistics->set_stats_level(StatsLevel::kExceptTimeForMutex);
-      BlockBasedTableOptions bbto;
-      bbto.enable_index_compression = false;
-      options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-      options.compression_manager = use_wrapper ? mgr : nullptr;
-      DestroyAndReopen(options);
-
-      Random rnd(301);
-      constexpr int kCount = 13;
-
-      // Highly compressible blocks, except 1 non-compressible. Half of the
-      // compressible are morked for bypass and 1 marked for rejection. Values
-      // are large enough to ensure just 1 k-v per block.
-      for (int i = 0; i < kCount; ++i) {
-        std::string value;
-        if (i == 6) {
-          // One non-compressible block
-          value = rnd.RandomBinaryString(20000);
-        } else {
-          test::CompressibleString(&rnd, 0.1, 20000, &value);
-        }
-        values.push_back(value);
-        ASSERT_OK(Put(Key(i), value));
-        ASSERT_EQ(Get(Key(i)), value);
-      }
-      ASSERT_OK(Flush());
-
-      // Ensure well-formed for reads
-      for (int i = 0; i < kCount; ++i) {
-        ASSERT_NE(Get(Key(i)), "NOT_FOUND");
-        ASSERT_EQ(Get(Key(i)), values[i]);
-      }
-      ASSERT_EQ(Get(Key(kCount)), "NOT_FOUND");
-    }
-  }
-}
-
-TEST_F(DBTest2, RandomMixedCompressionManager) {
-  if (ZSTD_Supported()) {
-    auto mgr = std::make_shared<RandomMixedCompressionManager>(
-        GetDefaultBuiltinCompressionManager());
-    std::vector<std::string> values;
-    for (bool use_wrapper : {true}) {
-      SCOPED_TRACE((use_wrapper ? "With " : "No ") + std::string("wrapper"));
-
-      Options options = CurrentOptions();
-      options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-      options.statistics->set_stats_level(StatsLevel::kExceptTimeForMutex);
-      BlockBasedTableOptions bbto;
-      bbto.enable_index_compression = false;
-      options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-      options.compression_manager = use_wrapper ? mgr : nullptr;
-      DestroyAndReopen(options);
-
-      Random rnd(301);
-      constexpr int kCount = 13;
-
-      // Highly compressible blocks, except 1 non-compressible. Half of the
-      // compressible are morked for bypass and 1 marked for rejection. Values
-      // are large enough to ensure just 1 k-v per block.
-      for (int i = 0; i < kCount; ++i) {
-        std::string value;
-        if (i == 6) {
-          // One non-compressible block
-          value = rnd.RandomBinaryString(20000);
-        } else {
-          test::CompressibleString(&rnd, 0.1, 20000, &value);
-        }
-        values.push_back(value);
-        ASSERT_OK(Put(Key(i), value));
-        ASSERT_EQ(Get(Key(i)), value);
-      }
-      ASSERT_OK(Flush());
-
-      // Ensure well-formed for reads
-      for (int i = 0; i < kCount; ++i) {
-        ASSERT_NE(Get(Key(i)), "NOT_FOUND");
-        ASSERT_EQ(Get(Key(i)), values[i]);
-      }
-      ASSERT_EQ(Get(Key(kCount)), "NOT_FOUND");
-    }
-  }
-}
-
-TEST_F(DBTest2, CompressionManagerWrapper) {
-  // Test that we can use a custom CompressionManager to wrap the built-in
-  // CompressionManager, thus adopting a custom *strategy* based on existing
-  // algorithms. This will "mark" some blocks (in their contents) as "do not
-  // compress", i.e. no attempt to compress, and some blocks as "reject
-  // compression", i.e. compression attempted but rejected because of ratio
-  // or otherwise. These cases are distinguishable for statistics that
-  // approximate "wasted effort".
-  static std::string kDoNotCompress = "do_not_compress";
-  static std::string kRejectCompression = "reject_compression";
-
-  struct MyCompressor : public CompressorWrapper {
-    using CompressorWrapper::CompressorWrapper;
-    const char* Name() const override { return "MyCompressor"; }
-
-    Status CompressBlock(Slice uncompressed_data,
-                         std::string* compressed_output,
-                         CompressionType* out_compression_type,
-                         ManagedWorkingArea* working_area) override {
-      auto begin = uncompressed_data.data();
-      auto end = uncompressed_data.data() + uncompressed_data.size();
-      if (std::search(begin, end, kDoNotCompress.begin(),
-                      kDoNotCompress.end()) != end) {
-        // Do not attempt compression
-        EXPECT_EQ(*out_compression_type, kNoCompression);
-        return Status::OK();
-      } else if (std::search(begin, end, kRejectCompression.begin(),
-                             kRejectCompression.end()) != end) {
-        // Simulate attempted & rejected compression
-        *compressed_output = "blah";
-        EXPECT_EQ(*out_compression_type, kNoCompression);
-        return Status::OK();
-      } else {
-        return wrapped_->CompressBlock(uncompressed_data, compressed_output,
-                                       out_compression_type, working_area);
-      }
-    }
-  };
-  struct MyManager : public CompressionManagerWrapper {
-    using CompressionManagerWrapper::CompressionManagerWrapper;
-    const char* Name() const override { return "MyManager"; }
-    std::unique_ptr<Compressor> GetCompressorForSST(
-        const FilterBuildingContext& context, const CompressionOptions& opts,
-        CompressionType preferred) override {
-      return std::make_unique<MyCompressor>(
-          wrapped_->GetCompressorForSST(context, opts, preferred));
-    }
-  };
-  auto mgr = std::make_shared<MyManager>(GetDefaultBuiltinCompressionManager());
-
-  for (CompressionType type : GetSupportedCompressions()) {
-    for (bool use_wrapper : {false, true}) {
-      if (type == kNoCompression) {
-        continue;
-      }
-      SCOPED_TRACE("Compression type: " + std::to_string(type) +
-                   (use_wrapper ? " with " : " no ") + "wrapper");
-
-      Options options = CurrentOptions();
-      options.compression = type;
-      options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-      options.statistics->set_stats_level(StatsLevel::kExceptTimeForMutex);
-      BlockBasedTableOptions bbto;
-      bbto.enable_index_compression = false;
-      options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-      options.compression_manager = use_wrapper ? mgr : nullptr;
-      DestroyAndReopen(options);
-
-      auto PopStat = [&](Tickers t) -> uint64_t {
-        return options.statistics->getAndResetTickerCount(t);
-      };
-
-      Random rnd(301);
-      constexpr int kCount = 13;
-
-      // Highly compressible blocks, except 1 non-compressible. Half of the
-      // compressible are morked for bypass and 1 marked for rejection. Values
-      // are large enough to ensure just 1 k-v per block.
-      for (int i = 0; i < kCount; ++i) {
-        std::string value;
-        if (i == 6) {
-          // One non-compressible block
-          value = rnd.RandomBinaryString(20000);
-        } else {
-          test::CompressibleString(&rnd, 0.1, 20000, &value);
-          if ((i % 2) == 0) {
-            // Half for bypass
-            value += kDoNotCompress;
-          } else if (i == 7) {
-            // One for rejection
-            value += kRejectCompression;
-          }
-        }
-        ASSERT_OK(Put(Key(i), value));
-      }
-      ASSERT_OK(Flush());
-
-      if (use_wrapper) {
-        EXPECT_EQ(kCount / 2 - 1, PopStat(NUMBER_BLOCK_COMPRESSED));
-        EXPECT_EQ(kCount / 2, PopStat(NUMBER_BLOCK_COMPRESSION_BYPASSED));
-        EXPECT_EQ(1 + 1, PopStat(NUMBER_BLOCK_COMPRESSION_REJECTED));
-      } else {
-        EXPECT_EQ(kCount - 1, PopStat(NUMBER_BLOCK_COMPRESSED));
-        EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSION_BYPASSED));
-        EXPECT_EQ(1, PopStat(NUMBER_BLOCK_COMPRESSION_REJECTED));
-      }
-
-      // Ensure well-formed for reads
-      for (int i = 0; i < kCount; ++i) {
-        ASSERT_NE(Get(Key(i)), "NOT_FOUND");
-      }
-      ASSERT_EQ(Get(Key(kCount)), "NOT_FOUND");
-    }
-  }
-}
-
-TEST_F(DBTest2, CompressionManagerCustomCompression) {
-  // Test that we can use a custom CompressionManager to implement custom
-  // compression algorithms, and that there are appropriate schema guard rails
-  // to ensure data is not processed by the wrong algorithm.
-  using Compressor8A = test::CompressorCustomAlg<kCustomCompression8A>;
-  using Compressor8B = test::CompressorCustomAlg<kCustomCompression8B>;
-  using Compressor8C = test::CompressorCustomAlg<kCustomCompression8C>;
-
-  if (!Compressor8A::Supported() || !LZ4_Supported()) {
-    fprintf(stderr,
-            "Prerequisite compression library not supported. Skipping\n");
-    return;
-  }
-
-  class MyManager : public CompressionManager {
-   public:
-    explicit MyManager(const char* compat_name) : compat_name_(compat_name) {}
-    const char* Name() const override { return name_.c_str(); }
-    const char* CompatibilityName() const override { return compat_name_; }
-
-    bool SupportsCompressionType(CompressionType type) const override {
-      return type == kCustomCompression8A || type == kCustomCompression8B ||
-             type == kCustomCompression8C ||
-             GetDefaultBuiltinCompressionManager()->SupportsCompressionType(
-                 type);
-    }
-
-    int used_compressor8A_count_ = 0;
-    int used_compressor8B_count_ = 0;
-    int used_compressor8C_count_ = 0;
-
-    std::unique_ptr<Compressor> GetCompressor(const CompressionOptions& opts,
-                                              CompressionType type) override {
-      switch (static_cast<unsigned char>(type)) {
-        case kCustomCompression8A:
-          used_compressor8A_count_++;
-          return std::make_unique<Compressor8A>();
-        case kCustomCompression8B:
-          used_compressor8B_count_++;
-          return std::make_unique<Compressor8B>();
-        case kCustomCompression8C:
-          used_compressor8C_count_++;
-          return std::make_unique<Compressor8C>();
-        // Also support built-in compression algorithms
-        default:
-          return GetDefaultBuiltinCompressionManager()->GetCompressor(opts,
-                                                                      type);
-      }
-    }
-
-    std::shared_ptr<Decompressor> GetDecompressor() override {
-      return std::make_shared<test::DecompressorCustomAlg>();
-    }
-
-    CompressionType last_specific_decompressor_type_ = kNoCompression;
-
-    std::shared_ptr<Decompressor> GetDecompressorForTypes(
-        const CompressionType* types_begin,
-        const CompressionType* types_end) override {
-      assert(types_end > types_begin);
-      last_specific_decompressor_type_ = *types_begin;
-      auto decomp = std::make_shared<test::DecompressorCustomAlg>();
-      decomp->SetAllowedTypes(types_begin, types_end);
-      return decomp;
-    }
-
-    void AddFriend(const std::shared_ptr<CompressionManager>& mgr) {
-      friends_[mgr->CompatibilityName()] = mgr;
-    }
-    std::shared_ptr<CompressionManager> FindCompatibleCompressionManager(
-        Slice compatibility_name) override {
-      std::shared_ptr<CompressionManager> rv =
-          CompressionManager::FindCompatibleCompressionManager(
-              compatibility_name);
-      if (!rv) {
-        auto it = friends_.find(compatibility_name.ToString());
-        if (it != friends_.end()) {
-          return it->second.lock();
-        }
-      }
-      return rv;
-    }
-
-   private:
-    const char* compat_name_;
-    std::string name_;
-    // weak_ptr to avoid cycles
-    std::map<std::string, std::weak_ptr<CompressionManager>> friends_;
-  };
-
-  for (bool use_dict : {false, true}) {
-    SCOPED_TRACE(use_dict ? "With dict" : "No dict");
-
-    // Although these compression managers are actually compatible, we must
-    // respect their distinct compatibility names and treat them as incompatible
-    // (or else risk processing data incorrectly)
-    // NOTE: these are not registered in ObjectRegistry to test what happens
-    // when the original CompressionManager might not be available.
-    auto mgr_foo = std::make_shared<MyManager>("Foo");
-    auto mgr_bar = std::make_shared<MyManager>("Bar");
-
-    // And this one claims to be fully compatible with the built-in compression
-    // manager when it's not fully compatible (for custom CompressionTypes)
-    auto mgr_claim_compatible = std::make_shared<MyManager>("BuiltinV2");
-
-    constexpr uint16_t kValueSize = 10000;
-
-    Options options = CurrentOptions();
-    options.level0_file_num_compaction_trigger = 20;
-    BlockBasedTableOptions bbto;
-    bbto.enable_index_compression = false;
-    bbto.format_version = 6;  // Before custom compression alg support
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    // Claims not to use custom compression (and doesn't unless setting a custom
-    // CompressionType)
-    options.compression_manager = mgr_claim_compatible;
-    // Use a built-in compression type with dictionary support
-    options.compression = kLZ4Compression;
-    options.compression_opts.max_dict_bytes = kValueSize / 2;
-    DestroyAndReopen(options);
-
-    Random rnd(404);
-    std::string value;
-    ASSERT_OK(
-        Put("a", test::CompressibleString(&rnd, 0.1, kValueSize, &value)));
-    ASSERT_OK(Flush());
-
-    // That data should be readable without access to the original compression
-    // manager, because it used the built-in CompatibilityName and a built-in
-    // CompressionType
-    options.compression_manager = nullptr;
-    Reopen(options);
-    ASSERT_EQ(Get("a"), value);
-
-    // Verify it was compressed
-    Range r = {"a", "a0"};
-    TablePropertiesCollection tables_properties;
-    ASSERT_OK(db_->GetPropertiesOfTablesInRange(db_->DefaultColumnFamily(), &r,
-                                                1, &tables_properties));
-    ASSERT_EQ(tables_properties.size(), 1U);
-    EXPECT_LT(tables_properties.begin()->second->data_size, kValueSize / 2);
-    EXPECT_EQ(tables_properties.begin()->second->compression_name, "LZ4");
-
-    // Disallow setting a custom CompressionType with a CompressionManager
-    // claiming to be built-in compatible.
-    options.compression_manager = mgr_claim_compatible;
-    options.compression = kCustomCompression8A;
-    ASSERT_EQ(TryReopen(options).code(), Status::Code::kInvalidArgument);
-
-    options.compression_manager = nullptr;
-    options.compression = kCustomCompressionFE;
-    ASSERT_EQ(TryReopen(options).code(), Status::Code::kInvalidArgument);
-    options.compression =
-        static_cast<CompressionType>(kLastBuiltinCompression + 1);
-    ASSERT_EQ(TryReopen(options).code(), Status::Code::kInvalidArgument);
-
-    // Custom compression schema (different CompatibilityName) not supported
-    // before format_version=7
-    options.compression_manager = mgr_foo;
-    options.compression = kLZ4Compression;
-    ASSERT_EQ(TryReopen(options).code(), Status::Code::kInvalidArgument);
-
-    // TODO: eliminate this hack when format_version=7 is published
-    SaveAndRestore guard(&TEST_AllowUnsupportedFormatVersion(), true);
-
-    // Set new format version
-    bbto.format_version = 7;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-
-    // Custom compression type not supported with built-in schema name, even
-    // with format_version=7
-    options.compression_manager = mgr_claim_compatible;
-    options.compression = kCustomCompression8B;
-    ASSERT_EQ(TryReopen(options).code(), Status::Code::kInvalidArgument);
-
-    // Using a built-in compression type with fv=7 but named custom schema
-    options.compression_manager = mgr_foo;
-    options.compression = kLZ4Compression;
-    Reopen(options);
-    ASSERT_OK(
-        Put("b", test::CompressibleString(&rnd, 0.1, kValueSize, &value)));
-    ASSERT_OK(Flush());
-    ASSERT_EQ(NumTableFilesAtLevel(0), 2);
-    ASSERT_EQ(Get("b"), value);
-
-    // Verify it was compressed with snappy
-    r = {"b", "b0"};
-    tables_properties.clear();
-    ASSERT_OK(db_->GetPropertiesOfTablesInRange(db_->DefaultColumnFamily(), &r,
-                                                1, &tables_properties));
-    ASSERT_EQ(tables_properties.size(), 1U);
-    EXPECT_LT(tables_properties.begin()->second->data_size, kValueSize / 2);
-    // Uses new format for "compression_name" property
-    EXPECT_EQ(tables_properties.begin()->second->compression_name, "Foo;04;");
-    EXPECT_EQ(mgr_foo->last_specific_decompressor_type_, kLZ4Compression);
-
-    // Custom compression type
-    options.compression = kCustomCompression8A;
-    Reopen(options);
-    ASSERT_OK(
-        Put("c", test::CompressibleString(&rnd, 0.1, kValueSize, &value)));
-    EXPECT_EQ(mgr_foo->used_compressor8A_count_, 0);
-    ASSERT_OK(Flush());
-    ASSERT_EQ(NumTableFilesAtLevel(0), 3);
-    ASSERT_EQ(Get("c"), value);
-    EXPECT_EQ(mgr_foo->used_compressor8A_count_, 1);
-
-    // Verify it was compressed with custom format
-    r = {"c", "c0"};
-    tables_properties.clear();
-    ASSERT_OK(db_->GetPropertiesOfTablesInRange(db_->DefaultColumnFamily(), &r,
-                                                1, &tables_properties));
-    ASSERT_EQ(tables_properties.size(), 1U);
-    EXPECT_LT(tables_properties.begin()->second->data_size, kValueSize / 2);
-    EXPECT_EQ(tables_properties.begin()->second->compression_name, "Foo;8A;");
-    EXPECT_EQ(mgr_foo->last_specific_decompressor_type_, kCustomCompression8A);
-
-    // Also dynamically changeable, because the compression manager will respect
-    // the current setting as reported under the legacy logic
-    ASSERT_OK(dbfull()->SetOptions({{"compression", "kLZ4Compression"}}));
-    ASSERT_OK(
-        Put("d", test::CompressibleString(&rnd, 0.1, kValueSize, &value)));
-    ASSERT_OK(Flush());
-    ASSERT_EQ(NumTableFilesAtLevel(0), 4);
-    ASSERT_EQ(Get("d"), value);
-
-    // Verify it was compressed with snappy
-    r = {"d", "d0"};
-    tables_properties.clear();
-    ASSERT_OK(db_->GetPropertiesOfTablesInRange(db_->DefaultColumnFamily(), &r,
-                                                1, &tables_properties));
-    ASSERT_EQ(tables_properties.size(), 1U);
-    EXPECT_LT(tables_properties.begin()->second->data_size, kValueSize / 2);
-    EXPECT_EQ(tables_properties.begin()->second->compression_name, "Foo;04;");
-    EXPECT_EQ(mgr_foo->last_specific_decompressor_type_, kLZ4Compression);
-
-    // Dynamically changeable to custom compressions also
-    ASSERT_OK(dbfull()->SetOptions({{"compression", "kCustomCompression8B"}}));
-    ASSERT_OK(
-        Put("e", test::CompressibleString(&rnd, 0.1, kValueSize, &value)));
-    ASSERT_OK(Flush());
-    ASSERT_EQ(NumTableFilesAtLevel(0), 5);
-    ASSERT_EQ(Get("e"), value);
-
-    // Verify it was compressed with custom format
-    r = {"e", "e0"};
-    tables_properties.clear();
-    ASSERT_OK(db_->GetPropertiesOfTablesInRange(db_->DefaultColumnFamily(), &r,
-                                                1, &tables_properties));
-    ASSERT_EQ(tables_properties.size(), 1U);
-    EXPECT_LT(tables_properties.begin()->second->data_size, kValueSize / 2);
-    EXPECT_EQ(tables_properties.begin()->second->compression_name, "Foo;8B;");
-    EXPECT_EQ(mgr_foo->last_specific_decompressor_type_, kCustomCompression8B);
-
-    // Fails to re-open with incompatible compression manager (can't find
-    // compression manager Foo because it's not registered nor known by Bar)
-    options.compression_manager = mgr_bar;
-    options.compression = kLZ4Compression;
-    ASSERT_EQ(TryReopen(options).code(), Status::Code::kNotSupported);
-
-    // But should re-open if we make Bar aware of the Foo compression manager
-    mgr_bar->AddFriend(mgr_foo);
-    Reopen(options);
-
-    // Can still read everything
-    ASSERT_EQ(Get("a").size(), kValueSize);
-    ASSERT_EQ(Get("b").size(), kValueSize);
-    ASSERT_EQ(Get("c").size(), kValueSize);
-    ASSERT_EQ(Get("d").size(), kValueSize);
-    ASSERT_EQ(Get("e").size(), kValueSize);
-
-    // TODO: mix of compatibility names in same DB
-    // TODO: test old version of a compression manager unable to read a
-    // compression type
-    // TODO: test getting compression manager from object registry
-  }
-}
-
 class CompactionStallTestListener : public EventListener {
  public:
   CompactionStallTestListener()
@@ -3497,7 +3010,7 @@ TEST_F(DBTest2, PausingManualCompaction1) {
       "TestCompactFiles:PausingManualCompaction:3", [&](void* arg) {
         auto paused = static_cast<std::atomic<int>*>(arg);
         // CompactFiles() relies on manual_compactions_paused to
-        // determine if this compaction should be paused or not
+        // determine if thie compaction should be paused or not
         ASSERT_EQ(0, paused->load(std::memory_order_acquire));
         paused->fetch_add(1, std::memory_order_release);
       });
@@ -3609,7 +3122,6 @@ TEST_F(DBTest2, PausingManualCompaction3) {
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
   dbfull()->DisableManualCompaction();
-
   ASSERT_TRUE(dbfull()
                   ->CompactRange(compact_options, nullptr, nullptr)
                   .IsManualCompactionPaused());
@@ -5909,103 +5421,6 @@ TEST_F(DBTest2, TestCompactFiles) {
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
-TEST_F(DBTest2, TestCancelCompactFiles) {
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  Options options;
-  options.env = env_;
-  options.num_levels = 2;
-  options.disable_auto_compactions = true;
-  Reopen(options);
-
-  auto* handle = db_->DefaultColumnFamily();
-  ASSERT_EQ(db_->NumberLevels(handle), 2);
-
-  ROCKSDB_NAMESPACE::SstFileWriter sst_file_writer{
-      ROCKSDB_NAMESPACE::EnvOptions(), options};
-
-  // ingest large SST files
-  std::vector<std::string> external_sst_file_names;
-  int key_counter = 0;
-  const int num_keys_per_file = 100000;
-  const int num_files = 10;
-  for (int i = 0; i < num_files; ++i) {
-    std::string file_name =
-        dbname_ + "/test_compact_files" + std::to_string(i) + ".sst_t";
-    external_sst_file_names.push_back(file_name);
-    ASSERT_OK(sst_file_writer.Open(file_name));
-    for (int j = 0; j < num_keys_per_file; ++j) {
-      ASSERT_OK(sst_file_writer.Put(Key(j + num_keys_per_file * key_counter),
-                                    std::to_string(j)));
-    }
-    key_counter += 1;
-    ASSERT_OK(sst_file_writer.Finish());
-  }
-
-  ASSERT_OK(db_->IngestExternalFile(handle, external_sst_file_names,
-                                    IngestExternalFileOptions()));
-  ASSERT_EQ(NumTableFilesAtLevel(1, 0), num_files);
-  std::vector<std::string> files;
-  GetSstFiles(env_, dbname_, &files);
-  ASSERT_EQ(files.size(), num_files);
-
-  // Test that 0 compactions happen - canceled is set to True initially
-  CompactionOptions compaction_options;
-  std::atomic<bool> canceled(true);
-  compaction_options.canceled = &canceled;
-
-  ASSERT_TRUE(db_->CompactFiles(compaction_options, handle, files, 1)
-                  .IsManualCompactionPaused());
-  ASSERT_EQ(NumTableFilesAtLevel(1, 0), num_files);
-
-  // Test cancellation before the check to cancel compaction happens -
-  // compaction should not occur
-  bool disable_compaction = false;
-  compaction_options.canceled->store(false, std::memory_order_release);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "TestCancelCompactFiles:SuccessfulCompaction", [&](void* arg) {
-        auto paused = static_cast<std::atomic<int>*>(arg);
-        if (disable_compaction) {
-          db_->DisableManualCompaction();
-          ASSERT_EQ(1, paused->load(std::memory_order_acquire));
-        } else {
-          compaction_options.canceled->store(true, std::memory_order_release);
-          ASSERT_EQ(0, paused->load(std::memory_order_acquire));
-        }
-      });
-
-  ASSERT_TRUE(db_->CompactFiles(compaction_options, handle, files, 1)
-                  .IsManualCompactionPaused());
-  ASSERT_EQ(NumTableFilesAtLevel(1, 0), num_files);
-
-  // DisableManualCompaction() should successfully cancel compaction
-  disable_compaction = true;
-  compaction_options.canceled->store(false, std::memory_order_release);
-  ASSERT_TRUE(db_->CompactFiles(compaction_options, handle, files, 1)
-                  .IsManualCompactionPaused());
-  ASSERT_EQ(NumTableFilesAtLevel(1, 0), num_files);
-  // unlike CompactRange, value of compaction_options.canceled will be
-  // unaffected by calling DisableManualCompactions()
-  ASSERT_FALSE(compaction_options.canceled->load());
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-  db_->EnableManualCompaction();
-
-  // Test cancelation after the check to cancel compaction - compaction should
-  // occur, leaving only 1 file
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactFilesImpl:0", [&](void* /*arg*/) {
-        compaction_options.canceled->store(true, std::memory_order_release);
-      });
-
-  compaction_options.canceled->store(false, std::memory_order_release);
-  ASSERT_OK(db_->CompactFiles(compaction_options, handle, files, 1));
-  ASSERT_EQ(NumTableFilesAtLevel(1, 0), 1);
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 TEST_F(DBTest2, MultiDBParallelOpenTest) {
   const int kNumDbs = 2;
   Options options = CurrentOptions();

db/db_universal_compaction_test.cc

@@ -1672,75 +1672,55 @@ TEST_P(DBTestUniversalCompaction, ConcurrentBottomPriLowPriCompactions) {
   }
   const int kNumFilesTrigger = 3;
   Env::Default()->SetBackgroundThreads(1, Env::Priority::BOTTOM);
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleUniversal;
+  options.max_background_compactions = 2;
+  options.num_levels = num_levels_;
+  options.write_buffer_size = 100 << 10;     // 100KB
+  options.target_file_size_base = 32 << 10;  // 32KB
+  options.level0_file_num_compaction_trigger = kNumFilesTrigger;
+  // Trigger compaction if size amplification exceeds 110%
+  options.compaction_options_universal.max_size_amplification_percent = 110;
+  DestroyAndReopen(options);
 
-  for (bool universal_reduce_file_locking : {true, false}) {
-    Options options = CurrentOptions();
-    options.compaction_style = kCompactionStyleUniversal;
-    options.compaction_options_universal.reduce_file_locking =
-        universal_reduce_file_locking;
-    options.max_background_compactions = 2;
-    options.num_levels = num_levels_;
-    options.write_buffer_size = 100 << 10;     // 100KB
-    options.target_file_size_base = 32 << 10;  // 32KB
-    options.level0_file_num_compaction_trigger = kNumFilesTrigger;
-    // Trigger compaction if size amplification exceeds 110%
-    options.compaction_options_universal.max_size_amplification_percent = 110;
-    DestroyAndReopen(options);
+  // Need to get a token to enable compaction parallelism up to
+  // `max_background_compactions` jobs.
+  auto pressure_token =
+      dbfull()->TEST_write_controler().GetCompactionPressureToken();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {// wait for the full compaction to be picked before adding files intended
+       // for the second one.
+       {"DBImpl::BackgroundCompaction:ForwardToBottomPriPool",
+        "DBTestUniversalCompaction:ConcurrentBottomPriLowPriCompactions:0"},
+       // the full (bottom-pri) compaction waits until a partial (low-pri)
+       // compaction has started to verify they can run in parallel.
+       {"DBImpl::BackgroundCompaction:NonTrivial",
+        "DBImpl::BGWorkBottomCompaction"}});
+  SyncPoint::GetInstance()->EnableProcessing();
 
-    // Need to get a token to enable compaction parallelism up to
-    // `max_background_compactions` jobs.
-    auto pressure_token =
-        dbfull()->TEST_write_controler().GetCompactionPressureToken();
-    if (universal_reduce_file_locking) {
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-          {// Wait for the full compaction to be repicked before adding files
-           // intended for the second compaction.
-           {"DBImpl::BackgroundCompaction():AfterPickCompactionBottomPri",
-            "DBTestUniversalCompaction:ConcurrentBottomPriLowPriCompactions:0"},
-           // Wait for the second compaction to run before running the full
-           // compaction to verify they can run in parallel
-           {"DBImpl::BackgroundCompaction:NonTrivial:BeforeRun",
-            "DBImpl::BackgroundCompaction:NonTrivial:BeforeRunBottomPri"}});
-    } else {
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-          {// Wait for the full compaction to be forwarded before adding files
-           // intended for the second compaction.
-           {"DBImpl::BackgroundCompaction:ForwardToBottomPriPool",
-            "DBTestUniversalCompaction:ConcurrentBottomPriLowPriCompactions:0"},
-           // Wait for the second compaction to run before running the full
-           // compaction to verify they can run in parallel
-           {"DBImpl::BackgroundCompaction:NonTrivial:BeforeRun",
-            "DBImpl::BackgroundCompaction:NonTrivial:BeforeRunBottomPri"}});
+  Random rnd(301);
+  for (int i = 0; i < 2; ++i) {
+    for (int num = 0; num < kNumFilesTrigger; num++) {
+      int key_idx = 0;
+      GenerateNewFile(&rnd, &key_idx, true /* no_wait */);
+      // use no_wait above because that one waits for flush and compaction. We
+      // don't want to wait for compaction because the full compaction is
+      // intentionally blocked while more files are flushed.
+      ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
     }
-
-    SyncPoint::GetInstance()->EnableProcessing();
-
-    Random rnd(301);
-    for (int i = 0; i < 2; ++i) {
-      for (int num = 0; num < kNumFilesTrigger; num++) {
-        int key_idx = 0;
-        GenerateNewFile(&rnd, &key_idx, true /* no_wait */);
-        // use no_wait above because that one waits for flush and compaction. We
-        // don't want to wait for compaction because the full compaction is
-        // intentionally blocked while more files are flushed.
-        ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
-      }
-      if (i == 0) {
-        TEST_SYNC_POINT(
-            "DBTestUniversalCompaction:ConcurrentBottomPriLowPriCompactions:0");
-      }
+    if (i == 0) {
+      TEST_SYNC_POINT(
+          "DBTestUniversalCompaction:ConcurrentBottomPriLowPriCompactions:0");
     }
-    ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-    // First compaction should output to bottom level. Second should output to
-    // L0 since older L0 files pending compaction prevent it from being placed
-    // lower.
-    ASSERT_EQ(NumSortedRuns(), 2);
-    ASSERT_GT(NumTableFilesAtLevel(0), 0);
-    ASSERT_GT(NumTableFilesAtLevel(num_levels_ - 1), 0);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
   }
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
+  // First compaction should output to bottom level. Second should output to L0
+  // since older L0 files pending compaction prevent it from being placed lower.
+  ASSERT_EQ(NumSortedRuns(), 2);
+  ASSERT_GT(NumTableFilesAtLevel(0), 0);
+  ASSERT_GT(NumTableFilesAtLevel(num_levels_ - 1), 0);
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
   Env::Default()->SetBackgroundThreads(0, Env::Priority::BOTTOM);
 }
 

db/event_helpers.cc

@@ -77,12 +77,7 @@ void EventHelpers::LogAndNotifyTableFileCreationFinished(
     TableFileCreationReason reason, const Status& s,
     const std::string& file_checksum,
     const std::string& file_checksum_func_name) {
-  if (!event_logger && listeners.empty()) {
-    s.PermitUncheckedError();
-    return;
-  }
-
-  if (event_logger) {
+  if (s.ok() && event_logger) {
     JSONWriter jwriter;
     AppendCurrentTime(&jwriter);
     jwriter << "cf_name" << cf_name << "job" << job_id << "event"
@@ -170,8 +165,6 @@ void EventHelpers::LogAndNotifyTableFileCreationFinished(
       jwriter << "oldest_blob_file_number" << oldest_blob_file_number;
     }
 
-    jwriter << "status" << s.ToString();
-
     jwriter.EndObject();
 
     event_logger->Log(jwriter);
@@ -202,22 +195,18 @@ void EventHelpers::LogAndNotifyTableFileDeletion(
     const std::string& file_path, const Status& status,
     const std::string& dbname,
     const std::vector<std::shared_ptr<EventListener>>& listeners) {
-  if (!event_logger && listeners.empty()) {
-    status.PermitUncheckedError();
-    return;
+  JSONWriter jwriter;
+  AppendCurrentTime(&jwriter);
+
+  jwriter << "job" << job_id << "event" << "table_file_deletion"
+          << "file_number" << file_number;
+  if (!status.ok()) {
+    jwriter << "status" << status.ToString();
   }
 
-  if (event_logger) {
-    JSONWriter jwriter;
-    AppendCurrentTime(&jwriter);
+  jwriter.EndObject();
 
-    jwriter << "job" << job_id << "event" << "table_file_deletion"
-            << "file_number" << file_number << "status" << status.ToString();
-
-    jwriter.EndObject();
-
-    event_logger->Log(jwriter);
-  }
+  event_logger->Log(jwriter);
 
   if (listeners.empty()) {
     return;
@@ -285,12 +274,7 @@ void EventHelpers::LogAndNotifyBlobFileCreationFinished(
     const std::string& file_checksum,
     const std::string& file_checksum_func_name, uint64_t total_blob_count,
     uint64_t total_blob_bytes) {
-  if (!event_logger && listeners.empty()) {
-    s.PermitUncheckedError();
-    return;
-  }
-
-  if (event_logger) {
+  if (s.ok() && event_logger) {
     JSONWriter jwriter;
     AppendCurrentTime(&jwriter);
     jwriter << "cf_name" << cf_name << "job" << job_id << "event"
@@ -321,17 +305,15 @@ void EventHelpers::LogAndNotifyBlobFileDeletion(
     const std::vector<std::shared_ptr<EventListener>>& listeners, int job_id,
     uint64_t file_number, const std::string& file_path, const Status& status,
     const std::string& dbname) {
-  if (!event_logger && listeners.empty()) {
-    status.PermitUncheckedError();
-    return;
-  }
-
   if (event_logger) {
     JSONWriter jwriter;
     AppendCurrentTime(&jwriter);
 
     jwriter << "job" << job_id << "event" << "blob_file_deletion"
-            << "file_number" << file_number << "status" << status.ToString();
+            << "file_number" << file_number;
+    if (!status.ok()) {
+      jwriter << "status" << status.ToString();
+    }
 
     jwriter.EndObject();
     event_logger->Log(jwriter);

db/external_sst_file_basic_test.cc

@@ -16,7 +16,6 @@
 #include "test_util/testharness.h"
 #include "test_util/testutil.h"
 #include "util/defer.h"
-#include "util/file_checksum_helper.h"
 #include "util/random.h"
 #include "utilities/fault_injection_env.h"
 
@@ -261,6 +260,55 @@ TEST_F(ExternalSSTFileBasicTest, Basic) {
   s = sst_file_writer.DeleteRange(Key(100), Key(200));
   ASSERT_NOK(s) << s.ToString();
 
+  DestroyAndReopen(options);
+
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::IngestExternalFile:AfterIncIngestFileCounter",
+       "ExternalSSTFileBasicTest.LiveWriteStart"},
+      {"WriteThread::JoinBatchGroup:Wait",
+       "DBImpl::IngestExternalFile:AfterIncIngestFileCounter:2"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  PerfContext* write_thread_perf_context;
+  std::thread write_thread([&] {
+    TEST_SYNC_POINT("ExternalSSTFileBasicTest.LiveWriteStart");
+    SetPerfLevel(kEnableWait);
+    write_thread_perf_context = get_perf_context();
+    write_thread_perf_context->Reset();
+    ASSERT_OK(db_->Put(WriteOptions(), "bar", "v2"));
+    ASSERT_GT(write_thread_perf_context->write_thread_wait_nanos, 0);
+    // Test sync points were used to make sure this live write enter write
+    // thread after the file ingestion entered write thread. So by the time this
+    // live write finishes, the latest seqno is 1 means file ingestion used
+    // seqno 0.
+    ASSERT_EQ(db_->GetLatestSequenceNumber(), 1U);
+  });
+
+  // Add file using file path
+  SetPerfLevel(kEnableTimeExceptForMutex);
+  PerfContext* perf_ctx = get_perf_context();
+  perf_ctx->Reset();
+  s = DeprecatedAddFile({file1});
+  ASSERT_GT(perf_context.file_ingestion_nanos, 0);
+  ASSERT_GT(perf_context.file_ingestion_blocking_live_writes_nanos, 0);
+  ASSERT_OK(s) << s.ToString();
+  for (int k = 0; k < 100; k++) {
+    ASSERT_EQ(Get(Key(k)), Key(k) + "_val");
+  }
+
+  write_thread.join();
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  // Re-ingest the file just to check the perf context not enabled at and below
+  // kEnableWait.
+  SetPerfLevel(kEnableWait);
+  perf_ctx->Reset();
+  IngestExternalFileOptions opts;
+  opts.allow_global_seqno = true;
+  opts.allow_blocking_flush = true;
+  ASSERT_OK(db_->IngestExternalFile({file1}, opts));
+  ASSERT_EQ(perf_context.file_ingestion_nanos, 0);
+  ASSERT_EQ(perf_context.file_ingestion_blocking_live_writes_nanos, 0);
   DestroyAndRecreateExternalSSTFilesDir();
 }
 
@@ -347,8 +395,7 @@ class ChecksumVerifyHelper {
 
   Status GetSingleFileChecksumAndFuncName(
       const std::string& file_path, std::string* file_checksum,
-      std::string* file_checksum_func_name,
-      const std::string& requested_func_name = {}) {
+      std::string* file_checksum_func_name) {
     Status s;
     EnvOptions soptions;
     std::unique_ptr<SequentialFile> file_reader;
@@ -366,8 +413,6 @@ class ChecksumVerifyHelper {
       return Status::OK();
     } else {
       FileChecksumGenContext gen_context;
-      gen_context.file_name = file_path;
-      gen_context.requested_checksum_func_name = requested_func_name;
       std::unique_ptr<FileChecksumGenerator> file_checksum_gen =
           file_checksum_gen_factory->CreateFileChecksumGenerator(gen_context);
       *file_checksum_func_name = file_checksum_gen->Name();
@@ -443,50 +488,10 @@ TEST_F(ExternalSSTFileBasicTest, BasicWithFileChecksumCrc32c) {
   DestroyAndRecreateExternalSSTFilesDir();
 }
 
-namespace {
-class VariousFileChecksumGenerator : public FileChecksumGenCrc32c {
- public:
-  explicit VariousFileChecksumGenerator(const std::string& name)
-      : FileChecksumGenCrc32c({}), name_(name) {}
-
-  const char* Name() const override { return name_.c_str(); }
-
-  std::string GetChecksum() const override {
-    return FileChecksumGenCrc32c::GetChecksum() + "_" + name_;
-  }
-
- private:
-  const std::string name_;
-};
-
-class VariousFileChecksumGenFactory : public FileChecksumGenFactory {
- public:
-  std::unique_ptr<FileChecksumGenerator> CreateFileChecksumGenerator(
-      const FileChecksumGenContext& context) override {
-    static RelaxedAtomic<int> counter{0};
-    if (Slice(context.requested_checksum_func_name).starts_with("Various")) {
-      return std::make_unique<VariousFileChecksumGenerator>(
-          context.requested_checksum_func_name);
-    } else if (context.requested_checksum_func_name.empty()) {
-      // Lacking a specific request, use a different function name for each
-      // result.
-      return std::make_unique<VariousFileChecksumGenerator>(
-          "Various" + std::to_string(counter.FetchAddRelaxed(1)));
-    } else {
-      return nullptr;
-    }
-  }
-
-  static const char* kClassName() { return "VariousFileChecksumGenFactory"; }
-  const char* Name() const override { return kClassName(); }
-};
-}  // namespace
-
 TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   Options old_options = CurrentOptions();
   Options options = CurrentOptions();
-  options.file_checksum_gen_factory =
-      std::make_shared<VariousFileChecksumGenFactory>();
+  options.file_checksum_gen_factory = GetFileChecksumGenCrc32cFactory();
   const ImmutableCFOptions ioptions(options);
   ChecksumVerifyHelper checksum_helper(options);
 
@@ -507,8 +512,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_EQ(file1_info.largest_key, Key(1099));
   std::string file_checksum1, file_checksum_func_name1;
   ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-      file1, &file_checksum1, &file_checksum_func_name1,
-      file1_info.file_checksum_func_name));
+      file1, &file_checksum1, &file_checksum_func_name1));
   ASSERT_EQ(file1_info.file_checksum, file_checksum1);
   ASSERT_EQ(file1_info.file_checksum_func_name, file_checksum_func_name1);
 
@@ -527,8 +531,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_EQ(file2_info.largest_key, Key(1299));
   std::string file_checksum2, file_checksum_func_name2;
   ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-      file2, &file_checksum2, &file_checksum_func_name2,
-      file2_info.file_checksum_func_name));
+      file2, &file_checksum2, &file_checksum_func_name2));
   ASSERT_EQ(file2_info.file_checksum, file_checksum2);
   ASSERT_EQ(file2_info.file_checksum_func_name, file_checksum_func_name2);
 
@@ -547,8 +550,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_EQ(file3_info.largest_key, Key(1499));
   std::string file_checksum3, file_checksum_func_name3;
   ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-      file3, &file_checksum3, &file_checksum_func_name3,
-      file3_info.file_checksum_func_name));
+      file3, &file_checksum3, &file_checksum_func_name3));
   ASSERT_EQ(file3_info.file_checksum, file_checksum3);
   ASSERT_EQ(file3_info.file_checksum_func_name, file_checksum_func_name3);
 
@@ -567,8 +569,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_EQ(file4_info.largest_key, Key(1799));
   std::string file_checksum4, file_checksum_func_name4;
   ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-      file4, &file_checksum4, &file_checksum_func_name4,
-      file4_info.file_checksum_func_name));
+      file4, &file_checksum4, &file_checksum_func_name4));
   ASSERT_EQ(file4_info.file_checksum, file_checksum4);
   ASSERT_EQ(file4_info.file_checksum_func_name, file_checksum_func_name4);
 
@@ -587,8 +588,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_EQ(file5_info.largest_key, Key(1999));
   std::string file_checksum5, file_checksum_func_name5;
   ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-      file5, &file_checksum5, &file_checksum_func_name5,
-      file5_info.file_checksum_func_name));
+      file5, &file_checksum5, &file_checksum_func_name5));
   ASSERT_EQ(file5_info.file_checksum, file_checksum5);
   ASSERT_EQ(file5_info.file_checksum_func_name, file_checksum_func_name5);
 
@@ -607,8 +607,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_EQ(file6_info.largest_key, Key(2199));
   std::string file_checksum6, file_checksum_func_name6;
   ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-      file6, &file_checksum6, &file_checksum_func_name6,
-      file6_info.file_checksum_func_name));
+      file6, &file_checksum6, &file_checksum_func_name6));
   ASSERT_EQ(file6_info.file_checksum, file_checksum6);
   ASSERT_EQ(file6_info.file_checksum_func_name, file_checksum_func_name6);
 
@@ -678,23 +677,18 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   }
   ASSERT_OK(env_->FileExists(file2));
 
-  // Enable verify_file_checksum option. No checksum information is provided,
-  // so it is generated when ingesting. The configured checksum factory will
-  // use a different function than before.
-  s = AddFileWithFileChecksum({file3}, {}, {}, true, false, false, false);
+  // Enable verify_file_checksum option
+  // No checksum information is provided, generate it when ingesting
+  std::vector<std::string> checksum, checksum_func;
+  s = AddFileWithFileChecksum({file3}, checksum, checksum_func, true, false,
+                              false, false);
   ASSERT_OK(s) << s.ToString();
   std::vector<LiveFileMetaData> live_files2;
   dbfull()->GetLiveFilesMetaData(&live_files2);
   for (const auto& f : live_files2) {
     if (set1.find(f.name) == set1.end()) {
-      // Recomputed checksum, different function
-      EXPECT_NE(f.file_checksum_func_name, file_checksum_func_name3);
-      std::string cur_checksum3, cur_checksum_func_name3;
-      ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-          dbname_ + f.name, &cur_checksum3, &cur_checksum_func_name3,
-          f.file_checksum_func_name));
-      EXPECT_EQ(f.file_checksum, cur_checksum3);
-      EXPECT_EQ(f.file_checksum_func_name, cur_checksum_func_name3);
+      ASSERT_EQ(f.file_checksum, file_checksum3);
+      ASSERT_EQ(f.file_checksum_func_name, file_checksum_func_name3);
       set1.insert(f.name);
     }
   }
@@ -708,9 +702,8 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_NOK(s) << s.ToString();
 
   // Does not enable verify_file_checksum options
-  // Checksum function name is recognized, so store the checksum being ingested.
-  std::string file_checksum_func_name4alt = "VariousABCD";
-  s = AddFileWithFileChecksum({file4}, {"asd"}, {file_checksum_func_name4alt},
+  // Checksum function name matches, store the checksum being ingested.
+  s = AddFileWithFileChecksum({file4}, {"asd"}, {file_checksum_func_name4},
                               false, false, false, false);
   ASSERT_OK(s) << s.ToString();
   std::vector<LiveFileMetaData> live_files3;
@@ -719,7 +712,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
     if (set1.find(f.name) == set1.end()) {
       ASSERT_FALSE(f.file_checksum == file_checksum4);
       ASSERT_EQ(f.file_checksum, "asd");
-      ASSERT_EQ(f.file_checksum_func_name, file_checksum_func_name4alt);
+      ASSERT_EQ(f.file_checksum_func_name, file_checksum_func_name4);
       set1.insert(f.name);
     }
   }
@@ -728,8 +721,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
 
   // enable verify_file_checksum options, DB enable checksum, and enable
   // write_global_seq. So the checksum stored is different from the one
-  // ingested due to the sequence number changes. The checksum function name
-  // may also change since the checksum is recomputed.
+  // ingested due to the sequence number changes.
   s = AddFileWithFileChecksum({file5}, {file_checksum5},
                               {file_checksum_func_name5}, true, false, false,
                               true);
@@ -738,14 +730,11 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   dbfull()->GetLiveFilesMetaData(&live_files4);
   for (const auto& f : live_files4) {
     if (set1.find(f.name) == set1.end()) {
-      // Recomputed checksum, different function
-      EXPECT_NE(f.file_checksum_func_name, file_checksum_func_name5);
       std::string cur_checksum5, cur_checksum_func_name5;
       ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-          dbname_ + f.name, &cur_checksum5, &cur_checksum_func_name5,
-          f.file_checksum_func_name));
-      EXPECT_EQ(f.file_checksum, cur_checksum5);
-      EXPECT_EQ(f.file_checksum_func_name, cur_checksum_func_name5);
+          dbname_ + f.name, &cur_checksum5, &cur_checksum_func_name5));
+      ASSERT_EQ(f.file_checksum, cur_checksum5);
+      ASSERT_EQ(f.file_checksum_func_name, file_checksum_func_name5);
       set1.insert(f.name);
     }
   }
@@ -753,22 +742,18 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithFileChecksum) {
   ASSERT_OK(env_->FileExists(file5));
 
   // Does not enable verify_file_checksum options and also the ingested file
-  // checksum information is empty. DB will generate and store file checksum
-  // in Manifest, which could be different from the previous invocation.
-  s = AddFileWithFileChecksum({file6}, {}, {}, false, false, false, false);
+  // checksum information is empty. DB will generate and store the checksum
+  // in Manifest.
+  std::vector<std::string> files_c6, files_name6;
+  s = AddFileWithFileChecksum({file6}, files_c6, files_name6, false, false,
+                              false, false);
   ASSERT_OK(s) << s.ToString();
   std::vector<LiveFileMetaData> live_files6;
   dbfull()->GetLiveFilesMetaData(&live_files6);
   for (const auto& f : live_files6) {
     if (set1.find(f.name) == set1.end()) {
-      // Recomputed checksum, different function
-      EXPECT_NE(f.file_checksum_func_name, file_checksum_func_name6);
-      std::string cur_checksum6, cur_checksum_func_name6;
-      ASSERT_OK(checksum_helper.GetSingleFileChecksumAndFuncName(
-          dbname_ + f.name, &cur_checksum6, &cur_checksum_func_name6,
-          f.file_checksum_func_name));
-      EXPECT_EQ(f.file_checksum, cur_checksum6);
-      EXPECT_EQ(f.file_checksum_func_name, cur_checksum_func_name6);
+      ASSERT_EQ(f.file_checksum, file_checksum6);
+      ASSERT_EQ(f.file_checksum_func_name, file_checksum_func_name6);
       set1.insert(f.name);
     }
   }

db/external_sst_file_ingestion_job.cc

@@ -260,6 +260,10 @@ Status ExternalSstFileIngestionJob::Prepare(
     } else {
       need_generate_file_checksum_ = true;
     }
+    FileChecksumGenContext gen_context;
+    std::unique_ptr<FileChecksumGenerator> file_checksum_gen =
+        db_options_.file_checksum_gen_factory->CreateFileChecksumGenerator(
+            gen_context);
     std::vector<std::string> generated_checksums;
     std::vector<std::string> generated_checksum_func_names;
     // Step 1: generate the checksum for ingested sst file.
@@ -267,9 +271,7 @@ Status ExternalSstFileIngestionJob::Prepare(
       for (size_t i = 0; i < files_to_ingest_.size(); i++) {
         std::string generated_checksum;
         std::string generated_checksum_func_name;
-        std::string requested_checksum_func_name =
-            i < files_checksum_func_names.size() ? files_checksum_func_names[i]
-                                                 : "";
+        std::string requested_checksum_func_name;
         // TODO: rate limit file reads for checksum calculation during file
         // ingestion.
         // TODO: plumb Env::IOActivity
@@ -312,50 +314,40 @@ Status ExternalSstFileIngestionJob::Prepare(
             if (files_checksum_func_names[i] !=
                 generated_checksum_func_names[i]) {
               status = Status::InvalidArgument(
-                  "DB file checksum gen factory " +
-                  std::string(db_options_.file_checksum_gen_factory->Name()) +
-                  " generated checksum function name " +
-                  generated_checksum_func_names[i] + " for file " +
-                  external_files_paths[i] +
-                  " which does not match requested/provided " +
-                  files_checksum_func_names[i]);
+                  "Checksum function name does not match with the checksum "
+                  "function name of this DB");
+              ROCKS_LOG_WARN(
+                  db_options_.info_log,
+                  "Sst file checksum verification of file: %s failed: %s",
+                  external_files_paths[i].c_str(), status.ToString().c_str());
               break;
             }
             if (files_checksums[i] != generated_checksums[i]) {
               status = Status::Corruption(
-                  "Checksum verification mismatch for ingestion file " +
-                  external_files_paths[i] + " using function " +
-                  generated_checksum_func_names[i] + ". Expected: " +
-                  Slice(files_checksums[i]).ToString(/*hex=*/true) +
-                  " Computed: " +
-                  Slice(generated_checksums[i]).ToString(/*hex=*/true));
+                  "Ingested checksum does not match with the generated "
+                  "checksum");
+              ROCKS_LOG_WARN(
+                  db_options_.info_log,
+                  "Sst file checksum verification of file: %s failed: %s",
+                  files_to_ingest_[i].internal_file_path.c_str(),
+                  status.ToString().c_str());
               break;
             }
           }
         } else {
-          // If verify_file_checksum is not enabled, we only verify the factory
-          // recognizes the checksum function name. If it does not match, fail
-          // the ingestion. If matches, we trust the ingested checksum
-          // information and store in the Manifest.
+          // If verify_file_checksum is not enabled, we only verify the
+          // checksum function name. If it does not match, fail the ingestion.
+          // If matches, we trust the ingested checksum information and store
+          // in the Manifest.
           for (size_t i = 0; i < files_to_ingest_.size(); i++) {
-            FileChecksumGenContext gen_context;
-            gen_context.file_name = files_to_ingest_[i].internal_file_path;
-            gen_context.requested_checksum_func_name =
-                files_checksum_func_names[i];
-            auto file_checksum_gen =
-                db_options_.file_checksum_gen_factory
-                    ->CreateFileChecksumGenerator(gen_context);
-
-            if (file_checksum_gen == nullptr ||
-                files_checksum_func_names[i] != file_checksum_gen->Name()) {
+            if (files_checksum_func_names[i] != file_checksum_gen->Name()) {
               status = Status::InvalidArgument(
-                  "Checksum function name " + files_checksum_func_names[i] +
-                  " for file " + external_files_paths[i] +
-                  " not recognized by DB checksum gen factory" +
-                  db_options_.file_checksum_gen_factory->Name() +
-                  (file_checksum_gen ? (" Returned function " +
-                                        std::string(file_checksum_gen->Name()))
-                                     : ""));
+                  "Checksum function name does not match with the checksum "
+                  "function name of this DB");
+              ROCKS_LOG_WARN(
+                  db_options_.info_log,
+                  "Sst file checksum verification of file: %s failed: %s",
+                  external_files_paths[i].c_str(), status.ToString().c_str());
               break;
             }
             files_to_ingest_[i].file_checksum = files_checksums[i];
@@ -370,11 +362,12 @@ Status ExternalSstFileIngestionJob::Prepare(
         status = Status::InvalidArgument(
             "The checksum information of ingested sst files are nonempty and "
             "the size of checksums or the size of the checksum function "
-            "names does not match with the number of ingested sst files");
-      }
-      if (!status.ok()) {
-        ROCKS_LOG_WARN(db_options_.info_log, "Ingestion failed: %s",
-                       status.ToString().c_str());
+            "names "
+            "does not match with the number of ingested sst files");
+        ROCKS_LOG_WARN(
+            db_options_.info_log,
+            "The ingested sst files checksum information is incomplete: %s",
+            status.ToString().c_str());
       }
     }
   }
@@ -841,8 +834,7 @@ Status ExternalSstFileIngestionJob::ResetTableReader(
       ro,
       TableReaderOptions(
           cfd_->ioptions(), sv->mutable_cf_options.prefix_extractor,
-          sv->mutable_cf_options.compression_manager.get(), env_options_,
-          cfd_->internal_comparator(),
+          env_options_, cfd_->internal_comparator(),
           sv->mutable_cf_options.block_protection_bytes_per_key,
           /*skip_filters*/ false, /*immortal*/ false,
           /*force_direct_prefetch*/ false, /*level*/ -1,

db/flush_job.cc

@@ -92,10 +92,12 @@ FlushJob::FlushJob(
     const MutableCFOptions& mutable_cf_options, uint64_t max_memtable_id,
     const FileOptions& file_options, VersionSet* versions,
     InstrumentedMutex* db_mutex, std::atomic<bool>* shutting_down,
-    JobContext* job_context, FlushReason flush_reason, LogBuffer* log_buffer,
-    FSDirectory* db_directory, FSDirectory* output_file_directory,
-    CompressionType output_compression, Statistics* stats,
-    EventLogger* event_logger, bool measure_io_stats,
+    std::vector<SequenceNumber> existing_snapshots,
+    SequenceNumber earliest_write_conflict_snapshot,
+    SnapshotChecker* snapshot_checker, JobContext* job_context,
+    FlushReason flush_reason, LogBuffer* log_buffer, FSDirectory* db_directory,
+    FSDirectory* output_file_directory, CompressionType output_compression,
+    Statistics* stats, EventLogger* event_logger, bool measure_io_stats,
     const bool sync_output_directory, const bool write_manifest,
     Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
     std::shared_ptr<const SeqnoToTimeMapping> seqno_to_time_mapping,
@@ -112,7 +114,12 @@ FlushJob::FlushJob(
       versions_(versions),
       db_mutex_(db_mutex),
       shutting_down_(shutting_down),
-      earliest_snapshot_(job_context->GetEarliestSnapshotSequence()),
+      existing_snapshots_(std::move(existing_snapshots)),
+      earliest_snapshot_(existing_snapshots_.empty()
+                             ? kMaxSequenceNumber
+                             : existing_snapshots_.at(0)),
+      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
+      snapshot_checker_(snapshot_checker),
       job_context_(job_context),
       flush_reason_(flush_reason),
       log_buffer_(log_buffer),
@@ -133,7 +140,6 @@ FlushJob::FlushJob(
       full_history_ts_low_(std::move(full_history_ts_low)),
       blob_callback_(blob_callback),
       seqno_to_time_mapping_(std::move(seqno_to_time_mapping)) {
-  assert(job_context->snapshot_context_initialized);
   // Update the thread status to indicate flush.
   ReportStartedFlush();
   TEST_SYNC_POINT("FlushJob::FlushJob()");
@@ -450,7 +456,7 @@ Status FlushJob::MemPurge() {
   const std::string* const full_history_ts_low = &(cfd_->GetFullHistoryTsLow());
   std::unique_ptr<CompactionRangeDelAggregator> range_del_agg(
       new CompactionRangeDelAggregator(&(cfd_->internal_comparator()),
-                                       job_context_->snapshot_seqs,
+                                       existing_snapshots_,
                                        full_history_ts_low));
   for (auto& rd_iter : range_del_iters) {
     range_del_agg->AddTombstones(std::move(rd_iter));
@@ -489,19 +495,19 @@ Status FlushJob::MemPurge() {
 
     Env* env = db_options_.env;
     assert(env);
-    MergeHelper merge(env, (cfd_->internal_comparator()).user_comparator(),
-                      (ioptions.merge_operator).get(), compaction_filter.get(),
-                      ioptions.logger,
-                      true /* internal key corruption is not ok */,
-                      job_context_->GetLatestSnapshotSequence(),
-                      job_context_->snapshot_checker);
+    MergeHelper merge(
+        env, (cfd_->internal_comparator()).user_comparator(),
+        (ioptions.merge_operator).get(), compaction_filter.get(),
+        ioptions.logger, true /* internal key corruption is not ok */,
+        existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
+        snapshot_checker_);
     assert(job_context_);
+    SequenceNumber job_snapshot_seq = job_context_->GetJobSnapshotSequence();
     const std::atomic<bool> kManualCompactionCanceledFalse{false};
     CompactionIterator c_iter(
         iter.get(), (cfd_->internal_comparator()).user_comparator(), &merge,
-        kMaxSequenceNumber, &job_context_->snapshot_seqs, earliest_snapshot_,
-        job_context_->earliest_write_conflict_snapshot,
-        job_context_->GetJobSnapshotSequence(), job_context_->snapshot_checker,
+        kMaxSequenceNumber, &existing_snapshots_, earliest_snapshot_,
+        earliest_write_conflict_snapshot_, job_snapshot_seq, snapshot_checker_,
         env, ShouldReportDetailedTime(env, ioptions.stats),
         true /* internal key corruption is not ok */, range_del_agg.get(),
         nullptr, ioptions.allow_data_in_errors,
@@ -755,7 +761,7 @@ bool FlushJob::MemPurgeDecider(double threshold) {
       // Pick the oldest existing snapshot that is more recent
       // than the sequence number of the sampled entry.
       min_seqno_snapshot = kMaxSequenceNumber;
-      for (SequenceNumber seq_num : job_context_->snapshot_seqs) {
+      for (SequenceNumber seq_num : existing_snapshots_) {
         if (seq_num > res.sequence && seq_num < min_seqno_snapshot) {
           min_seqno_snapshot = seq_num;
         }
@@ -862,9 +868,7 @@ Status FlushJob::WriteLevel0Table() {
       ts_sz > 0 && !cfd_->ioptions().persist_user_defined_timestamps;
 
   std::vector<BlobFileAddition> blob_file_additions;
-  // Note that here we treat flush as level 0 compaction in internal stats
-  InternalStats::CompactionStats flush_stats(CompactionReason::kFlush,
-                                             1 /* count**/);
+
   {
     auto write_hint = base_->storage_info()->CalculateSSTWriteHint(
         /*level=*/0, db_options_.calculate_sst_write_lifetime_hint_set);
@@ -883,7 +887,7 @@ Status FlushJob::WriteLevel0Table() {
     ro.total_order_seek = true;
     ro.io_activity = Env::IOActivity::kFlush;
     Arena arena;
-    uint64_t total_num_input_entries = 0, total_num_deletes = 0;
+    uint64_t total_num_entries = 0, total_num_deletes = 0;
     uint64_t total_data_size = 0;
     size_t total_memory_usage = 0;
     uint64_t total_num_range_deletes = 0;
@@ -918,7 +922,7 @@ Status FlushJob::WriteLevel0Table() {
       if (range_del_iter != nullptr) {
         range_del_iters.emplace_back(range_del_iter);
       }
-      total_num_input_entries += m->NumEntries();
+      total_num_entries += m->NumEntries();
       total_num_deletes += m->NumDeletion();
       total_data_size += m->GetDataSize();
       total_memory_usage += m->ApproximateMemoryUsage();
@@ -930,12 +934,11 @@ Status FlushJob::WriteLevel0Table() {
     //  "Write Buffer Full", should make update flush_reason_ accordingly.
     event_logger_->Log() << "job" << job_context_->job_id << "event"
                          << "flush_started" << "num_memtables" << mems_.size()
-                         << "total_num_input_entries" << total_num_input_entries
-                         << "num_deletes" << total_num_deletes
-                         << "total_data_size" << total_data_size
-                         << "memory_usage" << total_memory_usage
-                         << "num_range_deletes" << total_num_range_deletes
-                         << "flush_reason"
+                         << "num_entries" << total_num_entries << "num_deletes"
+                         << total_num_deletes << "total_data_size"
+                         << total_data_size << "memory_usage"
+                         << total_memory_usage << "num_range_deletes"
+                         << total_num_range_deletes << "flush_reason"
                          << GetFlushReasonString(flush_reason_);
 
     {
@@ -973,6 +976,7 @@ Status FlushJob::WriteLevel0Table() {
       meta_.oldest_ancester_time = oldest_ancester_time;
       meta_.file_creation_time = current_time;
 
+      uint64_t num_input_entries = 0;
       uint64_t memtable_payload_bytes = 0;
       uint64_t memtable_garbage_bytes = 0;
       IOStatus io_s;
@@ -994,49 +998,28 @@ Status FlushJob::WriteLevel0Table() {
           preclude_last_level_min_seqno_ == kMaxSequenceNumber
               ? preclude_last_level_min_seqno_
               : std::min(earliest_snapshot_, preclude_last_level_min_seqno_));
+      const SequenceNumber job_snapshot_seq =
+          job_context_->GetJobSnapshotSequence();
+
       s = BuildTable(
           dbname_, versions_, db_options_, tboptions, file_options_,
           cfd_->table_cache(), iter.get(), std::move(range_del_iters), &meta_,
-          &blob_file_additions, job_context_->snapshot_seqs, earliest_snapshot_,
-          job_context_->earliest_write_conflict_snapshot,
-          job_context_->GetJobSnapshotSequence(),
-          job_context_->snapshot_checker,
-          mutable_cf_options_.paranoid_file_checks, cfd_->internal_stats(),
-          &io_s, io_tracer_, BlobFileCreationReason::kFlush,
-          seqno_to_time_mapping_.get(), event_logger_, job_context_->job_id,
-          &table_properties_, write_hint, full_history_ts_low, blob_callback_,
-          base_, &memtable_payload_bytes, &memtable_garbage_bytes,
-          &flush_stats);
+          &blob_file_additions, existing_snapshots_, earliest_snapshot_,
+          earliest_write_conflict_snapshot_, job_snapshot_seq,
+          snapshot_checker_, mutable_cf_options_.paranoid_file_checks,
+          cfd_->internal_stats(), &io_s, io_tracer_,
+          BlobFileCreationReason::kFlush, seqno_to_time_mapping_.get(),
+          event_logger_, job_context_->job_id, &table_properties_, write_hint,
+          full_history_ts_low, blob_callback_, base_, &num_input_entries,
+          &memtable_payload_bytes, &memtable_garbage_bytes);
       TEST_SYNC_POINT_CALLBACK("FlushJob::WriteLevel0Table:s", &s);
       // TODO: Cleanup io_status in BuildTable and table builders
       assert(!s.ok() || io_s.ok());
       io_s.PermitUncheckedError();
-      if (s.ok() && total_num_input_entries != flush_stats.num_input_records) {
-        std::string msg = "Expected " +
-                          std::to_string(total_num_input_entries) +
+      if (num_input_entries != total_num_entries && s.ok()) {
+        std::string msg = "Expected " + std::to_string(total_num_entries) +
                           " entries in memtables, but read " +
-                          std::to_string(flush_stats.num_input_records);
-        ROCKS_LOG_WARN(db_options_.info_log, "[%s] [JOB %d] Level-0 flush %s",
-                       cfd_->GetName().c_str(), job_context_->job_id,
-                       msg.c_str());
-        if (db_options_.flush_verify_memtable_count) {
-          s = Status::Corruption(msg);
-        }
-      }
-
-      // Only verify on table with format collects table properties
-      if (s.ok() &&
-          (mutable_cf_options_.table_factory->IsInstanceOf(
-               TableFactory::kBlockBasedTableName()) ||
-           mutable_cf_options_.table_factory->IsInstanceOf(
-               TableFactory::kPlainTableName())) &&
-          flush_stats.num_output_records != table_properties_.num_entries) {
-        std::string msg =
-            "Number of keys in flush output SST files does not match "
-            "number of keys added to the table. Expected " +
-            std::to_string(flush_stats.num_output_records) + " but there are " +
-            std::to_string(table_properties_.num_entries) +
-            " in output SST files";
+                          std::to_string(num_input_entries);
         ROCKS_LOG_WARN(db_options_.info_log, "[%s] [JOB %d] Level-0 flush %s",
                        cfd_->GetName().c_str(), job_context_->job_id,
                        msg.c_str());
@@ -1102,10 +1085,12 @@ Status FlushJob::WriteLevel0Table() {
   // Piggyback FlushJobInfo on the first first flushed memtable.
   mems_[0]->SetFlushJobInfo(GetFlushJobInfo());
 
+  // Note that here we treat flush as level 0 compaction in internal stats
+  InternalStats::CompactionStats stats(CompactionReason::kFlush, 1);
   const uint64_t micros = clock_->NowMicros() - start_micros;
   const uint64_t cpu_micros = clock_->CPUMicros() - start_cpu_micros;
-  flush_stats.micros = micros;
-  flush_stats.cpu_micros = cpu_micros;
+  stats.micros = micros;
+  stats.cpu_micros = cpu_micros;
 
   ROCKS_LOG_INFO(db_options_.info_log,
                  "[%s] [JOB %d] Flush lasted %" PRIu64
@@ -1114,23 +1099,22 @@ Status FlushJob::WriteLevel0Table() {
                  cpu_micros);
 
   if (has_output) {
-    flush_stats.bytes_written = meta_.fd.GetFileSize();
-    flush_stats.num_output_files = 1;
+    stats.bytes_written = meta_.fd.GetFileSize();
+    stats.num_output_files = 1;
   }
 
   const auto& blobs = edit_->GetBlobFileAdditions();
   for (const auto& blob : blobs) {
-    flush_stats.bytes_written_blob += blob.GetTotalBlobBytes();
+    stats.bytes_written_blob += blob.GetTotalBlobBytes();
   }
 
-  flush_stats.num_output_files_blob = static_cast<int>(blobs.size());
+  stats.num_output_files_blob = static_cast<int>(blobs.size());
 
-  RecordTimeToHistogram(stats_, FLUSH_TIME, flush_stats.micros);
-  cfd_->internal_stats()->AddCompactionStats(0 /* level */, thread_pri_,
-                                             flush_stats);
+  RecordTimeToHistogram(stats_, FLUSH_TIME, stats.micros);
+  cfd_->internal_stats()->AddCompactionStats(0 /* level */, thread_pri_, stats);
   cfd_->internal_stats()->AddCFStats(
       InternalStats::BYTES_FLUSHED,
-      flush_stats.bytes_written + flush_stats.bytes_written_blob);
+      stats.bytes_written + stats.bytes_written_blob);
   RecordFlushIOStats();
 
   return s;

db/flush_job.h

@@ -63,9 +63,11 @@ class FlushJob {
            const MutableCFOptions& mutable_cf_options, uint64_t max_memtable_id,
            const FileOptions& file_options, VersionSet* versions,
            InstrumentedMutex* db_mutex, std::atomic<bool>* shutting_down,
-           JobContext* job_context, FlushReason flush_reason,
-           LogBuffer* log_buffer, FSDirectory* db_directory,
-           FSDirectory* output_file_directory,
+           std::vector<SequenceNumber> existing_snapshots,
+           SequenceNumber earliest_write_conflict_snapshot,
+           SnapshotChecker* snapshot_checker, JobContext* job_context,
+           FlushReason flush_reason, LogBuffer* log_buffer,
+           FSDirectory* db_directory, FSDirectory* output_file_directory,
            CompressionType output_compression, Statistics* stats,
            EventLogger* event_logger, bool measure_io_stats,
            const bool sync_output_directory, const bool write_manifest,
@@ -165,7 +167,10 @@ class FlushJob {
   VersionSet* versions_;
   InstrumentedMutex* db_mutex_;
   std::atomic<bool>* shutting_down_;
+  std::vector<SequenceNumber> existing_snapshots_;
   SequenceNumber earliest_snapshot_;
+  SequenceNumber earliest_write_conflict_snapshot_;
+  SnapshotChecker* snapshot_checker_;
   JobContext* job_context_;
   FlushReason flush_reason_;
   LogBuffer* log_buffer_;

db/flush_job_test.cc

@@ -186,16 +186,16 @@ TEST_F(FlushJobTest, Empty) {
   JobContext job_context(0);
   auto cfd = versions_->GetColumnFamilySet()->GetDefault();
   EventLogger event_logger(db_options_.info_log.get());
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
-  FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
-                     db_options_, cfd->GetLatestMutableCFOptions(),
-                     std::numeric_limits<uint64_t>::max() /* memtable_id */,
-                     env_options_, versions_.get(), &mutex_, &shutting_down_,
-                     &job_context, FlushReason::kTest, nullptr, nullptr,
-                     nullptr, kNoCompression, nullptr, &event_logger, false,
-                     true /* sync_output_directory */,
-                     true /* write_manifest */, Env::Priority::USER,
-                     nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      cfd->GetLatestMutableCFOptions(),
+      std::numeric_limits<uint64_t>::max() /* memtable_id */, env_options_,
+      versions_.get(), &mutex_, &shutting_down_, {}, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, nullptr, &event_logger, false,
+      true /* sync_output_directory */, true /* write_manifest */,
+      Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
   {
     InstrumentedMutexLock l(&mutex_);
     flush_job.PickMemTable();
@@ -272,16 +272,16 @@ TEST_F(FlushJobTest, NonEmpty) {
   }
 
   EventLogger event_logger(db_options_.info_log.get());
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
-  FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
-                     db_options_, cfd->GetLatestMutableCFOptions(),
-                     std::numeric_limits<uint64_t>::max() /* memtable_id */,
-                     env_options_, versions_.get(), &mutex_, &shutting_down_,
-                     &job_context, FlushReason::kTest, nullptr, nullptr,
-                     nullptr, kNoCompression, db_options_.statistics.get(),
-                     &event_logger, true, true /* sync_output_directory */,
-                     true /* write_manifest */, Env::Priority::USER,
-                     nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      cfd->GetLatestMutableCFOptions(),
+      std::numeric_limits<uint64_t>::max() /* memtable_id */, env_options_,
+      versions_.get(), &mutex_, &shutting_down_, {}, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
+      Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
 
   HistogramData hist;
   FileMetaData file_meta;
@@ -332,18 +332,18 @@ TEST_F(FlushJobTest, FlushMemTablesSingleColumnFamily) {
   }
 
   EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
 
   assert(memtable_ids.size() == num_mems);
   uint64_t smallest_memtable_id = memtable_ids.front();
   uint64_t flush_memtable_id = smallest_memtable_id + num_mems_to_flush - 1;
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
   FlushJob flush_job(
       dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
       cfd->GetLatestMutableCFOptions(), flush_memtable_id, env_options_,
-      versions_.get(), &mutex_, &shutting_down_, &job_context,
-      FlushReason::kTest, nullptr, nullptr, nullptr, kNoCompression,
-      db_options_.statistics.get(), &event_logger, true,
-      true /* sync_output_directory */, true /* write_manifest */,
+      versions_.get(), &mutex_, &shutting_down_, {}, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
       Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
   HistogramData hist;
   FileMetaData file_meta;
@@ -405,17 +405,18 @@ TEST_F(FlushJobTest, FlushMemtablesMultipleColumnFamilies) {
   }
 
   EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relevant
   std::vector<std::unique_ptr<FlushJob>> flush_jobs;
   k = 0;
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
   for (auto cfd : all_cfds) {
     std::vector<SequenceNumber> snapshot_seqs;
     flush_jobs.emplace_back(new FlushJob(
         dbname_, cfd, db_options_, cfd->GetLatestMutableCFOptions(),
         memtable_ids[k], env_options_, versions_.get(), &mutex_,
-        &shutting_down_, &job_context, FlushReason::kTest, nullptr, nullptr,
-        nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
-        true, false /* sync_output_directory */, false /* write_manifest */,
+        &shutting_down_, snapshot_seqs, kMaxSequenceNumber, snapshot_checker,
+        &job_context, FlushReason::kTest, nullptr, nullptr, nullptr,
+        kNoCompression, db_options_.statistics.get(), &event_logger, true,
+        false /* sync_output_directory */, false /* write_manifest */,
         Env::Priority::USER, nullptr /*IOTracer*/,
         empty_seqno_to_time_mapping_));
     k++;
@@ -531,17 +532,16 @@ TEST_F(FlushJobTest, Snapshots) {
   }
 
   EventLogger event_logger(db_options_.info_log.get());
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber,
-                                  std::move(snapshots));
-  FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
-                     db_options_, cfd->GetLatestMutableCFOptions(),
-                     std::numeric_limits<uint64_t>::max() /* memtable_id */,
-                     env_options_, versions_.get(), &mutex_, &shutting_down_,
-                     &job_context, FlushReason::kTest, nullptr, nullptr,
-                     nullptr, kNoCompression, db_options_.statistics.get(),
-                     &event_logger, true, true /* sync_output_directory */,
-                     true /* write_manifest */, Env::Priority::USER,
-                     nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      cfd->GetLatestMutableCFOptions(),
+      std::numeric_limits<uint64_t>::max() /* memtable_id */, env_options_,
+      versions_.get(), &mutex_, &shutting_down_, snapshots, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
+      Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
   mutex_.Lock();
   flush_job.PickMemTable();
   ASSERT_OK(flush_job.Run());
@@ -585,18 +585,18 @@ TEST_F(FlushJobTest, GetRateLimiterPriorityForWrite) {
   }
 
   EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
 
   assert(memtable_ids.size() == num_mems);
   uint64_t smallest_memtable_id = memtable_ids.front();
   uint64_t flush_memtable_id = smallest_memtable_id + num_mems_to_flush - 1;
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
   FlushJob flush_job(
       dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
       cfd->GetLatestMutableCFOptions(), flush_memtable_id, env_options_,
-      versions_.get(), &mutex_, &shutting_down_, &job_context,
-      FlushReason::kTest, nullptr, nullptr, nullptr, kNoCompression,
-      db_options_.statistics.get(), &event_logger, true,
-      true /* sync_output_directory */, true /* write_manifest */,
+      versions_.get(), &mutex_, &shutting_down_, {}, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
       Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_);
 
   // When the state from WriteController is normal.
@@ -658,16 +658,16 @@ TEST_F(FlushJobTest, ReplaceTimedPutWriteTimeWithPreferredSeqno) {
   }
 
   EventLogger event_logger(db_options_.info_log.get());
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
-  FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
-                     db_options_, cfd->GetLatestMutableCFOptions(),
-                     std::numeric_limits<uint64_t>::max() /* memtable_id */,
-                     env_options_, versions_.get(), &mutex_, &shutting_down_,
-                     &job_context, FlushReason::kTest, nullptr, nullptr,
-                     nullptr, kNoCompression, db_options_.statistics.get(),
-                     &event_logger, true, true /* sync_output_directory */,
-                     true /* write_manifest */, Env::Priority::USER,
-                     nullptr /*IOTracer*/, seqno_to_time_mapping);
+  SnapshotChecker* snapshot_checker = nullptr;  // not relevant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      cfd->GetLatestMutableCFOptions(),
+      std::numeric_limits<uint64_t>::max() /* memtable_id */, env_options_,
+      versions_.get(), &mutex_, &shutting_down_, {}, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
+      Env::Priority::USER, nullptr /*IOTracer*/, seqno_to_time_mapping);
 
   FileMetaData file_meta;
   mutex_.Lock();
@@ -761,19 +761,19 @@ TEST_P(FlushJobTimestampTest, AllKeysExpired) {
   }
 
   std::vector<SequenceNumber> snapshots;
+  constexpr SnapshotChecker* const snapshot_checker = nullptr;
   JobContext job_context(0);
   EventLogger event_logger(db_options_.info_log.get());
   std::string full_history_ts_low;
   PutFixed64(&full_history_ts_low, std::numeric_limits<uint64_t>::max());
   cfd->SetFullHistoryTsLow(full_history_ts_low);
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
   FlushJob flush_job(
       dbname_, cfd, db_options_, cfd->GetLatestMutableCFOptions(),
       std::numeric_limits<uint64_t>::max() /* memtable_id */, env_options_,
-      versions_.get(), &mutex_, &shutting_down_, &job_context,
-      FlushReason::kTest, nullptr, nullptr, nullptr, kNoCompression,
-      db_options_.statistics.get(), &event_logger, true,
-      true /* sync_output_directory */, true /* write_manifest */,
+      versions_.get(), &mutex_, &shutting_down_, snapshots, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
       Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_,
       /*db_id=*/"",
       /*db_session_id=*/"", full_history_ts_low);
@@ -823,8 +823,8 @@ TEST_P(FlushJobTimestampTest, NoKeyExpired) {
   }
 
   std::vector<SequenceNumber> snapshots;
+  SnapshotChecker* const snapshot_checker = nullptr;
   JobContext job_context(0);
-  job_context.InitSnapshotContext(nullptr, nullptr, kMaxSequenceNumber, {});
   EventLogger event_logger(db_options_.info_log.get());
   std::string full_history_ts_low;
   PutFixed64(&full_history_ts_low, 0);
@@ -832,10 +832,10 @@ TEST_P(FlushJobTimestampTest, NoKeyExpired) {
   FlushJob flush_job(
       dbname_, cfd, db_options_, cfd->GetLatestMutableCFOptions(),
       std::numeric_limits<uint64_t>::max() /* memtable_id */, env_options_,
-      versions_.get(), &mutex_, &shutting_down_, &job_context,
-      FlushReason::kTest, nullptr, nullptr, nullptr, kNoCompression,
-      db_options_.statistics.get(), &event_logger, true,
-      true /* sync_output_directory */, true /* write_manifest */,
+      versions_.get(), &mutex_, &shutting_down_, snapshots, kMaxSequenceNumber,
+      snapshot_checker, &job_context, FlushReason::kTest, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */,
       Env::Priority::USER, nullptr /*IOTracer*/, empty_seqno_to_time_mapping_,
       /*db_id=*/"",
       /*db_session_id=*/"", full_history_ts_low);

db/forward_iterator.h

@@ -42,7 +42,6 @@ using MinIterHeap =
     std::priority_queue<InternalIterator*, std::vector<InternalIterator*>,
                         MinIterComparator>;
 
-// TODO: name to TailingIterator
 /**
  * ForwardIterator is a special type of iterator that only supports Seek()
  * and Next(). It is expected to perform better than TailingIterator by

db/import_column_family_job.cc

@@ -324,8 +324,7 @@ Status ImportColumnFamilyJob::GetIngestedFileInfo(
   status = sv->mutable_cf_options.table_factory->NewTableReader(
       TableReaderOptions(
           cfd_->ioptions(), sv->mutable_cf_options.prefix_extractor,
-          sv->mutable_cf_options.compression_manager.get(), env_options_,
-          cfd_->internal_comparator(),
+          env_options_, cfd_->internal_comparator(),
           sv->mutable_cf_options.block_protection_bytes_per_key,
           /*skip_filters*/ false, /*immortal*/ false,
           /*force_direct_prefetch*/ false, /*level*/ -1,

db/internal_stats.cc

@@ -45,8 +45,6 @@ const std::map<LevelStatType, LevelStat> InternalStats::compaction_level_stats =
         {LevelStatType::RN_GB, LevelStat{"RnGB", "Rn(GB)"}},
         {LevelStatType::RNP1_GB, LevelStat{"Rnp1GB", "Rnp1(GB)"}},
         {LevelStatType::WRITE_GB, LevelStat{"WriteGB", "Write(GB)"}},
-        {LevelStatType::WRITE_PRE_COMP_GB,
-         LevelStat{"WPreCompGB", "WPreComp(GB)"}},
         {LevelStatType::W_NEW_GB, LevelStat{"WnewGB", "Wnew(GB)"}},
         {LevelStatType::MOVED_GB, LevelStat{"MovedGB", "Moved(GB)"}},
         {LevelStatType::WRITE_AMP, LevelStat{"WriteAmp", "W-Amp"}},
@@ -102,20 +100,19 @@ void PrintLevelStatsHeader(char* buf, size_t len, const std::string& cf_name,
   int line_size = snprintf(
       buf + written_size, len - written_size,
       "%s    %s   %s     %s %s  %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s "
-      "%s "
       "%s\n",
       // Note that we skip COMPACTED_FILES and merge it with Files column
       group_by.c_str(), hdr(LevelStatType::NUM_FILES),
       hdr(LevelStatType::SIZE_BYTES), hdr(LevelStatType::SCORE),
       hdr(LevelStatType::READ_GB), hdr(LevelStatType::RN_GB),
       hdr(LevelStatType::RNP1_GB), hdr(LevelStatType::WRITE_GB),
-      hdr(LevelStatType::WRITE_PRE_COMP_GB), hdr(LevelStatType::W_NEW_GB),
-      hdr(LevelStatType::MOVED_GB), hdr(LevelStatType::WRITE_AMP),
-      hdr(LevelStatType::READ_MBPS), hdr(LevelStatType::WRITE_MBPS),
-      hdr(LevelStatType::COMP_SEC), hdr(LevelStatType::COMP_CPU_SEC),
-      hdr(LevelStatType::COMP_COUNT), hdr(LevelStatType::AVG_SEC),
-      hdr(LevelStatType::KEY_IN), hdr(LevelStatType::KEY_DROP),
-      hdr(LevelStatType::R_BLOB_GB), hdr(LevelStatType::W_BLOB_GB));
+      hdr(LevelStatType::W_NEW_GB), hdr(LevelStatType::MOVED_GB),
+      hdr(LevelStatType::WRITE_AMP), hdr(LevelStatType::READ_MBPS),
+      hdr(LevelStatType::WRITE_MBPS), hdr(LevelStatType::COMP_SEC),
+      hdr(LevelStatType::COMP_CPU_SEC), hdr(LevelStatType::COMP_COUNT),
+      hdr(LevelStatType::AVG_SEC), hdr(LevelStatType::KEY_IN),
+      hdr(LevelStatType::KEY_DROP), hdr(LevelStatType::R_BLOB_GB),
+      hdr(LevelStatType::W_BLOB_GB));
 
   written_size += line_size;
   written_size = std::min(written_size, static_cast<int>(len));
@@ -143,8 +140,6 @@ void PrepareLevelStats(std::map<LevelStatType, double>* level_stats,
       stats.bytes_read_non_output_levels / kGB;
   (*level_stats)[LevelStatType::RNP1_GB] = stats.bytes_read_output_level / kGB;
   (*level_stats)[LevelStatType::WRITE_GB] = stats.bytes_written / kGB;
-  (*level_stats)[LevelStatType::WRITE_PRE_COMP_GB] =
-      stats.bytes_written_pre_comp / kGB;
   (*level_stats)[LevelStatType::W_NEW_GB] = bytes_new / kGB;
   (*level_stats)[LevelStatType::MOVED_GB] = stats.bytes_moved / kGB;
   (*level_stats)[LevelStatType::WRITE_AMP] = w_amp;
@@ -169,13 +164,12 @@ void PrintLevelStats(char* buf, size_t len, const std::string& name,
       buf, len,
       "%4s "      /*  Level */
       "%6d/%-3d " /*  Files */
-      "%10s "     /*  Size */
+      "%8s "      /*  Size */
       "%5.1f "    /*  Score */
       "%8.1f "    /*  Read(GB) */
       "%7.1f "    /*  Rn(GB) */
       "%8.1f "    /*  Rnp1(GB) */
       "%9.1f "    /*  Write(GB) */
-      "%9.1f "    /*  WPreComp(GB) */
       "%8.1f "    /*  Wnew(GB) */
       "%9.1f "    /*  Moved(GB) */
       "%5.1f "    /*  W-Amp */
@@ -199,7 +193,6 @@ void PrintLevelStats(char* buf, size_t len, const std::string& name,
       stat_value.at(LevelStatType::RN_GB),
       stat_value.at(LevelStatType::RNP1_GB),
       stat_value.at(LevelStatType::WRITE_GB),
-      stat_value.at(LevelStatType::WRITE_PRE_COMP_GB),
       stat_value.at(LevelStatType::W_NEW_GB),
       stat_value.at(LevelStatType::MOVED_GB),
       stat_value.at(LevelStatType::WRITE_AMP),

db/internal_stats.h

@@ -71,7 +71,6 @@ enum class LevelStatType {
   RN_GB,
   RNP1_GB,
   WRITE_GB,
-  WRITE_PRE_COMP_GB,
   W_NEW_GB,
   MOVED_GB,
   WRITE_AMP,
@@ -180,9 +179,6 @@ class InternalStats {
     // Total number of bytes written to table files during compaction
     uint64_t bytes_written;
 
-    // Total number of bytes written pre-compression during compaction
-    uint64_t bytes_written_pre_comp;
-
     // Total number of bytes written to blob files during compaction
     uint64_t bytes_written_blob;
 
@@ -235,7 +231,6 @@ class InternalStats {
           bytes_skipped_output_level(0),
           bytes_read_blob(0),
           bytes_written(0),
-          bytes_written_pre_comp(0),
           bytes_written_blob(0),
           bytes_moved(0),
           num_input_files_in_non_output_levels(0),
@@ -263,7 +258,6 @@ class InternalStats {
           bytes_skipped_output_level(0),
           bytes_read_blob(0),
           bytes_written(0),
-          bytes_written_pre_comp(0),
           bytes_written_blob(0),
           bytes_moved(0),
           num_input_files_in_non_output_levels(0),
@@ -297,7 +291,6 @@ class InternalStats {
           bytes_skipped_output_level(c.bytes_skipped_output_level),
           bytes_read_blob(c.bytes_read_blob),
           bytes_written(c.bytes_written),
-          bytes_written_pre_comp(c.bytes_written_pre_comp),
           bytes_written_blob(c.bytes_written_blob),
           bytes_moved(c.bytes_moved),
           num_input_files_in_non_output_levels(
@@ -328,7 +321,6 @@ class InternalStats {
       bytes_skipped_output_level = c.bytes_skipped_output_level;
       bytes_read_blob = c.bytes_read_blob;
       bytes_written = c.bytes_written;
-      bytes_written_pre_comp = c.bytes_written_pre_comp;
       bytes_written_blob = c.bytes_written_blob;
       bytes_moved = c.bytes_moved;
       num_input_files_in_non_output_levels =
@@ -361,7 +353,6 @@ class InternalStats {
       this->bytes_skipped_output_level = 0;
       this->bytes_read_blob = 0;
       this->bytes_written = 0;
-      this->bytes_written_pre_comp = 0;
       this->bytes_written_blob = 0;
       this->bytes_moved = 0;
       this->num_input_files_in_non_output_levels = 0;
@@ -390,7 +381,6 @@ class InternalStats {
       this->bytes_skipped_output_level += c.bytes_skipped_output_level;
       this->bytes_read_blob += c.bytes_read_blob;
       this->bytes_written += c.bytes_written;
-      this->bytes_written_pre_comp += c.bytes_written_pre_comp;
       this->bytes_written_blob += c.bytes_written_blob;
       this->bytes_moved += c.bytes_moved;
       this->num_input_files_in_non_output_levels +=
@@ -423,7 +413,6 @@ class InternalStats {
       this->bytes_skipped_output_level -= c.bytes_skipped_output_level;
       this->bytes_read_blob -= c.bytes_read_blob;
       this->bytes_written -= c.bytes_written;
-      this->bytes_written_pre_comp -= c.bytes_written_pre_comp;
       this->bytes_written_blob -= c.bytes_written_blob;
       this->bytes_moved -= c.bytes_moved;
       this->num_input_files_in_non_output_levels -=
@@ -708,10 +697,7 @@ class InternalStats {
   // a full cache, which would force a re-scan on the next GetStats.
   std::shared_ptr<CacheEntryStatsCollector<CacheEntryRoleStats>>
       cache_entry_stats_collector_;
-
-  // Per-column family and level compaction statistics, including flush and file
-  // ingestion. These are treated as compactions to L0 or the level where the
-  // file was ingested.
+  // Per-ColumnFamily/level compaction stats
   std::vector<CompactionStats> comp_stats_;
   std::vector<CompactionStats> comp_stats_by_pri_;
   CompactionStats per_key_placement_comp_stats_;

db/job_context.h

@@ -135,37 +135,6 @@ struct JobContext {
     return kMaxSequenceNumber;
   }
 
-  SequenceNumber GetLatestSnapshotSequence() const {
-    assert(snapshot_context_initialized);
-    if (snapshot_seqs.empty()) {
-      return 0;
-    }
-    return snapshot_seqs.back();
-  }
-
-  SequenceNumber GetEarliestSnapshotSequence() const {
-    assert(snapshot_context_initialized);
-    if (snapshot_seqs.empty()) {
-      return kMaxSequenceNumber;
-    }
-    return snapshot_seqs.front();
-  }
-
-  void InitSnapshotContext(SnapshotChecker* checker,
-                           std::unique_ptr<ManagedSnapshot> managed_snapshot,
-                           SequenceNumber earliest_write_conflict,
-                           std::vector<SequenceNumber>&& snapshots) {
-    if (snapshot_context_initialized) {
-      return;
-    }
-    snapshot_context_initialized = true;
-    snapshot_checker = checker;
-    assert(!job_snapshot);
-    job_snapshot = std::move(managed_snapshot);
-    earliest_write_conflict_snapshot = earliest_write_conflict;
-    snapshot_seqs = std::move(snapshots);
-  }
-
   // Structure to store information for candidate files to delete.
   struct CandidateFileInfo {
     std::string file_name;
@@ -177,6 +146,9 @@ struct JobContext {
     }
   };
 
+  // Unique job id
+  int job_id;
+
   // a list of all files that we'll consider deleting
   // (every once in a while this is filled up with all files
   // in the DB directory)
@@ -225,14 +197,14 @@ struct JobContext {
 
   // the current manifest_file_number, log_number and prev_log_number
   // that corresponds to the set of files in 'live'.
-  uint64_t manifest_file_number = 0;
-  uint64_t pending_manifest_file_number = 0;
+  uint64_t manifest_file_number;
+  uint64_t pending_manifest_file_number;
 
   // Used for remote compaction. To prevent OPTIONS files from getting
   // purged by PurgeObsoleteFiles() of the primary host
   uint64_t min_options_file_number;
-  uint64_t log_number = 0;
-  uint64_t prev_log_number = 0;
+  uint64_t log_number;
+  uint64_t prev_log_number;
 
   uint64_t min_pending_output = 0;
   uint64_t prev_wals_total_size = 0;
@@ -241,27 +213,17 @@ struct JobContext {
 
   // Snapshot taken before flush/compaction job.
   std::unique_ptr<ManagedSnapshot> job_snapshot;
-  SnapshotChecker* snapshot_checker = nullptr;
-  std::vector<SequenceNumber> snapshot_seqs;
-  // This is the earliest snapshot that could be used for write-conflict
-  // checking by a transaction.  For any user-key newer than this snapshot, we
-  // should make sure not to remove evidence that a write occurred.
-  SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber;
-
-  // Unique job id
-  int job_id;
-
-  bool snapshot_context_initialized = false;
 
   explicit JobContext(int _job_id, bool create_superversion = false) {
     job_id = _job_id;
+    manifest_file_number = 0;
+    pending_manifest_file_number = 0;
+    log_number = 0;
+    prev_log_number = 0;
     superversion_contexts.emplace_back(
         SuperVersionContext(create_superversion));
   }
 
-  // Delete the default constructor
-  JobContext() = delete;
-
   // For non-empty JobContext Clean() has to be called at least once before
   // before destruction (see asserts in ~JobContext()). Should be called with
   // unlocked DB mutex. Destructor doesn't call Clean() to avoid accidentally

db/listener_test.cc

@@ -537,47 +537,6 @@ TEST_F(EventListenerTest, DisableBGCompaction) {
   ASSERT_GE(listener->slowdown_count, kSlowdownTrigger * 9);
 }
 
-class TestNumInputFilesTotalInputBytesPouplatedInListener
-    : public EventListener {
- public:
-  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
-    std::lock_guard<std::mutex> lock(mutex_);
-    num_input_files = ci.stats.num_input_files;
-    total_num_of_bytes = ci.stats.total_input_bytes;
-  }
-  size_t num_input_files = 0;
-  size_t total_num_of_bytes = 0;
-  std::mutex mutex_;
-};
-
-TEST_F(EventListenerTest, NumInputFilesTotalBytesPopulated) {
-  Options options;
-  options.level_compaction_dynamic_level_bytes = false;
-  options.env = CurrentOptions().env;
-  options.create_if_missing = true;
-  options.memtable_factory.reset(test::NewSpecialSkipListFactory(
-      DBTestBase::kNumKeysByGenerateNewRandomFile));
-
-  TestNumInputFilesTotalInputBytesPouplatedInListener* listener =
-      new TestNumInputFilesTotalInputBytesPouplatedInListener();
-  options.listeners.emplace_back(listener);
-
-  options.level0_file_num_compaction_trigger = 4;
-  options.compaction_style = kCompactionStyleLevel;
-
-  DestroyAndReopen(options);
-  Random rnd(301);
-  ASSERT_EQ(listener->num_input_files, 0);
-  ASSERT_EQ(listener->total_num_of_bytes, 0);
-  // Write 4 files in L0
-  for (int i = 0; i < 4; i++) {
-    GenerateNewRandomFile(&rnd);
-  }
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  ASSERT_EQ(listener->num_input_files, 4);
-  ASSERT_NE(listener->total_num_of_bytes, 0);
-}
-
 class TestCompactionReasonListener : public EventListener {
  public:
   void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {

db/memtable.cc

@@ -196,11 +196,10 @@ bool MemTable::ShouldFlushNow() {
   // allocate one more block.
   const double kAllowOverAllocationRatio = 0.6;
 
-  // range deletion use skip list which allocates all memeory through `arena_`
-  assert(range_del_table_->ApproximateMemoryUsage() == 0);
   // If arena still have room for new block allocation, we can safely say it
   // shouldn't flush.
   auto allocated_memory = table_->ApproximateMemoryUsage() +
+                          range_del_table_->ApproximateMemoryUsage() +
                           arena_.MemoryAllocatedBytes();
 
   approximate_memory_usage_.store(allocated_memory, std::memory_order_relaxed);

db/memtable.h

@@ -688,7 +688,6 @@ class MemTable final : public ReadOnlyMemTable {
   // Update counters and flush status after inserting a whole write batch
   // Used in concurrent memtable inserts.
   void BatchPostProcess(const MemTablePostProcessInfo& update_counters) {
-    table_->BatchPostProcess();
     num_entries_.fetch_add(update_counters.num_entries,
                            std::memory_order_relaxed);
     data_size_.fetch_add(update_counters.data_size, std::memory_order_relaxed);
@@ -699,10 +698,6 @@ class MemTable final : public ReadOnlyMemTable {
     if (update_counters.num_range_deletes > 0) {
       num_range_deletes_.fetch_add(update_counters.num_range_deletes,
                                    std::memory_order_relaxed);
-      // noop for skip-list memtable
-      // Besides correctness test in stress test, memtable flush record count
-      // check will catch this if it were not noop.
-      // range_del_table_->BatchPostProcess();
     }
     UpdateFlushState();
   }

db/table_cache.cc

@@ -146,8 +146,7 @@ Status TableCache::GetTableReader(
     s = mutable_cf_options.table_factory->NewTableReader(
         ro,
         TableReaderOptions(
-            ioptions_, mutable_cf_options.prefix_extractor,
-            mutable_cf_options.compression_manager.get(), file_options,
+            ioptions_, mutable_cf_options.prefix_extractor, file_options,
             internal_comparator,
             mutable_cf_options.block_protection_bytes_per_key, skip_filters,
             immortal_tables_, false /* force_direct_prefetch */, level,

db/version_edit_handler.cc

@@ -1135,15 +1135,6 @@ void DumpManifestHandler::CheckIterationResult(const log::Reader& reader,
     // Print out DebugStrings. Can include non-terminating null characters.
     fwrite(cfd->current()->DebugString(hex_).data(), sizeof(char),
            cfd->current()->DebugString(hex_).size(), stdout);
-
-    fprintf(stdout,
-            "By default, manifest file dump prints LSM trees as if %d levels "
-            "were configured, "
-            "which is not necessarily true for the column family (CF) this "
-            "manifest is associated with. "
-            "Please consult other DB files, such as the OPTIONS file, to "
-            "confirm.\n",
-            cfd->ioptions().num_levels);
   }
   fprintf(stdout,
           "next_file_number %" PRIu64 " last_sequence %" PRIu64

db/write_batch.cc

@@ -551,6 +551,9 @@ Status WriteBatchInternal::Iterate(const WriteBatch* wb,
 
     if (LIKELY(!s.IsTryAgain())) {
       last_was_try_again = false;
+      tag = 0;
+      column_family = 0;  // default
+
       s = ReadRecordFromWriteBatch(&input, &tag, &column_family, &key, &value,
                                    &blob, &xid, &write_unix_time);
       if (!s.ok()) {
@@ -1894,6 +1897,7 @@ Status WriteBatch::VerifyChecksum() const {
     // ReadRecordFromWriteBatch
     key.clear();
     value.clear();
+    column_family = 0;
     s = ReadRecordFromWriteBatch(&input, &tag, &column_family, &key, &value,
                                  &blob, &xid, /*write_unix_time=*/nullptr);
     if (!s.ok()) {
@@ -3210,11 +3214,11 @@ Status WriteBatchInternal::InsertInto(
     ColumnFamilyMemTables* memtables, FlushScheduler* flush_scheduler,
     TrimHistoryScheduler* trim_history_scheduler,
     bool ignore_missing_column_families, uint64_t recovery_log_number, DB* db,
-    bool seq_per_batch, bool batch_per_txn) {
+    bool concurrent_memtable_writes, bool seq_per_batch, bool batch_per_txn) {
   MemTableInserter inserter(
       sequence, memtables, flush_scheduler, trim_history_scheduler,
       ignore_missing_column_families, recovery_log_number, db,
-      /*concurrent_memtable_writes=*/false, nullptr /* prot_info */,
+      concurrent_memtable_writes, nullptr /* prot_info */,
       nullptr /*has_valid_writes*/, seq_per_batch, batch_per_txn);
   for (auto w : write_group) {
     if (w->CallbackFailed()) {

db/write_batch_internal.h

@@ -185,19 +185,18 @@ class WriteBatchInternal {
   // If flush_scheduler is non-null, it will be invoked if the memtable
   // should be flushed.
   //
-  // This overload is for non-concurrent insertion only.
+  // Under concurrent use, the caller is responsible for making sure that
+  // the memtables object itself is thread-local.
   static Status InsertInto(
       WriteThread::WriteGroup& write_group, SequenceNumber sequence,
       ColumnFamilyMemTables* memtables, FlushScheduler* flush_scheduler,
       TrimHistoryScheduler* trim_history_scheduler,
       bool ignore_missing_column_families = false, uint64_t log_number = 0,
-      DB* db = nullptr, bool seq_per_batch = false, bool batch_per_txn = true);
+      DB* db = nullptr, bool concurrent_memtable_writes = false,
+      bool seq_per_batch = false, bool batch_per_txn = true);
 
   // Convenience form of InsertInto when you have only one batch
   // next_seq returns the seq after last sequence number used in MemTable insert
-  //
-  // Under concurrent use, the caller is responsible for making sure that
-  // the memtables object itself is thread-local.
   static Status InsertInto(
       const WriteBatch* batch, ColumnFamilyMemTables* memtables,
       FlushScheduler* flush_scheduler,

db_stress_tool/db_stress_common.h

@@ -398,7 +398,6 @@ DECLARE_bool(use_adaptive_mutex_lru);
 DECLARE_uint32(compress_format_version);
 DECLARE_uint64(manifest_preallocation_size);
 DECLARE_bool(enable_checksum_handoff);
-DECLARE_string(compression_manager);
 DECLARE_uint64(max_total_wal_size);
 DECLARE_double(high_pri_pool_ratio);
 DECLARE_double(low_pri_pool_ratio);
@@ -419,15 +418,12 @@ DECLARE_uint32(uncache_aggressiveness);
 DECLARE_int32(test_ingest_standalone_range_deletion_one_in);
 DECLARE_bool(allow_unprepared_value);
 DECLARE_string(file_temperature_age_thresholds);
-DECLARE_bool(allow_trivial_copy_when_change_temperature);
 DECLARE_uint32(commit_bypass_memtable_one_in);
 DECLARE_bool(track_and_verify_wals);
 DECLARE_bool(enable_remote_compaction);
 DECLARE_bool(auto_refresh_iterator_with_snapshot);
 DECLARE_uint32(memtable_op_scan_flush_trigger);
-DECLARE_uint32(memtable_avg_op_scan_flush_trigger);
 DECLARE_uint32(ingest_wbwi_one_in);
-DECLARE_bool(universal_reduce_file_locking);
 
 constexpr long KB = 1024;
 constexpr int kRandomValueMaxFactor = 3;

db_stress_tool/db_stress_compression_manager.h

@@ -1,65 +0,0 @@
-//  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).
-
-#pragma once
-
-#include "test_util/testutil.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class DbStressCustomCompressionManager : public CompressionManager {
- public:
-  const char* Name() const override {
-    return "DbStressCustomCompressionManager";
-  }
-  const char* CompatibilityName() const override { return "DbStressCustom1"; }
-
-  bool SupportsCompressionType(CompressionType type) const override {
-    return default_->SupportsCompressionType(type) ||
-           type == kCustomCompressionAA || type == kCustomCompressionAB ||
-           type == kCustomCompressionAC;
-  }
-
-  std::unique_ptr<Compressor> GetCompressor(const CompressionOptions& opts,
-                                            CompressionType type) override {
-    // db_stress never specifies a custom type, so we randomly use them anyway
-    // when this compression manager is used.
-    std::array<CompressionType, 4> choices = {
-        type, kCustomCompressionAA, kCustomCompressionAB, kCustomCompressionAC};
-    type = choices[Random::GetTLSInstance()->Uniform(4)];
-    switch (static_cast<unsigned char>(type)) {
-      case kCustomCompressionAA:
-        return std::make_unique<
-            test::CompressorCustomAlg<kCustomCompressionAA>>();
-      case kCustomCompressionAB:
-        return std::make_unique<
-            test::CompressorCustomAlg<kCustomCompressionAB>>();
-      case kCustomCompressionAC:
-        return std::make_unique<
-            test::CompressorCustomAlg<kCustomCompressionAC>>();
-      // Also support built-in compression algorithms
-      default:
-        return GetDefaultBuiltinCompressionManager()->GetCompressor(opts, type);
-    }
-  }
-
-  std::shared_ptr<Decompressor> GetDecompressor() override {
-    return std::make_shared<test::DecompressorCustomAlg>();
-  }
-
-  std::shared_ptr<Decompressor> GetDecompressorForTypes(
-      const CompressionType* types_begin,
-      const CompressionType* types_end) override {
-    auto decomp = std::make_shared<test::DecompressorCustomAlg>();
-    decomp->SetAllowedTypes(types_begin, types_end);
-    return decomp;
-  }
-
- protected:
-  std::shared_ptr<CompressionManager> default_ =
-      GetDefaultBuiltinCompressionManager();
-};
-
-}  // namespace ROCKSDB_NAMESPACE

db_stress_tool/db_stress_gflags.cc

@@ -467,9 +467,7 @@ DEFINE_uint64(blob_file_size,
 DEFINE_string(blob_compression_type, "none",
               "[Integrated BlobDB] The compression algorithm to use for large "
               "values stored in blob files.");
-DEFINE_string(compression_manager, "mixed",
-              "Ability to change compression manager specified in "
-              "simple_mixed_manager.h (mixed -> roundRobin)");
+
 DEFINE_bool(enable_blob_garbage_collection,
             ROCKSDB_NAMESPACE::AdvancedColumnFamilyOptions()
                 .enable_blob_garbage_collection,
@@ -538,9 +536,6 @@ DEFINE_string(file_temperature_age_thresholds, "",
               "See CompactionOptionsFIFO::file_temperature_age_thresholds. "
               "empty == unset");
 
-DEFINE_bool(allow_trivial_copy_when_change_temperature, true,
-            "Allow kChangeTemperature to do trivial copy");
-
 static const bool FLAGS_subcompactions_dummy __attribute__((__unused__)) =
     RegisterFlagValidator(&FLAGS_subcompactions, &ValidateUint32Range);
 
@@ -1484,15 +1479,4 @@ DEFINE_uint32(
     ROCKSDB_NAMESPACE::ColumnFamilyOptions().memtable_op_scan_flush_trigger,
     "Sets CF option memtable_op_scan_flush_trigger.");
 
-DEFINE_uint32(
-    memtable_avg_op_scan_flush_trigger,
-    ROCKSDB_NAMESPACE::ColumnFamilyOptions().memtable_avg_op_scan_flush_trigger,
-    "Sets CF option memtable_avg_op_scan_flush_trigger.");
-
-DEFINE_bool(
-    universal_reduce_file_locking,
-    ROCKSDB_NAMESPACE::ColumnFamilyOptions()
-        .compaction_options_universal.reduce_file_locking,
-    "Sets "
-    "ColumnFamilyOptions().compaciton_options_universal.reduce_file_locking.");
 #endif  // GFLAGS

db_stress_tool/db_stress_table_properties_collector.h

@@ -26,50 +26,25 @@ class DbStressTablePropertiesCollector : public TablePropertiesCollector {
   Status AddUserKey(const Slice& /* key */, const Slice& /* value */,
                     EntryType /*type*/, SequenceNumber /*seq*/,
                     uint64_t /*file_size*/) override {
-    ++keys_added;
-    ++all_calls;
     return Status::OK();
   }
 
-  void BlockAdd(uint64_t /* block_uncomp_bytes */,
-                uint64_t /* block_compressed_bytes_fast */,
-                uint64_t /* block_compressed_bytes_slow */) override {
-    ++blocks_added;
-    ++all_calls;
-  }
-
-  Status Finish(UserCollectedProperties* properties) override {
-    ++all_calls;
-    (*properties)["db_stress_collector_property"] =
-        std::to_string(keys_added) + ";" + std::to_string(blocks_added) + ";" +
-        std::to_string(all_calls);
+  Status Finish(UserCollectedProperties* /* properties */) override {
     return Status::OK();
   }
 
   UserCollectedProperties GetReadableProperties() const override {
-    UserCollectedProperties props;
-    const_cast<DbStressTablePropertiesCollector*>(this)->Finish(&props);
-    return props;
+    return UserCollectedProperties{};
   }
 
   const char* Name() const override {
     return "DbStressTablePropertiesCollector";
   }
 
-  bool NeedCompact() const override {
-    ++all_calls;
-    return need_compact_;
-  }
+  bool NeedCompact() const override { return need_compact_; }
 
  private:
   const bool need_compact_;
-  // These are tracked to detect race conditions that would arise from RocksDB
-  // invoking TablePropertiesCollector functions in an unsynchronized way, as
-  // TablePropertiesCollectors are allowed (encouraged) not to be thread safe.
-  size_t keys_added = 0;
-  size_t blocks_added = 0;
-  // Including race between BlockAdd and AddUserKey (etc.)
-  mutable size_t all_calls = 0;
 };
 
 // A `DbStressTablePropertiesCollectorFactory` creates

db_stress_tool/db_stress_test_base.cc

@@ -11,7 +11,6 @@
 #include <ios>
 #include <thread>
 
-#include "db_stress_tool/db_stress_compression_manager.h"
 #include "db_stress_tool/db_stress_listener.h"
 #include "rocksdb/io_status.h"
 #include "rocksdb/options.h"
@@ -35,7 +34,6 @@
 #include "rocksdb/utilities/write_batch_with_index.h"
 #include "test_util/testutil.h"
 #include "util/cast_util.h"
-#include "util/simple_mixed_compressor.h"
 #include "utilities/backup/backup_engine_impl.h"
 #include "utilities/fault_injection_fs.h"
 #include "utilities/fault_injection_secondary_cache.h"
@@ -429,11 +427,6 @@ bool StressTest::BuildOptionsTable() {
         std::vector<std::string>{
             "{{temperature=kWarm;age=30}:{temperature=kCold;age=300}}",
             "{{temperature=kCold;age=100}}", "{}"});
-    options_tbl.emplace(
-        "allow_trivial_copy_when_change_temperature",
-        std::vector<std::string>{
-            FLAGS_allow_trivial_copy_when_change_temperature ? "true"
-                                                             : "false"});
   }
 
   // NOTE: allow -1 to mean starting disabled but dynamically changing
@@ -845,21 +838,11 @@ Status StressTest::NewTxn(WriteOptions& write_opts, ThreadState* thread,
         FLAGS_use_only_the_last_commit_time_batch_for_recovery;
     txn_options.lock_timeout = 600000;  // 10 min
     txn_options.deadlock_detect = true;
-    if (FLAGS_commit_bypass_memtable_one_in > 0 &&
-        thread->rand.OneIn(FLAGS_commit_bypass_memtable_one_in)) {
+    if (FLAGS_commit_bypass_memtable_one_in > 0) {
       assert(FLAGS_txn_write_policy == 0);
       assert(FLAGS_user_timestamp_size == 0);
-      if (thread->rand.OneIn(2)) {
-        txn_options.commit_bypass_memtable = true;
-      }
-      if (thread->rand.OneIn(2)) {
-        txn_options.large_txn_commit_optimize_threshold = 1;
-      }
-      if (thread->rand.OneIn(2) ||
-          (!txn_options.commit_bypass_memtable &&
-           txn_options.large_txn_commit_optimize_threshold != 1)) {
-        txn_options.large_txn_commit_optimize_byte_threshold = 1;
-      }
+      txn_options.commit_bypass_memtable =
+          thread->rand.OneIn(FLAGS_commit_bypass_memtable_one_in);
       if (commit_bypass_memtable) {
         *commit_bypass_memtable = txn_options.commit_bypass_memtable;
       }
@@ -3413,44 +3396,7 @@ void StressTest::Open(SharedState* shared, bool reopen) {
     InitializeOptionsFromFlags(cache_, filter_policy_, options_);
   }
   InitializeOptionsGeneral(cache_, filter_policy_, sqfc_factory_, options_);
-  {
-    // We must register any compression managers with a custom
-    // CompatibilityName() so that if it was used in a past invocation but not
-    // the current invocation, we can still read the SST files requiring it.
-    static std::once_flag loaded;
-    std::call_once(loaded, [&]() {
-      TEST_AllowUnsupportedFormatVersion() = true;
-      auto& library = *ObjectLibrary::Default();
-      library.AddFactory<CompressionManager>(
-          DbStressCustomCompressionManager().CompatibilityName(),
-          [](const std::string& /*uri*/,
-             std::unique_ptr<CompressionManager>* guard,
-             std::string* /*errmsg*/) {
-            *guard = std::make_unique<DbStressCustomCompressionManager>();
-            return guard->get();
-          });
-    });
-  }
-  if (!strcasecmp(FLAGS_compression_manager.c_str(), "custom")) {
-    options_.compression_manager =
-        std::make_shared<DbStressCustomCompressionManager>();
-  } else if (!strcasecmp(FLAGS_compression_manager.c_str(), "mixed")) {
-    options_.compression_manager = std::make_shared<RoundRobinManager>(
-        GetDefaultBuiltinCompressionManager());
-  } else if (!strcasecmp(FLAGS_compression_manager.c_str(), "randommixed")) {
-    options_.compression_manager =
-        std::make_shared<RandomMixedCompressionManager>(
-            GetDefaultBuiltinCompressionManager());
-  } else if (!strcasecmp(FLAGS_compression_manager.c_str(), "autoskip")) {
-    options_.compression_manager =
-        CreateAutoSkipCompressionManager(GetDefaultBuiltinCompressionManager());
-  } else if (!strcasecmp(FLAGS_compression_manager.c_str(), "none")) {
-    // Nothing to do using default compression manager
-  } else {
-    fprintf(stderr, "Unknown compression manager: %s\n",
-            FLAGS_compression_manager.c_str());
-    exit(1);
-  }
+
   if (FLAGS_prefix_size == 0 && FLAGS_rep_factory == kHashSkipList) {
     fprintf(stderr,
             "prefeix_size cannot be zero if memtablerep == prefix_hash\n");
@@ -4270,14 +4216,10 @@ void InitializeOptionsFromFlags(
       StringToTemperature(FLAGS_default_temperature.c_str());
 
   if (!FLAGS_file_temperature_age_thresholds.empty()) {
-    const std::string allowTrivialCopyBoolStr =
-        FLAGS_allow_trivial_copy_when_change_temperature ? "true" : "false";
     Status s = GetColumnFamilyOptionsFromString(
         {}, options,
         "compaction_options_fifo={file_temperature_age_thresholds=" +
-            FLAGS_file_temperature_age_thresholds +
-            ";allow_trivial_copy_when_change_temperature=" +
-            allowTrivialCopyBoolStr + "}",
+            FLAGS_file_temperature_age_thresholds + "}",
         &options);
     if (!s.ok()) {
       fprintf(stderr, "While setting file_temperature_age_thresholds: %s\n",
@@ -4376,8 +4318,6 @@ void InitializeOptionsFromFlags(
   }
 
   options.memtable_op_scan_flush_trigger = FLAGS_memtable_op_scan_flush_trigger;
-  options.compaction_options_universal.reduce_file_locking =
-      FLAGS_universal_reduce_file_locking;
 }
 
 void InitializeOptionsGeneral(

db_stress_tool/no_batched_ops_stress.cc

@@ -233,13 +233,6 @@ class NonBatchedOpsStressTest : public StressTest {
           }
 
           Status s = secondary_db_->TryCatchUpWithPrimary();
-#ifndef NDEBUG
-          uint64_t manifest_num = static_cast_with_check<DBImpl>(secondary_db_)
-                                      ->TEST_Current_Manifest_FileNo();
-#else
-          uint64_t manifest_num = 0;
-#endif
-
           if (!s.ok()) {
             VerificationAbort(shared,
                               "Secondary failed to catch up to the primary");
@@ -274,11 +267,9 @@ class NonBatchedOpsStressTest : public StressTest {
             assert(!pre_read_expected_values.empty() &&
                    static_cast<size_t>(i - start) <
                        pre_read_expected_values.size());
-            VerifyValueRange(
-                static_cast<int>(cf), i, options, shared, from_db,
-                /* msg_prefix */ "Secondary get verification, manifest: " +
-                    std::to_string(manifest_num),
-                s, pre_read_expected_values[i - start]);
+            VerifyValueRange(static_cast<int>(cf), i, options, shared, from_db,
+                             /* msg_prefix */ "Secondary get verification", s,
+                             pre_read_expected_values[i - start]);
           }
         }
       } else if (method == VerificationMethod::kGetEntity) {

file/file_util.cc

@@ -22,10 +22,7 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
                   Temperature src_temp_hint,
                   std::unique_ptr<WritableFileWriter>& dest_writer,
                   uint64_t size, bool use_fsync,
-                  const std::shared_ptr<IOTracer>& io_tracer,
-                  uint64_t max_read_buffer_size,
-                  const std::optional<IOOptions>& readIOOptions,
-                  const std::optional<IOOptions>& writeIOOptions) {
+                  const std::shared_ptr<IOTracer>& io_tracer) {
   FileOptions soptions;
   IOStatus io_s;
   std::unique_ptr<SequentialFileReader> src_reader;
@@ -41,8 +38,7 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
 
     if (size == 0) {
       // default argument means copy everything
-      io_s =
-          fs->GetFileSize(source, readIOOptions.value_or(opts), &size, nullptr);
+      io_s = fs->GetFileSize(source, opts, &size, nullptr);
       if (!io_s.ok()) {
         return io_s;
       }
@@ -51,23 +47,14 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
         new SequentialFileReader(std::move(srcfile), source, io_tracer));
   }
 
-  const size_t read_buffer_size = std::max(
-      static_cast<size_t>(4096), static_cast<size_t>(max_read_buffer_size));
-  std::unique_ptr<char[]> buffer;
-  buffer.reset(new char[read_buffer_size]);
-
-  Env::IOPriority read_rate_limiter_priority = Env::IO_TOTAL;
-  if (readIOOptions.has_value()) {
-    read_rate_limiter_priority = readIOOptions.value().rate_limiter_priority;
-  }
+  char buffer[4096];
   Slice slice;
   while (size > 0) {
-    size_t bytes_to_read = std::min(static_cast<size_t>(read_buffer_size),
-                                    static_cast<size_t>(size));
+    size_t bytes_to_read = std::min(sizeof(buffer), static_cast<size_t>(size));
     // TODO: rate limit copy file
-    io_s = status_to_io_status(src_reader->Read(
-        bytes_to_read, &slice, buffer.get(),
-        read_rate_limiter_priority /* rate_limiter_priority */));
+    io_s = status_to_io_status(
+        src_reader->Read(bytes_to_read, &slice, buffer,
+                         Env::IO_TOTAL /* rate_limiter_priority */));
     if (!io_s.ok()) {
       return io_s;
     }
@@ -78,22 +65,19 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
           std::to_string(dest_writer->GetFileSize()));
     }
 
-    io_s = dest_writer->Append(writeIOOptions.value_or(opts), slice);
+    io_s = dest_writer->Append(opts, slice);
     if (!io_s.ok()) {
       return io_s;
     }
     size -= slice.size();
   }
-  return dest_writer->Sync(writeIOOptions.value_or(opts), use_fsync);
+  return dest_writer->Sync(opts, use_fsync);
 }
 
 IOStatus CopyFile(FileSystem* fs, const std::string& source,
                   Temperature src_temp_hint, const std::string& destination,
                   Temperature dst_temp, uint64_t size, bool use_fsync,
-                  const std::shared_ptr<IOTracer>& io_tracer,
-                  uint64_t max_read_buffer_size,
-                  const std::optional<IOOptions>& readIOOptions,
-                  const std::optional<IOOptions>& writeIOOptions) {
+                  const std::shared_ptr<IOTracer>& io_tracer) {
   FileOptions options;
   IOStatus io_s;
   std::unique_ptr<WritableFileWriter> dest_writer;
@@ -112,8 +96,7 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
   }
 
   return CopyFile(fs, source, src_temp_hint, dest_writer, size, use_fsync,
-                  io_tracer, max_read_buffer_size, readIOOptions,
-                  writeIOOptions);
+                  io_tracer);
 }
 
 // Utility function to create a file with the provided contents
@@ -247,16 +230,15 @@ IOStatus GenerateOneFileChecksum(
   Slice slice;
   uint64_t offset = 0;
   IOOptions opts;
-  IODebugContext dbg;
-  io_s = reader->PrepareIOOptions(read_options, opts, &dbg);
+  io_s = reader->PrepareIOOptions(read_options, opts);
   if (!io_s.ok()) {
     return io_s;
   }
   while (size > 0) {
     size_t bytes_to_read =
         static_cast<size_t>(std::min(uint64_t{readahead_size}, size));
-    io_s = reader->Read(opts, offset, bytes_to_read, &slice, buf.get(), nullptr,
-                        &dbg);
+    io_s =
+        reader->Read(opts, offset, bytes_to_read, &slice, buf.get(), nullptr);
     if (!io_s.ok()) {
       return IOStatus::Corruption("file read failed with error: " +
                                   io_s.ToString());

file/file_util.h

@@ -24,28 +24,18 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
                   Temperature src_temp_hint,
                   std::unique_ptr<WritableFileWriter>& dest_writer,
                   uint64_t size, bool use_fsync,
-                  const std::shared_ptr<IOTracer>& io_tracer,
-                  uint64_t max_read_buffer_size = 4096,
-                  const std::optional<IOOptions>& readIOOptions = {},
-                  const std::optional<IOOptions>& writeIOOptions = {});
+                  const std::shared_ptr<IOTracer>& io_tracer);
 IOStatus CopyFile(FileSystem* fs, const std::string& source,
                   Temperature src_temp_hint, const std::string& destination,
                   Temperature dst_temp, uint64_t size, bool use_fsync,
-                  const std::shared_ptr<IOTracer>& io_tracer,
-                  uint64_t max_read_buffer_size = 4096,
-                  const std::optional<IOOptions>& readIOOptions = {},
-                  const std::optional<IOOptions>& writeIOOptions = {});
+                  const std::shared_ptr<IOTracer>& io_tracer);
 inline IOStatus CopyFile(const std::shared_ptr<FileSystem>& fs,
                          const std::string& source, Temperature src_temp_hint,
                          const std::string& destination, Temperature dst_temp,
                          uint64_t size, bool use_fsync,
-                         const std::shared_ptr<IOTracer>& io_tracer,
-                         uint64_t max_read_buffer_size = 4096,
-                         const std::optional<IOOptions>& readIOOptions = {},
-                         const std::optional<IOOptions>& writeIOOptions = {}) {
+                         const std::shared_ptr<IOTracer>& io_tracer) {
   return CopyFile(fs.get(), source, src_temp_hint, destination, dst_temp, size,
-                  use_fsync, io_tracer, max_read_buffer_size, readIOOptions,
-                  writeIOOptions);
+                  use_fsync, io_tracer);
 }
 IOStatus CreateFile(FileSystem* fs, const std::string& destination,
                     const std::string& contents, bool use_fsync);
@@ -86,14 +76,7 @@ IOStatus GenerateOneFileChecksum(
     const ReadOptions& read_options, Statistics* stats, SystemClock* clock);
 
 inline IOStatus PrepareIOFromReadOptions(const ReadOptions& ro,
-                                         SystemClock* clock, IOOptions& opts,
-                                         IODebugContext* dbg = nullptr) {
-  if (ro.request_id != nullptr) {
-    if (dbg != nullptr && dbg->request_id == nullptr) {
-      dbg->SetRequestId(ro.request_id);
-    }
-  }
-
+                                         SystemClock* clock, IOOptions& opts) {
   if (ro.deadline.count()) {
     std::chrono::microseconds now =
         std::chrono::microseconds(clock->NowMicros());

file/random_access_file_reader.cc

@@ -106,14 +106,11 @@ IOStatus RandomAccessFileReader::Create(
 
 IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
                                       size_t n, Slice* result, char* scratch,
-                                      AlignedBuf* aligned_buf,
-                                      IODebugContext* dbg) const {
+                                      AlignedBuf* aligned_buf) const {
   (void)aligned_buf;
   const Env::IOPriority rate_limiter_priority = opts.rate_limiter_priority;
 
   TEST_SYNC_POINT_CALLBACK("RandomAccessFileReader::Read", nullptr);
-  TEST_SYNC_POINT_CALLBACK("RandomAccessFileReader::Read:IODebugContext",
-                           const_cast<void*>(static_cast<void*>(dbg)));
 
   // To be paranoid: modify scratch a little bit, so in case underlying
   // FileSystem doesn't fill the buffer but return success and `scratch` returns
@@ -178,7 +175,7 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
           // the opts.timeout before calling file_->Read
           assert(!opts.timeout.count() || allowed == read_size);
           io_s = file_->Read(aligned_offset + buf.CurrentSize(), allowed, opts,
-                             &tmp, buf.Destination(), dbg);
+                             &tmp, buf.Destination(), nullptr);
         }
         if (ShouldNotifyListeners()) {
           auto finish_ts = FileOperationInfo::FinishNow();
@@ -240,7 +237,7 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
           // the opts.timeout before calling file_->Read
           assert(!opts.timeout.count() || allowed == n);
           io_s = file_->Read(offset + pos, allowed, opts, &tmp_result,
-                             scratch + pos, dbg);
+                             scratch + pos, nullptr);
         }
         if (ShouldNotifyListeners()) {
           auto finish_ts = FileOperationInfo::FinishNow();
@@ -314,8 +311,7 @@ bool TryMerge(FSReadRequest* dest, const FSReadRequest& src) {
 IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
                                            FSReadRequest* read_reqs,
                                            size_t num_reqs,
-                                           AlignedBuf* aligned_buf,
-                                           IODebugContext* dbg) const {
+                                           AlignedBuf* aligned_buf) const {
   (void)aligned_buf;  // suppress warning of unused variable in LITE mode
   assert(num_reqs > 0);
 
@@ -424,10 +420,8 @@ IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
           remaining_bytes -= request_bytes;
         }
       }
-      TEST_SYNC_POINT_CALLBACK(
-          "RandomAccessFileReader::MultiRead:IODebugContext",
-          const_cast<void*>(static_cast<void*>(dbg)));
-      io_s = file_->MultiRead(fs_reqs, num_fs_reqs, opts, dbg);
+      io_s = file_->MultiRead(fs_reqs, num_fs_reqs, opts,
+                              /*IODebugContext*=*/nullptr);
       RecordInHistogram(stats_, MULTIGET_IO_BATCH_SIZE, num_fs_reqs);
     }
 
@@ -481,21 +475,18 @@ IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
 }
 
 IOStatus RandomAccessFileReader::PrepareIOOptions(const ReadOptions& ro,
-                                                  IOOptions& opts,
-                                                  IODebugContext* dbg) const {
+                                                  IOOptions& opts) const {
   if (clock_ != nullptr) {
-    return PrepareIOFromReadOptions(ro, clock_, opts, dbg);
+    return PrepareIOFromReadOptions(ro, clock_, opts);
   } else {
-    return PrepareIOFromReadOptions(ro, SystemClock::Default().get(), opts,
-                                    dbg);
+    return PrepareIOFromReadOptions(ro, SystemClock::Default().get(), opts);
   }
 }
 
 IOStatus RandomAccessFileReader::ReadAsync(
     FSReadRequest& req, const IOOptions& opts,
     std::function<void(FSReadRequest&, void*)> cb, void* cb_arg,
-    void** io_handle, IOHandleDeleter* del_fn, AlignedBuf* aligned_buf,
-    IODebugContext* dbg) {
+    void** io_handle, IOHandleDeleter* del_fn, AlignedBuf* aligned_buf) {
   IOStatus s;
   // Create a callback and populate info.
   auto read_async_callback =
@@ -541,14 +532,14 @@ IOStatus RandomAccessFileReader::ReadAsync(
                  (stats_ != nullptr) ? &elapsed : nullptr, true /*overwrite*/,
                  true /*delay_enabled*/);
     s = file_->ReadAsync(aligned_req, opts, read_async_callback,
-                         read_async_info, io_handle, del_fn, dbg);
+                         read_async_info, io_handle, del_fn, nullptr /*dbg*/);
   } else {
     StopWatch sw(clock_, stats_, hist_type_,
                  GetFileReadHistograms(stats_, opts.io_activity),
                  (stats_ != nullptr) ? &elapsed : nullptr, true /*overwrite*/,
                  true /*delay_enabled*/);
     s = file_->ReadAsync(req, opts, read_async_callback, read_async_info,
-                         io_handle, del_fn, dbg);
+                         io_handle, del_fn, nullptr /*dbg*/);
   }
   RecordTick(stats_, READ_ASYNC_MICROS, elapsed);
 

file/random_access_file_reader.h

@@ -164,8 +164,7 @@ class RandomAccessFileReader {
   // the internally allocated buffer on return, and the result refers to a
   // region in aligned_buf.
   IOStatus Read(const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
-                char* scratch, AlignedBuf* aligned_buf,
-                IODebugContext* dbg = nullptr) const;
+                char* scratch, AlignedBuf* aligned_buf) const;
 
   // REQUIRES:
   // num_reqs > 0, reqs do not overlap, and offsets in reqs are increasing.
@@ -173,12 +172,10 @@ class RandomAccessFileReader {
   // In direct IO mode, aligned_buf stores the aligned buffer allocated inside
   // MultiRead, the result Slices in reqs refer to aligned_buf.
   IOStatus MultiRead(const IOOptions& opts, FSReadRequest* reqs,
-                     size_t num_reqs, AlignedBuf* aligned_buf,
-                     IODebugContext* dbg = nullptr) const;
+                     size_t num_reqs, AlignedBuf* aligned_buf) const;
 
-  IOStatus Prefetch(const IOOptions& opts, uint64_t offset, size_t n,
-                    IODebugContext* dbg = nullptr) const {
-    return file_->Prefetch(offset, n, opts, dbg);
+  IOStatus Prefetch(const IOOptions& opts, uint64_t offset, size_t n) const {
+    return file_->Prefetch(offset, n, opts, nullptr);
   }
 
   FSRandomAccessFile* file() { return file_.get(); }
@@ -187,13 +184,12 @@ class RandomAccessFileReader {
 
   bool use_direct_io() const { return file_->use_direct_io(); }
 
-  IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts,
-                            IODebugContext* dbg = nullptr) const;
+  IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts) const;
 
   IOStatus ReadAsync(FSReadRequest& req, const IOOptions& opts,
                      std::function<void(FSReadRequest&, void*)> cb,
                      void* cb_arg, void** io_handle, IOHandleDeleter* del_fn,
-                     AlignedBuf* aligned_buf, IODebugContext* dbg = nullptr);
+                     AlignedBuf* aligned_buf);
 
   void ReadAsyncCallback(FSReadRequest& req, void* cb_arg);
 };

file/random_access_file_reader_test.cc

@@ -147,9 +147,8 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     reqs.push_back(std::move(r0));
     reqs.push_back(std::move(r1));
     AlignedBuf aligned_buf;
-    IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(
+        r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf));
 
     AssertResult(content, reqs);
 
@@ -193,9 +192,8 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     reqs.push_back(std::move(r1));
     reqs.push_back(std::move(r2));
     AlignedBuf aligned_buf;
-    IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(
+        r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf));
 
     AssertResult(content, reqs);
 
@@ -239,9 +237,8 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     reqs.push_back(std::move(r1));
     reqs.push_back(std::move(r2));
     AlignedBuf aligned_buf;
-    IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(
+        r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf));
 
     AssertResult(content, reqs);
 
@@ -277,9 +274,8 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     reqs.push_back(std::move(r0));
     reqs.push_back(std::move(r1));
     AlignedBuf aligned_buf;
-    IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(
+        r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf));
 
     AssertResult(content, reqs);
 

file/writable_file_writer.cc

@@ -687,9 +687,9 @@ IOStatus WritableFileWriter::WriteBufferedWithChecksum(const IOOptions& opts,
   if (rate_limiter_ != nullptr && rate_limiter_priority_used != Env::IO_TOTAL) {
     while (data_size > 0) {
       size_t tmp_size;
-      tmp_size =
-          rate_limiter_->RequestToken(data_size, 0, rate_limiter_priority_used,
-                                      stats_, RateLimiter::OpType::kWrite);
+      tmp_size = rate_limiter_->RequestToken(data_size, buf_.Alignment(),
+                                             rate_limiter_priority_used, stats_,
+                                             RateLimiter::OpType::kWrite);
       data_size -= tmp_size;
     }
   }

fuzz/sst_file_writer_fuzzer.cc

@@ -91,8 +91,7 @@ TableReader* NewTableReader(const std::string& sst_file_path,
   }
   if (s.ok()) {
     ImmutableOptions iopts(options, cf_ioptions);
-    TableReaderOptions t_opt(iopts, /*prefix_extractor=*/nullptr,
-                             /*compression_manager=*/nullptr, env_options,
+    TableReaderOptions t_opt(iopts, /*prefix_extractor=*/nullptr, env_options,
                              cf_ioptions.internal_comparator,
                              0 /* block_protection_bytes_per_key */);
     t_opt.largest_seqno = kMaxSequenceNumber;

include/rocksdb/advanced_compression.h

@@ -1,591 +0,0 @@
-//  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).
-//
-// APIs for customizing compression in RocksDB.
-//
-// ***********************************************************************
-// EXPERIMENTAL - subject to change while under development
-// ***********************************************************************
-
-#pragma once
-
-#include "rocksdb/cache.h"
-#include "rocksdb/compression_type.h"
-#include "rocksdb/data_structure.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-// TODO: alias/adapt for compression
-struct FilterBuildingContext;
-
-// A Compressor represents a very specific but potentially adapting strategy for
-// compressing blocks, including the relevant algorithm(s), options, dictionary,
-// etc. as applicable--every input except the sequence of bytes to compress.
-// Compressor is generally thread-safe so can be shared by multiple threads. (It
-// could make sense to convert unique_ptr<Compressor> to
-// shared_ptr<Compressor>.) A Compressor for data files is expected to be used
-// for just one file, so that compression strategy can be explicitly
-// reconsidered for each new file. However, a Compressor for in-memory use could
-// live indefinitely.
-//
-// If a single thread is doing many compressions under the same strategy, it
-// should request a WorkingArea that will in some cases make repeated
-// compression in a single thread more efficient. Unlike the rest of Compressor,
-// each WorkingArea can only be used by one thread at a time. WorkingAreas can
-// have pre-allocated space and/or data structures, and/or thread-local
-// statistics that are later incorporated into shared statistics objects.
-//
-// The Compressor marks each block with a CompressionType to guide
-// decompression. However, the compression dictionary (or whether there is one
-// associated) is determined at Compressor creation time, though the process of
-// getting a Compressor with a dictionary starts with a Compressor without
-// dictionary (which will often be relevant alongside); see relevant functions.
-// If the Compressor wants to decide block-by-block whether to apply the
-// configured dictionary, that would need to be encoded in CompressionType or
-// the compressed output. (NOTE: this was historically NOT encoded in
-// CompressionType and instead implied by BlockType and the presence of a
-// dictionary block in the file. Some of the resulting awkwardness includes
-// a number of built-in CompressionTypes that ignore any dictionary block in
-// the file; therefore they cannot accommodate dictionary compression in the
-// future without a schema change / extension.)
-class Compressor {
- public:
-  Compressor() = default;
-  virtual ~Compressor() = default;
-
-  // Class name for logging / debugging purposes
-  virtual const char* Name() const = 0;
-
-  // Potentially more elaborate identifier for logging / debugging purposes
-  virtual std::string GetId() const {
-    std::string id = Name();
-    return id;
-  }
-
-  // Returns the max total bytes of for all sampled blocks for creating the data
-  // dictionary, or zero indicating dictionary compression should not be
-  // used/configured. This will typically be called after
-  // CompressionManager::GetCompressor() to see if samples should be accumulated
-  // and passed to MaybeCloneSpecialized().
-  virtual size_t GetMaxSampleSizeIfWantDict(CacheEntryRole block_type) const {
-    // Default implementation: no dictionary
-    (void)block_type;
-    return 0;
-  }
-
-  // Returns the serialized form of the data dictionary associated with this
-  // Compressor. NOTE: empty dict is equivalent to no dict.
-  virtual Slice GetSerializedDict() const { return Slice(); }
-
-  // If there's a dominant compression type returned by this compressor as
-  // configured, return it. Otherwise, return kDisableCompressionOption.
-  virtual CompressionType GetPreferredCompressionType() const {
-    return CompressionType::kDisableCompressionOption;
-  }
-
-  // Utility struct for providing sample data for the compression dictionary.
-  // Potentially extensible by callers of Compressor (but not recommended)
-  struct DictSampleArgs {
-    // All the sample input blocks stored contiguously
-    std::string sample_data;
-    // The lengths of each of the sample blocks in `sample_data`
-    std::vector<size_t> sample_lens;
-
-    bool empty() { return sample_data.empty(); }
-    bool Verify() {
-      size_t total_len = 0;
-      for (auto len : sample_lens) {
-        total_len += len;
-      }
-      return total_len == sample_data.size();
-    }
-  };
-
-  // Create potential variants of the same Compressor that might be
-  // (a) optimized for a particular block type (does not affect correct
-  //     decompression), and/or
-  // (b) configured to use a compression dictionary, based on the given
-  //     samples (decompression must provide the dictionary from
-  //     GetSerializedDict())
-  // Return of nullptr indicates no specialization exists or was attempted
-  // and the caller is best to use the current Compressor for the desired
-  // scenario. Using CacheEntryRole:kMisc for block_type generally means
-  // "unspecified", and both parameters are merely suggestions. The exact
-  // dictionary associated with a returned compressor must be read from
-  // GetSerializedDict().
-  virtual std::unique_ptr<Compressor> MaybeCloneSpecialized(
-      CacheEntryRole block_type, DictSampleArgs&& dict_samples) {
-    // Default implementation: no specialization
-    (void)block_type;
-    (void)dict_samples;
-    // Caller should have checked GetMaxSampleSizeIfWantDict before attempting
-    // to provide dictionary samples
-    assert(dict_samples.empty());
-    return nullptr;
-  }
-
-  // A WorkingArea is an optional structure (both for callers and
-  // implementations) that can enable optimizing repeated compressions by
-  // reusing working space or thread-local tracking of statistics or trends.
-  // This enables use of ZSTD context, for example.
-  //
-  // EXTENSIBLE or reinterpret_cast-able by custom Compressor implementations
-  struct WorkingArea {};
-
- protected:
-  // To allow for flexible re-use / reclaimation, we have explicit Get and
-  // Release functions, and usually wrap in a special RAII smart pointer.
-  // For example, a WorkingArea could be saved/recycled in thread-local or
-  // core-local storage, or heap managed, etc., though an explicit WorkingArea
-  // is only advised for repeated compression (by a single thread).
-  virtual void ReleaseWorkingArea(WorkingArea*) {}
-
- public:
-  using ManagedWorkingArea =
-      ManagedPtr<WorkingArea, Compressor, &Compressor::ReleaseWorkingArea>;
-
-  // See struct WorkingArea above
-  virtual ManagedWorkingArea ObtainWorkingArea() {
-    // Default implementation: no working area
-    return {};
-  }
-
-  // Compress `uncompressed_data` to `compressed_output`, which should be
-  // passed in empty. Note that the compressed output will be decompressed
-  // by the sequence Decompressor::ExtractUncompressedSize() followed by
-  // Decompressor::DecompressBlock(), which must also be provided the same
-  // CompressionType saved in `out_compression_type`. (In many configurations,
-  // `compressed_output` will have a prefix storing the uncompressed_data size
-  // before the compressed bytes returned by the underlying compression
-  // algorithm. And the compression type is usually stored adjacent to the
-  // compressed data, or in some cases assumed/asserted based on the particular
-  // Compressor.)
-  //
-  // If return status is not OK, then some fatal condition has arisen. On OK
-  // status, setting `*out_compression_type = kNoCompression` means compression
-  // is declined and the caller should use the original uncompressed_data and
-  // ignore any result in `compressed_output`. Otherwise, compression has
-  // happened with results in `compressed_output` and `out_compression_type`,
-  // which are allowed to vary from call to call.
-  //
-  // The working area is optional and used to optimize repeated compression by
-  // a single thread. ManagedWorkingArea is provided rather than just
-  // WorkingArea so that it can be used only if the `owner` matches expectation.
-  // This could be useful for a Compressor wrapping more than one alternative
-  // underlying Compressor.
-  //
-  // TODO: instead of string, consider a buffer only large enough for max
-  // tolerable compressed size. Does that work for all existing algorithms?
-  // * Looks like Snappy doesn't support that. :(
-  //   * Except perhaps using the Sink interface
-  // * But looks like everything else should. :)
-  // Could save CPU by eliminating extra zero-ing and giving up quicker when
-  // ratio is insufficient.
-  virtual Status CompressBlock(Slice uncompressed_data,
-                               std::string* compressed_output,
-                               CompressionType* out_compression_type,
-                               ManagedWorkingArea* working_area) = 0;
-
-  // TODO: something to populate table properties based on settings, after all
-  // or as WorkingAreas released. Maybe also update stats, or that could be in
-  // thread-specific WorkingArea.
-};
-
-// A Decompressor usually has a wide capability to decompress all kinds of
-// compressed data in the scope of a CompressionManager (see that class below),
-// except
-// (a) it might be optimized for or limited to a particular compression type(s)
-//     (see GetDecompressor* functions for in CompressionManager),
-// (b) distinct Decompressors are required to decompress with compression
-//     dictionaries. (Decompressors are generally associated with empty/no
-//     dictionary unless created with MaybeCloneForDict().)
-//
-// Similar to Compressor, Decompressor is generally thread safe except that each
-// WorkingArea can only be used by a single thread at a time.
-//
-// Decompressors known to be associated with no dictionary are typically
-// returned as shared_ptr, because they are broadly usable across threads.
-// Because compression dictionaries are externally managed (see
-// MaybeCloneForDict()), Decompressors associated with compression dictionaries
-// are typically returned as unique_ptr, so that they are more easily
-// guaranteed not to outlive their dictionaries (e.g. in block cache).
-// Decompressors associated with compression dictionaries might include a
-// processed or "digested" form of the raw dictionary for efficient repeated
-// compressions.
-//
-// NOTE: Splitting the interface between ExtractUncompressedSize and
-// DecompressBlock leaves to the caller details of (and flexibility in)
-// allocating buffers for decompressing into. For example, the data could be
-// decompressed into part of a single buffer allocated to hold a block's
-// uncompressed contents along with an in-memory object representation of the
-// block (to reduce fragmentation and other overheads of separate objects).
-class Decompressor {
- public:
-  Decompressor() = default;
-  virtual ~Decompressor() = default;
-
-  // A name for logging / debugging purposes
-  virtual const char* Name() const = 0;
-
-  // A WorkingArea is an optional structure (both for callers and
-  // implementations) that can enable optimizing repeated decompressions by
-  // reusing working space or thread-local tracking of statistics. This enables
-  // use of ZSTD context, for example.
-  //
-  // EXTENSIBLE or reinterpret_cast-able by custom Compressor implementations
-  struct WorkingArea {};
-
-  // To allow for flexible re-use / reclaimation, we have explicit Obtain and
-  // Release functions, which are typically wrapped in a special RAII smart
-  // pointer. For example, a WorkingArea could be saved/recycled in thread-local
-  // or core-local storage, or heap managed, etc., though an explicit
-  // WorkingArea is only advised for repeated decompression (by a single
-  // thread). ReleaseWorkingArea() in not intended to be called directly, but
-  // used by ManagedWorkingArea.
-  virtual void ReleaseWorkingArea(WorkingArea* wa) {
-    // Default implementation: no working area
-    (void)wa;
-    assert(wa == nullptr);
-  }
-
-  using ManagedWorkingArea =
-      ManagedPtr<WorkingArea, Decompressor, &Decompressor::ReleaseWorkingArea>;
-
-  virtual ManagedWorkingArea ObtainWorkingArea(CompressionType /*preferred*/) {
-    // Default implementation: no working area
-    return {};
-  }
-
-  // If this Decompressor is associated with a (de)compression dictionary
-  // (created with MaybeCloneForDict()), this returns a pointer to those raw (or
-  // "serialized") bytes, which are externally managed (see
-  // MaybeCloneForDict()).
-  // Default: empty slice => no dictionary
-  virtual const Slice& GetSerializedDict() const;
-
-  // Create a variant of this Decompressor in `out` using the specified raw
-  // ("serialized") dictionary. This step is required for decompressing data
-  // compressed with the same dictionary. The new Decompressor references the
-  // given Slice through its lifetime so the data it points to must be managed
-  // by the caller along with (or beyond) the new Decompressor. If the
-  // dictionary is processed into a form reusable by repeated compressions in
-  // many threads, that happens within this call.
-  //
-  // Must return OK if and only if storing a result in `out`. Otherwise, could
-  // return values like NotSupported - dictionary compression is not (yet)
-  // supported for this kind of Decompressor. Corruption - dictionary is
-  // malformed (though many implementations will accept any data as a
-  // dictionary)
-  virtual Status MaybeCloneForDict(const Slice& /*serialized_dict*/,
-                                   std::unique_ptr<Decompressor>* /*out*/) {
-    return Status::NotSupported(
-        "Dictionary compression not (yet) supported by " + std::string(Name()));
-  }
-
-  // Memory size of this object and others it owns. Does not include the
-  // serialized dictionary (when used) which is externally managed.
-  virtual size_t ApproximateOwnedMemoryUsage() const {
-    // Default: negligible
-    return 0;
-  }
-
-  // Potentially extensible by callers of Decompressor (but not recommended)
-  struct Args {
-    CompressionType compression_type = kNoCompression;
-    Slice compressed_data;
-    uint64_t uncompressed_size = 0;
-    ManagedWorkingArea* working_area = nullptr;
-  };
-
-  // For efficiency on the read path, RocksDB strongly prefers the uncompressed
-  // data size to be encoded in the compressed data in an easily accessible way,
-  // so that allocation of a potentially long-lived buffer can be ideally sized.
-  // This function determines the uncompressed size and potentially modifies
-  // `args.compressed_data` to strip off the size metadata, for providing both
-  // to DecompressBlock along with an appropriate buffer based on that size.
-  // Some implementations will leave `compressed_data` unmodified and let
-  // DecompressBlock call a library function that processes a format that
-  // includes size metadata (e.g. Snappy).
-  //
-  // Even for legacy cases without size metadata (e.g. some very old RocksDB
-  // formats), an exact size is required and could require decompressing the
-  // data (here and in DecompressBlock()).
-  //
-  // Return non-OK in case of corrupt data or some other unworkable limitation
-  // or failure.
-  //
-  // The default implementation uses a standard format for prepending
-  // uncompressed size to the compressed payload. (RocksDB
-  // compress_format_version=2 except Snappy)
-  virtual Status ExtractUncompressedSize(Args& args);
-
-  // Called to decompress a block of data after running ExtractUncompressedSize
-  // on it. `args.compressed_data` is what ExtractUncompressedSize left there
-  // after potentially stripping off the uncompressed size metadata. Returns OK
-  // iff uncompressed data of size `uncompressed_size` is written to
-  // `uncompressed_output`.
-  virtual Status DecompressBlock(const Args& args,
-                                 char* uncompressed_output) = 0;
-};
-
-// A CompressionManager represents
-// * When/where/how to use different compressions
-// * A schema (or set of schemas) and implementation for mapping
-//     <CompressionType, dictionary, compressed data>
-//   to uncompressed data (or error), which can expand over time (error in fewer
-//   cases) for a given CompatibilityName() but can never change that mapping
-//   (because that would break backward compatibility, potential quiet
-//   corruption)
-// TODO: consider adding optional streaming compression support (low priority)
-class CompressionManager
-    : public std::enable_shared_from_this<CompressionManager>,
-      public Customizable {
- public:
-  CompressionManager() = default;
-  virtual ~CompressionManager() = default;
-  static const char* Type() { return "CompressionManager"; }
-
-  // *************** Creating various Compression Managers *************** //
-  // A name for the schema family of this CompressionManager. In short, if
-  // two CompressionManagers have functionally the same Decompressor(s), they
-  // should have the same CompatibilityName(), so that a compatible
-  // CompressionManager/Decompressor might be used if the original is
-  // unavailable. (Name() can be useful in addition to CompatibilityName() for
-  // understanding what compression strategy was used.) This name should be
-  // limited to legal variable names in C++ (alphanumeric and underscores).
-  virtual const char* CompatibilityName() const = 0;
-
-  // Default implementation checks the current compatibility name and returns
-  // this CompressionManager (via `out`) if appropriate, and otherwise defers
-  // to CreateFromString(). Failure should simply be a matter of "not found" in
-  // which case nullptr is returned.
-  virtual std::shared_ptr<CompressionManager> FindCompatibleCompressionManager(
-      Slice compatibility_name);
-
-  // Create or find a CompressionManager from a string, including built-in
-  // CompressionManager types.
-  // TODO: ObjectLibrary stuff
-  static Status CreateFromString(const ConfigOptions& config_options,
-                                 const std::string& id,
-                                 std::shared_ptr<CompressionManager>* result);
-
-  // Will this compression type be used if requested in calling
-  // GetCompressor/GetCompressorForSST?
-  virtual bool SupportsCompressionType(CompressionType type) const = 0;
-
-  // TODO: function to check compatibility with or sanitize CompressionOptions
-
-  // ************************* Compressor creation *********************** //
-  // Returning nullptr means compression is entirely disabled for the file,
-  // which is valid at the discretion of the CompressionManager. Returning
-  // nullptr should normally be the result if preferred == kNoCompression.
-  //
-  // These functions must be thread-safe.
-
-  // Get a compressor for an SST file.
-  // SUBJECT TO CHANGE
-  // TODO: is it practical to get ColumnFamilyOptions plumbed into here?
-  virtual std::unique_ptr<Compressor> GetCompressorForSST(
-      const FilterBuildingContext&, const CompressionOptions& opts,
-      CompressionType preferred) {
-    return GetCompressor(opts, preferred);
-  }
-
-  // Get a compressor for a generic/unspecified purpose (e.g. in-memory
-  // compression).
-  virtual std::unique_ptr<Compressor> GetCompressor(
-      const CompressionOptions& opts, CompressionType type) = 0;
-
-  // **************************** Decompressors ************************** //
-  // Get a decompressor that is compatible with any blocks compressed by
-  // compressors returned by this CompressionManager (at least this code
-  // revision and earlier). (NOTE: recommended to return a shared_ptr alias of
-  // this shared_ptr to a field that is a Decompressor.)
-  // Justification for not making CompressionManager inherit Decompressor: this
-  // tends to run into the diamond inheritance problem in implementations and
-  // potential overheads of virtual inheritance.
-  virtual std::shared_ptr<Decompressor> GetDecompressor() = 0;
-
-  // Compatible with same as above, but potentially optimized for a certain
-  // expected CompressionType
-  virtual std::shared_ptr<Decompressor> GetDecompressorOptimizeFor(
-      CompressionType /*optimize_for_type*/) {
-    // Safe default implementation
-    return GetDecompressor();
-  }
-
-  // Get a decompressor that is allowed to have support only for the
-  // CompressionTypes in the given start-to-end array (unique, sorted by
-  // unsigned char)
-  virtual std::shared_ptr<Decompressor> GetDecompressorForTypes(
-      const CompressionType* /*types_begin*/,
-      const CompressionType* /*types_end*/) {
-    // Safe default implementation
-    return GetDecompressor();
-  }
-
-  // Get a decompressor that is allowed to have support only for the
-  // CompressionTypes used by the given Compressor.
-  virtual std::shared_ptr<Decompressor> GetDecompressorForCompressor(
-      const Compressor& compressor) {
-    // Reasonable default implementation
-    return GetDecompressorOptimizeFor(compressor.GetPreferredCompressionType());
-  }
-};
-
-// ************************* Utility wrappers etc. *********************** //
-class CompressorWrapper : public Compressor {
- public:
-  explicit CompressorWrapper(std::unique_ptr<Compressor> compressor)
-      : wrapped_(std::move(compressor)) {}
-  // No copies
-  CompressorWrapper(const CompressorWrapper&) = delete;
-  CompressorWrapper& operator=(const CompressorWrapper&) = delete;
-
-  size_t GetMaxSampleSizeIfWantDict(CacheEntryRole block_type) const override {
-    return wrapped_->GetMaxSampleSizeIfWantDict(block_type);
-  }
-
-  Slice GetSerializedDict() const override {
-    return wrapped_->GetSerializedDict();
-  }
-
-  CompressionType GetPreferredCompressionType() const override {
-    return wrapped_->GetPreferredCompressionType();
-  }
-
-  std::unique_ptr<Compressor> MaybeCloneSpecialized(
-      CacheEntryRole block_type, DictSampleArgs&& dict_samples) override {
-    return wrapped_->MaybeCloneSpecialized(block_type, std::move(dict_samples));
-  }
-
-  ManagedWorkingArea ObtainWorkingArea() override {
-    return wrapped_->ObtainWorkingArea();
-  }
-
-  Status CompressBlock(Slice uncompressed_data, std::string* compressed_output,
-                       CompressionType* out_compression_type,
-                       ManagedWorkingArea* working_area) override {
-    return wrapped_->CompressBlock(uncompressed_data, compressed_output,
-                                   out_compression_type, working_area);
-  }
-
- protected:
-  std::unique_ptr<Compressor> wrapped_;
-};
-
-class DecompressorWrapper : public Decompressor {
- public:
-  explicit DecompressorWrapper(std::shared_ptr<Decompressor> decompressor)
-      : wrapped_(std::move(decompressor)) {}
-  // No copies
-  DecompressorWrapper(const DecompressorWrapper&) = delete;
-  DecompressorWrapper& operator=(const DecompressorWrapper&) = delete;
-
-  const char* Name() const override { return wrapped_->Name(); }
-
-  void ReleaseWorkingArea(WorkingArea* wa) override {
-    wrapped_->ReleaseWorkingArea(wa);
-  }
-
-  ManagedWorkingArea ObtainWorkingArea(CompressionType preferred) override {
-    return wrapped_->ObtainWorkingArea(preferred);
-  }
-
-  const Slice& GetSerializedDict() const override {
-    return wrapped_->GetSerializedDict();
-  }
-
-  Status MaybeCloneForDict(const Slice& serialized_dict,
-                           std::unique_ptr<Decompressor>* out) override {
-    // NOTE: derived class probably needs to override this to ensure a
-    // derived wrapper around the new Decompressor
-    return wrapped_->MaybeCloneForDict(serialized_dict, out);
-  }
-
-  size_t ApproximateOwnedMemoryUsage() const override {
-    return wrapped_->ApproximateOwnedMemoryUsage();
-  }
-
-  Status ExtractUncompressedSize(Args& args) override {
-    return wrapped_->ExtractUncompressedSize(args);
-  }
-
-  Status DecompressBlock(const Args& args, char* uncompressed_output) override {
-    return wrapped_->DecompressBlock(args, uncompressed_output);
-  }
-
- protected:
-  std::shared_ptr<Decompressor> wrapped_;
-};
-
-// TODO: CompressorBase, for custom compressions
-
-class CompressionManagerWrapper : public CompressionManager {
- public:
-  explicit CompressionManagerWrapper(
-      std::shared_ptr<CompressionManager> wrapped)
-      : wrapped_(std::move(wrapped)) {}
-
-  const char* CompatibilityName() const override {
-    return wrapped_->CompatibilityName();
-  }
-
-  std::shared_ptr<CompressionManager> FindCompatibleCompressionManager(
-      Slice compatibility_name) override {
-    return wrapped_->FindCompatibleCompressionManager(compatibility_name);
-  }
-
-  bool SupportsCompressionType(CompressionType type) const override {
-    return wrapped_->SupportsCompressionType(type);
-  }
-
-  std::unique_ptr<Compressor> GetCompressorForSST(
-      const FilterBuildingContext& context, const CompressionOptions& opts,
-      CompressionType preferred) override {
-    return wrapped_->GetCompressorForSST(context, opts, preferred);
-  }
-
-  std::unique_ptr<Compressor> GetCompressor(const CompressionOptions& opts,
-                                            CompressionType type) override {
-    return wrapped_->GetCompressor(opts, type);
-  }
-
-  std::shared_ptr<Decompressor> GetDecompressor() override {
-    return wrapped_->GetDecompressor();
-  }
-
-  std::shared_ptr<Decompressor> GetDecompressorOptimizeFor(
-      CompressionType optimize_for_type) override {
-    return wrapped_->GetDecompressorOptimizeFor(optimize_for_type);
-  }
-
-  std::shared_ptr<Decompressor> GetDecompressorForTypes(
-      const CompressionType* types_begin,
-      const CompressionType* types_end) override {
-    return wrapped_->GetDecompressorForTypes(types_begin, types_end);
-  }
-
-  std::shared_ptr<Decompressor> GetDecompressorForCompressor(
-      const Compressor& compressor) override {
-    return wrapped_->GetDecompressorForCompressor(compressor);
-  }
-
- protected:
-  std::shared_ptr<CompressionManager> wrapped_;
-};
-
-// Compression manager that implements built-in compression strategy. The
-// behavior of compression_manager=nullptr is essentially equivalent to
-// using this compression manager.
-const std::shared_ptr<CompressionManager>&
-GetDefaultBuiltinCompressionManager();
-// Gets CompressionManager designed for the automated compression strategy.
-// This may include deciding to compress or not.
-// In future should be able to select compression algorithm based on the CPU
-// utilization and IO constraints.
-std::shared_ptr<CompressionManagerWrapper> CreateAutoSkipCompressionManager(
-    std::shared_ptr<CompressionManager> wrapped);
-}  // namespace ROCKSDB_NAMESPACE

include/rocksdb/advanced_options.h

@@ -115,21 +115,6 @@ struct CompactionOptionsFIFO {
   // Default: empty
   std::vector<FileTemperatureAge> file_temperature_age_thresholds{};
 
-  // EXPERIMENTAL
-  // If true, when compaction is picked for kChangeTemperature reason,
-  // allow the trivia copy of the sst file from source FileSystem to
-  // destination FileSystem. If false, the changeTemperature will be
-  // the non-trivial copy by iterating/appending blocks by blocks of the
-  // sst file.
-  bool allow_trivial_copy_when_change_temperature = false;
-
-  // EXPERIMENTAL
-  // If 'allow_trivia_copy_op_when_change_temperature=true', the tmp buffer size
-  // to copy the file from the source FileSystem to the destnation FileSystem.
-  // If 'allow_trivia_copy_op_when_change_temperature=false', this field will
-  // not be used. The minmum buffer size must be at least 4KiB
-  uint64_t trivial_copy_buffer_size = 4096;
-
   CompactionOptionsFIFO() : max_table_files_size(1 * 1024 * 1024 * 1024) {}
   CompactionOptionsFIFO(uint64_t _max_table_files_size, bool _allow_compaction)
       : max_table_files_size(_max_table_files_size),
@@ -863,7 +848,7 @@ struct AdvancedColumnFamilyOptions {
   //
   // Default: 0 (disable the feature)
   //
-  // Dynamically changeable through the SetOptions() API
+  // Not dynamically changeable, change it requires db restart.
   uint64_t preclude_last_level_data_seconds = 0;
 
   // EXPERIMENTAL
@@ -886,7 +871,7 @@ struct AdvancedColumnFamilyOptions {
   //
   // Default: 0 (disable the feature)
   //
-  // Dynamically changeable through the SetOptions() API
+  // Not dynamically changeable, change it requires db restart.
   uint64_t preserve_internal_time_seconds = 0;
 
   // When set, large values (blobs) are written to separate blob files, and
@@ -1121,31 +1106,10 @@ struct AdvancedColumnFamilyOptions {
   // CompactOnDeletionCollectorFactory) together with this option to compact
   // away tombstones after the memtable is flushed.
   //
-  // Note that this option has no effect on tailing iterators yet.
-  //
   // Default: 0 (disabled)
   // Dynamically changeable through the SetOptions() API.
   uint32_t memtable_op_scan_flush_trigger = 0;
 
-  // Similar to `memtable_op_scan_flush_trigger`, but this option applies to
-  // Next() calls between Seeks or until iterator destruction. If the average
-  // of the number of invisible entries scanned from the active memtable, the
-  // memtable will be marked for flush.
-  // Note that to avoid the case where the window between Seeks is too small,
-  // the option only takes effect if the total number of hidden entries scanned
-  // within a window is at least `memtable_op_scan_flush_trigger`. So this
-  // option is only effective when `memtable_op_scan_flush_trigger` is set.
-  //
-  // This option should be set to a lower value than
-  // `memtable_op_scan_flush_trigger`. It covers the case where an iterator
-  // scans through an expensive key range with many invisible entries from the
-  // active memtable, but the number of invisible entries per operation does not
-  // exceed `memtable_op_scan_flush_trigger`.
-  //
-  // Default: 0 (disabled)
-  // Dynamically changeable through the SetOptions() API.
-  uint32_t memtable_avg_op_scan_flush_trigger = 0;
-
   // Create ColumnFamilyOptions with default values for all fields
   AdvancedColumnFamilyOptions();
   // Create ColumnFamilyOptions from Options

include/rocksdb/c.h

@@ -69,7 +69,6 @@ extern "C" {
 /* Exported types */
 
 typedef struct rocksdb_t rocksdb_t;
-typedef struct rocksdb_status_ptr_t rocksdb_status_ptr_t;
 typedef struct rocksdb_backup_engine_t rocksdb_backup_engine_t;
 typedef struct rocksdb_backup_engine_info_t rocksdb_backup_engine_info_t;
 typedef struct rocksdb_backup_engine_options_t rocksdb_backup_engine_options_t;
@@ -80,7 +79,6 @@ typedef struct rocksdb_hyper_clock_cache_options_t
     rocksdb_hyper_clock_cache_options_t;
 typedef struct rocksdb_cache_t rocksdb_cache_t;
 typedef struct rocksdb_write_buffer_manager_t rocksdb_write_buffer_manager_t;
-typedef struct rocksdb_sst_file_manager_t rocksdb_sst_file_manager_t;
 typedef struct rocksdb_compactionfilter_t rocksdb_compactionfilter_t;
 typedef struct rocksdb_compactionfiltercontext_t
     rocksdb_compactionfiltercontext_t;
@@ -143,15 +141,6 @@ typedef struct rocksdb_statistics_histogram_data_t
     rocksdb_statistics_histogram_data_t;
 typedef struct rocksdb_wait_for_compact_options_t
     rocksdb_wait_for_compact_options_t;
-typedef struct rocksdb_flushjobinfo_t rocksdb_flushjobinfo_t;
-typedef struct rocksdb_compactionjobinfo_t rocksdb_compactionjobinfo_t;
-typedef struct rocksdb_subcompactionjobinfo_t rocksdb_subcompactionjobinfo_t;
-typedef struct rocksdb_externalfileingestioninfo_t
-    rocksdb_externalfileingestioninfo_t;
-typedef struct rocksdb_eventlistener_t rocksdb_eventlistener_t;
-typedef struct rocksdb_writestallinfo_t rocksdb_writestallinfo_t;
-typedef struct rocksdb_writestallcondition_t rocksdb_writestallcondition_t;
-typedef struct rocksdb_memtableinfo_t rocksdb_memtableinfo_t;
 
 /* DB operations */
 
@@ -997,22 +986,11 @@ extern ROCKSDB_LIBRARY_API char* rocksdb_writebatch_wi_get_from_batch_and_db(
     rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
     const rocksdb_readoptions_t* options, const char* key, size_t keylen,
     size_t* vallen, char** errptr);
-extern ROCKSDB_LIBRARY_API rocksdb_pinnableslice_t*
-rocksdb_writebatch_wi_get_pinned_from_batch_and_db(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
-    const rocksdb_readoptions_t* options, const char* key, size_t keylen,
-    char** errptr);
 extern ROCKSDB_LIBRARY_API char* rocksdb_writebatch_wi_get_from_batch_and_db_cf(
     rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
     const rocksdb_readoptions_t* options,
     rocksdb_column_family_handle_t* column_family, const char* key,
     size_t keylen, size_t* vallen, char** errptr);
-extern ROCKSDB_LIBRARY_API rocksdb_pinnableslice_t*
-rocksdb_writebatch_wi_get_pinned_from_batch_and_db_cf(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_t* db,
-    const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key,
-    size_t keylen, char** errptr);
 extern ROCKSDB_LIBRARY_API void rocksdb_write_writebatch_wi(
     rocksdb_t* db, const rocksdb_writeoptions_t* options,
     rocksdb_writebatch_wi_t* wbwi, char** errptr);
@@ -1020,20 +998,13 @@ extern ROCKSDB_LIBRARY_API rocksdb_iterator_t*
 rocksdb_writebatch_wi_create_iterator_with_base(
     rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator);
 extern ROCKSDB_LIBRARY_API rocksdb_iterator_t*
-rocksdb_writebatch_wi_create_iterator_with_base_readopts(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
-    const rocksdb_readoptions_t* options);
-extern ROCKSDB_LIBRARY_API rocksdb_iterator_t*
 rocksdb_writebatch_wi_create_iterator_with_base_cf(
     rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
     rocksdb_column_family_handle_t* cf);
-extern ROCKSDB_LIBRARY_API rocksdb_iterator_t*
-rocksdb_writebatch_wi_create_iterator_with_base_cf_readopts(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
-    rocksdb_column_family_handle_t* cf, const rocksdb_readoptions_t* options);
 extern ROCKSDB_LIBRARY_API void rocksdb_writebatch_wi_update_timestamps(
     rocksdb_writebatch_wi_t* wbwi, const char* ts, size_t tslen, void* state,
     size_t (*get_ts_size)(void*, uint32_t), char** errptr);
+
 /* Options utils */
 
 // Load the latest rocksdb options from the specified db_path.
@@ -1155,137 +1126,6 @@ rocksdb_block_based_options_set_unpartitioned_pinning_tier(
 extern ROCKSDB_LIBRARY_API void rocksdb_options_set_write_buffer_manager(
     rocksdb_options_t* opt, rocksdb_write_buffer_manager_t* wbm);
 
-/* Flush job info */
-
-extern ROCKSDB_LIBRARY_API const char* rocksdb_flushjobinfo_cf_name(
-    const rocksdb_flushjobinfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API const char* rocksdb_flushjobinfo_file_path(
-    const rocksdb_flushjobinfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API unsigned char
-rocksdb_flushjobinfo_triggered_writes_slowdown(const rocksdb_flushjobinfo_t*);
-extern ROCKSDB_LIBRARY_API unsigned char
-rocksdb_flushjobinfo_triggered_writes_stop(const rocksdb_flushjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_flushjobinfo_largest_seqno(const rocksdb_flushjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_flushjobinfo_smallest_seqno(const rocksdb_flushjobinfo_t*);
-extern ROCKSDB_LIBRARY_API void rocksdb_reset_status(
-    rocksdb_status_ptr_t* status_ptr);
-
-/* Compaction job info */
-extern ROCKSDB_LIBRARY_API void rocksdb_compactionjobinfo_status(
-    const rocksdb_compactionjobinfo_t* info, char** errptr);
-extern ROCKSDB_LIBRARY_API const char* rocksdb_compactionjobinfo_cf_name(
-    const rocksdb_compactionjobinfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API size_t
-rocksdb_compactionjobinfo_input_files_count(const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API const char* rocksdb_compactionjobinfo_input_file_at(
-    const rocksdb_compactionjobinfo_t*, size_t pos, size_t*);
-extern ROCKSDB_LIBRARY_API size_t rocksdb_compactionjobinfo_output_files_count(
-    const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API const char* rocksdb_compactionjobinfo_output_file_at(
-    const rocksdb_compactionjobinfo_t*, size_t pos, size_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_compactionjobinfo_elapsed_micros(const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_compactionjobinfo_num_corrupt_keys(const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API int rocksdb_compactionjobinfo_base_input_level(
-    const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API int rocksdb_compactionjobinfo_output_level(
-    const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_compactionjobinfo_input_records(const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_compactionjobinfo_output_records(const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_compactionjobinfo_total_input_bytes(const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_compactionjobinfo_total_output_bytes(
-    const rocksdb_compactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API uint32_t rocksdb_compactionjobinfo_compaction_reason(
-    const rocksdb_compactionjobinfo_t* info);
-extern ROCKSDB_LIBRARY_API size_t rocksdb_compactionjobinfo_num_input_files(
-    const rocksdb_compactionjobinfo_t* info);
-extern ROCKSDB_LIBRARY_API size_t
-rocksdb_compactionjobinfo_num_input_files_at_output_level(
-    const rocksdb_compactionjobinfo_t* info);
-
-/* Subcompaction job info */
-extern ROCKSDB_LIBRARY_API void rocksdb_subcompactionjobinfo_status(
-    const rocksdb_subcompactionjobinfo_t*, char**);
-extern ROCKSDB_LIBRARY_API const char* rocksdb_subcompactionjobinfo_cf_name(
-    const rocksdb_subcompactionjobinfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_subcompactionjobinfo_thread_id(const rocksdb_subcompactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API int rocksdb_subcompactionjobinfo_base_input_level(
-    const rocksdb_subcompactionjobinfo_t*);
-extern ROCKSDB_LIBRARY_API int rocksdb_subcompactionjobinfo_output_level(
-    const rocksdb_subcompactionjobinfo_t*);
-
-/* External file ingestion info */
-extern ROCKSDB_LIBRARY_API const char*
-rocksdb_externalfileingestioninfo_cf_name(
-    const rocksdb_externalfileingestioninfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API const char*
-rocksdb_externalfileingestioninfo_internal_file_path(
-    const rocksdb_externalfileingestioninfo_t*, size_t*);
-
-/* External write stall info */
-extern ROCKSDB_LIBRARY_API const char* rocksdb_writestallinfo_cf_name(
-    const rocksdb_writestallinfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API const rocksdb_writestallcondition_t*
-rocksdb_writestallinfo_cur(const rocksdb_writestallinfo_t*);
-extern ROCKSDB_LIBRARY_API const rocksdb_writestallcondition_t*
-rocksdb_writestallinfo_prev(const rocksdb_writestallinfo_t*);
-extern ROCKSDB_LIBRARY_API const char* rocksdb_memtableinfo_cf_name(
-    const rocksdb_memtableinfo_t*, size_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_memtableinfo_first_seqno(const rocksdb_memtableinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_memtableinfo_earliest_seqno(const rocksdb_memtableinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_memtableinfo_num_entries(const rocksdb_memtableinfo_t*);
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_memtableinfo_num_deletes(const rocksdb_memtableinfo_t*);
-
-/* Event listener */
-
-typedef void (*on_flush_begin_cb)(void*, rocksdb_t*,
-                                  const rocksdb_flushjobinfo_t*);
-typedef void (*on_flush_completed_cb)(void*, rocksdb_t*,
-                                      const rocksdb_flushjobinfo_t*);
-typedef void (*on_compaction_begin_cb)(void*, rocksdb_t*,
-                                       const rocksdb_compactionjobinfo_t*);
-typedef void (*on_compaction_completed_cb)(void*, rocksdb_t*,
-                                           const rocksdb_compactionjobinfo_t*);
-typedef void (*on_subcompaction_begin_cb)(
-    void*, const rocksdb_subcompactionjobinfo_t*);
-typedef void (*on_subcompaction_completed_cb)(
-    void*, const rocksdb_subcompactionjobinfo_t*);
-typedef void (*on_external_file_ingested_cb)(
-    void*, rocksdb_t*, const rocksdb_externalfileingestioninfo_t*);
-typedef void (*on_background_error_cb)(void*, uint32_t, rocksdb_status_ptr_t*);
-typedef void (*on_stall_conditions_changed_cb)(void*,
-                                               const rocksdb_writestallinfo_t*);
-typedef void (*rocksdb_logger_logv_cb)(void*, uint32_t log_level, const char*);
-typedef void (*on_memtable_sealed_cb)(void*, const rocksdb_memtableinfo_t*);
-extern ROCKSDB_LIBRARY_API rocksdb_eventlistener_t*
-rocksdb_eventlistener_create(
-    void* state_, void (*destructor_)(void*), on_flush_begin_cb on_flush_begin,
-    on_flush_completed_cb on_flush_completed,
-    on_compaction_begin_cb on_compaction_begin,
-    on_compaction_completed_cb on_compaction_completed,
-    on_subcompaction_begin_cb on_subcompaction_begin,
-    on_subcompaction_completed_cb on_subcompaction_completed,
-    on_external_file_ingested_cb on_external_file_ingested,
-    on_background_error_cb on_background_error,
-    on_stall_conditions_changed_cb on_stall_conditions_changed,
-    on_memtable_sealed_cb on_memtable_sealed);
-extern ROCKSDB_LIBRARY_API void rocksdb_eventlistener_destroy(
-    rocksdb_eventlistener_t*);
-extern ROCKSDB_LIBRARY_API void rocksdb_options_add_eventlistener(
-    rocksdb_options_t*, rocksdb_eventlistener_t*);
-
 /* Cuckoo table options */
 
 extern ROCKSDB_LIBRARY_API rocksdb_cuckoo_table_options_t*
@@ -1507,12 +1347,6 @@ rocksdb_options_set_memtable_op_scan_flush_trigger(rocksdb_options_t*,
 extern ROCKSDB_LIBRARY_API uint32_t
 rocksdb_options_get_memtable_op_scan_flush_trigger(rocksdb_options_t*);
 
-extern ROCKSDB_LIBRARY_API void
-rocksdb_options_set_memtable_avg_op_scan_flush_trigger(rocksdb_options_t*,
-                                                       uint32_t);
-extern ROCKSDB_LIBRARY_API uint32_t
-rocksdb_options_get_memtable_avg_op_scan_flush_trigger(rocksdb_options_t*);
-
 enum {
   rocksdb_statistics_level_disable_all = 0,
   rocksdb_statistics_level_except_tickers =
@@ -2041,8 +1875,7 @@ enum {
   rocksdb_blob_decompress_time,
   rocksdb_internal_range_del_reseek_count,
   rocksdb_block_read_cpu_time,
-  rocksdb_internal_merge_point_lookup_count,
-  rocksdb_total_metric_count = 80
+  rocksdb_total_metric_count = 79
 };
 
 extern ROCKSDB_LIBRARY_API void rocksdb_set_perf_level(int);
@@ -2392,51 +2225,6 @@ extern ROCKSDB_LIBRARY_API void rocksdb_write_buffer_manager_set_buffer_size(
 extern ROCKSDB_LIBRARY_API void rocksdb_write_buffer_manager_set_allow_stall(
     rocksdb_write_buffer_manager_t* wbm, bool new_allow_stall);
 
-/* SstFileManager */
-
-extern ROCKSDB_LIBRARY_API rocksdb_sst_file_manager_t*
-rocksdb_sst_file_manager_create(rocksdb_env_t* env);
-
-extern ROCKSDB_LIBRARY_API void rocksdb_sst_file_manager_destroy(
-    rocksdb_sst_file_manager_t* sfm);
-
-extern ROCKSDB_LIBRARY_API void
-rocksdb_sst_file_manager_set_max_allowed_space_usage(
-    rocksdb_sst_file_manager_t* sfm, uint64_t max_allowed_space);
-
-extern ROCKSDB_LIBRARY_API void
-rocksdb_sst_file_manager_set_compaction_buffer_size(
-    rocksdb_sst_file_manager_t* sfm, uint64_t compaction_buffer_size);
-
-extern ROCKSDB_LIBRARY_API bool
-rocksdb_sst_file_manager_is_max_allowed_space_reached(
-    rocksdb_sst_file_manager_t* sfm);
-
-extern ROCKSDB_LIBRARY_API bool
-rocksdb_sst_file_manager_is_max_allowed_space_reached_including_compactions(
-    rocksdb_sst_file_manager_t* sfm);
-
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_sst_file_manager_get_total_size(rocksdb_sst_file_manager_t* sfm);
-
-extern ROCKSDB_LIBRARY_API int64_t
-rocksdb_sst_file_manager_get_delete_rate_bytes_per_second(
-    rocksdb_sst_file_manager_t* sfm);
-
-extern ROCKSDB_LIBRARY_API void
-rocksdb_sst_file_manager_set_delete_rate_bytes_per_second(
-    rocksdb_sst_file_manager_t* sfm, int64_t delete_rate);
-
-extern ROCKSDB_LIBRARY_API double
-rocksdb_sst_file_manager_get_max_trash_db_ratio(
-    rocksdb_sst_file_manager_t* sfm);
-
-extern ROCKSDB_LIBRARY_API void rocksdb_sst_file_manager_set_max_trash_db_ratio(
-    rocksdb_sst_file_manager_t* sfm, double ratio);
-
-extern ROCKSDB_LIBRARY_API uint64_t
-rocksdb_sst_file_manager_get_total_trash_size(rocksdb_sst_file_manager_t* sfm);
-
 /* HyperClockCache */
 
 extern ROCKSDB_LIBRARY_API rocksdb_hyper_clock_cache_options_t*

include/rocksdb/compression_type.h

@@ -18,146 +18,14 @@ namespace ROCKSDB_NAMESPACE {
 enum CompressionType : unsigned char {
   // NOTE: do not change the values of existing entries, as these are
   // part of the persistent format on disk.
-  kNoCompression = 0x00,
-  kSnappyCompression = 0x01,
-  kZlibCompression = 0x02,
-  kBZip2Compression = 0x03,
-  kLZ4Compression = 0x04,
-  kLZ4HCCompression = 0x05,
-  kXpressCompression = 0x06,
-  kZSTD = 0x07,
-  kLastBuiltinCompression = kZSTD,
-
-  // Reserved for future use: up to 0x7F
-
-  // For use by user custom CompressionManagers
-  kCustomCompression80 = 0x80,
-  kCustomCompression81 = 0x81,
-  kCustomCompression82 = 0x82,
-  kCustomCompression83 = 0x83,
-  kCustomCompression84 = 0x84,
-  kCustomCompression85 = 0x85,
-  kCustomCompression86 = 0x86,
-  kCustomCompression87 = 0x87,
-  kCustomCompression88 = 0x88,
-  kCustomCompression89 = 0x89,
-  kCustomCompression8A = 0x8A,
-  kCustomCompression8B = 0x8B,
-  kCustomCompression8C = 0x8C,
-  kCustomCompression8D = 0x8D,
-  kCustomCompression8E = 0x8E,
-  kCustomCompression8F = 0x8F,
-  kCustomCompression90 = 0x90,
-  kCustomCompression91 = 0x91,
-  kCustomCompression92 = 0x92,
-  kCustomCompression93 = 0x93,
-  kCustomCompression94 = 0x94,
-  kCustomCompression95 = 0x95,
-  kCustomCompression96 = 0x96,
-  kCustomCompression97 = 0x97,
-  kCustomCompression98 = 0x98,
-  kCustomCompression99 = 0x99,
-  kCustomCompression9A = 0x9A,
-  kCustomCompression9B = 0x9B,
-  kCustomCompression9C = 0x9C,
-  kCustomCompression9D = 0x9D,
-  kCustomCompression9E = 0x9E,
-  kCustomCompression9F = 0x9F,
-  kCustomCompressionA0 = 0xA0,
-  kCustomCompressionA1 = 0xA1,
-  kCustomCompressionA2 = 0xA2,
-  kCustomCompressionA3 = 0xA3,
-  kCustomCompressionA4 = 0xA4,
-  kCustomCompressionA5 = 0xA5,
-  kCustomCompressionA6 = 0xA6,
-  kCustomCompressionA7 = 0xA7,
-  kCustomCompressionA8 = 0xA8,
-  kCustomCompressionA9 = 0xA9,
-  kCustomCompressionAA = 0xAA,
-  kCustomCompressionAB = 0xAB,
-  kCustomCompressionAC = 0xAC,
-  kCustomCompressionAD = 0xAD,
-  kCustomCompressionAE = 0xAE,
-  kCustomCompressionAF = 0xAF,
-  kCustomCompressionB0 = 0xB0,
-  kCustomCompressionB1 = 0xB1,
-  kCustomCompressionB2 = 0xB2,
-  kCustomCompressionB3 = 0xB3,
-  kCustomCompressionB4 = 0xB4,
-  kCustomCompressionB5 = 0xB5,
-  kCustomCompressionB6 = 0xB6,
-  kCustomCompressionB7 = 0xB7,
-  kCustomCompressionB8 = 0xB8,
-  kCustomCompressionB9 = 0xB9,
-  kCustomCompressionBA = 0xBA,
-  kCustomCompressionBB = 0xBB,
-  kCustomCompressionBC = 0xBC,
-  kCustomCompressionBD = 0xBD,
-  kCustomCompressionBE = 0xBE,
-  kCustomCompressionBF = 0xBF,
-  kCustomCompressionC0 = 0xC0,
-  kCustomCompressionC1 = 0xC1,
-  kCustomCompressionC2 = 0xC2,
-  kCustomCompressionC3 = 0xC3,
-  kCustomCompressionC4 = 0xC4,
-  kCustomCompressionC5 = 0xC5,
-  kCustomCompressionC6 = 0xC6,
-  kCustomCompressionC7 = 0xC7,
-  kCustomCompressionC8 = 0xC8,
-  kCustomCompressionC9 = 0xC9,
-  kCustomCompressionCA = 0xCA,
-  kCustomCompressionCB = 0xCB,
-  kCustomCompressionCC = 0xCC,
-  kCustomCompressionCD = 0xCD,
-  kCustomCompressionCE = 0xCE,
-  kCustomCompressionCF = 0xCF,
-  kCustomCompressionD0 = 0xD0,
-  kCustomCompressionD1 = 0xD1,
-  kCustomCompressionD2 = 0xD2,
-  kCustomCompressionD3 = 0xD3,
-  kCustomCompressionD4 = 0xD4,
-  kCustomCompressionD5 = 0xD5,
-  kCustomCompressionD6 = 0xD6,
-  kCustomCompressionD7 = 0xD7,
-  kCustomCompressionD8 = 0xD8,
-  kCustomCompressionD9 = 0xD9,
-  kCustomCompressionDA = 0xDA,
-  kCustomCompressionDB = 0xDB,
-  kCustomCompressionDC = 0xDC,
-  kCustomCompressionDD = 0xDD,
-  kCustomCompressionDE = 0xDE,
-  kCustomCompressionDF = 0xDF,
-  kCustomCompressionE0 = 0xE0,
-  kCustomCompressionE1 = 0xE1,
-  kCustomCompressionE2 = 0xE2,
-  kCustomCompressionE3 = 0xE3,
-  kCustomCompressionE4 = 0xE4,
-  kCustomCompressionE5 = 0xE5,
-  kCustomCompressionE6 = 0xE6,
-  kCustomCompressionE7 = 0xE7,
-  kCustomCompressionE8 = 0xE8,
-  kCustomCompressionE9 = 0xE9,
-  kCustomCompressionEA = 0xEA,
-  kCustomCompressionEB = 0xEB,
-  kCustomCompressionEC = 0xEC,
-  kCustomCompressionED = 0xED,
-  kCustomCompressionEE = 0xEE,
-  kCustomCompressionEF = 0xEF,
-  kCustomCompressionF0 = 0xF0,
-  kCustomCompressionF1 = 0xF1,
-  kCustomCompressionF2 = 0xF2,
-  kCustomCompressionF3 = 0xF3,
-  kCustomCompressionF4 = 0xF4,
-  kCustomCompressionF5 = 0xF5,
-  kCustomCompressionF6 = 0xF6,
-  kCustomCompressionF7 = 0xF7,
-  kCustomCompressionF8 = 0xF8,
-  kCustomCompressionF9 = 0xF9,
-  kCustomCompressionFA = 0xFA,
-  kCustomCompressionFB = 0xFB,
-  kCustomCompressionFC = 0xFC,
-  kCustomCompressionFD = 0xFD,
-  kCustomCompressionFE = 0xFE,
+  kNoCompression = 0x0,
+  kSnappyCompression = 0x1,
+  kZlibCompression = 0x2,
+  kBZip2Compression = 0x3,
+  kLZ4Compression = 0x4,
+  kLZ4HCCompression = 0x5,
+  kXpressCompression = 0x6,
+  kZSTD = 0x7,
 
   // kDisableCompressionOption is used to disable some compression options.
   kDisableCompressionOption = 0xff,
@@ -312,7 +180,4 @@ struct CompressionOptions {
 #endif
 };
 
-// See advanced_compression.h
-class CompressionManager;
-
 }  // namespace ROCKSDB_NAMESPACE