Merge branch 'main' into verify_flushed_data_recovery

.github/workflows/pr-jobs.yml

@@ -90,6 +90,9 @@ jobs:
     container:
       image: zjay437/rocksdb:0.6
       options: --shm-size=16gb
+    env:
+      CC: gcc-10
+      CXX: g++-10
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
@@ -104,38 +107,47 @@ jobs:
     container:
       image: zjay437/rocksdb:0.6
       options: --shm-size=16gb
+    env:
+      CC: gcc-10
+      CXX: g++-10
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
     - uses: "./.github/actions/setup-folly"
     - run: "(mkdir build && cd build && cmake -DUSE_FOLLY_LITE=1 -DWITH_GFLAGS=1 .. && make V=1 -j20)"
     - uses: "./.github/actions/post-steps"
-  build-linux-gcc-7-with-folly:
+  build-linux-make-with-folly:
     if: ${{ github.repository_owner == 'facebook' }}
     runs-on:
       labels: 16-core-ubuntu
     container:
       image: zjay437/rocksdb:0.6
       options: --shm-size=16gb
+    env:
+      CC: gcc-10
+      CXX: g++-10
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
     - uses: "./.github/actions/setup-folly"
     - uses: "./.github/actions/build-folly"
-    - run: USE_FOLLY=1 LIB_MODE=static CC=gcc-7 CXX=g++-7 V=1 make -j32 check
+    - run: USE_FOLLY=1 LIB_MODE=static V=1 make -j32 check
     - uses: "./.github/actions/post-steps"
-  build-linux-gcc-7-with-folly-lite-no-test:
+  build-linux-make-with-folly-lite-no-test:
     if: ${{ github.repository_owner == 'facebook' }}
     runs-on:
       labels: 16-core-ubuntu
     container:
       image: zjay437/rocksdb:0.6
       options: --shm-size=16gb
+    env:
+      CC: gcc-10
+      CXX: g++-10
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
     - uses: "./.github/actions/setup-folly"
-    - run: USE_FOLLY_LITE=1 CC=gcc-7 CXX=g++-7 V=1 make -j32 all
+    - run: USE_FOLLY_LITE=1 V=1 make -j32 all
     - uses: "./.github/actions/post-steps"
   build-linux-cmake-with-folly-coroutines:
     if: ${{ github.repository_owner == 'facebook' }}

CMakeLists.txt

@@ -617,7 +617,7 @@ if(USE_FOLLY)
     FMT_INST_PATH)
     exec_program(ls ARGS -d ${FOLLY_INST_PATH}/../gflags* OUTPUT_VARIABLE
     GFLAGS_INST_PATH)
-    set(Boost_DIR ${BOOST_INST_PATH}/lib/cmake/Boost-1.78.0)
+    set(Boost_DIR ${BOOST_INST_PATH}/lib/cmake/Boost-1.83.0)
     if(EXISTS ${FMT_INST_PATH}/lib64)
       set(fmt_DIR ${FMT_INST_PATH}/lib64/cmake/fmt)
     else()
@@ -1052,13 +1052,20 @@ if(USE_FOLLY_LITE)
   list(APPEND SOURCES
     third-party/folly/folly/container/detail/F14Table.cpp
     third-party/folly/folly/detail/Futex.cpp
+    third-party/folly/folly/lang/Exception.cpp
     third-party/folly/folly/lang/SafeAssert.cpp
     third-party/folly/folly/lang/ToAscii.cpp
     third-party/folly/folly/ScopeGuard.cpp
     third-party/folly/folly/synchronization/AtomicNotification.cpp
     third-party/folly/folly/synchronization/DistributedMutex.cpp
     third-party/folly/folly/synchronization/ParkingLot.cpp)
   include_directories(${PROJECT_SOURCE_DIR}/third-party/folly)
+  exec_program(python3 ${PROJECT_SOURCE_DIR}/third-party/folly ARGS
+  build/fbcode_builder/getdeps.py show-source-dir boost OUTPUT_VARIABLE
+  BOOST_SOURCE_PATH)
+  exec_program(ls ARGS -d ${BOOST_SOURCE_PATH}/boost* OUTPUT_VARIABLE
+  BOOST_INCLUDE_DIR)
+  include_directories(${BOOST_INCLUDE_DIR})
   add_definitions(-DUSE_FOLLY -DFOLLY_NO_CONFIG)
   list(APPEND THIRDPARTY_LIBS glog)
 endif()

HISTORY.md

@@ -1,6 +1,31 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
+## 9.4.0 (06/23/2024)
+### New Features
+* Added a `CompactForTieringCollectorFactory` to auto trigger compaction for tiering use case.
+* Optimistic transactions and pessimistic transactions with the WriteCommitted policy now support the `GetEntityForUpdate` API.
+* Added a new "count" command to the ldb repl shell. By default, it prints a count of keys in the database from start to end. The options --from=<key> and/or --to=<key> can be specified to limit the range.
+* Add `rocksdb_writebatch_update_timestamps`, `rocksdb_writebatch_wi_update_timestamps` in C API.
+* Add `rocksdb_iter_refresh` in C API.
+* Add `rocksdb_writebatch_create_with_params`, `rocksdb_writebatch_wi_create_with_params` to create WB and WBWI with all options in C API
+
+### Public API Changes
+* Deprecated names `LogFile` and `VectorLogPtr` in favor of new names `WalFile` and `VectorWalPtr`.
+* Introduce a new universal compaction option CompactionOptionsUniversal::max_read_amp which allows user to define the limit on the number of sorted runs separately from the trigger for compaction (`level0_file_num_compaction_trigger`) #12477.
+
+### Behavior Changes
+* Inactive WALs are immediately closed upon being fully sync-ed rather than in a background thread. This is to ensure LinkFile() is not called on files still open for write, which might not be supported by some FileSystem implementations. This should not be a performance issue, but an opt-out is available with with new DB option `background_close_inactive_wals`.
+
+### Bug Fixes
+* Fix a rare case in which a hard-linked WAL in a Checkpoint is not fully synced (so might lose data on power loss).
+* Fixed the output of the `ldb dump_wal` command for `PutEntity` records so it prints the key and correctly resets the hexadecimal formatting flag after printing the wide-column entity.
+* Fixed an issue where `PutEntity` records were handled incorrectly while rebuilding transactions during recovery.
+* Various read operations could ignore various ReadOptions that might be relevant. Fixed many such cases, which can result in behavior change but a better reflection of specified options.
+
+### Performance Improvements
+* Improved write throughput to memtable when there's a large number of concurrent writers and allow_concurrent_memtable_write=true(#12545)
+
 ## 9.3.0 (05/17/2024)
 ### New Features
 * Optimistic transactions and pessimistic transactions with the WriteCommitted policy now support the `GetEntity` API.

Makefile

@@ -103,6 +103,7 @@ dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
                   export LIB_MODE="$(LIB_MODE)"; \
 		  export ROCKSDB_CXX_STANDARD="$(ROCKSDB_CXX_STANDARD)"; \
 		  export USE_FOLLY="$(USE_FOLLY)"; \
+		  export USE_FOLLY_LITE="$(USE_FOLLY_LITE)"; \
                   "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
 # this file is generated by the previous line to set build flags and sources
 include make_config.mk
@@ -500,6 +501,17 @@ endif
 ifeq ($(USE_FOLLY_LITE),1)
 	# Path to the Folly source code and include files
 	FOLLY_DIR = ./third-party/folly
+ifneq ($(strip $(BOOST_SOURCE_PATH)),)
+	BOOST_INCLUDE = $(shell (ls -d $(BOOST_SOURCE_PATH)/boost*/))
+	# AIX: pre-defined system headers are surrounded by an extern "C" block
+	ifeq ($(PLATFORM), OS_AIX)
+		PLATFORM_CCFLAGS += -I$(BOOST_INCLUDE)
+		PLATFORM_CXXFLAGS += -I$(BOOST_INCLUDE)
+	else
+		PLATFORM_CCFLAGS += -isystem $(BOOST_INCLUDE)
+		PLATFORM_CXXFLAGS += -isystem $(BOOST_INCLUDE)
+	endif
+endif  # BOOST_SOURCE_PATH
 	# AIX: pre-defined system headers are surrounded by an extern "C" block
 	ifeq ($(PLATFORM), OS_AIX)
 		PLATFORM_CCFLAGS += -I$(FOLLY_DIR)
@@ -2472,14 +2484,13 @@ 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 beacd86d63cd71c904632262e6c36f60874d78ba
-	@# A hack to remove boost dependency.
-	@# NOTE: this hack is only needed if building using USE_FOLLY_LITE
-	perl -pi -e 's/^(#include <boost)/\/\/$$1/' third-party/folly/folly/functional/Invoke.h
+	cd third-party/folly && git reset --hard c48fdd205c1c291651749d532b8055fe822bba25
 	@# NOTE: this hack is required for clang in some cases
 	perl -pi -e 's/int rv = syscall/int rv = (int)syscall/' third-party/folly/folly/detail/Futex.cpp
 	@# NOTE: this hack is required for gcc in some cases
 	perl -pi -e 's/(__has_include.<experimental.memory_resource>.)/__cpp_rtti && $$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
 
 CXX_M_FLAGS = $(filter -m%, $(CXXFLAGS))
 
@@ -2491,8 +2502,6 @@ build_folly:
 		echo "Please run checkout_folly first"; \
 		false; \
 	fi
-	# Restore the original version of Invoke.h with boost dependency
-	cd third-party/folly && ${GIT_COMMAND} checkout folly/functional/Invoke.h
 	cd third-party/folly && \
 		CXXFLAGS=" $(CXX_M_FLAGS) -DHAVE_CXX11_ATOMIC " $(PYTHON) build/fbcode_builder/getdeps.py build --no-tests
 

build_tools/build_detect_platform

@@ -585,7 +585,7 @@ EOF
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbenchmark"
         fi
     fi
-    if test $USE_FOLLY; then
+    if test $USE_FOLLY || test $USE_FOLLY_LITE; then
         # Test whether libfolly library is installed
         $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
           #include <folly/synchronization/DistributedMutex.h>
@@ -751,6 +751,11 @@ if [ "$USE_FOLLY" ]; then
     FOLLY_PATH=`cd $FOLLY_DIR && $PYTHON build/fbcode_builder/getdeps.py show-inst-dir folly`
   fi
 fi
+if [ "$USE_FOLLY_LITE" ]; then
+  if [ "$FOLLY_DIR" ]; then
+    BOOST_SOURCE_PATH=`cd $FOLLY_DIR && $PYTHON build/fbcode_builder/getdeps.py show-source-dir boost`
+  fi
+fi
 
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"
@@ -792,6 +797,7 @@ echo "PROFILING_FLAGS=$PROFILING_FLAGS" >> "$OUTPUT"
 echo "FIND=$FIND" >> "$OUTPUT"
 echo "WATCH=$WATCH" >> "$OUTPUT"
 echo "FOLLY_PATH=$FOLLY_PATH" >> "$OUTPUT"
+echo "BOOST_SOURCE_PATH=$BOOST_SOURCE_PATH" >> "$OUTPUT"
 
 # This will enable some related identifiers for the preprocessor
 if test -n "$JEMALLOC"; then

db/arena_wrapped_db_iter.cc

@@ -138,10 +138,10 @@ Status ArenaWrappedDBIter::Refresh(const Snapshot* snapshot) {
             reinit_internal_iter();
             break;
           } else {
-            delete *memtable_range_tombstone_iter_;
-            *memtable_range_tombstone_iter_ = new TruncatedRangeDelIterator(
-                std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
-                &cfd->internal_comparator(), nullptr, nullptr);
+            *memtable_range_tombstone_iter_ =
+                std::make_unique<TruncatedRangeDelIterator>(
+                    std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
+                    &cfd->internal_comparator(), nullptr, nullptr);
           }
         }
         db_impl->ReturnAndCleanupSuperVersion(cfd, sv);

db/arena_wrapped_db_iter.h

@@ -55,7 +55,8 @@ class ArenaWrappedDBIter : public Iterator {
     db_iter_->SetIter(iter);
   }
 
-  void SetMemtableRangetombstoneIter(TruncatedRangeDelIterator** iter) {
+  void SetMemtableRangetombstoneIter(
+      std::unique_ptr<TruncatedRangeDelIterator>* iter) {
     memtable_range_tombstone_iter_ = iter;
   }
 
@@ -110,7 +111,8 @@ class ArenaWrappedDBIter : public Iterator {
   bool allow_refresh_ = true;
   // If this is nullptr, it means the mutable memtable does not contain range
   // tombstone when added under this DBIter.
-  TruncatedRangeDelIterator** memtable_range_tombstone_iter_ = nullptr;
+  std::unique_ptr<TruncatedRangeDelIterator>* memtable_range_tombstone_iter_ =
+      nullptr;
 };
 
 // Generate the arena wrapped iterator class.

db/db_impl/db_impl.cc

@@ -2064,19 +2064,19 @@ InternalIterator* DBImpl::NewInternalIterator(
       read_options, super_version->GetSeqnoToTimeMapping(), arena);
   Status s;
   if (!read_options.ignore_range_deletions) {
-    TruncatedRangeDelIterator* mem_tombstone_iter = nullptr;
+    std::unique_ptr<TruncatedRangeDelIterator> mem_tombstone_iter;
     auto range_del_iter = super_version->mem->NewRangeTombstoneIterator(
         read_options, sequence, false /* immutable_memtable */);
     if (range_del_iter == nullptr || range_del_iter->empty()) {
       delete range_del_iter;
     } else {
-      mem_tombstone_iter = new TruncatedRangeDelIterator(
+      mem_tombstone_iter = std::make_unique<TruncatedRangeDelIterator>(
           std::unique_ptr<FragmentedRangeTombstoneIterator>(range_del_iter),
           &cfd->ioptions()->internal_comparator, nullptr /* smallest */,
           nullptr /* largest */);
     }
-    merge_iter_builder.AddPointAndTombstoneIterator(mem_iter,
-                                                    mem_tombstone_iter);
+    merge_iter_builder.AddPointAndTombstoneIterator(
+        mem_iter, std::move(mem_tombstone_iter));
   } else {
     merge_iter_builder.AddIterator(mem_iter);
   }

db/db_impl/db_impl_write.cc

@@ -2263,14 +2263,15 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
     SequenceNumber seq = versions_->LastSequence();
     new_mem = cfd->ConstructNewMemtable(mutable_cf_options, seq);
     context->superversion_context.NewSuperVersion();
+
+    ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                   "[%s] New memtable created with log file: #%" PRIu64
+                   ". Immutable memtables: %d.\n",
+                   cfd->GetName().c_str(), new_log_number, num_imm_unflushed);
+    // There should be no concurrent write as the thread is at the front of
+    // writer queue
+    cfd->mem()->ConstructFragmentedRangeTombstones();
   }
-  ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                 "[%s] New memtable created with log file: #%" PRIu64
-                 ". Immutable memtables: %d.\n",
-                 cfd->GetName().c_str(), new_log_number, num_imm_unflushed);
-  // There should be no concurrent write as the thread is at the front of
-  // writer queue
-  cfd->mem()->ConstructFragmentedRangeTombstones();
 
   mutex_.Lock();
   if (recycle_log_number != 0) {

db/event_helpers.cc

@@ -228,15 +228,18 @@ void EventHelpers::NotifyOnErrorRecoveryEnd(
     InstrumentedMutex* db_mutex) {
   if (!listeners.empty()) {
     db_mutex->AssertHeld();
+    // Make copies before releasing mutex to avoid race.
+    Status old_bg_error_cp = old_bg_error;
+    Status new_bg_error_cp = new_bg_error;
     // release lock while notifying events
     db_mutex->Unlock();
     TEST_SYNC_POINT("NotifyOnErrorRecoveryEnd:MutexUnlocked:1");
     TEST_SYNC_POINT("NotifyOnErrorRecoveryEnd:MutexUnlocked:2");
     for (auto& listener : listeners) {
       BackgroundErrorRecoveryInfo info;
-      info.old_bg_error = old_bg_error;
-      info.new_bg_error = new_bg_error;
-      listener->OnErrorRecoveryCompleted(old_bg_error);
+      info.old_bg_error = old_bg_error_cp;
+      info.new_bg_error = new_bg_error_cp;
+      listener->OnErrorRecoveryCompleted(old_bg_error_cp);
       listener->OnErrorRecoveryEnd(info);
       info.old_bg_error.PermitUncheckedError();
       info.new_bg_error.PermitUncheckedError();

db/memtable.cc

@@ -618,8 +618,9 @@ FragmentedRangeTombstoneIterator* MemTable::NewRangeTombstoneIteratorInternal(
 }
 
 void MemTable::ConstructFragmentedRangeTombstones() {
-  assert(!IsFragmentedRangeTombstonesConstructed(false));
-  // There should be no concurrent Construction
+  // There should be no concurrent Construction.
+  // We could also check fragmented_range_tombstone_list_ to avoid repeate
+  // constructions. We just construct them here again to be safe.
   if (!is_range_del_table_empty_.load(std::memory_order_relaxed)) {
     // TODO: plumb Env::IOActivity, Env::IOPriority
     auto* unfragmented_iter = new MemTableIterator(

db/memtable.h

@@ -534,21 +534,21 @@ class MemTable {
   // Returns a heuristic flush decision
   bool ShouldFlushNow();
 
+  // Updates `fragmented_range_tombstone_list_` that will be used to serve reads
+  // when this memtable becomes an immutable memtable (in some
+  // MemtableListVersion::memlist_). Should be called when this memtable is
+  // about to become immutable. May be called multiple times since
+  // SwitchMemtable() may fail.
   void ConstructFragmentedRangeTombstones();
 
   // Returns whether a fragmented range tombstone list is already constructed
   // for this memtable. It should be constructed right before a memtable is
   // added to an immutable memtable list. Note that if a memtable does not have
-  // any range tombstone, then no range tombstone list will ever be constructed.
-  // @param allow_empty Specifies whether a memtable with no range tombstone is
-  // considered to have its fragmented range tombstone list constructed.
-  bool IsFragmentedRangeTombstonesConstructed(bool allow_empty = true) const {
-    if (allow_empty) {
-      return fragmented_range_tombstone_list_.get() != nullptr ||
-             is_range_del_table_empty_;
-    } else {
-      return fragmented_range_tombstone_list_.get() != nullptr;
-    }
+  // any range tombstone, then no range tombstone list will ever be constructed
+  // and true is returned in that case.
+  bool IsFragmentedRangeTombstonesConstructed() const {
+    return fragmented_range_tombstone_list_.get() != nullptr ||
+           is_range_del_table_empty_;
   }
 
   // Get the newest user-defined timestamp contained in this MemTable. Check

db/memtable_list.cc

@@ -235,19 +235,19 @@ void MemTableListVersion::AddIterators(
       SequenceNumber read_seq = options.snapshot != nullptr
                                     ? options.snapshot->GetSequenceNumber()
                                     : kMaxSequenceNumber;
-      TruncatedRangeDelIterator* mem_tombstone_iter = nullptr;
+      std::unique_ptr<TruncatedRangeDelIterator> mem_tombstone_iter;
       auto range_del_iter = m->NewRangeTombstoneIterator(
           options, read_seq, true /* immutale_memtable */);
       if (range_del_iter == nullptr || range_del_iter->empty()) {
         delete range_del_iter;
       } else {
-        mem_tombstone_iter = new TruncatedRangeDelIterator(
+        mem_tombstone_iter = std::make_unique<TruncatedRangeDelIterator>(
             std::unique_ptr<FragmentedRangeTombstoneIterator>(range_del_iter),
             &m->GetInternalKeyComparator(), nullptr /* smallest */,
             nullptr /* largest */);
       }
-      merge_iter_builder->AddPointAndTombstoneIterator(mem_iter,
-                                                       mem_tombstone_iter);
+      merge_iter_builder->AddPointAndTombstoneIterator(
+          mem_iter, std::move(mem_tombstone_iter));
     }
   }
 }

db/table_cache.cc

@@ -230,7 +230,7 @@ InternalIterator* TableCache::NewIterator(
     const InternalKey* smallest_compaction_key,
     const InternalKey* largest_compaction_key, bool allow_unprepared_value,
     uint8_t block_protection_bytes_per_key, const SequenceNumber* read_seqno,
-    TruncatedRangeDelIterator** range_del_iter) {
+    std::unique_ptr<TruncatedRangeDelIterator>* range_del_iter) {
   PERF_TIMER_GUARD(new_table_iterator_nanos);
 
   Status s;
@@ -285,7 +285,7 @@ InternalIterator* TableCache::NewIterator(
         delete new_range_del_iter;
         *range_del_iter = nullptr;
       } else {
-        *range_del_iter = new TruncatedRangeDelIterator(
+        *range_del_iter = std::make_unique<TruncatedRangeDelIterator>(
             std::unique_ptr<FragmentedRangeTombstoneIterator>(
                 new_range_del_iter),
             &icomparator, &file_meta.smallest, &file_meta.largest);