rocksdb/db/db_impl/db_impl_debug.cc
Hui Xiao 11cb6af6e5 Fix bug of prematurely excluded CF in atomic flush contains unflushed data that should've been included in the atomic flush (#11148)
Summary:
**Context:**
Atomic flush should guarantee recoverability of all data of seqno up to the max seqno of the flush. It achieves this by ensuring all such data are flushed by the time this atomic flush finishes through `SelectColumnFamiliesForAtomicFlush()`. However, our crash test exposed the following case where an excluded CF from an atomic flush contains unflushed data of seqno less than the max seqno of that atomic flush and loses its data with `WriteOptions::DisableWAL=true` in face of a crash right after the atomic flush finishes .
```
./db_stress --preserve_unverified_changes=1 --reopen=0 --acquire_snapshot_one_in=0 --adaptive_readahead=1 --allow_data_in_errors=True --async_io=1 --atomic_flush=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=15 --bottommost_compression_type=none --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_size=8388608 --cache_type=lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=0 --charge_table_reader=0 --checkpoint_one_in=0 --checksum_type=kXXH3 --clear_column_family_one_in=0 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=1 --compaction_ttl=100 --compression_max_dict_buffer_bytes=134217727 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=lz4hc --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=$db --db_write_buffer_size=1048576 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_wal=1 --enable_compaction_filter=0 --enable_pipelined_write=0 --expected_values_dir=$exp --fail_if_options_file_error=0 --fifo_allow_compaction=0 --file_checksum_impl=none --flush_one_in=0 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=100 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=2 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=524288 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --long_running_snapshots=1 --manual_wal_flush_one_in=100 --mark_for_compaction_one_file_in=0 --max_auto_readahead_size=0 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=10000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=64 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_prefix_bloom_size_ratio=0.01 --memtable_protection_bytes_per_key=4 --memtable_whole_key_filtering=0 --memtablerep=skip_list --min_write_buffer_number_to_merge=2 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=-1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=100000000 --optimize_filters_for_memory=1 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=0 --periodic_compaction_seconds=100 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --preserve_internal_time_seconds=3600 --progress_reports=0 --read_fault_one_in=32 --readahead_size=16384 --readpercent=50 --recycle_log_file_num=0 --ribbon_starting_level=6 --secondary_cache_fault_one_in=0 --set_options_one_in=10000 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=1048576 --stats_dump_period_sec=10 --subcompactions=1 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=0 --unpartitioned_pinning=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=0 --use_multiget=1 --use_put_entity_one_in=0 --user_timestamp_size=0 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=0 --verify_db_one_in=1000 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=524288 --wal_compression=none --write_buffer_size=524288 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=30 &
    pid=$!
    sleep 0.2
    sleep 10
    kill $pid
    sleep 0.2
./db_stress --ops_per_thread=1 --preserve_unverified_changes=1 --reopen=0 --acquire_snapshot_one_in=0 --adaptive_readahead=1 --allow_data_in_errors=True --async_io=1 --atomic_flush=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=15 --bottommost_compression_type=none --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_size=8388608 --cache_type=lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=0 --charge_table_reader=0 --checkpoint_one_in=0 --checksum_type=kXXH3 --clear_column_family_one_in=0 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=1 --compaction_ttl=100 --compression_max_dict_buffer_bytes=134217727 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=lz4hc --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=$db --db_write_buffer_size=1048576 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_wal=1 --enable_compaction_filter=0 --enable_pipelined_write=0 --expected_values_dir=$exp --fail_if_options_file_error=0 --fifo_allow_compaction=0 --file_checksum_impl=none --flush_one_in=0 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=100 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=2 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=524288 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --long_running_snapshots=1 --manual_wal_flush_one_in=100 --mark_for_compaction_one_file_in=0 --max_auto_readahead_size=0 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=10000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=64 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_prefix_bloom_size_ratio=0.01 --memtable_protection_bytes_per_key=4 --memtable_whole_key_filtering=0 --memtablerep=skip_list --min_write_buffer_number_to_merge=2 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=-1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=100000000 --optimize_filters_for_memory=1 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=0 --periodic_compaction_seconds=100 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --preserve_internal_time_seconds=3600 --progress_reports=0 --read_fault_one_in=32 --readahead_size=16384 --readpercent=50 --recycle_log_file_num=0 --ribbon_starting_level=6 --secondary_cache_fault_one_in=0 --set_options_one_in=10000 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=1048576 --stats_dump_period_sec=10 --subcompactions=1 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=0 --unpartitioned_pinning=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=0 --use_multiget=1 --use_put_entity_one_in=0 --user_timestamp_size=0 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=0 --verify_db_one_in=1000 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=524288 --wal_compression=none --write_buffer_size=524288 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=30 &
    pid=$!
    sleep 0.2
    sleep 40
    kill $pid
    sleep 0.2

Verification failed for column family 6 key 0000000000000239000000000000012B0000000000000138 (56622): value_from_db: , value_from_expected: 4A6331754E4F4C4D42434041464744455A5B58595E5F5C5D5253505156575455, msg: Value not found: NotFound:
Crash-recovery verification failed :(
No writes or ops?
Verification failed :(
```

The bug is due to the following:
- When atomic flush is used, an empty CF is legally [excluded](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_filesnapshot.cc#L39) in `SelectColumnFamiliesForAtomicFlush` as the first step of `DBImpl::FlushForGetLiveFiles` before [passing](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_filesnapshot.cc#L42) the included CFDs to `AtomicFlushMemTables`.
- But [later](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_impl/db_impl_compaction_flush.cc#L2133) in `AtomicFlushMemTables`, `WaitUntilFlushWouldNotStallWrites` will [release the db mutex](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_impl/db_impl_compaction_flush.cc#L2403), during which data@seqno N can be inserted into the excluded CF and data@seqno M can be inserted into one of the included CFs, where M > N.
- However, data@seqno N in an already-excluded CF is thus excluded from this atomic flush while we seqno N is less than seqno M.

**Summary:**
- Replace `SelectColumnFamiliesForAtomicFlush()`-before-`AtomicFlushMemTables()` with `SelectColumnFamiliesForAtomicFlush()`-after-wait-within-`AtomicFlushMemTables()` so we ensure no write affecting the recoverability of this atomic job (i.e, change to max seqno of this atomic flush or insertion of data with less seqno than the max seqno of the atomic flush to excluded CF) can happen after calling `SelectColumnFamiliesForAtomicFlush()`.
- For above, refactored and clarified comments on `SelectColumnFamiliesForAtomicFlush()` and `AtomicFlushMemTables()` for clearer semantics of passed-in CFDs to atomic-flush

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11148

Test Plan:
- New unit test failed before the fix and passes after
- Make check
- Rehearsal stress test

Reviewed By: ajkr

Differential Revision: D42799871

Pulled By: hx235

fbshipit-source-id: 13636b63e9c25c5895857afc36ea580d57f6d644
2023-03-14 16:53:20 -07:00

315 lines
9.1 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#ifndef NDEBUG
#include "db/column_family.h"
#include "db/db_impl/db_impl.h"
#include "db/error_handler.h"
#include "db/periodic_task_scheduler.h"
#include "monitoring/thread_status_updater.h"
#include "util/cast_util.h"
namespace ROCKSDB_NAMESPACE {
uint64_t DBImpl::TEST_GetLevel0TotalSize() {
InstrumentedMutexLock l(&mutex_);
return default_cf_handle_->cfd()->current()->storage_info()->NumLevelBytes(0);
}
Status DBImpl::TEST_SwitchWAL() {
WriteContext write_context;
InstrumentedMutexLock l(&mutex_);
void* writer = TEST_BeginWrite();
auto s = SwitchWAL(&write_context);
TEST_EndWrite(writer);
return s;
}
uint64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
ColumnFamilyHandle* column_family) {
ColumnFamilyData* cfd;
if (column_family == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
cfd = cfh->cfd();
}
InstrumentedMutexLock l(&mutex_);
return cfd->current()->storage_info()->MaxNextLevelOverlappingBytes();
}
void DBImpl::TEST_GetFilesMetaData(
ColumnFamilyHandle* column_family,
std::vector<std::vector<FileMetaData>>* metadata,
std::vector<std::shared_ptr<BlobFileMetaData>>* blob_metadata) {
assert(metadata);
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
assert(cfh);
auto cfd = cfh->cfd();
assert(cfd);
InstrumentedMutexLock l(&mutex_);
const auto* current = cfd->current();
assert(current);
const auto* vstorage = current->storage_info();
assert(vstorage);
metadata->resize(NumberLevels());
for (int level = 0; level < NumberLevels(); ++level) {
const std::vector<FileMetaData*>& files = vstorage->LevelFiles(level);
(*metadata)[level].clear();
(*metadata)[level].reserve(files.size());
for (const auto& f : files) {
(*metadata)[level].push_back(*f);
}
}
if (blob_metadata) {
*blob_metadata = vstorage->GetBlobFiles();
}
}
uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
return versions_->manifest_file_number();
}
uint64_t DBImpl::TEST_Current_Next_FileNo() {
return versions_->current_next_file_number();
}
Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
const Slice* end,
ColumnFamilyHandle* column_family,
bool disallow_trivial_move) {
ColumnFamilyData* cfd;
if (column_family == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
cfd = cfh->cfd();
}
int output_level =
(cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
cfd->ioptions()->compaction_style == kCompactionStyleFIFO)
? level
: level + 1;
return RunManualCompaction(
cfd, level, output_level, CompactRangeOptions(), begin, end, true,
disallow_trivial_move,
std::numeric_limits<uint64_t>::max() /*max_file_num_to_ignore*/,
"" /*trim_ts*/);
}
Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
WriteContext write_context;
InstrumentedMutexLock l(&mutex_);
if (cfd == nullptr) {
cfd = default_cf_handle_->cfd();
}
Status s;
void* writer = TEST_BeginWrite();
if (two_write_queues_) {
WriteThread::Writer nonmem_w;
nonmem_write_thread_.EnterUnbatched(&nonmem_w, &mutex_);
s = SwitchMemtable(cfd, &write_context);
nonmem_write_thread_.ExitUnbatched(&nonmem_w);
} else {
s = SwitchMemtable(cfd, &write_context);
}
TEST_EndWrite(writer);
return s;
}
Status DBImpl::TEST_FlushMemTable(bool wait, bool allow_write_stall,
ColumnFamilyHandle* cfh) {
FlushOptions fo;
fo.wait = wait;
fo.allow_write_stall = allow_write_stall;
ColumnFamilyData* cfd;
if (cfh == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfhi = static_cast_with_check<ColumnFamilyHandleImpl>(cfh);
cfd = cfhi->cfd();
}
return FlushMemTable(cfd, fo, FlushReason::kTest);
}
Status DBImpl::TEST_FlushMemTable(ColumnFamilyData* cfd,
const FlushOptions& flush_opts) {
return FlushMemTable(cfd, flush_opts, FlushReason::kTest);
}
Status DBImpl::TEST_AtomicFlushMemTables(
const autovector<ColumnFamilyData*>& provided_candidate_cfds,
const FlushOptions& flush_opts) {
return AtomicFlushMemTables(flush_opts, FlushReason::kTest,
provided_candidate_cfds);
}
Status DBImpl::TEST_WaitForBackgroundWork() {
InstrumentedMutexLock l(&mutex_);
WaitForBackgroundWork();
return error_handler_.GetBGError();
}
Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
ColumnFamilyData* cfd;
if (column_family == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
cfd = cfh->cfd();
}
return WaitForFlushMemTable(cfd, nullptr, false);
}
Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
// Wait until the compaction completes
return WaitForCompact(wait_unscheduled);
}
Status DBImpl::TEST_WaitForPurge() {
InstrumentedMutexLock l(&mutex_);
while (bg_purge_scheduled_ && error_handler_.GetBGError().ok()) {
bg_cv_.Wait();
}
return error_handler_.GetBGError();
}
Status DBImpl::TEST_GetBGError() {
InstrumentedMutexLock l(&mutex_);
return error_handler_.GetBGError();
}
void DBImpl::TEST_LockMutex() { mutex_.Lock(); }
void DBImpl::TEST_UnlockMutex() { mutex_.Unlock(); }
void DBImpl::TEST_SignalAllBgCv() { bg_cv_.SignalAll(); }
void* DBImpl::TEST_BeginWrite() {
auto w = new WriteThread::Writer();
write_thread_.EnterUnbatched(w, &mutex_);
return reinterpret_cast<void*>(w);
}
void DBImpl::TEST_EndWrite(void* w) {
auto writer = reinterpret_cast<WriteThread::Writer*>(w);
write_thread_.ExitUnbatched(writer);
delete writer;
}
size_t DBImpl::TEST_LogsToFreeSize() {
InstrumentedMutexLock l(&log_write_mutex_);
return logs_to_free_.size();
}
uint64_t DBImpl::TEST_LogfileNumber() {
InstrumentedMutexLock l(&mutex_);
return logfile_number_;
}
Status DBImpl::TEST_GetAllImmutableCFOptions(
std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map) {
std::vector<std::string> cf_names;
std::vector<const ImmutableCFOptions*> iopts;
{
InstrumentedMutexLock l(&mutex_);
for (auto cfd : *versions_->GetColumnFamilySet()) {
cf_names.push_back(cfd->GetName());
iopts.push_back(cfd->ioptions());
}
}
iopts_map->clear();
for (size_t i = 0; i < cf_names.size(); ++i) {
iopts_map->insert({cf_names[i], iopts[i]});
}
return Status::OK();
}
uint64_t DBImpl::TEST_FindMinLogContainingOutstandingPrep() {
return logs_with_prep_tracker_.FindMinLogContainingOutstandingPrep();
}
size_t DBImpl::TEST_PreparedSectionCompletedSize() {
return logs_with_prep_tracker_.TEST_PreparedSectionCompletedSize();
}
size_t DBImpl::TEST_LogsWithPrepSize() {
return logs_with_prep_tracker_.TEST_LogsWithPrepSize();
}
uint64_t DBImpl::TEST_FindMinPrepLogReferencedByMemTable() {
autovector<MemTable*> empty_list;
return FindMinPrepLogReferencedByMemTable(versions_.get(), empty_list);
}
Status DBImpl::TEST_GetLatestMutableCFOptions(
ColumnFamilyHandle* column_family, MutableCFOptions* mutable_cf_options) {
InstrumentedMutexLock l(&mutex_);
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
*mutable_cf_options = *cfh->cfd()->GetLatestMutableCFOptions();
return Status::OK();
}
int DBImpl::TEST_BGCompactionsAllowed() const {
InstrumentedMutexLock l(&mutex_);
return GetBGJobLimits().max_compactions;
}
int DBImpl::TEST_BGFlushesAllowed() const {
InstrumentedMutexLock l(&mutex_);
return GetBGJobLimits().max_flushes;
}
SequenceNumber DBImpl::TEST_GetLastVisibleSequence() const {
if (last_seq_same_as_publish_seq_) {
return versions_->LastSequence();
} else {
return versions_->LastAllocatedSequence();
}
}
size_t DBImpl::TEST_GetWalPreallocateBlockSize(
uint64_t write_buffer_size) const {
InstrumentedMutexLock l(&mutex_);
return GetWalPreallocateBlockSize(write_buffer_size);
}
void DBImpl::TEST_WaitForPeriodicTaskRun(std::function<void()> callback) const {
periodic_task_scheduler_.TEST_WaitForRun(callback);
}
const PeriodicTaskScheduler& DBImpl::TEST_GetPeriodicTaskScheduler() const {
return periodic_task_scheduler_;
}
SeqnoToTimeMapping DBImpl::TEST_GetSeqnoToTimeMapping() const {
InstrumentedMutexLock l(&mutex_);
return seqno_time_mapping_;
}
size_t DBImpl::TEST_EstimateInMemoryStatsHistorySize() const {
return EstimateInMemoryStatsHistorySize();
}
} // namespace ROCKSDB_NAMESPACE
#endif // NDEBUG