rocksdb/db
Yi Wu 5d4fddfa52 WritePrepared: Fix visible key compacted out by compaction (#4883)
Summary:
With WritePrepared transaction, flush/compaction can contain uncommitted keys, and those keys can get committed during compaction. If a snapshot is taken before the key is committed, it should not see the key. On the other hand, compaction grab the list of snapshots at its beginning, and only consider those snapshots to dedup keys. Consider the case:
```
seq = 1: put "foo" = "bar"
seq = 2: transaction T: delete "foo", prepare
seq = 3: compaction start
seq = 4: take snapshot S
seq = 5: transaction T: commit.
...
seq = N: compaction iterator reached key "foo".
```
When compaction start, the list of snapshot is empty. Compaction doesn't take snapshot S into account. When it reached "foo", transaction T is committed. Compaction may think the value "foo=bar" is not visible by any snapshot (which is wrong), and compact the value out.

The fix is to explicitly take a snapshot before compaction grabbing the list of snapshots. Compaction will then has to keep keys visible to this snapshot.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4883

Differential Revision: D13668775

Pulled By: maysamyabandeh

fbshipit-source-id: 1cab9615f94b7d3e8522cc3d44c3a14c7d4720e4
2019-01-15 21:34:38 -08:00
..
builder.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
builder.h Add compaction logic to RangeDelAggregatorV2 (#4758) 2018-12-17 13:20:51 -08:00
c.cc Support setting options on column families via C bindings (#4785) 2018-12-17 13:52:12 -08:00
c_test.c Get `CompactionJobInfo` from CompactFiles 2018-12-13 14:21:24 -08:00
column_family.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
column_family.h Lock free MultiGet (#4754) 2019-01-02 11:42:54 -08:00
column_family_test.cc Fix spelling errors (#4827) 2019-01-02 11:17:57 -08:00
compact_files_test.cc Get `CompactionJobInfo` from CompactFiles 2018-12-13 14:21:24 -08:00
compacted_db_impl.cc move dump stats to a separate thread (#4382) 2018-10-08 22:54:43 -07:00
compacted_db_impl.h Enable checkpoint of read-only db (#4681) 2018-12-07 17:06:02 -08:00
compaction.cc Truncate range tombstones by leveraging InternalKeys (#4432) 2018-10-09 15:19:38 -07:00
compaction.h Truncate range tombstones by leveraging InternalKeys (#4432) 2018-10-09 15:19:38 -07:00
compaction_iteration_stats.h add counter for deletion dropping optimization 2017-08-19 14:10:08 -07:00
compaction_iterator.cc WritePrepared: Fix visible key compacted out by compaction (#4883) 2019-01-15 21:34:38 -08:00
compaction_iterator.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
compaction_iterator_test.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
compaction_job.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
compaction_job.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
compaction_job_stats_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
compaction_job_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
compaction_picker.cc Move FIFOCompactionPicker to a separate file (#4724) 2018-11-29 16:04:52 -08:00
compaction_picker.h Move FIFOCompactionPicker to a separate file (#4724) 2018-11-29 16:04:52 -08:00
compaction_picker_fifo.cc Move FIFOCompactionPicker to a separate file (#4724) 2018-11-29 16:04:52 -08:00
compaction_picker_fifo.h Move FIFOCompactionPicker to a separate file (#4724) 2018-11-29 16:04:52 -08:00
compaction_picker_test.cc Move FIFOCompactionPicker to a separate file (#4724) 2018-11-29 16:04:52 -08:00
compaction_picker_universal.cc Remove random writes from SST file ingestion (#4172) 2018-07-27 16:12:23 -07:00
compaction_picker_universal.h Delete triggered compaction for universal style 2018-05-29 15:44:34 -07:00
comparator_db_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
convenience.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
corruption_test.cc fix DeleteRange memory leak for mmap and block cache (#4810) 2018-12-20 21:59:49 -08:00
cuckoo_table_db_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
db_basic_test.cc Lock free MultiGet (#4754) 2019-01-02 11:42:54 -08:00
db_blob_index_test.cc fix lite build 2017-10-17 08:57:09 -07:00
db_block_cache_test.cc Fix spelling errors (#4827) 2019-01-02 11:17:57 -08:00
db_bloom_filter_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
db_compaction_filter_test.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
db_compaction_test.cc Preload some files even if options.max_open_files (#3340) 2018-12-28 18:02:28 -08:00
db_dynamic_level_test.cc Fix flaky DBDynamicLevelTest.DynamicLevelMaxBytesBase2 (#4668) 2018-11-12 16:42:16 -08:00
db_encryption_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
db_filesnapshot.cc Remove redundant member var and set options (#4631) 2018-11-12 12:24:26 -08:00
db_flush_test.cc Improve flushing multiple column families (#4708) 2018-12-13 15:12:40 -08:00
db_impl.cc WritePrepared: Fix visible key compacted out by compaction (#4883) 2019-01-15 21:34:38 -08:00
db_impl.h WritePrepared: Fix visible key compacted out by compaction (#4883) 2019-01-15 21:34:38 -08:00
db_impl_compaction_flush.cc WritePrepared: Fix visible key compacted out by compaction (#4883) 2019-01-15 21:34:38 -08:00
db_impl_debug.cc Enable atomic flush (#4023) 2018-10-26 15:08:43 -07:00
db_impl_experimental.cc Update JobContext. (#3949) 2018-08-03 17:42:34 -07:00
db_impl_files.cc Fix #3840: only `SyncClosedLogs` for multiple CFs (#4460) 2018-11-13 11:32:16 -08:00
db_impl_open.cc Improve Error Message When wal_dir doesn't exist (#4874) 2019-01-15 16:46:04 -08:00
db_impl_readonly.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
db_impl_readonly.h Get `CompactionJobInfo` from CompactFiles 2018-12-13 14:21:24 -08:00
db_impl_write.cc Fix skip WAL for whole write_group when leader's callback fail (#4838) 2019-01-03 12:40:42 -08:00
db_info_dumper.cc avoid copying when iterating using range-based for (#4459) 2018-10-09 17:15:51 -07:00
db_info_dumper.h Change RocksDB License 2017-07-15 16:11:23 -07:00
db_inplace_update_test.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
db_io_failure_test.cc Disable DBIOFailureTest.NoSpaceCompactRange in LITE (#4596) 2018-10-29 14:36:31 -07:00
db_iter.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
db_iter.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
db_iter_stress_test.cc Move prefix_extractor to MutableCFOptions 2018-05-21 14:43:11 -07:00
db_iter_test.cc Fix regression bug of Prev() with upper bound (#3989) 2018-06-12 16:57:36 -07:00
db_iterator_test.cc Fix ticker stat for number files closed (#4703) 2018-11-21 18:31:34 -08:00
db_log_iter_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
db_memtable_test.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
db_merge_operator_test.cc WriteUnPrepared Txn: Disable seek to snapshot optimization (#3955) 2018-06-27 12:23:07 -07:00
db_options_test.cc move dump stats to a separate thread (#4382) 2018-10-08 22:54:43 -07:00
db_properties_test.cc fix accounting for range tombstones in TableProperties (#4841) 2019-01-02 15:08:53 -08:00
db_range_del_test.cc Fix point lookup on range tombstone sentinel endpoint (#4829) 2019-01-04 11:24:08 -08:00
db_sst_test.cc Try to fix DBSSTTest.RateLimitedDelete flakiness (#4840) 2019-01-03 11:05:19 -08:00
db_statistics_test.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
db_table_properties_test.cc Allow dynamic modification of window size and deletion trigger (#4403) 2018-09-20 15:15:28 -07:00
db_tailing_iter_test.cc Remove managed iterator 2018-07-17 14:43:18 -07:00
db_test.cc Get `CompactionJobInfo` from CompactFiles 2018-12-13 14:21:24 -08:00
db_test2.cc Remove duplicates from SnapshotList::GetAll (#4860) 2019-01-09 16:25:42 -08:00
db_test_util.cc Lock free MultiGet (#4754) 2019-01-02 11:42:54 -08:00
db_test_util.h Lock free MultiGet (#4754) 2019-01-02 11:42:54 -08:00
db_universal_compaction_test.cc Adapt three unit tests with newer compiler/libraries (#4562) 2018-10-24 08:17:56 -07:00
db_wal_test.cc Preload some files even if options.max_open_files (#3340) 2018-12-28 18:02:28 -08:00
db_write_test.cc Suppress tsan lock-order-inversion on FlushWAL 2018-05-14 21:13:35 -07:00
dbformat.cc types: add kEntryBlobIndex for TablePropertiesCollector (#4233) 2018-08-06 18:27:44 -07:00
dbformat.h s/CacheAllocator/MemoryAllocator/g (#4590) 2018-10-26 14:30:30 -07:00
dbformat_test.cc Relax VersionStorageInfo::GetOverlappingInputs check (#4050) 2018-07-13 17:42:38 -07:00
deletefile_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
error_handler.cc Fix typos in comments (#4456) 2018-10-04 20:46:50 -07:00
error_handler.h Fix typos in comments (#4456) 2018-10-04 20:46:50 -07:00
error_handler_test.cc Fix regression test failures introduced by PR #4164 (#4375) 2018-09-17 13:14:07 -07:00
event_helpers.cc Auto recovery from out of space errors (#4164) 2018-09-15 13:43:04 -07:00
event_helpers.h Auto recovery from out of space errors (#4164) 2018-09-15 13:43:04 -07:00
experimental.cc comment unused parameters to turn on -Wunused-parameter flag 2018-04-12 17:59:16 -07:00
external_sst_file_basic_test.cc Change directory where ExternalSSTFileBasicTest runs (#4766) 2018-12-11 10:21:37 -08:00
external_sst_file_ingestion_job.cc Fix typos in comments (#4456) 2018-10-04 20:46:50 -07:00
external_sst_file_ingestion_job.h Remove random writes from SST file ingestion (#4172) 2018-07-27 16:12:23 -07:00
external_sst_file_test.cc Try to fix ExternalSSTFileTest.IngestNonExistingFile flakines (#4625) 2018-11-02 17:26:35 -07:00
fault_injection_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
file_indexer.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
file_indexer.h Change RocksDB License 2017-07-15 16:11:23 -07:00
file_indexer_test.cc Comment out unused variables 2018-03-05 13:13:41 -08:00
filename_test.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
flush_job.cc Add compaction logic to RangeDelAggregatorV2 (#4758) 2018-12-17 13:20:51 -08:00
flush_job.h Add support to flush multiple CFs atomically (#4262) 2018-10-15 20:01:17 -07:00
flush_job_test.cc Remove duplicates from SnapshotList::GetAll (#4860) 2019-01-09 16:25:42 -08:00
flush_scheduler.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
flush_scheduler.h Change RocksDB License 2017-07-15 16:11:23 -07:00
forward_iterator.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
forward_iterator.h Comment out unused variables 2018-03-05 13:13:41 -08:00
forward_iterator_bench.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
internal_stats.cc Add DB property for SST files kept from deletion (#4618) 2018-11-05 20:24:40 -08:00
internal_stats.h Add DB property for SST files kept from deletion (#4618) 2018-11-05 20:24:40 -08:00
job_context.h WritePrepared: Fix visible key compacted out by compaction (#4883) 2019-01-15 21:34:38 -08:00
listener_test.cc Add listener to sample file io (#3933) 2018-10-12 18:36:11 -07:00
log_format.h Fix an inaccurate comment (#4315) 2018-08-24 18:13:20 -07:00
log_reader.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
log_reader.h Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
log_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
log_writer.cc Pass manual_wal_flush also to the first wal file 2018-05-14 10:57:56 -07:00
log_writer.h Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
logs_with_prep_tracker.cc Skip deleted WALs during recovery 2018-05-03 15:43:09 -07:00
logs_with_prep_tracker.h Skip deleted WALs during recovery 2018-05-03 15:43:09 -07:00
malloc_stats.cc Detect if Jemalloc is linked with the binary (#4844) 2019-01-03 16:30:12 -08:00
malloc_stats.h Change RocksDB License 2017-07-15 16:11:23 -07:00
manual_compaction_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
memtable.cc Change is_range_del_table_empty_ flag to atomic (#4801) 2018-12-19 17:21:14 -08:00
memtable.h Refactor atomic flush result installation to MANIFEST (#4791) 2019-01-03 20:56:24 -08:00
memtable_list.cc Refactor atomic flush result installation to MANIFEST (#4791) 2019-01-03 20:56:24 -08:00
memtable_list.h Refactor atomic flush result installation to MANIFEST (#4791) 2019-01-03 20:56:24 -08:00
memtable_list_test.cc Refactor atomic flush result installation to MANIFEST (#4791) 2019-01-03 20:56:24 -08:00
merge_context.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
merge_helper.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
merge_helper.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
merge_helper_test.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
merge_operator.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
merge_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
obsolete_files_test.cc Modify verification logic of ObsoleteOptionsFileTest (#4218) 2018-08-03 13:57:40 -07:00
options_file_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
perf_context_test.cc Add a new per level counter for block cache hit (#4796) 2018-12-21 13:20:05 -08:00
pinned_iterators_manager.h Change RocksDB License 2017-07-15 16:11:23 -07:00
plain_table_db_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
pre_release_callback.h Fix pre_release callback argument list. 2018-04-05 11:12:16 -07:00
prefix_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
range_del_aggregator.cc Remove stale TODO (#4800) 2018-12-19 15:45:37 -08:00
range_del_aggregator.h Fix unused member compile error 2018-12-18 14:28:42 -08:00
range_del_aggregator_bench.cc Fix Windows broken build error due to non-const override (#4798) 2018-12-19 13:29:51 -08:00
range_del_aggregator_test.cc Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
range_tombstone_fragmenter.cc Add compaction logic to RangeDelAggregatorV2 (#4758) 2018-12-17 13:20:51 -08:00
range_tombstone_fragmenter.h Add compaction logic to RangeDelAggregatorV2 (#4758) 2018-12-17 13:20:51 -08:00
range_tombstone_fragmenter_test.cc Prepare FragmentedRangeTombstoneIterator for use in compaction (#4740) 2018-12-11 12:10:48 -08:00
read_callback.h WriteUnPrepared Txn: Disable seek to snapshot optimization (#3955) 2018-06-27 12:23:07 -07:00
repair.cc Add compaction logic to RangeDelAggregatorV2 (#4758) 2018-12-17 13:20:51 -08:00
repair_test.cc Acquire lock on DB LOCK file before starting repair. (#4435) 2018-10-12 10:41:54 -07:00
snapshot_checker.h Add path to WritableFileWriter. (#4039) 2018-08-23 10:12:58 -07:00
snapshot_impl.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
snapshot_impl.h Remove duplicates from SnapshotList::GetAll (#4860) 2019-01-09 16:25:42 -08:00
table_cache.cc Introduce a CPU time counter in perf_context (#4741) 2018-12-20 12:03:44 -08:00
table_cache.h Preload some files even if options.max_open_files (#3340) 2018-12-28 18:02:28 -08:00
table_properties_collector.cc Promote rocksdb.{deleted.keys,merge.operands} to main table properties (#4594) 2018-10-30 15:34:27 -07:00
table_properties_collector.h Promote rocksdb.{deleted.keys,merge.operands} to main table properties (#4594) 2018-10-30 15:34:27 -07:00
table_properties_collector_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
transaction_log_impl.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
transaction_log_impl.h Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
version_builder.cc Preload some files even if options.max_open_files (#3340) 2018-12-28 18:02:28 -08:00
version_builder.h Preload some files even if options.max_open_files (#3340) 2018-12-28 18:02:28 -08:00
version_builder_test.cc Remove random writes from SST file ingestion (#4172) 2018-07-27 16:12:23 -07:00
version_edit.cc Fix spelling errors (#4827) 2019-01-02 11:17:57 -08:00
version_edit.h Update recovery code for version edits group commit. (#3945) 2018-08-20 14:58:00 -07:00
version_edit_test.cc Update recovery code for version edits group commit. (#3945) 2018-08-20 14:58:00 -07:00
version_set.cc Non-initial file preloading should always prefetch index and filter (#4852) 2019-01-08 12:47:34 -08:00
version_set.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
version_set_test.cc Refactor atomic flush result installation to MANIFEST (#4791) 2019-01-03 20:56:24 -08:00
wal_manager.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
wal_manager.h Fix memleak when DB::DeleteFile() 2018-01-11 18:57:33 -08:00
wal_manager_test.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
write_batch.cc Update all unique/shared_ptr instances to be qualified with namespace std (#4638) 2018-11-09 11:19:58 -08:00
write_batch_base.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
write_batch_internal.h WriteUnPrepared: Add new WAL marker kTypeBeginUnprepareXID (#4069) 2018-06-28 18:58:29 -07:00
write_batch_test.cc Clean up FragmentedRangeTombstoneList (#4692) 2018-11-28 15:29:02 -08:00
write_callback.h Change RocksDB License 2017-07-15 16:11:23 -07:00
write_callback_test.cc Per-thread unique test db names (#4135) 2018-07-13 17:27:39 -07:00
write_controller.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
write_controller.h Change RocksDB License 2017-07-15 16:11:23 -07:00
write_controller_test.cc Change RocksDB License 2017-07-15 16:11:23 -07:00
write_thread.cc Add more sync point to fix flaky test GroupCommitTest 2018-11-07 14:07:53 -08:00
write_thread.h Fix skip WAL for whole write_group when leader's callback fail (#4838) 2019-01-03 12:40:42 -08:00