rocksdb/tools
Hui Xiao fc74abb436 Fix FIFO causing overlapping seqnos in L0 files due to overlapped seqnos between ingested files and memtable's (#10777)
Summary:
**Context:**
Same as https://github.com/facebook/rocksdb/pull/5958#issue-511150930 but apply the fix to FIFO Compaction case
Repro:
```
COERCE_CONTEXT_SWICH=1 make -j56 db_stress

./db_stress --acquire_snapshot_one_in=0 --adaptive_readahead=0 --allow_data_in_errors=True --async_io=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=18 --bottommost_compression_type=disable --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=1 --charge_table_reader=1 --checkpoint_one_in=0 --checksum_type=kCRC32c --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=0 --compact_range_one_in=1000 --compaction_pri=3 --open_files=-1 --compaction_style=2 --fifo_allow_compaction=1 --compaction_ttl=0 --compression_max_dict_buffer_bytes=8388607 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=zlib --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=/dev/shm/rocksdb_test0/rocksdb_crashtest_whitebox --db_write_buffer_size=8388608 --delpercent=4 --delrangepercent=1 --destroy_db_initially=1 --detect_filter_construct_corruption=0 --disable_wal=0 --enable_compaction_filter=0 --enable_pipelined_write=1 --fail_if_options_file_error=1 --file_checksum_impl=none --flush_one_in=1000 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=0 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=15 --index_type=3 --ingest_external_file_one_in=100 --initial_auto_readahead_size=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --log2_keys_per_lock=10 --long_running_snapshots=0 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=16384 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=100000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=1048576 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=4194304 --memtable_prefix_bloom_size_ratio=0.5 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=1 --memtablerep=skip_list --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --num_levels=1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=32 --open_write_fault_one_in=0 --ops_per_thread=200000 --optimize_filters_for_memory=0 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=1 --pause_background_one_in=0 --periodic_compaction_seconds=0 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --progress_reports=0 --read_fault_one_in=0 --readahead_size=16384 --readpercent=45 --recycle_log_file_num=1 --reopen=20 --ribbon_starting_level=999 --snapshot_hold_ops=1000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --subcompactions=2 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=3 --unpartitioned_pinning=0 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=1 --use_merge=0 --use_multiget=1 --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=0 --wal_compression=zstd --write_buffer_size=524288 --write_dbid_to_manifest=0 --writepercent=35

put or merge error: Corruption: force_consistency_checks(DEBUG): VersionBuilder: L0 file https://github.com/facebook/rocksdb/issues/479 with seqno 23711 29070 vs. file https://github.com/facebook/rocksdb/issues/482 with seqno 27138 29049
```

**Summary:**
FIFO only does intra-L0 compaction in the following four cases. For other cases, FIFO drops data instead of compacting on data, which is irrelevant to the overlapping seqno issue we are solving.
-  [FIFOCompactionPicker::PickSizeCompaction](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L155) when `total size < compaction_options_fifo.max_table_files_size` and `compaction_options_fifo.allow_compaction == true`
   - For this path, we simply reuse the fix in `FindIntraL0Compaction` https://github.com/facebook/rocksdb/pull/5958/files#diff-c261f77d6dd2134333c4a955c311cf4a196a08d3c2bb6ce24fd6801407877c89R56
   - This path was not stress-tested at all. Therefore we covered `fifo.allow_compaction` in stress test to surface the overlapping seqno issue we are fixing here.
- [FIFOCompactionPicker::PickCompactionToWarm](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L313) when `compaction_options_fifo.age_for_warm > 0`
  - For this path, we simply replicate the idea in https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and skip files of largest seqno greater than `earliest_mem_seqno`
  - This path was not stress-tested at all. However covering `age_for_warm` option worths a separate PR to deal with db stress compatibility. Therefore we manually tested this path for this PR
- [FIFOCompactionPicker::CompactRange](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L365) that ends up picking one of the above two compactions
- [CompactionPicker::CompactFiles](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker.cc#L378)
    - Since `SanitizeCompactionInputFiles()` will be called [before](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker.h#L111-L113) `CompactionPicker::CompactFiles` , we simply replicate the idea in https://github.com/facebook/rocksdb/pull/5958#issue-511150930  in `SanitizeCompactionInputFiles()`. To simplify implementation, we return `Stats::Abort()` on encountering seqno-overlapped file when doing compaction to L0 instead of skipping the file and proceed with the compaction.

Some additional clean-up included in this PR:
- Renamed `earliest_memtable_seqno` to `earliest_mem_seqno` for consistent naming
- Added comment about `earliest_memtable_seqno` in related APIs
- Made parameter `earliest_memtable_seqno` constant and required

Pull Request resolved: https://github.com/facebook/rocksdb/pull/10777

Test Plan:
- make check
- New unit test `TEST_P(DBCompactionTestFIFOCheckConsistencyWithParam, FlushAfterIntraL0CompactionWithIngestedFile)`corresponding to the above 4 cases, which will fail accordingly without the fix
- Regular CI stress run on this PR + stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761  and on FIFO compaction only

Reviewed By: ajkr

Differential Revision: D40090485

Pulled By: hx235

fbshipit-source-id: 52624186952ee7109117788741aeeac86b624a4f
2022-10-25 10:39:58 -07:00
..
advisor Fix lint issues after enable BLACK (#10717) 2022-09-21 13:37:51 -07:00
block_cache_analyzer Refactor block cache tracing APIs (#10811) 2022-10-21 12:15:35 -07:00
dump Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
analyze_txn_stress_test.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
auto_sanity_test.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
backup_db.sh Revamp check_format_compatible.sh (#8012) 2021-03-02 11:42:27 -08:00
benchmark.sh Fix file modes (#10815) 2022-10-13 09:00:37 -07:00
benchmark_ci.py Enable BLACK for internal_repo_rocksdb (#10710) 2022-09-20 17:47:52 -07:00
benchmark_compare.sh Fix file modes (#10815) 2022-10-13 09:00:37 -07:00
benchmark_leveldb.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
blob_dump.cc Remove using namespace (#9369) 2022-01-12 09:31:12 -08:00
check_all_python.py Enable BLACK for internal_repo_rocksdb (#10710) 2022-09-20 17:47:52 -07:00
check_format_compatible.sh Update version.h, HISTORY.md and add branches to compatibility check (#10846) 2022-10-23 19:42:06 -07:00
CMakeLists.txt Mark dependencies as PRIVATE and fix missing dependencies in tools. (#6790) 2020-05-12 21:07:55 -07:00
db_bench.cc Add (& fix) some simple source code checks (#8821) 2021-09-07 21:19:27 -07:00
db_bench_tool.cc Enable preclude_last_level_data_seconds in stress test (#10824) 2022-10-16 09:28:43 -07:00
db_bench_tool_test.cc Print stack traces on frozen tests in CI (#10828) 2022-10-18 00:35:35 -07:00
db_crashtest.py Fix FIFO causing overlapping seqnos in L0 files due to overlapped seqnos between ingested files and memtable's (#10777) 2022-10-25 10:39:58 -07:00
db_repl_stress.cc Remove using namespace (#9369) 2022-01-12 09:31:12 -08:00
db_sanity_test.cc Migrate to docker for CI run (#10496) 2022-08-10 17:34:38 -07:00
dbench_monitor Fix /bin/bash shebangs 2017-08-03 15:56:46 -07:00
Dockerfile adding docker build script and dockerfile 2015-05-22 16:03:39 -07:00
generate_random_db.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
ingest_external_sst.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
io_tracer_parser.cc Add IO Tracer Parser (#7333) 2020-09-23 15:50:26 -07:00
io_tracer_parser_test.cc Print stack traces on frozen tests in CI (#10828) 2022-10-18 00:35:35 -07:00
io_tracer_parser_tool.cc Add request_id in IODebugContext. (#8045) 2021-04-01 13:14:51 -07:00
io_tracer_parser_tool.h Add IO Tracer Parser (#7333) 2020-09-23 15:50:26 -07:00
ldb.cc Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
ldb_cmd.cc Sync dir containing CURRENT after RenameFile on CURRENT as much as possible (#10573) 2022-08-29 17:35:21 -07:00
ldb_cmd_impl.h Support single delete in ldb (#9469) 2022-05-10 16:37:19 -07:00
ldb_cmd_test.cc Allow manifest fix-up without requiring prior state (#10796) 2022-10-10 17:59:17 -07:00
ldb_test.py Enable BLACK for internal_repo_rocksdb (#10710) 2022-09-20 17:47:52 -07:00
ldb_tool.cc Default try_load_options to true when DB is specified (#9937) 2022-05-04 08:49:46 -07:00
pflag Fix /bin/bash shebangs 2017-08-03 15:56:46 -07:00
reduce_levels_test.cc Print stack traces on frozen tests in CI (#10828) 2022-10-18 00:35:35 -07:00
regression_test.sh regression_test.sh: kill very old db_bench (and more) (#10441) 2022-08-02 09:16:17 -07:00
restore_db.sh Revamp check_format_compatible.sh (#8012) 2021-03-02 11:42:27 -08:00
rocksdb_dump_test.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
run_blob_bench.sh Support prepopulating/warming the blob cache (#10298) 2022-07-17 07:13:59 -07:00
run_flash_bench.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
run_leveldb.sh Add copyright headers per FB open-source checkup tool. (#5199) 2019-04-18 10:55:01 -07:00
sample-dump.dmp First version of rocksdb_dump and rocksdb_undump. 2015-06-19 16:24:36 -07:00
simulated_hybrid_file_system.cc Improve SimulatedHybridFileSystem (#9301) 2021-12-29 11:14:42 -08:00
simulated_hybrid_file_system.h Improve SimulatedHybridFileSystem (#9301) 2021-12-29 11:14:42 -08:00
sst_dump.cc Implement a new subcommand "identify" for sst_dump (#6943) 2020-06-08 13:58:28 -07:00
sst_dump_test.cc Use the comparator from the sst file table properties in sst_dump_tool (#9491) 2022-02-08 12:15:35 -08:00
sst_dump_tool.cc Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857) 2022-05-20 12:09:09 -07:00
trace_analyzer.cc Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
trace_analyzer_test.cc Print stack traces on frozen tests in CI (#10828) 2022-10-18 00:35:35 -07:00
trace_analyzer_tool.cc fix trace_analyzer_tool args column position (#10576) 2022-08-26 08:44:52 -07:00
trace_analyzer_tool.h Add commit marker with timestamp (#9266) 2021-12-10 11:05:35 -08:00
verify_random_db.sh Fix some bugs in verify_random_db.sh (#10112) 2022-06-03 16:35:13 -07:00
write_external_sst.sh Revamp check_format_compatible.sh (#8012) 2021-03-02 11:42:27 -08:00
write_stress.cc Add a SystemClock class to capture the time functions of an Env (#7858) 2021-01-25 22:09:11 -08:00
write_stress_runner.py Enable BLACK for internal_repo_rocksdb (#10710) 2022-09-20 17:47:52 -07:00