mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-29 18:33:58 +00:00
fc74abb436
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 |
||
|---|---|---|
| .. | ||
| blob | ||
| compaction | ||
| db_impl | ||
| wide | ||
| arena_wrapped_db_iter.cc | ||
| arena_wrapped_db_iter.h | ||
| builder.cc | ||
| builder.h | ||
| c.cc | ||
| c_test.c | ||
| column_family.cc | ||
| column_family.h | ||
| column_family_test.cc | ||
| compact_files_test.cc | ||
| comparator_db_test.cc | ||
| convenience.cc | ||
| corruption_test.cc | ||
| cuckoo_table_db_test.cc | ||
| db_basic_test.cc | ||
| db_block_cache_test.cc | ||
| db_bloom_filter_test.cc | ||
| db_compaction_filter_test.cc | ||
| db_compaction_test.cc | ||
| db_dynamic_level_test.cc | ||
| db_encryption_test.cc | ||
| db_filesnapshot.cc | ||
| db_flush_test.cc | ||
| db_info_dumper.cc | ||
| db_info_dumper.h | ||
| db_inplace_update_test.cc | ||
| db_io_failure_test.cc | ||
| db_iter.cc | ||
| db_iter.h | ||
| db_iter_stress_test.cc | ||
| db_iter_test.cc | ||
| db_iterator_test.cc | ||
| db_kv_checksum_test.cc | ||
| db_log_iter_test.cc | ||
| db_logical_block_size_cache_test.cc | ||
| db_memtable_test.cc | ||
| db_merge_operand_test.cc | ||
| db_merge_operator_test.cc | ||
| db_options_test.cc | ||
| db_properties_test.cc | ||
| db_range_del_test.cc | ||
| db_rate_limiter_test.cc | ||
| db_readonly_with_timestamp_test.cc | ||
| db_secondary_test.cc | ||
| db_sst_test.cc | ||
| db_statistics_test.cc | ||
| db_table_properties_test.cc | ||
| db_tailing_iter_test.cc | ||
| db_test.cc | ||
| db_test2.cc | ||
| db_test_util.cc | ||
| db_test_util.h | ||
| db_universal_compaction_test.cc | ||
| db_wal_test.cc | ||
| db_with_timestamp_basic_test.cc | ||
| db_with_timestamp_compaction_test.cc | ||
| db_with_timestamp_test_util.cc | ||
| db_with_timestamp_test_util.h | ||
| db_write_buffer_manager_test.cc | ||
| db_write_test.cc | ||
| dbformat.cc | ||
| dbformat.h | ||
| dbformat_test.cc | ||
| deletefile_test.cc | ||
| error_handler.cc | ||
| error_handler.h | ||
| error_handler_fs_test.cc | ||
| event_helpers.cc | ||
| event_helpers.h | ||
| experimental.cc | ||
| external_sst_file_basic_test.cc | ||
| external_sst_file_ingestion_job.cc | ||
| external_sst_file_ingestion_job.h | ||
| external_sst_file_test.cc | ||
| fault_injection_test.cc | ||
| file_indexer.cc | ||
| file_indexer.h | ||
| file_indexer_test.cc | ||
| filename_test.cc | ||
| flush_job.cc | ||
| flush_job.h | ||
| flush_job_test.cc | ||
| flush_scheduler.cc | ||
| flush_scheduler.h | ||
| forward_iterator.cc | ||
| forward_iterator.h | ||
| forward_iterator_bench.cc | ||
| history_trimming_iterator.h | ||
| import_column_family_job.cc | ||
| import_column_family_job.h | ||
| import_column_family_test.cc | ||
| internal_stats.cc | ||
| internal_stats.h | ||
| job_context.h | ||
| kv_checksum.h | ||
| listener_test.cc | ||
| log_format.h | ||
| log_reader.cc | ||
| log_reader.h | ||
| log_test.cc | ||
| log_writer.cc | ||
| log_writer.h | ||
| logs_with_prep_tracker.cc | ||
| logs_with_prep_tracker.h | ||
| lookup_key.h | ||
| malloc_stats.cc | ||
| malloc_stats.h | ||
| manual_compaction_test.cc | ||
| memtable.cc | ||
| memtable.h | ||
| memtable_list.cc | ||
| memtable_list.h | ||
| memtable_list_test.cc | ||
| merge_context.h | ||
| merge_helper.cc | ||
| merge_helper.h | ||
| merge_helper_test.cc | ||
| merge_operator.cc | ||
| merge_test.cc | ||
| obsolete_files_test.cc | ||
| options_file_test.cc | ||
| output_validator.cc | ||
| output_validator.h | ||
| perf_context_test.cc | ||
| periodic_task_scheduler.cc | ||
| periodic_task_scheduler.h | ||
| periodic_task_scheduler_test.cc | ||
| pinned_iterators_manager.h | ||
| plain_table_db_test.cc | ||
| post_memtable_callback.h | ||
| pre_release_callback.h | ||
| prefix_test.cc | ||
| range_del_aggregator.cc | ||
| range_del_aggregator.h | ||
| range_del_aggregator_bench.cc | ||
| range_del_aggregator_test.cc | ||
| range_tombstone_fragmenter.cc | ||
| range_tombstone_fragmenter.h | ||
| range_tombstone_fragmenter_test.cc | ||
| read_callback.h | ||
| repair.cc | ||
| repair_test.cc | ||
| seqno_time_test.cc | ||
| seqno_to_time_mapping.cc | ||
| seqno_to_time_mapping.h | ||
| snapshot_checker.h | ||
| snapshot_impl.cc | ||
| snapshot_impl.h | ||
| table_cache.cc | ||
| table_cache.h | ||
| table_cache_sync_and_async.h | ||
| table_properties_collector.cc | ||
| table_properties_collector.h | ||
| table_properties_collector_test.cc | ||
| transaction_log_impl.cc | ||
| transaction_log_impl.h | ||
| trim_history_scheduler.cc | ||
| trim_history_scheduler.h | ||
| version_builder.cc | ||
| version_builder.h | ||
| version_builder_test.cc | ||
| version_edit.cc | ||
| version_edit.h | ||
| version_edit_handler.cc | ||
| version_edit_handler.h | ||
| version_edit_test.cc | ||
| version_set.cc | ||
| version_set.h | ||
| version_set_sync_and_async.h | ||
| version_set_test.cc | ||
| version_util.h | ||
| wal_edit.cc | ||
| wal_edit.h | ||
| wal_edit_test.cc | ||
| wal_manager.cc | ||
| wal_manager.h | ||
| wal_manager_test.cc | ||
| write_batch.cc | ||
| write_batch_base.cc | ||
| write_batch_internal.h | ||
| write_batch_test.cc | ||
| write_callback.h | ||
| write_callback_test.cc | ||
| write_controller.cc | ||
| write_controller.h | ||
| write_controller_test.cc | ||
| write_thread.cc | ||
| write_thread.h | ||