dolysis
/
rocksdb
mirror of https://github.com/facebook/rocksdb.git
3
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Disable WAL fault injection in some case (#13000) 

Summary:
when manual_wal_flush is true and when there are more than 1 CF, WAL fault injection can cause CFs to be inconsistent. See more explanation and repro in T199157789. Disable the combination for now until we have a fix that allows auto recovery. This also helps to see if there's other cause of stress test failures.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/13000

Test Plan:
the following command could repro db consistency failure in a few runs before this PR.
From stress test output we can also see that exclude_wal_from_write_fault_injection and metadata_write_fault_one_in are sanitized to 0.
```
python3 ./tools/db_crashtest.py blackbox --interval=60 --metadata_write_fault_one_in=1000 --column_families=10 --exclude_wal_from_write_fault_injection=0 --manual_wal_flush_one_in=1000 --WAL_size_limit_MB=10240 --WAL_ttl_seconds=0 --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --adm_policy=1 --advise_random_on_open=1 --allow_data_in_errors=True --allow_fallocate=1 --async_io=0 --auto_readahead_size=0 --avoid_flush_during_recovery=1 --avoid_flush_during_shutdown=1 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --bgerror_resume_retry_interval=100 --block_align=1 --block_protection_bytes_per_key=0 --block_size=16384 --bloom_before_level=2147483647 --bottommost_compression_type=none --bottommost_file_compaction_delay=0 --bytes_per_sync=0 --cache_index_and_filter_blocks=1 --cache_index_and_filter_blocks_with_high_priority=1 --cache_size=33554432 --cache_type=auto_hyper_clock_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=1 --charge_table_reader=0 --check_multiget_consistency=0 --check_multiget_entity_consistency=0 --checkpoint_one_in=0 --checksum_type=kxxHash64 --clear_column_family_one_in=0 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=1 --compaction_readahead_size=1048576 --compaction_ttl=0 --compress_format_version=1 --compressed_secondary_cache_size=8388608 --compression_checksum=0 --compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 --compression_parallel_threads=4 --compression_type=none --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --daily_offpeak_time_utc= --data_block_index_type=0  --db_write_buffer_size=0 --decouple_partitioned_filters=1 --default_temperature=kCold --default_write_temperature=kWarm --delete_obsolete_files_period_micros=30000000 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_file_deletions_one_in=1000000 --disable_manual_compaction_one_in=1000000 --disable_wal=0 --dump_malloc_stats=1 --enable_checksum_handoff=1 --enable_compaction_filter=0 --enable_custom_split_merge=0 --enable_do_not_compress_roles=0 --enable_index_compression=0 --enable_memtable_insert_with_hint_prefix_extractor=0 --enable_pipelined_write=1 --enable_sst_partitioner_factory=0 --enable_thread_tracking=1 --enable_write_thread_adaptive_yield=1 --error_recovery_with_no_fault_injection=1 --fail_if_options_file_error=1 --fifo_allow_compaction=1 --file_checksum_impl=big --fill_cache=1 --flush_one_in=1000000 --format_version=6 --get_all_column_family_metadata_one_in=1000000 --get_current_wal_file_one_in=0 --get_live_files_apis_one_in=10000 --get_properties_of_all_tables_one_in=1000000 --get_property_one_in=100000 --get_sorted_wal_files_one_in=0 --hard_pending_compaction_bytes_limit=274877906944  --index_block_restart_interval=4 --index_shortening=1 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=16384 --inplace_update_support=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --key_may_exist_one_in=100000 --last_level_temperature=kWarm --level_compaction_dynamic_level_bytes=0 --lock_wal_one_in=10000 --log_file_time_to_roll=0 --log_readahead_size=0 --long_running_snapshots=0 --lowest_used_cache_tier=2 --manifest_preallocation_size=5120 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=0 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=100000 --max_key_len=3 --max_log_file_size=0 --max_manifest_file_size=1073741824 --max_sequential_skip_in_iterations=16 --max_total_wal_size=0 --max_write_batch_group_size_bytes=16777216 --max_write_buffer_number=10 --max_write_buffer_size_to_maintain=2097152 --memtable_insert_hint_per_batch=1 --memtable_max_range_deletions=0 --memtable_prefix_bloom_size_ratio=0.001 --memtable_protection_bytes_per_key=2 --memtable_whole_key_filtering=0 --memtablerep=skip_list --metadata_charge_policy=1 --metadata_read_fault_one_in=0 --min_write_buffer_number_to_merge=1 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=2 --open_files=100 --open_metadata_read_fault_one_in=0 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --optimize_filters_for_hits=0 --optimize_filters_for_memory=0 --optimize_multiget_for_io=0 --paranoid_file_checks=1 --paranoid_memory_checks=0 --partition_filters=0 --partition_pinning=2 --pause_background_one_in=10000 --periodic_compaction_seconds=0 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --preserve_internal_time_seconds=0 --progress_reports=0 --promote_l0_one_in=0 --read_amp_bytes_per_bit=0 --read_fault_one_in=0 --readahead_size=524288 --readpercent=45 --recycle_log_file_num=0 --reopen=0 --report_bg_io_stats=0 --reset_stats_one_in=10000 --sample_for_compression=5 --secondary_cache_fault_one_in=0 --secondary_cache_uri= --set_options_one_in=10000 --skip_stats_update_on_db_open=1 --snapshot_hold_ops=100000 --soft_pending_compaction_bytes_limit=1048576 --sqfc_name=bar --sqfc_version=1 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=600 --stats_history_buffer_size=1048576 --strict_bytes_per_sync=1 --subcompactions=2 --sync=0 --sync_fault_injection=1 --table_cache_numshardbits=6 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=3 --uncache_aggressiveness=8 --universal_max_read_amp=-1 --unpartitioned_pinning=2 --use_adaptive_mutex=1 --use_adaptive_mutex_lru=0 --use_attribute_group=1 --use_delta_encoding=0 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_get_entity=0 --use_merge=1 --use_multi_cf_iterator=1 --use_multi_get_entity=0 --use_multiget=0 --use_put_entity_one_in=1 --use_sqfc_for_range_queries=0 --use_timed_put_one_in=0 --use_write_buffer_manager=0 --user_timestamp_size=0 --value_size_mult=32 --verification_only=0 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_compression=1 --verify_db_one_in=100000 --verify_file_checksums_one_in=1000000 --verify_iterator_with_expected_state_one_in=5 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=0 --wal_compression=none --write_buffer_size=4194304 --write_dbid_to_manifest=0 --write_fault_one_in=50 --writepercent=35 --ops_per_thread=100000 --preserve_unverified_changes=1
```

Reviewed By: hx235

Differential Revision: D62303631

Pulled By: cbi42

fbshipit-source-id: d9441188ee84d53e5e7916f3305e50843fe9fde2
This commit is contained in:
Changyu Bi 2024-09-06 11:05:49 -07:00 committed by Facebook GitHub Bot
parent 4577b672d5
commit 0bea5a2cfe
1 changed files with 16 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
tools/db_crashtest.py
View File

@ -923,16 +923,22 @@ def finalize_and_sanitize(src_params):
dest_params["prefixpercent"] = 0
dest_params["check_multiget_consistency"] = 0
dest_params["check_multiget_entity_consistency"] = 0
if dest_params.get("disable_wal") == 0 and dest_params.get("reopen") > 0:
# Reopen with WAL currently requires persisting WAL data before closing for reopen.
# Previous injected WAL write errors may not be cleared by the time of closing and ready
# for persisting WAL.
# To simplify, we disable any WAL write error injection.
# TODO(hx235): support WAL write error injection with reopen
# TODO(hx235): support excluding WAL from metadata write fault injection so we don't
# have to disable metadata write fault injection to other file
dest_params["exclude_wal_from_write_fault_injection"] = 1
dest_params["metadata_write_fault_one_in"] = 0
if dest_params.get("disable_wal") == 0:
if dest_params.get("reopen") > 0 or (dest_params.get("manual_wal_flush_one_in") and dest_params.get("column_families") != 1):
# Reopen with WAL currently requires persisting WAL data before closing for reopen.
# Previous injected WAL write errors may not be cleared by the time of closing and ready
# for persisting WAL.
# To simplify, we disable any WAL write error injection.
# TODO(hx235): support WAL write error injection with reopen
# TODO(hx235): support excluding WAL from metadata write fault injection so we don't
# have to disable metadata write fault injection to other file
#
# WAL write failure can drop buffered WAL data. This can cause
# inconsistency when one CF has a successful flush during auto
# recovery. Disable the fault injection in this path for now until
# we have a fix that allows auto recovery.
dest_params["exclude_wal_from_write_fault_injection"] = 1
dest_params["metadata_write_fault_one_in"] = 0
if dest_params.get("disable_wal") == 1:
# disableWAL and recycle_log_file_num options are not mutually
# compatible at the moment