From f3bcac39a601585dadbf27f632522bb48d622d13 Mon Sep 17 00:00:00 2001 From: Akanksha Mahajan Date: Mon, 11 Apr 2022 10:56:11 -0700 Subject: [PATCH] Fix stress test failure in ReadAsync. (#9824) Summary: Fix stress test failure in ReadAsync by ignoring errors injected during async read by FaultInjectionFS. Failure: ``` WARNING: prefix_size is non-zero but memtablerep != prefix_hash Didn't get expected error from MultiGet. num_keys 14 Expected 1 errors, seen 0 Callstack that injected the fault Injected error type = 32538 Message: error; #0 ./db_stress() [0x6f7dd4] rocksdb::port::SaveStack(int*, int) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/port/stack_trace.cc:152 https://github.com/facebook/rocksdb/issues/1 ./db_stress() [0x7f2bda] rocksdb::FaultInjectionTestFS::InjectThreadSpecificReadError(rocksdb::FaultInjectionTestFS::ErrorOperation, rocksdb::Slice*, bool, char*, bool, bool*) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/utilities/fault_injection_fs.cc:891 https://github.com/facebook/rocksdb/issues/2 ./db_stress() [0x7f2e78] rocksdb::TestFSRandomAccessFile::Read(unsigned long, unsigned long, rocksdb::IOOptions const&, rocksdb::Slice*, char*, rocksdb::IODebugContext*) const /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/utilities/fault_injection_fs.cc:367 https://github.com/facebook/rocksdb/issues/3 ./db_stress() [0x6483d7] rocksdb::(anonymous namespace)::CompositeRandomAccessFileWrapper::Read(unsigned long, unsigned long, rocksdb::Slice*, char*) const /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/env/composite_env.cc:61 https://github.com/facebook/rocksdb/issues/4 ./db_stress() [0x654564] rocksdb::(anonymous namespace)::LegacyRandomAccessFileWrapper::Read(unsigned long, unsigned long, rocksdb::IOOptions const&, rocksdb::Slice*, char*, rocksdb::IODebugContext*) const /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/env/env.cc:152 https://github.com/facebook/rocksdb/issues/5 ./db_stress() [0x659b3b] rocksdb::FSRandomAccessFile::ReadAsync(rocksdb::FSReadRequest&, rocksdb::IOOptions const&, std::function, void*, void**, std::function*, rocksdb::IODebugContext*) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/./include/rocksdb/file_system.h:896 https://github.com/facebook/rocksdb/issues/6 ./db_stress() [0x8b8bab] rocksdb::RandomAccessFileReader::ReadAsync(rocksdb::FSReadRequest&, rocksdb::IOOptions const&, std::function, void*, void**, std::function*, rocksdb::Env::IOPriority) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/file/random_access_file_reader.cc:459 https://github.com/facebook/rocksdb/issues/7 ./db_stress() [0x8b501f] rocksdb::FilePrefetchBuffer::ReadAsync(rocksdb::IOOptions const&, rocksdb::RandomAccessFileReader*, rocksdb::Env::IOPriority, unsigned long, unsigned long, unsigned long, unsigned int) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/file/file_prefetch_buffer.cc:124 https://github.com/facebook/rocksdb/issues/8 ./db_stress() [0x8b55fc] rocksdb::FilePrefetchBuffer::PrefetchAsync(rocksdb::IOOptions const&, rocksdb::RandomAccessFileReader*, unsigned long, unsigned long, unsigned long, rocksdb::Env::IOPriority, bool&) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/file/file_prefetch_buffer.cc:363 https://github.com/facebook/rocksdb/issues/9 ./db_stress() [0x8b61f8] rocksdb::FilePrefetchBuffer::TryReadFromCacheAsync(rocksdb::IOOptions const&, rocksdb::RandomAccessFileReader*, unsigned long, unsigned long, rocksdb::Slice*, rocksdb::Status*, rocksdb::Env::IOPriority, bool) /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/file/file_prefetch_buffer.cc:482 https://github.com/facebook/rocksdb/issues/10 ./db_stress() [0x745e04] rocksdb::BlockFetcher::TryGetFromPrefetchBuffer() /data/sandcastle/boxes/trunk-hg-fbcode-fbsource/fbcode/internal_repo_rocksdb/repo/table/block_fetcher.cc:76 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9824 Test Plan: ``` ./db_stress --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --allow_concurrent_memtable_write=0 --async_io=1 --atomic_flush=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 -- backup_max_size=104857600 --backup_one_in=100000 --batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=5.037629726741734 --bottommost_compression_type=lz4hc --cache_index_and_filter_blocks=0 --cache_size=8388608 --checkpoint_one_in=1000000 --checksum_type=kxxHash --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=1000000 --compact_range_one_in=1000000 --compaction_ttl=100 --compression_max_dict_buffer_bytes=1073741823 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=zstd --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --db=/home/akankshamahajan/dev/shm/rocksdb/rocksdb_crashtest_blackbox --db_write_buffer_size=8388608 --delpercent=0 --delrangepercent=0 --destroy_db_initially=0 - detect_filter_construct_corruption=1 --disable_wal=1 --enable_compaction_filter=0 --enable_pipelined_write=0 --expected_values_dir=/home/akankshamahajan/dev/shm/rocksdb/rocksdb_crashtest_expected --experimental_mempurge_threshold=8.772789063014715 --fail_if_options_file_error=0 --file_checksum_impl=crc32c --flush_one_in=1000000 --format_version=3 --get_current_wal_file_one_in=0 --get_live_files_one_in=1000000 --get_property_one_in=1000000 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=15 --index_type=3 --iterpercent=0 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=False --long_running_snapshots=0 --mark_for_compaction_one_file_in=0 --max_background_compactions=1 --max_bytes_for_level_base=67108864 --max_key=25000000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=16777216 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=2097152 --memtable_prefix_bloom_size_ratio=0.001 --memtable_whole_key_filtering=1 --memtablerep=skip_list --mmap_read=0 --mock_direct_io=True --nooverwritepercent=1 --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=0 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=2 --pause_background_one_in=1000000 --periodic_compaction_seconds=1000 --prefix_size=-1 --prefixpercent=0 --prepopulate_block_cache=0 --progress_reports=0 --read_fault_one_in=32 --readpercent=100 --recycle_log_file_num=1 --reopen=0 --reserve_table_reader_memory=1 --ribbon_starting_level=999 --secondary_cache_fault_one_in=0 --set_options_one_in=0 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --subcompactions=2 --sync=0 --sync_fault_injection=False --target_file_size_base=16777216 --target_file_size_multiplier=1 --test_batches_snapshots=0 --top_level_index_pinning=3 --unpartitioned_pinning=2 --use_block_based_filter=0 --use_clock_cache=0 --use_direct_io_for_flush_and_compaction=1 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=1 --use_multiget=1 --user_timestamp_size=0 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_db_one_in=100000 --wal_compression=none --write_buffer_size=33554432 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=0 ``` Reviewed By: anand1976 Differential Revision: D35514566 Pulled By: akankshamahajan15 fbshipit-source-id: e2a868fdd7422604774c1419738f9926a21e92a4 --- file/file_prefetch_buffer.cc | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/file/file_prefetch_buffer.cc b/file/file_prefetch_buffer.cc index 1fce53b65..a357221a7 100644 --- a/file/file_prefetch_buffer.cc +++ b/file/file_prefetch_buffer.cc @@ -516,6 +516,16 @@ bool FilePrefetchBuffer::TryReadFromCacheAsync( void FilePrefetchBuffer::PrefetchAsyncCallback(const FSReadRequest& req, void* /*cb_arg*/) { uint32_t index = curr_ ^ 1; + +#ifndef NDEBUG + if (req.result.size() < req.len) { + // Fake an IO error to force db_stress fault injection to ignore + // truncated read errors + IGNORE_STATUS_IF_ERROR(Status::IOError()); + } + IGNORE_STATUS_IF_ERROR(req.status); +#endif + if (req.status.ok()) { if (req.offset + req.result.size() <= bufs_[index].offset_ + bufs_[index].buffer_.CurrentSize()) {