mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 13:41:46 +00:00
f97e33454f
Summary:
A recent crash test failure shows that auto recovery from WAL write failure can cause CFs to be inconsistent. A unit test repro in P1569398553. The following is an example sequence of events:
```
0. manual_wal_flush is true. There are multiple CFs in a DB.
1. Submit a write batch with updates to multiple CF
2. A FlushWAL or a memtable swtich that will try to write the buffered WAL data. Fail this write so that buffered WAL data is dropped: 4b1d595306/file/writable_file_writer.cc (L624)
The error needs to be retryable to start background auto recovery.
3. One CF successfully flushes its memtable during auto recovery.
4. Crash the process.
5. Reopen the DB, one CF will have the update as a result of successful flush. Other CFs will miss all the updates in the write batch since WAL does not have them.
```
This can happen if a users configures manual_wal_flush, uses more than one CF, and can hit retryable error for WAL writes. This PR is a short-term fix that upgrades WAL related errors to fatal and not trigger auto recovery.
A long-term fix may be not drop buffered WAL data by checking how much data is actually written, or require atomically flushing all column families during error recovery from this kind of errors.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12995
Test Plan:
added unit test to check error severity and if recovery is triggered. A crash test repro command that fails in a few runs before this PR:
```
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: D62888510
Pulled By: cbi42
fbshipit-source-id: 308bdbbb8d897cc8eba950155cd0e37cf7eb76fe
151 lines
5.1 KiB
C++
151 lines
5.1 KiB
C++
// Copyright (c) 2018-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
#pragma once
|
|
|
|
#include <sstream>
|
|
|
|
#include "monitoring/instrumented_mutex.h"
|
|
#include "options/db_options.h"
|
|
#include "rocksdb/io_status.h"
|
|
#include "rocksdb/listener.h"
|
|
#include "rocksdb/status.h"
|
|
#include "util/autovector.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class DBImpl;
|
|
|
|
// This structure is used to store the DB recovery context. The context is
|
|
// the information that related to the recover actions. For example, it contains
|
|
// FlushReason, which tells the flush job why this flush is called.
|
|
struct DBRecoverContext {
|
|
FlushReason flush_reason;
|
|
bool flush_after_recovery;
|
|
|
|
DBRecoverContext()
|
|
: flush_reason(FlushReason::kErrorRecovery),
|
|
flush_after_recovery(false) {}
|
|
DBRecoverContext(FlushReason reason)
|
|
: flush_reason(reason), flush_after_recovery(false) {}
|
|
};
|
|
|
|
class ErrorHandler {
|
|
public:
|
|
ErrorHandler(DBImpl* db, const ImmutableDBOptions& db_options,
|
|
InstrumentedMutex* db_mutex)
|
|
: db_(db),
|
|
db_options_(db_options),
|
|
cv_(db_mutex),
|
|
end_recovery_(false),
|
|
recovery_thread_(nullptr),
|
|
db_mutex_(db_mutex),
|
|
auto_recovery_(false),
|
|
recovery_in_prog_(false),
|
|
soft_error_no_bg_work_(false),
|
|
is_db_stopped_(false),
|
|
bg_error_stats_(db_options.statistics) {
|
|
// Clear the checked flag for uninitialized errors
|
|
bg_error_.PermitUncheckedError();
|
|
recovery_error_.PermitUncheckedError();
|
|
}
|
|
|
|
void EnableAutoRecovery() { auto_recovery_ = true; }
|
|
|
|
Status::Severity GetErrorSeverity(BackgroundErrorReason reason,
|
|
Status::Code code, Status::SubCode subcode);
|
|
|
|
void SetBGError(const Status& bg_err, BackgroundErrorReason reason,
|
|
bool wal_related = false);
|
|
|
|
Status GetBGError() const { return bg_error_; }
|
|
|
|
Status GetRecoveryError() const { return recovery_error_; }
|
|
|
|
Status ClearBGError();
|
|
|
|
bool IsDBStopped() { return is_db_stopped_.load(std::memory_order_acquire); }
|
|
|
|
bool IsBGWorkStopped() {
|
|
assert(db_mutex_);
|
|
db_mutex_->AssertHeld();
|
|
return !bg_error_.ok() &&
|
|
(bg_error_.severity() >= Status::Severity::kHardError ||
|
|
!auto_recovery_ || soft_error_no_bg_work_);
|
|
}
|
|
|
|
bool IsSoftErrorNoBGWork() { return soft_error_no_bg_work_; }
|
|
|
|
bool IsRecoveryInProgress() { return recovery_in_prog_; }
|
|
|
|
Status RecoverFromBGError(bool is_manual = false);
|
|
void CancelErrorRecovery();
|
|
|
|
void EndAutoRecovery();
|
|
|
|
void AddFilesToQuarantine(
|
|
autovector<const autovector<uint64_t>*> files_to_quarantine);
|
|
|
|
const autovector<uint64_t>& GetFilesToQuarantine() const {
|
|
db_mutex_->AssertHeld();
|
|
return files_to_quarantine_;
|
|
}
|
|
|
|
void ClearFilesToQuarantine();
|
|
|
|
private:
|
|
void RecordStats(
|
|
const std::vector<Tickers>& ticker_types,
|
|
const std::vector<std::tuple<Histograms, uint64_t>>& int_histograms);
|
|
|
|
DBImpl* db_;
|
|
const ImmutableDBOptions& db_options_;
|
|
Status bg_error_;
|
|
// A separate Status variable used to record any errors during the
|
|
// recovery process from hard errors
|
|
IOStatus recovery_error_;
|
|
// The condition variable used with db_mutex during auto resume for time
|
|
// wait.
|
|
InstrumentedCondVar cv_;
|
|
bool end_recovery_;
|
|
std::unique_ptr<port::Thread> recovery_thread_;
|
|
|
|
InstrumentedMutex* db_mutex_;
|
|
// A flag indicating whether automatic recovery from errors is enabled. Auto
|
|
// recovery applies for delegating to SstFileManager to handle no space type
|
|
// of errors. This flag doesn't control the auto resume behavior to recover
|
|
// from retryable IO errors.
|
|
bool auto_recovery_;
|
|
bool recovery_in_prog_;
|
|
// A flag to indicate that for the soft error, we should not allow any
|
|
// background work except the work is from recovery.
|
|
bool soft_error_no_bg_work_;
|
|
|
|
// Used to store the context for recover, such as flush reason.
|
|
DBRecoverContext recover_context_;
|
|
std::atomic<bool> is_db_stopped_;
|
|
|
|
// The pointer of DB statistics.
|
|
std::shared_ptr<Statistics> bg_error_stats_;
|
|
|
|
// During recovery from manifest IO errors, files whose VersionEdits entries
|
|
// could be in an ambiguous state are quarantined and file deletion refrain
|
|
// from deleting them. Successful recovery will clear this vector. Files are
|
|
// added to this vector while DB mutex was locked, this data structure is
|
|
// unsorted.
|
|
autovector<uint64_t> files_to_quarantine_;
|
|
|
|
void HandleKnownErrors(const Status& bg_err, BackgroundErrorReason reason);
|
|
Status OverrideNoSpaceError(const Status& bg_error, bool* auto_recovery);
|
|
void RecoverFromNoSpace();
|
|
void StartRecoverFromRetryableBGIOError(const IOStatus& io_error);
|
|
void RecoverFromRetryableBGIOError();
|
|
// First, if it is in recovery and the recovery_error is ok. Set the
|
|
// recovery_error_ to bg_err. Second, if the severity is higher than the
|
|
// current bg_error_, overwrite it.
|
|
void CheckAndSetRecoveryAndBGError(const Status& bg_err);
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|