rocksdb/db_stress_tool/db_stress_test_base.h
Hui Xiao 0d93c8a6ca Decouple sync fault and write injection in FaultInjectionTestFS & fix tracing issue under WAL write error injection (#12797)
Summary:
**Context/Summary:**

After injecting write error to WAL, we started to see crash recovery verification failure in prefix recovery. That's because the current tracing implementation traces every write before it writes to WAL even when the WAL write can fail with write error injection. One consequence of that is the traced writes in trace files does not corresponding to write sequence sequence anymore e.g, it has more traced writes that the actual assigned sequence number to successful writes. Therefore b4a84efb4e/db_stress_tool/expected_state.cc (L674) won't restore the ExpectedState to the correct sequence number we want.

Ideally, we should have a prepare-commit mechanism for tracing just like our ExpectedState so we can ignore the traced write if the write fails later. But for now, to simplify, we simply don't inject WAL error (and metadata write error cuz it could fail write when sync WAL dir fails)

To do so, we need to be able to exclude WAL from write injection but still allow sync fault injection in it to maintain its original sync fault testing coverage. This prompts us to decouple sync fault and write injection in FaultInjectionTestFS. And this is what this PR mainly about.

So now `FaultInjectionTestFS` works as the following:
- If direct_writable is true, then `FaultInjectionTestFS` is bypassed for writable file
- Otherwise, FaultInjectionTestFS` can buffer data for sync fault injection (if inject_unsynced_data_loss_ == true, global settings) and/or inject write error (if MaybeInjectThreadLocalError(), thread-local settings). WAL file can be optionally excluded from write injection

Bonus: better naming of relevant variables

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12797

Test Plan:
- The follow commands failed before this fix but passes after
```
python3 tools/db_crashtest.py --simple blackbox \
    --interval=5 \
    --preserve_unverified_changes=1 \
    --threads=32 \
    --disable_auto_compactions=1 \
    --WAL_size_limit_MB=0 --WAL_ttl_seconds=0 --acquire_snapshot_one_in=0 --adaptive_readahead=0 --adm_policy=0 --advise_random_on_open=1 --allow_concurrent_memtable_write=0 --allow_data_in_errors=True --allow_fallocate=1 --async_io=0 --auto_readahead_size=0 --avoid_flush_during_recovery=1 --avoid_flush_during_shutdown=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --bgerror_resume_retry_interval=1000000 --block_align=0 --block_protection_bytes_per_key=4 --block_size=16384 --bloom_before_level=2147483646 --bloom_bits=3.2003682301518492 --bottommost_compression_type=zlib --bottommost_file_compaction_delay=600 --bytes_per_sync=0 --cache_index_and_filter_blocks=1 --cache_index_and_filter_blocks_with_high_priority=1 --cache_size=33554432 --cache_type=fixed_hyper_clock_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=0 --charge_filter_construction=0 --charge_table_reader=1 --check_multiget_consistency=0 --check_multiget_entity_consistency=0 --checkpoint_one_in=0 --checksum_type=kxxHash64 --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=2 --compaction_readahead_size=0 --compaction_ttl=0 --compress_format_version=1 --compressed_secondary_cache_size=16777216 --compression_checksum=1 --compression_max_dict_buffer_bytes=549755813887 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=none --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --daily_offpeak_time_utc=00:00-23:59 --data_block_index_type=0 \
    --db_write_buffer_size=0 --delete_obsolete_files_period_micros=0 --delpercent=0 --delrangepercent=0 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_file_deletions_one_in=0 --disable_manual_compaction_one_in=0 --disable_wal=0 --dump_malloc_stats=0 --enable_checksum_handoff=0 --enable_compaction_filter=0 --enable_custom_split_merge=0 --enable_do_not_compress_roles=1 --enable_index_compression=0 --enable_memtable_insert_with_hint_prefix_extractor=0 --enable_pipelined_write=0 --enable_sst_partitioner_factory=0 --enable_thread_tracking=0 --enable_write_thread_adaptive_yield=0 --error_recovery_with_no_fault_injection=0 --fail_if_options_file_error=0 --fifo_allow_compaction=1 --file_checksum_impl=xxh64 --fill_cache=0 --flush_one_in=100 --format_version=4 --get_all_column_family_metadata_one_in=0 --get_current_wal_file_one_in=0 --get_live_files_apis_one_in=0 --get_properties_of_all_tables_one_in=0 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --hard_pending_compaction_bytes_limit=274877906944 --high_pri_pool_ratio=0.5 --index_block_restart_interval=9 --index_shortening=1 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=0 --inplace_update_support=0 --iterpercent=0 --key_len_percent_dist=1,30,69 --key_may_exist_one_in=0 --last_level_temperature=kUnknown --level_compaction_dynamic_level_bytes=1 --lock_wal_one_in=0 --log2_keys_per_lock=10 --log_file_time_to_roll=0 --log_readahead_size=16777216 --long_running_snapshots=0 --low_pri_pool_ratio=0 --lowest_used_cache_tier=2 --manifest_preallocation_size=0 --manual_wal_flush_one_in=0 --mark_for_compaction_one_file_in=0 --max_auto_readahead_size=524288 --max_background_compactions=1 --max_bytes_for_level_base=67108864 --max_key=1000 --max_key_len=3 --memtable_insert_hint_per_batch=0 --memtable_max_range_deletions=0 --memtable_prefix_bloom_size_ratio=0.5 --memtable_protection_bytes_per_key=8 --memtable_whole_key_filtering=0 --memtablerep=skip_list --metadata_charge_policy=0 --metadata_read_fault_one_in=0 --metadata_write_fault_one_in=0 --min_write_buffer_number_to_merge=1 --mmap_read=0 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=-1 --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 --ops_per_thread=20000000 \
    --optimize_filters_for_hits=1 --optimize_filters_for_memory=1 --optimize_multiget_for_io=0 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=0 --periodic_compaction_seconds=0 --prefix_size=1 --prefixpercent=0 --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=0 --readpercent=0 --recycle_log_file_num=0 --reopen=0 --report_bg_io_stats=0 --reset_stats_one_in=1000000 --sample_for_compression=5 --secondary_cache_fault_one_in=0 --secondary_cache_uri= --skip_stats_update_on_db_open=0 --snapshot_hold_ops=100000 --soft_pending_compaction_bytes_limit=68719476736 --sqfc_name=bar --sqfc_version=1 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=10 --stats_history_buffer_size=0 --strict_bytes_per_sync=0 --subcompactions=1 --sync=0 --sync_fault_injection=1 --table_cache_numshardbits=0 --target_file_size_base=16777216 --target_file_size_multiplier=1 --test_batches_snapshots=0 --top_level_index_pinning=3 --uncache_aggressiveness=9890 --universal_max_read_amp=-1 --unpartitioned_pinning=3 --use_adaptive_mutex=0 --use_adaptive_mutex_lru=1 --use_attribute_group=0 --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=0 --use_multi_cf_iterator=0 --use_multi_get_entity=0 --use_multiget=0 --use_put_entity_one_in=0 --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=0 --verify_checksum_one_in=0 --verify_compression=1 --verify_db_one_in=0 --verify_file_checksums_one_in=0 --verify_iterator_with_expected_state_one_in=5 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=0 --wal_compression=zstd --write_buffer_size=335544320 --write_dbid_to_manifest=1 --write_fault_one_in=100 --writepercent=100

```
- CI

Reviewed By: cbi42

Differential Revision: D58917145

Pulled By: hx235

fbshipit-source-id: b6397036bea035a92341c2b05fb01872db2153d7
2024-06-26 14:56:35 -07:00

400 lines
16 KiB
C++

// Copyright (c) 2011-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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#include "rocksdb/io_status.h"
#ifdef GFLAGS
#pragma once
#include "db_stress_tool/db_stress_common.h"
#include "db_stress_tool/db_stress_shared_state.h"
#include "rocksdb/experimental.h"
namespace ROCKSDB_NAMESPACE {
class SystemClock;
class Transaction;
class TransactionDB;
class OptimisticTransactionDB;
struct TransactionDBOptions;
using experimental::SstQueryFilterConfigsManager;
class StressTest {
public:
StressTest();
virtual ~StressTest();
std::shared_ptr<Cache> NewCache(size_t capacity, int32_t num_shard_bits);
static std::vector<std::string> GetBlobCompressionTags();
bool BuildOptionsTable();
void InitDb(SharedState*);
// The initialization work is split into two parts to avoid a circular
// dependency with `SharedState`.
virtual void FinishInitDb(SharedState*);
void TrackExpectedState(SharedState* shared);
void OperateDb(ThreadState* thread);
virtual void VerifyDb(ThreadState* thread) const = 0;
virtual void ContinuouslyVerifyDb(ThreadState* /*thread*/) const = 0;
void PrintStatistics();
bool MightHaveUnsyncedDataLoss() {
return FLAGS_sync_fault_injection || FLAGS_disable_wal ||
FLAGS_manual_wal_flush_one_in > 0;
}
protected:
static int GetMinInjectedErrorCount(int error_count_1, int error_count_2) {
if (error_count_1 > 0 && error_count_2 > 0) {
return std::min(error_count_1, error_count_2);
} else if (error_count_1 > 0) {
return error_count_1;
} else if (error_count_2 > 0) {
return error_count_2;
} else {
return 0;
}
}
Status AssertSame(DB* db, ColumnFamilyHandle* cf,
ThreadState::SnapshotState& snap_state);
// Currently PreloadDb has to be single-threaded.
void PreloadDbAndReopenAsReadOnly(int64_t number_of_keys,
SharedState* shared);
Status SetOptions(ThreadState* thread);
// For transactionsDB, there can be txns prepared but not yet committeed
// right before previous stress run crash.
// They will be recovered and processed through
// ProcessRecoveredPreparedTxnsHelper on the start of current stress run.
void ProcessRecoveredPreparedTxns(SharedState* shared);
// Default implementation will first update ExpectedState to be
// `SharedState::UNKNOWN` for each keys in `txn` and then randomly
// commit or rollback `txn`.
virtual void ProcessRecoveredPreparedTxnsHelper(Transaction* txn,
SharedState* shared);
// ExecuteTransaction is recommended instead
Status NewTxn(WriteOptions& write_opts,
std::unique_ptr<Transaction>* out_txn);
Status CommitTxn(Transaction& txn, ThreadState* thread = nullptr);
// Creates a transaction, executes `ops`, and tries to commit
Status ExecuteTransaction(WriteOptions& write_opts, ThreadState* thread,
std::function<Status(Transaction&)>&& ops);
virtual void MaybeClearOneColumnFamily(ThreadState* /* thread */) {}
virtual bool ShouldAcquireMutexOnKey() const { return false; }
// Returns true if DB state is tracked by the stress test.
virtual bool IsStateTracked() const = 0;
virtual std::vector<int> GenerateColumnFamilies(
const int /* num_column_families */, int rand_column_family) const {
return {rand_column_family};
}
virtual std::vector<int64_t> GenerateKeys(int64_t rand_key) const {
return {rand_key};
}
virtual void TestKeyMayExist(ThreadState*, const ReadOptions&,
const std::vector<int>&,
const std::vector<int64_t>&) {}
virtual Status TestGet(ThreadState* thread, const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual std::vector<Status> TestMultiGet(
ThreadState* thread, const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual void TestGetEntity(ThreadState* thread, const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual void TestMultiGetEntity(ThreadState* thread,
const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual Status TestPrefixScan(ThreadState* thread,
const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual Status TestPut(ThreadState* thread, WriteOptions& write_opts,
const ReadOptions& read_opts,
const std::vector<int>& cf_ids,
const std::vector<int64_t>& keys,
char (&value)[100]) = 0;
virtual Status TestDelete(ThreadState* thread, WriteOptions& write_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual Status TestDeleteRange(ThreadState* thread, WriteOptions& write_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
virtual void TestIngestExternalFile(
ThreadState* thread, const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys) = 0;
// Issue compact range, starting with start_key, whose integer value
// is rand_key.
virtual void TestCompactRange(ThreadState* thread, int64_t rand_key,
const Slice& start_key,
ColumnFamilyHandle* column_family);
virtual void TestPromoteL0(ThreadState* thread,
ColumnFamilyHandle* column_family);
// Calculate a hash value for all keys in range [start_key, end_key]
// at a certain snapshot.
uint32_t GetRangeHash(ThreadState* thread, const Snapshot* snapshot,
ColumnFamilyHandle* column_family,
const Slice& start_key, const Slice& end_key);
// Return a column family handle that mirrors what is pointed by
// `column_family_id`, which will be used to validate data to be correct.
// By default, the column family itself will be returned.
virtual ColumnFamilyHandle* GetControlCfh(ThreadState* /* thread*/,
int column_family_id) {
return column_families_[column_family_id];
}
// Generated a list of keys that close to boundaries of SST keys.
// If there isn't any SST file in the DB, return empty list.
std::vector<std::string> GetWhiteBoxKeys(ThreadState* thread, DB* db,
ColumnFamilyHandle* cfh,
size_t num_keys);
// Given a key K, this creates an iterator which scans to K and then
// does a random sequence of Next/Prev operations.
virtual Status TestIterate(ThreadState* thread, const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys);
// Given a key K, this creates an attribute group iterator which scans to K
// and then does a random sequence of Next/Prev operations. Called only when
// use_attribute_group=1
virtual Status TestIterateAttributeGroups(
ThreadState* thread, const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys);
template <typename IterType, typename NewIterFunc, typename VerifyFunc>
Status TestIterateImpl(ThreadState* thread, const ReadOptions& read_opts,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys,
NewIterFunc new_iter_func, VerifyFunc verify_func);
virtual Status TestIterateAgainstExpected(
ThreadState* /* thread */, const ReadOptions& /* read_opts */,
const std::vector<int>& /* rand_column_families */,
const std::vector<int64_t>& /* rand_keys */) {
return Status::NotSupported();
}
// Enum used by VerifyIterator() to identify the mode to validate.
enum LastIterateOp {
kLastOpSeek,
kLastOpSeekForPrev,
kLastOpNextOrPrev,
kLastOpSeekToFirst,
kLastOpSeekToLast
};
// Compare the two iterator, iter and cmp_iter are in the same position,
// unless iter might be made invalidate or undefined because of
// upper or lower bounds, or prefix extractor.
// Will flag failure if the verification fails.
// diverged = true if the two iterator is already diverged.
// True if verification passed, false if not.
// op_logs is the information to print when validation fails.
template <typename IterType, typename VerifyFuncType>
void VerifyIterator(ThreadState* thread, ColumnFamilyHandle* cmp_cfh,
const ReadOptions& ro, IterType* iter, Iterator* cmp_iter,
LastIterateOp op, const Slice& seek_key,
const std::string& op_logs, VerifyFuncType verifyFunc,
bool* diverged);
virtual Status TestBackupRestore(ThreadState* thread,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys);
virtual Status PrepareOptionsForRestoredDB(Options* options);
virtual Status TestCheckpoint(ThreadState* thread,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys);
void TestCompactFiles(ThreadState* thread, ColumnFamilyHandle* column_family);
Status TestFlush(const std::vector<int>& rand_column_families);
Status TestResetStats();
Status TestPauseBackground(ThreadState* thread);
Status TestDisableFileDeletions(ThreadState* thread);
Status TestDisableManualCompaction(ThreadState* thread);
void TestAcquireSnapshot(ThreadState* thread, int rand_column_family,
const std::string& keystr, uint64_t i);
Status MaybeReleaseSnapshots(ThreadState* thread, uint64_t i);
Status TestGetLiveFiles() const;
Status TestGetLiveFilesMetaData() const;
Status TestGetLiveFilesStorageInfo() const;
Status TestGetAllColumnFamilyMetaData() const;
Status TestGetSortedWalFiles() const;
Status TestGetCurrentWalFile() const;
void TestGetProperty(ThreadState* thread) const;
Status TestGetPropertiesOfAllTables() const;
virtual Status TestApproximateSize(
ThreadState* thread, uint64_t iteration,
const std::vector<int>& rand_column_families,
const std::vector<int64_t>& rand_keys);
virtual Status TestCustomOperations(
ThreadState* /*thread*/,
const std::vector<int>& /*rand_column_families*/) {
return Status::NotSupported("TestCustomOperations() must be overridden");
}
bool IsErrorInjectedAndRetryable(const Status& error_s) const {
assert(!error_s.ok());
return error_s.getState() && std::strstr(error_s.getState(), "inject") &&
!status_to_io_status(Status(error_s)).GetDataLoss();
}
void ProcessStatus(SharedState* shared, std::string msg, const Status& s,
bool ignore_injected_error = true) const;
void VerificationAbort(SharedState* shared, std::string msg) const;
void VerificationAbort(SharedState* shared, std::string msg, int cf,
int64_t key) const;
void VerificationAbort(SharedState* shared, std::string msg, int cf,
int64_t key, Slice value_from_db,
Slice value_from_expected) const;
void VerificationAbort(SharedState* shared, int cf, int64_t key,
const Slice& value, const WideColumns& columns) const;
static std::string DebugString(const Slice& value,
const WideColumns& columns);
void PrintEnv() const;
void Open(SharedState* shared, bool reopen = false);
void Reopen(ThreadState* thread);
virtual void RegisterAdditionalListeners() {}
virtual void PrepareTxnDbOptions(SharedState* /*shared*/,
TransactionDBOptions& /*txn_db_opts*/) {}
// Returns whether the timestamp of read_opts is updated.
bool MaybeUseOlderTimestampForPointLookup(ThreadState* thread,
std::string& ts_str,
Slice& ts_slice,
ReadOptions& read_opts);
void MaybeUseOlderTimestampForRangeScan(ThreadState* thread,
std::string& ts_str, Slice& ts_slice,
ReadOptions& read_opts);
std::shared_ptr<Cache> cache_;
std::shared_ptr<Cache> compressed_cache_;
std::shared_ptr<const FilterPolicy> filter_policy_;
DB* db_;
TransactionDB* txn_db_;
OptimisticTransactionDB* optimistic_txn_db_;
// Currently only used in MultiOpsTxnsStressTest
std::atomic<DB*> db_aptr_;
Options options_;
SystemClock* clock_;
std::vector<ColumnFamilyHandle*> column_families_;
std::vector<std::string> column_family_names_;
std::atomic<int> new_column_family_name_;
int num_times_reopened_;
std::unordered_map<std::string, std::vector<std::string>> options_table_;
std::vector<std::string> options_index_;
std::atomic<bool> db_preload_finished_;
std::shared_ptr<SstQueryFilterConfigsManager::Factory> sqfc_factory_;
// Fields used for continuous verification from another thread
DB* cmp_db_;
std::vector<ColumnFamilyHandle*> cmp_cfhs_;
bool is_db_stopped_;
};
// Load options from OPTIONS file and populate `options`.
bool InitializeOptionsFromFile(Options& options);
// Initialize `options` using command line arguments.
// When this function is called, `cache`, `block_cache_compressed`,
// `filter_policy` have all been initialized. Therefore, we just pass them as
// input arguments.
void InitializeOptionsFromFlags(
const std::shared_ptr<Cache>& cache,
const std::shared_ptr<const FilterPolicy>& filter_policy, Options& options);
// Initialize `options` on which `InitializeOptionsFromFile()` and
// `InitializeOptionsFromFlags()` have both been called already.
// There are two cases.
// Case 1: OPTIONS file is not specified. Command line arguments have been used
// to initialize `options`. InitializeOptionsGeneral() will use
// `cache` and `filter_policy` to initialize
// corresponding fields of `options`. InitializeOptionsGeneral() will
// also set up other fields of `options` so that stress test can run.
// Examples include `create_if_missing` and
// `create_missing_column_families`, etc.
// Case 2: OPTIONS file is specified. It is possible that, after loading from
// the given OPTIONS files, some shared object fields are still not
// initialized because they are not set in the OPTIONS file. In this
// case, if command line arguments indicate that the user wants to set
// up such shared objects, e.g. block cache, compressed block cache,
// row cache, filter policy, then InitializeOptionsGeneral() will honor
// the user's choice, thus passing `cache`,
// `filter_policy` as input arguments.
//
// InitializeOptionsGeneral() must not overwrite fields of `options` loaded
// from OPTIONS file.
void InitializeOptionsGeneral(
const std::shared_ptr<Cache>& cache,
const std::shared_ptr<const FilterPolicy>& filter_policy,
const std::shared_ptr<SstQueryFilterConfigsManager::Factory>& sqfc_factory,
Options& options);
// If no OPTIONS file is specified, set up `options` so that we can test
// user-defined timestamp which requires `-user_timestamp_size=8`.
// This function also checks for known (currently) incompatible features with
// user-defined timestamp.
void CheckAndSetOptionsForUserTimestamp(Options& options);
} // namespace ROCKSDB_NAMESPACE
#endif // GFLAGS