1
0
mirror of https://github.com/facebook/rocksdb.git synced 2025-05-15 09:23:03 +08:00
Hui Xiao 408e8d4c85 Handle injected write error after successful WAL write in crash test + misc ()
Summary:
**Context/Summary:**
We discovered the following false positive in our crash test lately:
(1) PUT() writes k/v to WAL but fails in `ApplyWALToManifest()`. The k/v is in the WAL
(2) Current stress test logic will rollback the expected state of such k/v since PUT() fails
(3) If the DB crashes before recovery finishes and reopens, the WAL will be replayed and the k/v is in the DB while the expected state have been roll-backed.

We decided to leave those expected state to be pending until the loop-write of the same key succeeds.

Bonus: Now that I realized write to manifest can also fail the write which faces the similar problem as https://github.com/facebook/rocksdb/pull/12797, I decided to disable fault injection on user write per thread (instead of globally) when tracing is needed for prefix recovery; some refactory

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12838

Test Plan:
Rehearsal CI
Run below command (varies on sync_fault_injection=1,0 to verify ExpectedState behavior) for a while to ensure crash recovery validation works fine

```
python3 tools/db_crashtest.py --simple blackbox --interval=30 --WAL_size_limit_MB=0 --WAL_ttl_seconds=0 --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --adm_policy=1 --advise_random_on_open=0 --allow_concurrent_memtable_write=0 --allow_data_in_errors=True --allow_fallocate=0 --async_io=0 --auto_readahead_size=0 --avoid_flush_during_recovery=0 --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=1 --block_protection_bytes_per_key=4 --block_size=16384 --bloom_before_level=4 --bloom_bits=56.810257702625165 --bottommost_compression_type=none --bottommost_file_compaction_delay=0 --bytes_per_sync=262144 --cache_index_and_filter_blocks=1 --cache_index_and_filter_blocks_with_high_priority=1 --cache_size=8388608 --cache_type=auto_hyper_clock_cache --charge_compression_dictionary_building_buffer=1 --charge_file_metadata=1 --charge_filter_construction=1 --charge_table_reader=0 --check_multiget_consistency=0 --check_multiget_entity_consistency=1 --checkpoint_one_in=10000 --checksum_type=kxxHash --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=1000 --compact_range_one_in=1000 --compaction_pri=4 --compaction_readahead_size=1048576 --compaction_ttl=10 --compress_format_version=1 --compressed_secondary_cache_ratio=0.0 --compressed_secondary_cache_size=0 --compression_checksum=0 --compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 --compression_parallel_threads=1 --compression_type=none --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --daily_offpeak_time_utc=04:00-08:00 --data_block_index_type=1 --db_write_buffer_size=0 --default_temperature=kWarm --default_write_temperature=kCold --delete_obsolete_files_period_micros=30000000 --delpercent=20 --delrangepercent=20 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_file_deletions_one_in=10000 --disable_manual_compaction_one_in=1000000 --disable_wal=0 --dump_malloc_stats=0 --enable_checksum_handoff=1 --enable_compaction_filter=0 --enable_custom_split_merge=0 --enable_do_not_compress_roles=0 --enable_index_compression=1 --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=1 --exclude_wal_from_write_fault_injection=0 --fail_if_options_file_error=1 --fifo_allow_compaction=0 --file_checksum_impl=crc32c --fill_cache=1 --flush_one_in=1000000 --format_version=3 --get_all_column_family_metadata_one_in=1000000 --get_current_wal_file_one_in=0 --get_live_files_apis_one_in=1000000 --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 --high_pri_pool_ratio=0.5 --index_block_restart_interval=4 --index_shortening=2 --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=100 --last_level_temperature=kWarm --level_compaction_dynamic_level_bytes=1 --lock_wal_one_in=10000 --log_file_time_to_roll=60 --log_readahead_size=16777216 --long_running_snapshots=1 --low_pri_pool_ratio=0 --lowest_used_cache_tier=0 --manifest_preallocation_size=0 --manual_wal_flush_one_in=0 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=16384 --max_background_compactions=1 --max_bytes_for_level_base=67108864 --max_key=100000 --max_key_len=3 --max_log_file_size=1048576 --max_manifest_file_size=32768 --max_sequential_skip_in_iterations=1 --max_total_wal_size=0 --max_write_batch_group_size_bytes=16 --max_write_buffer_number=10 --max_write_buffer_size_to_maintain=8388608 --memtable_insert_hint_per_batch=1 --memtable_max_range_deletions=0 --memtable_prefix_bloom_size_ratio=0.01 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=1 --memtablerep=skip_list --metadata_charge_policy=1 --metadata_read_fault_one_in=0 --metadata_write_fault_one_in=8 --min_write_buffer_number_to_merge=1 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=1 --open_files=-1 --open_metadata_read_fault_one_in=0 --open_metadata_write_fault_one_in=8 --open_read_fault_one_in=0 --open_write_fault_one_in=8 --ops_per_thread=100000000 --optimize_filters_for_hits=1 --optimize_filters_for_memory=1 --optimize_multiget_for_io=1 --paranoid_file_checks=0 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=1000000 --periodic_compaction_seconds=2 --prefix_size=7 --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=1000 --readahead_size=524288 --readpercent=10 --recycle_log_file_num=1 --reopen=0 --report_bg_io_stats=0 --reset_stats_one_in=1000000 --sample_for_compression=0 --secondary_cache_fault_one_in=0 --set_options_one_in=0 --skip_stats_update_on_db_open=1 --snapshot_hold_ops=100000 --soft_pending_compaction_bytes_limit=68719476736 --sqfc_name=foo --sqfc_version=0 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=10 --stats_history_buffer_size=0 --strict_bytes_per_sync=1 --subcompactions=4 --sync=1 --sync_fault_injection=0 --table_cache_numshardbits=6 --target_file_size_base=16777216 --target_file_size_multiplier=1 --test_batches_snapshots=0 --top_level_index_pinning=2 --uncache_aggressiveness=239 --universal_max_read_amp=-1 --unpartitioned_pinning=1 --use_adaptive_mutex=1 --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=1 --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=0 --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=33554432 --write_dbid_to_manifest=0 --write_fault_one_in=8 --writepercent=40
```

Reviewed By: cbi42

Differential Revision: D59377075

Pulled By: hx235

fbshipit-source-id: 91f602fd67e2d339d378cd28b982095fd073dcb6
2024-07-29 13:51:49 -07:00

279 lines
9.4 KiB
C++

// Copyright (c) 2021-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).
#ifdef GFLAGS
#pragma once
#include <stdint.h>
#include <stdio.h>
#include <atomic>
#include <cassert>
#include <memory>
#include "rocksdb/rocksdb_namespace.h"
namespace ROCKSDB_NAMESPACE {
// `ExpectedValue` represents the expected value of a key used in db stress,
// which provides APIs to obtain various information e.g, value base, existence,
// pending operation status and APIs to edit expected value.
//
// This class is not thread-safe.
class ExpectedValue {
public:
static uint32_t GetValueBaseMask() { return VALUE_BASE_MASK; }
static uint32_t GetValueBaseDelta() { return VALUE_BASE_DELTA; }
static uint32_t GetDelCounterDelta() { return DEL_COUNTER_DELTA; }
static uint32_t GetDelMask() { return DEL_MASK; }
static bool IsValueBaseValid(uint32_t value_base) {
return IsValuePartValid(value_base, VALUE_BASE_MASK);
}
ExpectedValue() : expected_value_(DEL_MASK) {}
explicit ExpectedValue(uint32_t expected_value)
: expected_value_(expected_value) {}
bool Exists() const { return PendingWrite() || !IsDeleted(); }
uint32_t Read() const { return expected_value_; }
bool Put(bool pending);
bool Delete(bool pending);
void SyncPut(uint32_t value_base);
void SyncPendingPut();
void SyncDelete();
uint32_t GetValueBase() const { return GetValuePart(VALUE_BASE_MASK); }
uint32_t NextValueBase() const {
return GetIncrementedValuePart(VALUE_BASE_MASK, VALUE_BASE_DELTA);
}
void SetValueBase(uint32_t new_value_base) {
SetValuePart(VALUE_BASE_MASK, new_value_base);
}
bool PendingWrite() const {
const uint32_t pending_write = GetValuePart(PENDING_WRITE_MASK);
return pending_write != 0;
}
void SetPendingWrite() {
SetValuePart(PENDING_WRITE_MASK, PENDING_WRITE_MASK);
}
void ClearPendingWrite() { ClearValuePart(PENDING_WRITE_MASK); }
uint32_t GetDelCounter() const { return GetValuePart(DEL_COUNTER_MASK); }
uint32_t NextDelCounter() const {
return GetIncrementedValuePart(DEL_COUNTER_MASK, DEL_COUNTER_DELTA);
}
void SetDelCounter(uint32_t new_del_counter) {
SetValuePart(DEL_COUNTER_MASK, new_del_counter);
}
bool PendingDelete() const {
const uint32_t pending_del = GetValuePart(PENDING_DEL_MASK);
return pending_del != 0;
}
void SetPendingDel() { SetValuePart(PENDING_DEL_MASK, PENDING_DEL_MASK); }
void ClearPendingDel() { ClearValuePart(PENDING_DEL_MASK); }
bool IsDeleted() const {
const uint32_t deleted = GetValuePart(DEL_MASK);
return deleted != 0;
}
void SetDeleted() { SetValuePart(DEL_MASK, DEL_MASK); }
void ClearDeleted() { ClearValuePart(DEL_MASK); }
uint32_t GetFinalValueBase() const;
uint32_t GetFinalDelCounter() const;
private:
static bool IsValuePartValid(uint32_t value_part, uint32_t value_part_mask) {
return (value_part & (~value_part_mask)) == 0;
}
// The 32-bit expected_value_ is divided into following parts:
// Bit 0 - 14: value base
static constexpr uint32_t VALUE_BASE_MASK = 0x7fff;
static constexpr uint32_t VALUE_BASE_DELTA = 1;
// Bit 15: whether write to this value base is pending (0 equals `false`)
static constexpr uint32_t PENDING_WRITE_MASK = (uint32_t)1 << 15;
// Bit 16 - 29: deletion counter (i.e, number of times this value base has
// been deleted)
static constexpr uint32_t DEL_COUNTER_MASK = 0x3fff0000;
static constexpr uint32_t DEL_COUNTER_DELTA = (uint32_t)1 << 16;
// Bit 30: whether deletion of this value base is pending (0 equals `false`)
static constexpr uint32_t PENDING_DEL_MASK = (uint32_t)1 << 30;
// Bit 31: whether this value base is deleted (0 equals `false`)
static constexpr uint32_t DEL_MASK = (uint32_t)1 << 31;
uint32_t GetValuePart(uint32_t value_part_mask) const {
return expected_value_ & value_part_mask;
}
uint32_t GetIncrementedValuePart(uint32_t value_part_mask,
uint32_t value_part_delta) const {
uint32_t current_value_part = GetValuePart(value_part_mask);
ExpectedValue temp_expected_value(current_value_part + value_part_delta);
return temp_expected_value.GetValuePart(value_part_mask);
}
void SetValuePart(uint32_t value_part_mask, uint32_t new_value_part) {
assert(IsValuePartValid(new_value_part, value_part_mask));
ClearValuePart(value_part_mask);
expected_value_ |= new_value_part;
}
void ClearValuePart(uint32_t value_part_mask) {
expected_value_ &= (~value_part_mask);
}
uint32_t expected_value_;
};
// `PendingExpectedValue` represents the expected value of a key undergoing a
// pending operation in db stress.
//
// After a `PendingExpectedValue` object is created, either `Rollback` or
// `Commit` should be called to close its pending state before it's destructed.
// In case no pending state was introduced while creating this
// `PendingExpectedValue` and user want to ignore the unclosed pending state,
// `PermitUnclosedPendingState` should be called explicitly.
// This class is not thread-safe.
class PendingExpectedValue {
public:
explicit PendingExpectedValue(std::atomic<uint32_t>* value_ptr,
ExpectedValue orig_value,
ExpectedValue final_value)
: value_ptr_(value_ptr),
orig_value_(orig_value),
final_value_(final_value),
pending_state_closed_(false) {}
PendingExpectedValue(const PendingExpectedValue& other)
: value_ptr_(other.value_ptr_),
orig_value_(other.orig_value_),
final_value_(other.final_value_),
pending_state_closed_(false) {
other.ClosePendingState();
}
PendingExpectedValue(PendingExpectedValue&& other) noexcept
: value_ptr_(std::move(other.value_ptr_)),
orig_value_(std::move(other.orig_value_)),
final_value_(std::move(other.final_value_)),
pending_state_closed_(false) {
other.ClosePendingState();
}
PendingExpectedValue& operator=(const PendingExpectedValue& other) {
if (this != &other) {
other.ClosePendingState();
value_ptr_ = other.value_ptr_;
orig_value_ = other.orig_value_;
final_value_ = other.final_value_;
pending_state_closed_ = false;
}
return *this;
}
PendingExpectedValue& operator=(PendingExpectedValue&& other) {
if (this != &other) {
other.ClosePendingState();
value_ptr_ = std::move(other.value_ptr_);
orig_value_ = std::move(other.orig_value_);
final_value_ = std::move(other.final_value_);
pending_state_closed_ = false;
}
return *this;
}
~PendingExpectedValue() { assert(pending_state_closed_); }
void Commit() {
assert(!pending_state_closed_);
ClosePendingState();
// To prevent low-level instruction reordering that results
// in setting expected value happens before db write
std::atomic_thread_fence(std::memory_order_release);
value_ptr_->store(final_value_.Read());
}
// Rollbacks the key to its original state.
// This rollbacks the pending state created in `ExpectedState::Precommit`,
// such as pending delete, pending put. If `ExpectedState::Precommit()` is not
// called before creating this `PendingExpectedValue`, this is a no-op.
void Rollback() {
assert(!pending_state_closed_);
ClosePendingState();
// To prevent low-level instruction reordering that results
// in setting expected value happens before db write
std::atomic_thread_fence(std::memory_order_release);
value_ptr_->store(orig_value_.Read());
}
void PermitUnclosedPendingState() const {
assert(!pending_state_closed_);
ClosePendingState();
}
uint32_t GetFinalValueBase() { return final_value_.GetValueBase(); }
private:
inline void ClosePendingState() const { pending_state_closed_ = true; }
std::atomic<uint32_t>* value_ptr_;
ExpectedValue orig_value_;
ExpectedValue final_value_;
mutable bool pending_state_closed_;
};
// `ExpectedValueHelper` provides utils to parse `ExpectedValue` to obtain
// useful info about it in db stress
class ExpectedValueHelper {
public:
// Return whether the key associated with `pre_read_expected_value` and
// `post_read_expected_value` is expected not to exist from begining till the
// end of the read
//
// The negation of `MustHaveNotExisted()` is "may have not existed".
// To assert some key must have existsed, please use `MustHaveExisted()`
static bool MustHaveNotExisted(ExpectedValue pre_read_expected_value,
ExpectedValue post_read_expected_value);
// Return whether the key associated with `pre_read_expected_value` and
// `post_read_expected_value` is expected to exist from begining till the end
// of the read.
//
// The negation of `MustHaveExisted()` is "may have existed".
// To assert some key must have not existsed, please use
// `MustHaveNotExisted()`
static bool MustHaveExisted(ExpectedValue pre_read_expected_value,
ExpectedValue post_read_expected_value);
// Return whether the `value_base` falls within the expected value base
static bool InExpectedValueBaseRange(uint32_t value_base,
ExpectedValue pre_read_expected_value,
ExpectedValue post_read_expected_value);
};
} // namespace ROCKSDB_NAMESPACE
#endif // GFLAGS