You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/db_stress_tool/db_stress_common.h

652 lines
23 KiB

// 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.
//
// The test uses an array to compare against values written to the database.
// Keys written to the array are in 1:1 correspondence to the actual values in
// the database according to the formula in the function GenerateValue.
// Space is reserved in the array from 0 to FLAGS_max_key and values are
// randomly written/deleted/read from those positions. During verification we
// compare all the positions in the array. To shorten/elongate the running
// time, you could change the settings: FLAGS_max_key, FLAGS_ops_per_thread,
// (sometimes also FLAGS_threads).
//
// NOTE that if FLAGS_test_batches_snapshots is set, the test will have
// different behavior. See comment of the flag for details.
#ifdef GFLAGS
#pragma once
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/types.h>
#include <algorithm>
#include <array>
#include <chrono>
#include <cinttypes>
#include <exception>
#include <queue>
#include <thread>
#include "db/db_impl/db_impl.h"
#include "db/version_set.h"
#include "db_stress_tool/db_stress_env_wrapper.h"
#include "db_stress_tool/db_stress_listener.h"
#include "db_stress_tool/db_stress_shared_state.h"
#include "db_stress_tool/db_stress_test_base.h"
#include "logging/logging.h"
#include "monitoring/histogram.h"
#include "options/options_helper.h"
#include "port/port.h"
#include "rocksdb/cache.h"
#include "rocksdb/env.h"
#include "rocksdb/slice.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/statistics.h"
#include "rocksdb/utilities/backup_engine.h"
#include "rocksdb/utilities/checkpoint.h"
#include "rocksdb/utilities/db_ttl.h"
#include "rocksdb/utilities/debug.h"
#include "rocksdb/utilities/options_util.h"
#include "rocksdb/utilities/transaction.h"
#include "rocksdb/utilities/transaction_db.h"
#include "rocksdb/write_batch.h"
#include "test_util/testutil.h"
#include "util/coding.h"
#include "util/compression.h"
#include "util/crc32c.h"
#include "util/gflags_compat.h"
#include "util/mutexlock.h"
#include "util/random.h"
#include "util/string_util.h"
#include "utilities/blob_db/blob_db.h"
#include "utilities/fault_injection_fs.h"
#include "utilities/merge_operators.h"
using GFLAGS_NAMESPACE::ParseCommandLineFlags;
using GFLAGS_NAMESPACE::RegisterFlagValidator;
using GFLAGS_NAMESPACE::SetUsageMessage;
DECLARE_uint64(seed);
DECLARE_bool(read_only);
DECLARE_int64(max_key);
DECLARE_double(hot_key_alpha);
DECLARE_int32(max_key_len);
DECLARE_string(key_len_percent_dist);
DECLARE_int32(key_window_scale_factor);
DECLARE_int32(column_families);
DECLARE_string(options_file);
DECLARE_int64(active_width);
DECLARE_bool(test_batches_snapshots);
DECLARE_bool(atomic_flush);
Add manual_wal_flush, FlushWAL() to stress/crash test (#10698) Summary: **Context/Summary:** Introduce `manual_wal_flush_one_in` as titled. - When `manual_wal_flush_one_in > 0`, we also need tracing to correctly verify recovery because WAL data can be lost in this case when `FlushWAL()` is not explicitly called by users of RocksDB (in our case, db stress) and the recovery from such potential WAL data loss is a prefix recovery that requires tracing to verify. As another consequence, we need to disable features can't run under unsync data loss with `manual_wal_flush_one_in` Incompatibilities fixed along the way: ``` db_stress: db/db_impl/db_impl_open.cc:2063: static rocksdb::Status rocksdb::DBImpl::Open(const rocksdb::DBOptions&, const string&, const std::vector<rocksdb::ColumnFamilyDescriptor>&, std::vector<rocksdb::ColumnFamilyHandle*>*, rocksdb::DB**, bool, bool): Assertion `impl->TEST_WALBufferIsEmpty()' failed. ``` - It turns out that `Writer::AddCompressionTypeRecord` before this assertion `EmitPhysicalRecord(kSetCompressionType, encode.data(), encode.size());` but do not trigger flush if `manual_wal_flush` is set . This leads to `impl->TEST_WALBufferIsEmpty()' is false. - As suggested, assertion is removed and violation case is handled by `FlushWAL(sync=true)` along with refactoring `TEST_WALBufferIsEmpty()` to be `WALBufferIsEmpty()` since it is used in prod code now. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10698 Test Plan: - Locally running `python3 tools/db_crashtest.py blackbox --manual_wal_flush_one_in=1 --manual_wal_flush=1 --sync_wal_one_in=100 --atomic_flush=1 --flush_one_in=100 --column_families=3` - Joined https://github.com/facebook/rocksdb/pull/10624 in auto CI testings with all RocksDB stress/crash test jobs Reviewed By: ajkr Differential Revision: D39593752 Pulled By: ajkr fbshipit-source-id: 3a2135bb792c52d2ffa60257d4fbc557fb04d2ce
2 years ago
DECLARE_int32(manual_wal_flush_one_in);
DECLARE_bool(test_cf_consistency);
DECLARE_bool(test_multi_ops_txns);
DECLARE_int32(threads);
DECLARE_int32(ttl);
DECLARE_int32(value_size_mult);
DECLARE_int32(compaction_readahead_size);
DECLARE_bool(enable_pipelined_write);
DECLARE_bool(verify_before_write);
DECLARE_bool(histogram);
DECLARE_bool(destroy_db_initially);
DECLARE_bool(verbose);
DECLARE_bool(progress_reports);
DECLARE_uint64(db_write_buffer_size);
DECLARE_int32(write_buffer_size);
DECLARE_int32(max_write_buffer_number);
DECLARE_int32(min_write_buffer_number_to_merge);
DECLARE_int32(max_write_buffer_number_to_maintain);
DECLARE_int64(max_write_buffer_size_to_maintain);
DECLARE_double(memtable_prefix_bloom_size_ratio);
DECLARE_bool(memtable_whole_key_filtering);
DECLARE_int32(open_files);
DECLARE_int64(compressed_cache_size);
Avoid overwriting options loaded from OPTIONS (#9943) Summary: This is similar to https://github.com/facebook/rocksdb/issues/9862, including the following fixes/refactoring: 1. If OPTIONS file is specified via `-options_file`, majority of options will be loaded from the file. We should not overwrite options that have been loaded from the file. Instead, we configure only fields of options which are shared objects and not set by the OPTIONS file. We also configure a few fields, e.g. `create_if_missing` necessary for stress test to run. 2. Refactor options initialization into three functions, `InitializeOptionsFromFile()`, `InitializeOptionsFromFlags()` and `InitializeOptionsGeneral()` similar to db_bench. I hope they can be shared in the future. The high-level logic is as follows: ```cpp if (!InitializeOptionsFromFile(...)) { InitializeOptionsFromFlags(...); } InitializeOptionsGeneral(...); ``` 3. Currently, the setting for `block_cache_compressed` does not seem correct because it by default specifies a size of `numeric_limits<size_t>::max()` ((size_t)-1). According to code comments, `-1` indicates default value, which should be referring to `num_shard_bits` argument. 4. Clarify `fail_if_options_file_error`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9943 Test Plan: 1. make check 2. Run stress tests, and manually check generated OPTIONS file and compare them with input OPTIONS files Reviewed By: jay-zhuang Differential Revision: D36133769 Pulled By: riversand963 fbshipit-source-id: 35dacdc090a0a72c922907170cd132b9ecaa073e
3 years ago
DECLARE_int32(compressed_cache_numshardbits);
DECLARE_int32(compaction_style);
DECLARE_int32(compaction_pri);
DECLARE_int32(num_levels);
DECLARE_int32(level0_file_num_compaction_trigger);
DECLARE_int32(level0_slowdown_writes_trigger);
DECLARE_int32(level0_stop_writes_trigger);
DECLARE_int32(block_size);
DECLARE_int32(format_version);
DECLARE_int32(index_block_restart_interval);
Improve stress test for transactions (#9568) Summary: Test only, no change to functionality. Extremely low risk of library regression. Update test key generation by maintaining existing and non-existing keys. Update db_crashtest.py to drive multiops_txn stress test for both write-committed and write-prepared. Add a make target 'blackbox_crash_test_with_multiops_txn'. Running the following commands caught the bug exposed in https://github.com/facebook/rocksdb/issues/9571. ``` $rm -rf /tmp/rocksdbtest/* $./db_stress -progress_reports=0 -test_multi_ops_txns -use_txn -clear_column_family_one_in=0 \ -column_families=1 -writepercent=0 -delpercent=0 -delrangepercent=0 -customopspercent=60 \ -readpercent=20 -prefixpercent=0 -iterpercent=20 -reopen=0 -ops_per_thread=1000 -ub_a=10000 \ -ub_c=100 -destroy_db_initially=0 -key_spaces_path=/dev/shm/key_spaces_desc -threads=32 -read_fault_one_in=0 $./db_stress -progress_reports=0 -test_multi_ops_txns -use_txn -clear_column_family_one_in=0 -column_families=1 -writepercent=0 -delpercent=0 -delrangepercent=0 -customopspercent=60 -readpercent=20 \ -prefixpercent=0 -iterpercent=20 -reopen=0 -ops_per_thread=1000 -ub_a=10000 -ub_c=100 -destroy_db_initially=0 \ -key_spaces_path=/dev/shm/key_spaces_desc -threads=32 -read_fault_one_in=0 ``` Running the following command caught a bug which will be fixed in https://github.com/facebook/rocksdb/issues/9648 . ``` $TEST_TMPDIR=/dev/shm make blackbox_crash_test_with_multiops_wc_txn ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9568 Reviewed By: jay-zhuang Differential Revision: D34308154 Pulled By: riversand963 fbshipit-source-id: 99ff1b65c19b46c471d2f2d3b47adcd342a1b9e7
3 years ago
DECLARE_bool(disable_auto_compactions);
DECLARE_int32(max_background_compactions);
DECLARE_int32(num_bottom_pri_threads);
DECLARE_int32(compaction_thread_pool_adjust_interval);
DECLARE_int32(compaction_thread_pool_variations);
DECLARE_int32(max_background_flushes);
DECLARE_int32(universal_size_ratio);
DECLARE_int32(universal_min_merge_width);
DECLARE_int32(universal_max_merge_width);
DECLARE_int32(universal_max_size_amplification_percent);
DECLARE_int32(clear_column_family_one_in);
DECLARE_int32(get_live_files_one_in);
DECLARE_int32(get_sorted_wal_files_one_in);
DECLARE_int32(get_current_wal_file_one_in);
DECLARE_int32(set_options_one_in);
DECLARE_int32(set_in_place_one_in);
DECLARE_int64(cache_size);
DECLARE_int32(cache_numshardbits);
DECLARE_bool(cache_index_and_filter_blocks);
Rewrite memory-charging feature's option API (#9926) Summary: **Context:** Previous PR https://github.com/facebook/rocksdb/pull/9748, https://github.com/facebook/rocksdb/pull/9073, https://github.com/facebook/rocksdb/pull/8428 added separate flag for each charged memory area. Such API design is not scalable as we charge more and more memory areas. Also, we foresee an opportunity to consolidate this feature with other cache usage related features such as `cache_index_and_filter_blocks` using `CacheEntryRole`. Therefore we decided to consolidate all these flags with `CacheUsageOptions cache_usage_options` and this PR serves as the first step by consolidating memory-charging related flags. **Summary:** - Replaced old API reference with new ones, including making `kCompressionDictionaryBuildingBuffer` opt-out and added a unit test for that - Added missing db bench/stress test for some memory charging features - Renamed related test suite to indicate they are under the same theme of memory charging - Refactored a commonly used mocked cache component in memory charging related tests to reduce code duplication - Replaced the phrases "memory tracking" / "cache reservation" (other than CacheReservationManager-related ones) with "memory charging" for standard description of this feature. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9926 Test Plan: - New unit test for opt-out `kCompressionDictionaryBuildingBuffer` `TEST_F(ChargeCompressionDictionaryBuildingBufferTest, Basic)` - New unit test for option validation/sanitization `TEST_F(CacheUsageOptionsOverridesTest, SanitizeAndValidateOptions)` - CI - db bench (in case querying new options introduces regression) **+0.5% micros/op**: `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_compression_dictionary_building_buffer=1(remove this for comparison) -compression_max_dict_bytes=10000 -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 | egrep 'fillseq'` #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 3.9711 | 0.264408 | 3.9914 | 0.254563 | 0.5111933721 20 | 3.83905 | 0.0664488 | 3.8251 | 0.0695456 | **-0.3633711465** 40 | 3.86625 | 0.136669 | 3.8867 | 0.143765 | **0.5289363078** - db_stress: `python3 tools/db_crashtest.py blackbox -charge_compression_dictionary_building_buffer=1 -charge_filter_construction=1 -charge_table_reader=1 -cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D36054712 Pulled By: hx235 fbshipit-source-id: d406e90f5e0c5ea4dbcb585a484ad9302d4302af
3 years ago
DECLARE_bool(charge_compression_dictionary_building_buffer);
DECLARE_bool(charge_filter_construction);
DECLARE_bool(charge_table_reader);
Account memory of FileMetaData in global memory limit (#9924) Summary: **Context/Summary:** As revealed by heap profiling, allocation of `FileMetaData` for [newly created file added to a Version](https://github.com/facebook/rocksdb/pull/9924/files#diff-a6aa385940793f95a2c5b39cc670bd440c4547fa54fd44622f756382d5e47e43R774) can consume significant heap memory. This PR is to account that toward our global memory limit based on block cache capacity. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9924 Test Plan: - Previous `make check` verified there are only 2 places where the memory of the allocated `FileMetaData` can be released - New unit test `TEST_P(ChargeFileMetadataTestWithParam, Basic)` - db bench (CPU cost of `charge_file_metadata` in write and compact) - **write micros/op: -0.24%** : `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_file_metadata=1 (remove this option for pre-PR) -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 | egrep 'fillseq'` - **compact micros/op -0.87%** : `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_file_metadata=1 -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 -numdistinct=1000 && ./db_bench -benchmarks=compact -db=$TEST_TMPDIR -use_existing_db=1 -charge_file_metadata=1 -disable_auto_compactions=1 | egrep 'compact'` table 1 - write #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 3.9711 | 0.264408 | 3.9914 | 0.254563 | 0.5111933721 20 | 3.83905 | 0.0664488 | 3.8251 | 0.0695456 | -0.3633711465 40 | 3.86625 | 0.136669 | 3.8867 | 0.143765 | 0.5289363078 80 | 3.87828 | 0.119007 | 3.86791 | 0.115674 | **-0.2673865734** 160 | 3.87677 | 0.162231 | 3.86739 | 0.16663 | **-0.2419539978** table 2 - compact #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 2,399,650.00 | 96,375.80 | 2,359,537.00 | 53,243.60 | -1.67 20 | 2,410,480.00 | 89,988.00 | 2,433,580.00 | 91,121.20 | 0.96 40 | 2.41E+06 | 121811 | 2.39E+06 | 131525 | **-0.96** 80 | 2.40E+06 | 134503 | 2.39E+06 | 108799 | **-0.78** - stress test: `python3 tools/db_crashtest.py blackbox --charge_file_metadata=1 --cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D36055583 Pulled By: hx235 fbshipit-source-id: b60eab94707103cb1322cf815f05810ef0232625
3 years ago
DECLARE_bool(charge_file_metadata);
DECLARE_bool(charge_blob_cache);
DECLARE_int32(top_level_index_pinning);
DECLARE_int32(partition_pinning);
DECLARE_int32(unpartitioned_pinning);
DECLARE_string(cache_type);
DECLARE_uint64(subcompactions);
DECLARE_uint64(periodic_compaction_seconds);
DECLARE_uint64(compaction_ttl);
Fix FIFO causing overlapping seqnos in L0 files due to overlapped seqnos between ingested files and memtable's (#10777) Summary: **Context:** Same as https://github.com/facebook/rocksdb/pull/5958#issue-511150930 but apply the fix to FIFO Compaction case Repro: ``` COERCE_CONTEXT_SWICH=1 make -j56 db_stress ./db_stress --acquire_snapshot_one_in=0 --adaptive_readahead=0 --allow_data_in_errors=True --async_io=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=18 --bottommost_compression_type=disable --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_size=8388608 --cache_type=lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=1 --charge_table_reader=1 --checkpoint_one_in=0 --checksum_type=kCRC32c --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=0 --compact_range_one_in=1000 --compaction_pri=3 --open_files=-1 --compaction_style=2 --fifo_allow_compaction=1 --compaction_ttl=0 --compression_max_dict_buffer_bytes=8388607 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=zlib --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=/dev/shm/rocksdb_test0/rocksdb_crashtest_whitebox --db_write_buffer_size=8388608 --delpercent=4 --delrangepercent=1 --destroy_db_initially=1 --detect_filter_construct_corruption=0 --disable_wal=0 --enable_compaction_filter=0 --enable_pipelined_write=1 --fail_if_options_file_error=1 --file_checksum_impl=none --flush_one_in=1000 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=0 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=15 --index_type=3 --ingest_external_file_one_in=100 --initial_auto_readahead_size=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --log2_keys_per_lock=10 --long_running_snapshots=0 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=16384 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=100000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=1048576 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=4194304 --memtable_prefix_bloom_size_ratio=0.5 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=1 --memtablerep=skip_list --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --num_levels=1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=32 --open_write_fault_one_in=0 --ops_per_thread=200000 --optimize_filters_for_memory=0 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=1 --pause_background_one_in=0 --periodic_compaction_seconds=0 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --progress_reports=0 --read_fault_one_in=0 --readahead_size=16384 --readpercent=45 --recycle_log_file_num=1 --reopen=20 --ribbon_starting_level=999 --snapshot_hold_ops=1000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --subcompactions=2 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=3 --unpartitioned_pinning=0 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=1 --use_merge=0 --use_multiget=1 --user_timestamp_size=0 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=0 --verify_db_one_in=1000 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=0 --wal_compression=zstd --write_buffer_size=524288 --write_dbid_to_manifest=0 --writepercent=35 put or merge error: Corruption: force_consistency_checks(DEBUG): VersionBuilder: L0 file https://github.com/facebook/rocksdb/issues/479 with seqno 23711 29070 vs. file https://github.com/facebook/rocksdb/issues/482 with seqno 27138 29049 ``` **Summary:** FIFO only does intra-L0 compaction in the following four cases. For other cases, FIFO drops data instead of compacting on data, which is irrelevant to the overlapping seqno issue we are solving. - [FIFOCompactionPicker::PickSizeCompaction](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L155) when `total size < compaction_options_fifo.max_table_files_size` and `compaction_options_fifo.allow_compaction == true` - For this path, we simply reuse the fix in `FindIntraL0Compaction` https://github.com/facebook/rocksdb/pull/5958/files#diff-c261f77d6dd2134333c4a955c311cf4a196a08d3c2bb6ce24fd6801407877c89R56 - This path was not stress-tested at all. Therefore we covered `fifo.allow_compaction` in stress test to surface the overlapping seqno issue we are fixing here. - [FIFOCompactionPicker::PickCompactionToWarm](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L313) when `compaction_options_fifo.age_for_warm > 0` - For this path, we simply replicate the idea in https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and skip files of largest seqno greater than `earliest_mem_seqno` - This path was not stress-tested at all. However covering `age_for_warm` option worths a separate PR to deal with db stress compatibility. Therefore we manually tested this path for this PR - [FIFOCompactionPicker::CompactRange](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L365) that ends up picking one of the above two compactions - [CompactionPicker::CompactFiles](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker.cc#L378) - Since `SanitizeCompactionInputFiles()` will be called [before](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker.h#L111-L113) `CompactionPicker::CompactFiles` , we simply replicate the idea in https://github.com/facebook/rocksdb/pull/5958#issue-511150930 in `SanitizeCompactionInputFiles()`. To simplify implementation, we return `Stats::Abort()` on encountering seqno-overlapped file when doing compaction to L0 instead of skipping the file and proceed with the compaction. Some additional clean-up included in this PR: - Renamed `earliest_memtable_seqno` to `earliest_mem_seqno` for consistent naming - Added comment about `earliest_memtable_seqno` in related APIs - Made parameter `earliest_memtable_seqno` constant and required Pull Request resolved: https://github.com/facebook/rocksdb/pull/10777 Test Plan: - make check - New unit test `TEST_P(DBCompactionTestFIFOCheckConsistencyWithParam, FlushAfterIntraL0CompactionWithIngestedFile)`corresponding to the above 4 cases, which will fail accordingly without the fix - Regular CI stress run on this PR + stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761 and on FIFO compaction only Reviewed By: ajkr Differential Revision: D40090485 Pulled By: hx235 fbshipit-source-id: 52624186952ee7109117788741aeeac86b624a4f
2 years ago
DECLARE_bool(fifo_allow_compaction);
DECLARE_bool(allow_concurrent_memtable_write);
Memtable sampling for mempurge heuristic. (#8628) Summary: Changes the API of the MemPurge process: the `bool experimental_allow_mempurge` and `experimental_mempurge_policy` flags have been replaced by a `double experimental_mempurge_threshold` option. This change of API reflects another major change introduced in this PR: the MemPurgeDecider() function now works by sampling the memtables being flushed to estimate the overall amount of useful payload (payload minus the garbage), and then compare this useful payload estimate with the `double experimental_mempurge_threshold` value. Therefore, when the value of this flag is `0.0` (default value), mempurge is simply deactivated. On the other hand, a value of `DBL_MAX` would be equivalent to always going through a mempurge regardless of the garbage ratio estimate. At the moment, a `double experimental_mempurge_threshold` value else than 0.0 or `DBL_MAX` is opnly supported`with the `SkipList` memtable representation. Regarding the sampling, this PR includes the introduction of a `MemTable::UniqueRandomSample` function that collects (approximately) random entries from the memtable by using the new `SkipList::Iterator::RandomSeek()` under the hood, or by iterating through each memtable entry, depending on the target sample size and the total number of entries. The unit tests have been readapted to support this new API. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8628 Reviewed By: pdillinger Differential Revision: D30149315 Pulled By: bjlemaire fbshipit-source-id: 1feef5390c95db6f4480ab4434716533d3947f27
3 years ago
DECLARE_double(experimental_mempurge_threshold);
DECLARE_bool(enable_write_thread_adaptive_yield);
DECLARE_int32(reopen);
DECLARE_double(bloom_bits);
Add Bloom/Ribbon hybrid API support (#8679) Summary: This is essentially resurrection and fixing of the part of https://github.com/facebook/rocksdb/issues/8198 that was reverted in https://github.com/facebook/rocksdb/issues/8212, using data added in https://github.com/facebook/rocksdb/issues/8246. Basically, when configuring Ribbon filter, you can specify an LSM level before which Bloom will be used instead of Ribbon. But Bloom is only considered for Leveled and Universal compaction styles and file going into a known LSM level. This way, SST file writer, FIFO compaction, etc. use Ribbon filter as you would expect with NewRibbonFilterPolicy. So that this can be controlled with a single int value and so that flushes can be distinguished from intra-L0, we consider flush to go to level -1 for the purposes of this option. (Explained in API comment.) I also expect the most common and recommended Ribbon configuration to use Bloom during flush, to minimize slowing down writes and because according to my estimates, Ribbon only pays off if the structure lives in memory for more than an hour. Thus, I have changed the default for NewRibbonFilterPolicy to be this mild hybrid configuration. I don't really want to add something like NewHybridFilterPolicy because at least the mild hybrid configuration (Bloom for flush, Ribbon otherwise) should be considered a natural choice. C APIs also updated, but because they don't support overloading, rocksdb_filterpolicy_create_ribbon is kept pure ribbon for clarity and rocksdb_filterpolicy_create_ribbon_hybrid must be called for a hybrid configuration. While touching C API, I changed bits per key options from int to double. BuiltinFilterPolicy is needed so that LevelThresholdFilterPolicy doesn't inherit unused fields from BloomFilterPolicy. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8679 Test Plan: new + updated tests, including crash test Reviewed By: jay-zhuang Differential Revision: D30445797 Pulled By: pdillinger fbshipit-source-id: 6f5aeddfd6d79f7e55493b563c2d1d2d568892e1
3 years ago
DECLARE_int32(ribbon_starting_level);
DECLARE_bool(partition_filters);
Minimize memory internal fragmentation for Bloom filters (#6427) Summary: New experimental option BBTO::optimize_filters_for_memory builds filters that maximize their use of "usable size" from malloc_usable_size, which is also used to compute block cache charges. Rather than always "rounding up," we track state in the BloomFilterPolicy object to mix essentially "rounding down" and "rounding up" so that the average FP rate of all generated filters is the same as without the option. (YMMV as heavily accessed filters might be unluckily lower accuracy.) Thus, the option near-minimizes what the block cache considers as "memory used" for a given target Bloom filter false positive rate and Bloom filter implementation. There are no forward or backward compatibility issues with this change, though it only works on the format_version=5 Bloom filter. With Jemalloc, we see about 10% reduction in memory footprint (and block cache charge) for Bloom filters, but 1-2% increase in storage footprint, due to encoding efficiency losses (FP rate is non-linear with bits/key). Why not weighted random round up/down rather than state tracking? By only requiring malloc_usable_size, we don't actually know what the next larger and next smaller usable sizes for the allocator are. We pick a requested size, accept and use whatever usable size it has, and use the difference to inform our next choice. This allows us to narrow in on the right balance without tracking/predicting usable sizes. Why not weight history of generated filter false positive rates by number of keys? This could lead to excess skew in small filters after generating a large filter. Results from filter_bench with jemalloc (irrelevant details omitted): (normal keys/filter, but high variance) $ ./filter_bench -quick -impl=2 -average_keys_per_filter=30000 -vary_key_count_ratio=0.9 Build avg ns/key: 29.6278 Number of filters: 5516 Total size (MB): 200.046 Reported total allocated memory (MB): 220.597 Reported internal fragmentation: 10.2732% Bits/key stored: 10.0097 Average FP rate %: 0.965228 $ ./filter_bench -quick -impl=2 -average_keys_per_filter=30000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory Build avg ns/key: 30.5104 Number of filters: 5464 Total size (MB): 200.015 Reported total allocated memory (MB): 200.322 Reported internal fragmentation: 0.153709% Bits/key stored: 10.1011 Average FP rate %: 0.966313 (very few keys / filter, optimization not as effective due to ~59 byte internal fragmentation in blocked Bloom filter representation) $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000 -vary_key_count_ratio=0.9 Build avg ns/key: 29.5649 Number of filters: 162950 Total size (MB): 200.001 Reported total allocated memory (MB): 224.624 Reported internal fragmentation: 12.3117% Bits/key stored: 10.2951 Average FP rate %: 0.821534 $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory Build avg ns/key: 31.8057 Number of filters: 159849 Total size (MB): 200 Reported total allocated memory (MB): 208.846 Reported internal fragmentation: 4.42297% Bits/key stored: 10.4948 Average FP rate %: 0.811006 (high keys/filter) $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000000 -vary_key_count_ratio=0.9 Build avg ns/key: 29.7017 Number of filters: 164 Total size (MB): 200.352 Reported total allocated memory (MB): 221.5 Reported internal fragmentation: 10.5552% Bits/key stored: 10.0003 Average FP rate %: 0.969358 $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory Build avg ns/key: 30.7131 Number of filters: 160 Total size (MB): 200.928 Reported total allocated memory (MB): 200.938 Reported internal fragmentation: 0.00448054% Bits/key stored: 10.1852 Average FP rate %: 0.963387 And from db_bench (block cache) with jemalloc: $ ./db_bench -db=/dev/shm/dbbench.no_optimize -benchmarks=fillrandom -format_version=5 -value_size=90 -bloom_bits=10 -num=2000000 -threads=8 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false $ ./db_bench -db=/dev/shm/dbbench -benchmarks=fillrandom -format_version=5 -value_size=90 -bloom_bits=10 -num=2000000 -threads=8 -optimize_filters_for_memory -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false $ (for FILE in /dev/shm/dbbench.no_optimize/*.sst; do ./sst_dump --file=$FILE --show_properties | grep 'filter block' ; done) | awk '{ t += $4; } END { print t; }' 17063835 $ (for FILE in /dev/shm/dbbench/*.sst; do ./sst_dump --file=$FILE --show_properties | grep 'filter block' ; done) | awk '{ t += $4; } END { print t; }' 17430747 $ #^ 2.1% additional filter storage $ ./db_bench -db=/dev/shm/dbbench.no_optimize -use_existing_db -benchmarks=readrandom,stats -statistics -bloom_bits=10 -num=2000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false -duration=10 -cache_index_and_filter_blocks -cache_size=1000000000 rocksdb.block.cache.index.add COUNT : 33 rocksdb.block.cache.index.bytes.insert COUNT : 8440400 rocksdb.block.cache.filter.add COUNT : 33 rocksdb.block.cache.filter.bytes.insert COUNT : 21087528 rocksdb.bloom.filter.useful COUNT : 4963889 rocksdb.bloom.filter.full.positive COUNT : 1214081 rocksdb.bloom.filter.full.true.positive COUNT : 1161999 $ #^ 1.04 % observed FP rate $ ./db_bench -db=/dev/shm/dbbench -use_existing_db -benchmarks=readrandom,stats -statistics -bloom_bits=10 -num=2000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false -optimize_filters_for_memory -duration=10 -cache_index_and_filter_blocks -cache_size=1000000000 rocksdb.block.cache.index.add COUNT : 33 rocksdb.block.cache.index.bytes.insert COUNT : 8448592 rocksdb.block.cache.filter.add COUNT : 33 rocksdb.block.cache.filter.bytes.insert COUNT : 18220328 rocksdb.bloom.filter.useful COUNT : 5360933 rocksdb.bloom.filter.full.positive COUNT : 1321315 rocksdb.bloom.filter.full.true.positive COUNT : 1262999 $ #^ 1.08 % observed FP rate, 13.6% less memory usage for filters (Due to specific key density, this example tends to generate filters that are "worse than average" for internal fragmentation. "Better than average" cases can show little or no improvement.) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6427 Test Plan: unit test added, 'make check' with gcc, clang and valgrind Reviewed By: siying Differential Revision: D22124374 Pulled By: pdillinger fbshipit-source-id: f3e3aa152f9043ddf4fae25799e76341d0d8714e
5 years ago
DECLARE_bool(optimize_filters_for_memory);
Detect (new) Bloom/Ribbon Filter construction corruption (#9342) Summary: Note: rebase on and merge after https://github.com/facebook/rocksdb/pull/9349, https://github.com/facebook/rocksdb/pull/9345, (optional) https://github.com/facebook/rocksdb/pull/9393 **Context:** (Quoted from pdillinger) Layers of information during new Bloom/Ribbon Filter construction in building block-based tables includes the following: a) set of keys to add to filter b) set of hashes to add to filter (64-bit hash applied to each key) c) set of Bloom indices to set in filter, with duplicates d) set of Bloom indices to set in filter, deduplicated e) final filter and its checksum This PR aims to detect corruption (e.g, unexpected hardware/software corruption on data structures residing in the memory for a long time) from b) to e) and leave a) as future works for application level. - b)'s corruption is detected by verifying the xor checksum of the hash entries calculated as the entries accumulate before being added to the filter. (i.e, `XXPH3FilterBitsBuilder::MaybeVerifyHashEntriesChecksum()`) - c) - e)'s corruption is detected by verifying the hash entries indeed exists in the constructed filter by re-querying these hash entries in the filter (i.e, `FilterBitsBuilder::MaybePostVerify()`) after computing the block checksum (except for PartitionFilter, which is done right after each `FilterBitsBuilder::Finish` for impl simplicity - see code comment for more). For this stage of detection, we assume hash entries are not corrupted after checking on b) since the time interval from b) to c) is relatively short IMO. Option to enable this feature of detection is `BlockBasedTableOptions::detect_filter_construct_corruption` which is false by default. **Summary:** - Implemented new functions `XXPH3FilterBitsBuilder::MaybeVerifyHashEntriesChecksum()` and `FilterBitsBuilder::MaybePostVerify()` - Ensured hash entries, final filter and banding and their [cache reservation ](https://github.com/facebook/rocksdb/issues/9073) are released properly despite corruption - See [Filter.construction.artifacts.release.point.pdf ](https://github.com/facebook/rocksdb/files/7923487/Design.Filter.construction.artifacts.release.point.pdf) for high-level design - Bundled and refactored hash entries's related artifact in XXPH3FilterBitsBuilder into `HashEntriesInfo` for better control on lifetime of these artifact during `SwapEntires`, `ResetEntries` - Ensured RocksDB block-based table builder calls `FilterBitsBuilder::MaybePostVerify()` after constructing the filter by `FilterBitsBuilder::Finish()` - When encountering such filter construction corruption, stop writing the filter content to files and mark such a block-based table building non-ok by storing the corruption status in the builder. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9342 Test Plan: - Added new unit test `DBFilterConstructionCorruptionTestWithParam.DetectCorruption` - Included this new feature in `DBFilterConstructionReserveMemoryTestWithParam.ReserveMemory` as this feature heavily touch ReserveMemory's impl - For fallback case, I run `./filter_bench -impl=3 -detect_filter_construct_corruption=true -reserve_table_builder_memory=true -strict_capacity_limit=true -quick -runs 10 | grep 'Build avg'` to make sure nothing break. - Added to `filter_bench`: increased filter construction time by **30%**, mostly by `MaybePostVerify()` - FastLocalBloom - Before change: `./filter_bench -impl=2 -quick -runs 10 | grep 'Build avg'`: **28.86643s** - After change: - `./filter_bench -impl=2 -detect_filter_construct_corruption=false -quick -runs 10 | grep 'Build avg'` (expect a tiny increase due to MaybePostVerify is always called regardless): **27.6644s (-4% perf improvement might be due to now we don't drop bloom hash entry in `AddAllEntries` along iteration but in bulk later, same with the bypassing-MaybePostVerify case below)** - `./filter_bench -impl=2 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'` (expect acceptable increase): **34.41159s (+20%)** - `./filter_bench -impl=2 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'` (by-passing MaybePostVerify, expect minor increase): **27.13431s (-6%)** - Standard128Ribbon - Before change: `./filter_bench -impl=3 -quick -runs 10 | grep 'Build avg'`: **122.5384s** - After change: - `./filter_bench -impl=3 -detect_filter_construct_corruption=false -quick -runs 10 | grep 'Build avg'` (expect a tiny increase due to MaybePostVerify is always called regardless - verified by removing MaybePostVerify under this case and found only +-1ns difference): **124.3588s (+2%)** - `./filter_bench -impl=3 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'`(expect acceptable increase): **159.4946s (+30%)** - `./filter_bench -impl=3 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'`(by-passing MaybePostVerify, expect minor increase) : **125.258s (+2%)** - Added to `db_stress`: `make crash_test`, `./db_stress --detect_filter_construct_corruption=true` - Manually smoke-tested: manually corrupted the filter construction in some db level tests with basic PUT and background flush. As expected, the error did get returned to users in subsequent PUT and Flush status. Reviewed By: pdillinger Differential Revision: D33746928 Pulled By: hx235 fbshipit-source-id: cb056426be5a7debc1cd16f23bc250f36a08ca57
3 years ago
DECLARE_bool(detect_filter_construct_corruption);
DECLARE_int32(index_type);
DECLARE_int32(data_block_index_type);
DECLARE_string(db);
DECLARE_string(secondaries_base);
DECLARE_bool(test_secondary);
Refactor expected state in stress/crash test (#8913) Summary: This is a precursor refactoring to enable an upcoming feature: persistence failure correctness testing. - Changed `--expected_values_path` to `--expected_values_dir` and migrated "db_crashtest.py" to use the new flag. For persistence failure correctness testing there are multiple possible correct states since unsynced data is allowed to be dropped. Making it possible to restore all these possible correct states will eventually involve files containing snapshots of expected values and DB trace files. - The expected values directory is managed by an `ExpectedStateManager` instance. Managing expected state files is separated out of `SharedState` to prevent `SharedState` from becoming too complex when the new files and features (snapshotting, tracing, and restoring) are introduced. - Migrated expected values file access/management out of `SharedState` into a separate class called `ExpectedState`. This is not exposed directly to the test but rather the `ExpectedState` for the latest values file is accessed via a pass-through API on `ExpectedStateManager`. This forces the test to always access the single latest `ExpectedState`. - Changed the initialization of the latest expected values file to use a tempfile followed by rename, and also add cleanup logic for possible stranded tempfiles. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8913 Test Plan: run in several ways; try to make sure it's not obviously broken. - crashtest blackbox without TEST_TMPDIR ``` $ python3 tools/db_crashtest.py blackbox --simple --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --max_key=100000 --value_size_mult=33 --compression_type=none --duration=120 --interval=10 --compression_type=none --blob_compression_type=none ``` - crashtest blackbox with TEST_TMPDIR ``` $ TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py blackbox --simple --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --max_key=100000 --value_size_mult=33 --compression_type=none --duration=120 --interval=10 --compression_type=none --blob_compression_type=none ``` - crashtest whitebox with TEST_TMPDIR ``` $ TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py whitebox --simple --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --max_key=100000 --value_size_mult=33 --compression_type=none --duration=120 --interval=10 --compression_type=none --blob_compression_type=none --random_kill_odd=88887 ``` - db_stress without expected_values_dir ``` $ ./db_stress --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --max_key=100000 --value_size_mult=33 --compression_type=none --ops_per_thread=10000 --clear_column_family_one_in=0 --destroy_db_initially=true ``` - db_stress with expected_values_dir and manual corruption ``` $ ./db_stress --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --max_key=100000 --value_size_mult=33 --compression_type=none --ops_per_thread=10000 --clear_column_family_one_in=0 --destroy_db_initially=true --expected_values_dir=./ // modify one byte in "./LATEST.state" $ ./db_stress --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --max_key=100000 --value_size_mult=33 --compression_type=none --ops_per_thread=10000 --clear_column_family_one_in=0 --destroy_db_initially=false --expected_values_dir=./ ... Verification failed for column family 0 key 0000000000000000 (0): Value not found: NotFound: ... ``` Reviewed By: riversand963 Differential Revision: D30921951 Pulled By: ajkr fbshipit-source-id: babfe218062e55d018c9b046536c0289fb78f41c
3 years ago
DECLARE_string(expected_values_dir);
DECLARE_bool(verify_checksum);
DECLARE_bool(mmap_read);
DECLARE_bool(mmap_write);
DECLARE_bool(use_direct_reads);
DECLARE_bool(use_direct_io_for_flush_and_compaction);
DECLARE_bool(mock_direct_io);
DECLARE_bool(statistics);
DECLARE_bool(sync);
DECLARE_bool(use_fsync);
DECLARE_uint64(stats_dump_period_sec);
DECLARE_uint64(bytes_per_sync);
DECLARE_uint64(wal_bytes_per_sync);
DECLARE_int32(kill_random_test);
DECLARE_string(kill_exclude_prefixes);
DECLARE_bool(disable_wal);
DECLARE_uint64(recycle_log_file_num);
DECLARE_int64(target_file_size_base);
DECLARE_int32(target_file_size_multiplier);
DECLARE_uint64(max_bytes_for_level_base);
DECLARE_double(max_bytes_for_level_multiplier);
DECLARE_int32(range_deletion_width);
DECLARE_uint64(rate_limiter_bytes_per_sec);
DECLARE_bool(rate_limit_bg_reads);
Add rate limiter priority to ReadOptions (#9424) Summary: Users can set the priority for file reads associated with their operation by setting `ReadOptions::rate_limiter_priority` to something other than `Env::IO_TOTAL`. Rate limiting `VerifyChecksum()` and `VerifyFileChecksums()` is the motivation for this PR, so it also includes benchmarks and minor bug fixes to get that working. `RandomAccessFileReader::Read()` already had support for rate limiting compaction reads. I changed that rate limiting to be non-specific to compaction, but rather performed according to the passed in `Env::IOPriority`. Now the compaction read rate limiting is supported by setting `rate_limiter_priority = Env::IO_LOW` on its `ReadOptions`. There is no default value for the new `Env::IOPriority` parameter to `RandomAccessFileReader::Read()`. That means this PR goes through all callers (in some cases multiple layers up the call stack) to find a `ReadOptions` to provide the priority. There are TODOs for cases I believe it would be good to let user control the priority some day (e.g., file footer reads), and no TODO in cases I believe it doesn't matter (e.g., trace file reads). The API doc only lists the missing cases where a file read associated with a provided `ReadOptions` cannot be rate limited. For cases like file ingestion checksum calculation, there is no API to provide `ReadOptions` or `Env::IOPriority`, so I didn't count that as missing. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9424 Test Plan: - new unit tests - new benchmarks on ~50MB database with 1MB/s read rate limit and 100ms refill interval; verified with strace reads are chunked (at 0.1MB per chunk) and spaced roughly 100ms apart. - setup command: `./db_bench -benchmarks=fillrandom,compact -db=/tmp/testdb -target_file_size_base=1048576 -disable_auto_compactions=true -file_checksum=true` - benchmarks command: `strace -ttfe pread64 ./db_bench -benchmarks=verifychecksum,verifyfilechecksums -use_existing_db=true -db=/tmp/testdb -rate_limiter_bytes_per_sec=1048576 -rate_limit_bg_reads=1 -rate_limit_user_ops=true -file_checksum=true` - crash test using IO_USER priority on non-validation reads with https://github.com/facebook/rocksdb/issues/9567 reverted: `python3 tools/db_crashtest.py blackbox --max_key=1000000 --write_buffer_size=524288 --target_file_size_base=524288 --level_compaction_dynamic_level_bytes=true --duration=3600 --rate_limit_bg_reads=true --rate_limit_user_ops=true --rate_limiter_bytes_per_sec=10485760 --interval=10` Reviewed By: hx235 Differential Revision: D33747386 Pulled By: ajkr fbshipit-source-id: a2d985e97912fba8c54763798e04f006ccc56e0c
3 years ago
DECLARE_bool(rate_limit_user_ops);
Rate-limit automatic WAL flush after each user write (#9607) Summary: **Context:** WAL flush is currently not rate-limited by `Options::rate_limiter`. This PR is to provide rate-limiting to auto WAL flush, the one that automatically happen after each user write operation (i.e, `Options::manual_wal_flush == false`), by adding `WriteOptions::rate_limiter_options`. Note that we are NOT rate-limiting WAL flush that do NOT automatically happen after each user write, such as `Options::manual_wal_flush == true + manual FlushWAL()` (rate-limiting multiple WAL flushes), for the benefits of: - being consistent with [ReadOptions::rate_limiter_priority](https://github.com/facebook/rocksdb/blob/7.0.fb/include/rocksdb/options.h#L515) - being able to turn off some WAL flush's rate-limiting but not all (e.g, turn off specific the WAL flush of a critical user write like a service's heartbeat) `WriteOptions::rate_limiter_options` only accept `Env::IO_USER` and `Env::IO_TOTAL` currently due to an implementation constraint. - The constraint is that we currently queue parallel writes (including WAL writes) based on FIFO policy which does not factor rate limiter priority into this layer's scheduling. If we allow lower priorities such as `Env::IO_HIGH/MID/LOW` and such writes specified with lower priorities occurs before ones specified with higher priorities (even just by a tiny bit in arrival time), the former would have blocked the latter, leading to a "priority inversion" issue and contradictory to what we promise for rate-limiting priority. Therefore we only allow `Env::IO_USER` and `Env::IO_TOTAL` right now before improving that scheduling. A pre-requisite to this feature is to support operation-level rate limiting in `WritableFileWriter`, which is also included in this PR. **Summary:** - Renamed test suite `DBRateLimiterTest to DBRateLimiterOnReadTest` for adding a new test suite - Accept `rate_limiter_priority` in `WritableFileWriter`'s private and public write functions - Passed `WriteOptions::rate_limiter_options` to `WritableFileWriter` in the path of automatic WAL flush. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9607 Test Plan: - Added new unit test to verify existing flush/compaction rate-limiting does not break, since `DBTest, RateLimitingTest` is disabled and current db-level rate-limiting tests focus on read only (e.g, `db_rate_limiter_test`, `DBTest2, RateLimitedCompactionReads`). - Added new unit test `DBRateLimiterOnWriteWALTest, AutoWalFlush` - `strace -ftt -e trace=write ./db_bench -benchmarks=fillseq -db=/dev/shm/testdb -rate_limit_auto_wal_flush=1 -rate_limiter_bytes_per_sec=15 -rate_limiter_refill_period_us=1000000 -write_buffer_size=100000000 -disable_auto_compactions=1 -num=100` - verified that WAL flush(i.e, system-call _write_) were chunked into 15 bytes and each _write_ was roughly 1 second apart - verified the chunking disappeared when `-rate_limit_auto_wal_flush=0` - crash test: `python3 tools/db_crashtest.py blackbox --disable_wal=0 --rate_limit_auto_wal_flush=1 --rate_limiter_bytes_per_sec=10485760 --interval=10` killed as normal **Benchmarked on flush/compaction to ensure no performance regression:** - compaction with rate-limiting (see table 1, avg over 1280-run): pre-change: **915635 micros/op**; post-change: **907350 micros/op (improved by 0.106%)** ``` #!/bin/bash TEST_TMPDIR=/dev/shm/testdb START=1 NUM_DATA_ENTRY=8 N=10 rm -f compact_bmk_output.txt compact_bmk_output_2.txt dont_care_output.txt for i in $(eval echo "{$START..$NUM_DATA_ENTRY}") do NUM_RUN=$(($N*(2**($i-1)))) for j in $(eval echo "{$START..$NUM_RUN}") do ./db_bench --benchmarks=fillrandom -db=$TEST_TMPDIR -disable_auto_compactions=1 -write_buffer_size=6710886 > dont_care_output.txt && ./db_bench --benchmarks=compact -use_existing_db=1 -db=$TEST_TMPDIR -level0_file_num_compaction_trigger=1 -rate_limiter_bytes_per_sec=100000000 | egrep 'compact' done > compact_bmk_output.txt && awk -v NUM_RUN=$NUM_RUN '{sum+=$3;sum_sqrt+=$3^2}END{print sum/NUM_RUN, sqrt(sum_sqrt/NUM_RUN-(sum/NUM_RUN)^2)}' compact_bmk_output.txt >> compact_bmk_output_2.txt done ``` - compaction w/o rate-limiting (see table 2, avg over 640-run): pre-change: **822197 micros/op**; post-change: **823148 micros/op (regressed by 0.12%)** ``` Same as above script, except that -rate_limiter_bytes_per_sec=0 ``` - flush with rate-limiting (see table 3, avg over 320-run, run on the [patch](https://github.com/hx235/rocksdb/commit/ee5c6023a9f6533fab9afdc681568daa21da4953) to augment current db_bench ): pre-change: **745752 micros/op**; post-change: **745331 micros/op (regressed by 0.06 %)** ``` #!/bin/bash TEST_TMPDIR=/dev/shm/testdb START=1 NUM_DATA_ENTRY=8 N=10 rm -f flush_bmk_output.txt flush_bmk_output_2.txt for i in $(eval echo "{$START..$NUM_DATA_ENTRY}") do NUM_RUN=$(($N*(2**($i-1)))) for j in $(eval echo "{$START..$NUM_RUN}") do ./db_bench -db=$TEST_TMPDIR -write_buffer_size=1048576000 -num=1000000 -rate_limiter_bytes_per_sec=100000000 -benchmarks=fillseq,flush | egrep 'flush' done > flush_bmk_output.txt && awk -v NUM_RUN=$NUM_RUN '{sum+=$3;sum_sqrt+=$3^2}END{print sum/NUM_RUN, sqrt(sum_sqrt/NUM_RUN-(sum/NUM_RUN)^2)}' flush_bmk_output.txt >> flush_bmk_output_2.txt done ``` - flush w/o rate-limiting (see table 4, avg over 320-run, run on the [patch](https://github.com/hx235/rocksdb/commit/ee5c6023a9f6533fab9afdc681568daa21da4953) to augment current db_bench): pre-change: **487512 micros/op**, post-change: **485856 micors/ops (improved by 0.34%)** ``` Same as above script, except that -rate_limiter_bytes_per_sec=0 ``` | table 1 - compact with rate-limiting| #-run | (pre-change) avg micros/op | std micros/op | (post-change) avg micros/op | std micros/op | change in avg micros/op (%) -- | -- | -- | -- | -- | -- 10 | 896978 | 16046.9 | 901242 | 15670.9 | 0.475373978 20 | 893718 | 15813 | 886505 | 17544.7 | -0.8070778478 40 | 900426 | 23882.2 | 894958 | 15104.5 | -0.6072681153 80 | 906635 | 21761.5 | 903332 | 23948.3 | -0.3643141948 160 | 898632 | 21098.9 | 907583 | 21145 | 0.9960695813 3.20E+02 | 905252 | 22785.5 | 908106 | 25325.5 | 0.3152713278 6.40E+02 | 905213 | 23598.6 | 906741 | 21370.5 | 0.1688000504 **1.28E+03** | **908316** | **23533.1** | **907350** | **24626.8** | **-0.1063506533** average over #-run | 901896.25 | 21064.9625 | 901977.125 | 20592.025 | 0.008967217682 | table 2 - compact w/o rate-limiting| #-run | (pre-change) avg micros/op | std micros/op | (post-change) avg micros/op | std micros/op | change in avg micros/op (%) -- | -- | -- | -- | -- | -- 10 | 811211 | 26996.7 | 807586 | 28456.4 | -0.4468627768 20 | 815465 | 14803.7 | 814608 | 28719.7 | -0.105093413 40 | 809203 | 26187.1 | 797835 | 25492.1 | -1.404839082 80 | 822088 | 28765.3 | 822192 | 32840.4 | 0.01265071379 160 | 821719 | 36344.7 | 821664 | 29544.9 | -0.006693285661 3.20E+02 | 820921 | 27756.4 | 821403 | 28347.7 | 0.05871454135 **6.40E+02** | **822197** | **28960.6** | **823148** | **30055.1** | **0.1156657103** average over #-run | 8.18E+05 | 2.71E+04 | 8.15E+05 | 2.91E+04 | -0.25 | table 3 - flush with rate-limiting| #-run | (pre-change) avg micros/op | std micros/op | (post-change) avg micros/op | std micros/op | change in avg micros/op (%) -- | -- | -- | -- | -- | -- 10 | 741721 | 11770.8 | 740345 | 5949.76 | -0.1855144994 20 | 735169 | 3561.83 | 743199 | 9755.77 | 1.09226586 40 | 743368 | 8891.03 | 742102 | 8683.22 | -0.1703059588 80 | 742129 | 8148.51 | 743417 | 9631.58| 0.1735547324 160 | 749045 | 9757.21 | 746256 | 9191.86 | -0.3723407806 **3.20E+02** | **745752** | **9819.65** | **745331** | **9840.62** | **-0.0564530836** 6.40E+02 | 749006 | 11080.5 | 748173 | 10578.7 | -0.1112140624 average over #-run | 743741.4286 | 9004.218571 | 744117.5714 | 9090.215714 | 0.05057441238 | table 4 - flush w/o rate-limiting| #-run | (pre-change) avg micros/op | std micros/op | (post-change) avg micros/op | std micros/op | change in avg micros/op (%) -- | -- | -- | -- | -- | -- 10 | 477283 | 24719.6 | 473864 | 12379 | -0.7163464863 20 | 486743 | 20175.2 | 502296 | 23931.3 | 3.195320734 40 | 482846 | 15309.2 | 489820 | 22259.5 | 1.444352858 80 | 491490 | 21883.1 | 490071 | 23085.7 | -0.2887139108 160 | 493347 | 28074.3 | 483609 | 21211.7 | -1.973864238 **3.20E+02** | **487512** | **21401.5** | **485856** | **22195.2** | **-0.3396839462** 6.40E+02 | 490307 | 25418.6 | 485435 | 22405.2 | -0.9936631539 average over #-run | 4.87E+05 | 2.24E+04 | 4.87E+05 | 2.11E+04 | 0.00E+00 Reviewed By: ajkr Differential Revision: D34442441 Pulled By: hx235 fbshipit-source-id: 4790f13e1e5c0a95ae1d1cc93ffcf69dc6e78bdd
3 years ago
DECLARE_bool(rate_limit_auto_wal_flush);
DECLARE_uint64(sst_file_manager_bytes_per_sec);
DECLARE_uint64(sst_file_manager_bytes_per_truncate);
DECLARE_bool(use_txn);
DECLARE_uint64(txn_write_policy);
DECLARE_bool(unordered_write);
DECLARE_int32(backup_one_in);
DECLARE_uint64(backup_max_size);
DECLARE_int32(checkpoint_one_in);
DECLARE_int32(ingest_external_file_one_in);
DECLARE_int32(ingest_external_file_width);
DECLARE_int32(compact_files_one_in);
DECLARE_int32(compact_range_one_in);
DECLARE_int32(mark_for_compaction_one_file_in);
DECLARE_int32(flush_one_in);
DECLARE_int32(pause_background_one_in);
DECLARE_int32(compact_range_width);
DECLARE_int32(acquire_snapshot_one_in);
DECLARE_bool(compare_full_db_state_snapshot);
DECLARE_uint64(snapshot_hold_ops);
DECLARE_bool(long_running_snapshots);
DECLARE_bool(use_multiget);
DECLARE_int32(readpercent);
DECLARE_int32(prefixpercent);
DECLARE_int32(writepercent);
DECLARE_int32(delpercent);
DECLARE_int32(delrangepercent);
DECLARE_int32(nooverwritepercent);
DECLARE_int32(iterpercent);
DECLARE_uint64(num_iterations);
DECLARE_int32(customopspercent);
DECLARE_string(compression_type);
DECLARE_string(bottommost_compression_type);
DECLARE_int32(compression_max_dict_bytes);
DECLARE_int32(compression_zstd_max_train_bytes);
DECLARE_int32(compression_parallel_threads);
Limit buffering for collecting samples for compression dictionary (#7970) Summary: For dictionary compression, we need to collect some representative samples of the data to be compressed, which we use to either generate or train (when `CompressionOptions::zstd_max_train_bytes > 0`) a dictionary. Previously, the strategy was to buffer all the data blocks during flush, and up to the target file size during compaction. That strategy allowed us to randomly pick samples from as wide a range as possible that'd be guaranteed to land in a single output file. However, some users try to make huge files in memory-constrained environments, where this strategy can cause OOM. This PR introduces an option, `CompressionOptions::max_dict_buffer_bytes`, that limits how much data blocks are buffered before we switch to unbuffered mode (which means creating the per-SST dictionary, writing out the buffered data, and compressing/writing new blocks as soon as they are built). It is not strict as we currently buffer more than just data blocks -- also keys are buffered. But it does make a step towards giving users predictable memory usage. Related changes include: - Changed sampling for dictionary compression to select unique data blocks when there is limited availability of data blocks - Made use of `BlockBuilder::SwapAndReset()` to save an allocation+memcpy when buffering data blocks for building a dictionary - Changed `ParseBoolean()` to accept an input containing characters after the boolean. This is necessary since, with this PR, a value for `CompressionOptions::enabled` is no longer necessarily the final component in the `CompressionOptions` string. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7970 Test Plan: - updated `CompressionOptions` unit tests to verify limit is respected (to the extent expected in the current implementation) in various scenarios of flush/compaction to bottommost/non-bottommost level - looked at jemalloc heap profiles right before and after switching to unbuffered mode during flush/compaction. Verified memory usage in buffering is proportional to the limit set. Reviewed By: pdillinger Differential Revision: D26467994 Pulled By: ajkr fbshipit-source-id: 3da4ef9fba59974e4ef40e40c01611002c861465
4 years ago
DECLARE_uint64(compression_max_dict_buffer_bytes);
Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857) Summary: An untrained dictionary is currently simply the concatenation of several samples. The ZSTD API, ZDICT_finalizeDictionary(), can improve such a dictionary's effectiveness at low cost. This PR changes how dictionary is created by calling the ZSTD ZDICT_finalizeDictionary() API instead of creating raw content dictionary (when max_dict_buffer_bytes > 0), and pass in all buffered uncompressed data blocks as samples. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9857 Test Plan: #### db_bench test for cpu/memory of compression+decompression and space saving on synthetic data: Set up: change the parameter [here](https://github.com/facebook/rocksdb/blob/fb9a167a55e0970b1ef6f67c1600c8d9c4c6114f/tools/db_bench_tool.cc#L1766) to 16384 to make synthetic data more compressible. ``` # linked local ZSTD with version 1.5.2 # DEBUG_LEVEL=0 ROCKSDB_NO_FBCODE=1 ROCKSDB_DISABLE_ZSTD=1 EXTRA_CXXFLAGS="-DZSTD_STATIC_LINKING_ONLY -DZSTD -I/data/users/changyubi/install/include/" EXTRA_LDFLAGS="-L/data/users/changyubi/install/lib/ -l:libzstd.a" make -j32 db_bench dict_bytes=16384 train_bytes=1048576 echo "========== No Dictionary ==========" TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=0 -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1 TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=0 -block_size=4096 2>&1 | grep elapsed du -hc /dev/shm/dbbench/*sst | grep total echo "========== Raw Content Dictionary ==========" TEST_TMPDIR=/dev/shm ./db_bench_main -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1 TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench_main -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -block_size=4096 2>&1 | grep elapsed du -hc /dev/shm/dbbench/*sst | grep total echo "========== FinalizeDictionary ==========" TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1 TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false -block_size=4096 2>&1 | grep elapsed du -hc /dev/shm/dbbench/*sst | grep total echo "========== TrainDictionary ==========" TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1 TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -block_size=4096 2>&1 | grep elapsed du -hc /dev/shm/dbbench/*sst | grep total # Result: TrainDictionary is much better on space saving, but FinalizeDictionary seems to use less memory. # before compression data size: 1.2GB dict_bytes=16384 max_dict_buffer_bytes = 1048576 space cpu/memory No Dictionary 468M 14.93user 1.00system 0:15.92elapsed 100%CPU (0avgtext+0avgdata 23904maxresident)k Raw Dictionary 251M 15.81user 0.80system 0:16.56elapsed 100%CPU (0avgtext+0avgdata 156808maxresident)k FinalizeDictionary 236M 11.93user 0.64system 0:12.56elapsed 100%CPU (0avgtext+0avgdata 89548maxresident)k TrainDictionary 84M 7.29user 0.45system 0:07.75elapsed 100%CPU (0avgtext+0avgdata 97288maxresident)k ``` #### Benchmark on 10 sample SST files for spacing saving and CPU time on compression: FinalizeDictionary is comparable to TrainDictionary in terms of space saving, and takes less time in compression. ``` dict_bytes=16384 train_bytes=1048576 for sst_file in `ls ../temp/myrock-sst/` do echo "********** $sst_file **********" echo "========== No Dictionary ==========" ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD echo "========== Raw Content Dictionary ==========" ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes echo "========== FinalizeDictionary ==========" ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes --compression_zstd_max_train_bytes=$train_bytes --compression_use_zstd_finalize_dict echo "========== TrainDictionary ==========" ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes --compression_zstd_max_train_bytes=$train_bytes done 010240.sst (Size/Time) 011029.sst 013184.sst 021552.sst 185054.sst 185137.sst 191666.sst 7560381.sst 7604174.sst 7635312.sst No Dictionary 28165569 / 2614419 32899411 / 2976832 32977848 / 3055542 31966329 / 2004590 33614351 / 1755877 33429029 / 1717042 33611933 / 1776936 33634045 / 2771417 33789721 / 2205414 33592194 / 388254 Raw Content Dictionary 28019950 / 2697961 33748665 / 3572422 33896373 / 3534701 26418431 / 2259658 28560825 / 1839168 28455030 / 1846039 28494319 / 1861349 32391599 / 3095649 33772142 / 2407843 33592230 / 474523 FinalizeDictionary 27896012 / 2650029 33763886 / 3719427 33904283 / 3552793 26008225 / 2198033 28111872 / 1869530 28014374 / 1789771 28047706 / 1848300 32296254 / 3204027 33698698 / 2381468 33592344 / 517433 TrainDictionary 28046089 / 2740037 33706480 / 3679019 33885741 / 3629351 25087123 / 2204558 27194353 / 1970207 27234229 / 1896811 27166710 / 1903119 32011041 / 3322315 32730692 / 2406146 33608631 / 570593 ``` #### Decompression/Read test: With FinalizeDictionary/TrainDictionary, some data structure used for decompression are in stored in dictionary, so they are expected to be faster in terms of decompression/reads. ``` dict_bytes=16384 train_bytes=1048576 echo "No Dictionary" TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=0 > /dev/null 2>&1 TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=0 2>&1 | grep MB/s echo "Raw Dictionary" TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes > /dev/null 2>&1 TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes 2>&1 | grep MB/s echo "FinalizeDict" TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false > /dev/null 2>&1 TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false 2>&1 | grep MB/s echo "Train Dictionary" TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes > /dev/null 2>&1 TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes 2>&1 | grep MB/s No Dictionary readrandom : 12.183 micros/op 82082 ops/sec 12.183 seconds 1000000 operations; 9.1 MB/s (1000000 of 1000000 found) Raw Dictionary readrandom : 12.314 micros/op 81205 ops/sec 12.314 seconds 1000000 operations; 9.0 MB/s (1000000 of 1000000 found) FinalizeDict readrandom : 9.787 micros/op 102180 ops/sec 9.787 seconds 1000000 operations; 11.3 MB/s (1000000 of 1000000 found) Train Dictionary readrandom : 9.698 micros/op 103108 ops/sec 9.699 seconds 1000000 operations; 11.4 MB/s (1000000 of 1000000 found) ``` Reviewed By: ajkr Differential Revision: D35720026 Pulled By: cbi42 fbshipit-source-id: 24d230fdff0fd28a1bb650658798f00dfcfb2a1f
3 years ago
DECLARE_bool(compression_use_zstd_dict_trainer);
DECLARE_string(checksum_type);
DECLARE_string(env_uri);
DECLARE_string(fs_uri);
DECLARE_uint64(ops_per_thread);
DECLARE_uint64(log2_keys_per_lock);
DECLARE_uint64(max_manifest_file_size);
DECLARE_bool(in_place_update);
DECLARE_string(memtablerep);
DECLARE_int32(prefix_size);
DECLARE_bool(use_merge);
Add the PutEntity API to the stress/crash tests (#10760) Summary: The patch adds the `PutEntity` API to the non-batched, batched, and CF consistency stress tests. Namely, when the new `db_stress` command line parameter `use_put_entity_one_in` is greater than zero, one in N writes on average is performed using `PutEntity` rather than `Put`. The wide-column entity written has the generated value in its default column; in addition, it contains up to three additional columns where the original generated value is divided up between the column name and the column value (with the column name containing the first k characters of the generated value, and the column value containing the rest). Whether `PutEntity` is used (and if so, how many columns the entity has) is completely determined by the "value base" used to generate the value (that is, there is no randomness involved). Assuming the same `use_put_entity_one_in` setting is used across `db_stress` invocations, this enables us to reconstruct and validate the entity during subsequent `db_stress` runs. Note that `PutEntity` is currently incompatible with `Merge`, transactions, and user-defined timestamps; these combinations are currently disabled/disallowed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10760 Test Plan: Ran some batched, non-batched, and CF consistency stress tests using the script. Reviewed By: riversand963 Differential Revision: D39939032 Pulled By: ltamasi fbshipit-source-id: eafdf124e95993fb7d73158e3b006d11819f7fa9
2 years ago
DECLARE_uint32(use_put_entity_one_in);
DECLARE_bool(use_full_merge_v1);
DECLARE_int32(sync_wal_one_in);
DECLARE_bool(avoid_unnecessary_blocking_io);
DECLARE_bool(write_dbid_to_manifest);
DECLARE_bool(avoid_flush_during_recovery);
DECLARE_uint64(max_write_batch_group_size_bytes);
DECLARE_bool(level_compaction_dynamic_level_bytes);
DECLARE_int32(verify_checksum_one_in);
DECLARE_int32(verify_db_one_in);
DECLARE_int32(continuous_verification_interval);
DECLARE_int32(get_property_one_in);
DECLARE_string(file_checksum_impl);
#ifndef ROCKSDB_LITE
// Options for StackableDB-based BlobDB
DECLARE_bool(use_blob_db);
DECLARE_uint64(blob_db_min_blob_size);
DECLARE_uint64(blob_db_bytes_per_sync);
DECLARE_uint64(blob_db_file_size);
DECLARE_bool(blob_db_enable_gc);
DECLARE_double(blob_db_gc_cutoff);
#endif // !ROCKSDB_LITE
// Options for integrated BlobDB
DECLARE_bool(allow_setting_blob_options_dynamically);
DECLARE_bool(enable_blob_files);
DECLARE_uint64(min_blob_size);
DECLARE_uint64(blob_file_size);
DECLARE_string(blob_compression_type);
DECLARE_bool(enable_blob_garbage_collection);
DECLARE_double(blob_garbage_collection_age_cutoff);
Make it possible to force the garbage collection of the oldest blob files (#8994) Summary: The current BlobDB garbage collection logic works by relocating the valid blobs from the oldest blob files as they are encountered during compaction, and cleaning up blob files once they contain nothing but garbage. However, with sufficiently skewed workloads, it is theoretically possible to end up in a situation when few or no compactions get scheduled for the SST files that contain references to the oldest blob files, which can lead to increased space amp due to the lack of GC. In order to efficiently handle such workloads, the patch adds a new BlobDB configuration option called `blob_garbage_collection_force_threshold`, which signals to BlobDB to schedule targeted compactions for the SST files that keep alive the oldest batch of blob files if the overall ratio of garbage in the given blob files meets the threshold *and* all the given blob files are eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example, if the new option is set to 0.9, targeted compactions will get scheduled if the sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the oldest blob files, assuming all affected blob files are below the age-based cutoff.) The net result of these targeted compactions is that the valid blobs in the oldest blob files are relocated and the oldest blob files themselves cleaned up (since *all* SST files that rely on them get compacted away). These targeted compactions are similar to periodic compactions in the sense that they force certain SST files that otherwise would not get picked up to undergo compaction and also in the sense that instead of merging files from multiple levels, they target a single file. (Note: such compactions might still include neighboring files from the same level due to the need of having a "clean cut" boundary but they never include any files from any other level.) This functionality is currently only supported with the leveled compaction style and is inactive by default (since the default value is set to 1.0, i.e. 100%). Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994 Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests. Reviewed By: riversand963 Differential Revision: D31489850 Pulled By: ltamasi fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
DECLARE_double(blob_garbage_collection_force_threshold);
DECLARE_uint64(blob_compaction_readahead_size);
Make it possible to enable blob files starting from a certain LSM tree level (#10077) Summary: Currently, if blob files are enabled (i.e. `enable_blob_files` is true), large values are extracted both during flush/recovery (when SST files are written into level 0 of the LSM tree) and during compaction into any LSM tree level. For certain use cases that have a mix of short-lived and long-lived values, it might make sense to support extracting large values only during compactions whose output level is greater than or equal to a specified LSM tree level (e.g. compactions into L1/L2/... or above). This could reduce the space amplification caused by large values that are turned into garbage shortly after being written at the price of some write amplification incurred by long-lived values whose extraction to blob files is delayed. In order to achieve this, we would like to do the following: - Add a new configuration option `blob_file_starting_level` (default: 0) to `AdvancedColumnFamilyOptions` (and `MutableCFOptions` and extend the related logic) - Instantiate `BlobFileBuilder` in `BuildTable` (used during flush and recovery, where the LSM tree level is L0) and `CompactionJob` iff `enable_blob_files` is set and the LSM tree level is `>= blob_file_starting_level` - Add unit tests for the new functionality, and add the new option to our stress tests (`db_stress` and `db_crashtest.py` ) - Add the new option to our benchmarking tool `db_bench` and the BlobDB benchmark script `run_blob_bench.sh` - Add the new option to the `ldb` tool (see https://github.com/facebook/rocksdb/wiki/Administration-and-Data-Access-Tool) - Ideally extend the C and Java bindings with the new option - Update the BlobDB wiki to document the new option. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10077 Reviewed By: ltamasi Differential Revision: D36884156 Pulled By: gangliao fbshipit-source-id: 942bab025f04633edca8564ed64791cb5e31627d
3 years ago
DECLARE_int32(blob_file_starting_level);
DECLARE_bool(use_blob_cache);
DECLARE_bool(use_shared_block_and_blob_cache);
DECLARE_uint64(blob_cache_size);
DECLARE_int32(blob_cache_numshardbits);
DECLARE_int32(prepopulate_blob_cache);
DECLARE_int32(approximate_size_one_in);
DECLARE_bool(sync_fault_injection);
DECLARE_bool(best_efforts_recovery);
DECLARE_bool(skip_verifydb);
DECLARE_bool(enable_compaction_filter);
DECLARE_bool(paranoid_file_checks);
DECLARE_bool(fail_if_options_file_error);
Integrity protection for live updates to WriteBatch (#7748) Summary: This PR adds the foundation classes for key-value integrity protection and the first use case: protecting live updates from the source buffers added to `WriteBatch` through the destination buffer in `MemTable`. The width of the protection info is not yet configurable -- only eight bytes per key is supported. This PR allows users to enable protection by constructing `WriteBatch` with `protection_bytes_per_key == 8`. It does not yet expose a way for users to get integrity protection via other write APIs (e.g., `Put()`, `Merge()`, `Delete()`, etc.). The foundation classes (`ProtectionInfo.*`) embed the coverage info in their type, and provide `Protect.*()` and `Strip.*()` functions to navigate between types with different coverage. For making bytes per key configurable (for powers of two up to eight) in the future, these classes are templated on the unsigned integer type used to store the protection info. That integer contains the XOR'd result of hashes with independent seeds for all covered fields. For integer fields, the hash is computed on the raw unadjusted bytes, so the result is endian-dependent. The most significant bytes are truncated when the hash value (8 bytes) is wider than the protection integer. When `WriteBatch` is constructed with `protection_bytes_per_key == 8`, we hold a `ProtectionInfoKVOTC` (i.e., one that covers key, value, optype aka `ValueType`, timestamp, and CF ID) for each entry added to the batch. The protection info is generated from the original buffers passed by the user, as well as the original metadata generated internally. When writing to memtable, each entry is transformed to a `ProtectionInfoKVOTS` (i.e., dropping coverage of CF ID and adding coverage of sequence number), since at that point we know the sequence number, and have already selected a memtable corresponding to a particular CF. This protection info is verified once the entry is encoded in the `MemTable` buffer. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7748 Test Plan: - an integration test to verify a wide variety of single-byte changes to the encoded `MemTable` buffer are caught - add to stress/crash test to verify it works in variety of configs/operations without intentional corruption - [deferred] unit tests for `ProtectionInfo.*` classes for edge cases like KV swap, `SliceParts` and `Slice` APIs are interchangeable, etc. Reviewed By: pdillinger Differential Revision: D25754492 Pulled By: ajkr fbshipit-source-id: e481bac6c03c2ab268be41359730f1ceb9964866
4 years ago
DECLARE_uint64(batch_protection_bytes_per_key);
Add memtable per key-value checksum (#10281) Summary: Append per key-value checksum to internal key. These checksums are verified on read paths including Get, Iterator and during Flush. Get and Iterator will return `Corruption` status if there is a checksum verification failure. Flush will make DB become read-only upon memtable entry checksum verification failure. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10281 Test Plan: - Added new unit test cases: `make check` - Benchmark on memtable insert ``` TEST_TMPDIR=/dev/shm/memtable_write ./db_bench -benchmarks=fillseq -disable_wal=true -max_write_buffer_number=100 -num=10000000 -min_write_buffer_number_to_merge=100 # avg over 10 runs Baseline: 1166936 ops/sec memtable 2 bytes kv checksum : 1.11674e+06 ops/sec (-4%) memtable 2 bytes kv checksum + write batch 8 bytes kv checksum: 1.08579e+06 ops/sec (-6.95%) write batch 8 bytes kv checksum: 1.17979e+06 ops/sec (+1.1%) ``` - Benchmark on only memtable read: ops/sec dropped 31% for `readseq` due to time spend on verifying checksum. ops/sec for `readrandom` dropped ~6.8%. ``` # Readseq sudo TEST_TMPDIR=/dev/shm/memtable_read ./db_bench -benchmarks=fillseq,readseq"[-X20]" -disable_wal=true -max_write_buffer_number=100 -num=10000000 -min_write_buffer_number_to_merge=100 readseq [AVG 20 runs] : 7432840 (± 212005) ops/sec; 822.3 (± 23.5) MB/sec readseq [MEDIAN 20 runs] : 7573878 ops/sec; 837.9 MB/sec With -memtable_protection_bytes_per_key=2: readseq [AVG 20 runs] : 5134607 (± 119596) ops/sec; 568.0 (± 13.2) MB/sec readseq [MEDIAN 20 runs] : 5232946 ops/sec; 578.9 MB/sec # Readrandom sudo TEST_TMPDIR=/dev/shm/memtable_read ./db_bench -benchmarks=fillrandom,readrandom"[-X10]" -disable_wal=true -max_write_buffer_number=100 -num=1000000 -min_write_buffer_number_to_merge=100 readrandom [AVG 10 runs] : 140236 (± 3938) ops/sec; 9.8 (± 0.3) MB/sec readrandom [MEDIAN 10 runs] : 140545 ops/sec; 9.8 MB/sec With -memtable_protection_bytes_per_key=2: readrandom [AVG 10 runs] : 130632 (± 2738) ops/sec; 9.1 (± 0.2) MB/sec readrandom [MEDIAN 10 runs] : 130341 ops/sec; 9.1 MB/sec ``` - Stress test: `python3 -u tools/db_crashtest.py whitebox --duration=1800` Reviewed By: ajkr Differential Revision: D37607896 Pulled By: cbi42 fbshipit-source-id: fdaefb475629d2471780d4a5f5bf81b44ee56113
2 years ago
DECLARE_uint32(memtable_protection_bytes_per_key);
DECLARE_uint64(user_timestamp_size);
DECLARE_string(secondary_cache_uri);
DECLARE_int32(secondary_cache_fault_one_in);
DECLARE_int32(prepopulate_block_cache);
Improve stress test for transactions (#9568) Summary: Test only, no change to functionality. Extremely low risk of library regression. Update test key generation by maintaining existing and non-existing keys. Update db_crashtest.py to drive multiops_txn stress test for both write-committed and write-prepared. Add a make target 'blackbox_crash_test_with_multiops_txn'. Running the following commands caught the bug exposed in https://github.com/facebook/rocksdb/issues/9571. ``` $rm -rf /tmp/rocksdbtest/* $./db_stress -progress_reports=0 -test_multi_ops_txns -use_txn -clear_column_family_one_in=0 \ -column_families=1 -writepercent=0 -delpercent=0 -delrangepercent=0 -customopspercent=60 \ -readpercent=20 -prefixpercent=0 -iterpercent=20 -reopen=0 -ops_per_thread=1000 -ub_a=10000 \ -ub_c=100 -destroy_db_initially=0 -key_spaces_path=/dev/shm/key_spaces_desc -threads=32 -read_fault_one_in=0 $./db_stress -progress_reports=0 -test_multi_ops_txns -use_txn -clear_column_family_one_in=0 -column_families=1 -writepercent=0 -delpercent=0 -delrangepercent=0 -customopspercent=60 -readpercent=20 \ -prefixpercent=0 -iterpercent=20 -reopen=0 -ops_per_thread=1000 -ub_a=10000 -ub_c=100 -destroy_db_initially=0 \ -key_spaces_path=/dev/shm/key_spaces_desc -threads=32 -read_fault_one_in=0 ``` Running the following command caught a bug which will be fixed in https://github.com/facebook/rocksdb/issues/9648 . ``` $TEST_TMPDIR=/dev/shm make blackbox_crash_test_with_multiops_wc_txn ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9568 Reviewed By: jay-zhuang Differential Revision: D34308154 Pulled By: riversand963 fbshipit-source-id: 99ff1b65c19b46c471d2f2d3b47adcd342a1b9e7
3 years ago
DECLARE_bool(two_write_queues);
#ifndef ROCKSDB_LITE
DECLARE_bool(use_only_the_last_commit_time_batch_for_recovery);
DECLARE_uint64(wp_snapshot_cache_bits);
DECLARE_uint64(wp_commit_cache_bits);
#endif // !ROCKSDB_LITE
DECLARE_bool(adaptive_readahead);
DECLARE_bool(async_io);
DECLARE_string(wal_compression);
DECLARE_bool(verify_sst_unique_id_in_manifest);
Snapshots with user-specified timestamps (#9879) Summary: In RocksDB, keys are associated with (internal) sequence numbers which denote when the keys are written to the database. Sequence numbers in different RocksDB instances are unrelated, thus not comparable. It is nice if we can associate sequence numbers with their corresponding actual timestamps. One thing we can do is to support user-defined timestamp, which allows the applications to specify the format of custom timestamps and encode a timestamp with each key. More details can be found at https://github.com/facebook/rocksdb/wiki/User-defined-Timestamp-%28Experimental%29. This PR provides a different but complementary approach. We can associate rocksdb snapshots (defined in https://github.com/facebook/rocksdb/blob/7.2.fb/include/rocksdb/snapshot.h#L20) with **user-specified** timestamps. Since a snapshot is essentially an object representing a sequence number, this PR establishes a bi-directional mapping between sequence numbers and timestamps. In the past, snapshots are usually taken by readers. The current super-version is grabbed, and a `rocksdb::Snapshot` object is created with the last published sequence number of the super-version. You can see that the reader actually has no good idea of what timestamp to assign to this snapshot, because by the time the `GetSnapshot()` is called, an arbitrarily long period of time may have already elapsed since the last write, which is when the last published sequence number is written. This observation motivates the creation of "timestamped" snapshots on the write path. Currently, this functionality is exposed only to the layer of `TransactionDB`. Application can tell RocksDB to create a snapshot when a transaction commits, effectively associating the last sequence number with a timestamp. It is also assumed that application will ensure any two snapshots with timestamps should satisfy the following: ``` snapshot1.seq < snapshot2.seq iff. snapshot1.ts < snapshot2.ts ``` If the application can guarantee that when a reader takes a timestamped snapshot, there is no active writes going on in the database, then we also allow the user to use a new API `TransactionDB::CreateTimestampedSnapshot()` to create a snapshot with associated timestamp. Code example ```cpp // Create a timestamped snapshot when committing transaction. txn->SetCommitTimestamp(100); txn->SetSnapshotOnNextOperation(); txn->Commit(); // A wrapper API for convenience Status Transaction::CommitAndTryCreateSnapshot( std::shared_ptr<TransactionNotifier> notifier, TxnTimestamp ts, std::shared_ptr<const Snapshot>* ret); // Create a timestamped snapshot if caller guarantees no concurrent writes std::pair<Status, std::shared_ptr<const Snapshot>> snapshot = txn_db->CreateTimestampedSnapshot(100); ``` The snapshots created in this way will be managed by RocksDB with ref-counting and potentially shared with other readers. We provide the following APIs for readers to retrieve a snapshot given a timestamp. ```cpp // Return the timestamped snapshot correponding to given timestamp. If ts is // kMaxTxnTimestamp, then we return the latest timestamped snapshot if present. // Othersise, we return the snapshot whose timestamp is equal to `ts`. If no // such snapshot exists, then we return null. std::shared_ptr<const Snapshot> TransactionDB::GetTimestampedSnapshot(TxnTimestamp ts) const; // Return the latest timestamped snapshot if present. std::shared_ptr<const Snapshot> TransactionDB::GetLatestTimestampedSnapshot() const; ``` We also provide two additional APIs for stats collection and reporting purposes. ```cpp Status TransactionDB::GetAllTimestampedSnapshots( std::vector<std::shared_ptr<const Snapshot>>& snapshots) const; // Return timestamped snapshots whose timestamps fall in [ts_lb, ts_ub) and store them in `snapshots`. Status TransactionDB::GetTimestampedSnapshots( TxnTimestamp ts_lb, TxnTimestamp ts_ub, std::vector<std::shared_ptr<const Snapshot>>& snapshots) const; ``` To prevent the number of timestamped snapshots from growing infinitely, we provide the following API to release timestamped snapshots whose timestamps are older than or equal to a given threshold. ```cpp void TransactionDB::ReleaseTimestampedSnapshotsOlderThan(TxnTimestamp ts); ``` Before shutdown, RocksDB will release all timestamped snapshots. Comparison with user-defined timestamp and how they can be combined: User-defined timestamp persists every key with a timestamp, while timestamped snapshots maintain a volatile mapping between snapshots (sequence numbers) and timestamps. Different internal keys with the same user key but different timestamps will be treated as different by compaction, thus a newer version will not hide older versions (with smaller timestamps) unless they are eligible for garbage collection. In contrast, taking a timestamped snapshot at a certain sequence number and timestamp prevents all the keys visible in this snapshot from been dropped by compaction. Here, visible means (seq < snapshot and most recent). The timestamped snapshot supports the semantics of reading at an exact point in time. Timestamped snapshots can also be used with user-defined timestamp. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9879 Test Plan: ``` make check TEST_TMPDIR=/dev/shm make crash_test_with_txn ``` Reviewed By: siying Differential Revision: D35783919 Pulled By: riversand963 fbshipit-source-id: 586ad905e169189e19d3bfc0cb0177a7239d1bd4
3 years ago
DECLARE_int32(create_timestamped_snapshot_one_in);
DECLARE_bool(allow_data_in_errors);
// Tiered storage
DECLARE_bool(enable_tiered_storage); // set last_level_temperature
DECLARE_int64(preclude_last_level_data_seconds);
DECLARE_int64(preserve_internal_time_seconds);
Add Iterator test against expected state to stress test (#10538) Summary: As mentioned in https://github.com/facebook/rocksdb/pull/5506#issuecomment-506021913, `db_stress` does not have much verification for iterator correctness. It has a `TestIterate()` function, but that is mainly for comparing results between two iterators, one with `total_order_seek` and the other optionally sets auto_prefix, upper/lower bounds. Commit 49a0581ad2462e31aa3f768afa769e0d33390f33 added a new `TestIterateAgainstExpected()` function that compares iterator against expected state. It locks a range of keys, creates an iterator, does a random sequence of `Next/Prev` and compares against expected state. This PR is based on that commit, the main changes include some logs (for easier debugging if a test fails), a forward and backward scan to cover the entire locked key range, and a flag for optionally turning on this version of Iterator testing. Added constraint that the checks against expected state in `TestIterateAgainstExpected()` and in `TestGet()` are only turned on when `--skip_verifydb` flag is not set. Remove the change log introduced in https://github.com/facebook/rocksdb/issues/10553. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10538 Test Plan: Run `db_stress` with `--verify_iterator_with_expected_state_one_in=1`, and a large `--iterpercent` and `--num_iterations`. Checked `op_logs` manually to ensure expected coverage. Tweaked part of the code in https://github.com/facebook/rocksdb/issues/10449 and stress test was able to catch it. - internally run various flavor of crash test Reviewed By: ajkr Differential Revision: D38847269 Pulled By: cbi42 fbshipit-source-id: 8b4402a9bba9f6cfa08051943cd672579d489599
2 years ago
DECLARE_int32(verify_iterator_with_expected_state_one_in);
db_stress option to preserve all files until verification success (#10659) Summary: In `db_stress`, DB and expected state files containing changes leading up to a verification failure are often deleted, which makes debugging such failures difficult. On the DB side, flushed WAL files and compacted SST files are marked obsolete and then deleted. Without those files, we cannot pinpoint where a key that failed verification changed unexpectedly. On the expected state side, files for verifying prefix-recoverability in the presence of unsynced data loss are deleted before verification. These include a baseline state file containing the expected state at the time of the last successful verification, and a trace file containing all operations since then. Without those files, we cannot know the sequence of DB operations expected to be recovered. This PR attempts to address this gap with a new `db_stress` flag: `preserve_unverified_changes`. Setting `preserve_unverified_changes=1` has two effects. First, prior to startup verification, `db_stress` hardlinks all DB and expected state files in "unverified/" subdirectories of `FLAGS_db` and `FLAGS_expected_values_dir`. The separate directories are needed because the pre-verification opening process deletes files written by the previous `db_stress` run as described above. These "unverified/" subdirectories are cleaned up following startup verification success. I considered other approaches for preserving DB files through startup verification, like using a read-only DB or preventing deletion of DB files externally, e.g., in the `Env` layer. However, I decided against it since such an approach would not work for expected state files, and I did not want to change the DB management logic. If there were a way to disable DB file deletions before regular DB open, I would have preferred to use that. Second, `db_stress` attempts to keep all DB and expected state files that were live at some point since the start of the `db_stress` run. This is a bit tricky and involves the following changes. - Open the DB with `disable_auto_compactions=1` and `avoid_flush_during_recovery=1` - DisableFileDeletions() - EnableAutoCompactions() For this part, too, I would have preferred to use a hypothetical API that disables DB file deletion before regular DB open. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10659 Reviewed By: hx235 Differential Revision: D39407454 Pulled By: ajkr fbshipit-source-id: 6e981025c7dce147649d2e770728471395a7fa53
2 years ago
DECLARE_bool(preserve_unverified_changes);
Add Iterator test against expected state to stress test (#10538) Summary: As mentioned in https://github.com/facebook/rocksdb/pull/5506#issuecomment-506021913, `db_stress` does not have much verification for iterator correctness. It has a `TestIterate()` function, but that is mainly for comparing results between two iterators, one with `total_order_seek` and the other optionally sets auto_prefix, upper/lower bounds. Commit 49a0581ad2462e31aa3f768afa769e0d33390f33 added a new `TestIterateAgainstExpected()` function that compares iterator against expected state. It locks a range of keys, creates an iterator, does a random sequence of `Next/Prev` and compares against expected state. This PR is based on that commit, the main changes include some logs (for easier debugging if a test fails), a forward and backward scan to cover the entire locked key range, and a flag for optionally turning on this version of Iterator testing. Added constraint that the checks against expected state in `TestIterateAgainstExpected()` and in `TestGet()` are only turned on when `--skip_verifydb` flag is not set. Remove the change log introduced in https://github.com/facebook/rocksdb/issues/10553. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10538 Test Plan: Run `db_stress` with `--verify_iterator_with_expected_state_one_in=1`, and a large `--iterpercent` and `--num_iterations`. Checked `op_logs` manually to ensure expected coverage. Tweaked part of the code in https://github.com/facebook/rocksdb/issues/10449 and stress test was able to catch it. - internally run various flavor of crash test Reviewed By: ajkr Differential Revision: D38847269 Pulled By: cbi42 fbshipit-source-id: 8b4402a9bba9f6cfa08051943cd672579d489599
2 years ago
DECLARE_uint64(readahead_size);
DECLARE_uint64(initial_auto_readahead_size);
DECLARE_uint64(max_auto_readahead_size);
DECLARE_uint64(num_file_reads_for_auto_readahead);
constexpr long KB = 1024;
constexpr int kRandomValueMaxFactor = 3;
constexpr int kValueMaxLen = 100;
// wrapped posix environment
extern ROCKSDB_NAMESPACE::Env* db_stress_env;
extern ROCKSDB_NAMESPACE::Env* db_stress_listener_env;
extern std::shared_ptr<ROCKSDB_NAMESPACE::FaultInjectionTestFS> fault_fs_guard;
extern enum ROCKSDB_NAMESPACE::CompressionType compression_type_e;
extern enum ROCKSDB_NAMESPACE::CompressionType bottommost_compression_type_e;
extern enum ROCKSDB_NAMESPACE::ChecksumType checksum_type_e;
enum RepFactory { kSkipList, kHashSkipList, kVectorRep };
inline enum RepFactory StringToRepFactory(const char* ctype) {
assert(ctype);
if (!strcasecmp(ctype, "skip_list"))
return kSkipList;
else if (!strcasecmp(ctype, "prefix_hash"))
return kHashSkipList;
else if (!strcasecmp(ctype, "vector"))
return kVectorRep;
fprintf(stdout, "Cannot parse memreptable %s\n", ctype);
return kSkipList;
}
extern enum RepFactory FLAGS_rep_factory;
namespace ROCKSDB_NAMESPACE {
inline enum ROCKSDB_NAMESPACE::CompressionType StringToCompressionType(
const char* ctype) {
assert(ctype);
ROCKSDB_NAMESPACE::CompressionType ret_compression_type;
if (!strcasecmp(ctype, "disable")) {
ret_compression_type = ROCKSDB_NAMESPACE::kDisableCompressionOption;
} else if (!strcasecmp(ctype, "none")) {
ret_compression_type = ROCKSDB_NAMESPACE::kNoCompression;
} else if (!strcasecmp(ctype, "snappy")) {
ret_compression_type = ROCKSDB_NAMESPACE::kSnappyCompression;
} else if (!strcasecmp(ctype, "zlib")) {
ret_compression_type = ROCKSDB_NAMESPACE::kZlibCompression;
} else if (!strcasecmp(ctype, "bzip2")) {
ret_compression_type = ROCKSDB_NAMESPACE::kBZip2Compression;
} else if (!strcasecmp(ctype, "lz4")) {
ret_compression_type = ROCKSDB_NAMESPACE::kLZ4Compression;
} else if (!strcasecmp(ctype, "lz4hc")) {
ret_compression_type = ROCKSDB_NAMESPACE::kLZ4HCCompression;
} else if (!strcasecmp(ctype, "xpress")) {
ret_compression_type = ROCKSDB_NAMESPACE::kXpressCompression;
} else if (!strcasecmp(ctype, "zstd")) {
ret_compression_type = ROCKSDB_NAMESPACE::kZSTD;
} else {
fprintf(stderr, "Cannot parse compression type '%s'\n", ctype);
ret_compression_type =
ROCKSDB_NAMESPACE::kSnappyCompression; // default value
}
if (ret_compression_type != ROCKSDB_NAMESPACE::kDisableCompressionOption &&
!CompressionTypeSupported(ret_compression_type)) {
// Use no compression will be more portable but considering this is
// only a stress test and snappy is widely available. Use snappy here.
ret_compression_type = ROCKSDB_NAMESPACE::kSnappyCompression;
}
return ret_compression_type;
}
inline enum ROCKSDB_NAMESPACE::ChecksumType StringToChecksumType(
const char* ctype) {
assert(ctype);
auto iter = ROCKSDB_NAMESPACE::checksum_type_string_map.find(ctype);
if (iter != ROCKSDB_NAMESPACE::checksum_type_string_map.end()) {
return iter->second;
}
fprintf(stderr, "Cannot parse checksum type '%s'\n", ctype);
return ROCKSDB_NAMESPACE::kCRC32c;
}
inline std::string ChecksumTypeToString(ROCKSDB_NAMESPACE::ChecksumType ctype) {
auto iter = std::find_if(
ROCKSDB_NAMESPACE::checksum_type_string_map.begin(),
ROCKSDB_NAMESPACE::checksum_type_string_map.end(),
[&](const std::pair<std::string, ROCKSDB_NAMESPACE::ChecksumType>&
name_and_enum_val) { return name_and_enum_val.second == ctype; });
assert(iter != ROCKSDB_NAMESPACE::checksum_type_string_map.end());
return iter->first;
}
inline std::vector<std::string> SplitString(std::string src) {
std::vector<std::string> ret;
if (src.empty()) {
return ret;
}
size_t pos = 0;
size_t pos_comma;
while ((pos_comma = src.find(',', pos)) != std::string::npos) {
ret.push_back(src.substr(pos, pos_comma - pos));
pos = pos_comma + 1;
}
ret.push_back(src.substr(pos, src.length()));
return ret;
}
#ifdef _MSC_VER
#pragma warning(push)
// truncation of constant value on static_cast
#pragma warning(disable : 4309)
#endif
inline bool GetNextPrefix(const ROCKSDB_NAMESPACE::Slice& src, std::string* v) {
std::string ret = src.ToString();
for (int i = static_cast<int>(ret.size()) - 1; i >= 0; i--) {
if (ret[i] != static_cast<char>(255)) {
ret[i] = ret[i] + 1;
break;
} else if (i != 0) {
ret[i] = 0;
} else {
// all FF. No next prefix
return false;
}
}
*v = ret;
return true;
}
#ifdef _MSC_VER
#pragma warning(pop)
#endif
Optimize db_stress setup phase (#9475) Summary: It is too slow that our `db_crashtest.py` often kills `db_stress` before the setup phase completes. Profiled it and found a few ways to optimize. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9475 Test Plan: Measured setup phase time reduced 22% (36 -> 28 seconds) for first run, and 36% (38 -> 24 seconds) for non-first run on empty-ish DB. - first run benchmark command: `rm -rf /dev/shm/dbstress*/ && mkdir -p /dev/shm/dbstress_expected/ && ./db_stress -max_key=100000000 -destroy_db_initially=1 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:14:05 Initializing db_stress ... 2022/01/31-11:14:41 Starting database operations ``` output after this PR: ``` ... 2022/01/31-11:12:23 Initializing db_stress ... 2022/01/31-11:12:51 Starting database operations ``` - non-first run benchmark command: `./db_stress -max_key=100000000 -destroy_db_initially=0 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:20:45 Initializing db_stress ... 2022/01/31-11:21:23 Starting database operations ``` output after this PR: ``` 2022/01/31-11:22:02 Initializing db_stress ... 2022/01/31-11:22:26 Starting database operations ``` - ran minified crash test a while: `DEBUG_LEVEL=0 TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py blackbox --simple --interval=10 --max_key=1000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33` Reviewed By: anand1976 Differential Revision: D33897793 Pulled By: ajkr fbshipit-source-id: 0d7b2c93e1e2a9f8a878e87632c2455406313087
3 years ago
// Append `val` to `*key` in fixed-width big-endian format
extern inline void AppendIntToString(uint64_t val, std::string* key) {
// PutFixed64 uses little endian
PutFixed64(key, val);
// Reverse to get big endian
char* int_data = &((*key)[key->size() - sizeof(uint64_t)]);
for (size_t i = 0; i < sizeof(uint64_t) / 2; ++i) {
std::swap(int_data[i], int_data[sizeof(uint64_t) - 1 - i]);
}
}
// A struct for maintaining the parameters for generating variable length keys
struct KeyGenContext {
// Number of adjacent keys in one cycle of key lengths
uint64_t window;
// Number of keys of each possible length in a given window
std::vector<uint64_t> weights;
};
extern KeyGenContext key_gen_ctx;
// Generate a variable length key string from the given int64 val. The
// order of the keys is preserved. The key could be anywhere from 8 to
// max_key_len * 8 bytes.
// The algorithm picks the length based on the
// offset of the val within a configured window and the distribution of the
// number of keys of various lengths in that window. For example, if x, y, x are
// the weights assigned to each possible key length, the keys generated would be
// - {0}...{x-1}
// {(x-1),0}..{(x-1),(y-1)},{(x-1),(y-1),0}..{(x-1),(y-1),(z-1)} and so on.
// Additionally, a trailer of 0-7 bytes could be appended.
extern inline std::string Key(int64_t val) {
uint64_t window = key_gen_ctx.window;
size_t levels = key_gen_ctx.weights.size();
std::string key;
Optimize db_stress setup phase (#9475) Summary: It is too slow that our `db_crashtest.py` often kills `db_stress` before the setup phase completes. Profiled it and found a few ways to optimize. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9475 Test Plan: Measured setup phase time reduced 22% (36 -> 28 seconds) for first run, and 36% (38 -> 24 seconds) for non-first run on empty-ish DB. - first run benchmark command: `rm -rf /dev/shm/dbstress*/ && mkdir -p /dev/shm/dbstress_expected/ && ./db_stress -max_key=100000000 -destroy_db_initially=1 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:14:05 Initializing db_stress ... 2022/01/31-11:14:41 Starting database operations ``` output after this PR: ``` ... 2022/01/31-11:12:23 Initializing db_stress ... 2022/01/31-11:12:51 Starting database operations ``` - non-first run benchmark command: `./db_stress -max_key=100000000 -destroy_db_initially=0 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:20:45 Initializing db_stress ... 2022/01/31-11:21:23 Starting database operations ``` output after this PR: ``` 2022/01/31-11:22:02 Initializing db_stress ... 2022/01/31-11:22:26 Starting database operations ``` - ran minified crash test a while: `DEBUG_LEVEL=0 TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py blackbox --simple --interval=10 --max_key=1000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33` Reviewed By: anand1976 Differential Revision: D33897793 Pulled By: ajkr fbshipit-source-id: 0d7b2c93e1e2a9f8a878e87632c2455406313087
3 years ago
// Over-reserve and for now do not bother `shrink_to_fit()` since the key
// strings are transient.
key.reserve(FLAGS_max_key_len * 8);
Optimize db_stress setup phase (#9475) Summary: It is too slow that our `db_crashtest.py` often kills `db_stress` before the setup phase completes. Profiled it and found a few ways to optimize. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9475 Test Plan: Measured setup phase time reduced 22% (36 -> 28 seconds) for first run, and 36% (38 -> 24 seconds) for non-first run on empty-ish DB. - first run benchmark command: `rm -rf /dev/shm/dbstress*/ && mkdir -p /dev/shm/dbstress_expected/ && ./db_stress -max_key=100000000 -destroy_db_initially=1 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:14:05 Initializing db_stress ... 2022/01/31-11:14:41 Starting database operations ``` output after this PR: ``` ... 2022/01/31-11:12:23 Initializing db_stress ... 2022/01/31-11:12:51 Starting database operations ``` - non-first run benchmark command: `./db_stress -max_key=100000000 -destroy_db_initially=0 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:20:45 Initializing db_stress ... 2022/01/31-11:21:23 Starting database operations ``` output after this PR: ``` 2022/01/31-11:22:02 Initializing db_stress ... 2022/01/31-11:22:26 Starting database operations ``` - ran minified crash test a while: `DEBUG_LEVEL=0 TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py blackbox --simple --interval=10 --max_key=1000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33` Reviewed By: anand1976 Differential Revision: D33897793 Pulled By: ajkr fbshipit-source-id: 0d7b2c93e1e2a9f8a878e87632c2455406313087
3 years ago
uint64_t window_idx = static_cast<uint64_t>(val) / window;
uint64_t offset = static_cast<uint64_t>(val) % window;
for (size_t level = 0; level < levels; ++level) {
uint64_t weight = key_gen_ctx.weights[level];
Optimize db_stress setup phase (#9475) Summary: It is too slow that our `db_crashtest.py` often kills `db_stress` before the setup phase completes. Profiled it and found a few ways to optimize. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9475 Test Plan: Measured setup phase time reduced 22% (36 -> 28 seconds) for first run, and 36% (38 -> 24 seconds) for non-first run on empty-ish DB. - first run benchmark command: `rm -rf /dev/shm/dbstress*/ && mkdir -p /dev/shm/dbstress_expected/ && ./db_stress -max_key=100000000 -destroy_db_initially=1 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:14:05 Initializing db_stress ... 2022/01/31-11:14:41 Starting database operations ``` output after this PR: ``` ... 2022/01/31-11:12:23 Initializing db_stress ... 2022/01/31-11:12:51 Starting database operations ``` - non-first run benchmark command: `./db_stress -max_key=100000000 -destroy_db_initially=0 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:20:45 Initializing db_stress ... 2022/01/31-11:21:23 Starting database operations ``` output after this PR: ``` 2022/01/31-11:22:02 Initializing db_stress ... 2022/01/31-11:22:26 Starting database operations ``` - ran minified crash test a while: `DEBUG_LEVEL=0 TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py blackbox --simple --interval=10 --max_key=1000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33` Reviewed By: anand1976 Differential Revision: D33897793 Pulled By: ajkr fbshipit-source-id: 0d7b2c93e1e2a9f8a878e87632c2455406313087
3 years ago
uint64_t pfx;
if (level == 0) {
pfx = window_idx * weight;
} else {
pfx = 0;
}
pfx += offset >= weight ? weight - 1 : offset;
AppendIntToString(pfx, &key);
if (offset < weight) {
// Use the bottom 3 bits of offset as the number of trailing 'x's in the
// key. If the next key is going to be of the next level, then skip the
// trailer as it would break ordering. If the key length is already at
// max, skip the trailer.
if (offset < weight - 1 && level < levels - 1) {
size_t trailer_len = offset & 0x7;
key.append(trailer_len, 'x');
}
break;
}
Optimize db_stress setup phase (#9475) Summary: It is too slow that our `db_crashtest.py` often kills `db_stress` before the setup phase completes. Profiled it and found a few ways to optimize. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9475 Test Plan: Measured setup phase time reduced 22% (36 -> 28 seconds) for first run, and 36% (38 -> 24 seconds) for non-first run on empty-ish DB. - first run benchmark command: `rm -rf /dev/shm/dbstress*/ && mkdir -p /dev/shm/dbstress_expected/ && ./db_stress -max_key=100000000 -destroy_db_initially=1 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:14:05 Initializing db_stress ... 2022/01/31-11:14:41 Starting database operations ``` output after this PR: ``` ... 2022/01/31-11:12:23 Initializing db_stress ... 2022/01/31-11:12:51 Starting database operations ``` - non-first run benchmark command: `./db_stress -max_key=100000000 -destroy_db_initially=0 -expected_values_dir=/dev/shm/dbstress_expected/ -db=/dev/shm/dbstress/ --clear_column_family_one_in=0 --reopen=0 --nooverwritepercent=1` output before this PR: ``` 2022/01/31-11:20:45 Initializing db_stress ... 2022/01/31-11:21:23 Starting database operations ``` output after this PR: ``` 2022/01/31-11:22:02 Initializing db_stress ... 2022/01/31-11:22:26 Starting database operations ``` - ran minified crash test a while: `DEBUG_LEVEL=0 TEST_TMPDIR=/dev/shm python3 tools/db_crashtest.py blackbox --simple --interval=10 --max_key=1000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33` Reviewed By: anand1976 Differential Revision: D33897793 Pulled By: ajkr fbshipit-source-id: 0d7b2c93e1e2a9f8a878e87632c2455406313087
3 years ago
offset -= weight;
}
return key;
}
// Given a string key, map it to an index into the expected values buffer
extern inline bool GetIntVal(std::string big_endian_key, uint64_t* key_p) {
size_t size_key = big_endian_key.size();
std::vector<uint64_t> prefixes;
assert(size_key <= key_gen_ctx.weights.size() * sizeof(uint64_t));
std::string little_endian_key;
little_endian_key.resize(size_key);
for (size_t start = 0; start + sizeof(uint64_t) <= size_key;
start += sizeof(uint64_t)) {
size_t end = start + sizeof(uint64_t);
for (size_t i = 0; i < sizeof(uint64_t); ++i) {
little_endian_key[start + i] = big_endian_key[end - 1 - i];
}
Slice little_endian_slice =
Slice(&little_endian_key[start], sizeof(uint64_t));
uint64_t pfx;
if (!GetFixed64(&little_endian_slice, &pfx)) {
return false;
}
prefixes.emplace_back(pfx);
}
uint64_t key = 0;
for (size_t i = 0; i < prefixes.size(); ++i) {
uint64_t pfx = prefixes[i];
key += (pfx / key_gen_ctx.weights[i]) * key_gen_ctx.window +
pfx % key_gen_ctx.weights[i];
if (i < prefixes.size() - 1) {
// The encoding writes a `key_gen_ctx.weights[i] - 1` that counts for
// `key_gen_ctx.weights[i]` when there are more prefixes to come. So we
// need to add back the one here as we're at a non-last prefix.
++key;
}
}
*key_p = key;
return true;
}
// Given a string prefix, map it to the first corresponding index in the
// expected values buffer.
inline bool GetFirstIntValInPrefix(std::string big_endian_prefix,
uint64_t* key_p) {
size_t size_key = big_endian_prefix.size();
// Pad with zeros to make it a multiple of 8. This function may be called
// with a prefix, in which case we return the first index that falls
// inside or outside that prefix, dependeing on whether the prefix is
// the start of upper bound of a scan
unsigned int pad = sizeof(uint64_t) - (size_key % sizeof(uint64_t));
if (pad < sizeof(uint64_t)) {
big_endian_prefix.append(pad, '\0');
}
return GetIntVal(std::move(big_endian_prefix), key_p);
}
extern inline uint64_t GetPrefixKeyCount(const std::string& prefix,
const std::string& ub) {
uint64_t start = 0;
uint64_t end = 0;
if (!GetFirstIntValInPrefix(prefix, &start) ||
!GetFirstIntValInPrefix(ub, &end)) {
return 0;
}
return end - start;
}
extern inline std::string StringToHex(const std::string& str) {
std::string result = "0x";
result.append(Slice(str).ToString(true));
return result;
}
// Unified output format for double parameters
extern inline std::string FormatDoubleParam(double param) {
return std::to_string(param);
}
// Make sure that double parameter is a value we can reproduce by
// re-inputting the value printed.
extern inline void SanitizeDoubleParam(double* param) {
*param = std::atof(FormatDoubleParam(*param).c_str());
}
extern void PoolSizeChangeThread(void* v);
extern void DbVerificationThread(void* v);
Snapshots with user-specified timestamps (#9879) Summary: In RocksDB, keys are associated with (internal) sequence numbers which denote when the keys are written to the database. Sequence numbers in different RocksDB instances are unrelated, thus not comparable. It is nice if we can associate sequence numbers with their corresponding actual timestamps. One thing we can do is to support user-defined timestamp, which allows the applications to specify the format of custom timestamps and encode a timestamp with each key. More details can be found at https://github.com/facebook/rocksdb/wiki/User-defined-Timestamp-%28Experimental%29. This PR provides a different but complementary approach. We can associate rocksdb snapshots (defined in https://github.com/facebook/rocksdb/blob/7.2.fb/include/rocksdb/snapshot.h#L20) with **user-specified** timestamps. Since a snapshot is essentially an object representing a sequence number, this PR establishes a bi-directional mapping between sequence numbers and timestamps. In the past, snapshots are usually taken by readers. The current super-version is grabbed, and a `rocksdb::Snapshot` object is created with the last published sequence number of the super-version. You can see that the reader actually has no good idea of what timestamp to assign to this snapshot, because by the time the `GetSnapshot()` is called, an arbitrarily long period of time may have already elapsed since the last write, which is when the last published sequence number is written. This observation motivates the creation of "timestamped" snapshots on the write path. Currently, this functionality is exposed only to the layer of `TransactionDB`. Application can tell RocksDB to create a snapshot when a transaction commits, effectively associating the last sequence number with a timestamp. It is also assumed that application will ensure any two snapshots with timestamps should satisfy the following: ``` snapshot1.seq < snapshot2.seq iff. snapshot1.ts < snapshot2.ts ``` If the application can guarantee that when a reader takes a timestamped snapshot, there is no active writes going on in the database, then we also allow the user to use a new API `TransactionDB::CreateTimestampedSnapshot()` to create a snapshot with associated timestamp. Code example ```cpp // Create a timestamped snapshot when committing transaction. txn->SetCommitTimestamp(100); txn->SetSnapshotOnNextOperation(); txn->Commit(); // A wrapper API for convenience Status Transaction::CommitAndTryCreateSnapshot( std::shared_ptr<TransactionNotifier> notifier, TxnTimestamp ts, std::shared_ptr<const Snapshot>* ret); // Create a timestamped snapshot if caller guarantees no concurrent writes std::pair<Status, std::shared_ptr<const Snapshot>> snapshot = txn_db->CreateTimestampedSnapshot(100); ``` The snapshots created in this way will be managed by RocksDB with ref-counting and potentially shared with other readers. We provide the following APIs for readers to retrieve a snapshot given a timestamp. ```cpp // Return the timestamped snapshot correponding to given timestamp. If ts is // kMaxTxnTimestamp, then we return the latest timestamped snapshot if present. // Othersise, we return the snapshot whose timestamp is equal to `ts`. If no // such snapshot exists, then we return null. std::shared_ptr<const Snapshot> TransactionDB::GetTimestampedSnapshot(TxnTimestamp ts) const; // Return the latest timestamped snapshot if present. std::shared_ptr<const Snapshot> TransactionDB::GetLatestTimestampedSnapshot() const; ``` We also provide two additional APIs for stats collection and reporting purposes. ```cpp Status TransactionDB::GetAllTimestampedSnapshots( std::vector<std::shared_ptr<const Snapshot>>& snapshots) const; // Return timestamped snapshots whose timestamps fall in [ts_lb, ts_ub) and store them in `snapshots`. Status TransactionDB::GetTimestampedSnapshots( TxnTimestamp ts_lb, TxnTimestamp ts_ub, std::vector<std::shared_ptr<const Snapshot>>& snapshots) const; ``` To prevent the number of timestamped snapshots from growing infinitely, we provide the following API to release timestamped snapshots whose timestamps are older than or equal to a given threshold. ```cpp void TransactionDB::ReleaseTimestampedSnapshotsOlderThan(TxnTimestamp ts); ``` Before shutdown, RocksDB will release all timestamped snapshots. Comparison with user-defined timestamp and how they can be combined: User-defined timestamp persists every key with a timestamp, while timestamped snapshots maintain a volatile mapping between snapshots (sequence numbers) and timestamps. Different internal keys with the same user key but different timestamps will be treated as different by compaction, thus a newer version will not hide older versions (with smaller timestamps) unless they are eligible for garbage collection. In contrast, taking a timestamped snapshot at a certain sequence number and timestamp prevents all the keys visible in this snapshot from been dropped by compaction. Here, visible means (seq < snapshot and most recent). The timestamped snapshot supports the semantics of reading at an exact point in time. Timestamped snapshots can also be used with user-defined timestamp. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9879 Test Plan: ``` make check TEST_TMPDIR=/dev/shm make crash_test_with_txn ``` Reviewed By: siying Differential Revision: D35783919 Pulled By: riversand963 fbshipit-source-id: 586ad905e169189e19d3bfc0cb0177a7239d1bd4
3 years ago
extern void TimestampedSnapshotsThread(void* v);
extern void PrintKeyValue(int cf, uint64_t key, const char* value, size_t sz);
extern int64_t GenerateOneKey(ThreadState* thread, uint64_t iteration);
extern std::vector<int64_t> GenerateNKeys(ThreadState* thread, int num_keys,
uint64_t iteration);
extern size_t GenerateValue(uint32_t rand, char* v, size_t max_sz);
extern uint32_t GetValueBase(Slice s);
Add the PutEntity API to the stress/crash tests (#10760) Summary: The patch adds the `PutEntity` API to the non-batched, batched, and CF consistency stress tests. Namely, when the new `db_stress` command line parameter `use_put_entity_one_in` is greater than zero, one in N writes on average is performed using `PutEntity` rather than `Put`. The wide-column entity written has the generated value in its default column; in addition, it contains up to three additional columns where the original generated value is divided up between the column name and the column value (with the column name containing the first k characters of the generated value, and the column value containing the rest). Whether `PutEntity` is used (and if so, how many columns the entity has) is completely determined by the "value base" used to generate the value (that is, there is no randomness involved). Assuming the same `use_put_entity_one_in` setting is used across `db_stress` invocations, this enables us to reconstruct and validate the entity during subsequent `db_stress` runs. Note that `PutEntity` is currently incompatible with `Merge`, transactions, and user-defined timestamps; these combinations are currently disabled/disallowed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10760 Test Plan: Ran some batched, non-batched, and CF consistency stress tests using the script. Reviewed By: riversand963 Differential Revision: D39939032 Pulled By: ltamasi fbshipit-source-id: eafdf124e95993fb7d73158e3b006d11819f7fa9
2 years ago
extern WideColumns GenerateWideColumns(uint32_t value_base, const Slice& slice);
extern WideColumns GenerateExpectedWideColumns(uint32_t value_base,
const Slice& slice);
extern StressTest* CreateCfConsistencyStressTest();
extern StressTest* CreateBatchedOpsStressTest();
extern StressTest* CreateNonBatchedOpsStressTest();
extern StressTest* CreateMultiOpsTxnsStressTest();
extern void CheckAndSetOptionsForMultiOpsTxnStressTest();
extern void InitializeHotKeyGenerator(double alpha);
extern int64_t GetOneHotKeyID(double rand_seed, int64_t max_key);
extern std::string GetNowNanos();
std::shared_ptr<FileChecksumGenFactory> GetFileChecksumImpl(
const std::string& name);
db_stress option to preserve all files until verification success (#10659) Summary: In `db_stress`, DB and expected state files containing changes leading up to a verification failure are often deleted, which makes debugging such failures difficult. On the DB side, flushed WAL files and compacted SST files are marked obsolete and then deleted. Without those files, we cannot pinpoint where a key that failed verification changed unexpectedly. On the expected state side, files for verifying prefix-recoverability in the presence of unsynced data loss are deleted before verification. These include a baseline state file containing the expected state at the time of the last successful verification, and a trace file containing all operations since then. Without those files, we cannot know the sequence of DB operations expected to be recovered. This PR attempts to address this gap with a new `db_stress` flag: `preserve_unverified_changes`. Setting `preserve_unverified_changes=1` has two effects. First, prior to startup verification, `db_stress` hardlinks all DB and expected state files in "unverified/" subdirectories of `FLAGS_db` and `FLAGS_expected_values_dir`. The separate directories are needed because the pre-verification opening process deletes files written by the previous `db_stress` run as described above. These "unverified/" subdirectories are cleaned up following startup verification success. I considered other approaches for preserving DB files through startup verification, like using a read-only DB or preventing deletion of DB files externally, e.g., in the `Env` layer. However, I decided against it since such an approach would not work for expected state files, and I did not want to change the DB management logic. If there were a way to disable DB file deletions before regular DB open, I would have preferred to use that. Second, `db_stress` attempts to keep all DB and expected state files that were live at some point since the start of the `db_stress` run. This is a bit tricky and involves the following changes. - Open the DB with `disable_auto_compactions=1` and `avoid_flush_during_recovery=1` - DisableFileDeletions() - EnableAutoCompactions() For this part, too, I would have preferred to use a hypothetical API that disables DB file deletion before regular DB open. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10659 Reviewed By: hx235 Differential Revision: D39407454 Pulled By: ajkr fbshipit-source-id: 6e981025c7dce147649d2e770728471395a7fa53
2 years ago
Status DeleteFilesInDirectory(const std::string& dirname);
Status SaveFilesInDirectory(const std::string& src_dirname,
const std::string& dst_dirname);
Status DestroyUnverifiedSubdir(const std::string& dirname);
Status InitUnverifiedSubdir(const std::string& dirname);
} // namespace ROCKSDB_NAMESPACE
#endif // GFLAGS