2016-02-09 23:12:00 +00:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-15 23:03:42 +00:00
|
|
|
// 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).
|
2014-04-15 20:39:26 +00:00
|
|
|
//
|
|
|
|
// 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.
|
|
|
|
|
2015-10-13 00:35:43 +00:00
|
|
|
#ifndef NDEBUG
|
2014-04-15 20:39:26 +00:00
|
|
|
|
2019-08-15 23:59:42 +00:00
|
|
|
#include "db/column_family.h"
|
2019-05-31 18:52:59 +00:00
|
|
|
#include "db/db_impl/db_impl.h"
|
2018-06-28 19:23:57 +00:00
|
|
|
#include "db/error_handler.h"
|
2022-08-26 01:52:37 +00:00
|
|
|
#include "db/periodic_task_scheduler.h"
|
2017-04-06 02:02:00 +00:00
|
|
|
#include "monitoring/thread_status_updater.h"
|
2019-08-15 23:59:42 +00:00
|
|
|
#include "util/cast_util.h"
|
2014-04-15 20:39:26 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
namespace ROCKSDB_NAMESPACE {
|
2014-04-15 20:39:26 +00:00
|
|
|
uint64_t DBImpl::TEST_GetLevel0TotalSize() {
|
2015-02-05 05:39:45 +00:00
|
|
|
InstrumentedMutexLock l(&mutex_);
|
2014-10-31 15:48:19 +00:00
|
|
|
return default_cf_handle_->cfd()->current()->storage_info()->NumLevelBytes(0);
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
2020-12-10 05:19:55 +00:00
|
|
|
Status DBImpl::TEST_SwitchWAL() {
|
2017-04-04 17:19:33 +00:00
|
|
|
WriteContext write_context;
|
2017-01-19 23:21:07 +00:00
|
|
|
InstrumentedMutexLock l(&mutex_);
|
2020-02-18 21:52:09 +00:00
|
|
|
void* writer = TEST_BeginWrite();
|
2020-12-10 05:19:55 +00:00
|
|
|
auto s = SwitchWAL(&write_context);
|
2020-02-18 21:52:09 +00:00
|
|
|
TEST_EndWrite(writer);
|
2020-12-10 05:19:55 +00:00
|
|
|
return s;
|
2017-01-19 23:21:07 +00:00
|
|
|
}
|
|
|
|
|
2021-07-08 17:07:37 +00:00
|
|
|
uint64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
|
2014-04-15 20:39:26 +00:00
|
|
|
ColumnFamilyHandle* column_family) {
|
|
|
|
ColumnFamilyData* cfd;
|
|
|
|
if (column_family == nullptr) {
|
|
|
|
cfd = default_cf_handle_->cfd();
|
|
|
|
} else {
|
2020-07-03 02:24:25 +00:00
|
|
|
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
|
2014-04-15 20:39:26 +00:00
|
|
|
cfd = cfh->cfd();
|
|
|
|
}
|
2015-02-05 05:39:45 +00:00
|
|
|
InstrumentedMutexLock l(&mutex_);
|
2014-10-31 15:48:19 +00:00
|
|
|
return cfd->current()->storage_info()->MaxNextLevelOverlappingBytes();
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
void DBImpl::TEST_GetFilesMetaData(
|
|
|
|
ColumnFamilyHandle* column_family,
|
2021-06-28 15:12:32 +00:00
|
|
|
std::vector<std::vector<FileMetaData>>* metadata,
|
|
|
|
std::vector<std::shared_ptr<BlobFileMetaData>>* blob_metadata) {
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
assert(metadata);
|
|
|
|
|
2020-07-03 02:24:25 +00:00
|
|
|
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
assert(cfh);
|
|
|
|
|
2014-04-15 20:39:26 +00:00
|
|
|
auto cfd = cfh->cfd();
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
assert(cfd);
|
|
|
|
|
2015-02-05 05:39:45 +00:00
|
|
|
InstrumentedMutexLock l(&mutex_);
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
|
|
|
|
const auto* current = cfd->current();
|
|
|
|
assert(current);
|
|
|
|
|
|
|
|
const auto* vstorage = current->storage_info();
|
|
|
|
assert(vstorage);
|
|
|
|
|
2014-04-15 20:39:26 +00:00
|
|
|
metadata->resize(NumberLevels());
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
|
|
|
|
for (int level = 0; level < NumberLevels(); ++level) {
|
|
|
|
const std::vector<FileMetaData*>& files = vstorage->LevelFiles(level);
|
2014-04-15 20:39:26 +00:00
|
|
|
|
|
|
|
(*metadata)[level].clear();
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
(*metadata)[level].reserve(files.size());
|
|
|
|
|
2014-04-15 20:39:26 +00:00
|
|
|
for (const auto& f : files) {
|
|
|
|
(*metadata)[level].push_back(*f);
|
|
|
|
}
|
|
|
|
}
|
Use a sorted vector instead of a map to store blob file metadata (#9526)
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
2022-02-09 20:35:39 +00:00
|
|
|
|
|
|
|
if (blob_metadata) {
|
|
|
|
*blob_metadata = vstorage->GetBlobFiles();
|
2021-06-28 15:12:32 +00:00
|
|
|
}
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
|
2014-11-04 01:45:55 +00:00
|
|
|
return versions_->manifest_file_number();
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
2017-10-10 20:07:00 +00:00
|
|
|
uint64_t DBImpl::TEST_Current_Next_FileNo() {
|
|
|
|
return versions_->current_next_file_number();
|
|
|
|
}
|
|
|
|
|
2014-04-15 20:39:26 +00:00
|
|
|
Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
|
|
|
|
const Slice* end,
|
Allowing L0 -> L1 trivial move on sorted data
Summary:
This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping
The conditions for trivial move have been updated
Introduced conditions:
- Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual)
- Input level files cannot be overlapping
Removed conditions:
- Trivial move only run when the compaction is not manual
- Input level should can contain only 1 file
More context on what tests failed because of Trivial move
```
DBTest.CompactionsGenerateMultipleFiles
This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1
```
```
DBTest.NoSpaceCompactRange
This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation
because trivial move does not need any extra space, and did not check for that
```
```
DBTest.DropWrites
Similar to DBTest.NoSpaceCompactRange
```
```
DBTest.DeleteObsoleteFilesPendingOutputs
This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3
```
```
CuckooTableDBTest.CompactionIntoMultipleFiles
Same as DBTest.CompactionsGenerateMultipleFiles
```
This diff is based on a work by @sdong https://reviews.facebook.net/D34149
Test Plan: make -j64 check
Reviewers: rven, sdong, igor
Reviewed By: igor
Subscribers: yhchiang, ott, march, dhruba, sdong
Differential Revision: https://reviews.facebook.net/D34797
2015-06-04 23:51:25 +00:00
|
|
|
ColumnFamilyHandle* column_family,
|
|
|
|
bool disallow_trivial_move) {
|
2014-04-15 20:39:26 +00:00
|
|
|
ColumnFamilyData* cfd;
|
|
|
|
if (column_family == nullptr) {
|
|
|
|
cfd = default_cf_handle_->cfd();
|
|
|
|
} else {
|
2020-07-03 02:24:25 +00:00
|
|
|
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
|
2014-04-15 20:39:26 +00:00
|
|
|
cfd = cfh->cfd();
|
|
|
|
}
|
|
|
|
int output_level =
|
2014-11-18 18:20:10 +00:00
|
|
|
(cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
|
|
|
|
cfd->ioptions()->compaction_style == kCompactionStyleFIFO)
|
2014-04-15 20:39:26 +00:00
|
|
|
? level
|
|
|
|
: level + 1;
|
2022-05-05 20:08:21 +00:00
|
|
|
return RunManualCompaction(
|
|
|
|
cfd, level, output_level, CompactRangeOptions(), begin, end, true,
|
|
|
|
disallow_trivial_move,
|
|
|
|
std::numeric_limits<uint64_t>::max() /*max_file_num_to_ignore*/,
|
|
|
|
"" /*trim_ts*/);
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
2017-10-03 16:08:07 +00:00
|
|
|
Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
|
|
|
|
WriteContext write_context;
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
if (cfd == nullptr) {
|
|
|
|
cfd = default_cf_handle_->cfd();
|
|
|
|
}
|
2019-11-15 21:59:03 +00:00
|
|
|
|
2020-02-18 21:52:09 +00:00
|
|
|
Status s;
|
|
|
|
void* writer = TEST_BeginWrite();
|
2019-11-15 21:59:03 +00:00
|
|
|
if (two_write_queues_) {
|
|
|
|
WriteThread::Writer nonmem_w;
|
|
|
|
nonmem_write_thread_.EnterUnbatched(&nonmem_w, &mutex_);
|
2020-02-18 21:52:09 +00:00
|
|
|
s = SwitchMemtable(cfd, &write_context);
|
2019-11-15 21:59:03 +00:00
|
|
|
nonmem_write_thread_.ExitUnbatched(&nonmem_w);
|
|
|
|
} else {
|
2020-02-18 21:52:09 +00:00
|
|
|
s = SwitchMemtable(cfd, &write_context);
|
2019-11-15 21:59:03 +00:00
|
|
|
}
|
2020-02-18 21:52:09 +00:00
|
|
|
TEST_EndWrite(writer);
|
|
|
|
return s;
|
2017-10-03 16:08:07 +00:00
|
|
|
}
|
|
|
|
|
2018-08-29 18:58:13 +00:00
|
|
|
Status DBImpl::TEST_FlushMemTable(bool wait, bool allow_write_stall,
|
2019-03-27 23:13:08 +00:00
|
|
|
ColumnFamilyHandle* cfh) {
|
2014-04-15 20:39:26 +00:00
|
|
|
FlushOptions fo;
|
|
|
|
fo.wait = wait;
|
2018-08-29 18:58:13 +00:00
|
|
|
fo.allow_write_stall = allow_write_stall;
|
2016-04-18 18:11:51 +00:00
|
|
|
ColumnFamilyData* cfd;
|
|
|
|
if (cfh == nullptr) {
|
|
|
|
cfd = default_cf_handle_->cfd();
|
|
|
|
} else {
|
2020-07-03 02:24:25 +00:00
|
|
|
auto cfhi = static_cast_with_check<ColumnFamilyHandleImpl>(cfh);
|
2016-04-18 18:11:51 +00:00
|
|
|
cfd = cfhi->cfd();
|
|
|
|
}
|
2018-02-09 20:09:55 +00:00
|
|
|
return FlushMemTable(cfd, fo, FlushReason::kTest);
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
2019-07-01 21:04:10 +00:00
|
|
|
Status DBImpl::TEST_FlushMemTable(ColumnFamilyData* cfd,
|
|
|
|
const FlushOptions& flush_opts) {
|
|
|
|
return FlushMemTable(cfd, flush_opts, FlushReason::kTest);
|
|
|
|
}
|
|
|
|
|
|
|
|
Status DBImpl::TEST_AtomicFlushMemTables(
|
Fix bug of prematurely excluded CF in atomic flush contains unflushed data that should've been included in the atomic flush (#11148)
Summary:
**Context:**
Atomic flush should guarantee recoverability of all data of seqno up to the max seqno of the flush. It achieves this by ensuring all such data are flushed by the time this atomic flush finishes through `SelectColumnFamiliesForAtomicFlush()`. However, our crash test exposed the following case where an excluded CF from an atomic flush contains unflushed data of seqno less than the max seqno of that atomic flush and loses its data with `WriteOptions::DisableWAL=true` in face of a crash right after the atomic flush finishes .
```
./db_stress --preserve_unverified_changes=1 --reopen=0 --acquire_snapshot_one_in=0 --adaptive_readahead=1 --allow_data_in_errors=True --async_io=1 --atomic_flush=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=15 --bottommost_compression_type=none --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=0 --charge_table_reader=0 --checkpoint_one_in=0 --checksum_type=kXXH3 --clear_column_family_one_in=0 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=1 --compaction_ttl=100 --compression_max_dict_buffer_bytes=134217727 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=lz4hc --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=$db --db_write_buffer_size=1048576 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_wal=1 --enable_compaction_filter=0 --enable_pipelined_write=0 --expected_values_dir=$exp --fail_if_options_file_error=0 --fifo_allow_compaction=0 --file_checksum_impl=none --flush_one_in=0 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=100 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=2 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=524288 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --long_running_snapshots=1 --manual_wal_flush_one_in=100 --mark_for_compaction_one_file_in=0 --max_auto_readahead_size=0 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=10000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=64 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_prefix_bloom_size_ratio=0.01 --memtable_protection_bytes_per_key=4 --memtable_whole_key_filtering=0 --memtablerep=skip_list --min_write_buffer_number_to_merge=2 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=-1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=100000000 --optimize_filters_for_memory=1 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=0 --periodic_compaction_seconds=100 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --preserve_internal_time_seconds=3600 --progress_reports=0 --read_fault_one_in=32 --readahead_size=16384 --readpercent=50 --recycle_log_file_num=0 --ribbon_starting_level=6 --secondary_cache_fault_one_in=0 --set_options_one_in=10000 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=1048576 --stats_dump_period_sec=10 --subcompactions=1 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=0 --unpartitioned_pinning=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=0 --use_multiget=1 --use_put_entity_one_in=0 --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=524288 --wal_compression=none --write_buffer_size=524288 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=30 &
pid=$!
sleep 0.2
sleep 10
kill $pid
sleep 0.2
./db_stress --ops_per_thread=1 --preserve_unverified_changes=1 --reopen=0 --acquire_snapshot_one_in=0 --adaptive_readahead=1 --allow_data_in_errors=True --async_io=1 --atomic_flush=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=15 --bottommost_compression_type=none --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_size=8388608 --cache_type=lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=0 --charge_table_reader=0 --checkpoint_one_in=0 --checksum_type=kXXH3 --clear_column_family_one_in=0 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=1 --compaction_ttl=100 --compression_max_dict_buffer_bytes=134217727 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=lz4hc --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=$db --db_write_buffer_size=1048576 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_wal=1 --enable_compaction_filter=0 --enable_pipelined_write=0 --expected_values_dir=$exp --fail_if_options_file_error=0 --fifo_allow_compaction=0 --file_checksum_impl=none --flush_one_in=0 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=100 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=2 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=524288 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --long_running_snapshots=1 --manual_wal_flush_one_in=100 --mark_for_compaction_one_file_in=0 --max_auto_readahead_size=0 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=10000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=64 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_prefix_bloom_size_ratio=0.01 --memtable_protection_bytes_per_key=4 --memtable_whole_key_filtering=0 --memtablerep=skip_list --min_write_buffer_number_to_merge=2 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=-1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=100000000 --optimize_filters_for_memory=1 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=0 --periodic_compaction_seconds=100 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --preserve_internal_time_seconds=3600 --progress_reports=0 --read_fault_one_in=32 --readahead_size=16384 --readpercent=50 --recycle_log_file_num=0 --ribbon_starting_level=6 --secondary_cache_fault_one_in=0 --set_options_one_in=10000 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=1048576 --stats_dump_period_sec=10 --subcompactions=1 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=0 --unpartitioned_pinning=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=0 --use_multiget=1 --use_put_entity_one_in=0 --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=524288 --wal_compression=none --write_buffer_size=524288 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=30 &
pid=$!
sleep 0.2
sleep 40
kill $pid
sleep 0.2
Verification failed for column family 6 key 0000000000000239000000000000012B0000000000000138 (56622): value_from_db: , value_from_expected: 4A6331754E4F4C4D42434041464744455A5B58595E5F5C5D5253505156575455, msg: Value not found: NotFound:
Crash-recovery verification failed :(
No writes or ops?
Verification failed :(
```
The bug is due to the following:
- When atomic flush is used, an empty CF is legally [excluded](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_filesnapshot.cc#L39) in `SelectColumnFamiliesForAtomicFlush` as the first step of `DBImpl::FlushForGetLiveFiles` before [passing](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_filesnapshot.cc#L42) the included CFDs to `AtomicFlushMemTables`.
- But [later](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_impl/db_impl_compaction_flush.cc#L2133) in `AtomicFlushMemTables`, `WaitUntilFlushWouldNotStallWrites` will [release the db mutex](https://github.com/facebook/rocksdb/blob/7.10.fb/db/db_impl/db_impl_compaction_flush.cc#L2403), during which data@seqno N can be inserted into the excluded CF and data@seqno M can be inserted into one of the included CFs, where M > N.
- However, data@seqno N in an already-excluded CF is thus excluded from this atomic flush while we seqno N is less than seqno M.
**Summary:**
- Replace `SelectColumnFamiliesForAtomicFlush()`-before-`AtomicFlushMemTables()` with `SelectColumnFamiliesForAtomicFlush()`-after-wait-within-`AtomicFlushMemTables()` so we ensure no write affecting the recoverability of this atomic job (i.e, change to max seqno of this atomic flush or insertion of data with less seqno than the max seqno of the atomic flush to excluded CF) can happen after calling `SelectColumnFamiliesForAtomicFlush()`.
- For above, refactored and clarified comments on `SelectColumnFamiliesForAtomicFlush()` and `AtomicFlushMemTables()` for clearer semantics of passed-in CFDs to atomic-flush
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11148
Test Plan:
- New unit test failed before the fix and passes after
- Make check
- Rehearsal stress test
Reviewed By: ajkr
Differential Revision: D42799871
Pulled By: hx235
fbshipit-source-id: 13636b63e9c25c5895857afc36ea580d57f6d644
2023-03-14 23:53:20 +00:00
|
|
|
const autovector<ColumnFamilyData*>& provided_candidate_cfds,
|
|
|
|
const FlushOptions& flush_opts) {
|
|
|
|
return AtomicFlushMemTables(flush_opts, FlushReason::kTest,
|
|
|
|
provided_candidate_cfds);
|
2019-07-01 21:04:10 +00:00
|
|
|
}
|
|
|
|
|
2021-12-23 05:58:11 +00:00
|
|
|
Status DBImpl::TEST_WaitForBackgroundWork() {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
WaitForBackgroundWork();
|
2022-01-21 16:24:06 +00:00
|
|
|
return error_handler_.GetBGError();
|
2021-12-23 05:58:11 +00:00
|
|
|
}
|
|
|
|
|
2014-04-15 20:39:26 +00:00
|
|
|
Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
|
|
|
|
ColumnFamilyData* cfd;
|
|
|
|
if (column_family == nullptr) {
|
|
|
|
cfd = default_cf_handle_->cfd();
|
|
|
|
} else {
|
2020-07-03 02:24:25 +00:00
|
|
|
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
|
2014-04-15 20:39:26 +00:00
|
|
|
cfd = cfh->cfd();
|
|
|
|
}
|
2018-10-26 22:06:44 +00:00
|
|
|
return WaitForFlushMemTable(cfd, nullptr, false);
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
|
|
|
|
2023-05-26 00:25:51 +00:00
|
|
|
Status DBImpl::TEST_WaitForCompact() {
|
|
|
|
return WaitForCompact(WaitForCompactOptions());
|
|
|
|
}
|
|
|
|
Status DBImpl::TEST_WaitForCompact(
|
|
|
|
const WaitForCompactOptions& wait_for_compact_options) {
|
|
|
|
return WaitForCompact(wait_for_compact_options);
|
2014-04-15 20:39:26 +00:00
|
|
|
}
|
2014-04-29 17:27:58 +00:00
|
|
|
|
2021-11-03 19:20:19 +00:00
|
|
|
Status DBImpl::TEST_WaitForPurge() {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
while (bg_purge_scheduled_ && error_handler_.GetBGError().ok()) {
|
|
|
|
bg_cv_.Wait();
|
|
|
|
}
|
|
|
|
return error_handler_.GetBGError();
|
|
|
|
}
|
|
|
|
|
2021-01-28 01:56:17 +00:00
|
|
|
Status DBImpl::TEST_GetBGError() {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
return error_handler_.GetBGError();
|
|
|
|
}
|
|
|
|
|
2019-03-27 23:13:08 +00:00
|
|
|
void DBImpl::TEST_LockMutex() { mutex_.Lock(); }
|
2014-09-05 22:20:05 +00:00
|
|
|
|
2019-03-27 23:13:08 +00:00
|
|
|
void DBImpl::TEST_UnlockMutex() { mutex_.Unlock(); }
|
2014-09-05 22:20:05 +00:00
|
|
|
|
2023-02-03 20:08:37 +00:00
|
|
|
void DBImpl::TEST_SignalAllBgCv() { bg_cv_.SignalAll(); }
|
|
|
|
|
2014-09-05 22:20:05 +00:00
|
|
|
void* DBImpl::TEST_BeginWrite() {
|
2015-08-05 23:56:28 +00:00
|
|
|
auto w = new WriteThread::Writer();
|
|
|
|
write_thread_.EnterUnbatched(w, &mutex_);
|
2014-09-05 22:20:05 +00:00
|
|
|
return reinterpret_cast<void*>(w);
|
|
|
|
}
|
|
|
|
|
|
|
|
void DBImpl::TEST_EndWrite(void* w) {
|
2014-09-12 23:23:58 +00:00
|
|
|
auto writer = reinterpret_cast<WriteThread::Writer*>(w);
|
2015-08-05 23:56:28 +00:00
|
|
|
write_thread_.ExitUnbatched(writer);
|
2014-09-08 15:01:25 +00:00
|
|
|
delete writer;
|
2014-09-05 22:20:05 +00:00
|
|
|
}
|
|
|
|
|
2015-03-30 19:04:10 +00:00
|
|
|
size_t DBImpl::TEST_LogsToFreeSize() {
|
2022-07-21 20:35:36 +00:00
|
|
|
InstrumentedMutexLock l(&log_write_mutex_);
|
2015-03-30 19:04:10 +00:00
|
|
|
return logs_to_free_.size();
|
|
|
|
}
|
|
|
|
|
2015-07-02 21:27:00 +00:00
|
|
|
uint64_t DBImpl::TEST_LogfileNumber() {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
return logfile_number_;
|
|
|
|
}
|
|
|
|
|
2015-11-04 01:52:17 +00:00
|
|
|
Status DBImpl::TEST_GetAllImmutableCFOptions(
|
|
|
|
std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map) {
|
|
|
|
std::vector<std::string> cf_names;
|
|
|
|
std::vector<const ImmutableCFOptions*> iopts;
|
|
|
|
{
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
for (auto cfd : *versions_->GetColumnFamilySet()) {
|
|
|
|
cf_names.push_back(cfd->GetName());
|
|
|
|
iopts.push_back(cfd->ioptions());
|
|
|
|
}
|
|
|
|
}
|
|
|
|
iopts_map->clear();
|
|
|
|
for (size_t i = 0; i < cf_names.size(); ++i) {
|
|
|
|
iopts_map->insert({cf_names[i], iopts[i]});
|
|
|
|
}
|
|
|
|
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
2016-04-18 18:11:51 +00:00
|
|
|
uint64_t DBImpl::TEST_FindMinLogContainingOutstandingPrep() {
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-03 22:35:11 +00:00
|
|
|
return logs_with_prep_tracker_.FindMinLogContainingOutstandingPrep();
|
2016-04-18 18:11:51 +00:00
|
|
|
}
|
|
|
|
|
2018-03-02 04:33:41 +00:00
|
|
|
size_t DBImpl::TEST_PreparedSectionCompletedSize() {
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-03 22:35:11 +00:00
|
|
|
return logs_with_prep_tracker_.TEST_PreparedSectionCompletedSize();
|
2018-03-02 04:33:41 +00:00
|
|
|
}
|
|
|
|
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-03 22:35:11 +00:00
|
|
|
size_t DBImpl::TEST_LogsWithPrepSize() {
|
|
|
|
return logs_with_prep_tracker_.TEST_LogsWithPrepSize();
|
|
|
|
}
|
2018-03-02 04:33:41 +00:00
|
|
|
|
2016-04-18 18:11:51 +00:00
|
|
|
uint64_t DBImpl::TEST_FindMinPrepLogReferencedByMemTable() {
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-03 22:35:11 +00:00
|
|
|
autovector<MemTable*> empty_list;
|
Fix a silent data loss for write-committed txn (#9571)
Summary:
The following sequence of events can cause silent data loss for write-committed
transactions.
```
Time thread 1 bg flush
| db->Put("a")
| txn = NewTxn()
| txn->Put("b", "v")
| txn->Prepare() // writes only to 5.log
| db->SwitchMemtable() // memtable 1 has "a"
| // close 5.log,
| // creates 8.log
| trigger flush
| pick memtable 1
| unlock db mutex
| write new sst
| txn->ctwb->Put("gtid", "1") // writes 8.log
| txn->Commit() // writes to 8.log
| // writes to memtable 2
| compute min_log_number_to_keep_2pc, this
| will be 8 (incorrect).
|
| Purge obsolete wals, including 5.log
|
V
```
At this point, writes of txn exists only in memtable. Close db without flush because db thinks the data in
memtable are backed by log. Then reopen, the writes are lost except key-value pair {"gtid"->"1"},
only the commit marker of txn is in 8.log
The reason lies in `PrecomputeMinLogNumberToKeep2PC()` which calls `FindMinPrepLogReferencedByMemTable()`.
In the above example, when bg flush thread tries to find obsolete wals, it uses the information
computed by `PrecomputeMinLogNumberToKeep2PC()`. The return value of `PrecomputeMinLogNumberToKeep2PC()`
depends on three components
- `PrecomputeMinLogNumberToKeepNon2PC()`. This represents the WAL that has unflushed data. As the name of this method suggests, it does not account for 2PC. Although the keys reside in the prepare section of a previous WAL, the column family references the current WAL when they are actually inserted into the memtable during txn commit.
- `prep_tracker->FindMinLogContainingOutstandingPrep()`. This represents the WAL with a prepare section but the txn hasn't committed.
- `FindMinPrepLogReferencedByMemTable()`. This represents the WAL on which some memtables (mutable and immutable) depend for their unflushed data.
The bug lies in `FindMinPrepLogReferencedByMemTable()`. Originally, this function skips checking the column families
that are being flushed, but the unit test added in this PR shows that they should not be. In this unit test, there is
only the default column family, and one of its memtables has unflushed data backed by a prepare section in 5.log.
We should return this information via `FindMinPrepLogReferencedByMemTable()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9571
Test Plan:
```
./transaction_test --gtest_filter=*/TransactionTest.SwitchMemtableDuringPrepareAndCommit_WC/*
make check
```
Reviewed By: siying
Differential Revision: D34235236
Pulled By: riversand963
fbshipit-source-id: 120eb21a666728a38dda77b96276c6af72b008b1
2022-02-17 07:07:48 +00:00
|
|
|
return FindMinPrepLogReferencedByMemTable(versions_.get(), empty_list);
|
2016-04-18 18:11:51 +00:00
|
|
|
}
|
2016-05-17 20:11:56 +00:00
|
|
|
|
|
|
|
Status DBImpl::TEST_GetLatestMutableCFOptions(
|
|
|
|
ColumnFamilyHandle* column_family, MutableCFOptions* mutable_cf_options) {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
|
2020-07-03 02:24:25 +00:00
|
|
|
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
|
2016-05-17 20:11:56 +00:00
|
|
|
*mutable_cf_options = *cfh->cfd()->GetLatestMutableCFOptions();
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
2016-10-14 19:25:39 +00:00
|
|
|
int DBImpl::TEST_BGCompactionsAllowed() const {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
2017-05-24 18:25:38 +00:00
|
|
|
return GetBGJobLimits().max_compactions;
|
|
|
|
}
|
|
|
|
|
|
|
|
int DBImpl::TEST_BGFlushesAllowed() const {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
return GetBGJobLimits().max_flushes;
|
2016-10-14 19:25:39 +00:00
|
|
|
}
|
|
|
|
|
2017-11-11 01:18:01 +00:00
|
|
|
SequenceNumber DBImpl::TEST_GetLastVisibleSequence() const {
|
2017-12-01 07:39:56 +00:00
|
|
|
if (last_seq_same_as_publish_seq_) {
|
2017-10-23 21:20:22 +00:00
|
|
|
return versions_->LastSequence();
|
2017-11-11 01:18:01 +00:00
|
|
|
} else {
|
|
|
|
return versions_->LastAllocatedSequence();
|
2017-10-23 21:20:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-26 17:34:56 +00:00
|
|
|
size_t DBImpl::TEST_GetWalPreallocateBlockSize(
|
|
|
|
uint64_t write_buffer_size) const {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
return GetWalPreallocateBlockSize(write_buffer_size);
|
|
|
|
}
|
|
|
|
|
2022-12-12 18:37:55 +00:00
|
|
|
void DBImpl::TEST_WaitForPeriodicTaskRun(std::function<void()> callback) const {
|
2022-08-26 01:52:37 +00:00
|
|
|
periodic_task_scheduler_.TEST_WaitForRun(callback);
|
move dump stats to a separate thread (#4382)
Summary:
Currently statistics are supposed to be dumped to info log at intervals of `options.stats_dump_period_sec`. However the implementation choice was to bind it with compaction thread, meaning if the database has been serving very light traffic, the stats may not get dumped at all.
We decided to separate stats dumping into a new timed thread using `TimerQueue`, which is already used in blob_db. This will allow us schedule new timed tasks with more deterministic behavior.
Tested with db_bench using `--stats_dump_period_sec=20` in command line:
> LOG:2018/09/17-14:07:45.575025 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG:2018/09/17-14:08:05.643286 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG:2018/09/17-14:08:25.691325 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG:2018/09/17-14:08:45.740989 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG content:
> 2018/09/17-14:07:45.575025 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
2018/09/17-14:07:45.575080 7fe99fbfe700 [WARN] [db/db_impl.cc:606]
** DB Stats **
Uptime(secs): 20.0 total, 20.0 interval
Cumulative writes: 4447K writes, 4447K keys, 4447K commit groups, 1.0 writes per commit group, ingest: 5.57 GB, 285.01 MB/s
Cumulative WAL: 4447K writes, 0 syncs, 4447638.00 writes per sync, written: 5.57 GB, 285.01 MB/s
Cumulative stall: 00:00:0.012 H:M:S, 0.1 percent
Interval writes: 4447K writes, 4447K keys, 4447K commit groups, 1.0 writes per commit group, ingest: 5700.71 MB, 285.01 MB/s
Interval WAL: 4447K writes, 0 syncs, 4447638.00 writes per sync, written: 5.57 MB, 285.01 MB/s
Interval stall: 00:00:0.012 H:M:S, 0.1 percent
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4382
Differential Revision: D9933051
Pulled By: miasantreble
fbshipit-source-id: 6d12bb1e4977674eea4bf2d2ac6d486b814bb2fa
2018-10-09 05:52:58 +00:00
|
|
|
}
|
2019-02-20 23:46:59 +00:00
|
|
|
|
2022-08-26 01:52:37 +00:00
|
|
|
const PeriodicTaskScheduler& DBImpl::TEST_GetPeriodicTaskScheduler() const {
|
|
|
|
return periodic_task_scheduler_;
|
2019-02-20 23:46:59 +00:00
|
|
|
}
|
2022-07-15 04:49:34 +00:00
|
|
|
|
2022-07-19 02:08:39 +00:00
|
|
|
SeqnoToTimeMapping DBImpl::TEST_GetSeqnoToTimeMapping() const {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
Refactor, clean up, fixes, and more testing for SeqnoToTimeMapping (#11905)
Summary:
This change is before a planned DBImpl change to ensure all sufficiently recent sequence numbers since Open are covered by SeqnoToTimeMapping (bug fix with existing test work-arounds). **Intended follow-up**
However, I found enough issues with SeqnoToTimeMapping to warrant this PR first, including very small fixes in DB implementation related to API contract of SeqnoToTimeMapping.
Functional fixes / changes:
* This fixes some mishandling of boundary cases. For example, if the user decides to stop writing to DB, the last written sequence number would perpetually have its write time updated to "now" and would always be ineligible for migration to cold tier. Part of the problem is that the SeqnoToTimeMapping would return a seqno known to have been written before (immediately or otherwise) the requested time, but compaction_job.cc would include that seqno in the preserve/exclude set. That is fixed (in part) by adding one in compaction_job.cc
* That problem was worse because a whole range of seqnos could be updated perpetually with new times in SeqnoToTimeMapping::Append (if no writes to DB). That logic was apparently optimized for GetOldestApproximateTime (now GetProximalTimeBeforeSeqno), which is not used in production, to the detriment of GetOldestSequenceNum (now GetProximalSeqnoBeforeTime), which is used in production. (Perhaps plans changed during development?) This is fixed in Append to optimize for accuracy of GetProximalSeqnoBeforeTime. (Unit tests added and updated.)
* Related: SeqnoToTimeMapping did not have a clear contract about the relationships between seqnos and times, just the idea of a rough correspondence. Now the class description makes it clear that the write time of each recorded seqno comes before or at the associated time, to support getting best results for GetProximalSeqnoBeforeTime. And this makes it easier to make clear the contract of each API function.
* Update `DBImpl::RecordSeqnoToTimeMapping()` to follow this ordering in gathering samples.
Some part of these changes has required an expanded test work-around for the problem (see intended follow-up above) that the DB does not immediately ensure recent seqnos are covered by its mapping. These work-arounds will be removed with that planned work.
An apparent compaction bug is revealed in
PrecludeLastLevelTest::RangeDelsCauseFileEndpointsToOverlap, so that test is disabled. Filed GitHub issue #11909
Cosmetic / code safety things (not exhaustive):
* Fix some confusing names.
* `seqno_time_mapping` was used inconsistently in places. Now just `seqno_to_time_mapping` to correspond to class name.
* Rename confusing `GetOldestSequenceNum` -> `GetProximalSeqnoBeforeTime` and `GetOldestApproximateTime` -> `GetProximalTimeBeforeSeqno`. Part of the motivation is that our times and seqnos here have the same underlying type, so we want to be clear about which is expected where to avoid mixing.
* Rename `kUnknownSeqnoTime` to `kUnknownTimeBeforeAll` because the value is a bad choice for unknown if we ever add ProximalAfterBlah functions.
* Arithmetic on SeqnoTimePair doesn't make sense except for delta encoding, so use better names / APIs with that in mind.
* (OMG) Don't allow direct comparison between SeqnoTimePair and SequenceNumber. (There is no checking that it isn't compared against time by accident.)
* A field name essentially matching the containing class name is a confusing pattern (`seqno_time_mapping_`).
* Wrap calls to confusing (but useful) upper_bound and lower_bound functions to have clearer names and more code reuse.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11905
Test Plan: GetOldestSequenceNum (now GetProximalSeqnoBeforeTime) and TruncateOldEntries were lacking unit tests, despite both being used in production (experimental feature). Added those and expanded others.
Reviewed By: jowlyzhang
Differential Revision: D49755592
Pulled By: pdillinger
fbshipit-source-id: f72a3baac74d24b963c77e538bba89a7fc8dce51
2023-09-29 18:21:59 +00:00
|
|
|
return seqno_to_time_mapping_;
|
2022-07-15 04:49:34 +00:00
|
|
|
}
|
|
|
|
|
2023-11-11 16:11:11 +00:00
|
|
|
const autovector<uint64_t>& DBImpl::TEST_GetFilesToQuarantine() const {
|
|
|
|
InstrumentedMutexLock l(&mutex_);
|
|
|
|
return error_handler_.GetFilesToQuarantine();
|
|
|
|
}
|
2019-02-20 23:46:59 +00:00
|
|
|
|
2019-06-17 22:17:43 +00:00
|
|
|
size_t DBImpl::TEST_EstimateInMemoryStatsHistorySize() const {
|
2023-10-12 17:05:23 +00:00
|
|
|
InstrumentedMutexLock l(&const_cast<DBImpl*>(this)->stats_history_mutex_);
|
2019-06-17 22:17:43 +00:00
|
|
|
return EstimateInMemoryStatsHistorySize();
|
2019-02-20 23:46:59 +00:00
|
|
|
}
|
2020-02-20 20:07:53 +00:00
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
2015-10-13 00:35:43 +00:00
|
|
|
#endif // NDEBUG
|