2019-06-17 22:17:43 +00:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
|
|
|
|
|
|
#include "monitoring/persistent_stats_history.h"
|
|
|
|
|
|
|
|
#include <cstring>
|
|
|
|
#include <string>
|
|
|
|
#include <utility>
|
2022-10-25 03:45:54 +00:00
|
|
|
|
2019-06-17 22:17:43 +00:00
|
|
|
#include "db/db_impl/db_impl.h"
|
|
|
|
#include "util/string_util.h"
|
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
namespace ROCKSDB_NAMESPACE {
|
2019-06-17 22:17:43 +00:00
|
|
|
// 10 digit seconds timestamp => [Sep 9, 2001 ~ Nov 20, 2286]
|
|
|
|
const int kNowSecondsStringLength = 10;
|
|
|
|
const std::string kFormatVersionKeyString =
|
|
|
|
"__persistent_stats_format_version__";
|
|
|
|
const std::string kCompatibleVersionKeyString =
|
|
|
|
"__persistent_stats_compatible_version__";
|
|
|
|
// Every release maintains two versions numbers for persistents stats: Current
|
|
|
|
// format version and compatible format version. Current format version
|
|
|
|
// designates what type of encoding will be used when writing to stats CF;
|
|
|
|
// compatible format version designates the minimum format version that
|
|
|
|
// can decode the stats CF encoded using the current format version.
|
|
|
|
const uint64_t kStatsCFCurrentFormatVersion = 1;
|
|
|
|
const uint64_t kStatsCFCompatibleFormatVersion = 1;
|
|
|
|
|
|
|
|
Status DecodePersistentStatsVersionNumber(DBImpl* db, StatsVersionKeyType type,
|
|
|
|
uint64_t* version_number) {
|
|
|
|
if (type >= StatsVersionKeyType::kKeyTypeMax) {
|
|
|
|
return Status::InvalidArgument("Invalid stats version key type provided");
|
|
|
|
}
|
|
|
|
std::string key;
|
|
|
|
if (type == StatsVersionKeyType::kFormatVersion) {
|
|
|
|
key = kFormatVersionKeyString;
|
|
|
|
} else if (type == StatsVersionKeyType::kCompatibleVersion) {
|
|
|
|
key = kCompatibleVersionKeyString;
|
|
|
|
}
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
|
|
|
|
// TODO: plumb Env::IOActivity, Env::IOPriority
|
2019-06-17 22:17:43 +00:00
|
|
|
ReadOptions options;
|
|
|
|
options.verify_checksums = true;
|
|
|
|
std::string result;
|
|
|
|
Status s = db->Get(options, db->PersistentStatsColumnFamily(), key, &result);
|
|
|
|
if (!s.ok() || result.empty()) {
|
|
|
|
return Status::NotFound("Persistent stats version key " + key +
|
|
|
|
" not found.");
|
|
|
|
}
|
|
|
|
|
|
|
|
// read version_number but do nothing in current version
|
|
|
|
*version_number = ParseUint64(result);
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
|
|
|
int EncodePersistentStatsKey(uint64_t now_seconds, const std::string& key,
|
|
|
|
int size, char* buf) {
|
|
|
|
char timestamp[kNowSecondsStringLength + 1];
|
|
|
|
// make time stamp string equal in length to allow sorting by time
|
|
|
|
snprintf(timestamp, sizeof(timestamp), "%010d",
|
|
|
|
static_cast<int>(now_seconds));
|
|
|
|
timestamp[kNowSecondsStringLength] = '\0';
|
|
|
|
return snprintf(buf, size, "%s#%s", timestamp, key.c_str());
|
|
|
|
}
|
|
|
|
|
|
|
|
void OptimizeForPersistentStats(ColumnFamilyOptions* cfo) {
|
|
|
|
cfo->write_buffer_size = 2 << 20;
|
|
|
|
cfo->target_file_size_base = 2 * 1048576;
|
|
|
|
cfo->max_bytes_for_level_base = 10 * 1048576;
|
|
|
|
cfo->soft_pending_compaction_bytes_limit = 256 * 1048576;
|
|
|
|
cfo->hard_pending_compaction_bytes_limit = 1073741824ul;
|
|
|
|
cfo->compression = kNoCompression;
|
|
|
|
}
|
|
|
|
|
2023-12-01 19:10:30 +00:00
|
|
|
PersistentStatsHistoryIterator::~PersistentStatsHistoryIterator() = default;
|
2019-06-17 22:17:43 +00:00
|
|
|
|
|
|
|
bool PersistentStatsHistoryIterator::Valid() const { return valid_; }
|
|
|
|
|
|
|
|
Status PersistentStatsHistoryIterator::status() const { return status_; }
|
|
|
|
|
|
|
|
void PersistentStatsHistoryIterator::Next() {
|
|
|
|
// increment start_time by 1 to avoid infinite loop
|
|
|
|
AdvanceIteratorByTime(GetStatsTime() + 1, end_time_);
|
|
|
|
}
|
|
|
|
|
|
|
|
uint64_t PersistentStatsHistoryIterator::GetStatsTime() const { return time_; }
|
|
|
|
|
|
|
|
const std::map<std::string, uint64_t>&
|
|
|
|
PersistentStatsHistoryIterator::GetStatsMap() const {
|
|
|
|
return stats_map_;
|
|
|
|
}
|
|
|
|
|
|
|
|
std::pair<uint64_t, std::string> parseKey(const Slice& key,
|
|
|
|
uint64_t start_time) {
|
|
|
|
std::pair<uint64_t, std::string> result;
|
|
|
|
std::string key_str = key.ToString();
|
2023-12-01 19:10:30 +00:00
|
|
|
std::string::size_type pos = key_str.find('#');
|
2019-06-17 22:17:43 +00:00
|
|
|
// TODO(Zhongyi): add counters to track parse failures?
|
|
|
|
if (pos == std::string::npos) {
|
2022-05-05 20:08:21 +00:00
|
|
|
result.first = std::numeric_limits<uint64_t>::max();
|
2019-06-17 22:17:43 +00:00
|
|
|
result.second.clear();
|
|
|
|
} else {
|
|
|
|
uint64_t parsed_time = ParseUint64(key_str.substr(0, pos));
|
|
|
|
// skip entries with timestamp smaller than start_time
|
|
|
|
if (parsed_time < start_time) {
|
2022-05-05 20:08:21 +00:00
|
|
|
result.first = std::numeric_limits<uint64_t>::max();
|
2019-06-17 22:17:43 +00:00
|
|
|
result.second = "";
|
|
|
|
} else {
|
|
|
|
result.first = parsed_time;
|
|
|
|
std::string key_resize = key_str.substr(pos + 1);
|
|
|
|
result.second = key_resize;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
// advance the iterator to the next time between [start_time, end_time)
|
|
|
|
// if success, update time_ and stats_map_ with new_time and stats_map
|
|
|
|
void PersistentStatsHistoryIterator::AdvanceIteratorByTime(uint64_t start_time,
|
|
|
|
uint64_t end_time) {
|
|
|
|
// try to find next entry in stats_history_ map
|
|
|
|
if (db_impl_ != nullptr) {
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
// TODO: plumb Env::IOActivity, Env::IOPriority
|
2019-06-17 22:17:43 +00:00
|
|
|
ReadOptions ro;
|
|
|
|
Iterator* iter =
|
|
|
|
db_impl_->NewIterator(ro, db_impl_->PersistentStatsColumnFamily());
|
|
|
|
|
|
|
|
char timestamp[kNowSecondsStringLength + 1];
|
|
|
|
snprintf(timestamp, sizeof(timestamp), "%010d",
|
|
|
|
static_cast<int>(std::max(time_, start_time)));
|
|
|
|
timestamp[kNowSecondsStringLength] = '\0';
|
|
|
|
|
|
|
|
iter->Seek(timestamp);
|
|
|
|
// no more entries with timestamp >= start_time is found or version key
|
|
|
|
// is found to be incompatible
|
|
|
|
if (!iter->Valid()) {
|
|
|
|
valid_ = false;
|
|
|
|
delete iter;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
time_ = parseKey(iter->key(), start_time).first;
|
|
|
|
valid_ = true;
|
|
|
|
// check parsed time and invalid if it exceeds end_time
|
|
|
|
if (time_ > end_time) {
|
|
|
|
valid_ = false;
|
|
|
|
delete iter;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
// find all entries with timestamp equal to time_
|
|
|
|
std::map<std::string, uint64_t> new_stats_map;
|
|
|
|
std::pair<uint64_t, std::string> kv;
|
|
|
|
for (; iter->Valid(); iter->Next()) {
|
|
|
|
kv = parseKey(iter->key(), start_time);
|
|
|
|
if (kv.first != time_) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (kv.second.compare(kFormatVersionKeyString) == 0) {
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
new_stats_map[kv.second] = ParseUint64(iter->value().ToString());
|
|
|
|
}
|
|
|
|
stats_map_.swap(new_stats_map);
|
|
|
|
delete iter;
|
|
|
|
} else {
|
|
|
|
valid_ = false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
} // namespace ROCKSDB_NAMESPACE
|