mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 22:41:48 +00:00
151242ce46
Summary:
**Context:**
The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them.
**Summary**
- Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros`
- Fixed the default histogram in `RandomAccessFileReader`
- New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader`
- Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288
Test Plan:
- **Stress test**
- **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob)
- May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads.
```
./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10)
```
```
// BlockBasedTable
rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805
rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116
rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689
// PlainTable
Does not apply
```
- **Db bench 2: performance**
**Read**
SETUP: db with 900 files
```
./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none
```run till convergence
```
./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3
```
Pre-change
`readrandom [AVG 60 runs] : 21568 (± 248) ops/sec`
Post-change (no regression, -0.3%)
`readrandom [AVG 60 runs] : 21486 (± 236) ops/sec`
**Compaction/Flush**run till convergence
```
./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none
rocksdb.sst.read.micros COUNT : 33820
rocksdb.sst.read.flush.micros COUNT : 1800
rocksdb.sst.read.compaction.micros COUNT : 32020
```
Pre-change
`fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec`
Post-change (no regression, ~-0.4%)
`fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec`
Reviewed By: ajkr
Differential Revision: D44007011
Pulled By: hx235
fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
79 lines
3.2 KiB
C++
79 lines
3.2 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
#pragma once
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
|
|
#include "db/range_tombstone_fragmenter.h"
|
|
#include "db/seqno_to_time_mapping.h"
|
|
#include "db/table_properties_collector.h"
|
|
#include "db/version_set.h"
|
|
#include "logging/event_logger.h"
|
|
#include "options/cf_options.h"
|
|
#include "rocksdb/comparator.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/listener.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/status.h"
|
|
#include "rocksdb/table_properties.h"
|
|
#include "rocksdb/types.h"
|
|
#include "table/scoped_arena_iterator.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
struct FileMetaData;
|
|
|
|
class VersionSet;
|
|
class BlobFileAddition;
|
|
class SnapshotChecker;
|
|
class TableCache;
|
|
class TableBuilder;
|
|
class WritableFileWriter;
|
|
class InternalStats;
|
|
class BlobFileCompletionCallback;
|
|
|
|
// Convenience function for NewTableBuilder on the embedded table_factory.
|
|
TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
|
|
WritableFileWriter* file);
|
|
|
|
// Build a Table file from the contents of *iter. The generated file
|
|
// will be named according to number specified in meta. On success, the rest of
|
|
// *meta will be filled with metadata about the generated table.
|
|
// If no data is present in *iter, meta->file_size will be set to
|
|
// zero, and no Table file will be produced.
|
|
//
|
|
// @param column_family_name Name of the column family that is also identified
|
|
// by column_family_id, or empty string if unknown.
|
|
extern Status BuildTable(
|
|
const std::string& dbname, VersionSet* versions,
|
|
const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
|
|
const FileOptions& file_options, const ReadOptions& read_options,
|
|
TableCache* table_cache, InternalIterator* iter,
|
|
std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
|
|
range_del_iters,
|
|
FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
|
|
std::vector<SequenceNumber> snapshots,
|
|
SequenceNumber earliest_write_conflict_snapshot,
|
|
SequenceNumber job_snapshot, SnapshotChecker* snapshot_checker,
|
|
bool paranoid_file_checks, InternalStats* internal_stats,
|
|
IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
|
|
BlobFileCreationReason blob_creation_reason,
|
|
const SeqnoToTimeMapping& seqno_to_time_mapping,
|
|
EventLogger* event_logger = nullptr, int job_id = 0,
|
|
const Env::IOPriority io_priority = Env::IO_HIGH,
|
|
TableProperties* table_properties = nullptr,
|
|
Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
|
|
const std::string* full_history_ts_low = nullptr,
|
|
BlobFileCompletionCallback* blob_callback = nullptr,
|
|
Version* version = nullptr, uint64_t* num_input_entries = nullptr,
|
|
uint64_t* memtable_payload_bytes = nullptr,
|
|
uint64_t* memtable_garbage_bytes = nullptr);
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|