mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-01 07:15:51 +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
113 lines
4.4 KiB
C++
113 lines
4.4 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).
|
|
|
|
#pragma once
|
|
|
|
#include <cinttypes>
|
|
#include <memory>
|
|
|
|
#include "db/blob/blob_read_request.h"
|
|
#include "file/random_access_file_reader.h"
|
|
#include "rocksdb/compression_type.h"
|
|
#include "rocksdb/rocksdb_namespace.h"
|
|
#include "util/autovector.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class Status;
|
|
struct ImmutableOptions;
|
|
struct FileOptions;
|
|
class HistogramImpl;
|
|
struct ReadOptions;
|
|
class Slice;
|
|
class FilePrefetchBuffer;
|
|
class BlobContents;
|
|
class Statistics;
|
|
|
|
class BlobFileReader {
|
|
public:
|
|
static Status Create(const ImmutableOptions& immutable_options,
|
|
const ReadOptions& read_options,
|
|
const FileOptions& file_options,
|
|
uint32_t column_family_id,
|
|
HistogramImpl* blob_file_read_hist,
|
|
uint64_t blob_file_number,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
std::unique_ptr<BlobFileReader>* reader);
|
|
|
|
BlobFileReader(const BlobFileReader&) = delete;
|
|
BlobFileReader& operator=(const BlobFileReader&) = delete;
|
|
|
|
~BlobFileReader();
|
|
|
|
Status GetBlob(const ReadOptions& read_options, const Slice& user_key,
|
|
uint64_t offset, uint64_t value_size,
|
|
CompressionType compression_type,
|
|
FilePrefetchBuffer* prefetch_buffer,
|
|
MemoryAllocator* allocator,
|
|
std::unique_ptr<BlobContents>* result,
|
|
uint64_t* bytes_read) const;
|
|
|
|
// offsets must be sorted in ascending order by caller.
|
|
void MultiGetBlob(
|
|
const ReadOptions& read_options, MemoryAllocator* allocator,
|
|
autovector<std::pair<BlobReadRequest*, std::unique_ptr<BlobContents>>>&
|
|
blob_reqs,
|
|
uint64_t* bytes_read) const;
|
|
|
|
CompressionType GetCompressionType() const { return compression_type_; }
|
|
|
|
uint64_t GetFileSize() const { return file_size_; }
|
|
|
|
private:
|
|
BlobFileReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
|
|
uint64_t file_size, CompressionType compression_type,
|
|
SystemClock* clock, Statistics* statistics);
|
|
|
|
static Status OpenFile(const ImmutableOptions& immutable_options,
|
|
const FileOptions& file_opts,
|
|
HistogramImpl* blob_file_read_hist,
|
|
uint64_t blob_file_number,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
uint64_t* file_size,
|
|
std::unique_ptr<RandomAccessFileReader>* file_reader);
|
|
|
|
static Status ReadHeader(const RandomAccessFileReader* file_reader,
|
|
const ReadOptions& read_options,
|
|
uint32_t column_family_id, Statistics* statistics,
|
|
CompressionType* compression_type);
|
|
|
|
static Status ReadFooter(const RandomAccessFileReader* file_reader,
|
|
const ReadOptions& read_options, uint64_t file_size,
|
|
Statistics* statistics);
|
|
|
|
using Buffer = std::unique_ptr<char[]>;
|
|
|
|
static Status ReadFromFile(const RandomAccessFileReader* file_reader,
|
|
const ReadOptions& read_options,
|
|
uint64_t read_offset, size_t read_size,
|
|
Statistics* statistics, Slice* slice, Buffer* buf,
|
|
AlignedBuf* aligned_buf,
|
|
Env::IOPriority rate_limiter_priority);
|
|
|
|
static Status VerifyBlob(const Slice& record_slice, const Slice& user_key,
|
|
uint64_t value_size);
|
|
|
|
static Status UncompressBlobIfNeeded(const Slice& value_slice,
|
|
CompressionType compression_type,
|
|
MemoryAllocator* allocator,
|
|
SystemClock* clock,
|
|
Statistics* statistics,
|
|
std::unique_ptr<BlobContents>* result);
|
|
|
|
std::unique_ptr<RandomAccessFileReader> file_reader_;
|
|
uint64_t file_size_;
|
|
CompressionType compression_type_;
|
|
SystemClock* clock_;
|
|
Statistics* statistics_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|