mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-03 05:54:17 +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
211 lines
7.9 KiB
C++
211 lines
7.9 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 <atomic>
|
|
#include <sstream>
|
|
#include <string>
|
|
|
|
#include "env/file_system_tracer.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/file_system.h"
|
|
#include "rocksdb/listener.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/rate_limiter.h"
|
|
#include "util/aligned_buffer.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
class Statistics;
|
|
class HistogramImpl;
|
|
class SystemClock;
|
|
|
|
using AlignedBuf = std::unique_ptr<char[]>;
|
|
|
|
// Align the request r according to alignment and return the aligned result.
|
|
FSReadRequest Align(const FSReadRequest& r, size_t alignment);
|
|
|
|
// Try to merge src to dest if they have overlap.
|
|
//
|
|
// Each request represents an inclusive interval [offset, offset + len].
|
|
// If the intervals have overlap, update offset and len to represent the
|
|
// merged interval, and return true.
|
|
// Otherwise, do nothing and return false.
|
|
bool TryMerge(FSReadRequest* dest, const FSReadRequest& src);
|
|
|
|
// RandomAccessFileReader is a wrapper on top of FSRandomAccessFile. It is
|
|
// responsible for:
|
|
// - Handling Buffered and Direct reads appropriately.
|
|
// - Rate limiting compaction reads.
|
|
// - Notifying any interested listeners on the completion of a read.
|
|
// - Updating IO stats.
|
|
class RandomAccessFileReader {
|
|
private:
|
|
void NotifyOnFileReadFinish(
|
|
uint64_t offset, size_t length,
|
|
const FileOperationInfo::StartTimePoint& start_ts,
|
|
const FileOperationInfo::FinishTimePoint& finish_ts,
|
|
const Status& status) const {
|
|
FileOperationInfo info(FileOperationType::kRead, file_name_, start_ts,
|
|
finish_ts, status, file_temperature_);
|
|
info.offset = offset;
|
|
info.length = length;
|
|
|
|
for (auto& listener : listeners_) {
|
|
listener->OnFileReadFinish(info);
|
|
}
|
|
info.status.PermitUncheckedError();
|
|
}
|
|
|
|
void NotifyOnIOError(const IOStatus& io_status, FileOperationType operation,
|
|
const std::string& file_path, size_t length,
|
|
uint64_t offset) const {
|
|
if (listeners_.empty()) {
|
|
return;
|
|
}
|
|
IOErrorInfo io_error_info(io_status, operation, file_path, length, offset);
|
|
|
|
for (auto& listener : listeners_) {
|
|
listener->OnIOError(io_error_info);
|
|
}
|
|
io_status.PermitUncheckedError();
|
|
}
|
|
|
|
|
|
bool ShouldNotifyListeners() const { return !listeners_.empty(); }
|
|
|
|
FSRandomAccessFilePtr file_;
|
|
std::string file_name_;
|
|
SystemClock* clock_;
|
|
Statistics* stats_;
|
|
uint32_t hist_type_;
|
|
HistogramImpl* file_read_hist_;
|
|
RateLimiter* rate_limiter_;
|
|
std::vector<std::shared_ptr<EventListener>> listeners_;
|
|
const Temperature file_temperature_;
|
|
const bool is_last_level_;
|
|
|
|
struct ReadAsyncInfo {
|
|
ReadAsyncInfo(std::function<void(const FSReadRequest&, void*)> cb,
|
|
void* cb_arg, uint64_t start_time)
|
|
: cb_(cb),
|
|
cb_arg_(cb_arg),
|
|
start_time_(start_time),
|
|
user_scratch_(nullptr),
|
|
user_aligned_buf_(nullptr),
|
|
user_offset_(0),
|
|
user_len_(0),
|
|
is_aligned_(false) {}
|
|
|
|
std::function<void(const FSReadRequest&, void*)> cb_;
|
|
void* cb_arg_;
|
|
uint64_t start_time_;
|
|
FileOperationInfo::StartTimePoint fs_start_ts_;
|
|
// Below fields stores the parameters passed by caller in case of direct_io.
|
|
char* user_scratch_;
|
|
AlignedBuf* user_aligned_buf_;
|
|
uint64_t user_offset_;
|
|
size_t user_len_;
|
|
Slice user_result_;
|
|
// Used in case of direct_io
|
|
AlignedBuffer buf_;
|
|
bool is_aligned_;
|
|
};
|
|
|
|
public:
|
|
explicit RandomAccessFileReader(
|
|
std::unique_ptr<FSRandomAccessFile>&& raf, const std::string& _file_name,
|
|
SystemClock* clock = nullptr,
|
|
const std::shared_ptr<IOTracer>& io_tracer = nullptr,
|
|
Statistics* stats = nullptr,
|
|
uint32_t hist_type = Histograms::HISTOGRAM_ENUM_MAX,
|
|
HistogramImpl* file_read_hist = nullptr,
|
|
RateLimiter* rate_limiter = nullptr,
|
|
const std::vector<std::shared_ptr<EventListener>>& listeners = {},
|
|
Temperature file_temperature = Temperature::kUnknown,
|
|
bool is_last_level = false)
|
|
: file_(std::move(raf), io_tracer, _file_name),
|
|
file_name_(std::move(_file_name)),
|
|
clock_(clock),
|
|
stats_(stats),
|
|
hist_type_(hist_type),
|
|
file_read_hist_(file_read_hist),
|
|
rate_limiter_(rate_limiter),
|
|
listeners_(),
|
|
file_temperature_(file_temperature),
|
|
is_last_level_(is_last_level) {
|
|
std::for_each(listeners.begin(), listeners.end(),
|
|
[this](const std::shared_ptr<EventListener>& e) {
|
|
if (e->ShouldBeNotifiedOnFileIO()) {
|
|
listeners_.emplace_back(e);
|
|
}
|
|
});
|
|
}
|
|
|
|
static IOStatus Create(const std::shared_ptr<FileSystem>& fs,
|
|
const std::string& fname, const FileOptions& file_opts,
|
|
std::unique_ptr<RandomAccessFileReader>* reader,
|
|
IODebugContext* dbg);
|
|
RandomAccessFileReader(const RandomAccessFileReader&) = delete;
|
|
RandomAccessFileReader& operator=(const RandomAccessFileReader&) = delete;
|
|
|
|
// In non-direct IO mode,
|
|
// 1. if using mmap, result is stored in a buffer other than scratch;
|
|
// 2. if not using mmap, result is stored in the buffer starting from scratch.
|
|
//
|
|
// In direct IO mode, an aligned buffer is allocated internally.
|
|
// 1. If aligned_buf is null, then results are copied to the buffer
|
|
// starting from scratch;
|
|
// 2. Otherwise, scratch is not used and can be null, the aligned_buf owns
|
|
// the internally allocated buffer on return, and the result refers to a
|
|
// region in aligned_buf.
|
|
//
|
|
// `rate_limiter_priority` is used to charge the internal rate limiter when
|
|
// enabled. The special value `Env::IO_TOTAL` makes this operation bypass the
|
|
// rate limiter.
|
|
IOStatus Read(const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
|
|
char* scratch, AlignedBuf* aligned_buf,
|
|
Env::IOPriority rate_limiter_priority) const;
|
|
|
|
// REQUIRES:
|
|
// num_reqs > 0, reqs do not overlap, and offsets in reqs are increasing.
|
|
// In non-direct IO mode, aligned_buf should be null;
|
|
// In direct IO mode, aligned_buf stores the aligned buffer allocated inside
|
|
// MultiRead, the result Slices in reqs refer to aligned_buf.
|
|
//
|
|
// `rate_limiter_priority` will be used to charge the internal rate limiter.
|
|
// It is not yet supported so the client must provide the special value
|
|
// `Env::IO_TOTAL` to bypass the rate limiter.
|
|
IOStatus MultiRead(const IOOptions& opts, FSReadRequest* reqs,
|
|
size_t num_reqs, AlignedBuf* aligned_buf,
|
|
Env::IOPriority rate_limiter_priority) const;
|
|
|
|
IOStatus Prefetch(uint64_t offset, size_t n,
|
|
const Env::IOPriority rate_limiter_priority) const {
|
|
IOOptions opts;
|
|
opts.rate_limiter_priority = rate_limiter_priority;
|
|
return file_->Prefetch(offset, n, opts, nullptr);
|
|
}
|
|
|
|
FSRandomAccessFile* file() { return file_.get(); }
|
|
|
|
const std::string& file_name() const { return file_name_; }
|
|
|
|
bool use_direct_io() const { return file_->use_direct_io(); }
|
|
|
|
IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts) const;
|
|
|
|
IOStatus ReadAsync(FSReadRequest& req, const IOOptions& opts,
|
|
std::function<void(const FSReadRequest&, void*)> cb,
|
|
void* cb_arg, void** io_handle, IOHandleDeleter* del_fn,
|
|
AlignedBuf* aligned_buf);
|
|
|
|
void ReadAsyncCallback(const FSReadRequest& req, void* cb_arg);
|
|
};
|
|
} // namespace ROCKSDB_NAMESPACE
|