mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 22:41:48 +00:00
9a034801ce
Summary:
**Context/Summary:**
- Similar to https://github.com/facebook/rocksdb/pull/11288 but for user read such as `Get(), MultiGet(), DBIterator::XXX(), Verify(File)Checksum()`.
- For this, I refactored some user-facing `MultiGet` calls in `TransactionBase` and various types of `DB` so that it does not call a user-facing `Get()` but `GetImpl()` for passing the `ReadOptions::io_activity` check (see PR conversation)
- New user read stats breakdown are guarded by `kExceptDetailedTimers` since measurement shows they have 4-5% regression to the upstream/main.
- Misc
- More refactoring: with https://github.com/facebook/rocksdb/pull/11288, we complete passing `ReadOptions/IOOptions` to FS level. So we can now replace the previously [added](https://github.com/facebook/rocksdb/pull/9424) `rate_limiter_priority` parameter in `RandomAccessFileReader`'s `Read/MultiRead/Prefetch()` with `IOOptions::rate_limiter_priority`
- Also, `ReadAsync()` call time is measured in `SST_READ_MICRO` now
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11444
Test Plan:
- CI fake db crash/stress test
- Microbenchmarking
**Build** `make clean && ROCKSDB_NO_FBCODE=1 DEBUG_LEVEL=0 make -jN db_basic_bench`
- google benchmark version: 604f6fd3f4
- db_basic_bench_base: upstream
- db_basic_bench_pr: db_basic_bench_base + this PR
- asyncread_db_basic_bench_base: upstream + [db basic bench patch for IteratorNext](https://github.com/facebook/rocksdb/compare/main...hx235:rocksdb:micro_bench_async_read)
- asyncread_db_basic_bench_pr: asyncread_db_basic_bench_base + this PR
**Test**
Get
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{null_stat|base|pr} --benchmark_filter=DBGet/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/negative_query:0/enable_filter:0/mmap:1/threads:1 --benchmark_repetitions=1000
```
Result
```
Coming soon
```
AsyncRead
```
TEST_TMPDIR=/dev/shm ./asyncread_db_basic_bench_{base|pr} --benchmark_filter=IteratorNext/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/async_io:1/include_detailed_timers:0 --benchmark_repetitions=1000 > syncread_db_basic_bench_{base|pr}.out
```
Result
```
Base:
1956,1956,1968,1977,1979,1986,1988,1988,1988,1990,1991,1991,1993,1993,1993,1993,1994,1996,1997,1997,1997,1998,1999,2001,2001,2002,2004,2007,2007,2008,
PR (2.3% regression, due to measuring `SST_READ_MICRO` that wasn't measured before):
1993,2014,2016,2022,2024,2027,2027,2028,2028,2030,2031,2031,2032,2032,2038,2039,2042,2044,2044,2047,2047,2047,2048,2049,2050,2052,2052,2052,2053,2053,
```
Reviewed By: ajkr
Differential Revision: D45918925
Pulled By: hx235
fbshipit-source-id: 58a54560d9ebeb3a59b6d807639692614dad058a
123 lines
4.8 KiB
C++
123 lines
4.8 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 <string>
|
|
|
|
#include "env/file_system_tracer.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/file_system.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
// SequentialFileReader is a wrapper on top of Env::SequentialFile. It handles
|
|
// Buffered (i.e when page cache is enabled) and Direct (with O_DIRECT / page
|
|
// cache disabled) reads appropriately, and also updates the IO stats.
|
|
class SequentialFileReader {
|
|
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);
|
|
info.offset = offset;
|
|
info.length = length;
|
|
|
|
for (auto& listener : listeners_) {
|
|
listener->OnFileReadFinish(info);
|
|
}
|
|
info.status.PermitUncheckedError();
|
|
}
|
|
|
|
void AddFileIOListeners(
|
|
const std::vector<std::shared_ptr<EventListener>>& listeners) {
|
|
std::for_each(listeners.begin(), listeners.end(),
|
|
[this](const std::shared_ptr<EventListener>& e) {
|
|
if (e->ShouldBeNotifiedOnFileIO()) {
|
|
listeners_.emplace_back(e);
|
|
}
|
|
});
|
|
}
|
|
|
|
bool ShouldNotifyListeners() const { return !listeners_.empty(); }
|
|
|
|
std::string file_name_;
|
|
FSSequentialFilePtr file_;
|
|
std::atomic<size_t> offset_{0}; // read offset
|
|
std::vector<std::shared_ptr<EventListener>> listeners_{};
|
|
RateLimiter* rate_limiter_;
|
|
|
|
public:
|
|
explicit SequentialFileReader(
|
|
std::unique_ptr<FSSequentialFile>&& _file, const std::string& _file_name,
|
|
const std::shared_ptr<IOTracer>& io_tracer = nullptr,
|
|
const std::vector<std::shared_ptr<EventListener>>& listeners = {},
|
|
RateLimiter* rate_limiter =
|
|
nullptr) // TODO: migrate call sites to provide rate limiter
|
|
: file_name_(_file_name),
|
|
file_(std::move(_file), io_tracer, _file_name),
|
|
listeners_(),
|
|
rate_limiter_(rate_limiter) {
|
|
AddFileIOListeners(listeners);
|
|
}
|
|
|
|
explicit SequentialFileReader(
|
|
std::unique_ptr<FSSequentialFile>&& _file, const std::string& _file_name,
|
|
size_t _readahead_size,
|
|
const std::shared_ptr<IOTracer>& io_tracer = nullptr,
|
|
const std::vector<std::shared_ptr<EventListener>>& listeners = {},
|
|
RateLimiter* rate_limiter =
|
|
nullptr) // TODO: migrate call sites to provide rate limiter
|
|
: file_name_(_file_name),
|
|
file_(NewReadaheadSequentialFile(std::move(_file), _readahead_size),
|
|
io_tracer, _file_name),
|
|
listeners_(),
|
|
rate_limiter_(rate_limiter) {
|
|
AddFileIOListeners(listeners);
|
|
}
|
|
static IOStatus Create(const std::shared_ptr<FileSystem>& fs,
|
|
const std::string& fname, const FileOptions& file_opts,
|
|
std::unique_ptr<SequentialFileReader>* reader,
|
|
IODebugContext* dbg, RateLimiter* rate_limiter);
|
|
|
|
SequentialFileReader(const SequentialFileReader&) = delete;
|
|
SequentialFileReader& operator=(const SequentialFileReader&) = delete;
|
|
|
|
// `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. The amount charged to the internal rate limiter is n, even
|
|
// when less than n bytes are actually read (e.g. at end of file). To avoid
|
|
// overcharging the rate limiter, the caller can use file size to cap n to
|
|
// read until end of file.
|
|
//
|
|
// TODO(hx235): accept parameter `IOOptions` containing
|
|
// `rate_limiter_priority` like RandomAccessFileReader::Read()
|
|
IOStatus Read(size_t n, Slice* result, char* scratch,
|
|
Env::IOPriority rate_limiter_priority);
|
|
|
|
IOStatus Skip(uint64_t n);
|
|
|
|
FSSequentialFile* file() { return file_.get(); }
|
|
|
|
std::string file_name() { return file_name_; }
|
|
|
|
bool use_direct_io() const { return file_->use_direct_io(); }
|
|
|
|
private:
|
|
// NewReadaheadSequentialFile provides a wrapper over SequentialFile to
|
|
// always prefetch additional data with every read.
|
|
static std::unique_ptr<FSSequentialFile> NewReadaheadSequentialFile(
|
|
std::unique_ptr<FSSequentialFile>&& file, size_t readahead_size);
|
|
};
|
|
} // namespace ROCKSDB_NAMESPACE
|