mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-04 20:02:50 +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
198 lines
7.2 KiB
C++
198 lines
7.2 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 <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.
|
|
IOStatus Read(const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
|
|
char* scratch, AlignedBuf* aligned_buf) 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.
|
|
IOStatus MultiRead(const IOOptions& opts, FSReadRequest* reqs,
|
|
size_t num_reqs, AlignedBuf* aligned_buf) const;
|
|
|
|
IOStatus Prefetch(const IOOptions& opts, uint64_t offset, size_t n) const {
|
|
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
|