rocksdb/file/random_access_file_reader.h

148 lines
5.5 KiB
C
Raw Normal View History

// 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"
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
#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 Env::RnadomAccessFile. 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:
#ifndef ROCKSDB_LITE
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);
}
}
#endif // ROCKSDB_LITE
bool ShouldNotifyListeners() const { return !listeners_.empty(); }
FSRandomAccessFilePtr file_;
std::string file_name_;
std::shared_ptr<SystemClock> clock_;
Statistics* stats_;
uint32_t hist_type_;
HistogramImpl* file_read_hist_;
RateLimiter* rate_limiter_;
std::vector<std::shared_ptr<EventListener>> listeners_;
public:
explicit RandomAccessFileReader(
std::unique_ptr<FSRandomAccessFile>&& raf, const std::string& _file_name,
const std::shared_ptr<SystemClock>& clock = nullptr,
const std::shared_ptr<IOTracer>& io_tracer = nullptr,
Statistics* stats = nullptr, uint32_t hist_type = 0,
HistogramImpl* file_read_hist = nullptr,
RateLimiter* rate_limiter = nullptr,
const std::vector<std::shared_ptr<EventListener>>& listeners = {})
: 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_() {
#ifndef ROCKSDB_LITE
std::for_each(listeners.begin(), listeners.end(),
[this](const std::shared_ptr<EventListener>& e) {
if (e->ShouldBeNotifiedOnFileIO()) {
listeners_.emplace_back(e);
}
});
#else // !ROCKSDB_LITE
(void)listeners;
#endif
}
static Status 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.
Status Read(const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
char* scratch, AlignedBuf* aligned_buf,
bool for_compaction = false) 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.
Status MultiRead(const IOOptions& opts, FSReadRequest* reqs, size_t num_reqs,
AlignedBuf* aligned_buf) const;
Status Prefetch(uint64_t offset, size_t n) const {
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
return file_->Prefetch(offset, n, IOOptions(), nullptr);
}
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
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);
};
} // namespace ROCKSDB_NAMESPACE