rocksdb/file/writable_file_writer.h

270 lines
9.4 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 <string>
#include "db/version_edit.h"
#include "env/file_system_tracer.h"
#include "port/port.h"
#include "rocksdb/file_checksum.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 22:47:08 +00:00
#include "rocksdb/file_system.h"
#include "rocksdb/io_status.h"
#include "rocksdb/listener.h"
#include "rocksdb/rate_limiter.h"
#include "test_util/sync_point.h"
#include "util/aligned_buffer.h"
namespace ROCKSDB_NAMESPACE {
class Statistics;
class SystemClock;
// WritableFileWriter is a wrapper on top of Env::WritableFile. It provides
// facilities to:
// - Handle Buffered and Direct writes.
// - Rate limit writes.
// - Flush and Sync the data to the underlying filesystem.
// - Notify any interested listeners on the completion of a write.
// - Update IO stats.
class WritableFileWriter {
private:
#ifndef ROCKSDB_LITE
void NotifyOnFileWriteFinish(
uint64_t offset, size_t length,
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const IOStatus& io_status) {
FileOperationInfo info(FileOperationType::kWrite, file_name_, start_ts,
finish_ts, io_status);
info.offset = offset;
info.length = length;
for (auto& listener : listeners_) {
listener->OnFileWriteFinish(info);
}
info.status.PermitUncheckedError();
}
void NotifyOnFileFlushFinish(
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const IOStatus& io_status) {
FileOperationInfo info(FileOperationType::kFlush, file_name_, start_ts,
finish_ts, io_status);
for (auto& listener : listeners_) {
listener->OnFileFlushFinish(info);
}
info.status.PermitUncheckedError();
}
void NotifyOnFileSyncFinish(
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const IOStatus& io_status,
FileOperationType type = FileOperationType::kSync) {
FileOperationInfo info(type, file_name_, start_ts, finish_ts, io_status);
for (auto& listener : listeners_) {
listener->OnFileSyncFinish(info);
}
info.status.PermitUncheckedError();
}
void NotifyOnFileRangeSyncFinish(
uint64_t offset, size_t length,
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const IOStatus& io_status) {
FileOperationInfo info(FileOperationType::kRangeSync, file_name_, start_ts,
finish_ts, io_status);
info.offset = offset;
info.length = length;
for (auto& listener : listeners_) {
listener->OnFileRangeSyncFinish(info);
}
info.status.PermitUncheckedError();
}
void NotifyOnFileTruncateFinish(
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const IOStatus& io_status) {
FileOperationInfo info(FileOperationType::kTruncate, file_name_, start_ts,
finish_ts, io_status);
for (auto& listener : listeners_) {
listener->OnFileTruncateFinish(info);
}
info.status.PermitUncheckedError();
}
void NotifyOnFileCloseFinish(
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const IOStatus& io_status) {
FileOperationInfo info(FileOperationType::kClose, file_name_, start_ts,
finish_ts, io_status);
for (auto& listener : listeners_) {
listener->OnFileCloseFinish(info);
}
info.status.PermitUncheckedError();
}
#endif // ROCKSDB_LITE
bool ShouldNotifyListeners() const { return !listeners_.empty(); }
void UpdateFileChecksum(const Slice& data);
void Crc32cHandoffChecksumCalculation(const char* data, size_t size,
char* buf);
std::string file_name_;
FSWritableFilePtr writable_file_;
SystemClock* clock_;
AlignedBuffer buf_;
size_t max_buffer_size_;
// Actually written data size can be used for truncate
// not counting padding data
uint64_t filesize_;
#ifndef ROCKSDB_LITE
// This is necessary when we use unbuffered access
// and writes must happen on aligned offsets
// so we need to go back and write that page again
uint64_t next_write_offset_;
#endif // ROCKSDB_LITE
bool pending_sync_;
uint64_t last_sync_size_;
uint64_t bytes_per_sync_;
RateLimiter* rate_limiter_;
Statistics* stats_;
std::vector<std::shared_ptr<EventListener>> listeners_;
std::unique_ptr<FileChecksumGenerator> checksum_generator_;
bool checksum_finalized_;
bool perform_data_verification_;
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
uint32_t buffered_data_crc32c_checksum_;
bool buffered_data_with_checksum_;
public:
WritableFileWriter(
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 22:47:08 +00:00
std::unique_ptr<FSWritableFile>&& file, const std::string& _file_name,
const FileOptions& options, SystemClock* clock = nullptr,
const std::shared_ptr<IOTracer>& io_tracer = nullptr,
Statistics* stats = nullptr,
const std::vector<std::shared_ptr<EventListener>>& listeners = {},
FileChecksumGenFactory* file_checksum_gen_factory = nullptr,
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
bool perform_data_verification = false,
bool buffered_data_with_checksum = false)
: file_name_(_file_name),
writable_file_(std::move(file), io_tracer, _file_name),
clock_(clock),
buf_(),
max_buffer_size_(options.writable_file_max_buffer_size),
filesize_(0),
#ifndef ROCKSDB_LITE
next_write_offset_(0),
#endif // ROCKSDB_LITE
pending_sync_(false),
last_sync_size_(0),
bytes_per_sync_(options.bytes_per_sync),
rate_limiter_(options.rate_limiter),
stats_(stats),
listeners_(),
checksum_generator_(nullptr),
checksum_finalized_(false),
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
perform_data_verification_(perform_data_verification),
buffered_data_crc32c_checksum_(0),
buffered_data_with_checksum_(buffered_data_with_checksum) {
TEST_SYNC_POINT_CALLBACK("WritableFileWriter::WritableFileWriter:0",
reinterpret_cast<void*>(max_buffer_size_));
buf_.Alignment(writable_file_->GetRequiredBufferAlignment());
buf_.AllocateNewBuffer(std::min((size_t)65536, max_buffer_size_));
#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
if (file_checksum_gen_factory != nullptr) {
FileChecksumGenContext checksum_gen_context;
checksum_gen_context.file_name = _file_name;
checksum_generator_ =
file_checksum_gen_factory->CreateFileChecksumGenerator(
checksum_gen_context);
}
}
static Status Create(const std::shared_ptr<FileSystem>& fs,
const std::string& fname, const FileOptions& file_opts,
std::unique_ptr<WritableFileWriter>* writer,
IODebugContext* dbg);
WritableFileWriter(const WritableFileWriter&) = delete;
WritableFileWriter& operator=(const WritableFileWriter&) = delete;
~WritableFileWriter() {
auto s = Close();
s.PermitUncheckedError();
}
std::string file_name() const { return file_name_; }
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
// When this Append API is called, if the crc32c_checksum is not provided, we
// will calculate the checksum internally.
IOStatus Append(const Slice& data, uint32_t crc32c_checksum = 0);
IOStatus Pad(const size_t pad_bytes);
IOStatus Flush();
IOStatus Close();
IOStatus Sync(bool use_fsync);
// Sync only the data that was already Flush()ed. Safe to call concurrently
// with Append() and Flush(). If !writable_file_->IsSyncThreadSafe(),
// returns NotSupported status.
IOStatus SyncWithoutFlush(bool use_fsync);
uint64_t GetFileSize() const { return filesize_; }
IOStatus InvalidateCache(size_t offset, size_t length) {
return writable_file_->InvalidateCache(offset, length);
}
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 22:47:08 +00:00
FSWritableFile* writable_file() const { return writable_file_.get(); }
bool use_direct_io() { return writable_file_->use_direct_io(); }
bool TEST_BufferIsEmpty() { return buf_.CurrentSize() == 0; }
void TEST_SetFileChecksumGenerator(
FileChecksumGenerator* checksum_generator) {
checksum_generator_.reset(checksum_generator);
}
std::string GetFileChecksum();
const char* GetFileChecksumFuncName() const;
private:
// Used when os buffering is OFF and we are writing
// DMA such as in Direct I/O mode
#ifndef ROCKSDB_LITE
IOStatus WriteDirect();
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
IOStatus WriteDirectWithChecksum();
#endif // !ROCKSDB_LITE
// Normal write
IOStatus WriteBuffered(const char* data, size_t size);
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
IOStatus WriteBufferedWithChecksum(const char* data, size_t size);
IOStatus RangeSync(uint64_t offset, uint64_t nbytes);
IOStatus SyncInternal(bool use_fsync);
};
} // namespace ROCKSDB_NAMESPACE