mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 02:44:18 +00:00
da96f2fe00
Summary: Currently one thread in RocksDB keeps a WAL file open while another thread deletes it. Although the first thread never writes to the WAL again, it still tries to close it in the end. This is fine on POSIX, but can be problematic on other platforms, e.g. HDFS, etc.. It will either cause a lot of warning messages or throw exceptions. The solution is to let the second thread close the WAL before deleting it. RocksDB keeps the writers of the logs to delete in `logs_to_free_`, which is passed to `job_context` during `FindObsoleteFiles` (holding mutex). Then in `PurgeObsoleteFiles` (without mutex), these writers should close the logs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5233 Differential Revision: D15032670 Pulled By: riversand963 fbshipit-source-id: c55e8a612db8cc2306644001a5e6d53842a8f754
115 lines
3.8 KiB
C++
115 lines
3.8 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 <stdint.h>
|
|
|
|
#include <memory>
|
|
|
|
#include "db/log_format.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "rocksdb/status.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class WritableFileWriter;
|
|
|
|
namespace log {
|
|
|
|
/**
|
|
* Writer is a general purpose log stream writer. It provides an append-only
|
|
* abstraction for writing data. The details of the how the data is written is
|
|
* handled by the WriteableFile sub-class implementation.
|
|
*
|
|
* File format:
|
|
*
|
|
* File is broken down into variable sized records. The format of each record
|
|
* is described below.
|
|
* +-----+-------------+--+----+----------+------+-- ... ----+
|
|
* File | r0 | r1 |P | r2 | r3 | r4 | |
|
|
* +-----+-------------+--+----+----------+------+-- ... ----+
|
|
* <--- kBlockSize ------>|<-- kBlockSize ------>|
|
|
* rn = variable size records
|
|
* P = Padding
|
|
*
|
|
* Data is written out in kBlockSize chunks. If next record does not fit
|
|
* into the space left, the leftover space will be padded with \0.
|
|
*
|
|
* Legacy record format:
|
|
*
|
|
* +---------+-----------+-----------+--- ... ---+
|
|
* |CRC (4B) | Size (2B) | Type (1B) | Payload |
|
|
* +---------+-----------+-----------+--- ... ---+
|
|
*
|
|
* CRC = 32bit hash computed over the record type and payload using CRC
|
|
* Size = Length of the payload data
|
|
* Type = Type of record
|
|
* (kZeroType, kFullType, kFirstType, kLastType, kMiddleType )
|
|
* The type is used to group a bunch of records together to represent
|
|
* blocks that are larger than kBlockSize
|
|
* Payload = Byte stream as long as specified by the payload size
|
|
*
|
|
* Recyclable record format:
|
|
*
|
|
* +---------+-----------+-----------+----------------+--- ... ---+
|
|
* |CRC (4B) | Size (2B) | Type (1B) | Log number (4B)| Payload |
|
|
* +---------+-----------+-----------+----------------+--- ... ---+
|
|
*
|
|
* Same as above, with the addition of
|
|
* Log number = 32bit log file number, so that we can distinguish between
|
|
* records written by the most recent log writer vs a previous one.
|
|
*/
|
|
class Writer {
|
|
public:
|
|
// Create a writer that will append data to "*dest".
|
|
// "*dest" must be initially empty.
|
|
// "*dest" must remain live while this Writer is in use.
|
|
explicit Writer(std::unique_ptr<WritableFileWriter>&& dest,
|
|
uint64_t log_number, bool recycle_log_files,
|
|
bool manual_flush = false);
|
|
~Writer();
|
|
|
|
Status AddRecord(const Slice& slice);
|
|
|
|
WritableFileWriter* file() { return dest_.get(); }
|
|
const WritableFileWriter* file() const { return dest_.get(); }
|
|
|
|
uint64_t get_log_number() const { return log_number_; }
|
|
|
|
Status WriteBuffer();
|
|
|
|
Status Close();
|
|
|
|
bool TEST_BufferIsEmpty();
|
|
|
|
private:
|
|
std::unique_ptr<WritableFileWriter> dest_;
|
|
size_t block_offset_; // Current offset in block
|
|
uint64_t log_number_;
|
|
bool recycle_log_files_;
|
|
|
|
// crc32c values for all supported record types. These are
|
|
// pre-computed to reduce the overhead of computing the crc of the
|
|
// record type stored in the header.
|
|
uint32_t type_crc_[kMaxRecordType + 1];
|
|
|
|
Status EmitPhysicalRecord(RecordType type, const char* ptr, size_t length);
|
|
|
|
// If true, it does not flush after each write. Instead it relies on the upper
|
|
// layer to manually does the flush by calling ::WriteBuffer()
|
|
bool manual_flush_;
|
|
|
|
// No copying allowed
|
|
Writer(const Writer&);
|
|
void operator=(const Writer&);
|
|
};
|
|
|
|
} // namespace log
|
|
} // namespace rocksdb
|