mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 13:41:46 +00:00
a7b2bedfb0
Introduce new tags for records that have a log_number. This changes the header size from 7 to 11 for these records, making this a backward-incompatible change. If we read a record that belongs to a different log_number (i.e., a previous instantiation of this log file, before it was most recently recycled), we return kOldRecord from ReadPhysicalRecord. ReadRecord will translate this into a kEof or kBadRecord depending on what the WAL recovery mode is. We make several adjustments to the log_test.cc tests to compensate for the fact that the header size varies between the two modes. Signed-off-by: Sage Weil <sage@redhat.com>
104 lines
3.5 KiB
C++
104 lines
3.5 KiB
C++
// Copyright (c) 2013, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under the BSD-style license found in the
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
// of patent rights can be found in the PATENTS file in the same 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;
|
|
|
|
using std::unique_ptr;
|
|
|
|
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 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(unique_ptr<WritableFileWriter>&& dest,
|
|
uint64_t log_number, bool recycle_log_files);
|
|
~Writer();
|
|
|
|
Status AddRecord(const Slice& slice);
|
|
|
|
WritableFileWriter* file() { return dest_.get(); }
|
|
const WritableFileWriter* file() const { return dest_.get(); }
|
|
|
|
private:
|
|
unique_ptr<WritableFileWriter> dest_;
|
|
int 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);
|
|
|
|
// No copying allowed
|
|
Writer(const Writer&);
|
|
void operator=(const Writer&);
|
|
};
|
|
|
|
} // namespace log
|
|
} // namespace rocksdb
|