3dff28cf9b
Summary: For performance purposes, the lower level routines were changed to use a SystemClock* instead of a std::shared_ptr<SystemClock>. The shared ptr has some performance degradation on certain hardware classes. For most of the system, there is no risk of the pointer being deleted/invalid because the shared_ptr will be stored elsewhere. For example, the ImmutableDBOptions stores the Env which has a std::shared_ptr<SystemClock> in it. The SystemClock* within the ImmutableDBOptions is essentially a "short cut" to gain access to this constant resource. There were a few classes (PeriodicWorkScheduler?) where the "short cut" property did not hold. In those cases, the shared pointer was preserved. Using db_bench readrandom perf_level=3 on my EC2 box, this change performed as well or better than 6.17: 6.17: readrandom : 28.046 micros/op 854902 ops/sec; 61.3 MB/s (355999 of 355999 found) 6.18: readrandom : 32.615 micros/op 735306 ops/sec; 52.7 MB/s (290999 of 290999 found) PR: readrandom : 27.500 micros/op 871909 ops/sec; 62.5 MB/s (367999 of 367999 found) (Note that the times for 6.18 are prior to revert of the SystemClock). Pull Request resolved: https://github.com/facebook/rocksdb/pull/8033 Reviewed By: pdillinger Differential Revision: D27014563 Pulled By: mrambacher fbshipit-source-id: ad0459eba03182e454391b5926bf5cdd45657b67
79 lines
2.2 KiB
C++
79 lines
2.2 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).
|
|
//
|
|
#pragma once
|
|
|
|
#include <memory>
|
|
|
|
#include "db/blob/blob_log_format.h"
|
|
#include "rocksdb/slice.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class RandomAccessFileReader;
|
|
class Env;
|
|
class Statistics;
|
|
class Status;
|
|
class SystemClock;
|
|
|
|
/**
|
|
* BlobLogSequentialReader is a general purpose log stream reader
|
|
* implementation. The actual job of reading from the device is implemented by
|
|
* the RandomAccessFileReader interface.
|
|
*
|
|
* Please see BlobLogWriter for details on the file and record layout.
|
|
*/
|
|
|
|
class BlobLogSequentialReader {
|
|
public:
|
|
enum ReadLevel {
|
|
kReadHeader,
|
|
kReadHeaderKey,
|
|
kReadHeaderKeyBlob,
|
|
};
|
|
|
|
// Create a reader that will return log records from "*file_reader".
|
|
BlobLogSequentialReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
|
|
SystemClock* clock, Statistics* statistics);
|
|
|
|
// No copying allowed
|
|
BlobLogSequentialReader(const BlobLogSequentialReader&) = delete;
|
|
BlobLogSequentialReader& operator=(const BlobLogSequentialReader&) = delete;
|
|
|
|
~BlobLogSequentialReader();
|
|
|
|
Status ReadHeader(BlobLogHeader* header);
|
|
|
|
// Read the next record into *record. Returns true if read
|
|
// successfully, false if we hit end of the input. The contents filled in
|
|
// *record will only be valid until the next mutating operation on this
|
|
// reader.
|
|
// If blob_offset is non-null, return offset of the blob through it.
|
|
Status ReadRecord(BlobLogRecord* record, ReadLevel level = kReadHeader,
|
|
uint64_t* blob_offset = nullptr);
|
|
|
|
Status ReadFooter(BlobLogFooter* footer);
|
|
|
|
void ResetNextByte() { next_byte_ = 0; }
|
|
|
|
uint64_t GetNextByte() const { return next_byte_; }
|
|
|
|
private:
|
|
Status ReadSlice(uint64_t size, Slice* slice, char* buf);
|
|
|
|
const std::unique_ptr<RandomAccessFileReader> file_;
|
|
SystemClock* clock_;
|
|
|
|
Statistics* statistics_;
|
|
|
|
Slice buffer_;
|
|
char header_buf_[BlobLogRecord::kHeaderSize];
|
|
|
|
// which byte to read next
|
|
uint64_t next_byte_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|