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
84 lines
2.6 KiB
C++
84 lines
2.6 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 <cstdint>
|
|
#include <memory>
|
|
#include <string>
|
|
|
|
#include "db/blob/blob_log_format.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "rocksdb/statistics.h"
|
|
#include "rocksdb/status.h"
|
|
#include "rocksdb/types.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class WritableFileWriter;
|
|
class SystemClock;
|
|
/**
|
|
* BlobLogWriter is the blob log stream writer. It provides an append-only
|
|
* abstraction for writing blob data.
|
|
*
|
|
*
|
|
* Look at blob_db_format.h to see the details of the record formats.
|
|
*/
|
|
|
|
class BlobLogWriter {
|
|
public:
|
|
// Create a writer that will append data to "*dest".
|
|
// "*dest" must be initially empty.
|
|
// "*dest" must remain live while this BlobLogWriter is in use.
|
|
BlobLogWriter(std::unique_ptr<WritableFileWriter>&& dest, SystemClock* clock,
|
|
Statistics* statistics, uint64_t log_number, bool use_fsync,
|
|
bool do_flush, uint64_t boffset = 0);
|
|
// No copying allowed
|
|
BlobLogWriter(const BlobLogWriter&) = delete;
|
|
BlobLogWriter& operator=(const BlobLogWriter&) = delete;
|
|
|
|
~BlobLogWriter();
|
|
|
|
static void ConstructBlobHeader(std::string* buf, const Slice& key,
|
|
const Slice& val, uint64_t expiration);
|
|
|
|
Status AddRecord(const Slice& key, const Slice& val, uint64_t* key_offset,
|
|
uint64_t* blob_offset);
|
|
|
|
Status AddRecord(const Slice& key, const Slice& val, uint64_t expiration,
|
|
uint64_t* key_offset, uint64_t* blob_offset);
|
|
|
|
Status EmitPhysicalRecord(const std::string& headerbuf, const Slice& key,
|
|
const Slice& val, uint64_t* key_offset,
|
|
uint64_t* blob_offset);
|
|
|
|
Status AppendFooter(BlobLogFooter& footer, std::string* checksum_method,
|
|
std::string* checksum_value);
|
|
|
|
Status WriteHeader(BlobLogHeader& header);
|
|
|
|
WritableFileWriter* file() { return dest_.get(); }
|
|
|
|
const WritableFileWriter* file() const { return dest_.get(); }
|
|
|
|
uint64_t get_log_number() const { return log_number_; }
|
|
|
|
Status Sync();
|
|
|
|
private:
|
|
std::unique_ptr<WritableFileWriter> dest_;
|
|
SystemClock* clock_;
|
|
Statistics* statistics_;
|
|
uint64_t log_number_;
|
|
uint64_t block_offset_; // Current offset in block
|
|
bool use_fsync_;
|
|
bool do_flush_;
|
|
|
|
public:
|
|
enum ElemType { kEtNone, kEtFileHdr, kEtRecord, kEtFileFooter };
|
|
ElemType last_elem_type_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|