ae152ee666
Summary:
In previous https://github.com/facebook/rocksdb/issues/5079, we added user-specified timestamp to `DB::Get()` and `DB::Put()`. Limitation is that these two functions may cause extra memory allocation and key copy. The reason is that `WriteBatch` does not allocate extra memory for timestamps because it is not aware of timestamp size, and we did not provide an API to assign/update timestamp of each key within a `WriteBatch`.
We address these issues in this PR by doing the following.
1. Add a `timestamp_size_` to `WriteBatch` so that `WriteBatch` can take timestamps into account when calling `WriteBatch::Put`, `WriteBatch::Delete`, etc.
2. Add APIs `WriteBatch::AssignTimestamp` and `WriteBatch::AssignTimestamps` so that application can assign/update timestamps for each key in a `WriteBatch`.
3. Avoid key copy in `GetImpl` by adding new constructor to `LookupKey`.
Test plan (on devserver):
```
$make clean && COMPILE_WITH_ASAN=1 make -j32 all
$./db_basic_test --gtest_filter=Timestamp/DBBasicTestWithTimestampWithParam.PutAndGet/*
$make check
```
If the API extension looks good, I will add more unit tests.
Some simple benchmark using db_bench.
```
$rm -rf /dev/shm/dbbench/* && TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=fillseq,readrandom -num=1000000
$rm -rf /dev/shm/dbbench/* && TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=fillrandom -num=1000000 -disable_wal=true
```
Master is at a78503bd6c.
```
| | readrandom | fillrandom |
| master | 15.53 MB/s | 25.97 MB/s |
| PR5502 | 16.70 MB/s | 25.80 MB/s |
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5502
Differential Revision: D16340894
Pulled By: riversand963
fbshipit-source-id: 51132cf792be07d1efc3ac33f5768c4ee2608bb8
67 lines
2.0 KiB
C++
67 lines
2.0 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 <string>
|
|
#include <utility>
|
|
#include "rocksdb/db.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "rocksdb/types.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
// A helper class useful for DBImpl::Get()
|
|
class LookupKey {
|
|
public:
|
|
// Initialize *this for looking up user_key at a snapshot with
|
|
// the specified sequence number.
|
|
LookupKey(const Slice& _user_key, SequenceNumber sequence,
|
|
const Slice* ts = nullptr);
|
|
|
|
~LookupKey();
|
|
|
|
// Return a key suitable for lookup in a MemTable.
|
|
Slice memtable_key() const {
|
|
return Slice(start_, static_cast<size_t>(end_ - start_));
|
|
}
|
|
|
|
// Return an internal key (suitable for passing to an internal iterator)
|
|
Slice internal_key() const {
|
|
return Slice(kstart_, static_cast<size_t>(end_ - kstart_));
|
|
}
|
|
|
|
// Return the user key
|
|
Slice user_key() const {
|
|
return Slice(kstart_, static_cast<size_t>(end_ - kstart_ - 8));
|
|
}
|
|
|
|
private:
|
|
// We construct a char array of the form:
|
|
// klength varint32 <-- start_
|
|
// userkey char[klength] <-- kstart_
|
|
// tag uint64
|
|
// <-- end_
|
|
// The array is a suitable MemTable key.
|
|
// The suffix starting with "userkey" can be used as an InternalKey.
|
|
const char* start_;
|
|
const char* kstart_;
|
|
const char* end_;
|
|
char space_[200]; // Avoid allocation for short keys
|
|
|
|
// No copying allowed
|
|
LookupKey(const LookupKey&);
|
|
void operator=(const LookupKey&);
|
|
};
|
|
|
|
inline LookupKey::~LookupKey() {
|
|
if (start_ != space_) delete[] start_;
|
|
}
|
|
|
|
} // namespace rocksdb
|