rocksdb/db/arena_wrapped_db_iter.h
Yanqin Jin d93812c9ae Iterator with timestamp (#6255)
Summary:
Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests.

Create an iterator with timestamp.
```
...
read_opts.timestamp = &ts;
auto* iter = db->NewIterator(read_opts);
// target is key without timestamp.
for (iter->Seek(target); iter->Valid(); iter->Next()) {}
for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {}
delete iter;
read_opts.timestamp = &ts1;
// lower_bound and upper_bound are without timestamp.
read_opts.iterate_lower_bound = &lower_bound;
read_opts.iterate_upper_bound = &upper_bound;
auto* iter1 = db->NewIterator(read_opts);
// Do Seek or SeekToFirst()
delete iter1;
```

Test plan (dev server)
```
$make check
```

Simple benchmarking (dev server)
1. The overhead introduced by this PR even when timestamp is disabled.
key size: 16 bytes
value size: 100 bytes
Entries: 1000000
Data reside in main memory, and try to stress iterator.
Repeated three times on master and this PR.
- Seek without next
```
./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3
```
master: 159047.0 ops/sec
this PR: 158922.3 ops/sec (2% drop in throughput)
- Seek and next 10 times
```
./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10
```
master: 109539.3 ops/sec
this PR: 107519.7 ops/sec (2% drop in throughput)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255

Differential Revision: D19438227

Pulled By: riversand963

fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-06 16:24:27 -08:00

116 lines
4.4 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 <string>
#include "db/db_impl/db_impl.h"
#include "db/db_iter.h"
#include "db/dbformat.h"
#include "db/range_del_aggregator.h"
#include "memory/arena.h"
#include "options/cf_options.h"
#include "rocksdb/db.h"
#include "rocksdb/iterator.h"
#include "util/autovector.h"
namespace ROCKSDB_NAMESPACE {
class Arena;
// A wrapper iterator which wraps DB Iterator and the arena, with which the DB
// iterator is supposed to be allocated. This class is used as an entry point of
// a iterator hierarchy whose memory can be allocated inline. In that way,
// accessing the iterator tree can be more cache friendly. It is also faster
// to allocate.
// When using the class's Iterator interface, the behavior is exactly
// the same as the inner DBIter.
class ArenaWrappedDBIter : public Iterator {
public:
virtual ~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
// Get the arena to be used to allocate memory for DBIter to be wrapped,
// as well as child iterators in it.
virtual Arena* GetArena() { return &arena_; }
virtual ReadRangeDelAggregator* GetRangeDelAggregator() {
return db_iter_->GetRangeDelAggregator();
}
// Set the internal iterator wrapped inside the DB Iterator. Usually it is
// a merging iterator.
virtual void SetIterUnderDBIter(InternalIterator* iter) {
db_iter_->SetIter(iter);
}
bool Valid() const override { return db_iter_->Valid(); }
void SeekToFirst() override { db_iter_->SeekToFirst(); }
void SeekToLast() override { db_iter_->SeekToLast(); }
// 'target' does not contain timestamp, even if user timestamp feature is
// enabled.
void Seek(const Slice& target) override { db_iter_->Seek(target); }
void SeekForPrev(const Slice& target) override {
db_iter_->SeekForPrev(target);
}
void Next() override { db_iter_->Next(); }
void Prev() override { db_iter_->Prev(); }
Slice key() const override { return db_iter_->key(); }
Slice value() const override { return db_iter_->value(); }
Status status() const override { return db_iter_->status(); }
Slice timestamp() const override { return db_iter_->timestamp(); }
bool IsBlob() const { return db_iter_->IsBlob(); }
Status GetProperty(std::string prop_name, std::string* prop) override;
Status Refresh() override;
void Init(Env* env, const ReadOptions& read_options,
const ImmutableCFOptions& cf_options,
const MutableCFOptions& mutable_cf_options,
const SequenceNumber& sequence,
uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
bool allow_blob, bool allow_refresh);
// Store some parameters so we can refresh the iterator at a later point
// with these same params
void StoreRefreshInfo(const ReadOptions& read_options, DBImpl* db_impl,
ColumnFamilyData* cfd, ReadCallback* read_callback,
bool allow_blob) {
read_options_ = read_options;
db_impl_ = db_impl;
cfd_ = cfd;
read_callback_ = read_callback;
allow_blob_ = allow_blob;
}
private:
DBIter* db_iter_;
Arena arena_;
uint64_t sv_number_;
ColumnFamilyData* cfd_ = nullptr;
DBImpl* db_impl_ = nullptr;
ReadOptions read_options_;
ReadCallback* read_callback_;
bool allow_blob_ = false;
bool allow_refresh_ = true;
};
// Generate the arena wrapped iterator class.
// `db_impl` and `cfd` are used for reneweal. If left null, renewal will not
// be supported.
extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
Env* env, const ReadOptions& read_options,
const ImmutableCFOptions& cf_options,
const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
ReadCallback* read_callback, DBImpl* db_impl = nullptr,
ColumnFamilyData* cfd = nullptr, bool allow_blob = false,
bool allow_refresh = true);
} // namespace ROCKSDB_NAMESPACE