rocksdb/db/forward_iterator.h
Tomislav Novak 187b29938c ForwardIterator: update prev_key_ only if prefix hasn't changed
Summary:
Since ForwardIterator is on a level below DBIter, the latter may call Next() on
it (e.g. in order to skip deletion markers). Since this also updates
`prev_key_`, it may prevent the Seek() optimization.

For example, assume that there's only one SST file and it contains the following
entries: 0101, 0201 (`ValueType::kTypeDeletion`, i.e. a tombstone record), 0201
(`kTypeValue`), 0202. Memtable is empty. `Seek(0102)` will result in `prev_key_`
being set to `0201` instead of `0102`, since `DBIter::Seek()` will call
`ForwardIterator::Next()` to skip record 0201. Therefore, when `Seek(0102)` is
called again, `NeedToSeekImmutable()` will return true.

This fix relies on `prefix_extractor_` to detect prefix changes. `prev_key_` is
only set to `current_->key()` as long as they have the same prefix.

I also made a small change to `NeedToSeekImmutable()` so it no longer returns
true when the db is empty (i.e. there's nothing but a memtable).

Test Plan:
   $ TEST_TMPDIR=/dev/shm/rocksdbtest ROCKSDB_TESTS=TailingIterator ./db_test

Reviewers: sdong, igor, ljin

Reviewed By: ljin

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23823
2014-10-01 17:10:48 -07:00

110 lines
3 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.
#pragma once
#ifndef ROCKSDB_LITE
#include <string>
#include <vector>
#include <queue>
#include "rocksdb/db.h"
#include "rocksdb/iterator.h"
#include "rocksdb/options.h"
#include "db/dbformat.h"
#include "util/arena.h"
namespace rocksdb {
class DBImpl;
class Env;
struct SuperVersion;
class ColumnFamilyData;
class LevelIterator;
struct FileMetaData;
class MinIterComparator {
public:
explicit MinIterComparator(const Comparator* comparator) :
comparator_(comparator) {}
bool operator()(Iterator* a, Iterator* b) {
return comparator_->Compare(a->key(), b->key()) > 0;
}
private:
const Comparator* comparator_;
};
typedef std::priority_queue<Iterator*,
std::vector<Iterator*>,
MinIterComparator> MinIterHeap;
/**
* ForwardIterator is a special type of iterator that only supports Seek()
* and Next(). It is expected to perform better than TailingIterator by
* removing the encapsulation and making all information accessible within
* the iterator. At the current implementation, snapshot is taken at the
* time Seek() is called. The Next() followed do not see new values after.
*/
class ForwardIterator : public Iterator {
public:
ForwardIterator(DBImpl* db, const ReadOptions& read_options,
ColumnFamilyData* cfd);
virtual ~ForwardIterator();
void SeekToLast() override {
status_ = Status::NotSupported("ForwardIterator::SeekToLast()");
valid_ = false;
}
void Prev() {
status_ = Status::NotSupported("ForwardIterator::Prev");
valid_ = false;
}
virtual bool Valid() const override;
void SeekToFirst() override;
virtual void Seek(const Slice& target) override;
virtual void Next() override;
virtual Slice key() const override;
virtual Slice value() const override;
virtual Status status() const override;
private:
void Cleanup();
void RebuildIterators();
void ResetIncompleteIterators();
void SeekInternal(const Slice& internal_key, bool seek_to_first);
void UpdateCurrent();
bool NeedToSeekImmutable(const Slice& internal_key);
uint32_t FindFileInRange(
const std::vector<FileMetaData*>& files, const Slice& internal_key,
uint32_t left, uint32_t right);
DBImpl* const db_;
const ReadOptions read_options_;
ColumnFamilyData* const cfd_;
const SliceTransform* const prefix_extractor_;
const Comparator* user_comparator_;
MinIterHeap immutable_min_heap_;
SuperVersion* sv_;
Iterator* mutable_iter_;
std::vector<Iterator*> imm_iters_;
std::vector<Iterator*> l0_iters_;
std::vector<LevelIterator*> level_iters_;
Iterator* current_;
// internal iterator status
Status status_;
bool valid_;
IterKey prev_key_;
bool is_prev_set_;
bool is_prev_inclusive_;
Arena arena_;
};
} // namespace rocksdb
#endif // ROCKSDB_LITE