d93812c9ae
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
129 lines
5.1 KiB
C++
129 lines
5.1 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.
|
|
//
|
|
// An iterator yields a sequence of key/value pairs from a source.
|
|
// The following class defines the interface. Multiple implementations
|
|
// are provided by this library. In particular, iterators are provided
|
|
// to access the contents of a Table or a DB.
|
|
//
|
|
// Multiple threads can invoke const methods on an Iterator without
|
|
// external synchronization, but if any of the threads may call a
|
|
// non-const method, all threads accessing the same Iterator must use
|
|
// external synchronization.
|
|
|
|
#pragma once
|
|
|
|
#include <string>
|
|
#include "rocksdb/cleanable.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "rocksdb/status.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class Iterator : public Cleanable {
|
|
public:
|
|
Iterator() {}
|
|
// No copying allowed
|
|
Iterator(const Iterator&) = delete;
|
|
void operator=(const Iterator&) = delete;
|
|
|
|
virtual ~Iterator() {}
|
|
|
|
// An iterator is either positioned at a key/value pair, or
|
|
// not valid. This method returns true iff the iterator is valid.
|
|
// Always returns false if !status().ok().
|
|
virtual bool Valid() const = 0;
|
|
|
|
// Position at the first key in the source. The iterator is Valid()
|
|
// after this call iff the source is not empty.
|
|
virtual void SeekToFirst() = 0;
|
|
|
|
// Position at the last key in the source. The iterator is
|
|
// Valid() after this call iff the source is not empty.
|
|
// Currently incompatible with user timestamp.
|
|
virtual void SeekToLast() = 0;
|
|
|
|
// Position at the first key in the source that at or past target.
|
|
// The iterator is Valid() after this call iff the source contains
|
|
// an entry that comes at or past target.
|
|
// All Seek*() methods clear any error status() that the iterator had prior to
|
|
// the call; after the seek, status() indicates only the error (if any) that
|
|
// happened during the seek, not any past errors.
|
|
// Target does not contain timestamp.
|
|
virtual void Seek(const Slice& target) = 0;
|
|
|
|
// Position at the last key in the source that at or before target.
|
|
// The iterator is Valid() after this call iff the source contains
|
|
// an entry that comes at or before target.
|
|
// Currently incompatible with user timestamp.
|
|
virtual void SeekForPrev(const Slice& target) = 0;
|
|
|
|
// Moves to the next entry in the source. After this call, Valid() is
|
|
// true iff the iterator was not positioned at the last entry in the source.
|
|
// REQUIRES: Valid()
|
|
virtual void Next() = 0;
|
|
|
|
// Moves to the previous entry in the source. After this call, Valid() is
|
|
// true iff the iterator was not positioned at the first entry in source.
|
|
// Currently incompatible with user timestamp.
|
|
// REQUIRES: Valid()
|
|
virtual void Prev() = 0;
|
|
|
|
// Return the key for the current entry. The underlying storage for
|
|
// the returned slice is valid only until the next modification of
|
|
// the iterator.
|
|
// REQUIRES: Valid()
|
|
virtual Slice key() const = 0;
|
|
|
|
// Return the value for the current entry. The underlying storage for
|
|
// the returned slice is valid only until the next modification of
|
|
// the iterator.
|
|
// REQUIRES: Valid()
|
|
virtual Slice value() const = 0;
|
|
|
|
// If an error has occurred, return it. Else return an ok status.
|
|
// If non-blocking IO is requested and this operation cannot be
|
|
// satisfied without doing some IO, then this returns Status::Incomplete().
|
|
virtual Status status() const = 0;
|
|
|
|
// If supported, renew the iterator to represent the latest state. The
|
|
// iterator will be invalidated after the call. Not supported if
|
|
// ReadOptions.snapshot is given when creating the iterator.
|
|
virtual Status Refresh() {
|
|
return Status::NotSupported("Refresh() is not supported");
|
|
}
|
|
|
|
// Property "rocksdb.iterator.is-key-pinned":
|
|
// If returning "1", this means that the Slice returned by key() is valid
|
|
// as long as the iterator is not deleted.
|
|
// It is guaranteed to always return "1" if
|
|
// - Iterator created with ReadOptions::pin_data = true
|
|
// - DB tables were created with
|
|
// BlockBasedTableOptions::use_delta_encoding = false.
|
|
// Property "rocksdb.iterator.super-version-number":
|
|
// LSM version used by the iterator. The same format as DB Property
|
|
// kCurrentSuperVersionNumber. See its comment for more information.
|
|
// Property "rocksdb.iterator.internal-key":
|
|
// Get the user-key portion of the internal key at which the iteration
|
|
// stopped.
|
|
virtual Status GetProperty(std::string prop_name, std::string* prop);
|
|
|
|
virtual Slice timestamp() const {
|
|
assert(false);
|
|
return Slice();
|
|
}
|
|
};
|
|
|
|
// Return an empty iterator (yields nothing).
|
|
extern Iterator* NewEmptyIterator();
|
|
|
|
// Return an empty iterator with the specified status.
|
|
extern Iterator* NewErrorIterator(const Status& status);
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|