rocksdb/table/internal_iterator.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

184 lines
6.7 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 <string>
#include "db/dbformat.h"
#include "rocksdb/comparator.h"
#include "rocksdb/iterator.h"
#include "rocksdb/status.h"
#include "table/format.h"
namespace ROCKSDB_NAMESPACE {
class PinnedIteratorsManager;
struct IterateResult {
Slice key;
bool may_be_out_of_upper_bound;
};
template <class TValue>
class InternalIteratorBase : public Cleanable {
public:
InternalIteratorBase() {}
// No copying allowed
InternalIteratorBase(const InternalIteratorBase&) = delete;
InternalIteratorBase& operator=(const InternalIteratorBase&) = delete;
virtual ~InternalIteratorBase() {}
// 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.
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' contains user timestamp if timestamp is enabled.
virtual void Seek(const Slice& target) = 0;
// Position at the first 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.
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 next entry in the source, and return result. Iterator
// implementation should override this method to help methods inline better,
// or when MayBeOutOfUpperBound() is non-trivial.
// REQUIRES: Valid()
virtual bool NextAndGetResult(IterateResult* result) {
Next();
bool is_valid = Valid();
if (is_valid) {
result->key = key();
// Default may_be_out_of_upper_bound to true to avoid unnecessary virtual
// call. If an implementation has non-trivial MayBeOutOfUpperBound(),
// it should also override NextAndGetResult().
result->may_be_out_of_upper_bound = true;
assert(MayBeOutOfUpperBound());
}
return is_valid;
}
// 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.
// 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 user key for the current entry.
// REQUIRES: Valid()
virtual Slice user_key() const { return ExtractUserKey(key()); }
// 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 TValue 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;
// True if the iterator is invalidated because it reached a key that is above
// the iterator upper bound. Used by LevelIterator to decide whether it should
// stop or move on to the next file.
// Important: if iterator reached the end of the file without encountering any
// keys above the upper bound, IsOutOfBound() must return false.
virtual bool IsOutOfBound() { return false; }
// Keys return from this iterator can be smaller than iterate_lower_bound.
virtual bool MayBeOutOfLowerBound() { return true; }
// Keys return from this iterator can be larger or equal to
// iterate_upper_bound.
virtual bool MayBeOutOfUpperBound() { return true; }
// Pass the PinnedIteratorsManager to the Iterator, most Iterators don't
// communicate with PinnedIteratorsManager so default implementation is no-op
// but for Iterators that need to communicate with PinnedIteratorsManager
// they will implement this function and use the passed pointer to communicate
// with PinnedIteratorsManager.
virtual void SetPinnedItersMgr(PinnedIteratorsManager* /*pinned_iters_mgr*/) {
}
// If true, this means that the Slice returned by key() is valid as long as
// PinnedIteratorsManager::ReleasePinnedData is not called and the
// Iterator is not deleted.
//
// IsKeyPinned() is guaranteed to always return true if
// - Iterator is created with ReadOptions::pin_data = true
// - DB tables were created with BlockBasedTableOptions::use_delta_encoding
// set to false.
virtual bool IsKeyPinned() const { return false; }
// If true, this means that the Slice returned by value() is valid as long as
// PinnedIteratorsManager::ReleasePinnedData is not called and the
// Iterator is not deleted.
virtual bool IsValuePinned() const { return false; }
virtual Status GetProperty(std::string /*prop_name*/, std::string* /*prop*/) {
return Status::NotSupported("");
}
protected:
void SeekForPrevImpl(const Slice& target, const Comparator* cmp) {
Seek(target);
if (!Valid()) {
SeekToLast();
}
while (Valid() && cmp->Compare(target, key()) < 0) {
Prev();
}
}
bool is_mutable_;
};
using InternalIterator = InternalIteratorBase<Slice>;
// Return an empty iterator (yields nothing).
template <class TValue = Slice>
extern InternalIteratorBase<TValue>* NewEmptyInternalIterator();
// Return an empty iterator with the specified status.
template <class TValue = Slice>
extern InternalIteratorBase<TValue>* NewErrorInternalIterator(
const Status& status);
// Return an empty iterator with the specified status, allocated arena.
template <class TValue = Slice>
extern InternalIteratorBase<TValue>* NewErrorInternalIterator(
const Status& status, Arena* arena);
} // namespace ROCKSDB_NAMESPACE