rocksdb/db/write_batch.cc
Haobo Xu 05e8854085 [Rocksdb] Support Merge operation in rocksdb
Summary:
This diff introduces a new Merge operation into rocksdb.
The purpose of this review is mostly getting feedback from the team (everyone please) on the design.

Please focus on the four files under include/leveldb/, as they spell the client visible interface change.
include/leveldb/db.h
include/leveldb/merge_operator.h
include/leveldb/options.h
include/leveldb/write_batch.h

Please go over local/my_test.cc carefully, as it is a concerete use case.

Please also review the impelmentation files to see if the straw man implementation makes sense.

Note that, the diff does pass all make check and truly supports forward iterator over db and a version
of Get that's based on iterator.

Future work:
- Integration with compaction
- A raw Get implementation

I am working on a wiki that explains the design and implementation choices, but coding comes
just naturally and I think it might be a good idea to share the code earlier. The code is
heavily commented.

Test Plan: run all local tests

Reviewers: dhruba, heyongqiang

Reviewed By: dhruba

CC: leveldb, zshao, sheki, emayanke, MarkCallaghan

Differential Revision: https://reviews.facebook.net/D9651
2013-05-03 16:59:02 -07:00

174 lines
4.8 KiB
C++

// 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.
//
// WriteBatch::rep_ :=
// sequence: fixed64
// count: fixed32
// data: record[count]
// record :=
// kTypeValue varstring varstring
// kTypeMerge varstring varstring
// kTypeDeletion varstring
// varstring :=
// len: varint32
// data: uint8[len]
#include "leveldb/write_batch.h"
#include "leveldb/db.h"
#include "db/dbformat.h"
#include "db/memtable.h"
#include "db/write_batch_internal.h"
#include "util/coding.h"
#include <stdexcept>
namespace leveldb {
// WriteBatch header has an 8-byte sequence number followed by a 4-byte count.
static const size_t kHeader = 12;
WriteBatch::WriteBatch() {
Clear();
}
WriteBatch::~WriteBatch() { }
WriteBatch::Handler::~Handler() { }
void WriteBatch::Handler::Merge(const Slice& key, const Slice& value) {
throw std::runtime_error("Handler::Merge not implemented!");
}
void WriteBatch::Clear() {
rep_.clear();
rep_.resize(kHeader);
}
Status WriteBatch::Iterate(Handler* handler) const {
Slice input(rep_);
if (input.size() < kHeader) {
return Status::Corruption("malformed WriteBatch (too small)");
}
input.remove_prefix(kHeader);
Slice key, value;
int found = 0;
while (!input.empty()) {
found++;
char tag = input[0];
input.remove_prefix(1);
switch (tag) {
case kTypeValue:
if (GetLengthPrefixedSlice(&input, &key) &&
GetLengthPrefixedSlice(&input, &value)) {
handler->Put(key, value);
} else {
return Status::Corruption("bad WriteBatch Put");
}
break;
case kTypeDeletion:
if (GetLengthPrefixedSlice(&input, &key)) {
handler->Delete(key);
} else {
return Status::Corruption("bad WriteBatch Delete");
}
break;
case kTypeMerge:
if (GetLengthPrefixedSlice(&input, &key) &&
GetLengthPrefixedSlice(&input, &value)) {
handler->Merge(key, value);
} else {
return Status::Corruption("bad WriteBatch Merge");
}
break;
default:
return Status::Corruption("unknown WriteBatch tag");
}
}
if (found != WriteBatchInternal::Count(this)) {
return Status::Corruption("WriteBatch has wrong count");
} else {
return Status::OK();
}
}
int WriteBatchInternal::Count(const WriteBatch* b) {
return DecodeFixed32(b->rep_.data() + 8);
}
void WriteBatchInternal::SetCount(WriteBatch* b, int n) {
EncodeFixed32(&b->rep_[8], n);
}
SequenceNumber WriteBatchInternal::Sequence(const WriteBatch* b) {
return SequenceNumber(DecodeFixed64(b->rep_.data()));
}
void WriteBatchInternal::SetSequence(WriteBatch* b, SequenceNumber seq) {
EncodeFixed64(&b->rep_[0], seq);
}
void WriteBatch::Put(const Slice& key, const Slice& value) {
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
rep_.push_back(static_cast<char>(kTypeValue));
PutLengthPrefixedSlice(&rep_, key);
PutLengthPrefixedSlice(&rep_, value);
}
void WriteBatch::Delete(const Slice& key) {
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
rep_.push_back(static_cast<char>(kTypeDeletion));
PutLengthPrefixedSlice(&rep_, key);
}
void WriteBatch::Merge(const Slice& key, const Slice& value) {
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
rep_.push_back(static_cast<char>(kTypeMerge));
PutLengthPrefixedSlice(&rep_, key);
PutLengthPrefixedSlice(&rep_, value);
}
namespace {
class MemTableInserter : public WriteBatch::Handler {
public:
SequenceNumber sequence_;
MemTable* mem_;
virtual void Put(const Slice& key, const Slice& value) {
mem_->Add(sequence_, kTypeValue, key, value);
sequence_++;
}
virtual void Merge(const Slice& key, const Slice& value) {
mem_->Add(sequence_, kTypeMerge, key, value);
sequence_++;
}
virtual void Delete(const Slice& key) {
mem_->Add(sequence_, kTypeDeletion, key, Slice());
sequence_++;
}
};
} // namespace
Status WriteBatchInternal::InsertInto(const WriteBatch* b,
MemTable* memtable) {
MemTableInserter inserter;
inserter.sequence_ = WriteBatchInternal::Sequence(b);
inserter.mem_ = memtable;
return b->Iterate(&inserter);
}
void WriteBatchInternal::SetContents(WriteBatch* b, const Slice& contents) {
assert(contents.size() >= kHeader);
b->rep_.assign(contents.data(), contents.size());
}
void WriteBatchInternal::Append(WriteBatch* dst, const WriteBatch* src) {
SetCount(dst, Count(dst) + Count(src));
assert(src->rep_.size() >= kHeader);
dst->rep_.append(src->rep_.data() + kHeader, src->rep_.size() - kHeader);
}
} // namespace leveldb