2013-10-16 23:59:46 +02:00
|
|
|
// 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.
|
|
|
|
//
|
2011-03-18 23:37:00 +01:00
|
|
|
// 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 :=
|
2013-03-21 23:59:47 +01:00
|
|
|
// kTypeValue varstring varstring
|
|
|
|
// kTypeMerge varstring varstring
|
2011-03-18 23:37:00 +01:00
|
|
|
// kTypeDeletion varstring
|
2014-01-07 23:41:42 +01:00
|
|
|
// kTypeColumnFamilyValue varint32 varstring varstring
|
|
|
|
// kTypeColumnFamilyMerge varint32 varstring varstring
|
|
|
|
// kTypeColumnFamilyDeletion varint32 varstring varstring
|
2011-03-18 23:37:00 +01:00
|
|
|
// varstring :=
|
|
|
|
// len: varint32
|
|
|
|
// data: uint8[len]
|
|
|
|
|
2013-08-23 17:38:13 +02:00
|
|
|
#include "rocksdb/write_batch.h"
|
|
|
|
#include "rocksdb/options.h"
|
2014-01-11 02:33:56 +01:00
|
|
|
#include "rocksdb/merge_operator.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
#include "db/dbformat.h"
|
2013-07-13 01:56:52 +02:00
|
|
|
#include "db/db_impl.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
#include "db/memtable.h"
|
2013-07-26 21:57:01 +02:00
|
|
|
#include "db/snapshot.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
#include "db/write_batch_internal.h"
|
|
|
|
#include "util/coding.h"
|
2014-01-17 21:46:06 +01:00
|
|
|
#include "util/statistics.h"
|
2013-03-21 23:59:47 +01:00
|
|
|
#include <stdexcept>
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2013-10-04 06:49:15 +02:00
|
|
|
namespace rocksdb {
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2012-03-09 01:23:21 +01:00
|
|
|
// WriteBatch header has an 8-byte sequence number followed by a 4-byte count.
|
|
|
|
static const size_t kHeader = 12;
|
|
|
|
|
2014-01-14 19:42:36 +01:00
|
|
|
WriteBatch::WriteBatch(size_t reserved_bytes) {
|
|
|
|
rep_.reserve((reserved_bytes > kHeader) ? reserved_bytes : kHeader);
|
2011-03-18 23:37:00 +01:00
|
|
|
Clear();
|
|
|
|
}
|
|
|
|
|
|
|
|
WriteBatch::~WriteBatch() { }
|
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
WriteBatch::Handler::~Handler() { }
|
|
|
|
|
[RocksDB] [Column Family] Interface proposal
Summary:
<This diff is for Column Family branch>
Sharing some of the work I've done so far. This diff compiles and passes the tests.
The biggest change is in options.h - I broke down Options into two parts - DBOptions and ColumnFamilyOptions. DBOptions is DB-specific (env, create_if_missing, block_cache, etc.) and ColumnFamilyOptions is column family-specific (all compaction options, compresion options, etc.). Note that this does not break backwards compatibility at all.
Further, I created DBWithColumnFamily which inherits DB interface and adds new functions with column family support. Clients can transparently switch to DBWithColumnFamily and it will not break their backwards compatibility.
There are few methods worth checking out: ListColumnFamilies(), MultiNewIterator(), MultiGet() and GetSnapshot(). [GetSnapshot() returns the snapshot across all column families for now - I think that's what we agreed on]
Finally, I made small changes to WriteBatch so we are able to atomically insert data across column families.
Please provide feedback.
Test Plan: make check works, the code is backward compatible
Reviewers: dhruba, haobo, sdong, kailiu, emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14445
2013-12-03 20:14:09 +01:00
|
|
|
void WriteBatch::Handler::Put(const Slice& key, const Slice& value) {
|
|
|
|
// you need to either implement Put or PutCF
|
|
|
|
throw std::runtime_error("Handler::Put not implemented!");
|
|
|
|
}
|
|
|
|
|
2013-03-21 23:59:47 +01:00
|
|
|
void WriteBatch::Handler::Merge(const Slice& key, const Slice& value) {
|
|
|
|
throw std::runtime_error("Handler::Merge not implemented!");
|
|
|
|
}
|
|
|
|
|
[RocksDB] [Column Family] Interface proposal
Summary:
<This diff is for Column Family branch>
Sharing some of the work I've done so far. This diff compiles and passes the tests.
The biggest change is in options.h - I broke down Options into two parts - DBOptions and ColumnFamilyOptions. DBOptions is DB-specific (env, create_if_missing, block_cache, etc.) and ColumnFamilyOptions is column family-specific (all compaction options, compresion options, etc.). Note that this does not break backwards compatibility at all.
Further, I created DBWithColumnFamily which inherits DB interface and adds new functions with column family support. Clients can transparently switch to DBWithColumnFamily and it will not break their backwards compatibility.
There are few methods worth checking out: ListColumnFamilies(), MultiNewIterator(), MultiGet() and GetSnapshot(). [GetSnapshot() returns the snapshot across all column families for now - I think that's what we agreed on]
Finally, I made small changes to WriteBatch so we are able to atomically insert data across column families.
Please provide feedback.
Test Plan: make check works, the code is backward compatible
Reviewers: dhruba, haobo, sdong, kailiu, emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14445
2013-12-03 20:14:09 +01:00
|
|
|
void WriteBatch::Handler::Delete(const Slice& key) {
|
|
|
|
// you need to either implement Delete or DeleteCF
|
|
|
|
throw std::runtime_error("Handler::Delete not implemented!");
|
|
|
|
}
|
|
|
|
|
2013-08-15 01:32:46 +02:00
|
|
|
void WriteBatch::Handler::LogData(const Slice& blob) {
|
|
|
|
// If the user has not specified something to do with blobs, then we ignore
|
|
|
|
// them.
|
|
|
|
}
|
|
|
|
|
2013-08-22 03:27:48 +02:00
|
|
|
bool WriteBatch::Handler::Continue() {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
void WriteBatch::Clear() {
|
|
|
|
rep_.clear();
|
2012-03-09 01:23:21 +01:00
|
|
|
rep_.resize(kHeader);
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
|
2013-06-26 19:50:58 +02:00
|
|
|
int WriteBatch::Count() const {
|
|
|
|
return WriteBatchInternal::Count(this);
|
|
|
|
}
|
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
Status WriteBatch::Iterate(Handler* handler) const {
|
|
|
|
Slice input(rep_);
|
2012-03-09 01:23:21 +01:00
|
|
|
if (input.size() < kHeader) {
|
2011-05-21 04:17:43 +02:00
|
|
|
return Status::Corruption("malformed WriteBatch (too small)");
|
|
|
|
}
|
|
|
|
|
2012-03-09 01:23:21 +01:00
|
|
|
input.remove_prefix(kHeader);
|
2013-08-15 01:32:46 +02:00
|
|
|
Slice key, value, blob;
|
2011-05-21 04:17:43 +02:00
|
|
|
int found = 0;
|
2013-08-22 03:27:48 +02:00
|
|
|
while (!input.empty() && handler->Continue()) {
|
2011-05-21 04:17:43 +02:00
|
|
|
char tag = input[0];
|
|
|
|
input.remove_prefix(1);
|
2014-01-07 23:41:42 +01:00
|
|
|
uint32_t column_family = 0; // default
|
2011-05-21 04:17:43 +02:00
|
|
|
switch (tag) {
|
2014-01-07 23:41:42 +01:00
|
|
|
case kTypeColumnFamilyValue:
|
|
|
|
if (!GetVarint32(&input, &column_family)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Put");
|
|
|
|
}
|
|
|
|
// intentional fallthrough
|
2011-05-21 04:17:43 +02:00
|
|
|
case kTypeValue:
|
|
|
|
if (GetLengthPrefixedSlice(&input, &key) &&
|
|
|
|
GetLengthPrefixedSlice(&input, &value)) {
|
2014-01-07 23:41:42 +01:00
|
|
|
handler->PutCF(column_family, key, value);
|
2013-08-15 01:32:46 +02:00
|
|
|
found++;
|
2011-05-21 04:17:43 +02:00
|
|
|
} else {
|
|
|
|
return Status::Corruption("bad WriteBatch Put");
|
|
|
|
}
|
|
|
|
break;
|
2014-01-07 23:41:42 +01:00
|
|
|
case kTypeColumnFamilyDeletion:
|
|
|
|
if (!GetVarint32(&input, &column_family)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Delete");
|
|
|
|
}
|
|
|
|
// intentional fallthrough
|
2011-05-21 04:17:43 +02:00
|
|
|
case kTypeDeletion:
|
|
|
|
if (GetLengthPrefixedSlice(&input, &key)) {
|
2014-01-07 23:41:42 +01:00
|
|
|
handler->DeleteCF(column_family, key);
|
2013-08-15 01:32:46 +02:00
|
|
|
found++;
|
2011-05-21 04:17:43 +02:00
|
|
|
} else {
|
|
|
|
return Status::Corruption("bad WriteBatch Delete");
|
|
|
|
}
|
|
|
|
break;
|
2014-01-07 23:41:42 +01:00
|
|
|
case kTypeColumnFamilyMerge:
|
|
|
|
if (!GetVarint32(&input, &column_family)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Merge");
|
|
|
|
}
|
|
|
|
// intentional fallthrough
|
2013-03-21 23:59:47 +01:00
|
|
|
case kTypeMerge:
|
|
|
|
if (GetLengthPrefixedSlice(&input, &key) &&
|
|
|
|
GetLengthPrefixedSlice(&input, &value)) {
|
2014-01-07 23:41:42 +01:00
|
|
|
handler->MergeCF(column_family, key, value);
|
2013-08-15 01:32:46 +02:00
|
|
|
found++;
|
2013-03-21 23:59:47 +01:00
|
|
|
} else {
|
|
|
|
return Status::Corruption("bad WriteBatch Merge");
|
|
|
|
}
|
|
|
|
break;
|
2013-08-15 01:32:46 +02:00
|
|
|
case kTypeLogData:
|
|
|
|
if (GetLengthPrefixedSlice(&input, &blob)) {
|
|
|
|
handler->LogData(blob);
|
|
|
|
} else {
|
|
|
|
return Status::Corruption("bad WriteBatch Blob");
|
|
|
|
}
|
|
|
|
break;
|
2011-05-21 04:17:43 +02:00
|
|
|
default:
|
|
|
|
return Status::Corruption("unknown WriteBatch tag");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (found != WriteBatchInternal::Count(this)) {
|
|
|
|
return Status::Corruption("WriteBatch has wrong count");
|
|
|
|
} else {
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2014-01-07 23:41:42 +01:00
|
|
|
void WriteBatch::Put(uint32_t column_family_id, const Slice& key,
|
[RocksDB] [Column Family] Interface proposal
Summary:
<This diff is for Column Family branch>
Sharing some of the work I've done so far. This diff compiles and passes the tests.
The biggest change is in options.h - I broke down Options into two parts - DBOptions and ColumnFamilyOptions. DBOptions is DB-specific (env, create_if_missing, block_cache, etc.) and ColumnFamilyOptions is column family-specific (all compaction options, compresion options, etc.). Note that this does not break backwards compatibility at all.
Further, I created DBWithColumnFamily which inherits DB interface and adds new functions with column family support. Clients can transparently switch to DBWithColumnFamily and it will not break their backwards compatibility.
There are few methods worth checking out: ListColumnFamilies(), MultiNewIterator(), MultiGet() and GetSnapshot(). [GetSnapshot() returns the snapshot across all column families for now - I think that's what we agreed on]
Finally, I made small changes to WriteBatch so we are able to atomically insert data across column families.
Please provide feedback.
Test Plan: make check works, the code is backward compatible
Reviewers: dhruba, haobo, sdong, kailiu, emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14445
2013-12-03 20:14:09 +01:00
|
|
|
const Slice& value) {
|
2011-03-18 23:37:00 +01:00
|
|
|
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
|
|
|
// save some data on disk by not writing default column family
|
|
|
|
rep_.push_back(static_cast<char>(kTypeValue));
|
|
|
|
} else {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeColumnFamilyValue));
|
|
|
|
PutVarint32(&rep_, column_family_id);
|
|
|
|
}
|
2011-03-18 23:37:00 +01:00
|
|
|
PutLengthPrefixedSlice(&rep_, key);
|
|
|
|
PutLengthPrefixedSlice(&rep_, value);
|
|
|
|
}
|
|
|
|
|
2014-01-07 23:41:42 +01:00
|
|
|
void WriteBatch::Put(uint32_t column_family_id, const SliceParts& key,
|
|
|
|
const SliceParts& value) {
|
2013-11-07 21:37:58 +01:00
|
|
|
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeValue));
|
|
|
|
} else {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeColumnFamilyValue));
|
|
|
|
PutVarint32(&rep_, column_family_id);
|
|
|
|
}
|
2013-11-07 21:37:58 +01:00
|
|
|
PutLengthPrefixedSliceParts(&rep_, key);
|
|
|
|
PutLengthPrefixedSliceParts(&rep_, value);
|
|
|
|
}
|
|
|
|
|
2014-01-07 23:41:42 +01:00
|
|
|
void WriteBatch::Delete(uint32_t column_family_id, const Slice& key) {
|
2011-03-18 23:37:00 +01:00
|
|
|
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeDeletion));
|
|
|
|
} else {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeColumnFamilyDeletion));
|
|
|
|
PutVarint32(&rep_, column_family_id);
|
|
|
|
}
|
2011-03-18 23:37:00 +01:00
|
|
|
PutLengthPrefixedSlice(&rep_, key);
|
|
|
|
}
|
|
|
|
|
2014-01-07 23:41:42 +01:00
|
|
|
void WriteBatch::Merge(uint32_t column_family_id, const Slice& key,
|
|
|
|
const Slice& value) {
|
2013-03-21 23:59:47 +01:00
|
|
|
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeMerge));
|
|
|
|
} else {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeColumnFamilyMerge));
|
|
|
|
PutVarint32(&rep_, column_family_id);
|
|
|
|
}
|
2013-03-21 23:59:47 +01:00
|
|
|
PutLengthPrefixedSlice(&rep_, key);
|
|
|
|
PutLengthPrefixedSlice(&rep_, value);
|
|
|
|
}
|
|
|
|
|
2013-08-15 01:32:46 +02:00
|
|
|
void WriteBatch::PutLogData(const Slice& blob) {
|
|
|
|
rep_.push_back(static_cast<char>(kTypeLogData));
|
|
|
|
PutLengthPrefixedSlice(&rep_, blob);
|
|
|
|
}
|
2013-03-21 23:59:47 +01:00
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
namespace {
|
|
|
|
class MemTableInserter : public WriteBatch::Handler {
|
|
|
|
public:
|
|
|
|
SequenceNumber sequence_;
|
|
|
|
MemTable* mem_;
|
2013-07-13 01:56:52 +02:00
|
|
|
const Options* options_;
|
|
|
|
DBImpl* db_;
|
|
|
|
const bool filter_deletes_;
|
|
|
|
|
|
|
|
MemTableInserter(SequenceNumber sequence, MemTable* mem, const Options* opts,
|
|
|
|
DB* db, const bool filter_deletes)
|
|
|
|
: sequence_(sequence),
|
|
|
|
mem_(mem),
|
|
|
|
options_(opts),
|
|
|
|
db_(reinterpret_cast<DBImpl*>(db)),
|
|
|
|
filter_deletes_(filter_deletes) {
|
|
|
|
assert(mem_);
|
|
|
|
if (filter_deletes_) {
|
|
|
|
assert(options_);
|
|
|
|
assert(db_);
|
|
|
|
}
|
|
|
|
}
|
2011-05-21 04:17:43 +02:00
|
|
|
|
2014-01-07 23:41:42 +01:00
|
|
|
virtual void PutCF(uint32_t column_family_id, const Slice& key,
|
[RocksDB] [Column Family] Interface proposal
Summary:
<This diff is for Column Family branch>
Sharing some of the work I've done so far. This diff compiles and passes the tests.
The biggest change is in options.h - I broke down Options into two parts - DBOptions and ColumnFamilyOptions. DBOptions is DB-specific (env, create_if_missing, block_cache, etc.) and ColumnFamilyOptions is column family-specific (all compaction options, compresion options, etc.). Note that this does not break backwards compatibility at all.
Further, I created DBWithColumnFamily which inherits DB interface and adds new functions with column family support. Clients can transparently switch to DBWithColumnFamily and it will not break their backwards compatibility.
There are few methods worth checking out: ListColumnFamilies(), MultiNewIterator(), MultiGet() and GetSnapshot(). [GetSnapshot() returns the snapshot across all column families for now - I think that's what we agreed on]
Finally, I made small changes to WriteBatch so we are able to atomically insert data across column families.
Please provide feedback.
Test Plan: make check works, the code is backward compatible
Reviewers: dhruba, haobo, sdong, kailiu, emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14445
2013-12-03 20:14:09 +01:00
|
|
|
const Slice& value) {
|
In-place updates for equal keys and similar sized values
Summary:
Currently for each put, a fresh memory is allocated, and a new entry is added to the memtable with a new sequence number irrespective of whether the key already exists in the memtable. This diff is an attempt to update the value inplace for existing keys. It currently handles a very simple case:
1. Key already exists in the current memtable. Does not inplace update values in immutable memtable or snapshot
2. Latest value type is a 'put' ie kTypeValue
3. New value size is less than existing value, to avoid reallocating memory
TODO: For a put of an existing key, deallocate memory take by values, for other value types till a kTypeValue is found, ie. remove kTypeMerge.
TODO: Update the transaction log, to allow consistent reload of the memtable.
Test Plan: Added a unit test verifying the inplace update. But some other unit tests broken due to invalid sequence number checks. WIll fix them next.
Reviewers: xinyaohu, sumeet, haobo, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D12423
Automatic commit by arc
2013-08-19 23:12:47 +02:00
|
|
|
if (options_->inplace_update_support
|
|
|
|
&& mem_->Update(sequence_, kTypeValue, key, value)) {
|
2013-11-22 23:14:05 +01:00
|
|
|
RecordTick(options_->statistics.get(), NUMBER_KEYS_UPDATED);
|
In-place updates for equal keys and similar sized values
Summary:
Currently for each put, a fresh memory is allocated, and a new entry is added to the memtable with a new sequence number irrespective of whether the key already exists in the memtable. This diff is an attempt to update the value inplace for existing keys. It currently handles a very simple case:
1. Key already exists in the current memtable. Does not inplace update values in immutable memtable or snapshot
2. Latest value type is a 'put' ie kTypeValue
3. New value size is less than existing value, to avoid reallocating memory
TODO: For a put of an existing key, deallocate memory take by values, for other value types till a kTypeValue is found, ie. remove kTypeMerge.
TODO: Update the transaction log, to allow consistent reload of the memtable.
Test Plan: Added a unit test verifying the inplace update. But some other unit tests broken due to invalid sequence number checks. WIll fix them next.
Reviewers: xinyaohu, sumeet, haobo, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D12423
Automatic commit by arc
2013-08-19 23:12:47 +02:00
|
|
|
} else {
|
|
|
|
mem_->Add(sequence_, kTypeValue, key, value);
|
|
|
|
}
|
2011-05-21 04:17:43 +02:00
|
|
|
sequence_++;
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
2014-01-07 23:41:42 +01:00
|
|
|
virtual void MergeCF(uint32_t column_family_id, const Slice& key,
|
|
|
|
const Slice& value) {
|
2014-01-11 02:33:56 +01:00
|
|
|
bool perform_merge = false;
|
|
|
|
|
|
|
|
if (options_->max_successive_merges > 0 && db_ != nullptr) {
|
|
|
|
LookupKey lkey(key, sequence_);
|
|
|
|
|
|
|
|
// Count the number of successive merges at the head
|
|
|
|
// of the key in the memtable
|
|
|
|
size_t num_merges = mem_->CountSuccessiveMergeEntries(lkey);
|
|
|
|
|
|
|
|
if (num_merges >= options_->max_successive_merges) {
|
|
|
|
perform_merge = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (perform_merge) {
|
|
|
|
// 1) Get the existing value
|
|
|
|
std::string get_value;
|
|
|
|
|
|
|
|
// Pass in the sequence number so that we also include previous merge
|
|
|
|
// operations in the same batch.
|
|
|
|
SnapshotImpl read_from_snapshot;
|
|
|
|
read_from_snapshot.number_ = sequence_;
|
|
|
|
ReadOptions read_options;
|
|
|
|
read_options.snapshot = &read_from_snapshot;
|
|
|
|
|
|
|
|
db_->Get(read_options, key, &get_value);
|
|
|
|
Slice get_value_slice = Slice(get_value);
|
|
|
|
|
|
|
|
// 2) Apply this merge
|
|
|
|
auto merge_operator = options_->merge_operator.get();
|
|
|
|
assert(merge_operator);
|
|
|
|
|
|
|
|
std::deque<std::string> operands;
|
|
|
|
operands.push_front(value.ToString());
|
|
|
|
std::string new_value;
|
|
|
|
if (!merge_operator->FullMerge(key,
|
|
|
|
&get_value_slice,
|
|
|
|
operands,
|
|
|
|
&new_value,
|
|
|
|
options_->info_log.get())) {
|
|
|
|
// Failed to merge!
|
|
|
|
RecordTick(options_->statistics.get(), NUMBER_MERGE_FAILURES);
|
|
|
|
|
|
|
|
// Store the delta in memtable
|
|
|
|
perform_merge = false;
|
|
|
|
} else {
|
|
|
|
// 3) Add value to memtable
|
|
|
|
mem_->Add(sequence_, kTypeValue, key, new_value);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!perform_merge) {
|
|
|
|
// Add merge operator to memtable
|
|
|
|
mem_->Add(sequence_, kTypeMerge, key, value);
|
|
|
|
}
|
|
|
|
|
2013-03-21 23:59:47 +01:00
|
|
|
sequence_++;
|
|
|
|
}
|
2014-01-07 23:41:42 +01:00
|
|
|
virtual void DeleteCF(uint32_t column_family_id, const Slice& key) {
|
2013-07-26 21:57:01 +02:00
|
|
|
if (filter_deletes_) {
|
|
|
|
SnapshotImpl read_from_snapshot;
|
|
|
|
read_from_snapshot.number_ = sequence_;
|
|
|
|
ReadOptions ropts;
|
|
|
|
ropts.snapshot = &read_from_snapshot;
|
|
|
|
std::string value;
|
|
|
|
if (!db_->KeyMayExist(ropts, key, &value)) {
|
2013-11-22 23:14:05 +01:00
|
|
|
RecordTick(options_->statistics.get(), NUMBER_FILTERED_DELETES);
|
2013-07-26 21:57:01 +02:00
|
|
|
return;
|
|
|
|
}
|
2013-07-13 01:56:52 +02:00
|
|
|
}
|
2011-05-21 04:17:43 +02:00
|
|
|
mem_->Add(sequence_, kTypeDeletion, key, Slice());
|
|
|
|
sequence_++;
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
2011-05-21 04:17:43 +02:00
|
|
|
};
|
2011-10-31 18:22:06 +01:00
|
|
|
} // namespace
|
2011-05-21 04:17:43 +02:00
|
|
|
|
2013-07-13 01:56:52 +02:00
|
|
|
Status WriteBatchInternal::InsertInto(const WriteBatch* b, MemTable* mem,
|
|
|
|
const Options* opts, DB* db,
|
|
|
|
const bool filter_deletes) {
|
|
|
|
MemTableInserter inserter(WriteBatchInternal::Sequence(b), mem, opts, db,
|
|
|
|
filter_deletes);
|
2011-05-21 04:17:43 +02:00
|
|
|
return b->Iterate(&inserter);
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
void WriteBatchInternal::SetContents(WriteBatch* b, const Slice& contents) {
|
2012-03-09 01:23:21 +01:00
|
|
|
assert(contents.size() >= kHeader);
|
2011-03-18 23:37:00 +01:00
|
|
|
b->rep_.assign(contents.data(), contents.size());
|
|
|
|
}
|
|
|
|
|
2012-03-09 01:23:21 +01:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2013-10-04 06:49:15 +02:00
|
|
|
} // namespace rocksdb
|