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"
|
2015-07-11 05:15:45 +02:00
|
|
|
|
|
|
|
#include <stack>
|
|
|
|
#include <stdexcept>
|
|
|
|
|
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"
|
2014-08-19 00:19:17 +02:00
|
|
|
#include "db/column_family.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
#include "db/memtable.h"
|
2015-08-07 02:59:05 +02:00
|
|
|
#include "db/snapshot_impl.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"
|
2015-03-03 19:59:36 +01:00
|
|
|
#include "util/perf_context_imp.h"
|
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;
|
|
|
|
|
2015-07-11 05:15:45 +02:00
|
|
|
struct SavePoint {
|
|
|
|
size_t size; // size of rep_
|
|
|
|
int count; // count of elements in rep_
|
|
|
|
SavePoint(size_t s, int c) : size(s), count(c) {}
|
|
|
|
};
|
|
|
|
|
|
|
|
struct SavePoints {
|
|
|
|
std::stack<SavePoint> stack;
|
|
|
|
};
|
|
|
|
|
|
|
|
WriteBatch::WriteBatch(size_t reserved_bytes) : save_points_(nullptr) {
|
2014-01-14 19:42:36 +01:00
|
|
|
rep_.reserve((reserved_bytes > kHeader) ? reserved_bytes : kHeader);
|
2011-03-18 23:37:00 +01:00
|
|
|
Clear();
|
|
|
|
}
|
|
|
|
|
2015-07-11 05:15:45 +02:00
|
|
|
WriteBatch::~WriteBatch() {
|
|
|
|
if (save_points_ != nullptr) {
|
|
|
|
delete save_points_;
|
|
|
|
}
|
|
|
|
}
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
WriteBatch::Handler::~Handler() { }
|
|
|
|
|
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);
|
2015-07-11 05:15:45 +02:00
|
|
|
|
|
|
|
if (save_points_ != nullptr) {
|
|
|
|
while (!save_points_->stack.empty()) {
|
|
|
|
save_points_->stack.pop();
|
|
|
|
}
|
|
|
|
}
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
|
2013-06-26 19:50:58 +02:00
|
|
|
int WriteBatch::Count() const {
|
|
|
|
return WriteBatchInternal::Count(this);
|
|
|
|
}
|
|
|
|
|
2014-08-19 00:19:17 +02:00
|
|
|
Status ReadRecordFromWriteBatch(Slice* input, char* tag,
|
|
|
|
uint32_t* column_family, Slice* key,
|
|
|
|
Slice* value, Slice* blob) {
|
|
|
|
assert(key != nullptr && value != nullptr);
|
|
|
|
*tag = (*input)[0];
|
|
|
|
input->remove_prefix(1);
|
|
|
|
*column_family = 0; // default
|
|
|
|
switch (*tag) {
|
|
|
|
case kTypeColumnFamilyValue:
|
|
|
|
if (!GetVarint32(input, column_family)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Put");
|
|
|
|
}
|
|
|
|
// intentional fallthrough
|
|
|
|
case kTypeValue:
|
|
|
|
if (!GetLengthPrefixedSlice(input, key) ||
|
|
|
|
!GetLengthPrefixedSlice(input, value)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Put");
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case kTypeColumnFamilyDeletion:
|
|
|
|
if (!GetVarint32(input, column_family)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Delete");
|
|
|
|
}
|
|
|
|
// intentional fallthrough
|
|
|
|
case kTypeDeletion:
|
|
|
|
if (!GetLengthPrefixedSlice(input, key)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Delete");
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case kTypeColumnFamilyMerge:
|
|
|
|
if (!GetVarint32(input, column_family)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Merge");
|
|
|
|
}
|
|
|
|
// intentional fallthrough
|
|
|
|
case kTypeMerge:
|
|
|
|
if (!GetLengthPrefixedSlice(input, key) ||
|
|
|
|
!GetLengthPrefixedSlice(input, value)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Merge");
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case kTypeLogData:
|
|
|
|
assert(blob != nullptr);
|
|
|
|
if (!GetLengthPrefixedSlice(input, blob)) {
|
|
|
|
return Status::Corruption("bad WriteBatch Blob");
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
return Status::Corruption("unknown WriteBatch tag");
|
|
|
|
}
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
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;
|
2014-02-26 02:30:54 +01:00
|
|
|
Status s;
|
|
|
|
while (s.ok() && !input.empty() && handler->Continue()) {
|
2014-08-19 00:19:17 +02:00
|
|
|
char tag = 0;
|
2014-01-30 00:26:43 +01:00
|
|
|
uint32_t column_family = 0; // default
|
2014-08-19 00:19:17 +02:00
|
|
|
|
|
|
|
s = ReadRecordFromWriteBatch(&input, &tag, &column_family, &key, &value,
|
|
|
|
&blob);
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
switch (tag) {
|
2014-01-07 23:41:42 +01:00
|
|
|
case kTypeColumnFamilyValue:
|
2011-05-21 04:17:43 +02:00
|
|
|
case kTypeValue:
|
2014-08-19 00:19:17 +02:00
|
|
|
s = handler->PutCF(column_family, key, value);
|
|
|
|
found++;
|
2011-05-21 04:17:43 +02:00
|
|
|
break;
|
2014-01-07 23:41:42 +01:00
|
|
|
case kTypeColumnFamilyDeletion:
|
2011-05-21 04:17:43 +02:00
|
|
|
case kTypeDeletion:
|
2014-08-19 00:19:17 +02:00
|
|
|
s = handler->DeleteCF(column_family, key);
|
|
|
|
found++;
|
2011-05-21 04:17:43 +02:00
|
|
|
break;
|
2014-01-07 23:41:42 +01:00
|
|
|
case kTypeColumnFamilyMerge:
|
2013-03-21 23:59:47 +01:00
|
|
|
case kTypeMerge:
|
2014-08-19 00:19:17 +02:00
|
|
|
s = handler->MergeCF(column_family, key, value);
|
|
|
|
found++;
|
2013-03-21 23:59:47 +01:00
|
|
|
break;
|
2013-08-15 01:32:46 +02:00
|
|
|
case kTypeLogData:
|
2014-08-19 00:19:17 +02:00
|
|
|
handler->LogData(blob);
|
2013-08-15 01:32:46 +02:00
|
|
|
break;
|
2011-05-21 04:17:43 +02:00
|
|
|
default:
|
|
|
|
return Status::Corruption("unknown WriteBatch tag");
|
|
|
|
}
|
|
|
|
}
|
2014-02-26 02:30:54 +01:00
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
if (found != WriteBatchInternal::Count(this)) {
|
2011-05-21 04:17:43 +02:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2015-07-11 05:15:45 +02:00
|
|
|
size_t WriteBatchInternal::GetFirstOffset(WriteBatch* b) { return kHeader; }
|
|
|
|
|
2014-04-22 20:27:33 +02:00
|
|
|
void WriteBatchInternal::Put(WriteBatch* b, uint32_t column_family_id,
|
|
|
|
const Slice& key, const Slice& value) {
|
|
|
|
WriteBatchInternal::SetCount(b, WriteBatchInternal::Count(b) + 1);
|
|
|
|
if (column_family_id == 0) {
|
|
|
|
b->rep_.push_back(static_cast<char>(kTypeValue));
|
|
|
|
} else {
|
|
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyValue));
|
|
|
|
PutVarint32(&b->rep_, column_family_id);
|
|
|
|
}
|
|
|
|
PutLengthPrefixedSlice(&b->rep_, key);
|
|
|
|
PutLengthPrefixedSlice(&b->rep_, value);
|
|
|
|
}
|
|
|
|
|
|
|
|
void WriteBatch::Put(ColumnFamilyHandle* column_family, const Slice& key,
|
|
|
|
const Slice& value) {
|
|
|
|
WriteBatchInternal::Put(this, GetColumnFamilyID(column_family), key, value);
|
|
|
|
}
|
|
|
|
|
|
|
|
void WriteBatchInternal::Put(WriteBatch* b, uint32_t column_family_id,
|
|
|
|
const SliceParts& key, const SliceParts& value) {
|
|
|
|
WriteBatchInternal::SetCount(b, WriteBatchInternal::Count(b) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
2014-04-22 20:27:33 +02:00
|
|
|
b->rep_.push_back(static_cast<char>(kTypeValue));
|
2014-01-07 23:41:42 +01:00
|
|
|
} else {
|
2014-04-22 20:27:33 +02:00
|
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyValue));
|
|
|
|
PutVarint32(&b->rep_, column_family_id);
|
2014-01-07 23:41:42 +01:00
|
|
|
}
|
2014-04-22 20:27:33 +02:00
|
|
|
PutLengthPrefixedSliceParts(&b->rep_, key);
|
|
|
|
PutLengthPrefixedSliceParts(&b->rep_, value);
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
|
2014-03-14 19:26:13 +01:00
|
|
|
void WriteBatch::Put(ColumnFamilyHandle* column_family, const SliceParts& key,
|
2014-01-07 23:41:42 +01:00
|
|
|
const SliceParts& value) {
|
2014-04-22 20:27:33 +02:00
|
|
|
WriteBatchInternal::Put(this, GetColumnFamilyID(column_family), key, value);
|
|
|
|
}
|
2014-03-14 19:26:13 +01:00
|
|
|
|
2014-04-22 20:27:33 +02:00
|
|
|
void WriteBatchInternal::Delete(WriteBatch* b, uint32_t column_family_id,
|
|
|
|
const Slice& key) {
|
|
|
|
WriteBatchInternal::SetCount(b, WriteBatchInternal::Count(b) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
2014-04-22 20:27:33 +02:00
|
|
|
b->rep_.push_back(static_cast<char>(kTypeDeletion));
|
2014-01-07 23:41:42 +01:00
|
|
|
} else {
|
2014-04-22 20:27:33 +02:00
|
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyDeletion));
|
|
|
|
PutVarint32(&b->rep_, column_family_id);
|
2014-01-07 23:41:42 +01:00
|
|
|
}
|
2014-04-22 20:27:33 +02:00
|
|
|
PutLengthPrefixedSlice(&b->rep_, key);
|
2013-11-07 21:37:58 +01:00
|
|
|
}
|
|
|
|
|
2014-03-14 19:26:13 +01:00
|
|
|
void WriteBatch::Delete(ColumnFamilyHandle* column_family, const Slice& key) {
|
2014-04-22 20:27:33 +02:00
|
|
|
WriteBatchInternal::Delete(this, GetColumnFamilyID(column_family), key);
|
2014-07-10 18:31:42 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
void WriteBatchInternal::Delete(WriteBatch* b, uint32_t column_family_id,
|
|
|
|
const SliceParts& key) {
|
|
|
|
WriteBatchInternal::SetCount(b, WriteBatchInternal::Count(b) + 1);
|
|
|
|
if (column_family_id == 0) {
|
|
|
|
b->rep_.push_back(static_cast<char>(kTypeDeletion));
|
|
|
|
} else {
|
|
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyDeletion));
|
|
|
|
PutVarint32(&b->rep_, column_family_id);
|
|
|
|
}
|
|
|
|
PutLengthPrefixedSliceParts(&b->rep_, key);
|
|
|
|
}
|
|
|
|
|
|
|
|
void WriteBatch::Delete(ColumnFamilyHandle* column_family,
|
|
|
|
const SliceParts& key) {
|
|
|
|
WriteBatchInternal::Delete(this, GetColumnFamilyID(column_family), key);
|
2014-04-22 20:27:33 +02:00
|
|
|
}
|
2014-03-14 19:26:13 +01:00
|
|
|
|
2014-04-22 20:27:33 +02:00
|
|
|
void WriteBatchInternal::Merge(WriteBatch* b, uint32_t column_family_id,
|
|
|
|
const Slice& key, const Slice& value) {
|
|
|
|
WriteBatchInternal::SetCount(b, WriteBatchInternal::Count(b) + 1);
|
2014-01-07 23:41:42 +01:00
|
|
|
if (column_family_id == 0) {
|
2014-04-22 20:27:33 +02:00
|
|
|
b->rep_.push_back(static_cast<char>(kTypeMerge));
|
2014-01-07 23:41:42 +01:00
|
|
|
} else {
|
2014-04-22 20:27:33 +02:00
|
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyMerge));
|
|
|
|
PutVarint32(&b->rep_, column_family_id);
|
2014-01-07 23:41:42 +01:00
|
|
|
}
|
2014-04-22 20:27:33 +02:00
|
|
|
PutLengthPrefixedSlice(&b->rep_, key);
|
|
|
|
PutLengthPrefixedSlice(&b->rep_, value);
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
|
2014-03-14 19:26:13 +01:00
|
|
|
void WriteBatch::Merge(ColumnFamilyHandle* column_family, const Slice& key,
|
2014-01-07 23:41:42 +01:00
|
|
|
const Slice& value) {
|
2014-04-22 20:27:33 +02:00
|
|
|
WriteBatchInternal::Merge(this, GetColumnFamilyID(column_family), key, value);
|
2013-03-21 23:59:47 +01:00
|
|
|
}
|
|
|
|
|
2015-05-28 01:59:22 +02:00
|
|
|
void WriteBatchInternal::Merge(WriteBatch* b, uint32_t column_family_id,
|
|
|
|
const SliceParts& key,
|
|
|
|
const SliceParts& value) {
|
|
|
|
WriteBatchInternal::SetCount(b, WriteBatchInternal::Count(b) + 1);
|
|
|
|
if (column_family_id == 0) {
|
|
|
|
b->rep_.push_back(static_cast<char>(kTypeMerge));
|
|
|
|
} else {
|
|
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyMerge));
|
|
|
|
PutVarint32(&b->rep_, column_family_id);
|
|
|
|
}
|
|
|
|
PutLengthPrefixedSliceParts(&b->rep_, key);
|
|
|
|
PutLengthPrefixedSliceParts(&b->rep_, value);
|
|
|
|
}
|
|
|
|
|
|
|
|
void WriteBatch::Merge(ColumnFamilyHandle* column_family,
|
|
|
|
const SliceParts& key,
|
|
|
|
const SliceParts& value) {
|
|
|
|
WriteBatchInternal::Merge(this, GetColumnFamilyID(column_family),
|
|
|
|
key, 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
|
|
|
|
2015-07-11 05:15:45 +02:00
|
|
|
void WriteBatch::SetSavePoint() {
|
|
|
|
if (save_points_ == nullptr) {
|
|
|
|
save_points_ = new SavePoints();
|
|
|
|
}
|
|
|
|
// Record length and count of current batch of writes.
|
|
|
|
save_points_->stack.push(SavePoint(GetDataSize(), Count()));
|
|
|
|
}
|
|
|
|
|
|
|
|
Status WriteBatch::RollbackToSavePoint() {
|
|
|
|
if (save_points_ == nullptr || save_points_->stack.size() == 0) {
|
|
|
|
return Status::NotFound();
|
|
|
|
}
|
|
|
|
|
|
|
|
// Pop the most recent savepoint off the stack
|
|
|
|
SavePoint savepoint = save_points_->stack.top();
|
|
|
|
save_points_->stack.pop();
|
|
|
|
|
|
|
|
assert(savepoint.size <= rep_.size());
|
|
|
|
|
|
|
|
if (savepoint.size == rep_.size()) {
|
|
|
|
// No changes to rollback
|
|
|
|
} else if (savepoint.size == 0) {
|
|
|
|
// Rollback everything
|
|
|
|
Clear();
|
|
|
|
} else {
|
|
|
|
rep_.resize(savepoint.size);
|
|
|
|
WriteBatchInternal::SetCount(this, savepoint.count);
|
|
|
|
}
|
|
|
|
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
namespace {
|
2015-01-06 21:44:21 +01:00
|
|
|
// This class can *only* be used from a single-threaded write thread, because it
|
|
|
|
// calls ColumnFamilyMemTablesImpl::Seek()
|
2011-05-21 04:17:43 +02:00
|
|
|
class MemTableInserter : public WriteBatch::Handler {
|
|
|
|
public:
|
|
|
|
SequenceNumber sequence_;
|
2014-01-28 20:05:04 +01:00
|
|
|
ColumnFamilyMemTables* cf_mems_;
|
2014-09-02 22:29:05 +02:00
|
|
|
bool ignore_missing_column_families_;
|
2014-02-06 01:02:48 +01:00
|
|
|
uint64_t log_number_;
|
2013-07-13 01:56:52 +02:00
|
|
|
DBImpl* db_;
|
2014-02-06 01:02:48 +01:00
|
|
|
const bool dont_filter_deletes_;
|
2011-05-21 04:17:43 +02:00
|
|
|
|
2014-01-28 20:05:04 +01:00
|
|
|
MemTableInserter(SequenceNumber sequence, ColumnFamilyMemTables* cf_mems,
|
2014-09-02 22:29:05 +02:00
|
|
|
bool ignore_missing_column_families, uint64_t log_number,
|
|
|
|
DB* db, const bool dont_filter_deletes)
|
2014-01-28 20:05:04 +01:00
|
|
|
: sequence_(sequence),
|
|
|
|
cf_mems_(cf_mems),
|
2014-09-02 22:29:05 +02:00
|
|
|
ignore_missing_column_families_(ignore_missing_column_families),
|
2014-02-06 01:02:48 +01:00
|
|
|
log_number_(log_number),
|
2014-01-28 20:05:04 +01:00
|
|
|
db_(reinterpret_cast<DBImpl*>(db)),
|
2014-02-06 01:02:48 +01:00
|
|
|
dont_filter_deletes_(dont_filter_deletes) {
|
2014-01-28 20:05:04 +01:00
|
|
|
assert(cf_mems);
|
2014-02-06 01:02:48 +01:00
|
|
|
if (!dont_filter_deletes_) {
|
2014-01-28 20:05:04 +01:00
|
|
|
assert(db_);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-03-03 23:30:36 +01:00
|
|
|
bool SeekToColumnFamily(uint32_t column_family_id, Status* s) {
|
2015-01-06 21:44:21 +01:00
|
|
|
// We are only allowed to call this from a single-threaded write thread
|
|
|
|
// (or while holding DB mutex)
|
2014-02-06 01:02:48 +01:00
|
|
|
bool found = cf_mems_->Seek(column_family_id);
|
2014-09-02 22:29:05 +02:00
|
|
|
if (!found) {
|
|
|
|
if (ignore_missing_column_families_) {
|
|
|
|
*s = Status::OK();
|
|
|
|
} else {
|
|
|
|
*s = Status::InvalidArgument(
|
|
|
|
"Invalid column family specified in write batch");
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
if (log_number_ != 0 && log_number_ < cf_mems_->GetLogNumber()) {
|
|
|
|
// This is true only in recovery environment (log_number_ is always 0 in
|
|
|
|
// non-recovery, regular write code-path)
|
2014-03-03 23:30:36 +01:00
|
|
|
// * If log_number_ < cf_mems_->GetLogNumber(), this means that column
|
|
|
|
// family already contains updates from this log. We can't apply updates
|
|
|
|
// twice because of update-in-place or merge workloads -- ignore the
|
|
|
|
// update
|
|
|
|
*s = Status::OK();
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
virtual Status PutCF(uint32_t column_family_id, const Slice& key,
|
2015-02-26 20:28:41 +01:00
|
|
|
const Slice& value) override {
|
2014-03-03 23:30:36 +01:00
|
|
|
Status seek_status;
|
|
|
|
if (!SeekToColumnFamily(column_family_id, &seek_status)) {
|
|
|
|
++sequence_;
|
|
|
|
return seek_status;
|
2014-01-28 20:05:04 +01:00
|
|
|
}
|
2014-02-06 01:02:48 +01:00
|
|
|
MemTable* mem = cf_mems_->GetMemTable();
|
2014-09-09 03:46:52 +02:00
|
|
|
auto* moptions = mem->GetMemTableOptions();
|
|
|
|
if (!moptions->inplace_update_support) {
|
2014-02-07 00:42:16 +01:00
|
|
|
mem->Add(sequence_, kTypeValue, key, value);
|
2014-09-09 03:46:52 +02:00
|
|
|
} else if (moptions->inplace_callback == nullptr) {
|
2014-02-07 00:42:16 +01:00
|
|
|
mem->Update(sequence_, key, value);
|
2014-10-27 20:10:13 +01:00
|
|
|
RecordTick(moptions->statistics, 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 {
|
2014-09-09 03:46:52 +02:00
|
|
|
if (mem->UpdateCallback(sequence_, key, value)) {
|
2014-01-14 16:55:16 +01:00
|
|
|
} else {
|
Allow callback to change size of existing value. Change return type of the callback function to an enum status to handle 3 cases.
Summary:
This diff fixes 2 hacks:
* The callback function can modify the existing value inplace, if the merged value fits within the existing buffer size. But currently the existing buffer size is not being modified. Now the callback recieves a int* allowing the size to be modified. Since size is encoded as a varint in the internal key for memtable. It might happen that the entire value might have be copied to the new location if the new size varint is smaller than the existing size varint.
* The callback function has 3 functionalities
1. Modify existing buffer inplace, and update size correspondingly. Now to indicate that, Returns 1.
2. Generate a new buffer indicating merged value. Returns 2.
3. Fails to do either of above, based on whatever application logic. Returns 0.
Test Plan: Just make all for now. I'm adding another unit test to test each scenario.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb, sdong, kailiu, xinyaohu, sumeet, danguo
Differential Revision: https://reviews.facebook.net/D15195
2014-01-17 00:11:19 +01:00
|
|
|
// key not found in memtable. Do sst get, update, add
|
2014-01-14 16:55:16 +01:00
|
|
|
SnapshotImpl read_from_snapshot;
|
|
|
|
read_from_snapshot.number_ = sequence_;
|
|
|
|
ReadOptions ropts;
|
|
|
|
ropts.snapshot = &read_from_snapshot;
|
|
|
|
|
|
|
|
std::string prev_value;
|
|
|
|
std::string merged_value;
|
2014-02-11 02:04:44 +01:00
|
|
|
|
|
|
|
auto cf_handle = cf_mems_->GetColumnFamilyHandle();
|
|
|
|
if (cf_handle == nullptr) {
|
|
|
|
cf_handle = db_->DefaultColumnFamily();
|
|
|
|
}
|
|
|
|
Status s = db_->Get(ropts, cf_handle, key, &prev_value);
|
|
|
|
|
2014-01-14 16:55:16 +01:00
|
|
|
char* prev_buffer = const_cast<char*>(prev_value.c_str());
|
2014-11-11 22:47:22 +01:00
|
|
|
uint32_t prev_size = static_cast<uint32_t>(prev_value.size());
|
2014-09-09 03:46:52 +02:00
|
|
|
auto status = moptions->inplace_callback(s.ok() ? prev_buffer : nullptr,
|
|
|
|
s.ok() ? &prev_size : nullptr,
|
|
|
|
value, &merged_value);
|
Allow callback to change size of existing value. Change return type of the callback function to an enum status to handle 3 cases.
Summary:
This diff fixes 2 hacks:
* The callback function can modify the existing value inplace, if the merged value fits within the existing buffer size. But currently the existing buffer size is not being modified. Now the callback recieves a int* allowing the size to be modified. Since size is encoded as a varint in the internal key for memtable. It might happen that the entire value might have be copied to the new location if the new size varint is smaller than the existing size varint.
* The callback function has 3 functionalities
1. Modify existing buffer inplace, and update size correspondingly. Now to indicate that, Returns 1.
2. Generate a new buffer indicating merged value. Returns 2.
3. Fails to do either of above, based on whatever application logic. Returns 0.
Test Plan: Just make all for now. I'm adding another unit test to test each scenario.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb, sdong, kailiu, xinyaohu, sumeet, danguo
Differential Revision: https://reviews.facebook.net/D15195
2014-01-17 00:11:19 +01:00
|
|
|
if (status == UpdateStatus::UPDATED_INPLACE) {
|
2014-01-14 16:55:16 +01:00
|
|
|
// prev_value is updated in-place with final value.
|
2014-02-07 00:42:16 +01:00
|
|
|
mem->Add(sequence_, kTypeValue, key, Slice(prev_buffer, prev_size));
|
2014-10-27 20:10:13 +01:00
|
|
|
RecordTick(moptions->statistics, NUMBER_KEYS_WRITTEN);
|
Allow callback to change size of existing value. Change return type of the callback function to an enum status to handle 3 cases.
Summary:
This diff fixes 2 hacks:
* The callback function can modify the existing value inplace, if the merged value fits within the existing buffer size. But currently the existing buffer size is not being modified. Now the callback recieves a int* allowing the size to be modified. Since size is encoded as a varint in the internal key for memtable. It might happen that the entire value might have be copied to the new location if the new size varint is smaller than the existing size varint.
* The callback function has 3 functionalities
1. Modify existing buffer inplace, and update size correspondingly. Now to indicate that, Returns 1.
2. Generate a new buffer indicating merged value. Returns 2.
3. Fails to do either of above, based on whatever application logic. Returns 0.
Test Plan: Just make all for now. I'm adding another unit test to test each scenario.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb, sdong, kailiu, xinyaohu, sumeet, danguo
Differential Revision: https://reviews.facebook.net/D15195
2014-01-17 00:11:19 +01:00
|
|
|
} else if (status == UpdateStatus::UPDATED) {
|
|
|
|
// merged_value contains the final value.
|
2014-02-07 00:42:16 +01:00
|
|
|
mem->Add(sequence_, kTypeValue, key, Slice(merged_value));
|
2014-10-27 20:10:13 +01:00
|
|
|
RecordTick(moptions->statistics, NUMBER_KEYS_WRITTEN);
|
2014-01-14 16:55:16 +01:00
|
|
|
}
|
|
|
|
}
|
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
|
|
|
}
|
Allow callback to change size of existing value. Change return type of the callback function to an enum status to handle 3 cases.
Summary:
This diff fixes 2 hacks:
* The callback function can modify the existing value inplace, if the merged value fits within the existing buffer size. But currently the existing buffer size is not being modified. Now the callback recieves a int* allowing the size to be modified. Since size is encoded as a varint in the internal key for memtable. It might happen that the entire value might have be copied to the new location if the new size varint is smaller than the existing size varint.
* The callback function has 3 functionalities
1. Modify existing buffer inplace, and update size correspondingly. Now to indicate that, Returns 1.
2. Generate a new buffer indicating merged value. Returns 2.
3. Fails to do either of above, based on whatever application logic. Returns 0.
Test Plan: Just make all for now. I'm adding another unit test to test each scenario.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb, sdong, kailiu, xinyaohu, sumeet, danguo
Differential Revision: https://reviews.facebook.net/D15195
2014-01-17 00:11:19 +01:00
|
|
|
// Since all Puts are logged in trasaction logs (if enabled), always bump
|
|
|
|
// sequence number. Even if the update eventually fails and does not result
|
|
|
|
// in memtable add/update.
|
2011-05-21 04:17:43 +02:00
|
|
|
sequence_++;
|
2014-09-11 03:46:09 +02:00
|
|
|
cf_mems_->CheckMemtableFull();
|
2014-02-26 02:30:54 +01:00
|
|
|
return Status::OK();
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
2014-01-14 16:55:16 +01:00
|
|
|
|
2014-02-26 02:30:54 +01:00
|
|
|
virtual Status MergeCF(uint32_t column_family_id, const Slice& key,
|
2015-02-26 20:28:41 +01:00
|
|
|
const Slice& value) override {
|
2014-03-03 23:30:36 +01:00
|
|
|
Status seek_status;
|
|
|
|
if (!SeekToColumnFamily(column_family_id, &seek_status)) {
|
|
|
|
++sequence_;
|
|
|
|
return seek_status;
|
2014-01-28 20:05:04 +01:00
|
|
|
}
|
2014-02-06 01:02:48 +01:00
|
|
|
MemTable* mem = cf_mems_->GetMemTable();
|
2014-09-09 03:46:52 +02:00
|
|
|
auto* moptions = mem->GetMemTableOptions();
|
2014-01-11 02:33:56 +01:00
|
|
|
bool perform_merge = false;
|
|
|
|
|
2014-09-09 03:46:52 +02:00
|
|
|
if (moptions->max_successive_merges > 0 && db_ != nullptr) {
|
2014-01-11 02:33:56 +01:00
|
|
|
LookupKey lkey(key, sequence_);
|
|
|
|
|
|
|
|
// Count the number of successive merges at the head
|
|
|
|
// of the key in the memtable
|
2014-01-28 20:05:04 +01:00
|
|
|
size_t num_merges = mem->CountSuccessiveMergeEntries(lkey);
|
2014-01-11 02:33:56 +01:00
|
|
|
|
2014-09-09 03:46:52 +02:00
|
|
|
if (num_merges >= moptions->max_successive_merges) {
|
2014-01-11 02:33:56 +01:00
|
|
|
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;
|
|
|
|
|
2014-02-11 02:04:44 +01:00
|
|
|
auto cf_handle = cf_mems_->GetColumnFamilyHandle();
|
|
|
|
if (cf_handle == nullptr) {
|
|
|
|
cf_handle = db_->DefaultColumnFamily();
|
|
|
|
}
|
|
|
|
db_->Get(read_options, cf_handle, key, &get_value);
|
2014-01-11 02:33:56 +01:00
|
|
|
Slice get_value_slice = Slice(get_value);
|
|
|
|
|
|
|
|
// 2) Apply this merge
|
2014-10-27 20:10:13 +01:00
|
|
|
auto merge_operator = moptions->merge_operator;
|
2014-01-11 02:33:56 +01:00
|
|
|
assert(merge_operator);
|
|
|
|
|
|
|
|
std::deque<std::string> operands;
|
|
|
|
operands.push_front(value.ToString());
|
|
|
|
std::string new_value;
|
2015-03-03 19:59:36 +01:00
|
|
|
bool merge_success = false;
|
|
|
|
{
|
|
|
|
StopWatchNano timer(Env::Default(), moptions->statistics != nullptr);
|
|
|
|
PERF_TIMER_GUARD(merge_operator_time_nanos);
|
|
|
|
merge_success = merge_operator->FullMerge(
|
|
|
|
key, &get_value_slice, operands, &new_value, moptions->info_log);
|
|
|
|
RecordTick(moptions->statistics, MERGE_OPERATION_TOTAL_TIME,
|
|
|
|
timer.ElapsedNanos());
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!merge_success) {
|
2014-01-11 02:33:56 +01:00
|
|
|
// Failed to merge!
|
2014-10-27 20:10:13 +01:00
|
|
|
RecordTick(moptions->statistics, NUMBER_MERGE_FAILURES);
|
2014-01-11 02:33:56 +01:00
|
|
|
|
2014-07-28 21:05:36 +02:00
|
|
|
// Store the delta in memtable
|
|
|
|
perform_merge = false;
|
2014-01-11 02:33:56 +01:00
|
|
|
} else {
|
|
|
|
// 3) Add value to memtable
|
2014-01-28 20:05:04 +01:00
|
|
|
mem->Add(sequence_, kTypeValue, key, new_value);
|
2014-01-11 02:33:56 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!perform_merge) {
|
|
|
|
// Add merge operator to memtable
|
2014-01-28 20:05:04 +01:00
|
|
|
mem->Add(sequence_, kTypeMerge, key, value);
|
2014-01-11 02:33:56 +01:00
|
|
|
}
|
|
|
|
|
2013-03-21 23:59:47 +01:00
|
|
|
sequence_++;
|
2014-09-11 03:46:09 +02:00
|
|
|
cf_mems_->CheckMemtableFull();
|
2014-02-26 02:30:54 +01:00
|
|
|
return Status::OK();
|
2013-03-21 23:59:47 +01:00
|
|
|
}
|
2014-02-07 00:42:16 +01:00
|
|
|
|
2015-02-26 20:28:41 +01:00
|
|
|
virtual Status DeleteCF(uint32_t column_family_id,
|
|
|
|
const Slice& key) override {
|
2014-03-03 23:30:36 +01:00
|
|
|
Status seek_status;
|
|
|
|
if (!SeekToColumnFamily(column_family_id, &seek_status)) {
|
|
|
|
++sequence_;
|
|
|
|
return seek_status;
|
2014-01-28 20:05:04 +01:00
|
|
|
}
|
2014-02-06 01:02:48 +01:00
|
|
|
MemTable* mem = cf_mems_->GetMemTable();
|
2014-09-09 03:46:52 +02:00
|
|
|
auto* moptions = mem->GetMemTableOptions();
|
|
|
|
if (!dont_filter_deletes_ && moptions->filter_deletes) {
|
2013-07-26 21:57:01 +02:00
|
|
|
SnapshotImpl read_from_snapshot;
|
|
|
|
read_from_snapshot.number_ = sequence_;
|
|
|
|
ReadOptions ropts;
|
|
|
|
ropts.snapshot = &read_from_snapshot;
|
|
|
|
std::string value;
|
2014-02-11 02:04:44 +01:00
|
|
|
auto cf_handle = cf_mems_->GetColumnFamilyHandle();
|
|
|
|
if (cf_handle == nullptr) {
|
|
|
|
cf_handle = db_->DefaultColumnFamily();
|
|
|
|
}
|
|
|
|
if (!db_->KeyMayExist(ropts, cf_handle, key, &value)) {
|
2014-10-27 20:10:13 +01:00
|
|
|
RecordTick(moptions->statistics, NUMBER_FILTERED_DELETES);
|
2014-02-26 02:30:54 +01:00
|
|
|
return Status::OK();
|
2013-07-26 21:57:01 +02:00
|
|
|
}
|
2013-07-13 01:56:52 +02:00
|
|
|
}
|
2014-01-28 20:05:04 +01:00
|
|
|
mem->Add(sequence_, kTypeDeletion, key, Slice());
|
2011-05-21 04:17:43 +02:00
|
|
|
sequence_++;
|
2014-09-11 03:46:09 +02:00
|
|
|
cf_mems_->CheckMemtableFull();
|
2014-02-26 02:30:54 +01:00
|
|
|
return Status::OK();
|
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
|
|
|
|
2015-01-06 21:44:21 +01:00
|
|
|
// This function can only be called in these conditions:
|
|
|
|
// 1) During Recovery()
|
|
|
|
// 2) during Write(), in a single-threaded write thread
|
|
|
|
// The reason is that it calles ColumnFamilyMemTablesImpl::Seek(), which needs
|
|
|
|
// to be called from a single-threaded write thread (or while holding DB mutex)
|
2014-01-28 20:05:04 +01:00
|
|
|
Status WriteBatchInternal::InsertInto(const WriteBatch* b,
|
|
|
|
ColumnFamilyMemTables* memtables,
|
2014-09-02 22:29:05 +02:00
|
|
|
bool ignore_missing_column_families,
|
|
|
|
uint64_t log_number, DB* db,
|
|
|
|
const bool dont_filter_deletes) {
|
2014-02-06 01:02:48 +01:00
|
|
|
MemTableInserter inserter(WriteBatchInternal::Sequence(b), memtables,
|
2014-09-02 22:29:05 +02:00
|
|
|
ignore_missing_column_families, log_number, db,
|
|
|
|
dont_filter_deletes);
|
2014-01-28 20:05:04 +01:00
|
|
|
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
|