forked from facebook/rocksdb
-
Notifications
You must be signed in to change notification settings - Fork 0
/
write_batch.cc
335 lines (293 loc) · 10.5 KB
/
write_batch.cc
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
// 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.
//
// 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 "rocksdb/write_batch.h"
#include "rocksdb/options.h"
#include "rocksdb/merge_operator.h"
#include "db/dbformat.h"
#include "db/db_impl.h"
#include "db/memtable.h"
#include "db/snapshot.h"
#include "db/write_batch_internal.h"
#include "util/coding.h"
#include "util/statistics.h"
#include <stdexcept>
namespace rocksdb {
// WriteBatch header has an 8-byte sequence number followed by a 4-byte count.
static const size_t kHeader = 12;
WriteBatch::WriteBatch(size_t reserved_bytes) {
rep_.reserve((reserved_bytes > kHeader) ? reserved_bytes : kHeader);
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::Handler::LogData(const Slice& blob) {
// If the user has not specified something to do with blobs, then we ignore
// them.
}
bool WriteBatch::Handler::Continue() {
return true;
}
void WriteBatch::Clear() {
rep_.clear();
rep_.resize(kHeader);
}
int WriteBatch::Count() const {
return WriteBatchInternal::Count(this);
}
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, blob;
int found = 0;
while (!input.empty() && handler->Continue()) {
char tag = input[0];
input.remove_prefix(1);
switch (tag) {
case kTypeValue:
if (GetLengthPrefixedSlice(&input, &key) &&
GetLengthPrefixedSlice(&input, &value)) {
handler->Put(key, value);
found++;
} else {
return Status::Corruption("bad WriteBatch Put");
}
break;
case kTypeDeletion:
if (GetLengthPrefixedSlice(&input, &key)) {
handler->Delete(key);
found++;
} else {
return Status::Corruption("bad WriteBatch Delete");
}
break;
case kTypeMerge:
if (GetLengthPrefixedSlice(&input, &key) &&
GetLengthPrefixedSlice(&input, &value)) {
handler->Merge(key, value);
found++;
} else {
return Status::Corruption("bad WriteBatch Merge");
}
break;
case kTypeLogData:
if (GetLengthPrefixedSlice(&input, &blob)) {
handler->LogData(blob);
} else {
return Status::Corruption("bad WriteBatch Blob");
}
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::Put(const SliceParts& key, const SliceParts& value) {
WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
rep_.push_back(static_cast<char>(kTypeValue));
PutLengthPrefixedSliceParts(&rep_, key);
PutLengthPrefixedSliceParts(&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);
}
void WriteBatch::PutLogData(const Slice& blob) {
rep_.push_back(static_cast<char>(kTypeLogData));
PutLengthPrefixedSlice(&rep_, blob);
}
namespace {
class MemTableInserter : public WriteBatch::Handler {
public:
SequenceNumber sequence_;
MemTable* mem_;
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_);
}
}
virtual void Put(const Slice& key, const Slice& value) {
if (!options_->inplace_update_support) {
mem_->Add(sequence_, kTypeValue, key, value);
} else if (options_->inplace_callback == nullptr) {
mem_->Update(sequence_, key, value);
RecordTick(options_->statistics.get(), NUMBER_KEYS_UPDATED);
} else {
if (mem_->UpdateCallback(sequence_, key, value, *options_)) {
} else {
// key not found in memtable. Do sst get, update, add
SnapshotImpl read_from_snapshot;
read_from_snapshot.number_ = sequence_;
ReadOptions ropts;
ropts.snapshot = &read_from_snapshot;
std::string prev_value;
std::string merged_value;
Status s = db_->Get(ropts, key, &prev_value);
char* prev_buffer = const_cast<char*>(prev_value.c_str());
uint32_t prev_size = prev_value.size();
auto status =
options_->inplace_callback(s.ok() ? prev_buffer: nullptr,
s.ok() ? &prev_size: nullptr,
value, &merged_value);
if (status == UpdateStatus::UPDATED_INPLACE) {
// prev_value is updated in-place with final value.
mem_->Add(sequence_, kTypeValue, key, Slice(prev_buffer, prev_size));
RecordTick(options_->statistics.get(), NUMBER_KEYS_WRITTEN);
} else if (status == UpdateStatus::UPDATED) {
// merged_value contains the final value.
mem_->Add(sequence_, kTypeValue, key, Slice(merged_value));
RecordTick(options_->statistics.get(), NUMBER_KEYS_WRITTEN);
}
}
}
// 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.
sequence_++;
}
virtual void Merge(const Slice& key, const Slice& value) {
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);
}
sequence_++;
}
virtual void Delete(const Slice& key) {
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)) {
RecordTick(options_->statistics.get(), NUMBER_FILTERED_DELETES);
return;
}
}
mem_->Add(sequence_, kTypeDeletion, key, Slice());
sequence_++;
}
};
} // namespace
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);
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 rocksdb