mirror of
https://github.com/Xahau/xahaud.git
synced 2025-12-06 17:27:52 +00:00
1fdd726 Hotfix RocksDB 3.5 d67500a Add `make install` to Makefile in 3.5.fb. 4cb631a update HISTORY.md cfd0946 comments about the BlockBasedTableOptions migration in Options REVERT: 25888ae Merge pull request #329 from fyrz/master REVERT: 89833e5 Fixed signed-unsigned comparison warning in db_test.cc REVERT: fcac705 Fixed compile warning on Mac caused by unused variables. REVERT: b3343fd resolution for java build problem introduced by 5ec53f3edf62bec1b690ce12fb21a6c52203f3c8 REVERT: 187b299 ForwardIterator: update prev_key_ only if prefix hasn't changed REVERT: 5ec53f3 make compaction related options changeable REVERT: d122e7b Update INSTALL.md REVERT: 986dad0 Merge pull request #324 from dalgaaf/wip-da-SCA-20140930 REVERT: 8ee75dc db/memtable.cc: remove unused variable merge_result REVERT: 0fd8bbc db/db_impl.cc: reduce scope of prefix_initialized REVERT: 676ff7b compaction_picker.cc: remove check for >=0 for unsigned REVERT: e55aea5 document_db.cc: fix assert REVERT: d517c83 in_table_factory.cc: use correct format specifier REVERT: b140375 ttl/ttl_test.cc: prefer prefix ++operator for non-primitive types REVERT: 43c789c spatialdb/spatial_db.cc: use !empty() instead of 'size() > 0' REVERT: 0de452e document_db.cc: pass const parameter by reference REVERT: 4cc8643 util/ldb_cmd.cc: prefer prefix ++operator for non-primitive types REVERT: af8c2b2 util/signal_test.cc: suppress intentional null pointer deref REVERT: 33580fa db/db_impl.cc: fix object handling, remove double lines REVERT: 873f135 db_ttl_impl.h: pass func parameter by reference REVERT: 8558457 ldb_cmd_execute_result.h: perform init in initialization list REVERT: 063471b table/table_test.cc: pass func parameter by reference REVERT: 93548ce table/cuckoo_table_reader.cc: pass func parameter by ref REVERT: b8b7117 db/version_set.cc: use !empty() instead of 'size() > 0' REVERT: 8ce050b table/bloom_block.*: pass func parameter by reference REVERT: 53910dd db_test.cc: pass parameter by reference REVERT: 68ca534 corruption_test.cc: pass parameter by reference REVERT: 7506198 cuckoo_table_db_test.cc: add flush after delete REVERT: 1f96330 Print MB per second compaction throughput separately for reads and writes REVERT: ffe3d49 Add an instruction about SSE in INSTALL.md REVERT: ee1f3cc Package generation for Ubuntu and CentOS REVERT: f0f7955 Fixing comile errors on OS X REVERT: 99fb613 remove 2 space linter REVERT: b2d64a4 Fix linters, second try REVERT: 747523d Print per column family metrics in db_bench REVERT: 56ebd40 Fix arc lint (should fix #238) REVERT: 637f891 Merge pull request #321 from eonnen/master REVERT: 827e31c Make test use a compatible type in the size checks. REVERT: fd5d80d CompactedDB: log using the correct info_log REVERT: 2faf49d use GetContext to replace callback function pointer REVERT: 983d2de Add AUTHORS file. Fix #203 REVERT: abd70c5 Merge pull request #316 from fyrz/ReverseBytewiseComparator REVERT: 2dc6f62 handle kDelete type in cuckoo builder REVERT: 8b8011a Changed name of ReverseBytewiseComparator based on review comment REVERT: 389edb6 universal compaction picker: use double for potential overflow REVERT: 5340484 Built-in comparator(s) in RocksJava REVERT: d439451 delay initialization of cuckoo table iterator REVERT: 94997ea reduce memory usage of cuckoo table builder REVERT: c627595 improve memory efficiency of cuckoo reader REVERT: 581442d option to choose module when calculating CuckooTable hash REVERT: fbd2daf CompactedDBImpl::MultiGet() for better CuckooTable performance REVERT: 3c68006 CompactedDBImpl REVERT: f7375f3 Fix double deletes REVERT: 21ddcf6 Remove allow_thread_local REVERT: fb4a492 Merge pull request #311 from ankgup87/master REVERT: 611e286 Merge branch 'master' of https://github.com/facebook/rocksdb REVERT: 0103b44 Merge branch 'master' of ssh://github.com/ankgup87/rocksdb REVERT: 1dfb7bb Add block based table config options REVERT: cdaf44f Enlarge log size cap when printing file summary REVERT: 7cc1ed7 Merge pull request #309 from naveenatceg/staticbuild REVERT: ba6d660 Resolving merge conflict REVERT: 51eeaf6 Addressing review comments REVERT: fd7d3fe Addressing review comments (adding a env variable to override temp directory) REVERT: cf7ace8 Addressing review comments REVERT: 0a29ce5 re-enable BlockBasedTable::SetupForCompaction() REVERT: 55af370 Remove TODO for checking index checksums REVERT: 3d74f09 Fix compile REVERT: 53b0039 Fix release compile REVERT: d0de413 WriteBatchWithIndex to allow different Comparators for different column families REVERT: 57a32f1 change target_file_size_base to uint64_t REVERT: 5e6aee4 dont create backup_input if compaction filter v2 is not used REVERT: 49b5f94 Merge pull request #306 from Liuchang0812/fix_cast REVERT: 787cb4d remove cast, replace %llu with % PRIu64 REVERT: a7574d4 Update logging.cc REVERT: 7e0dcb9 Update logging.cc REVERT: 57fa3cc Merge pull request #304 from Liuchang0812/fix-check REVERT: cd44522 Merge pull request #305 from Liuchang0812/fix-logging REVERT: 6a031b6 remove unused variable REVERT: 4436f17 fixed #303: replace %ld with % PRId64 REVERT: 7a1bd05 Merge pull request #302 from ankgup87/master REVERT: 423e52c Merge branch 'master' of https://github.com/facebook/rocksdb REVERT: bfeef94 Add rate limiter REVERT: 32f2532 Print compression_size_percent as a signed int REVERT: 976caca Skip AllocateTest if fallocate() is not supported in the file system REVERT: 3b897cd Enable no-fbcode RocksDB build REVERT: f445947 RocksDB: Format uint64 using PRIu64 in db_impl.cc REVERT: e17bc65 Merge pull request #299 from ankgup87/master REVERT: b93797a Fix build REVERT: adae3ca [Java] Fix JNI link error caused by the removal of options.db_stats_log_interval REVERT: 90b8c07 Fix unit tests errors REVERT: 51af7c3 CuckooTable: add one option to allow identity function for the first hash function REVERT: 0350435 Fixed a signed-unsigned comparison in spatial_db.cc -- issue #293 REVERT: 2fb1fea Fix syncronization issues REVERT: ff76895 Remove some unnecessary constructors REVERT: feadb9d fix cuckoo table builder test REVERT: 3c232e1 Fix mac compile REVERT: 54cada9 Run make format on PR #249 REVERT: 27b22f1 Merge pull request #249 from tdfischer/decompression-refactoring REVERT: fb6456b Replace naked calls to operator new and delete (Fixes #222) REVERT: 5600c8f cuckoo table: return estimated size - 1 REVERT: a062e1f SetOptions() for memtable related options REVERT: e4eca6a Options conversion function for convenience REVERT: a7c2094 Merge pull request #292 from saghmrossi/master REVERT: 4d05234 Merge branch 'master' of github.com:saghmrossi/rocksdb REVERT: 60a4aa1 Test use_mmap_reads REVERT: 94e43a1 [Java] Fixed 32-bit overflowing issue when converting jlong to size_t REVERT: f9eaaa6 added include for inttypes.h to fix nonworking printf statements REVERT: f090575 Replaced "built on on earlier work" by "built on earlier work" in README.md REVERT: faad439 Fix #284 REVERT: 49aacd8 Fix make install REVERT: acb9348 [Java] Include WriteBatch into RocksDBSample.java, fix how DbBenchmark.java handles WriteBatch. REVERT: 4a27a2f Don't sync manifest when disableDataSync = true REVERT: 9b8480d Merge pull request #287 from yinqiwen/rate-limiter-crash-fix REVERT: 28be16b fix rate limiter crash #286 REVERT: 04ce1b2 Fix #284 REVERT: add22e3 standardize scripts to run RocksDB benchmarks REVERT: dee91c2 WriteThread REVERT: 540a257 Fix WAL synced REVERT: 24f034b Merge pull request #282 from Chilledheart/develop REVERT: 49fe329 Fix build issue under macosx REVERT: ebb5c65 Add make install REVERT: 0352a9f add_wrapped_bloom_test REVERT: 9c0e66c Don't run background jobs (flush, compactions) when bg_error_ is set REVERT: a9639bd Fix valgrind test REVERT: d1f24dc Relax FlushSchedule test REVERT: 3d9e6f7 Push model for flushing memtables REVERT: 059e584 [unit test] CompactRange should fail if we don't have space REVERT: dd641b2 fix RocksDB java build REVERT: 53404d9 add_qps_info_in cache bench REVERT: a52cecb Fix Mac compile REVERT: 092f97e Fix comments and typos REVERT: 6cc1286 Added a few statistics for BackupableDB REVERT: 0a42295 Fix SimpleWriteTimeoutTest REVERT: 06d9862 Always pass MergeContext as pointer, not reference REVERT: d343c3f Improve db recovery REVERT: 6bb7e3e Merger test REVERT: 88841bd Explicitly cast char to signed char in Hash() REVERT: 5231146 MemTableOptions REVERT: 1d284db Addressing review comments REVERT: 55114e7 Some updates for SpatialDB REVERT: 171d4ff remove TailingIterator reference in db_impl.h REVERT: 9b0f7ff rename version_set options_ to db_options_ to avoid confusion REVERT: 2d57828 Check stop level trigger-0 before slowdown level-0 trigger REVERT: 659d2d5 move compaction_filter to immutable_options REVERT: 048560a reduce references to cfd->options() in DBImpl REVERT: 011241b DB::Flush() Do not wait for background threads when there is nothing in mem table REVERT: a2bb7c3 Push- instead of pull-model for managing Write stalls REVERT: 0af157f Implement full filter for block based table. REVERT: 9360cc6 Fix valgrind issue REVERT: 02d5bff Merge pull request #277 from wankai/master REVERT: 88a2f44 fix comments REVERT: 7c16e39 Merge pull request #276 from wankai/master REVERT: 8237738 replace hard-coded number with named variable REVERT: db8ca52 Merge pull request #273 from nbougalis/static-analysis REVERT: b7b031f Merge pull request #274 from wankai/master REVERT: 4c2b1f0 Merge remote-tracking branch 'upstream/master' REVERT: a5d2863 typo improvement REVERT: 9f8aa09 Don't leak data returned by opendir REVERT: d1cfb71 Remove unused member(s) REVERT: bfee319 sizeof(int*) where sizeof(int) was intended REVERT: d40c1f7 Add missing break statement REVERT: 2e97c38 Avoid off-by-one error when using readlink REVERT: 40ddc3d add cache bench REVERT: 9f1c80b Drop column family from write thread REVERT: 8de151b Add db_bench with lots of column families to regression tests REVERT: c9e419c rename options_ to db_options_ in DBImpl to avoid confusion REVERT: 5cd0576 Fix compaction bug in Cuckoo Table Builder. Use kvs_.size() instead of num_entries in FileSize() method. REVERT: 0fbb3fa fixed memory leak in unit test DBIteratorBoundTest REVERT: adcd253 fix asan check REVERT: 4092b7a Merge pull request #272 from project-zerus/patch-1 REVERT: bb6ae0f fix more compile warnings REVERT: 6d31441 Merge pull request #271 from nbougalis/cleanups REVERT: 0cd0ec4 Plug memory leak during index creation REVERT: 4329d74 Fix swapped variable names to accurately reflect usage REVERT: 45a5e3e Remove path with arena==nullptr from NewInternalIterator REVERT: 5665e5e introduce ImmutableOptions REVERT: e0b99d4 created a new ReadOptions parameter 'iterate_upper_bound' REVERT: 51ea889 Fix travis builds REVERT: a481626 Relax backupable rate limiting test REVERT: f7f973d Merge pull request #269 from huahang/patch-2 REVERT: ef5b384 fix a few compile warnings REVERT: 2fd3806 Merge pull request #263 from wankai/master REVERT: 1785114 delete unused Comparator REVERT: 1b1d961 update HISTORY.md REVERT: 703c3ea comments about the BlockBasedTableOptions migration in Options REVERT: 4b5ad88 Merge pull request #260 from wankai/master REVERT: 19cc588 change to filter_block std::unique_ptr support RAII REVERT: 9b976e3 Merge pull request #259 from wankai/master REVERT: 5d25a46 Merge remote-tracking branch 'upstream/master' REVERT: dff2b1a typo improvement REVERT: 343e98a Reverting import change REVERT: ddb8039 RocksDB static build Make file changes to download and build the dependencies .Load the shared library when RocksDB is initialized git-subtree-dir: src/rocksdb2 git-subtree-split: 1fdd726a8254c13d0c66d8db8130ad17c13d7bcc
523 lines
17 KiB
C++
523 lines
17 KiB
C++
// 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
|
|
// kTypeColumnFamilyValue varint32 varstring varstring
|
|
// kTypeColumnFamilyMerge varint32 varstring varstring
|
|
// kTypeColumnFamilyDeletion varint32 varstring 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/column_family.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::Put(const Slice& key, const Slice& value) {
|
|
// you need to either implement Put or PutCF
|
|
throw std::runtime_error("Handler::Put not implemented!");
|
|
}
|
|
|
|
void WriteBatch::Handler::Merge(const Slice& key, const Slice& value) {
|
|
throw std::runtime_error("Handler::Merge not implemented!");
|
|
}
|
|
|
|
void WriteBatch::Handler::Delete(const Slice& key) {
|
|
// you need to either implement Delete or DeleteCF
|
|
throw std::runtime_error("Handler::Delete 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 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();
|
|
}
|
|
|
|
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;
|
|
Status s;
|
|
while (s.ok() && !input.empty() && handler->Continue()) {
|
|
char tag = 0;
|
|
uint32_t column_family = 0; // default
|
|
|
|
s = ReadRecordFromWriteBatch(&input, &tag, &column_family, &key, &value,
|
|
&blob);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
|
|
switch (tag) {
|
|
case kTypeColumnFamilyValue:
|
|
case kTypeValue:
|
|
s = handler->PutCF(column_family, key, value);
|
|
found++;
|
|
break;
|
|
case kTypeColumnFamilyDeletion:
|
|
case kTypeDeletion:
|
|
s = handler->DeleteCF(column_family, key);
|
|
found++;
|
|
break;
|
|
case kTypeColumnFamilyMerge:
|
|
case kTypeMerge:
|
|
s = handler->MergeCF(column_family, key, value);
|
|
found++;
|
|
break;
|
|
case kTypeLogData:
|
|
handler->LogData(blob);
|
|
break;
|
|
default:
|
|
return Status::Corruption("unknown WriteBatch tag");
|
|
}
|
|
}
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
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 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);
|
|
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);
|
|
}
|
|
PutLengthPrefixedSliceParts(&b->rep_, key);
|
|
PutLengthPrefixedSliceParts(&b->rep_, value);
|
|
}
|
|
|
|
void WriteBatch::Put(ColumnFamilyHandle* column_family, const SliceParts& key,
|
|
const SliceParts& value) {
|
|
WriteBatchInternal::Put(this, GetColumnFamilyID(column_family), key, value);
|
|
}
|
|
|
|
void WriteBatchInternal::Delete(WriteBatch* b, uint32_t column_family_id,
|
|
const Slice& 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);
|
|
}
|
|
PutLengthPrefixedSlice(&b->rep_, key);
|
|
}
|
|
|
|
void WriteBatch::Delete(ColumnFamilyHandle* column_family, const Slice& key) {
|
|
WriteBatchInternal::Delete(this, GetColumnFamilyID(column_family), key);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
void WriteBatchInternal::Merge(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>(kTypeMerge));
|
|
} else {
|
|
b->rep_.push_back(static_cast<char>(kTypeColumnFamilyMerge));
|
|
PutVarint32(&b->rep_, column_family_id);
|
|
}
|
|
PutLengthPrefixedSlice(&b->rep_, key);
|
|
PutLengthPrefixedSlice(&b->rep_, value);
|
|
}
|
|
|
|
void WriteBatch::Merge(ColumnFamilyHandle* column_family, const Slice& key,
|
|
const Slice& value) {
|
|
WriteBatchInternal::Merge(this, GetColumnFamilyID(column_family), key, 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_;
|
|
ColumnFamilyMemTables* cf_mems_;
|
|
bool ignore_missing_column_families_;
|
|
uint64_t log_number_;
|
|
DBImpl* db_;
|
|
const bool dont_filter_deletes_;
|
|
|
|
MemTableInserter(SequenceNumber sequence, ColumnFamilyMemTables* cf_mems,
|
|
bool ignore_missing_column_families, uint64_t log_number,
|
|
DB* db, const bool dont_filter_deletes)
|
|
: sequence_(sequence),
|
|
cf_mems_(cf_mems),
|
|
ignore_missing_column_families_(ignore_missing_column_families),
|
|
log_number_(log_number),
|
|
db_(reinterpret_cast<DBImpl*>(db)),
|
|
dont_filter_deletes_(dont_filter_deletes) {
|
|
assert(cf_mems);
|
|
if (!dont_filter_deletes_) {
|
|
assert(db_);
|
|
}
|
|
}
|
|
|
|
bool SeekToColumnFamily(uint32_t column_family_id, Status* s) {
|
|
bool found = cf_mems_->Seek(column_family_id);
|
|
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)
|
|
// * 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,
|
|
const Slice& value) {
|
|
Status seek_status;
|
|
if (!SeekToColumnFamily(column_family_id, &seek_status)) {
|
|
++sequence_;
|
|
return seek_status;
|
|
}
|
|
MemTable* mem = cf_mems_->GetMemTable();
|
|
const Options* options = cf_mems_->GetOptions();
|
|
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;
|
|
|
|
auto cf_handle = cf_mems_->GetColumnFamilyHandle();
|
|
if (cf_handle == nullptr) {
|
|
cf_handle = db_->DefaultColumnFamily();
|
|
}
|
|
Status s = db_->Get(ropts, cf_handle, 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_++;
|
|
return Status::OK();
|
|
}
|
|
|
|
virtual Status MergeCF(uint32_t column_family_id, const Slice& key,
|
|
const Slice& value) {
|
|
Status seek_status;
|
|
if (!SeekToColumnFamily(column_family_id, &seek_status)) {
|
|
++sequence_;
|
|
return seek_status;
|
|
}
|
|
MemTable* mem = cf_mems_->GetMemTable();
|
|
const Options* options = cf_mems_->GetOptions();
|
|
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;
|
|
|
|
auto cf_handle = cf_mems_->GetColumnFamilyHandle();
|
|
if (cf_handle == nullptr) {
|
|
cf_handle = db_->DefaultColumnFamily();
|
|
}
|
|
db_->Get(read_options, cf_handle, 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_++;
|
|
return Status::OK();
|
|
}
|
|
|
|
virtual Status DeleteCF(uint32_t column_family_id, const Slice& key) {
|
|
Status seek_status;
|
|
if (!SeekToColumnFamily(column_family_id, &seek_status)) {
|
|
++sequence_;
|
|
return seek_status;
|
|
}
|
|
MemTable* mem = cf_mems_->GetMemTable();
|
|
const Options* options = cf_mems_->GetOptions();
|
|
if (!dont_filter_deletes_ && options->filter_deletes) {
|
|
SnapshotImpl read_from_snapshot;
|
|
read_from_snapshot.number_ = sequence_;
|
|
ReadOptions ropts;
|
|
ropts.snapshot = &read_from_snapshot;
|
|
std::string value;
|
|
auto cf_handle = cf_mems_->GetColumnFamilyHandle();
|
|
if (cf_handle == nullptr) {
|
|
cf_handle = db_->DefaultColumnFamily();
|
|
}
|
|
if (!db_->KeyMayExist(ropts, cf_handle, key, &value)) {
|
|
RecordTick(options->statistics.get(), NUMBER_FILTERED_DELETES);
|
|
return Status::OK();
|
|
}
|
|
}
|
|
mem->Add(sequence_, kTypeDeletion, key, Slice());
|
|
sequence_++;
|
|
return Status::OK();
|
|
}
|
|
};
|
|
} // namespace
|
|
|
|
Status WriteBatchInternal::InsertInto(const WriteBatch* b,
|
|
ColumnFamilyMemTables* memtables,
|
|
bool ignore_missing_column_families,
|
|
uint64_t log_number, DB* db,
|
|
const bool dont_filter_deletes) {
|
|
MemTableInserter inserter(WriteBatchInternal::Sequence(b), memtables,
|
|
ignore_missing_column_families, log_number, db,
|
|
dont_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
|