014fd55adc
Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
77 lines
2.3 KiB
C++
77 lines
2.3 KiB
C++
// Copyright (c) 2015, 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.
|
|
|
|
#include "rocksdb/write_batch_base.h"
|
|
|
|
#include <string>
|
|
|
|
#include "rocksdb/slice.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
// Simple implementation of SlicePart variants of Put(). Child classes
|
|
// can override these method with more performant solutions if they choose.
|
|
void WriteBatchBase::Put(ColumnFamilyHandle* column_family,
|
|
const SliceParts& key, const SliceParts& value) {
|
|
std::string key_buf, value_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
Slice value_slice(value, &value_buf);
|
|
|
|
Put(column_family, key_slice, value_slice);
|
|
}
|
|
|
|
void WriteBatchBase::Put(const SliceParts& key, const SliceParts& value) {
|
|
std::string key_buf, value_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
Slice value_slice(value, &value_buf);
|
|
|
|
Put(key_slice, value_slice);
|
|
}
|
|
|
|
void WriteBatchBase::Delete(ColumnFamilyHandle* column_family,
|
|
const SliceParts& key) {
|
|
std::string key_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
Delete(column_family, key_slice);
|
|
}
|
|
|
|
void WriteBatchBase::Delete(const SliceParts& key) {
|
|
std::string key_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
Delete(key_slice);
|
|
}
|
|
|
|
void WriteBatchBase::SingleDelete(ColumnFamilyHandle* column_family,
|
|
const SliceParts& key) {
|
|
std::string key_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
SingleDelete(column_family, key_slice);
|
|
}
|
|
|
|
void WriteBatchBase::SingleDelete(const SliceParts& key) {
|
|
std::string key_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
SingleDelete(key_slice);
|
|
}
|
|
|
|
void WriteBatchBase::Merge(ColumnFamilyHandle* column_family,
|
|
const SliceParts& key, const SliceParts& value) {
|
|
std::string key_buf, value_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
Slice value_slice(value, &value_buf);
|
|
|
|
Merge(column_family, key_slice, value_slice);
|
|
}
|
|
|
|
void WriteBatchBase::Merge(const SliceParts& key, const SliceParts& value) {
|
|
std::string key_buf, value_buf;
|
|
Slice key_slice(key, &key_buf);
|
|
Slice value_slice(value, &value_buf);
|
|
|
|
Merge(key_slice, value_slice);
|
|
}
|
|
|
|
} // namespace rocksdb
|