9a357847eb
Summary: LevelDB should delete almost-new keys when a long-open snapshot exists. The previous behavior is to keep all versions that were created after the oldest open snapshot. This can lead to database size bloat for high-update workloads when there are long-open snapshots and long-open snapshot will be used for logical backup. By "almost new" I mean that the key was updated more than once after the oldest snapshot. If there were two snapshots with seq numbers s1 and s2 (s1 < s2), and if we find two instances of the same key k1 that lie entirely within s1 and s2 (i.e. s1 < k1 < s2), then the earlier version of k1 can be safely deleted because that version is not visible in any snapshot. Test Plan: unit test attached make clean check Differential Revision: https://reviews.facebook.net/D6999
82 lines
2.1 KiB
C++
82 lines
2.1 KiB
C++
// 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.
|
|
|
|
#ifndef STORAGE_LEVELDB_DB_SNAPSHOT_H_
|
|
#define STORAGE_LEVELDB_DB_SNAPSHOT_H_
|
|
|
|
#include "leveldb/db.h"
|
|
|
|
namespace leveldb {
|
|
|
|
class SnapshotList;
|
|
|
|
// Snapshots are kept in a doubly-linked list in the DB.
|
|
// Each SnapshotImpl corresponds to a particular sequence number.
|
|
class SnapshotImpl : public Snapshot {
|
|
public:
|
|
SequenceNumber number_; // const after creation
|
|
|
|
private:
|
|
friend class SnapshotList;
|
|
|
|
// SnapshotImpl is kept in a doubly-linked circular list
|
|
SnapshotImpl* prev_;
|
|
SnapshotImpl* next_;
|
|
|
|
SnapshotList* list_; // just for sanity checks
|
|
};
|
|
|
|
class SnapshotList {
|
|
public:
|
|
SnapshotList() {
|
|
list_.prev_ = &list_;
|
|
list_.next_ = &list_;
|
|
list_.number_ = 0xFFFFFFFFL; // placeholder marker, for debugging
|
|
}
|
|
|
|
bool empty() const { return list_.next_ == &list_; }
|
|
SnapshotImpl* oldest() const { assert(!empty()); return list_.next_; }
|
|
SnapshotImpl* newest() const { assert(!empty()); return list_.prev_; }
|
|
|
|
const SnapshotImpl* New(SequenceNumber seq) {
|
|
SnapshotImpl* s = new SnapshotImpl;
|
|
s->number_ = seq;
|
|
s->list_ = this;
|
|
s->next_ = &list_;
|
|
s->prev_ = list_.prev_;
|
|
s->prev_->next_ = s;
|
|
s->next_->prev_ = s;
|
|
return s;
|
|
}
|
|
|
|
void Delete(const SnapshotImpl* s) {
|
|
assert(s->list_ == this);
|
|
s->prev_->next_ = s->next_;
|
|
s->next_->prev_ = s->prev_;
|
|
delete s;
|
|
}
|
|
|
|
// retrieve all snapshot numbers. They are sorted in ascending order.
|
|
void getAll(std::vector<SequenceNumber>& ret) {
|
|
SnapshotImpl* s = &list_;
|
|
SequenceNumber prev;
|
|
prev = 0;
|
|
if (empty()) return;
|
|
while (s->next_ != &list_) {
|
|
assert(prev <= s->next_->number_);
|
|
assert(prev = s->next_->number_); // assignment
|
|
ret.push_back(s->next_->number_);
|
|
s = s ->next_;
|
|
}
|
|
}
|
|
|
|
private:
|
|
// Dummy head of doubly-linked list of snapshots
|
|
SnapshotImpl list_;
|
|
};
|
|
|
|
} // namespace leveldb
|
|
|
|
#endif // STORAGE_LEVELDB_DB_SNAPSHOT_H_
|