fb09ef05dc
Summary: There are situations when RocksDB tries to recover, but the db is in an inconsistent state due to SST files referenced in the MANIFEST being missing. In this case, previous RocksDB will just fail the recovery and return a non-ok status. This PR enables another possibility. During recovery, RocksDB checks possible MANIFEST files, and try to recover to the most recent state without missing table file. `VersionSet::Recover()` applies version edits incrementally and "materializes" a version only when this version does not reference any missing table file. After processing the entire MANIFEST, the version created last will be the latest version. `DBImpl::Recover()` calls `VersionSet::Recover()`. Afterwards, WAL replay will *not* be performed. To use this capability, set `options.best_efforts_recovery = true` when opening the db. Best-efforts recovery is currently incompatible with atomic flush. Test plan (on devserver): ``` $make check $COMPILE_WITH_ASAN=1 make all && make check ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/6334 Reviewed By: anand1976 Differential Revision: D19778960 Pulled By: riversand963 fbshipit-source-id: c27ea80f29bc952e7d3311ecf5ee9c54393b40a8
66 lines
2.2 KiB
C++
66 lines
2.2 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root 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.
|
|
//
|
|
#pragma once
|
|
|
|
#include <memory>
|
|
|
|
#include "rocksdb/file_system.h"
|
|
#include "rocksdb/slice_transform.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class TableCache;
|
|
class VersionStorageInfo;
|
|
class VersionEdit;
|
|
struct FileMetaData;
|
|
class InternalStats;
|
|
class Version;
|
|
class ColumnFamilyData;
|
|
|
|
// A helper class so we can efficiently apply a whole sequence
|
|
// of edits to a particular state without creating intermediate
|
|
// Versions that contain full copies of the intermediate state.
|
|
class VersionBuilder {
|
|
public:
|
|
VersionBuilder(const FileOptions& file_options, TableCache* table_cache,
|
|
VersionStorageInfo* base_vstorage, Logger* info_log = nullptr);
|
|
~VersionBuilder();
|
|
|
|
bool CheckConsistencyForNumLevels();
|
|
Status Apply(VersionEdit* edit);
|
|
Status SaveTo(VersionStorageInfo* vstorage);
|
|
Status LoadTableHandlers(InternalStats* internal_stats, int max_threads,
|
|
bool prefetch_index_and_filter_in_cache,
|
|
bool is_initial_load,
|
|
const SliceTransform* prefix_extractor);
|
|
|
|
private:
|
|
class Rep;
|
|
std::unique_ptr<Rep> rep_;
|
|
};
|
|
|
|
// A wrapper of version builder which references the current version in
|
|
// constructor and unref it in the destructor.
|
|
// Both of the constructor and destructor need to be called inside DB Mutex.
|
|
class BaseReferencedVersionBuilder {
|
|
public:
|
|
explicit BaseReferencedVersionBuilder(ColumnFamilyData* cfd);
|
|
BaseReferencedVersionBuilder(ColumnFamilyData* cfd, Version* v);
|
|
~BaseReferencedVersionBuilder();
|
|
VersionBuilder* version_builder() const { return version_builder_.get(); }
|
|
|
|
private:
|
|
std::unique_ptr<VersionBuilder> version_builder_;
|
|
Version* version_;
|
|
};
|
|
|
|
extern bool NewestFirstBySeqNo(FileMetaData* a, FileMetaData* b);
|
|
} // namespace ROCKSDB_NAMESPACE
|