|
|
|
// 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 <atomic>
|
|
|
|
#include <deque>
|
|
|
|
#include <limits>
|
|
|
|
#include <list>
|
|
|
|
#include <set>
|
|
|
|
#include <string>
|
|
|
|
#include <utility>
|
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
#include "db/column_family.h"
|
|
|
|
#include "db/dbformat.h"
|
|
|
|
#include "db/flush_scheduler.h"
|
|
|
|
#include "db/internal_stats.h"
|
|
|
|
#include "db/job_context.h"
|
|
|
|
#include "db/log_writer.h"
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
7 years ago
|
|
|
#include "db/logs_with_prep_tracker.h"
|
|
|
|
#include "db/memtable_list.h"
|
|
|
|
#include "db/snapshot_impl.h"
|
|
|
|
#include "db/version_edit.h"
|
|
|
|
#include "db/write_controller.h"
|
|
|
|
#include "db/write_thread.h"
|
|
|
|
#include "logging/event_logger.h"
|
|
|
|
#include "monitoring/instrumented_mutex.h"
|
|
|
|
#include "options/db_options.h"
|
|
|
|
#include "port/port.h"
|
|
|
|
#include "rocksdb/db.h"
|
|
|
|
#include "rocksdb/env.h"
|
|
|
|
#include "rocksdb/listener.h"
|
|
|
|
#include "rocksdb/memtablerep.h"
|
|
|
|
#include "rocksdb/transaction_log.h"
|
|
|
|
#include "table/scoped_arena_iterator.h"
|
|
|
|
#include "util/autovector.h"
|
|
|
|
#include "util/stop_watch.h"
|
|
|
|
#include "util/thread_local.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
7 years ago
|
|
|
class DBImpl;
|
|
|
|
class MemTable;
|
|
|
|
class SnapshotChecker;
|
|
|
|
class TableCache;
|
|
|
|
class Version;
|
|
|
|
class VersionEdit;
|
|
|
|
class VersionSet;
|
|
|
|
class Arena;
|
|
|
|
|
|
|
|
class FlushJob {
|
|
|
|
public:
|
|
|
|
// TODO(icanadi) make effort to reduce number of parameters here
|
|
|
|
// IMPORTANT: mutable_cf_options needs to be alive while FlushJob is alive
|
|
|
|
FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
|
|
|
|
const ImmutableDBOptions& db_options,
|
|
|
|
const MutableCFOptions& mutable_cf_options, uint64_t max_memtable_id,
|
|
|
|
const FileOptions& file_options, VersionSet* versions,
|
|
|
|
InstrumentedMutex* db_mutex, std::atomic<bool>* shutting_down,
|
|
|
|
std::vector<SequenceNumber> existing_snapshots,
|
Use SST files for Transaction conflict detection
Summary:
Currently, transactions can fail even if there is no actual write conflict. This is due to relying on only the memtables to check for write-conflicts. Users have to tune memtable settings to try to avoid this, but it's hard to figure out exactly how to tune these settings.
With this diff, TransactionDB will use both memtables and SST files to determine if there are any write conflicts. This relies on the fact that BlockBasedTable stores sequence numbers for all writes that happen after any open snapshot. Also, D50295 is needed to prevent SingleDelete from disappearing writes (the TODOs in this test code will be fixed once the other diff is approved and merged).
Note that Optimistic transactions will still rely on tuning memtable settings as we do not want to read from SST while on the write thread. Also, memtable settings can still be used to reduce how often TransactionDB needs to read SST files.
Test Plan: unit tests, db bench
Reviewers: rven, yhchiang, kradhakrishnan, IslamAbdelRahman, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb, yoshinorim
Differential Revision: https://reviews.facebook.net/D50475
9 years ago
|
|
|
SequenceNumber earliest_write_conflict_snapshot,
|
|
|
|
SnapshotChecker* snapshot_checker, JobContext* job_context,
|
|
|
|
LogBuffer* log_buffer, FSDirectory* db_directory,
|
|
|
|
FSDirectory* output_file_directory,
|
|
|
|
CompressionType output_compression, Statistics* stats,
|
|
|
|
EventLogger* event_logger, bool measure_io_stats,
|
|
|
|
const bool sync_output_directory, const bool write_manifest,
|
|
|
|
Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
|
|
|
|
const std::string& db_id = "", const std::string& db_session_id = "",
|
|
|
|
std::string full_history_ts_low = "");
|
|
|
|
|
|
|
|
~FlushJob();
|
|
|
|
|
|
|
|
// Require db_mutex held.
|
|
|
|
// Once PickMemTable() is called, either Run() or Cancel() has to be called.
|
|
|
|
void PickMemTable();
|
Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.
Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)
This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765
Differential Revision: D7747618
Pulled By: siying
fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
7 years ago
|
|
|
Status Run(LogsWithPrepTracker* prep_tracker = nullptr,
|
|
|
|
FileMetaData* file_meta = nullptr);
|
|
|
|
void Cancel();
|
|
|
|
const autovector<MemTable*>& GetMemTables() const { return mems_; }
|
|
|
|
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
std::list<std::unique_ptr<FlushJobInfo>>* GetCommittedFlushJobsInfo() {
|
|
|
|
return &committed_flush_jobs_info_;
|
|
|
|
}
|
|
|
|
#endif // !ROCKSDB_LITE
|
|
|
|
|
Pass IOStatus to write path and set retryable IO Error as hard error in BG jobs (#6487)
Summary:
In the current code base, we use Status to get and store the returned status from the call. Specifically, for IO related functions, the current Status cannot reflect the IO Error details such as error scope, error retryable attribute, and others. With the implementation of https://github.com/facebook/rocksdb/issues/5761, we have the new Wrapper for IO, which returns IOStatus instead of Status. However, the IOStatus is purged at the lower level of write path and transferred to Status.
The first job of this PR is to pass the IOStatus to the write path (flush, WAL write, and Compaction). The second job is to identify the Retryable IO Error as HardError, and set the bg_error_ as HardError. In this case, the DB Instance becomes read only. User is informed of the Status and need to take actions to deal with it (e.g., call db->Resume()).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6487
Test Plan: Added the testing case to error_handler_fs_test. Pass make asan_check
Reviewed By: anand1976
Differential Revision: D20685017
Pulled By: zhichao-cao
fbshipit-source-id: ff85f042896243abcd6ef37877834e26f36b6eb0
5 years ago
|
|
|
// Return the IO status
|
|
|
|
IOStatus io_status() const { return io_status_; }
|
|
|
|
|
|
|
|
private:
|
|
|
|
void ReportStartedFlush();
|
|
|
|
void ReportFlushInputSize(const autovector<MemTable*>& mems);
|
|
|
|
void RecordFlushIOStats();
|
|
|
|
Status WriteLevel0Table();
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
std::unique_ptr<FlushJobInfo> GetFlushJobInfo() const;
|
|
|
|
#endif // !ROCKSDB_LITE
|
|
|
|
|
|
|
|
const std::string& dbname_;
|
|
|
|
const std::string db_id_;
|
|
|
|
const std::string db_session_id_;
|
|
|
|
ColumnFamilyData* cfd_;
|
|
|
|
const ImmutableDBOptions& db_options_;
|
|
|
|
const MutableCFOptions& mutable_cf_options_;
|
|
|
|
// A variable storing the largest memtable id to flush in this
|
|
|
|
// flush job. RocksDB uses this variable to select the memtables to flush in
|
|
|
|
// this job. All memtables in this column family with an ID smaller than or
|
|
|
|
// equal to max_memtable_id_ will be selected for flush.
|
|
|
|
uint64_t max_memtable_id_;
|
Introduce a new storage specific Env API (#5761)
Summary:
The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc.
This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO.
The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before.
This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection.
The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761
Differential Revision: D18868376
Pulled By: anand1976
fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
5 years ago
|
|
|
const FileOptions file_options_;
|
|
|
|
VersionSet* versions_;
|
|
|
|
InstrumentedMutex* db_mutex_;
|
|
|
|
std::atomic<bool>* shutting_down_;
|
|
|
|
std::vector<SequenceNumber> existing_snapshots_;
|
Use SST files for Transaction conflict detection
Summary:
Currently, transactions can fail even if there is no actual write conflict. This is due to relying on only the memtables to check for write-conflicts. Users have to tune memtable settings to try to avoid this, but it's hard to figure out exactly how to tune these settings.
With this diff, TransactionDB will use both memtables and SST files to determine if there are any write conflicts. This relies on the fact that BlockBasedTable stores sequence numbers for all writes that happen after any open snapshot. Also, D50295 is needed to prevent SingleDelete from disappearing writes (the TODOs in this test code will be fixed once the other diff is approved and merged).
Note that Optimistic transactions will still rely on tuning memtable settings as we do not want to read from SST while on the write thread. Also, memtable settings can still be used to reduce how often TransactionDB needs to read SST files.
Test Plan: unit tests, db bench
Reviewers: rven, yhchiang, kradhakrishnan, IslamAbdelRahman, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb, yoshinorim
Differential Revision: https://reviews.facebook.net/D50475
9 years ago
|
|
|
SequenceNumber earliest_write_conflict_snapshot_;
|
|
|
|
SnapshotChecker* snapshot_checker_;
|
|
|
|
JobContext* job_context_;
|
|
|
|
LogBuffer* log_buffer_;
|
|
|
|
FSDirectory* db_directory_;
|
|
|
|
FSDirectory* output_file_directory_;
|
|
|
|
CompressionType output_compression_;
|
|
|
|
Statistics* stats_;
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
10 years ago
|
|
|
EventLogger* event_logger_;
|
|
|
|
TableProperties table_properties_;
|
|
|
|
bool measure_io_stats_;
|
|
|
|
// True if this flush job should call fsync on the output directory. False
|
|
|
|
// otherwise.
|
|
|
|
// Usually sync_output_directory_ is true. A flush job needs to call sync on
|
|
|
|
// the output directory before committing to the MANIFEST.
|
|
|
|
// However, an individual flush job does not have to call sync on the output
|
|
|
|
// directory if it is part of an atomic flush. After all flush jobs in the
|
|
|
|
// atomic flush succeed, call sync once on each distinct output directory.
|
|
|
|
const bool sync_output_directory_;
|
|
|
|
// True if this flush job should write to MANIFEST after successfully
|
|
|
|
// flushing memtables. False otherwise.
|
|
|
|
// Usually write_manifest_ is true. A flush job commits to the MANIFEST after
|
|
|
|
// flushing the memtables.
|
|
|
|
// However, an individual flush job cannot rashly write to the MANIFEST
|
|
|
|
// immediately after it finishes the flush if it is part of an atomic flush.
|
|
|
|
// In this case, only after all flush jobs succeed in flush can RocksDB
|
|
|
|
// commit to the MANIFEST.
|
|
|
|
const bool write_manifest_;
|
|
|
|
// The current flush job can commit flush result of a concurrent flush job.
|
|
|
|
// We collect FlushJobInfo of all jobs committed by current job and fire
|
|
|
|
// OnFlushCompleted for them.
|
|
|
|
std::list<std::unique_ptr<FlushJobInfo>> committed_flush_jobs_info_;
|
|
|
|
|
|
|
|
// Variables below are set by PickMemTable():
|
|
|
|
FileMetaData meta_;
|
|
|
|
autovector<MemTable*> mems_;
|
|
|
|
VersionEdit* edit_;
|
|
|
|
Version* base_;
|
|
|
|
bool pick_memtable_called;
|
|
|
|
Env::Priority thread_pri_;
|
Pass IOStatus to write path and set retryable IO Error as hard error in BG jobs (#6487)
Summary:
In the current code base, we use Status to get and store the returned status from the call. Specifically, for IO related functions, the current Status cannot reflect the IO Error details such as error scope, error retryable attribute, and others. With the implementation of https://github.com/facebook/rocksdb/issues/5761, we have the new Wrapper for IO, which returns IOStatus instead of Status. However, the IOStatus is purged at the lower level of write path and transferred to Status.
The first job of this PR is to pass the IOStatus to the write path (flush, WAL write, and Compaction). The second job is to identify the Retryable IO Error as HardError, and set the bg_error_ as HardError. In this case, the DB Instance becomes read only. User is informed of the Status and need to take actions to deal with it (e.g., call db->Resume()).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6487
Test Plan: Added the testing case to error_handler_fs_test. Pass make asan_check
Reviewed By: anand1976
Differential Revision: D20685017
Pulled By: zhichao-cao
fbshipit-source-id: ff85f042896243abcd6ef37877834e26f36b6eb0
5 years ago
|
|
|
IOStatus io_status_;
|
|
|
|
|
|
|
|
const std::shared_ptr<IOTracer> io_tracer_;
|
|
|
|
|
|
|
|
const std::string full_history_ts_low_;
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|