You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/db/flush_job.h

196 lines
7.7 KiB

// 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/blob/blob_file_completion_callback.h"
#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,
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 = "",
BlobFileCompletionCallback* blob_callback = nullptr);
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
10 years ago
~FlushJob();
// Require db_mutex held.
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
7 years ago
// 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
// Return the IO status
IOStatus io_status() const { return io_status_; }
private:
void ReportStartedFlush();
void ReportFlushInputSize(const autovector<MemTable*>& mems);
void RecordFlushIOStats();
Status WriteLevel0Table();
Make mempurge a background process (equivalent to in-memory compaction). (#8505) Summary: In https://github.com/facebook/rocksdb/issues/8454, I introduced a new process baptized `MemPurge` (memtable garbage collection). This new PR is built upon this past mempurge prototype. In this PR, I made the `mempurge` process a background task, which provides superior performance since the mempurge process does not cling on the db_mutex anymore, and addresses severe restrictions from the past iteration (including a scenario where the past mempurge was failling, when a memtable was mempurged but was still referred to by an iterator/snapshot/...). Now the mempurge process ressembles an in-memory compaction process: the stack of immutable memtables is filtered out, and the useful payload is used to populate an output memtable. If the output memtable is filled at more than 60% capacity (arbitrary heuristic) the mempurge process is aborted and a regular flush process takes place, else the output memtable is kept in the immutable memtable stack. Note that adding this output memtable to the `imm()` memtable stack does not trigger another flush process, so that the flush thread can go to sleep at the end of a successful mempurge. MemPurge is activated by making the `experimental_allow_mempurge` flag `true`. When activated, the `MemPurge` process will always happen when the flush reason is `kWriteBufferFull`. The 3 unit tests confirm that this process supports `Put`, `Get`, `Delete`, `DeleteRange` operators and is compatible with `Iterators` and `CompactionFilters`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8505 Reviewed By: pdillinger Differential Revision: D29619283 Pulled By: bjlemaire fbshipit-source-id: 8a99bee76b63a8211bff1a00e0ae32360aaece95
3 years ago
// Memtable Garbage Collection algorithm: a MemPurge takes the list
// of immutable memtables and filters out (or "purge") the outdated bytes
// out of it. The output (the filtered bytes, or "useful payload") is
// then transfered into a new memtable. If this memtable is filled, then
// the mempurge is aborted and rerouted to a regular flush process. Else,
// depending on the heuristics, placed onto the immutable memtable list.
// The addition to the imm list will not trigger a flush operation. The
// flush of the imm list will instead be triggered once the mutable memtable
// is added to the imm list.
// This process is typically intended for workloads with heavy overwrites
// when we want to avoid SSD writes (and reads) as much as possible.
// "MemPurge" is an experimental feature still at a very early stage
// of development. At the moment it is only compatible with the Get, Put,
// Delete operations as well as Iterators and CompactionFilters.
// For this early version, "MemPurge" is called by setting the
// options.experimental_allow_mempurge flag as "true". When this is
// the case, ALL automatic flush operations (kWRiteBufferManagerFull) will
// first go through the MemPurge process. herefore, we strongly
// recommend all users not to set this flag as true given that the MemPurge
// process has not matured yet.
Status MemPurge();
#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_;
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_;
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_;
IOStatus io_status_;
const std::shared_ptr<IOTracer> io_tracer_;
SystemClock* clock_;
const std::string full_history_ts_low_;
BlobFileCompletionCallback* blob_callback_;
};
} // namespace ROCKSDB_NAMESPACE