rocksdb/db/compaction/compaction_job.h

211 lines
7.6 KiB
C
Raw Normal View History

// 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 <functional>
#include <limits>
#include <set>
#include <string>
#include <utility>
#include <vector>
#include "db/column_family.h"
#include "db/compaction/compaction_iterator.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"
#include "db/memtable_list.h"
#include "db/range_del_aggregator.h"
#include "db/version_edit.h"
#include "db/write_controller.h"
#include "db/write_thread.h"
#include "logging/event_logger.h"
#include "options/cf_options.h"
#include "options/db_options.h"
#include "port/port.h"
#include "rocksdb/compaction_filter.h"
#include "rocksdb/compaction_job_stats.h"
#include "rocksdb/db.h"
#include "rocksdb/env.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 {
class Arena;
class ErrorHandler;
class MemTable;
class SnapshotChecker;
class SystemClock;
class TableCache;
class Version;
class VersionEdit;
class VersionSet;
// CompactionJob is responsible for executing the compaction. Each (manual or
// automated) compaction corresponds to a CompactionJob object, and usually
// goes through the stages of `Prepare()`->`Run()`->`Install()`. CompactionJob
// will divide the compaction into subcompactions and execute them in parallel
// if needed.
class CompactionJob {
public:
CompactionJob(
int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
const FileOptions& file_options, VersionSet* versions,
const std::atomic<bool>* shutting_down,
const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
FSDirectory* db_directory, FSDirectory* output_directory,
FSDirectory* blob_output_directory, Statistics* stats,
InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
std::vector<SequenceNumber> existing_snapshots,
SequenceNumber earliest_write_conflict_snapshot,
const SnapshotChecker* snapshot_checker,
std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
bool paranoid_file_checks, bool measure_io_stats,
const std::string& dbname, CompactionJobStats* compaction_job_stats,
Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
Disable manual compaction during `ReFitLevel()` (#7250) Summary: Manual compaction with `CompactRangeOptions::change_levels` set could refit to a level targeted by another manual compaction. If force_consistency_checks were disabled, it could be possible for overlapping files to be written at that target level. This PR prevents the possibility by calling `DisableManualCompaction()` prior to `ReFitLevel()`. It also improves the manual compaction disabling mechanism to wait for pending manual compactions to complete before returning, and support disabling from multiple threads. Fixes https://github.com/facebook/rocksdb/issues/6432. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7250 Test Plan: crash test command that repro'd the bug reliably: ``` $ TEST_TMPDIR=/dev/shm python tools/db_crashtest.py blackbox --simple -target_file_size_base=524288 -write_buffer_size=1048576 -clear_column_family_one_in=0 -reopen=0 -max_key=10000000 -column_families=1 -max_background_compactions=8 -compact_range_one_in=100000 -compression_type=none -compaction_style=1 -num_levels=5 -universal_min_merge_width=4 -universal_max_merge_width=8 -level0_file_num_compaction_trigger=12 -rate_limiter_bytes_per_sec=1048576000 -universal_max_size_amplification_percent=100 --duration=3600 --interval=60 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --enable_compaction_filter=0 ``` Reviewed By: ltamasi Differential Revision: D23090800 Pulled By: ajkr fbshipit-source-id: afcbcd51b42ce76789fdb907d8b9ada790709c13
2020-08-14 20:28:12 +02:00
const std::atomic<int>* manual_compaction_paused = nullptr,
const std::string& db_id = "", const std::string& db_session_id = "",
std::string full_history_ts_low = "");
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
2015-03-13 18:45:40 +01:00
~CompactionJob();
// no copy/move
CompactionJob(CompactionJob&& job) = delete;
CompactionJob(const CompactionJob& job) = delete;
CompactionJob& operator=(const CompactionJob& job) = delete;
// REQUIRED: mutex held
// Prepare for the compaction by setting up boundaries for each subcompaction
void Prepare();
// REQUIRED mutex not held
// Launch threads for each subcompaction and wait for them to finish. After
// that, verify table is usable and finally do bookkeeping to unify
// subcompaction results
Status Run();
Parallelize L0-L1 Compaction: Restructure Compaction Job Summary: As of now compactions involving files from Level 0 and Level 1 are single threaded because the files in L0, although sorted, are not range partitioned like the other levels. This means that during L0-L1 compaction each file from L1 needs to be merged with potentially all the files from L0. This attempt to parallelize the L0-L1 compaction assigns a thread and a corresponding iterator to each L1 file that then considers only the key range found in that L1 file and only the L0 files that have those keys (and only the specific portion of those L0 files in which those keys are found). In this way the overlap is minimized and potentially eliminated between different iterators focusing on the same files. The first step is to restructure the compaction logic to break L0-L1 compactions into multiple, smaller, sequential compactions. Eventually each of these smaller jobs will be run simultaneously. Areas to pay extra attention to are # Correct aggregation of compaction job statistics across multiple threads # Proper opening/closing of output files (make sure each thread's is unique) # Keys that span multiple L1 files # Skewed distributions of keys within L0 files Test Plan: Make and run db_test (newer version has separate compaction tests) and compaction_job_stats_test Reviewers: igor, noetzli, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: MarkCallaghan, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D42699
2015-08-03 20:32:14 +02:00
// REQUIRED: mutex held
// Add compaction input/output to the current version
Status Install(const MutableCFOptions& mutable_cf_options);
// Return the IO status
IOStatus io_status() const { return io_status_; }
private:
struct SubcompactionState;
void AggregateStatistics();
// Generates a histogram representing potential divisions of key ranges from
// the input. It adds the starting and/or ending keys of certain input files
// to the working set and then finds the approximate size of data in between
// each consecutive pair of slices. Then it divides these ranges into
// consecutive groups such that each group has a similar size.
void GenSubcompactionBoundaries();
Parallelize L0-L1 Compaction: Restructure Compaction Job Summary: As of now compactions involving files from Level 0 and Level 1 are single threaded because the files in L0, although sorted, are not range partitioned like the other levels. This means that during L0-L1 compaction each file from L1 needs to be merged with potentially all the files from L0. This attempt to parallelize the L0-L1 compaction assigns a thread and a corresponding iterator to each L1 file that then considers only the key range found in that L1 file and only the L0 files that have those keys (and only the specific portion of those L0 files in which those keys are found). In this way the overlap is minimized and potentially eliminated between different iterators focusing on the same files. The first step is to restructure the compaction logic to break L0-L1 compactions into multiple, smaller, sequential compactions. Eventually each of these smaller jobs will be run simultaneously. Areas to pay extra attention to are # Correct aggregation of compaction job statistics across multiple threads # Proper opening/closing of output files (make sure each thread's is unique) # Keys that span multiple L1 files # Skewed distributions of keys within L0 files Test Plan: Make and run db_test (newer version has separate compaction tests) and compaction_job_stats_test Reviewers: igor, noetzli, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: MarkCallaghan, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D42699
2015-08-03 20:32:14 +02:00
Allow GetThreadList() to report basic compaction operation properties. Summary: Now we're able to show more details about a compaction in GetThreadList() :) This patch allows GetThreadList() to report basic compaction operation properties. Basic compaction properties include: 1. job id 2. compaction input / output level 3. compaction property flags (is_manual, is_deletion, .. etc) 4. total input bytes 5. the number of bytes has been read currently. 6. the number of bytes has been written currently. Flush operation properties will be done in a seperate diff. Test Plan: /db_bench --threads=30 --num=1000000 --benchmarks=fillrandom --thread_status_per_interval=1 Sample output of tracking same job: ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 31.357 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 59.440 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 226.375 ms CompactionJob::Install BaseInputLevel 1 | BytesRead 3958013 | BytesWritten 3621940 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37653
2015-05-07 07:50:35 +02:00
// update the thread status for starting a compaction.
void ReportStartedCompaction(Compaction* compaction);
void AllocateCompactionOutputFileNumbers();
// Call compaction filter. Then iterate through input and compact the
// kv-pairs
void ProcessKeyValueCompaction(SubcompactionState* sub_compact);
Status FinishCompactionOutputFile(
const Status& input_status, SubcompactionState* sub_compact,
CompactionRangeDelAggregator* range_del_agg,
CompactionIterationStats* range_del_out_stats,
const Slice* next_table_min_key = nullptr);
Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
void RecordCompactionIOStats();
Status OpenCompactionOutputFile(SubcompactionState* sub_compact);
void CleanupCompaction();
void UpdateCompactionJobStats(
const InternalStats::CompactionStats& stats) const;
void RecordDroppedKeys(const CompactionIterationStats& c_iter_stats,
CompactionJobStats* compaction_job_stats = nullptr);
void UpdateCompactionStats();
void UpdateCompactionInputStatsHelper(
int* num_files, uint64_t* bytes_read, int input_level);
void LogCompaction();
int job_id_;
// CompactionJob state
struct CompactionState;
CompactionState* compact_;
CompactionJobStats* compaction_job_stats_;
InternalStats::CompactionStats compaction_stats_;
// DBImpl state
const std::string& dbname_;
const std::string db_id_;
const std::string db_session_id_;
const ImmutableDBOptions& db_options_;
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
2019-12-13 23:47:08 +01:00
const FileOptions file_options_;
Env* env_;
std::shared_ptr<SystemClock> clock_;
std::shared_ptr<IOTracer> io_tracer_;
FileSystemPtr fs_;
// env_option optimized for compaction table reads
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
2019-12-13 23:47:08 +01:00
FileOptions file_options_for_read_;
VersionSet* versions_;
const std::atomic<bool>* shutting_down_;
Disable manual compaction during `ReFitLevel()` (#7250) Summary: Manual compaction with `CompactRangeOptions::change_levels` set could refit to a level targeted by another manual compaction. If force_consistency_checks were disabled, it could be possible for overlapping files to be written at that target level. This PR prevents the possibility by calling `DisableManualCompaction()` prior to `ReFitLevel()`. It also improves the manual compaction disabling mechanism to wait for pending manual compactions to complete before returning, and support disabling from multiple threads. Fixes https://github.com/facebook/rocksdb/issues/6432. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7250 Test Plan: crash test command that repro'd the bug reliably: ``` $ TEST_TMPDIR=/dev/shm python tools/db_crashtest.py blackbox --simple -target_file_size_base=524288 -write_buffer_size=1048576 -clear_column_family_one_in=0 -reopen=0 -max_key=10000000 -column_families=1 -max_background_compactions=8 -compact_range_one_in=100000 -compression_type=none -compaction_style=1 -num_levels=5 -universal_min_merge_width=4 -universal_max_merge_width=8 -level0_file_num_compaction_trigger=12 -rate_limiter_bytes_per_sec=1048576000 -universal_max_size_amplification_percent=100 --duration=3600 --interval=60 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --enable_compaction_filter=0 ``` Reviewed By: ltamasi Differential Revision: D23090800 Pulled By: ajkr fbshipit-source-id: afcbcd51b42ce76789fdb907d8b9ada790709c13
2020-08-14 20:28:12 +02:00
const std::atomic<int>* manual_compaction_paused_;
Added support for differential snapshots Summary: The motivation for this PR is to add to RocksDB support for differential (incremental) snapshots, as snapshot of the DB changes between two points in time (one can think of it as diff between to sequence numbers, or the diff D which can be thought of as an SST file or just set of KVs that can be applied to sequence number S1 to get the database to the state at sequence number S2). This feature would be useful for various distributed storages layers built on top of RocksDB, as it should help reduce resources (time and network bandwidth) needed to recover and rebuilt DB instances as replicas in the context of distributed storages. From the API standpoint that would like client app requesting iterator between (start seqnum) and current DB state, and reading the "diff". This is a very draft PR for initial review in the discussion on the approach, i'm going to rework some parts and keep updating the PR. For now, what's done here according to initial discussions: Preserving deletes: - We want to be able to optionally preserve recent deletes for some defined period of time, so that if a delete came in recently and might need to be included in the next incremental snapshot it would't get dropped by a compaction. This is done by adding new param to Options (preserve deletes flag) and new variable to DB Impl where we keep track of the sequence number after which we don't want to drop tombstones, even if they are otherwise eligible for deletion. - I also added a new API call for clients to be able to advance this cutoff seqnum after which we drop deletes; i assume it's more flexible to let clients control this, since otherwise we'd need to keep some kind of timestamp < -- > seqnum mapping inside the DB, which sounds messy and painful to support. Clients could make use of it by periodically calling GetLatestSequenceNumber(), noting the timestamp, doing some calculation and figuring out by how much we need to advance the cutoff seqnum. - Compaction codepath in compaction_iterator.cc has been modified to avoid dropping tombstones with seqnum > cutoff seqnum. Iterator changes: - couple params added to ReadOptions, to optionally allow client to request internal keys instead of user keys (so that client can get the latest value of a key, be it delete marker or a put), as well as min timestamp and min seqnum. TableCache changes: - I modified table_cache code to be able to quickly exclude SST files from iterators heep if creation_time on the file is less then iter_start_ts as passed in ReadOptions. That would help a lot in some DB settings (like reading very recent data only or using FIFO compactions), but not so much for universal compaction with more or less long iterator time span. What's left: - Still looking at how to best plug that inside DBIter codepath. So far it seems that FindNextUserKeyInternal only parses values as UserKeys, and iter->key() call generally returns user key. Can we add new API to DBIter as internal_key(), and modify this internal method to optionally set saved_key_ to point to the full internal key? I don't need to store actual seqnum there, but I do need to store type. Closes https://github.com/facebook/rocksdb/pull/2999 Differential Revision: D6175602 Pulled By: mikhail-antonov fbshipit-source-id: c779a6696ee2d574d86c69cec866a3ae095aa900
2017-11-02 02:43:29 +01:00
const SequenceNumber preserve_deletes_seqnum_;
LogBuffer* log_buffer_;
FSDirectory* db_directory_;
FSDirectory* output_directory_;
FSDirectory* blob_output_directory_;
Statistics* stats_;
InstrumentedMutex* db_mutex_;
ErrorHandler* db_error_handler_;
// If there were two snapshots with seq numbers s1 and
// s2 and s1 < s2, and if we find two instances of a key k1 then lies
// entirely within s1 and s2, then the earlier version of k1 can be safely
// deleted because that version is not visible in any snapshot.
std::vector<SequenceNumber> existing_snapshots_;
// This is the earliest snapshot that could be used for write-conflict
// checking by a transaction. For any user-key newer than this snapshot, we
2015-12-10 17:54:48 +01:00
// should make sure not to remove evidence that a write occurred.
SequenceNumber earliest_write_conflict_snapshot_;
const SnapshotChecker* const snapshot_checker_;
std::shared_ptr<Cache> table_cache_;
EventLogger* event_logger_;
// Is this compaction creating a file in the bottom most level?
bool bottommost_level_;
bool paranoid_file_checks_;
bool measure_io_stats_;
// Stores the Slices that designate the boundaries for each subcompaction
std::vector<Slice> boundaries_;
// Stores the approx size of keys covered in the range of each subcompaction
std::vector<uint64_t> sizes_;
Env::WriteLifeTimeHint write_hint_;
Env::Priority thread_pri_;
IOStatus io_status_;
std::string full_history_ts_low_;
};
} // namespace ROCKSDB_NAMESPACE