rocksdb/db/compaction_job.h

166 lines
5.5 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_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"
Compaction Support for Range Deletion Summary: This diff introduces RangeDelAggregator, which takes ownership of iterators provided to it via AddTombstones(). The tombstones are organized in a two-level map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data copy by holding Slices returned by the iterator, which remain valid thanks to pinning. For compaction, we create a hierarchical range tombstone iterator with structure matching the iterator over compaction input data. An aggregator based on that iterator is used by CompactionIterator to determine which keys are covered by range tombstones. In case of merge operand, the same aggregator is used by MergeHelper. Upon finishing each file in the compaction, relevant range tombstones are added to the output file's range tombstone metablock and file boundaries are updated accordingly. To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete() considers tombstones in the key's snapshot stripe. When this function is used outside of compaction, it also checks newer stripes, which can contain covering tombstones. Currently the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges within a stripe such that binary search can be used. RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range to a new table's range tombstone meta-block. Since range tombstones may fall in the gap between files, we may need to extend some files' key-ranges. The strategy is (1) first file extends as far left as possible and other files do not extend left, (2) all files extend right until either the start of the next file or the end of the last range tombstone in the gap, whichever comes first. One other notable change is adding release/move semantics to ScopedArenaIterator such that it can be used to transfer ownership of an arena-allocated iterator, similar to how unique_ptr is used for malloc'd data. Depends on D61473 Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927 Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark Reviewed By: lightmark Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D62205
2016-10-18 21:04:56 +02:00
#include "db/range_del_aggregator.h"
#include "db/version_edit.h"
#include "db/write_controller.h"
#include "db/write_thread.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/event_logger.h"
#include "util/stop_watch.h"
#include "util/thread_local.h"
namespace rocksdb {
class MemTable;
class TableCache;
class Version;
class VersionEdit;
class VersionSet;
class Arena;
class CompactionJob {
public:
CompactionJob(int job_id, Compaction* compaction,
const ImmutableDBOptions& db_options,
const EnvOptions& env_options, VersionSet* versions,
const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
Directory* db_directory, Directory* output_directory,
Statistics* stats, InstrumentedMutex* db_mutex,
Status* db_bg_error,
std::vector<SequenceNumber> existing_snapshots,
SequenceNumber earliest_write_conflict_snapshot,
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);
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
void Prepare();
// REQUIRED mutex not held
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
Status Install(const MutableCFOptions& mutable_cf_options);
private:
struct SubcompactionState;
void AggregateStatistics();
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,
RangeDelAggregator* 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 ImmutableDBOptions& db_options_;
const EnvOptions& env_options_;
Env* env_;
VersionSet* versions_;
const std::atomic<bool>* shutting_down_;
LogBuffer* log_buffer_;
Directory* db_directory_;
Directory* output_directory_;
Statistics* stats_;
InstrumentedMutex* db_mutex_;
Status* db_bg_error_;
// 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_;
std::shared_ptr<Cache> table_cache_;
EventLogger* event_logger_;
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_;
};
} // namespace rocksdb