rocksdb/db/db_impl.h

1384 lines
57 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 <list>
#include <map>
#include <queue>
#include <set>
#include <string>
#include <utility>
#include <vector>
#include "db/column_family.h"
#include "db/compaction_job.h"
#include "db/dbformat.h"
#include "db/external_sst_file_ingestion_job.h"
#include "db/flush_job.h"
#include "db/flush_scheduler.h"
#include "db/internal_stats.h"
#include "db/log_writer.h"
#include "db/pre_release_callback.h"
#include "db/read_callback.h"
#include "db/snapshot_checker.h"
#include "db/snapshot_impl.h"
#include "db/version_edit.h"
#include "db/wal_manager.h"
#include "db/write_controller.h"
#include "db/write_thread.h"
#include "memtable_list.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/memtablerep.h"
#include "rocksdb/status.h"
#include "rocksdb/transaction_log.h"
#include "rocksdb/write_buffer_manager.h"
#include "table/scoped_arena_iterator.h"
#include "util/autovector.h"
#include "util/event_logger.h"
#include "util/hash.h"
#include "util/stop_watch.h"
#include "util/thread_local.h"
namespace rocksdb {
class Arena;
class ArenaWrappedDBIter;
class MemTable;
class TableCache;
class Version;
class VersionEdit;
class VersionSet;
class WriteCallback;
struct JobContext;
struct ExternalSstFileInfo;
struct MemTableInfo;
class DBImpl : public DB {
public:
DBImpl(const DBOptions& options, const std::string& dbname,
const bool seq_per_batch = false);
virtual ~DBImpl();
// Implementations of the DB interface
using DB::Put;
virtual Status Put(const WriteOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
const Slice& value) override;
using DB::Merge;
virtual Status Merge(const WriteOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
const Slice& value) override;
using DB::Delete;
virtual Status Delete(const WriteOptions& options,
ColumnFamilyHandle* column_family,
const Slice& key) override;
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
using DB::SingleDelete;
virtual Status SingleDelete(const WriteOptions& options,
ColumnFamilyHandle* column_family,
const Slice& key) override;
using DB::Write;
virtual Status Write(const WriteOptions& options,
WriteBatch* updates) override;
using DB::Get;
virtual Status Get(const ReadOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
PinnableSlice* value) override;
// Function that Get and KeyMayExist call with no_io true or false
// Note: 'value_found' from KeyMayExist propagates here
Status GetImpl(const ReadOptions& options, ColumnFamilyHandle* column_family,
const Slice& key, PinnableSlice* value,
bool* value_found = nullptr, ReadCallback* callback = nullptr,
bool* is_blob_index = nullptr);
using DB::MultiGet;
virtual std::vector<Status> MultiGet(
const ReadOptions& options,
const std::vector<ColumnFamilyHandle*>& column_family,
const std::vector<Slice>& keys,
std::vector<std::string>* values) override;
virtual Status CreateColumnFamily(const ColumnFamilyOptions& cf_options,
const std::string& column_family,
ColumnFamilyHandle** handle) override;
virtual Status CreateColumnFamilies(
const ColumnFamilyOptions& cf_options,
const std::vector<std::string>& column_family_names,
std::vector<ColumnFamilyHandle*>* handles) override;
virtual Status CreateColumnFamilies(
const std::vector<ColumnFamilyDescriptor>& column_families,
std::vector<ColumnFamilyHandle*>* handles) override;
virtual Status DropColumnFamily(ColumnFamilyHandle* column_family) override;
virtual Status DropColumnFamilies(
const std::vector<ColumnFamilyHandle*>& column_families) override;
// Returns false if key doesn't exist in the database and true if it may.
// If value_found is not passed in as null, then return the value if found in
// memory. On return, if value was found, then value_found will be set to true
// , otherwise false.
using DB::KeyMayExist;
virtual bool KeyMayExist(const ReadOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
std::string* value,
bool* value_found = nullptr) override;
using DB::NewIterator;
virtual Iterator* NewIterator(const ReadOptions& options,
ColumnFamilyHandle* column_family) override;
virtual Status NewIterators(
const ReadOptions& options,
const std::vector<ColumnFamilyHandle*>& column_families,
std::vector<Iterator*>* iterators) override;
ArenaWrappedDBIter* NewIteratorImpl(const ReadOptions& options,
ColumnFamilyData* cfd,
SequenceNumber snapshot,
ReadCallback* read_callback,
bool allow_blob = false);
virtual const Snapshot* GetSnapshot() override;
virtual void ReleaseSnapshot(const Snapshot* snapshot) override;
using DB::GetProperty;
virtual bool GetProperty(ColumnFamilyHandle* column_family,
const Slice& property, std::string* value) override;
using DB::GetMapProperty;
virtual bool GetMapProperty(
ColumnFamilyHandle* column_family, const Slice& property,
std::map<std::string, std::string>* value) override;
using DB::GetIntProperty;
virtual bool GetIntProperty(ColumnFamilyHandle* column_family,
const Slice& property, uint64_t* value) override;
using DB::GetAggregatedIntProperty;
virtual bool GetAggregatedIntProperty(const Slice& property,
uint64_t* aggregated_value) override;
using DB::GetApproximateSizes;
virtual void GetApproximateSizes(ColumnFamilyHandle* column_family,
const Range* range, int n, uint64_t* sizes,
uint8_t include_flags
= INCLUDE_FILES) override;
using DB::GetApproximateMemTableStats;
virtual void GetApproximateMemTableStats(ColumnFamilyHandle* column_family,
const Range& range,
uint64_t* const count,
uint64_t* const size) override;
using DB::CompactRange;
virtual Status CompactRange(const CompactRangeOptions& options,
ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end) override;
using DB::CompactFiles;
virtual Status CompactFiles(const CompactionOptions& compact_options,
ColumnFamilyHandle* column_family,
const std::vector<std::string>& input_file_names,
const int output_level,
const int output_path_id = -1) override;
virtual Status PauseBackgroundWork() override;
virtual Status ContinueBackgroundWork() override;
virtual Status EnableAutoCompaction(
const std::vector<ColumnFamilyHandle*>& column_family_handles) override;
using DB::SetOptions;
Status SetOptions(
ColumnFamilyHandle* column_family,
const std::unordered_map<std::string, std::string>& options_map) override;
virtual Status SetDBOptions(
const std::unordered_map<std::string, std::string>& options_map) override;
using DB::NumberLevels;
virtual int NumberLevels(ColumnFamilyHandle* column_family) override;
using DB::MaxMemCompactionLevel;
virtual int MaxMemCompactionLevel(ColumnFamilyHandle* column_family) override;
using DB::Level0StopWriteTrigger;
virtual int Level0StopWriteTrigger(
ColumnFamilyHandle* column_family) override;
virtual const std::string& GetName() const override;
virtual Env* GetEnv() const override;
using DB::GetOptions;
virtual Options GetOptions(ColumnFamilyHandle* column_family) const override;
using DB::GetDBOptions;
virtual DBOptions GetDBOptions() const override;
using DB::Flush;
virtual Status Flush(const FlushOptions& options,
ColumnFamilyHandle* column_family) override;
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
virtual Status FlushWAL(bool sync) override;
virtual Status SyncWAL() override;
virtual SequenceNumber GetLatestSequenceNumber() const override;
virtual void SetLastPublishedSequence(SequenceNumber seq);
// Returns LastSequence in last_seq_same_as_publish_seq_
// mode and LastAllocatedSequence otherwise. This is useful when visiblility
// depends also on data written to the WAL but not to the memtable.
SequenceNumber TEST_GetLastVisibleSequence() const;
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
virtual bool SetPreserveDeletesSequenceNumber(SequenceNumber seqnum) override;
// Whether there is an active snapshot in range [lower_bound, upper_bound).
bool HasActiveSnapshotInRange(SequenceNumber lower_bound,
SequenceNumber upper_bound);
#ifndef ROCKSDB_LITE
using DB::ResetStats;
virtual Status ResetStats() override;
virtual Status DisableFileDeletions() override;
virtual Status EnableFileDeletions(bool force) override;
virtual int IsFileDeletionsEnabled() const;
// All the returned filenames start with "/"
virtual Status GetLiveFiles(std::vector<std::string>&,
uint64_t* manifest_file_size,
bool flush_memtable = true) override;
virtual Status GetSortedWalFiles(VectorLogPtr& files) override;
virtual Status GetUpdatesSince(
SequenceNumber seq_number, unique_ptr<TransactionLogIterator>* iter,
const TransactionLogIterator::ReadOptions&
read_options = TransactionLogIterator::ReadOptions()) override;
virtual Status DeleteFile(std::string name) override;
Status DeleteFilesInRange(ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end);
virtual void GetLiveFilesMetaData(
std::vector<LiveFileMetaData>* metadata) override;
// Obtains the meta data of the specified column family of the DB.
// Status::NotFound() will be returned if the current DB does not have
// any column family match the specified name.
// TODO(yhchiang): output parameter is placed in the end in this codebase.
virtual void GetColumnFamilyMetaData(
ColumnFamilyHandle* column_family,
ColumnFamilyMetaData* metadata) override;
Status SuggestCompactRange(ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end) override;
Status PromoteL0(ColumnFamilyHandle* column_family,
int target_level) override;
// Similar to Write() but will call the callback once on the single write
// thread to determine whether it is safe to perform the write.
virtual Status WriteWithCallback(const WriteOptions& write_options,
WriteBatch* my_batch,
WriteCallback* callback);
// Returns the sequence number that is guaranteed to be smaller than or equal
// to the sequence number of any key that could be inserted into the current
// memtables. It can then be assumed that any write with a larger(or equal)
// sequence number will be present in this memtable or a later memtable.
//
// If the earliest sequence number could not be determined,
// kMaxSequenceNumber will be returned.
//
// If include_history=true, will also search Memtables in MemTableList
// History.
SequenceNumber GetEarliestMemTableSequenceNumber(SuperVersion* sv,
bool include_history);
// For a given key, check to see if there are any records for this key
// in the memtables, including memtable history. If cache_only is false,
// SST files will also be checked.
//
// If a key is found, *found_record_for_key will be set to true and
// *seq will be set to the stored sequence number for the latest
// operation on this key or kMaxSequenceNumber if unknown.
// If no key is found, *found_record_for_key will be set to false.
//
// Note: If cache_only=false, it is possible for *seq to be set to 0 if
// the sequence number has been cleared from the record. If the caller is
// holding an active db snapshot, we know the missing sequence must be less
// than the snapshot's sequence number (sequence numbers are only cleared
// when there are no earlier active snapshots).
//
// If NotFound is returned and found_record_for_key is set to false, then no
// record for this key was found. If the caller is holding an active db
// snapshot, we know that no key could have existing after this snapshot
// (since we do not compact keys that have an earlier snapshot).
//
// Returns OK or NotFound on success,
// other status on unexpected error.
// TODO(andrewkr): this API need to be aware of range deletion operations
Status GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
bool cache_only, SequenceNumber* seq,
bool* found_record_for_key,
bool* is_blob_index = nullptr);
using DB::IngestExternalFile;
virtual Status IngestExternalFile(
ColumnFamilyHandle* column_family,
const std::vector<std::string>& external_files,
const IngestExternalFileOptions& ingestion_options) override;
virtual Status VerifyChecksum() override;
#endif // ROCKSDB_LITE
// Similar to GetSnapshot(), but also lets the db know that this snapshot
// will be used for transaction write-conflict checking. The DB can then
// make sure not to compact any keys that would prevent a write-conflict from
// being detected.
const Snapshot* GetSnapshotForWriteConflictBoundary();
// checks if all live files exist on file system and that their file sizes
// match to our in-memory records
virtual Status CheckConsistency();
virtual Status GetDbIdentity(std::string& identity) const override;
Status RunManualCompaction(ColumnFamilyData* cfd, int input_level,
int output_level, uint32_t output_path_id,
Allowing L0 -> L1 trivial move on sorted data Summary: This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping The conditions for trivial move have been updated Introduced conditions: - Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual) - Input level files cannot be overlapping Removed conditions: - Trivial move only run when the compaction is not manual - Input level should can contain only 1 file More context on what tests failed because of Trivial move ``` DBTest.CompactionsGenerateMultipleFiles This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1 ``` ``` DBTest.NoSpaceCompactRange This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation because trivial move does not need any extra space, and did not check for that ``` ``` DBTest.DropWrites Similar to DBTest.NoSpaceCompactRange ``` ``` DBTest.DeleteObsoleteFilesPendingOutputs This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3 ``` ``` CuckooTableDBTest.CompactionIntoMultipleFiles Same as DBTest.CompactionsGenerateMultipleFiles ``` This diff is based on a work by @sdong https://reviews.facebook.net/D34149 Test Plan: make -j64 check Reviewers: rven, sdong, igor Reviewed By: igor Subscribers: yhchiang, ott, march, dhruba, sdong Differential Revision: https://reviews.facebook.net/D34797
2015-06-05 01:51:25 +02:00
const Slice* begin, const Slice* end,
bool exclusive,
Allowing L0 -> L1 trivial move on sorted data Summary: This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping The conditions for trivial move have been updated Introduced conditions: - Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual) - Input level files cannot be overlapping Removed conditions: - Trivial move only run when the compaction is not manual - Input level should can contain only 1 file More context on what tests failed because of Trivial move ``` DBTest.CompactionsGenerateMultipleFiles This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1 ``` ``` DBTest.NoSpaceCompactRange This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation because trivial move does not need any extra space, and did not check for that ``` ``` DBTest.DropWrites Similar to DBTest.NoSpaceCompactRange ``` ``` DBTest.DeleteObsoleteFilesPendingOutputs This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3 ``` ``` CuckooTableDBTest.CompactionIntoMultipleFiles Same as DBTest.CompactionsGenerateMultipleFiles ``` This diff is based on a work by @sdong https://reviews.facebook.net/D34149 Test Plan: make -j64 check Reviewers: rven, sdong, igor Reviewed By: igor Subscribers: yhchiang, ott, march, dhruba, sdong Differential Revision: https://reviews.facebook.net/D34797
2015-06-05 01:51:25 +02:00
bool disallow_trivial_move = false);
// Return an internal iterator over the current state of the database.
// The keys of this iterator are internal keys (see format.h).
// The returned iterator should be deleted when no longer needed.
InternalIterator* NewInternalIterator(
Arena* arena, RangeDelAggregator* range_del_agg,
ColumnFamilyHandle* column_family = nullptr);
#ifndef NDEBUG
// Extra methods (for testing) that are not in the public DB interface
// Implemented in db_impl_debug.cc
// Compact any files in the named level that overlap [*begin, *end]
Status TEST_CompactRange(int level, const Slice* begin, const Slice* end,
Allowing L0 -> L1 trivial move on sorted data Summary: This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping The conditions for trivial move have been updated Introduced conditions: - Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual) - Input level files cannot be overlapping Removed conditions: - Trivial move only run when the compaction is not manual - Input level should can contain only 1 file More context on what tests failed because of Trivial move ``` DBTest.CompactionsGenerateMultipleFiles This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1 ``` ``` DBTest.NoSpaceCompactRange This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation because trivial move does not need any extra space, and did not check for that ``` ``` DBTest.DropWrites Similar to DBTest.NoSpaceCompactRange ``` ``` DBTest.DeleteObsoleteFilesPendingOutputs This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3 ``` ``` CuckooTableDBTest.CompactionIntoMultipleFiles Same as DBTest.CompactionsGenerateMultipleFiles ``` This diff is based on a work by @sdong https://reviews.facebook.net/D34149 Test Plan: make -j64 check Reviewers: rven, sdong, igor Reviewed By: igor Subscribers: yhchiang, ott, march, dhruba, sdong Differential Revision: https://reviews.facebook.net/D34797
2015-06-05 01:51:25 +02:00
ColumnFamilyHandle* column_family = nullptr,
bool disallow_trivial_move = false);
void TEST_SwitchWAL();
bool TEST_UnableToFlushOldestLog() {
return unable_to_flush_oldest_log_;
}
bool TEST_IsLogGettingFlushed() {
return alive_log_files_.begin()->getting_flushed;
}
Status TEST_SwitchMemtable(ColumnFamilyData* cfd = nullptr);
// Force current memtable contents to be flushed.
Status TEST_FlushMemTable(bool wait = true,
ColumnFamilyHandle* cfh = nullptr);
// Wait for memtable compaction
Status TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family = nullptr);
// Wait for any compaction
Status TEST_WaitForCompact();
// Return the maximum overlapping data (in bytes) at next level for any
// file at a level >= 1.
int64_t TEST_MaxNextLevelOverlappingBytes(ColumnFamilyHandle* column_family =
nullptr);
// Return the current manifest file no.
uint64_t TEST_Current_Manifest_FileNo();
// Returns the number that'll be assigned to the next file that's created.
uint64_t TEST_Current_Next_FileNo();
// get total level0 file size. Only for testing.
uint64_t TEST_GetLevel0TotalSize();
void TEST_GetFilesMetaData(ColumnFamilyHandle* column_family,
std::vector<std::vector<FileMetaData>>* metadata);
void TEST_LockMutex();
void TEST_UnlockMutex();
// REQUIRES: mutex locked
void* TEST_BeginWrite();
// REQUIRES: mutex locked
// pass the pointer that you got from TEST_BeginWrite()
void TEST_EndWrite(void* w);
uint64_t TEST_MaxTotalInMemoryState() const {
return max_total_in_memory_state_;
}
size_t TEST_LogsToFreeSize();
uint64_t TEST_LogfileNumber();
uint64_t TEST_total_log_size() const { return total_log_size_; }
// Returns column family name to ImmutableCFOptions map.
Status TEST_GetAllImmutableCFOptions(
std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map);
// Return the lastest MutableCFOptions of a column family
Status TEST_GetLatestMutableCFOptions(ColumnFamilyHandle* column_family,
MutableCFOptions* mutable_cf_options);
Cache* TEST_table_cache() { return table_cache_.get(); }
WriteController& TEST_write_controler() { return write_controller_; }
uint64_t TEST_FindMinLogContainingOutstandingPrep();
uint64_t TEST_FindMinPrepLogReferencedByMemTable();
int TEST_BGCompactionsAllowed() const;
int TEST_BGFlushesAllowed() const;
#endif // NDEBUG
struct BGJobLimits {
int max_flushes;
int max_compactions;
};
// Returns maximum background flushes and compactions allowed to be scheduled
BGJobLimits GetBGJobLimits() const;
// Need a static version that can be called during SanitizeOptions().
static BGJobLimits GetBGJobLimits(int max_background_flushes,
int max_background_compactions,
int max_background_jobs,
bool parallelize_compactions);
// move logs pending closing from job_context to the DB queue and
// schedule a purge
void ScheduleBgLogWriterClose(JobContext* job_context);
uint64_t MinLogNumberToKeep();
// Returns the list of live files in 'live' and the list
// of all files in the filesystem in 'candidate_files'.
// If force == false and the last call was less than
// db_options_.delete_obsolete_files_period_micros microseconds ago,
// it will not fill up the job_context
void FindObsoleteFiles(JobContext* job_context, bool force,
bool no_full_scan = false);
// Diffs the files listed in filenames and those that do not
// belong to live files are posibly removed. Also, removes all the
// files in sst_delete_files and log_delete_files.
// It is not necessary to hold the mutex when invoking this method.
void PurgeObsoleteFiles(const JobContext& background_contet,
bool schedule_only = false);
void SchedulePurge();
ColumnFamilyHandle* DefaultColumnFamily() const override;
const SnapshotList& snapshots() const { return snapshots_; }
const ImmutableDBOptions& immutable_db_options() const {
return immutable_db_options_;
}
void CancelAllBackgroundWork(bool wait);
// Find Super version and reference it. Based on options, it might return
// the thread local cached one.
// Call ReturnAndCleanupSuperVersion() when it is no longer needed.
SuperVersion* GetAndRefSuperVersion(ColumnFamilyData* cfd);
// Similar to the previous function but looks up based on a column family id.
// nullptr will be returned if this column family no longer exists.
// REQUIRED: this function should only be called on the write thread or if the
// mutex is held.
SuperVersion* GetAndRefSuperVersion(uint32_t column_family_id);
// Un-reference the super version and clean it up if it is the last reference.
void CleanupSuperVersion(SuperVersion* sv);
// Un-reference the super version and return it to thread local cache if
// needed. If it is the last reference of the super version. Clean it up
// after un-referencing it.
void ReturnAndCleanupSuperVersion(ColumnFamilyData* cfd, SuperVersion* sv);
// Similar to the previous function but looks up based on a column family id.
// nullptr will be returned if this column family no longer exists.
// REQUIRED: this function should only be called on the write thread.
void ReturnAndCleanupSuperVersion(uint32_t colun_family_id, SuperVersion* sv);
// REQUIRED: this function should only be called on the write thread or if the
// mutex is held. Return value only valid until next call to this function or
// mutex is released.
ColumnFamilyHandle* GetColumnFamilyHandle(uint32_t column_family_id);
// Same as above, should called without mutex held and not on write thread.
ColumnFamilyHandle* GetColumnFamilyHandleUnlocked(uint32_t column_family_id);
// Returns the number of currently running flushes.
// REQUIREMENT: mutex_ must be held when calling this function.
int num_running_flushes() {
mutex_.AssertHeld();
return num_running_flushes_;
}
// Returns the number of currently running compactions.
// REQUIREMENT: mutex_ must be held when calling this function.
int num_running_compactions() {
mutex_.AssertHeld();
return num_running_compactions_;
}
const WriteController& write_controller() { return write_controller_; }
InternalIterator* NewInternalIterator(const ReadOptions&,
ColumnFamilyData* cfd,
SuperVersion* super_version,
Arena* arena,
RangeDelAggregator* range_del_agg);
// hollow transactions shell used for recovery.
// these will then be passed to TransactionDB so that
// locks can be reacquired before writing can resume.
struct RecoveredTransaction {
uint64_t log_number_;
std::string name_;
WriteBatch* batch_;
// The seq number of the first key in the batch
SequenceNumber seq_;
explicit RecoveredTransaction(const uint64_t log, const std::string& name,
WriteBatch* batch, SequenceNumber seq)
: log_number_(log), name_(name), batch_(batch), seq_(seq) {}
~RecoveredTransaction() { delete batch_; }
};
bool allow_2pc() const { return immutable_db_options_.allow_2pc; }
std::unordered_map<std::string, RecoveredTransaction*>
recovered_transactions() {
return recovered_transactions_;
}
RecoveredTransaction* GetRecoveredTransaction(const std::string& name) {
auto it = recovered_transactions_.find(name);
if (it == recovered_transactions_.end()) {
return nullptr;
} else {
return it->second;
}
}
void InsertRecoveredTransaction(const uint64_t log, const std::string& name,
WriteBatch* batch, SequenceNumber seq) {
recovered_transactions_[name] =
new RecoveredTransaction(log, name, batch, seq);
MarkLogAsContainingPrepSection(log);
}
void DeleteRecoveredTransaction(const std::string& name) {
auto it = recovered_transactions_.find(name);
assert(it != recovered_transactions_.end());
auto* trx = it->second;
recovered_transactions_.erase(it);
MarkLogAsHavingPrepSectionFlushed(trx->log_number_);
delete trx;
}
void DeleteAllRecoveredTransactions() {
for (auto it = recovered_transactions_.begin();
it != recovered_transactions_.end(); it++) {
delete it->second;
}
recovered_transactions_.clear();
}
void MarkLogAsHavingPrepSectionFlushed(uint64_t log);
void MarkLogAsContainingPrepSection(uint64_t log);
void AddToLogsToFreeQueue(log::Writer* log_writer) {
logs_to_free_queue_.push_back(log_writer);
}
void SetSnapshotChecker(SnapshotChecker* snapshot_checker);
InstrumentedMutex* mutex() { return &mutex_; }
Status NewDB();
// This is to be used only by internal rocksdb classes.
static Status Open(const DBOptions& db_options, const std::string& name,
const std::vector<ColumnFamilyDescriptor>& column_families,
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
const bool seq_per_batch);
protected:
Env* const env_;
const std::string dbname_;
unique_ptr<VersionSet> versions_;
const DBOptions initial_db_options_;
const ImmutableDBOptions immutable_db_options_;
MutableDBOptions mutable_db_options_;
Statistics* stats_;
std::unordered_map<std::string, RecoveredTransaction*>
recovered_transactions_;
// Except in DB::Open(), WriteOptionsFile can only be called when:
// Persist options to options file.
// If need_mutex_lock = false, the method will lock DB mutex.
// If need_enter_write_thread = false, the method will enter write thread.
Status WriteOptionsFile(bool need_mutex_lock, bool need_enter_write_thread);
// The following two functions can only be called when:
// 1. WriteThread::Writer::EnterUnbatched() is used.
// 2. db_mutex is NOT held
Status RenameTempFileToOptionsFile(const std::string& file_name);
Status DeleteObsoleteOptionsFiles();
void NotifyOnFlushBegin(ColumnFamilyData* cfd, FileMetaData* file_meta,
const MutableCFOptions& mutable_cf_options,
int job_id, TableProperties prop);
void NotifyOnFlushCompleted(ColumnFamilyData* cfd, FileMetaData* file_meta,
const MutableCFOptions& mutable_cf_options,
int job_id, TableProperties prop);
void NotifyOnCompactionCompleted(ColumnFamilyData* cfd,
Compaction *c, const Status &st,
const CompactionJobStats& job_stats,
int job_id);
void NotifyOnMemTableSealed(ColumnFamilyData* cfd,
const MemTableInfo& mem_table_info);
#ifndef ROCKSDB_LITE
void NotifyOnExternalFileIngested(
ColumnFamilyData* cfd, const ExternalSstFileIngestionJob& ingestion_job);
#endif // !ROCKSDB_LITE
void NewThreadStatusCfInfo(ColumnFamilyData* cfd) const;
void EraseThreadStatusCfInfo(ColumnFamilyData* cfd) const;
void EraseThreadStatusDbInfo() const;
// If disable_memtable is set the application logic must guarantee that the
// batch will still be skipped from memtable during the recovery. In
// WriteCommitted it is guarnateed since disable_memtable is used for prepare
// batch which will be written to memtable later during the commit, and in
// WritePrepared it is guaranteed since it will be used only for WAL markers
// which will never be written to memtable.
Status WriteImpl(const WriteOptions& options, WriteBatch* updates,
WriteCallback* callback = nullptr,
uint64_t* log_used = nullptr, uint64_t log_ref = 0,
bool disable_memtable = false, uint64_t* seq_used = nullptr,
PreReleaseCallback* pre_release_callback = nullptr);
Status PipelinedWriteImpl(const WriteOptions& options, WriteBatch* updates,
WriteCallback* callback = nullptr,
uint64_t* log_used = nullptr, uint64_t log_ref = 0,
bool disable_memtable = false,
uint64_t* seq_used = nullptr);
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
Status WriteImplWALOnly(const WriteOptions& options, WriteBatch* updates,
WriteCallback* callback = nullptr,
uint64_t* log_used = nullptr, uint64_t log_ref = 0,
uint64_t* seq_used = nullptr,
PreReleaseCallback* pre_release_callback = nullptr);
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
uint64_t FindMinLogContainingOutstandingPrep();
uint64_t FindMinPrepLogReferencedByMemTable();
// write cached_recoverable_state_ to memtable if it is not empty
// The writer must be the leader in write_thread_ and holding mutex_
Status WriteRecoverableState();
private:
friend class DB;
friend class InternalStats;
friend class PessimisticTransaction;
friend class WriteCommittedTxn;
friend class WritePreparedTxn;
friend class WritePreparedTxnDB;
friend class WriteBatchWithIndex;
#ifndef ROCKSDB_LITE
friend class ForwardIterator;
#endif
friend struct SuperVersion;
friend class CompactedDBImpl;
#ifndef NDEBUG
friend class DBTest2_ReadCallbackTest_Test;
friend class WriteCallbackTest_WriteWithCallbackTest_Test;
friend class XFTransactionWriteHandler;
friend class DBBlobIndexTest;
#endif
struct CompactionState;
struct WriteContext {
SuperVersionContext superversion_context;
autovector<MemTable*> memtables_to_free_;
explicit WriteContext(bool create_superversion = false)
: superversion_context(create_superversion) {}
~WriteContext() {
superversion_context.Clean();
for (auto& m : memtables_to_free_) {
delete m;
}
}
};
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
struct PrepickedCompaction;
struct PurgeFileInfo;
// Recover the descriptor from persistent storage. May do a significant
// amount of work to recover recently logged updates. Any changes to
// be made to the descriptor are added to *edit.
Status Recover(const std::vector<ColumnFamilyDescriptor>& column_families,
bool read_only = false, bool error_if_log_file_exist = false,
bool error_if_data_exists_in_logs = false);
void MaybeIgnoreError(Status* s) const;
const Status CreateArchivalDirectory();
Status CreateColumnFamilyImpl(const ColumnFamilyOptions& cf_options,
const std::string& cf_name,
ColumnFamilyHandle** handle);
Status DropColumnFamilyImpl(ColumnFamilyHandle* column_family);
// Delete any unneeded files and stale in-memory entries.
void DeleteObsoleteFiles();
// Delete obsolete files and log status and information of file deletion
void DeleteObsoleteFileImpl(int job_id, const std::string& fname,
FileType type, uint64_t number, uint32_t path_id);
// Background process needs to call
// auto x = CaptureCurrentFileNumberInPendingOutputs()
// auto file_num = versions_->NewFileNumber();
// <do something>
// ReleaseFileNumberFromPendingOutputs(x)
// This will protect any file with number `file_num` or greater from being
// deleted while <do something> is running.
// -----------
// This function will capture current file number and append it to
// pending_outputs_. This will prevent any background process to delete any
// file created after this point.
std::list<uint64_t>::iterator CaptureCurrentFileNumberInPendingOutputs();
// This function should be called with the result of
// CaptureCurrentFileNumberInPendingOutputs(). It then marks that any file
// created between the calls CaptureCurrentFileNumberInPendingOutputs() and
// ReleaseFileNumberFromPendingOutputs() can now be deleted (if it's not live
// and blocked by any other pending_outputs_ calls)
void ReleaseFileNumberFromPendingOutputs(std::list<uint64_t>::iterator v);
Status SyncClosedLogs(JobContext* job_context);
// Flush the in-memory write buffer to storage. Switches to a new
// log-file/memtable and writes a new descriptor iff successful.
Status FlushMemTableToOutputFile(ColumnFamilyData* cfd,
const MutableCFOptions& mutable_cf_options,
bool* madeProgress, JobContext* job_context,
LogBuffer* log_buffer);
// REQUIRES: log_numbers are sorted in ascending order
Status RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
SequenceNumber* next_sequence, bool read_only);
// The following two methods are used to flush a memtable to
// storage. The first one is used at database RecoveryTime (when the
// database is opened) and is heavyweight because it holds the mutex
// for the entire period. The second method WriteLevel0Table supports
// concurrent flush memtables to storage.
Status WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
MemTable* mem, VersionEdit* edit);
// num_bytes: for slowdown case, delay time is calculated based on
// `num_bytes` going through.
Status DelayWrite(uint64_t num_bytes, const WriteOptions& write_options);
Status ThrottleLowPriWritesIfNeeded(const WriteOptions& write_options,
WriteBatch* my_batch);
Status ScheduleFlushes(WriteContext* context);
Status SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context);
// Force current memtable contents to be flushed.
Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options,
bool writes_stopped = false);
// Wait for memtable flushed
Status WaitForFlushMemTable(ColumnFamilyData* cfd);
// REQUIRES: mutex locked
Status SwitchWAL(WriteContext* write_context);
// REQUIRES: mutex locked
Status HandleWriteBufferFull(WriteContext* write_context);
// REQUIRES: mutex locked
Status PreprocessWrite(const WriteOptions& write_options, bool* need_log_sync,
WriteContext* write_context);
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
WriteBatch* MergeBatch(const WriteThread::WriteGroup& write_group,
WriteBatch* tmp_batch, size_t* write_with_wal,
WriteBatch** to_be_cached_state);
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
Status WriteToWAL(const WriteBatch& merged_batch, log::Writer* log_writer,
uint64_t* log_used, uint64_t* log_size);
Status WriteToWAL(const WriteThread::WriteGroup& write_group,
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
log::Writer* log_writer, uint64_t* log_used,
bool need_log_sync, bool need_log_dir_sync,
SequenceNumber sequence);
Status ConcurrentWriteToWAL(const WriteThread::WriteGroup& write_group,
uint64_t* log_used, SequenceNumber* last_sequence,
size_t seq_inc);
// Used by WriteImpl to update bg_error_ if paranoid check is enabled.
void WriteCallbackStatusCheck(const Status& status);
// Used by WriteImpl to update bg_error_ in case of memtable insert error.
void MemTableInsertStatusCheck(const Status& memtable_insert_status);
#ifndef ROCKSDB_LITE
Status CompactFilesImpl(const CompactionOptions& compact_options,
ColumnFamilyData* cfd, Version* version,
const std::vector<std::string>& input_file_names,
const int output_level, int output_path_id,
JobContext* job_context, LogBuffer* log_buffer);
// Wait for current IngestExternalFile() calls to finish.
// REQUIRES: mutex_ held
void WaitForIngestFile();
#else
// IngestExternalFile is not supported in ROCKSDB_LITE so this function
// will be no-op
void WaitForIngestFile() {}
#endif // ROCKSDB_LITE
ColumnFamilyData* GetColumnFamilyDataByName(const std::string& cf_name);
void MaybeScheduleFlushOrCompaction();
Rewritten system for scheduling background work Summary: When scaling to higher number of column families, the worst bottleneck was MaybeScheduleFlushOrCompaction(), which did a for loop over all column families while holding a mutex. This patch addresses the issue. The approach is similar to our earlier efforts: instead of a pull-model, where we do something for every column family, we can do a push-based model -- when we detect that column family is ready to be flushed/compacted, we add it to the flush_queue_/compaction_queue_. That way we don't need to loop over every column family in MaybeScheduleFlushOrCompaction. Here are the performance results: Command: ./db_bench --write_buffer_size=268435456 --db_write_buffer_size=268435456 --db=/fast-rocksdb-tmp/rocks_lots_of_cf --use_existing_db=0 --open_files=55000 --statistics=1 --histogram=1 --disable_data_sync=1 --max_write_buffer_number=2 --sync=0 --benchmarks=fillrandom --threads=16 --num_column_families=5000 --disable_wal=1 --max_background_flushes=16 --max_background_compactions=16 --level0_file_num_compaction_trigger=2 --level0_slowdown_writes_trigger=2 --level0_stop_writes_trigger=3 --hard_rate_limit=1 --num=33333333 --writes=33333333 Before the patch: fillrandom : 26.950 micros/op 37105 ops/sec; 4.1 MB/s After the patch: fillrandom : 17.404 micros/op 57456 ops/sec; 6.4 MB/s Next bottleneck is VersionSet::AddLiveFiles, which is painfully slow when we have a lot of files. This is coming in the next patch, but when I removed that code, here's what I got: fillrandom : 7.590 micros/op 131758 ops/sec; 14.6 MB/s Test Plan: make check two stress tests: Big number of compactions and flushes: ./db_stress --threads=30 --ops_per_thread=20000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=15 --max_background_compactions=10 --max_background_flushes=10 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 max_background_flushes=0, to verify that this case also works correctly ./db_stress --threads=30 --ops_per_thread=2000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=3 --max_background_compactions=3 --max_background_flushes=0 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 Reviewers: ljin, rven, yhchiang, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D30123
2014-12-19 20:38:12 +01:00
void SchedulePendingFlush(ColumnFamilyData* cfd);
void SchedulePendingCompaction(ColumnFamilyData* cfd);
void SchedulePendingPurge(std::string fname, FileType type, uint64_t number,
uint32_t path_id, int job_id);
static void BGWorkCompaction(void* arg);
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
// Runs a pre-chosen universal compaction involving bottom level in a
// separate, bottom-pri thread pool.
static void BGWorkBottomCompaction(void* arg);
static void BGWorkFlush(void* db);
static void BGWorkPurge(void* arg);
static void UnscheduleCallback(void* arg);
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
void BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
Env::Priority bg_thread_pri);
void BackgroundCallFlush();
void BackgroundCallPurge();
Status BackgroundCompaction(bool* madeProgress, JobContext* job_context,
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
LogBuffer* log_buffer,
PrepickedCompaction* prepicked_compaction);
Status BackgroundFlush(bool* madeProgress, JobContext* job_context,
LogBuffer* log_buffer);
void PrintStatistics();
// dump rocksdb.stats to LOG
void MaybeDumpStats();
// Return the minimum empty level that could hold the total data in the
// input level. Return the input level, if such level could not be found.
int FindMinimumEmptyLevelFitting(ColumnFamilyData* cfd,
const MutableCFOptions& mutable_cf_options, int level);
// Move the files in the input level to the target level.
// If target_level < 0, automatically calculate the minimum level that could
// hold the data set.
Status ReFitLevel(ColumnFamilyData* cfd, int level, int target_level = -1);
Rewritten system for scheduling background work Summary: When scaling to higher number of column families, the worst bottleneck was MaybeScheduleFlushOrCompaction(), which did a for loop over all column families while holding a mutex. This patch addresses the issue. The approach is similar to our earlier efforts: instead of a pull-model, where we do something for every column family, we can do a push-based model -- when we detect that column family is ready to be flushed/compacted, we add it to the flush_queue_/compaction_queue_. That way we don't need to loop over every column family in MaybeScheduleFlushOrCompaction. Here are the performance results: Command: ./db_bench --write_buffer_size=268435456 --db_write_buffer_size=268435456 --db=/fast-rocksdb-tmp/rocks_lots_of_cf --use_existing_db=0 --open_files=55000 --statistics=1 --histogram=1 --disable_data_sync=1 --max_write_buffer_number=2 --sync=0 --benchmarks=fillrandom --threads=16 --num_column_families=5000 --disable_wal=1 --max_background_flushes=16 --max_background_compactions=16 --level0_file_num_compaction_trigger=2 --level0_slowdown_writes_trigger=2 --level0_stop_writes_trigger=3 --hard_rate_limit=1 --num=33333333 --writes=33333333 Before the patch: fillrandom : 26.950 micros/op 37105 ops/sec; 4.1 MB/s After the patch: fillrandom : 17.404 micros/op 57456 ops/sec; 6.4 MB/s Next bottleneck is VersionSet::AddLiveFiles, which is painfully slow when we have a lot of files. This is coming in the next patch, but when I removed that code, here's what I got: fillrandom : 7.590 micros/op 131758 ops/sec; 14.6 MB/s Test Plan: make check two stress tests: Big number of compactions and flushes: ./db_stress --threads=30 --ops_per_thread=20000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=15 --max_background_compactions=10 --max_background_flushes=10 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 max_background_flushes=0, to verify that this case also works correctly ./db_stress --threads=30 --ops_per_thread=2000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=3 --max_background_compactions=3 --max_background_flushes=0 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 Reviewers: ljin, rven, yhchiang, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D30123
2014-12-19 20:38:12 +01:00
// helper functions for adding and removing from flush & compaction queues
void AddToCompactionQueue(ColumnFamilyData* cfd);
ColumnFamilyData* PopFirstFromCompactionQueue();
void AddToFlushQueue(ColumnFamilyData* cfd);
ColumnFamilyData* PopFirstFromFlushQueue();
// helper function to call after some of the logs_ were synced
void MarkLogsSynced(uint64_t up_to, bool synced_dir, const Status& status);
const Snapshot* GetSnapshotImpl(bool is_write_conflict_boundary);
uint64_t GetMaxTotalWalSize() const;
// table_cache_ provides its own synchronization
std::shared_ptr<Cache> table_cache_;
// Lock over the persistent DB state. Non-nullptr iff successfully acquired.
FileLock* db_lock_;
// In addition to mutex_, log_write_mutex_ protected writes to logs_ and
// logfile_number_. With two_write_queues it also protects alive_log_files_,
// and log_empty_. Refer to the definition of each variable below for more
// details.
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
InstrumentedMutex log_write_mutex_;
// State below is protected by mutex_
// With two_write_queues enabled, some of the variables that accessed during
// WriteToWAL need different synchronization: log_empty_, alive_log_files_,
// logs_, logfile_number_. Refer to the definition of each variable below for
// more description.
mutable InstrumentedMutex mutex_;
std::atomic<bool> shutting_down_;
// This condition variable is signaled on these conditions:
// * whenever bg_compaction_scheduled_ goes down to 0
// * if AnyManualCompaction, whenever a compaction finishes, even if it hasn't
// made any progress
// * whenever a compaction made any progress
// * whenever bg_flush_scheduled_ or bg_purge_scheduled_ value decreases
// (i.e. whenever a flush is done, even if it didn't make any progress)
// * whenever there is an error in background purge, flush or compaction
// * whenever num_running_ingest_file_ goes to 0.
InstrumentedCondVar bg_cv_;
// Writes are protected by locking both mutex_ and log_write_mutex_, and reads
// must be under either mutex_ or log_write_mutex_. Since after ::Open,
// logfile_number_ is currently updated only in write_thread_, it can be read
// from the same write_thread_ without any locks.
uint64_t logfile_number_;
std::deque<uint64_t>
log_recycle_files; // a list of log files that we can recycle
bool log_dir_synced_;
// Without two_write_queues, read and writes to log_empty_ are protected by
// mutex_. Since it is currently updated/read only in write_thread_, it can be
// accessed from the same write_thread_ without any locks. With
// two_write_queues writes, where it can be updated in different threads,
// read and writes are protected by log_write_mutex_ instead. This is to avoid
// expesnive mutex_ lock during WAL write, which update log_empty_.
bool log_empty_;
ColumnFamilyHandleImpl* default_cf_handle_;
make internal stats independent of statistics Summary: also make it aware of column family output from db_bench ``` ** Compaction Stats [default] ** Level Files Size(MB) Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) RW-Amp W-Amp Rd(MB/s) Wr(MB/s) Rn(cnt) Rnp1(cnt) Wnp1(cnt) Wnew(cnt) Comp(sec) Comp(cnt) Avg(sec) Stall(sec) Stall(cnt) Avg(ms) ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ L0 14 956 0.9 0.0 0.0 0.0 2.7 2.7 0.0 0.0 0.0 111.6 0 0 0 0 24 40 0.612 75.20 492387 0.15 L1 21 2001 2.0 5.7 2.0 3.7 5.3 1.6 5.4 2.6 71.2 65.7 31 43 55 12 82 2 41.242 43.72 41183 1.06 L2 217 18974 1.9 16.5 2.0 14.4 15.1 0.7 15.6 7.4 70.1 64.3 17 182 185 3 241 16 15.052 0.00 0 0.00 L3 1641 188245 1.8 9.1 1.1 8.0 8.5 0.5 15.4 7.4 61.3 57.2 9 75 76 1 152 9 16.887 0.00 0 0.00 L4 4447 449025 0.4 13.4 4.8 8.6 9.1 0.5 4.7 1.9 77.8 52.7 38 79 100 21 176 38 4.639 0.00 0 0.00 Sum 6340 659201 0.0 44.7 10.0 34.7 40.6 6.0 32.0 15.2 67.7 61.6 95 379 416 37 676 105 6.439 118.91 533570 0.22 Int 0 0 0.0 1.2 0.4 0.8 1.3 0.5 5.2 2.7 59.1 65.6 3 7 9 2 20 10 2.003 0.00 0 0.00 Stalls(secs): 75.197 level0_slowdown, 0.000 level0_numfiles, 0.000 memtable_compaction, 43.717 leveln_slowdown Stalls(count): 492387 level0_slowdown, 0 level0_numfiles, 0 memtable_compaction, 41183 leveln_slowdown ** DB Stats ** Uptime(secs): 202.1 total, 13.5 interval Cumulative writes: 6291456 writes, 6291456 batches, 1.0 writes per batch, 4.90 ingest GB Cumulative WAL: 6291456 writes, 6291456 syncs, 1.00 writes per sync, 4.90 GB written Interval writes: 1048576 writes, 1048576 batches, 1.0 writes per batch, 836.0 ingest MB Interval WAL: 1048576 writes, 1048576 syncs, 1.00 writes per sync, 0.82 MB written Test Plan: ran it Reviewers: sdong, yhchiang, igor Reviewed By: igor Subscribers: leveldb Differential Revision: https://reviews.facebook.net/D19917
2014-07-21 21:57:29 +02:00
InternalStats* default_cf_internal_stats_;
unique_ptr<ColumnFamilyMemTablesImpl> column_family_memtables_;
struct LogFileNumberSize {
explicit LogFileNumberSize(uint64_t _number)
: number(_number) {}
void AddSize(uint64_t new_size) { size += new_size; }
uint64_t number;
uint64_t size = 0;
bool getting_flushed = false;
};
struct LogWriterNumber {
// pass ownership of _writer
LogWriterNumber(uint64_t _number, log::Writer* _writer)
: number(_number), writer(_writer) {}
log::Writer* ReleaseWriter() {
auto* w = writer;
writer = nullptr;
return w;
}
void ClearWriter() {
delete writer;
writer = nullptr;
}
uint64_t number;
// Visual Studio doesn't support deque's member to be noncopyable because
// of a unique_ptr as a member.
log::Writer* writer; // own
// true for some prefix of logs_
bool getting_synced = false;
};
// Without two_write_queues, read and writes to alive_log_files_ are
// protected by mutex_. However since back() is never popped, and push_back()
// is done only from write_thread_, the same thread can access the item
// reffered by back() without mutex_. With two_write_queues_, writes
// are protected by locking both mutex_ and log_write_mutex_, and reads must
// be under either mutex_ or log_write_mutex_.
std::deque<LogFileNumberSize> alive_log_files_;
// Log files that aren't fully synced, and the current log file.
// Synchronization:
// - push_back() is done from write_thread_ with locked mutex_ and
// log_write_mutex_
// - pop_front() is done from any thread with locked mutex_ and
// log_write_mutex_
// - reads are done with either locked mutex_ or log_write_mutex_
// - back() and items with getting_synced=true are not popped,
// - The same thread that sets getting_synced=true will reset it.
// - it follows that the object referred by back() can be safely read from
// the write_thread_ without using mutex
// - it follows that the items with getting_synced=true can be safely read
// from the same thread that has set getting_synced=true
std::deque<LogWriterNumber> logs_;
// Signaled when getting_synced becomes false for some of the logs_.
InstrumentedCondVar log_sync_cv_;
// This is the app-level state that is written to the WAL but will be used
// only during recovery. Using this feature enables not writing the state to
// memtable on normal writes and hence improving the throughput. Each new
// write of the state will replace the previous state entirely even if the
// keys in the two consecuitive states do not overlap.
// It is protected by log_write_mutex_ when two_write_queues_ is enabled.
// Otherwise only the heaad of write_thread_ can access it.
WriteBatch cached_recoverable_state_;
std::atomic<bool> cached_recoverable_state_empty_ = {true};
std::atomic<uint64_t> total_log_size_;
// only used for dynamically adjusting max_total_wal_size. it is a sum of
// [write_buffer_size * max_write_buffer_number] over all column families
uint64_t max_total_in_memory_state_;
// If true, we have only one (default) column family. We use this to optimize
// some code-paths
bool single_column_family_mode_;
// If this is non-empty, we need to delete these log files in background
// threads. Protected by db mutex.
autovector<log::Writer*> logs_to_free_;
bool is_snapshot_supported_;
// Class to maintain directories for all database paths other than main one.
class Directories {
public:
Status SetDirectories(Env* env, const std::string& dbname,
const std::string& wal_dir,
const std::vector<DbPath>& data_paths);
Directory* GetDataDir(size_t path_id);
Directory* GetWalDir() {
if (wal_dir_) {
return wal_dir_.get();
}
return db_dir_.get();
}
Directory* GetDbDir() { return db_dir_.get(); }
private:
std::unique_ptr<Directory> db_dir_;
std::vector<std::unique_ptr<Directory>> data_dirs_;
std::unique_ptr<Directory> wal_dir_;
Status CreateAndNewDirectory(Env* env, const std::string& dirname,
std::unique_ptr<Directory>* directory) const;
};
Directories directories_;
WriteBufferManager* write_buffer_manager_;
WriteThread write_thread_;
WriteBatch tmp_batch_;
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
// The write thread when the writers have no memtable write. This will be used
// in 2PC to batch the prepares separately from the serial commit.
WriteThread nonmem_write_thread_;
WriteController write_controller_;
unique_ptr<RateLimiter> low_pri_write_rate_limiter_;
// Size of the last batch group. In slowdown mode, next write needs to
// sleep if it uses up the quota.
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
// Note: This is to protect memtable and compaction. If the batch only writes
// to the WAL its size need not to be included in this.
uint64_t last_batch_group_size_;
FlushScheduler flush_scheduler_;
SnapshotList snapshots_;
// For each background job, pending_outputs_ keeps the current file number at
// the time that background job started.
// FindObsoleteFiles()/PurgeObsoleteFiles() never deletes any file that has
// number bigger than any of the file number in pending_outputs_. Since file
// numbers grow monotonically, this also means that pending_outputs_ is always
// sorted. After a background job is done executing, its file number is
// deleted from pending_outputs_, which allows PurgeObsoleteFiles() to clean
// it up.
// State is protected with db mutex.
std::list<uint64_t> pending_outputs_;
// PurgeFileInfo is a structure to hold information of files to be deleted in
// purge_queue_
struct PurgeFileInfo {
std::string fname;
FileType type;
uint64_t number;
uint32_t path_id;
int job_id;
PurgeFileInfo(std::string fn, FileType t, uint64_t num, uint32_t pid,
int jid)
: fname(fn), type(t), number(num), path_id(pid), job_id(jid) {}
};
Rewritten system for scheduling background work Summary: When scaling to higher number of column families, the worst bottleneck was MaybeScheduleFlushOrCompaction(), which did a for loop over all column families while holding a mutex. This patch addresses the issue. The approach is similar to our earlier efforts: instead of a pull-model, where we do something for every column family, we can do a push-based model -- when we detect that column family is ready to be flushed/compacted, we add it to the flush_queue_/compaction_queue_. That way we don't need to loop over every column family in MaybeScheduleFlushOrCompaction. Here are the performance results: Command: ./db_bench --write_buffer_size=268435456 --db_write_buffer_size=268435456 --db=/fast-rocksdb-tmp/rocks_lots_of_cf --use_existing_db=0 --open_files=55000 --statistics=1 --histogram=1 --disable_data_sync=1 --max_write_buffer_number=2 --sync=0 --benchmarks=fillrandom --threads=16 --num_column_families=5000 --disable_wal=1 --max_background_flushes=16 --max_background_compactions=16 --level0_file_num_compaction_trigger=2 --level0_slowdown_writes_trigger=2 --level0_stop_writes_trigger=3 --hard_rate_limit=1 --num=33333333 --writes=33333333 Before the patch: fillrandom : 26.950 micros/op 37105 ops/sec; 4.1 MB/s After the patch: fillrandom : 17.404 micros/op 57456 ops/sec; 6.4 MB/s Next bottleneck is VersionSet::AddLiveFiles, which is painfully slow when we have a lot of files. This is coming in the next patch, but when I removed that code, here's what I got: fillrandom : 7.590 micros/op 131758 ops/sec; 14.6 MB/s Test Plan: make check two stress tests: Big number of compactions and flushes: ./db_stress --threads=30 --ops_per_thread=20000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=15 --max_background_compactions=10 --max_background_flushes=10 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 max_background_flushes=0, to verify that this case also works correctly ./db_stress --threads=30 --ops_per_thread=2000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=3 --max_background_compactions=3 --max_background_flushes=0 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 Reviewers: ljin, rven, yhchiang, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D30123
2014-12-19 20:38:12 +01:00
// flush_queue_ and compaction_queue_ hold column families that we need to
// flush and compact, respectively.
// A column family is inserted into flush_queue_ when it satisfies condition
// cfd->imm()->IsFlushPending()
// A column family is inserted into compaction_queue_ when it satisfied
// condition cfd->NeedsCompaction()
// Column families in this list are all Ref()-erenced
// TODO(icanadi) Provide some kind of ReferencedColumnFamily class that will
// do RAII on ColumnFamilyData
// Column families are in this queue when they need to be flushed or
// compacted. Consumers of these queues are flush and compaction threads. When
// column family is put on this queue, we increase unscheduled_flushes_ and
// unscheduled_compactions_. When these variables are bigger than zero, that
// means we need to schedule background threads for compaction and thread.
// Once the background threads are scheduled, we decrease unscheduled_flushes_
// and unscheduled_compactions_. That way we keep track of number of
// compaction and flush threads we need to schedule. This scheduling is done
// in MaybeScheduleFlushOrCompaction()
// invariant(column family present in flush_queue_ <==>
// ColumnFamilyData::pending_flush_ == true)
std::deque<ColumnFamilyData*> flush_queue_;
// invariant(column family present in compaction_queue_ <==>
// ColumnFamilyData::pending_compaction_ == true)
std::deque<ColumnFamilyData*> compaction_queue_;
// A queue to store filenames of the files to be purged
std::deque<PurgeFileInfo> purge_queue_;
// A queue to store log writers to close
std::deque<log::Writer*> logs_to_free_queue_;
Rewritten system for scheduling background work Summary: When scaling to higher number of column families, the worst bottleneck was MaybeScheduleFlushOrCompaction(), which did a for loop over all column families while holding a mutex. This patch addresses the issue. The approach is similar to our earlier efforts: instead of a pull-model, where we do something for every column family, we can do a push-based model -- when we detect that column family is ready to be flushed/compacted, we add it to the flush_queue_/compaction_queue_. That way we don't need to loop over every column family in MaybeScheduleFlushOrCompaction. Here are the performance results: Command: ./db_bench --write_buffer_size=268435456 --db_write_buffer_size=268435456 --db=/fast-rocksdb-tmp/rocks_lots_of_cf --use_existing_db=0 --open_files=55000 --statistics=1 --histogram=1 --disable_data_sync=1 --max_write_buffer_number=2 --sync=0 --benchmarks=fillrandom --threads=16 --num_column_families=5000 --disable_wal=1 --max_background_flushes=16 --max_background_compactions=16 --level0_file_num_compaction_trigger=2 --level0_slowdown_writes_trigger=2 --level0_stop_writes_trigger=3 --hard_rate_limit=1 --num=33333333 --writes=33333333 Before the patch: fillrandom : 26.950 micros/op 37105 ops/sec; 4.1 MB/s After the patch: fillrandom : 17.404 micros/op 57456 ops/sec; 6.4 MB/s Next bottleneck is VersionSet::AddLiveFiles, which is painfully slow when we have a lot of files. This is coming in the next patch, but when I removed that code, here's what I got: fillrandom : 7.590 micros/op 131758 ops/sec; 14.6 MB/s Test Plan: make check two stress tests: Big number of compactions and flushes: ./db_stress --threads=30 --ops_per_thread=20000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=15 --max_background_compactions=10 --max_background_flushes=10 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 max_background_flushes=0, to verify that this case also works correctly ./db_stress --threads=30 --ops_per_thread=2000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=3 --max_background_compactions=3 --max_background_flushes=0 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 Reviewers: ljin, rven, yhchiang, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D30123
2014-12-19 20:38:12 +01:00
int unscheduled_flushes_;
int unscheduled_compactions_;
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
// count how many background compactions are running or have been scheduled in
// the BOTTOM pool
int bg_bottom_compaction_scheduled_;
Fix a deadlock in CompactRange() Summary: The way DBImpl::TEST_CompactRange() throttles down the number of bg compactions can cause it to deadlock when CompactRange() is called concurrently from multiple threads. Imagine a following scenario with only two threads (max_background_compactions is 10 and bg_compaction_scheduled_ is initially 0): 1. Thread #1 increments bg_compaction_scheduled_ (to LargeNumber), sets bg_compaction_scheduled_ to 9 (newvalue), schedules the compaction (bg_compaction_scheduled_ is now 10) and waits for it to complete. 2. Thread #2 calls TEST_CompactRange(), increments bg_compaction_scheduled_ (now LargeNumber + 10) and waits on a cv for bg_compaction_scheduled_ to drop to LargeNumber. 3. BG thread completes the first manual compaction, decrements bg_compaction_scheduled_ and wakes up all threads waiting on bg_cv_. Thread #1 runs, increments bg_compaction_scheduled_ by LargeNumber again (now 2*LargeNumber + 9). Since that's more than LargeNumber + newvalue, thread #2 also goes to sleep (waiting on bg_cv_), without resetting bg_compaction_scheduled_. This diff attempts to address the problem by introducing a new counter bg_manual_only_ (when positive, MaybeScheduleFlushOrCompaction() will only schedule manual compactions). Test Plan: I could pretty much consistently reproduce the deadlock with a program that calls CompactRange(nullptr, nullptr) immediately after Write() from multiple threads. This no longer happens with this patch. Tests (make check) pass. Reviewers: dhruba, igor, sdong, haobo Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D14799
2013-12-22 00:10:39 +01:00
// count how many background compactions are running or have been scheduled
int bg_compaction_scheduled_;
// stores the number of compactions are currently running
int num_running_compactions_;
// number of background memtable flush jobs, submitted to the HIGH pool
int bg_flush_scheduled_;
// stores the number of flushes are currently running
int num_running_flushes_;
// number of background obsolete file purge jobs, submitted to the HIGH pool
int bg_purge_scheduled_;
// Information for a manual compaction
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
struct ManualCompactionState {
ColumnFamilyData* cfd;
int input_level;
int output_level;
uint32_t output_path_id;
Status status;
bool done;
Allowing L0 -> L1 trivial move on sorted data Summary: This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping The conditions for trivial move have been updated Introduced conditions: - Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual) - Input level files cannot be overlapping Removed conditions: - Trivial move only run when the compaction is not manual - Input level should can contain only 1 file More context on what tests failed because of Trivial move ``` DBTest.CompactionsGenerateMultipleFiles This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1 ``` ``` DBTest.NoSpaceCompactRange This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation because trivial move does not need any extra space, and did not check for that ``` ``` DBTest.DropWrites Similar to DBTest.NoSpaceCompactRange ``` ``` DBTest.DeleteObsoleteFilesPendingOutputs This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3 ``` ``` CuckooTableDBTest.CompactionIntoMultipleFiles Same as DBTest.CompactionsGenerateMultipleFiles ``` This diff is based on a work by @sdong https://reviews.facebook.net/D34149 Test Plan: make -j64 check Reviewers: rven, sdong, igor Reviewed By: igor Subscribers: yhchiang, ott, march, dhruba, sdong Differential Revision: https://reviews.facebook.net/D34797
2015-06-05 01:51:25 +02:00
bool in_progress; // compaction request being processed?
bool incomplete; // only part of requested range compacted
bool exclusive; // current behavior of only one manual
bool disallow_trivial_move; // Force actual compaction to run
Allowing L0 -> L1 trivial move on sorted data Summary: This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping The conditions for trivial move have been updated Introduced conditions: - Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual) - Input level files cannot be overlapping Removed conditions: - Trivial move only run when the compaction is not manual - Input level should can contain only 1 file More context on what tests failed because of Trivial move ``` DBTest.CompactionsGenerateMultipleFiles This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1 ``` ``` DBTest.NoSpaceCompactRange This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation because trivial move does not need any extra space, and did not check for that ``` ``` DBTest.DropWrites Similar to DBTest.NoSpaceCompactRange ``` ``` DBTest.DeleteObsoleteFilesPendingOutputs This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3 ``` ``` CuckooTableDBTest.CompactionIntoMultipleFiles Same as DBTest.CompactionsGenerateMultipleFiles ``` This diff is based on a work by @sdong https://reviews.facebook.net/D34149 Test Plan: make -j64 check Reviewers: rven, sdong, igor Reviewed By: igor Subscribers: yhchiang, ott, march, dhruba, sdong Differential Revision: https://reviews.facebook.net/D34797
2015-06-05 01:51:25 +02:00
const InternalKey* begin; // nullptr means beginning of key range
const InternalKey* end; // nullptr means end of key range
InternalKey* manual_end; // how far we are compacting
Allowing L0 -> L1 trivial move on sorted data Summary: This diff updates the logic of how we do trivial move, now trivial move can run on any number of files in input level as long as they are not overlapping The conditions for trivial move have been updated Introduced conditions: - Trivial move cannot happen if we have a compaction filter (except if the compaction is not manual) - Input level files cannot be overlapping Removed conditions: - Trivial move only run when the compaction is not manual - Input level should can contain only 1 file More context on what tests failed because of Trivial move ``` DBTest.CompactionsGenerateMultipleFiles This test is expecting compaction on a file in L0 to generate multiple files in L1, this test will fail with trivial move because we end up with one file in L1 ``` ``` DBTest.NoSpaceCompactRange This test expect compaction to fail when we force environment to report running out of space, of course this is not valid in trivial move situation because trivial move does not need any extra space, and did not check for that ``` ``` DBTest.DropWrites Similar to DBTest.NoSpaceCompactRange ``` ``` DBTest.DeleteObsoleteFilesPendingOutputs This test expect that a file in L2 is deleted after it's moved to L3, this is not valid with trivial move because although the file was moved it is now used by L3 ``` ``` CuckooTableDBTest.CompactionIntoMultipleFiles Same as DBTest.CompactionsGenerateMultipleFiles ``` This diff is based on a work by @sdong https://reviews.facebook.net/D34149 Test Plan: make -j64 check Reviewers: rven, sdong, igor Reviewed By: igor Subscribers: yhchiang, ott, march, dhruba, sdong Differential Revision: https://reviews.facebook.net/D34797
2015-06-05 01:51:25 +02:00
InternalKey tmp_storage; // Used to keep track of compaction progress
InternalKey tmp_storage1; // Used to keep track of compaction progress
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
};
struct PrepickedCompaction {
// background compaction takes ownership of `compaction`.
Compaction* compaction;
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
// caller retains ownership of `manual_compaction_state` as it is reused
// across background compactions.
ManualCompactionState* manual_compaction_state; // nullptr if non-manual
};
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
std::deque<ManualCompactionState*> manual_compaction_dequeue_;
struct CompactionArg {
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
// caller retains ownership of `db`.
DBImpl* db;
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
// background compaction takes ownership of `prepicked_compaction`.
PrepickedCompaction* prepicked_compaction;
};
// Have we encountered a background error in paranoid mode?
Status bg_error_;
// shall we disable deletion of obsolete files
// if 0 the deletion is enabled.
// if non-zero, files will not be getting deleted
// This enables two different threads to call
// EnableFileDeletions() and DisableFileDeletions()
// without any synchronization
int disable_delete_obsolete_files_;
// last time when DeleteObsoleteFiles with full scan was executed. Originaly
// initialized with startup time.
uint64_t delete_obsolete_files_last_run_;
// last time stats were dumped to LOG
std::atomic<uint64_t> last_stats_dump_time_microsec_;
// Each flush or compaction gets its own job id. this counter makes sure
// they're unique
std::atomic<int> next_job_id_;
// A flag indicating whether the current rocksdb database has any
// data that is not yet persisted into either WAL or SST file.
// Used when disableWAL is true.
std::atomic<bool> has_unpersisted_data_;
// if an attempt was made to flush all column families that
// the oldest log depends on but uncommited data in the oldest
// log prevents the log from being released.
// We must attempt to free the dependent memtables again
// at a later time after the transaction in the oldest
// log is fully commited.
bool unable_to_flush_oldest_log_;
static const int KEEP_LOG_FILE_NUM = 1000;
// MSVC version 1800 still does not have constexpr for ::max()
static const uint64_t kNoTimeOut = port::kMaxUint64;
std::string db_absolute_path_;
// The options to access storage files
const EnvOptions env_options_;
// Additonal options for compaction and flush
EnvOptions env_options_for_compaction_;
// Number of running IngestExternalFile() calls.
// REQUIRES: mutex held
int num_running_ingest_file_;
#ifndef ROCKSDB_LITE
WalManager wal_manager_;
#endif // ROCKSDB_LITE
// Unified interface for logging events
EventLogger event_logger_;
// A value of > 0 temporarily disables scheduling of background work
int bg_work_paused_;
// A value of > 0 temporarily disables scheduling of background compaction
int bg_compaction_paused_;
// Guard against multiple concurrent refitting
bool refitting_level_;
// Indicate DB was opened successfully
bool opened_successfully_;
// minimum log number still containing prepared data.
// this is used by FindObsoleteFiles to determine which
// flushed logs we must keep around because they still
// contain prepared data which has not been flushed or rolled back
std::priority_queue<uint64_t, std::vector<uint64_t>, std::greater<uint64_t>>
min_log_with_prep_;
// to be used in conjunction with min_log_with_prep_.
// once a transaction with data in log L is committed or rolled back
// rather than removing the value from the heap we add that value
// to prepared_section_completed_ which maps LOG -> instance_count
// since a log could contain multiple prepared sections
//
// when trying to determine the minimum log still active we first
// consult min_log_with_prep_. while that root value maps to
// a value > 0 in prepared_section_completed_ we decrement the
// instance_count for that log and pop the root value in
// min_log_with_prep_. This will work the same as a min_heap
// where we are deleteing arbitrary elements and the up heaping.
std::unordered_map<uint64_t, uint64_t> prepared_section_completed_;
std::mutex prep_heap_mutex_;
// Callback for compaction to check if a key is visible to a snapshot.
// REQUIRES: mutex held
std::unique_ptr<SnapshotChecker> snapshot_checker_;
// No copying allowed
DBImpl(const DBImpl&);
void operator=(const DBImpl&);
// Background threads call this function, which is just a wrapper around
// the InstallSuperVersion() function. Background threads carry
// sv_context which can have new_superversion already
// allocated.
Rewritten system for scheduling background work Summary: When scaling to higher number of column families, the worst bottleneck was MaybeScheduleFlushOrCompaction(), which did a for loop over all column families while holding a mutex. This patch addresses the issue. The approach is similar to our earlier efforts: instead of a pull-model, where we do something for every column family, we can do a push-based model -- when we detect that column family is ready to be flushed/compacted, we add it to the flush_queue_/compaction_queue_. That way we don't need to loop over every column family in MaybeScheduleFlushOrCompaction. Here are the performance results: Command: ./db_bench --write_buffer_size=268435456 --db_write_buffer_size=268435456 --db=/fast-rocksdb-tmp/rocks_lots_of_cf --use_existing_db=0 --open_files=55000 --statistics=1 --histogram=1 --disable_data_sync=1 --max_write_buffer_number=2 --sync=0 --benchmarks=fillrandom --threads=16 --num_column_families=5000 --disable_wal=1 --max_background_flushes=16 --max_background_compactions=16 --level0_file_num_compaction_trigger=2 --level0_slowdown_writes_trigger=2 --level0_stop_writes_trigger=3 --hard_rate_limit=1 --num=33333333 --writes=33333333 Before the patch: fillrandom : 26.950 micros/op 37105 ops/sec; 4.1 MB/s After the patch: fillrandom : 17.404 micros/op 57456 ops/sec; 6.4 MB/s Next bottleneck is VersionSet::AddLiveFiles, which is painfully slow when we have a lot of files. This is coming in the next patch, but when I removed that code, here's what I got: fillrandom : 7.590 micros/op 131758 ops/sec; 14.6 MB/s Test Plan: make check two stress tests: Big number of compactions and flushes: ./db_stress --threads=30 --ops_per_thread=20000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=15 --max_background_compactions=10 --max_background_flushes=10 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 max_background_flushes=0, to verify that this case also works correctly ./db_stress --threads=30 --ops_per_thread=2000000 --max_key=10000 --column_families=20 --clear_column_family_one_in=10000000 --verify_before_write=0 --reopen=3 --max_background_compactions=3 --max_background_flushes=0 --db=/fast-rocksdb-tmp/db_stress --prefixpercent=0 --iterpercent=0 --writepercent=75 --db_write_buffer_size=2000000 Reviewers: ljin, rven, yhchiang, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D30123
2014-12-19 20:38:12 +01:00
// All ColumnFamily state changes go through this function. Here we analyze
// the new state and we schedule background work if we detect that the new
// state needs flush or compaction.
void InstallSuperVersionAndScheduleWork(
ColumnFamilyData* cfd, SuperVersionContext* sv_context,
const MutableCFOptions& mutable_cf_options);
#ifndef ROCKSDB_LITE
using DB::GetPropertiesOfAllTables;
virtual Status GetPropertiesOfAllTables(ColumnFamilyHandle* column_family,
TablePropertiesCollection* props)
override;
virtual Status GetPropertiesOfTablesInRange(
ColumnFamilyHandle* column_family, const Range* range, std::size_t n,
TablePropertiesCollection* props) override;
#endif // ROCKSDB_LITE
bool GetIntPropertyInternal(ColumnFamilyData* cfd,
const DBPropertyInfo& property_info,
bool is_locked, uint64_t* value);
bool HasPendingManualCompaction();
bool HasExclusiveManualCompaction();
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
void AddManualCompaction(ManualCompactionState* m);
void RemoveManualCompaction(ManualCompactionState* m);
bool ShouldntRunManualCompaction(ManualCompactionState* m);
bool HaveManualCompaction(ColumnFamilyData* cfd);
Introduce bottom-pri thread pool for large universal compactions Summary: When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs. This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions. - Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads. - Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default. - Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic. - Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`). - Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free. Closes https://github.com/facebook/rocksdb/pull/2580 Differential Revision: D5422916 Pulled By: ajkr fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
2017-08-04 00:36:28 +02:00
bool MCOverlap(ManualCompactionState* m, ManualCompactionState* m1);
size_t GetWalPreallocateBlockSize(uint64_t write_buffer_size) const;
Env::WriteLifeTimeHint CalculateWALWriteHint() {
return Env::WLTH_SHORT;
}
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
// When set, we use a seprate queue for writes that dont write to memtable. In
// 2PC these are the writes at Prepare phase.
const bool two_write_queues_;
Optimize for serial commits in 2PC Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
2017-06-24 23:06:43 +02:00
const bool manual_wal_flush_;
// Increase the sequence number after writing each batch, whether memtable is
// disabled for that or not. Otherwise the sequence number is increased after
// writing each key into memtable. This implies that when disable_memtable is
// set, the seq is not increased at all.
//
// Default: false
const bool seq_per_batch_;
// LastSequence also indicates last published sequence visibile to the
// readers. Otherwise LastPublishedSequence should be used.
const bool last_seq_same_as_publish_seq_;
// It indicates that a customized gc algorithm must be used for
// flush/compaction and if it is not provided vis SnapshotChecker, we should
// disable gc to be safe.
const bool use_custom_gc_;
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
// Clients must periodically call SetPreserveDeletesSequenceNumber()
// to advance this seqnum. Default value is 0 which means ALL deletes are
// preserved. Note that this has no effect if DBOptions.preserve_deletes
// is set to false.
std::atomic<SequenceNumber> preserve_deletes_seqnum_;
const bool preserve_deletes_;
};
extern Options SanitizeOptions(const std::string& db,
const Options& src);
extern DBOptions SanitizeOptions(const std::string& db, const DBOptions& src);
extern CompressionType GetCompressionFlush(
const ImmutableCFOptions& ioptions,
const MutableCFOptions& mutable_cf_options);
// Fix user-supplied options to be reasonable
template <class T, class V>
static void ClipToRange(T* ptr, V minvalue, V maxvalue) {
if (static_cast<V>(*ptr) > maxvalue) *ptr = maxvalue;
if (static_cast<V>(*ptr) < minvalue) *ptr = minvalue;
}
} // namespace rocksdb