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

651 lines
25 KiB

// Copyright (c) 2013, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#pragma once
#include <atomic>
#include <deque>
#include <limits>
#include <set>
#include <utility>
#include <vector>
#include <string>
#include "db/dbformat.h"
#include "db/log_writer.h"
#include "db/snapshot.h"
#include "db/column_family.h"
#include "db/version_edit.h"
#include "memtable_list.h"
#include "port/port.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/memtablerep.h"
#include "rocksdb/transaction_log.h"
#include "util/autovector.h"
#include "util/stop_watch.h"
#include "util/thread_local.h"
#include "db/internal_stats.h"
namespace rocksdb {
class MemTable;
class TableCache;
class Version;
class VersionEdit;
class VersionSet;
class CompactionFilterV2;
class Arena;
class DBImpl : public DB {
public:
DBImpl(const DBOptions& options, const std::string& dbname);
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);
using DB::Merge;
virtual Status Merge(const WriteOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
const Slice& value);
using DB::Delete;
virtual Status Delete(const WriteOptions& options,
ColumnFamilyHandle* column_family, const Slice& key);
using DB::Write;
virtual Status Write(const WriteOptions& options, WriteBatch* updates);
using DB::Get;
virtual Status Get(const ReadOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
std::string* value);
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);
virtual Status CreateColumnFamily(const ColumnFamilyOptions& options,
const std::string& column_family,
ColumnFamilyHandle** handle);
virtual Status DropColumnFamily(ColumnFamilyHandle* column_family);
// 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);
using DB::NewIterator;
virtual Iterator* NewIterator(const ReadOptions& options,
ColumnFamilyHandle* column_family);
virtual Status NewIterators(
const ReadOptions& options,
const std::vector<ColumnFamilyHandle*>& column_families,
std::vector<Iterator*>* iterators);
virtual const Snapshot* GetSnapshot();
virtual void ReleaseSnapshot(const Snapshot* snapshot);
using DB::GetProperty;
virtual bool GetProperty(ColumnFamilyHandle* column_family,
const Slice& property, std::string* value);
using DB::GetIntProperty;
virtual bool GetIntProperty(ColumnFamilyHandle* column_family,
const Slice& property, uint64_t* value) override;
using DB::GetApproximateSizes;
virtual void GetApproximateSizes(ColumnFamilyHandle* column_family,
const Range* range, int n, uint64_t* sizes);
using DB::CompactRange;
virtual Status CompactRange(ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end,
bool reduce_level = false, int target_level = -1,
uint32_t target_path_id = 0);
using DB::NumberLevels;
virtual int NumberLevels(ColumnFamilyHandle* column_family);
using DB::MaxMemCompactionLevel;
virtual int MaxMemCompactionLevel(ColumnFamilyHandle* column_family);
using DB::Level0StopWriteTrigger;
virtual int Level0StopWriteTrigger(ColumnFamilyHandle* column_family);
[RocksDB] BackupableDB Summary: In this diff I present you BackupableDB v1. You can easily use it to backup your DB and it will do incremental snapshots for you. Let's first describe how you would use BackupableDB. It's inheriting StackableDB interface so you can easily construct it with your DB object -- it will add a method RollTheSnapshot() to the DB object. When you call RollTheSnapshot(), current snapshot of the DB will be stored in the backup dir. To restore, you can just call RestoreDBFromBackup() on a BackupableDB (which is a static method) and it will restore all files from the backup dir. In the next version, it will even support automatic backuping every X minutes. There are multiple things you can configure: 1. backup_env and db_env can be different, which is awesome because then you can easily backup to HDFS or wherever you feel like. 2. sync - if true, it *guarantees* backup consistency on machine reboot 3. number of snapshots to keep - this will keep last N snapshots around if you want, for some reason, be able to restore from an earlier snapshot. All the backuping is done in incremental fashion - if we already have 00010.sst, we will not copy it again. *IMPORTANT* -- This is based on assumption that 00010.sst never changes - two files named 00010.sst from the same DB will always be exactly the same. Is this true? I always copy manifest, current and log files. 4. You can decide if you want to flush the memtables before you backup, or you're fine with backing up the log files -- either way, you get a complete and consistent view of the database at a time of backup. 5. More things you can find in BackupableDBOptions Here is the directory structure I use: backup_dir/CURRENT_SNAPSHOT - just 4 bytes holding the latest snapshot 0, 1, 2, ... - files containing serialized version of each snapshot - containing a list of files files/*.sst - sst files shared between snapshots - if one snapshot references 00010.sst and another one needs to backup it from the DB, it will just reference the same file files/ 0/, 1/, 2/, ... - snapshot directories containing private snapshot files - current, manifest and log files All the files are ref counted and deleted immediatelly when they get out of scope. Some other stuff in this diff: 1. Added GetEnv() method to the DB. Discussed with @haobo and we agreed that it seems right thing to do. 2. Fixed StackableDB interface. The way it was set up before, I was not able to implement BackupableDB. Test Plan: I have a unittest, but please don't look at this yet. I just hacked it up to help me with debugging. I will write a lot of good tests and update the diff. Also, `make asan_check` Reviewers: dhruba, haobo, emayanke Reviewed By: dhruba CC: leveldb, haobo Differential Revision: https://reviews.facebook.net/D14295
11 years ago
virtual const std::string& GetName() const;
virtual Env* GetEnv() const;
using DB::GetOptions;
virtual const Options& GetOptions(ColumnFamilyHandle* column_family) const;
using DB::Flush;
virtual Status Flush(const FlushOptions& options,
ColumnFamilyHandle* column_family);
virtual SequenceNumber GetLatestSequenceNumber() const;
#ifndef ROCKSDB_LITE
virtual Status DisableFileDeletions();
virtual Status EnableFileDeletions(bool force);
// All the returned filenames start with "/"
virtual Status GetLiveFiles(std::vector<std::string>&,
uint64_t* manifest_file_size,
bool flush_memtable = true);
virtual Status GetSortedWalFiles(VectorLogPtr& files);
virtual Status GetUpdatesSince(
SequenceNumber seq_number, unique_ptr<TransactionLogIterator>* iter,
const TransactionLogIterator::ReadOptions&
read_options = TransactionLogIterator::ReadOptions());
virtual Status DeleteFile(std::string name);
virtual void GetLiveFilesMetaData(std::vector<LiveFileMetaData>* metadata);
#endif // ROCKSDB_LITE
// 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);
Status RunManualCompaction(ColumnFamilyData* cfd, int input_level,
int output_level, uint32_t output_path_id,
const Slice* begin, const Slice* end);
#ifndef ROCKSDB_LITE
// 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,
ColumnFamilyHandle* column_family = nullptr);
// Force current memtable contents to be flushed.
Status TEST_FlushMemTable(bool wait = true);
// Wait for memtable compaction
Status TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family = nullptr);
// Wait for any compaction
Status TEST_WaitForCompact();
// 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.
Iterator* TEST_NewInternalIterator(ColumnFamilyHandle* column_family =
nullptr);
// 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();
// Trigger's a background call for testing.
void TEST_PurgeObsoleteteWAL();
// get total level0 file size. Only for testing.
uint64_t TEST_GetLevel0TotalSize();
void TEST_SetDefaultTimeToCheck(uint64_t default_interval_to_delete_obsolete_WAL)
{
default_interval_to_delete_obsolete_WAL_ = default_interval_to_delete_obsolete_WAL;
}
void TEST_GetFilesMetaData(ColumnFamilyHandle* column_family,
std::vector<std::vector<FileMetaData>>* metadata);
Status TEST_ReadFirstRecord(const WalFileType type, const uint64_t number,
SequenceNumber* sequence);
Status TEST_ReadFirstLine(const std::string& fname, SequenceNumber* sequence);
#endif // NDEBUG
// Structure to store information for candidate files to delete.
struct CandidateFileInfo {
std::string file_name;
uint32_t path_id;
CandidateFileInfo(std::string name, uint32_t path)
: file_name(name), path_id(path) {}
bool operator==(const CandidateFileInfo& other) const {
return file_name == other.file_name && path_id == other.path_id;
}
};
// needed for CleanupIteratorState
struct DeletionState {
inline bool HaveSomethingToDelete() const {
return candidate_files.size() ||
sst_delete_files.size() ||
log_delete_files.size();
}
// a list of all files that we'll consider deleting
// (every once in a while this is filled up with all files
// in the DB directory)
std::vector<CandidateFileInfo> candidate_files;
// the list of all live sst files that cannot be deleted
std::vector<FileDescriptor> sst_live;
// a list of sst files that we need to delete
std::vector<FileMetaData*> sst_delete_files;
// a list of log files that we need to delete
std::vector<uint64_t> log_delete_files;
// a list of memtables to be free
autovector<MemTable*> memtables_to_free;
autovector<SuperVersion*> superversions_to_free;
SuperVersion* new_superversion; // if nullptr no new superversion
// the current manifest_file_number, log_number and prev_log_number
// that corresponds to the set of files in 'live'.
uint64_t manifest_file_number, pending_manifest_file_number, log_number,
prev_log_number;
explicit DeletionState(bool create_superversion = false) {
manifest_file_number = 0;
pending_manifest_file_number = 0;
log_number = 0;
prev_log_number = 0;
new_superversion = create_superversion ? new SuperVersion() : nullptr;
}
~DeletionState() {
// free pending memtables
for (auto m : memtables_to_free) {
delete m;
}
// free superversions
for (auto s : superversions_to_free) {
delete s;
}
// if new_superversion was not used, it will be non-nullptr and needs
// to be freed here
delete new_superversion;
}
};
// 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
// options_.delete_obsolete_files_period_micros microseconds ago,
// it will not fill up the deletion_state
void FindObsoleteFiles(DeletionState& deletion_state,
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(DeletionState& deletion_state);
ColumnFamilyHandle* DefaultColumnFamily() const;
protected:
Env* const env_;
const std::string dbname_;
unique_ptr<VersionSet> versions_;
const DBOptions options_;
Statistics* stats_;
Iterator* NewInternalIterator(const ReadOptions&, ColumnFamilyData* cfd,
SuperVersion* super_version,
Arena* arena = nullptr);
private:
friend class DB;
friend class InternalStats;
#ifndef ROCKSDB_LITE
friend class TailingIterator;
friend class ForwardIterator;
#endif
friend struct SuperVersion;
struct CompactionState;
struct Writer;
Status NewDB();
// 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);
void MaybeIgnoreError(Status* s) const;
const Status CreateArchivalDirectory();
// Delete any unneeded files and stale in-memory entries.
void DeleteObsoleteFiles();
// 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, bool* madeProgress,
DeletionState& deletion_state,
LogBuffer* log_buffer);
Refactor Recover() code Summary: This diff does two things: * Rethinks how we call Recover() with read_only option. Before, we call it with pointer to memtable where we'd like to apply those changes to. This memtable is set in db_impl_readonly.cc and it's actually DBImpl::mem_. Why don't we just apply updates to mem_ right away? It seems more intuitive. * Changes when we apply updates to manifest. Before, the process is to recover all the logs, flush it to sst files and then do one giant commit that atomically adds all recovered sst files and sets the next log number. This works good enough, but causes some small troubles for my column family approach, since I can't have one VersionEdit apply to more than single column family[1]. The change here is to commit the files recovered from logs right away. Here is the state of the world before the change: 1. Recover log 5, add new sst files to edit 2. Recover log 7, add new sst files to edit 3. Recover log 8, add new sst files to edit 4. Commit all added sst files to manifest and mark log files 5, 7 and 8 as recoverd (via SetLogNumber(9) function) After the change, we'll do: 1. Recover log 5, commit the new sst files and set log 5 as recovered 2. Recover log 7, commit the new sst files and set log 7 as recovered 3. Recover log 8, commit the new sst files and set log 8 as recovered The added (small) benefit is that if we fail after (2), the new recovery will only have to recover log 8. In previous case, we'll have to restart the recovery from the beginning. The bigger benefit will be to enable easier integration of multiple column families in Recovery code path. [1] I'm happy to dicuss this decison, but I believe this is the cleanest way to go. It also makes backward compatibility much easier. We don't have a requirement of adding multiple column families atomically. Test Plan: make check Reviewers: dhruba, haobo, kailiu, sdong Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15237
11 years ago
Status RecoverLogFile(uint64_t log_number, SequenceNumber* max_sequence,
bool read_only);
// The following two methods are used to flush a memtable to
// storage. The first one is used atdatabase 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(ColumnFamilyData* cfd, MemTable* mem,
VersionEdit* edit);
Status WriteLevel0Table(ColumnFamilyData* cfd, autovector<MemTable*>& mems,
VersionEdit* edit, uint64_t* filenumber,
LogBuffer* log_buffer);
uint64_t SlowdownAmount(int n, double bottom, double top);
// TODO(icanadi) free superversion_to_free and old_log outside of mutex
Status MakeRoomForWrite(ColumnFamilyData* cfd,
bool force /* flush even if there is room? */,
autovector<SuperVersion*>* superversions_to_free,
autovector<log::Writer*>* logs_to_free,
uint64_t expiration_time);
void BuildBatchGroup(Writer** last_writer,
autovector<WriteBatch*>* write_batch_group);
// Force current memtable contents to be flushed.
Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options);
// Wait for memtable flushed
Status WaitForFlushMemTable(ColumnFamilyData* cfd);
void RecordFlushIOStats();
void RecordCompactionIOStats();
void MaybeScheduleFlushOrCompaction();
static void BGWorkCompaction(void* db);
static void BGWorkFlush(void* db);
void BackgroundCallCompaction();
void BackgroundCallFlush();
Status BackgroundCompaction(bool* madeProgress, DeletionState& deletion_state,
LogBuffer* log_buffer);
Status BackgroundFlush(bool* madeProgress, DeletionState& deletion_state,
LogBuffer* log_buffer);
void CleanupCompaction(CompactionState* compact, Status status);
Status DoCompactionWork(CompactionState* compact,
DeletionState& deletion_state,
LogBuffer* log_buffer);
// This function is called as part of compaction. It enables Flush process to
// preempt compaction, since it's higher prioirty
// Returns: micros spent executing
uint64_t CallFlushDuringCompaction(ColumnFamilyData* cfd,
DeletionState& deletion_state,
LogBuffer* log_buffer);
// Call compaction filter if is_compaction_v2 is not true. Then iterate
// through input and compact the kv-pairs
Status ProcessKeyValueCompaction(
bool is_snapshot_supported,
SequenceNumber visible_at_tip,
SequenceNumber earliest_snapshot,
SequenceNumber latest_snapshot,
DeletionState& deletion_state,
bool bottommost_level,
int64_t& imm_micros,
Iterator* input,
CompactionState* compact,
bool is_compaction_v2,
LogBuffer* log_buffer);
// Call compaction_filter_v2->Filter() on kv-pairs in compact
void CallCompactionFilterV2(CompactionState* compact,
CompactionFilterV2* compaction_filter_v2);
Status OpenCompactionOutputFile(CompactionState* compact);
Status FinishCompactionOutputFile(CompactionState* compact, Iterator* input);
Status InstallCompactionResults(CompactionState* compact,
LogBuffer* log_buffer);
void AllocateCompactionOutputFileNumbers(CompactionState* compact);
void ReleaseCompactionUnusedFileNumbers(CompactionState* compact);
#ifdef ROCKSDB_LITE
void PurgeObsoleteWALFiles() {
// this function is used for archiving WAL files. we don't need this in
// ROCKSDB_LITE
}
#else
void PurgeObsoleteWALFiles();
Status GetSortedWalsOfType(const std::string& path,
VectorLogPtr& log_files,
WalFileType type);
// Requires: all_logs should be sorted with earliest log file first
// Retains all log files in all_logs which contain updates with seq no.
// Greater Than or Equal to the requested SequenceNumber.
Status RetainProbableWalFiles(VectorLogPtr& all_logs,
const SequenceNumber target);
Status ReadFirstRecord(const WalFileType type, const uint64_t number,
SequenceNumber* sequence);
Status ReadFirstLine(const std::string& fname, SequenceNumber* sequence);
#endif // ROCKSDB_LITE
void PrintStatistics();
// dump rocksdb.stats to LOG
void MaybeDumpStats();
Add a new mem-table representation based on cuckoo hash. Summary: = Major Changes = * Add a new mem-table representation, HashCuckooRep, which is based cuckoo hash. Cuckoo hash uses multiple hash functions. This allows each key to have multiple possible locations in the mem-table. - Put: When insert a key, it will try to find whether one of its possible locations is vacant and store the key. If none of its possible locations are available, then it will kick out a victim key and store at that location. The kicked-out victim key will then be stored at a vacant space of its possible locations or kick-out another victim. In this diff, the kick-out path (known as cuckoo-path) is found using BFS, which guarantees to be the shortest. - Get: Simply tries all possible locations of a key --- this guarantees worst-case constant time complexity. - Time complexity: O(1) for Get, and average O(1) for Put if the fullness of the mem-table is below 80%. - Default using two hash functions, the number of hash functions used by the cuckoo-hash may dynamically increase if it fails to find a short-enough kick-out path. - Currently, HashCuckooRep does not support iteration and snapshots, as our current main purpose of this is to optimize point access. = Minor Changes = * Add IsSnapshotSupported() to DB to indicate whether the current DB supports snapshots. If it returns false, then DB::GetSnapshot() will always return nullptr. Test Plan: Run existing tests. Will develop a test specifically for cuckoo hash in the next diff. Reviewers: sdong, haobo Reviewed By: sdong CC: leveldb, dhruba, igor Differential Revision: https://reviews.facebook.net/D16155
11 years ago
// Return true if the current db supports snapshot. If the current
// DB does not support snapshot, then calling GetSnapshot() will always
// return nullptr.
//
// @see GetSnapshot()
virtual bool IsSnapshotSupported() const;
// 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, 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);
// 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_;
// State below is protected by mutex_
port::Mutex mutex_;
port::AtomicPointer shutting_down_;
// This condition variable is signaled on these conditions:
// * whenever bg_compaction_scheduled_ goes down to 0
// * if bg_manual_only_ > 0, whenever a compaction finishes, even if it hasn't
// made any progress
// * whenever a compaction made any progress
// * whenever bg_flush_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 flush or compaction
port::CondVar bg_cv_;
uint64_t logfile_number_;
unique_ptr<log::Writer> log_;
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
10 years ago
InternalStats* default_cf_internal_stats_;
unique_ptr<ColumnFamilyMemTablesImpl> column_family_memtables_;
struct LogFileNumberSize {
explicit LogFileNumberSize(uint64_t _number)
: number(_number), size(0), getting_flushed(false) {}
void AddSize(uint64_t new_size) { size += new_size; }
uint64_t number;
uint64_t size;
bool getting_flushed;
};
std::deque<LogFileNumberSize> alive_log_files_;
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_;
std::unique_ptr<Directory> db_directory_;
// Queue of writers.
std::deque<Writer*> writers_;
WriteBatch tmp_batch_;
SnapshotList snapshots_;
// cache for ReadFirstRecord() calls
std::unordered_map<uint64_t, SequenceNumber> read_first_record_cache_;
port::Mutex read_first_record_cache_mutex_;
// Set of table files to protect from deletion because they are
// part of ongoing compactions.
// map from pending file number ID to their path IDs.
FileNumToPathIdMap pending_outputs_;
// At least one compaction or flush job is pending but not yet scheduled
// because of the max background thread limit.
bool bg_schedule_needed_;
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
11 years ago
// count how many background compactions are running or have been scheduled
int bg_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
11 years ago
// If non-zero, MaybeScheduleFlushOrCompaction() will only schedule manual
// compactions (if manual_compaction_ is not null). This mechanism enables
// manual compactions to wait until all other compactions are finished.
int bg_manual_only_;
// number of background memtable flush jobs, submitted to the HIGH pool
int bg_flush_scheduled_;
// Information for a manual compaction
struct ManualCompaction {
ColumnFamilyData* cfd;
int input_level;
int output_level;
uint32_t output_path_id;
bool done;
Status status;
bool in_progress; // compaction request being processed?
const InternalKey* begin; // nullptr means beginning of key range
const InternalKey* end; // nullptr means end of key range
InternalKey tmp_storage; // Used to keep track of compaction progress
};
ManualCompaction* manual_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 was invoked
uint64_t delete_obsolete_files_last_run_;
// last time when PurgeObsoleteWALFiles ran.
uint64_t purge_wal_files_last_run_;
// last time stats were dumped to LOG
std::atomic<uint64_t> last_stats_dump_time_microsec_;
// obsolete files will be deleted every this seconds if ttl deletion is
// enabled and archive size_limit is disabled.
uint64_t default_interval_to_delete_obsolete_WAL_;
bool flush_on_destroy_; // Used when disableWAL is true.
static const int KEEP_LOG_FILE_NUM = 1000;
static const uint64_t kNoTimeOut = std::numeric_limits<uint64_t>::max();
std::string db_absolute_path_;
// count of the number of contiguous delaying writes
int delayed_writes_;
// The options to access storage files
const EnvOptions storage_options_;
// A value of true temporarily disables scheduling of background work
bool bg_work_gate_closed_;
// Guard against multiple concurrent refitting
bool refitting_level_;
// Indicate DB was opened successfully
bool opened_successfully_;
// No copying allowed
DBImpl(const DBImpl&);
void operator=(const DBImpl&);
// dump the delayed_writes_ to the log file and reset counter.
void DelayLoggingAndReset();
// Return the earliest snapshot where seqno is visible.
// Store the snapshot right before that, if any, in prev_snapshot
inline SequenceNumber findEarliestVisibleSnapshot(
SequenceNumber in,
std::vector<SequenceNumber>& snapshots,
SequenceNumber* prev_snapshot);
// Background threads call this function, which is just a wrapper around
// the cfd->InstallSuperVersion() function. Background threads carry
// deletion_state which can have new_superversion already allocated.
void InstallSuperVersion(ColumnFamilyData* cfd,
DeletionState& deletion_state);
// Find Super version and reference it. Based on options, it might return
// the thread local cached one.
inline SuperVersion* GetAndRefSuperVersion(ColumnFamilyData* cfd);
// 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.
inline void ReturnAndCleanupSuperVersion(ColumnFamilyData* cfd,
SuperVersion* sv);
#ifndef ROCKSDB_LITE
using DB::GetPropertiesOfAllTables;
virtual Status GetPropertiesOfAllTables(ColumnFamilyHandle* column_family,
TablePropertiesCollection* props)
override;
#endif // ROCKSDB_LITE
// 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, std::string* value,
bool* value_found = nullptr);
bool GetIntPropertyInternal(ColumnFamilyHandle* column_family,
DBPropertyType property_type,
bool need_out_of_mutex, uint64_t* value);
};
// Sanitize db options. The caller should delete result.info_log if
// it is not equal to src.info_log.
extern Options SanitizeOptions(const std::string& db,
const InternalKeyComparator* icmp,
const InternalFilterPolicy* ipolicy,
const Options& src);
extern DBOptions SanitizeOptions(const std::string& db, const DBOptions& src);
} // namespace rocksdb