rocksdb/db/db_impl.h

462 lines
16 KiB
C
Raw Normal View History

// 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 <set>
#include <vector>
#include "db/dbformat.h"
#include "db/log_writer.h"
#include "db/snapshot.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/memtablerep.h"
#include "rocksdb/transaction_log.h"
#include "port/port.h"
#include "util/stats_logger.h"
#include "memtablelist.h"
namespace rocksdb {
class MemTable;
class TableCache;
class Version;
class VersionEdit;
class VersionSet;
class DBImpl : public DB {
public:
DBImpl(const Options& options, const std::string& dbname);
virtual ~DBImpl();
// Implementations of the DB interface
virtual Status Put(const WriteOptions&, const Slice& key, const Slice& value);
virtual Status Merge(const WriteOptions&, const Slice& key,
const Slice& value);
virtual Status Delete(const WriteOptions&, const Slice& key);
virtual Status Write(const WriteOptions& options, WriteBatch* updates);
virtual Status Get(const ReadOptions& options,
const Slice& key,
std::string* value);
virtual std::vector<Status> MultiGet(const ReadOptions& options,
const std::vector<Slice>& keys,
std::vector<std::string>* values);
// 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.
virtual bool KeyMayExist(const ReadOptions& options,
const Slice& key,
std::string* value,
bool* value_found = nullptr);
virtual Iterator* NewIterator(const ReadOptions&);
virtual const Snapshot* GetSnapshot();
virtual void ReleaseSnapshot(const Snapshot* snapshot);
virtual bool GetProperty(const Slice& property, std::string* value);
virtual void GetApproximateSizes(const Range* range, int n, uint64_t* sizes);
virtual void CompactRange(const Slice* begin, const Slice* end,
bool reduce_level = false, int target_level = -1);
virtual int NumberLevels();
virtual int MaxMemCompactionLevel();
virtual int Level0StopWriteTrigger();
virtual Status Flush(const FlushOptions& options);
virtual Status DisableFileDeletions();
virtual Status EnableFileDeletions();
virtual Status GetLiveFiles(std::vector<std::string>&,
uint64_t* manifest_file_size,
bool flush_memtable = true);
virtual Status GetSortedWalFiles(VectorLogPtr& files);
virtual SequenceNumber GetLatestSequenceNumber() const;
virtual Status GetUpdatesSince(SequenceNumber seq_number,
unique_ptr<TransactionLogIterator>* iter);
virtual Status DeleteFile(std::string name);
virtual void GetLiveFilesMetaData(
std::vector<LiveFileMetaData> *metadata);
// Extra methods (for testing) that are not in the public DB interface
// Compact any files in the named level that overlap [*begin, *end]
void TEST_CompactRange(int level, const Slice* begin, const Slice* end);
// Force current memtable contents to be flushed.
Status TEST_FlushMemTable();
// Wait for memtable compaction
Status TEST_WaitForFlushMemTable();
// 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();
// Return the maximum overlapping data (in bytes) at next level for any
// file at a level >= 1.
int64_t TEST_MaxNextLevelOverlappingBytes();
// Simulate a db crash, no elegant closing of database.
void TEST_Destroy_DBImpl();
// 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() { return versions_->NumLevelBytes(0);}
void TEST_SetDefaultTimeToCheck(uint64_t default_interval_to_delete_obsolete_WAL)
{
default_interval_to_delete_obsolete_WAL_ = default_interval_to_delete_obsolete_WAL;
}
protected:
Env* const env_;
const std::string dbname_;
unique_ptr<VersionSet> versions_;
const InternalKeyComparator internal_comparator_;
const Options options_; // options_.comparator == &internal_comparator_
const Comparator* user_comparator() const {
return internal_comparator_.user_comparator();
}
MemTable* GetMemTable() {
return mem_;
}
Iterator* NewInternalIterator(const ReadOptions&,
SequenceNumber* latest_snapshot);
private:
friend class DB;
struct CompactionState;
struct Writer;
struct DeletionState;
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(VersionEdit* edit, MemTable* external_table = nullptr,
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(bool* madeProgress = nullptr);
Status RecoverLogFile(uint64_t log_number,
VersionEdit* edit,
SequenceNumber* max_sequence,
MemTable* external_table);
// 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(MemTable* mem, VersionEdit* edit);
Status WriteLevel0Table(std::vector<MemTable*> &mems, VersionEdit* edit,
uint64_t* filenumber);
uint64_t SlowdownAmount(int n, int top, int bottom);
Status MakeRoomForWrite(bool force /* compact even if there is room? */);
WriteBatch* BuildBatchGroup(Writer** last_writer);
// Force current memtable contents to be flushed.
Status FlushMemTable(const FlushOptions& options);
// Wait for memtable flushed
Status WaitForFlushMemTable();
void MaybeScheduleLogDBDeployStats();
static void BGLogDBDeployStats(void* db);
void LogDBDeployStats();
void MaybeScheduleFlushOrCompaction();
static void BGWorkCompaction(void* db);
static void BGWorkFlush(void* db);
void BackgroundCallCompaction();
void BackgroundCallFlush();
Status BackgroundCompaction(bool* madeProgress,DeletionState& deletion_state);
Status BackgroundFlush(bool* madeProgress);
void CleanupCompaction(CompactionState* compact, Status status);
Status DoCompactionWork(CompactionState* compact);
Status OpenCompactionOutputFile(CompactionState* compact);
Status FinishCompactionOutputFile(CompactionState* compact, Iterator* input);
Status InstallCompactionResults(CompactionState* compact);
void AllocateCompactionOutputFileNumbers(CompactionState* compact);
void ReleaseCompactionUnusedFileNumbers(CompactionState* compact);
// Returns the list of live files in 'live' and the list
// of all files in the filesystem in 'allfiles'.
void FindObsoleteFiles(DeletionState& deletion_state);
// Diffs the files listed in filenames and those that do not
// belong to live files are posibly removed. If the removed file
// is a sst file, then it returns the file number in files_to_evict.
void PurgeObsoleteFiles(DeletionState& deletion_state);
// Removes the file listed in files_to_evict from the table_cache
void EvictObsoleteFiles(DeletionState& deletion_state);
Status DeleteLogFile(uint64_t number);
void PurgeObsoleteWALFiles();
Status AppendSortedWalsOfType(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);
// return true if
bool CheckWalFileExistsAndEmpty(const WalFileType type,
const uint64_t number);
Status ReadFirstRecord(const WalFileType type, const uint64_t number,
WriteBatch* const result);
Status ReadFirstLine(const std::string& fname, WriteBatch* const batch);
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(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.
void ReFitLevel(int level, int target_level = -1);
// Constant after construction
const InternalFilterPolicy internal_filter_policy_;
bool owns_info_log_;
// table_cache_ provides its own synchronization
unique_ptr<TableCache> 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_;
port::CondVar bg_cv_; // Signalled when background work finishes
std::shared_ptr<MemTableRepFactory> mem_rep_factory_;
MemTable* mem_;
MemTableList imm_; // Memtable that are not changing
uint64_t logfile_number_;
unique_ptr<log::Writer> log_;
std::string host_name_;
// Queue of writers.
std::deque<Writer*> writers_;
WriteBatch tmp_batch_;
SnapshotList snapshots_;
// Set of table files to protect from deletion because they are
// part of ongoing compactions.
std::set<uint64_t> pending_outputs_;
// count how many background compaction been scheduled or is running?
int bg_compaction_scheduled_;
// number of background memtable flush jobs, submitted to the HIGH pool
int bg_flush_scheduled_;
// Has a background stats log thread scheduled?
bool bg_logstats_scheduled_;
// Information for a manual compaction
struct ManualCompaction {
int level;
bool done;
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_;
std::unique_ptr<StatsLogger> logger_;
int64_t volatile last_log_ts;
// shall we disable deletion of obsolete files
bool 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_;
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
// These count the number of microseconds for which MakeRoomForWrite stalls.
uint64_t stall_level0_slowdown_;
uint64_t stall_memtable_compaction_;
uint64_t stall_level0_num_files_;
std::vector<uint64_t> stall_leveln_slowdown_;
uint64_t stall_level0_slowdown_count_;
uint64_t stall_memtable_compaction_count_;
uint64_t stall_level0_num_files_count_;
std::vector<uint64_t> stall_leveln_slowdown_count_;
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
// Time at which this instance was started.
const uint64_t started_at_;
bool flush_on_destroy_; // Used when disableWAL is true.
// Per level compaction stats. stats_[level] stores the stats for
// compactions that produced data for the specified "level".
struct CompactionStats {
uint64_t micros;
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
// Bytes read from level N during compaction between levels N and N+1
int64_t bytes_readn;
// Bytes read from level N+1 during compaction between levels N and N+1
int64_t bytes_readnp1;
// Total bytes written during compaction between levels N and N+1
int64_t bytes_written;
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
// Files read from level N during compaction between levels N and N+1
int files_in_leveln;
// Files read from level N+1 during compaction between levels N and N+1
int files_in_levelnp1;
// Files written during compaction between levels N and N+1
int files_out_levelnp1;
// Number of compactions done
int count;
CompactionStats() : micros(0), bytes_readn(0), bytes_readnp1(0),
bytes_written(0), files_in_leveln(0),
files_in_levelnp1(0), files_out_levelnp1(0),
count(0) { }
void Add(const CompactionStats& c) {
this->micros += c.micros;
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
this->bytes_readn += c.bytes_readn;
this->bytes_readnp1 += c.bytes_readnp1;
this->bytes_written += c.bytes_written;
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
this->files_in_leveln += c.files_in_leveln;
this->files_in_levelnp1 += c.files_in_levelnp1;
this->files_out_levelnp1 += c.files_out_levelnp1;
this->count += 1;
}
};
Improve statistics Summary: This adds more statistics to be reported by GetProperty("leveldb.stats"). The new stats include time spent waiting on stalls in MakeRoomForWrite. This also includes the total amplification rate where that is: (#bytes of sequential IO during compaction) / (#bytes from Put) This also includes a lot more data for the per-level compaction report. * Rn(MB) - MB read from level N during compaction between levels N and N+1 * Rnp1(MB) - MB read from level N+1 during compaction between levels N and N+1 * Wnew(MB) - new data written to the level during compaction * Amplify - ( Write(MB) + Rnp1(MB) ) / Rn(MB) * Rn - files read from level N during compaction between levels N and N+1 * Rnp1 - files read from level N+1 during compaction between levels N and N+1 * Wnp1 - files written to level N+1 during compaction between levels N and N+1 * NewW - new files written to level N+1 during compaction * Count - number of compactions done for this level This is the new output from DB::GetProperty("leveldb.stats"). The old output stopped at Write(MB) Compactions Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count ------------------------------------------------------------------------------------------------------------------------------------- 0 3 6 33 0 576 0 0 576 -1.0 0.0 1.3 0 0 0 0 290 1 127 242 351 5316 5314 570 4747 567 17.0 12.1 12.1 287 2399 2685 286 32 2 161 328 54 822 824 326 496 328 4.0 1.9 1.9 160 251 411 160 161 Amplification: 22.3 rate, 0.56 GB in, 12.55 GB out Uptime(secs): 439.8 Stalls(secs): 206.938 level0_slowdown, 0.000 level0_numfiles, 24.129 memtable_compaction Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - (cherry picked from commit ecdeead38f86cc02e754d0032600742c4f02fec8) Reviewers: dhruba Differential Revision: https://reviews.facebook.net/D6153
2012-10-23 19:34:09 +02:00
std::vector<CompactionStats> stats_;
Improve output for GetProperty('leveldb.stats') Summary: Display separate values for read, write & total compaction IO. Display compaction amplification and write amplification. Add similar values for the period since the last call to GetProperty. Results since the server started are reported as "cumulative" stats. Results since the last call to GetProperty are reported as "interval" stats. Level Files Size(MB) Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count Ln-stall ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- 0 7 13 21 0 211 0 0 211 0.0 0.0 10.1 0 0 0 0 113 0.0 1 79 157 88 993 989 198 795 194 9.0 11.3 11.2 106 405 502 97 14 0.0 2 19 36 5 63 63 37 27 36 2.4 12.3 12.2 19 14 32 18 12 0.0 >>>>>>>>>>>>>>>>>>>>>>>>> text below has been is new and/or reformatted Uptime(secs): 122.2 total, 0.9 interval Compaction IO cumulative (GB): 0.21 new, 1.03 read, 1.23 write, 2.26 read+write Compaction IO cumulative (MB/sec): 1.7 new, 8.6 read, 10.3 write, 19.0 read+write Amplification cumulative: 6.0 write, 11.0 compaction Compaction IO interval (MB): 5.59 new, 0.00 read, 5.59 write, 5.59 read+write Compaction IO interval (MB/sec): 6.5 new, 0.0 read, 6.5 write, 6.5 read+write Amplification interval: 1.0 write, 1.0 compaction >>>>>>>>>>>>>>>>>>>>>>>> text above is new and/or reformatted Stalls(secs): 90.574 level0_slowdown, 0.000 level0_numfiles, 10.165 memtable_compaction, 0.000 leveln_slowdown Task ID: # Blame Rev: Test Plan: make check, run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - Reviewers: haobo Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D11049
2013-06-03 17:16:16 +02:00
// Used to compute per-interval statistics
struct StatsSnapshot {
uint64_t bytes_read_;
uint64_t bytes_written_;
uint64_t bytes_new_;
double seconds_up_;
StatsSnapshot() : bytes_read_(0), bytes_written_(0),
bytes_new_(0), seconds_up_(0) {}
};
StatsSnapshot last_stats_;
static const int KEEP_LOG_FILE_NUM = 1000;
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_;
// 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);
// Function that Get and KeyMayExist call with no_io true or false
// Note: 'value_found' from KeyMayExist propagates here
Status GetImpl(const ReadOptions& options,
const Slice& key,
std::string* value,
bool* value_found = nullptr);
};
// 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);
// Determine compression type, based on user options, level of the output
// file and whether compression is disabled.
// If enable_compression is false, then compression is always disabled no
// matter what the values of the other two parameters are.
// Otherwise, the compression type is determined based on options and level.
CompressionType GetCompressionType(const Options& options, int level,
const bool enable_compression);
} // namespace rocksdb