1cd45cd1b3
Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
131 lines
5.0 KiB
C++
131 lines
5.0 KiB
C++
// Copyright (c) 2011-present, 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.
|
|
// This source code is also licensed under the GPLv2 license found in the
|
|
// COPYING file in the root directory of this source tree.
|
|
//
|
|
// 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 <stdint.h>
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include "db/table_properties_collector.h"
|
|
#include "options/cf_options.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/table_properties.h"
|
|
#include "util/file_reader_writer.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class Slice;
|
|
class Status;
|
|
|
|
struct TableReaderOptions {
|
|
// @param skip_filters Disables loading/accessing the filter block
|
|
TableReaderOptions(const ImmutableCFOptions& _ioptions,
|
|
const EnvOptions& _env_options,
|
|
const InternalKeyComparator& _internal_comparator,
|
|
bool _skip_filters = false, int _level = -1)
|
|
: ioptions(_ioptions),
|
|
env_options(_env_options),
|
|
internal_comparator(_internal_comparator),
|
|
skip_filters(_skip_filters),
|
|
level(_level) {}
|
|
|
|
const ImmutableCFOptions& ioptions;
|
|
const EnvOptions& env_options;
|
|
const InternalKeyComparator& internal_comparator;
|
|
// This is only used for BlockBasedTable (reader)
|
|
bool skip_filters;
|
|
// what level this table/file is on, -1 for "not set, don't know"
|
|
int level;
|
|
};
|
|
|
|
struct TableBuilderOptions {
|
|
TableBuilderOptions(
|
|
const ImmutableCFOptions& _ioptions,
|
|
const InternalKeyComparator& _internal_comparator,
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
_int_tbl_prop_collector_factories,
|
|
CompressionType _compression_type,
|
|
const CompressionOptions& _compression_opts,
|
|
const std::string* _compression_dict, bool _skip_filters,
|
|
const std::string& _column_family_name, int _level,
|
|
const uint64_t _creation_time = 0)
|
|
: ioptions(_ioptions),
|
|
internal_comparator(_internal_comparator),
|
|
int_tbl_prop_collector_factories(_int_tbl_prop_collector_factories),
|
|
compression_type(_compression_type),
|
|
compression_opts(_compression_opts),
|
|
compression_dict(_compression_dict),
|
|
skip_filters(_skip_filters),
|
|
column_family_name(_column_family_name),
|
|
level(_level),
|
|
creation_time(_creation_time) {}
|
|
const ImmutableCFOptions& ioptions;
|
|
const InternalKeyComparator& internal_comparator;
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
int_tbl_prop_collector_factories;
|
|
CompressionType compression_type;
|
|
const CompressionOptions& compression_opts;
|
|
// Data for presetting the compression library's dictionary, or nullptr.
|
|
const std::string* compression_dict;
|
|
bool skip_filters; // only used by BlockBasedTableBuilder
|
|
const std::string& column_family_name;
|
|
int level; // what level this table/file is on, -1 for "not set, don't know"
|
|
const uint64_t creation_time;
|
|
};
|
|
|
|
// TableBuilder provides the interface used to build a Table
|
|
// (an immutable and sorted map from keys to values).
|
|
//
|
|
// Multiple threads can invoke const methods on a TableBuilder without
|
|
// external synchronization, but if any of the threads may call a
|
|
// non-const method, all threads accessing the same TableBuilder must use
|
|
// external synchronization.
|
|
class TableBuilder {
|
|
public:
|
|
// REQUIRES: Either Finish() or Abandon() has been called.
|
|
virtual ~TableBuilder() {}
|
|
|
|
// Add key,value to the table being constructed.
|
|
// REQUIRES: key is after any previously added key according to comparator.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
virtual void Add(const Slice& key, const Slice& value) = 0;
|
|
|
|
// Return non-ok iff some error has been detected.
|
|
virtual Status status() const = 0;
|
|
|
|
// Finish building the table.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
virtual Status Finish() = 0;
|
|
|
|
// Indicate that the contents of this builder should be abandoned.
|
|
// If the caller is not going to call Finish(), it must call Abandon()
|
|
// before destroying this builder.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
virtual void Abandon() = 0;
|
|
|
|
// Number of calls to Add() so far.
|
|
virtual uint64_t NumEntries() const = 0;
|
|
|
|
// Size of the file generated so far. If invoked after a successful
|
|
// Finish() call, returns the size of the final generated file.
|
|
virtual uint64_t FileSize() const = 0;
|
|
|
|
// If the user defined table properties collector suggest the file to
|
|
// be further compacted.
|
|
virtual bool NeedCompact() const { return false; }
|
|
|
|
// Returns table properties
|
|
virtual TableProperties GetTableProperties() const = 0;
|
|
};
|
|
|
|
} // namespace rocksdb
|