rocksdb/table/table_builder.h

206 lines
8.2 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 <stdint.h>
#include <string>
#include <utility>
#include <vector>
#include "db/dbformat.h"
#include "db/table_properties_collector.h"
#include "file/writable_file_writer.h"
#include "options/cf_options.h"
#include "rocksdb/options.h"
#include "rocksdb/table_properties.h"
#include "trace_replay/block_cache_tracer.h"
namespace ROCKSDB_NAMESPACE {
class Slice;
class Status;
struct TableReaderOptions {
// @param skip_filters Disables loading/accessing the filter block
TableReaderOptions(const ImmutableCFOptions& _ioptions,
const SliceTransform* _prefix_extractor,
const EnvOptions& _env_options,
const InternalKeyComparator& _internal_comparator,
bool _skip_filters = false, bool _immortal = false,
bool _force_direct_prefetch = false, int _level = -1,
BlockCacheTracer* const _block_cache_tracer = nullptr,
size_t _max_file_size_for_l0_meta_pin = 0)
: TableReaderOptions(_ioptions, _prefix_extractor, _env_options,
_internal_comparator, _skip_filters, _immortal,
_force_direct_prefetch, _level,
0 /* _largest_seqno */, _block_cache_tracer,
_max_file_size_for_l0_meta_pin) {}
// @param skip_filters Disables loading/accessing the filter block
TableReaderOptions(const ImmutableCFOptions& _ioptions,
const SliceTransform* _prefix_extractor,
const EnvOptions& _env_options,
const InternalKeyComparator& _internal_comparator,
bool _skip_filters, bool _immortal,
bool _force_direct_prefetch, int _level,
SequenceNumber _largest_seqno,
BlockCacheTracer* const _block_cache_tracer,
size_t _max_file_size_for_l0_meta_pin)
: ioptions(_ioptions),
prefix_extractor(_prefix_extractor),
env_options(_env_options),
internal_comparator(_internal_comparator),
skip_filters(_skip_filters),
immortal(_immortal),
force_direct_prefetch(_force_direct_prefetch),
level(_level),
largest_seqno(_largest_seqno),
block_cache_tracer(_block_cache_tracer),
max_file_size_for_l0_meta_pin(_max_file_size_for_l0_meta_pin) {}
const ImmutableCFOptions& ioptions;
const SliceTransform* prefix_extractor;
const EnvOptions& env_options;
const InternalKeyComparator& internal_comparator;
// This is only used for BlockBasedTable (reader)
bool skip_filters;
// Whether the table will be valid as long as the DB is open
bool immortal;
// When data prefetching is needed, even if direct I/O is off, read data to
// fetch into RocksDB's buffer, rather than relying
// RandomAccessFile::Prefetch().
bool force_direct_prefetch;
// what level this table/file is on, -1 for "not set, don't know"
int level;
// largest seqno in the table
SequenceNumber largest_seqno;
BlockCacheTracer* const block_cache_tracer;
// Largest L0 file size whose meta-blocks may be pinned (can be zero when
// unknown).
const size_t max_file_size_for_l0_meta_pin;
};
struct TableBuilderOptions {
TableBuilderOptions(
const ImmutableCFOptions& _ioptions, const MutableCFOptions& _moptions,
const InternalKeyComparator& _internal_comparator,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
_int_tbl_prop_collector_factories,
CompressionType _compression_type,
Reduce scope of compression dictionary to single SST (#4952) Summary: Our previous approach was to train one compression dictionary per compaction, using the first output SST to train a dictionary, and then applying it on subsequent SSTs in the same compaction. While this was great for minimizing CPU/memory/I/O overhead, it did not achieve good compression ratios in practice. In our most promising potential use case, moderate reductions in a dictionary's scope make a major difference on compression ratio. So, this PR changes compression dictionary to be scoped per-SST. It accepts the tradeoff during table building to use more memory and CPU. Important changes include: - The `BlockBasedTableBuilder` has a new state when dictionary compression is in-use: `kBuffered`. In that state it accumulates uncompressed data in-memory whenever `Add` is called. - After accumulating target file size bytes or calling `BlockBasedTableBuilder::Finish`, a `BlockBasedTableBuilder` moves to the `kUnbuffered` state. The transition (`EnterUnbuffered()`) involves sampling the buffered data, training a dictionary, and compressing/writing out all buffered data. In the `kUnbuffered` state, a `BlockBasedTableBuilder` behaves the same as before -- blocks are compressed/written out as soon as they fill up. - Samples are now whole uncompressed data blocks, except the final sample may be a partial data block so we don't breach the user's configured `max_dict_bytes` or `zstd_max_train_bytes`. The dictionary trainer is supposed to work better when we pass it real units of compression. Previously we were passing 64-byte KV samples which was not realistic. Pull Request resolved: https://github.com/facebook/rocksdb/pull/4952 Differential Revision: D13967980 Pulled By: ajkr fbshipit-source-id: 82bea6f7537e1529c7a1a4cdee84585f5949300f
2019-02-12 04:42:25 +01:00
const CompressionOptions& _compression_opts, bool _skip_filters,
uint32_t _column_family_id, const std::string& _column_family_name,
int _level, const uint64_t _creation_time = 0,
const int64_t _oldest_key_time = 0,
const uint64_t _file_creation_time = 0, const std::string& _db_id = "",
const std::string& _db_session_id = "",
const uint64_t _target_file_size = 0)
: ioptions(_ioptions),
moptions(_moptions),
internal_comparator(_internal_comparator),
int_tbl_prop_collector_factories(_int_tbl_prop_collector_factories),
compression_type(_compression_type),
compression_opts(_compression_opts),
skip_filters(_skip_filters),
column_family_id(_column_family_id),
column_family_name(_column_family_name),
FIFO Compaction with TTL 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
2017-06-28 02:02:20 +02:00
level(_level),
creation_time(_creation_time),
Reduce scope of compression dictionary to single SST (#4952) Summary: Our previous approach was to train one compression dictionary per compaction, using the first output SST to train a dictionary, and then applying it on subsequent SSTs in the same compaction. While this was great for minimizing CPU/memory/I/O overhead, it did not achieve good compression ratios in practice. In our most promising potential use case, moderate reductions in a dictionary's scope make a major difference on compression ratio. So, this PR changes compression dictionary to be scoped per-SST. It accepts the tradeoff during table building to use more memory and CPU. Important changes include: - The `BlockBasedTableBuilder` has a new state when dictionary compression is in-use: `kBuffered`. In that state it accumulates uncompressed data in-memory whenever `Add` is called. - After accumulating target file size bytes or calling `BlockBasedTableBuilder::Finish`, a `BlockBasedTableBuilder` moves to the `kUnbuffered` state. The transition (`EnterUnbuffered()`) involves sampling the buffered data, training a dictionary, and compressing/writing out all buffered data. In the `kUnbuffered` state, a `BlockBasedTableBuilder` behaves the same as before -- blocks are compressed/written out as soon as they fill up. - Samples are now whole uncompressed data blocks, except the final sample may be a partial data block so we don't breach the user's configured `max_dict_bytes` or `zstd_max_train_bytes`. The dictionary trainer is supposed to work better when we pass it real units of compression. Previously we were passing 64-byte KV samples which was not realistic. Pull Request resolved: https://github.com/facebook/rocksdb/pull/4952 Differential Revision: D13967980 Pulled By: ajkr fbshipit-source-id: 82bea6f7537e1529c7a1a4cdee84585f5949300f
2019-02-12 04:42:25 +01:00
oldest_key_time(_oldest_key_time),
Periodic Compactions (#5166) Summary: Introducing Periodic Compactions. This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold. - Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF. - This works across all levels. - The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used). - Compaction filters, if any, are invoked as usual. - A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS). This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166 Differential Revision: D14884441 Pulled By: sagar0 fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
2019-04-11 04:24:25 +02:00
target_file_size(_target_file_size),
file_creation_time(_file_creation_time),
db_id(_db_id),
db_session_id(_db_session_id) {}
const ImmutableCFOptions& ioptions;
const MutableCFOptions& moptions;
const InternalKeyComparator& internal_comparator;
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories;
const CompressionType compression_type;
const CompressionOptions& compression_opts;
const bool skip_filters; // only used by BlockBasedTableBuilder
const uint32_t column_family_id;
const std::string& column_family_name;
// what level this table/file is on, -1 for "not set, don't know"
const int level;
FIFO Compaction with TTL 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
2017-06-28 02:02:20 +02:00
const uint64_t creation_time;
const int64_t oldest_key_time;
Reduce scope of compression dictionary to single SST (#4952) Summary: Our previous approach was to train one compression dictionary per compaction, using the first output SST to train a dictionary, and then applying it on subsequent SSTs in the same compaction. While this was great for minimizing CPU/memory/I/O overhead, it did not achieve good compression ratios in practice. In our most promising potential use case, moderate reductions in a dictionary's scope make a major difference on compression ratio. So, this PR changes compression dictionary to be scoped per-SST. It accepts the tradeoff during table building to use more memory and CPU. Important changes include: - The `BlockBasedTableBuilder` has a new state when dictionary compression is in-use: `kBuffered`. In that state it accumulates uncompressed data in-memory whenever `Add` is called. - After accumulating target file size bytes or calling `BlockBasedTableBuilder::Finish`, a `BlockBasedTableBuilder` moves to the `kUnbuffered` state. The transition (`EnterUnbuffered()`) involves sampling the buffered data, training a dictionary, and compressing/writing out all buffered data. In the `kUnbuffered` state, a `BlockBasedTableBuilder` behaves the same as before -- blocks are compressed/written out as soon as they fill up. - Samples are now whole uncompressed data blocks, except the final sample may be a partial data block so we don't breach the user's configured `max_dict_bytes` or `zstd_max_train_bytes`. The dictionary trainer is supposed to work better when we pass it real units of compression. Previously we were passing 64-byte KV samples which was not realistic. Pull Request resolved: https://github.com/facebook/rocksdb/pull/4952 Differential Revision: D13967980 Pulled By: ajkr fbshipit-source-id: 82bea6f7537e1529c7a1a4cdee84585f5949300f
2019-02-12 04:42:25 +01:00
const uint64_t target_file_size;
Periodic Compactions (#5166) Summary: Introducing Periodic Compactions. This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold. - Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF. - This works across all levels. - The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used). - Compaction filters, if any, are invoked as usual. - A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS). This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166 Differential Revision: D14884441 Pulled By: sagar0 fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
2019-04-11 04:24:25 +02:00
const uint64_t file_creation_time;
const std::string db_id;
const std::string db_session_id;
};
// 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;
// Return non-ok iff some error happens during IO.
virtual IOStatus io_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;
// Whether the output file is completely empty. It has neither entries
// or tombstones.
virtual bool IsEmpty() const {
return NumEntries() == 0 && GetTableProperties().num_range_deletions == 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;
// Estimated size of the file generated so far. This is used when
// FileSize() cannot estimate final SST size, e.g. parallel compression
// is enabled.
virtual uint64_t EstimatedFileSize() const { return FileSize(); }
// 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;
// Return file checksum
virtual std::string GetFileChecksum() const = 0;
// Return file checksum function name
virtual const char* GetFileChecksumFuncName() const = 0;
};
} // namespace ROCKSDB_NAMESPACE