2016-02-09 23:12:00 +00:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2014-01-28 05:58:46 +00:00
|
|
|
// 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
|
|
|
|
|
2015-07-01 23:13:49 +00:00
|
|
|
#include <stdint.h>
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
2015-05-12 22:53:55 +00:00
|
|
|
#include <string>
|
|
|
|
#include <utility>
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
2015-04-06 17:04:30 +00:00
|
|
|
#include <vector>
|
|
|
|
#include "db/table_properties_collector.h"
|
|
|
|
#include "rocksdb/options.h"
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
2015-05-12 22:53:55 +00:00
|
|
|
#include "rocksdb/table_properties.h"
|
2015-09-11 18:36:33 +00:00
|
|
|
#include "util/file_reader_writer.h"
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
2015-04-06 17:04:30 +00:00
|
|
|
#include "util/mutable_cf_options.h"
|
|
|
|
|
2014-01-28 05:58:46 +00:00
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
class Slice;
|
|
|
|
class Status;
|
|
|
|
|
2015-09-11 18:36:33 +00:00
|
|
|
struct TableReaderOptions {
|
Skip bottom-level filter block caching when hit-optimized
Summary:
When Get() or NewIterator() trigger file loads, skip caching the filter block if
(1) optimize_filters_for_hits is set and (2) the file is on the bottommost
level. Also skip checking filters under the same conditions, which means that
for a preloaded file or a file that was trivially-moved to the bottom level, its
filter block will eventually expire from the cache.
- added parameters/instance variables in various places in order to propagate the config ("skip_filters") from version_set to block_based_table_reader
- in BlockBasedTable::Rep, this optimization prevents filter from being loaded when the file is opened simply by setting filter_policy = nullptr
- in BlockBasedTable::Get/BlockBasedTable::NewIterator, this optimization prevents filter from being used (even if it was loaded already) by setting filter = nullptr
Test Plan:
updated unit test:
$ ./db_test --gtest_filter=DBTest.OptimizeFiltersForHits
will also run 'make check'
Reviewers: sdong, igor, paultuckfield, anthony, rven, kradhakrishnan, IslamAbdelRahman, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D51633
2015-12-23 18:15:07 +00:00
|
|
|
// @param skip_filters Disables loading/accessing the filter block
|
2015-09-11 18:36:33 +00:00
|
|
|
TableReaderOptions(const ImmutableCFOptions& _ioptions,
|
|
|
|
const EnvOptions& _env_options,
|
Skip bottom-level filter block caching when hit-optimized
Summary:
When Get() or NewIterator() trigger file loads, skip caching the filter block if
(1) optimize_filters_for_hits is set and (2) the file is on the bottommost
level. Also skip checking filters under the same conditions, which means that
for a preloaded file or a file that was trivially-moved to the bottom level, its
filter block will eventually expire from the cache.
- added parameters/instance variables in various places in order to propagate the config ("skip_filters") from version_set to block_based_table_reader
- in BlockBasedTable::Rep, this optimization prevents filter from being loaded when the file is opened simply by setting filter_policy = nullptr
- in BlockBasedTable::Get/BlockBasedTable::NewIterator, this optimization prevents filter from being used (even if it was loaded already) by setting filter = nullptr
Test Plan:
updated unit test:
$ ./db_test --gtest_filter=DBTest.OptimizeFiltersForHits
will also run 'make check'
Reviewers: sdong, igor, paultuckfield, anthony, rven, kradhakrishnan, IslamAbdelRahman, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D51633
2015-12-23 18:15:07 +00:00
|
|
|
const InternalKeyComparator& _internal_comparator,
|
Adding pin_l0_filter_and_index_blocks_in_cache feature.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.
When the table reader is destroyed, it releases the pinned blocks (if there were any). This has to happen before the cache is destroyed, so I had to introduce a TableReader::Close(), to guarantee the order of destruction.
Test Plan:
Added two unit tests for this. Existing unit tests run fine (default is pin_l0_filter_and_index_blocks_in_cache=false).
DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32
Mac: OK.
Linux: with D55287 patched in it's OK.
Reviewers: sdong
Reviewed By: sdong
Subscribers: andrewkr, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D54801
2016-03-17 22:40:01 +00:00
|
|
|
bool _skip_filters = false, int _level = -1)
|
2015-09-11 18:36:33 +00:00
|
|
|
: ioptions(_ioptions),
|
|
|
|
env_options(_env_options),
|
Skip bottom-level filter block caching when hit-optimized
Summary:
When Get() or NewIterator() trigger file loads, skip caching the filter block if
(1) optimize_filters_for_hits is set and (2) the file is on the bottommost
level. Also skip checking filters under the same conditions, which means that
for a preloaded file or a file that was trivially-moved to the bottom level, its
filter block will eventually expire from the cache.
- added parameters/instance variables in various places in order to propagate the config ("skip_filters") from version_set to block_based_table_reader
- in BlockBasedTable::Rep, this optimization prevents filter from being loaded when the file is opened simply by setting filter_policy = nullptr
- in BlockBasedTable::Get/BlockBasedTable::NewIterator, this optimization prevents filter from being used (even if it was loaded already) by setting filter = nullptr
Test Plan:
updated unit test:
$ ./db_test --gtest_filter=DBTest.OptimizeFiltersForHits
will also run 'make check'
Reviewers: sdong, igor, paultuckfield, anthony, rven, kradhakrishnan, IslamAbdelRahman, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D51633
2015-12-23 18:15:07 +00:00
|
|
|
internal_comparator(_internal_comparator),
|
Adding pin_l0_filter_and_index_blocks_in_cache feature.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.
When the table reader is destroyed, it releases the pinned blocks (if there were any). This has to happen before the cache is destroyed, so I had to introduce a TableReader::Close(), to guarantee the order of destruction.
Test Plan:
Added two unit tests for this. Existing unit tests run fine (default is pin_l0_filter_and_index_blocks_in_cache=false).
DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32
Mac: OK.
Linux: with D55287 patched in it's OK.
Reviewers: sdong
Reviewed By: sdong
Subscribers: andrewkr, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D54801
2016-03-17 22:40:01 +00:00
|
|
|
skip_filters(_skip_filters),
|
|
|
|
level(_level) {}
|
2015-09-11 18:36:33 +00:00
|
|
|
|
|
|
|
const ImmutableCFOptions& ioptions;
|
|
|
|
const EnvOptions& env_options;
|
|
|
|
const InternalKeyComparator& internal_comparator;
|
Skip bottom-level filter block caching when hit-optimized
Summary:
When Get() or NewIterator() trigger file loads, skip caching the filter block if
(1) optimize_filters_for_hits is set and (2) the file is on the bottommost
level. Also skip checking filters under the same conditions, which means that
for a preloaded file or a file that was trivially-moved to the bottom level, its
filter block will eventually expire from the cache.
- added parameters/instance variables in various places in order to propagate the config ("skip_filters") from version_set to block_based_table_reader
- in BlockBasedTable::Rep, this optimization prevents filter from being loaded when the file is opened simply by setting filter_policy = nullptr
- in BlockBasedTable::Get/BlockBasedTable::NewIterator, this optimization prevents filter from being used (even if it was loaded already) by setting filter = nullptr
Test Plan:
updated unit test:
$ ./db_test --gtest_filter=DBTest.OptimizeFiltersForHits
will also run 'make check'
Reviewers: sdong, igor, paultuckfield, anthony, rven, kradhakrishnan, IslamAbdelRahman, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D51633
2015-12-23 18:15:07 +00:00
|
|
|
// This is only used for BlockBasedTable (reader)
|
|
|
|
bool skip_filters;
|
Adding pin_l0_filter_and_index_blocks_in_cache feature.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.
When the table reader is destroyed, it releases the pinned blocks (if there were any). This has to happen before the cache is destroyed, so I had to introduce a TableReader::Close(), to guarantee the order of destruction.
Test Plan:
Added two unit tests for this. Existing unit tests run fine (default is pin_l0_filter_and_index_blocks_in_cache=false).
DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32
Mac: OK.
Linux: with D55287 patched in it's OK.
Reviewers: sdong
Reviewed By: sdong
Subscribers: andrewkr, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D54801
2016-03-17 22:40:01 +00:00
|
|
|
// what level this table/file is on, -1 for "not set, don't know"
|
|
|
|
int level;
|
2015-09-11 18:36:33 +00:00
|
|
|
};
|
|
|
|
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
2015-04-06 17:04:30 +00:00
|
|
|
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, bool _skip_filters)
|
|
|
|
: ioptions(_ioptions),
|
|
|
|
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) {}
|
|
|
|
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;
|
Skip bottom-level filter block caching when hit-optimized
Summary:
When Get() or NewIterator() trigger file loads, skip caching the filter block if
(1) optimize_filters_for_hits is set and (2) the file is on the bottommost
level. Also skip checking filters under the same conditions, which means that
for a preloaded file or a file that was trivially-moved to the bottom level, its
filter block will eventually expire from the cache.
- added parameters/instance variables in various places in order to propagate the config ("skip_filters") from version_set to block_based_table_reader
- in BlockBasedTable::Rep, this optimization prevents filter from being loaded when the file is opened simply by setting filter_policy = nullptr
- in BlockBasedTable::Get/BlockBasedTable::NewIterator, this optimization prevents filter from being used (even if it was loaded already) by setting filter = nullptr
Test Plan:
updated unit test:
$ ./db_test --gtest_filter=DBTest.OptimizeFiltersForHits
will also run 'make check'
Reviewers: sdong, igor, paultuckfield, anthony, rven, kradhakrishnan, IslamAbdelRahman, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D51633
2015-12-23 18:15:07 +00:00
|
|
|
// This is only used for BlockBasedTableBuilder
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
2015-04-06 17:04:30 +00:00
|
|
|
bool skip_filters = false;
|
|
|
|
};
|
|
|
|
|
2014-01-28 05:58:46 +00:00
|
|
|
// 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;
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
2015-05-12 22:53:55 +00:00
|
|
|
|
2015-06-04 19:03:40 +00:00
|
|
|
// If the user defined table properties collector suggest the file to
|
|
|
|
// be further compacted.
|
|
|
|
virtual bool NeedCompact() const { return false; }
|
|
|
|
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
2015-05-12 22:53:55 +00:00
|
|
|
// Returns table properties
|
|
|
|
virtual TableProperties GetTableProperties() const = 0;
|
2014-01-28 05:58:46 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace rocksdb
|