2016-02-10 00:12:00 +01:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-16 01:03:42 +02:00
|
|
|
// 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).
|
2013-10-29 01:54:09 +01:00
|
|
|
//
|
2011-03-18 23:37:00 +01:00
|
|
|
// 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.
|
|
|
|
|
2013-10-29 01:54:09 +01:00
|
|
|
#pragma once
|
2011-03-18 23:37:00 +01:00
|
|
|
#include <stdint.h>
|
2014-06-09 21:26:09 +02:00
|
|
|
#include <limits>
|
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
2015-05-13 00:53:55 +02:00
|
|
|
#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 19:04:30 +02:00
|
|
|
#include <vector>
|
2014-03-01 03:19:07 +01:00
|
|
|
|
2020-02-11 00:42:46 +01:00
|
|
|
#include "db/version_edit.h"
|
2013-11-20 07:00:48 +01:00
|
|
|
#include "rocksdb/flush_block_policy.h"
|
2017-06-28 02:02:20 +02:00
|
|
|
#include "rocksdb/listener.h"
|
2013-08-23 17:38:13 +02:00
|
|
|
#include "rocksdb/options.h"
|
|
|
|
#include "rocksdb/status.h"
|
2019-05-31 02:39:43 +02:00
|
|
|
#include "table/meta_blocks.h"
|
2014-01-28 06:58:46 +01:00
|
|
|
#include "table/table_builder.h"
|
2018-06-04 21:04:52 +02:00
|
|
|
#include "util/compression.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2020-02-20 21:07:53 +01:00
|
|
|
namespace ROCKSDB_NAMESPACE {
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
class BlockBuilder;
|
|
|
|
class BlockHandle;
|
|
|
|
class WritableFile;
|
2014-03-01 03:19:07 +01:00
|
|
|
struct BlockBasedTableOptions;
|
2013-10-29 01:54:09 +01:00
|
|
|
|
2015-07-02 01:13:49 +02:00
|
|
|
extern const uint64_t kBlockBasedTableMagicNumber;
|
|
|
|
extern const uint64_t kLegacyBlockBasedTableMagicNumber;
|
|
|
|
|
2013-10-29 01:54:09 +01:00
|
|
|
class BlockBasedTableBuilder : public TableBuilder {
|
2011-03-18 23:37:00 +01:00
|
|
|
public:
|
|
|
|
// Create a builder that will store the contents of the table it is
|
|
|
|
// building in *file. Does not close the file. It is up to the
|
2013-10-30 18:52:33 +01:00
|
|
|
// caller to close the file after calling Finish().
|
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 19:04:30 +02:00
|
|
|
BlockBasedTableBuilder(
|
2018-05-21 23:33:55 +02:00
|
|
|
const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
|
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 19:04:30 +02:00
|
|
|
const BlockBasedTableOptions& table_options,
|
|
|
|
const InternalKeyComparator& internal_comparator,
|
|
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
|
|
int_tbl_prop_collector_factories,
|
2015-10-09 01:57:35 +02:00
|
|
|
uint32_t column_family_id, WritableFileWriter* file,
|
|
|
|
const CompressionType compression_type,
|
2019-03-18 20:07:35 +01:00
|
|
|
const uint64_t sample_for_compression,
|
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, const bool skip_filters,
|
2019-11-27 03:18:29 +01:00
|
|
|
const std::string& column_family_name, const int level_at_creation,
|
|
|
|
const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
|
|
|
|
const uint64_t target_file_size = 0,
|
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 = 0);
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2018-06-04 21:04:52 +02:00
|
|
|
// No copying allowed
|
|
|
|
BlockBasedTableBuilder(const BlockBasedTableBuilder&) = delete;
|
|
|
|
BlockBasedTableBuilder& operator=(const BlockBasedTableBuilder&) = delete;
|
|
|
|
|
2019-09-12 03:07:12 +02:00
|
|
|
// REQUIRES: Either Finish() or Abandon() has been called.
|
|
|
|
~BlockBasedTableBuilder();
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
// 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
|
2013-10-29 01:54:09 +01:00
|
|
|
void Add(const Slice& key, const Slice& value) override;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
// Return non-ok iff some error has been detected.
|
2013-10-29 01:54:09 +01:00
|
|
|
Status status() const override;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
Pass IOStatus to write path and set retryable IO Error as hard error in BG jobs (#6487)
Summary:
In the current code base, we use Status to get and store the returned status from the call. Specifically, for IO related functions, the current Status cannot reflect the IO Error details such as error scope, error retryable attribute, and others. With the implementation of https://github.com/facebook/rocksdb/issues/5761, we have the new Wrapper for IO, which returns IOStatus instead of Status. However, the IOStatus is purged at the lower level of write path and transferred to Status.
The first job of this PR is to pass the IOStatus to the write path (flush, WAL write, and Compaction). The second job is to identify the Retryable IO Error as HardError, and set the bg_error_ as HardError. In this case, the DB Instance becomes read only. User is informed of the Status and need to take actions to deal with it (e.g., call db->Resume()).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6487
Test Plan: Added the testing case to error_handler_fs_test. Pass make asan_check
Reviewed By: anand1976
Differential Revision: D20685017
Pulled By: zhichao-cao
fbshipit-source-id: ff85f042896243abcd6ef37877834e26f36b6eb0
2020-03-28 00:03:05 +01:00
|
|
|
// Return non-ok iff some error happens during IO.
|
|
|
|
IOStatus io_status() const override;
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
// Finish building the table. Stops using the file passed to the
|
|
|
|
// constructor after this function returns.
|
|
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
2013-10-29 01:54:09 +01:00
|
|
|
Status Finish() override;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
// Indicate that the contents of this builder should be abandoned. Stops
|
|
|
|
// using the file passed to the constructor after this function returns.
|
|
|
|
// If the caller is not going to call Finish(), it must call Abandon()
|
|
|
|
// before destroying this builder.
|
|
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
2013-10-29 01:54:09 +01:00
|
|
|
void Abandon() override;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
// Number of calls to Add() so far.
|
2013-10-29 01:54:09 +01:00
|
|
|
uint64_t NumEntries() const override;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
// Size of the file generated so far. If invoked after a successful
|
|
|
|
// Finish() call, returns the size of the final generated file.
|
2013-10-29 01:54:09 +01:00
|
|
|
uint64_t FileSize() const override;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2015-06-04 21:03:40 +02:00
|
|
|
bool NeedCompact() const override;
|
|
|
|
|
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
2015-05-13 00:53:55 +02:00
|
|
|
// Get table properties
|
|
|
|
TableProperties GetTableProperties() const override;
|
|
|
|
|
2020-02-11 00:42:46 +01:00
|
|
|
// Get file checksum
|
2020-03-30 00:57:02 +02:00
|
|
|
std::string GetFileChecksum() const override;
|
2020-02-11 00:42:46 +01:00
|
|
|
|
|
|
|
// Get file checksum function name
|
|
|
|
const char* GetFileChecksumFuncName() const override;
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
private:
|
|
|
|
bool ok() const { return status().ok(); }
|
Shared dictionary compression using reference block
Summary:
This adds a new metablock containing a shared dictionary that is used
to compress all data blocks in the SST file. The size of the shared dictionary
is configurable in CompressionOptions and defaults to 0. It's currently only
used for zlib/lz4/lz4hc, but the block will be stored in the SST regardless of
the compression type if the user chooses a nonzero dictionary size.
During compaction, computes the dictionary by randomly sampling the first
output file in each subcompaction. It pre-computes the intervals to sample
by assuming the output file will have the maximum allowable length. In case
the file is smaller, some of the pre-computed sampling intervals can be beyond
end-of-file, in which case we skip over those samples and the dictionary will
be a bit smaller. After the dictionary is generated using the first file in a
subcompaction, it is loaded into the compression library before writing each
block in each subsequent file of that subcompaction.
On the read path, gets the dictionary from the metablock, if it exists. Then,
loads that dictionary into the compression library before reading each block.
Test Plan: new unit test
Reviewers: yhchiang, IslamAbdelRahman, cyan, sdong
Reviewed By: sdong
Subscribers: andrewkr, yoshinorim, kradhakrishnan, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D52287
2016-04-28 02:36:03 +02:00
|
|
|
|
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
|
|
|
// Transition state from buffered to unbuffered. See `Rep::State` API comment
|
|
|
|
// for details of the states.
|
|
|
|
// REQUIRES: `rep_->state == kBuffered`
|
|
|
|
void EnterUnbuffered();
|
|
|
|
|
Compaction Support for Range Deletion
Summary:
This diff introduces RangeDelAggregator, which takes ownership of iterators
provided to it via AddTombstones(). The tombstones are organized in a two-level
map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data
copy by holding Slices returned by the iterator, which remain valid thanks to pinning.
For compaction, we create a hierarchical range tombstone iterator with structure
matching the iterator over compaction input data. An aggregator based on that
iterator is used by CompactionIterator to determine which keys are covered by
range tombstones. In case of merge operand, the same aggregator is used by
MergeHelper. Upon finishing each file in the compaction, relevant range tombstones
are added to the output file's range tombstone metablock and file boundaries are
updated accordingly.
To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete()
considers tombstones in the key's snapshot stripe. When this function is used outside of
compaction, it also checks newer stripes, which can contain covering tombstones. Currently
the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges
within a stripe such that binary search can be used.
RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range
to a new table's range tombstone meta-block. Since range tombstones may fall in the gap
between files, we may need to extend some files' key-ranges. The strategy is (1) first file
extends as far left as possible and other files do not extend left, (2) all files extend right
until either the start of the next file or the end of the last range tombstone in the gap,
whichever comes first.
One other notable change is adding release/move semantics to ScopedArenaIterator
such that it can be used to transfer ownership of an arena-allocated iterator, similar to
how unique_ptr is used for malloc'd data.
Depends on D61473
Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927
Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark
Reviewed By: lightmark
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D62205
2016-10-18 21:04:56 +02:00
|
|
|
// Call block's Finish() method
|
|
|
|
// and then write the compressed block contents to file.
|
Shared dictionary compression using reference block
Summary:
This adds a new metablock containing a shared dictionary that is used
to compress all data blocks in the SST file. The size of the shared dictionary
is configurable in CompressionOptions and defaults to 0. It's currently only
used for zlib/lz4/lz4hc, but the block will be stored in the SST regardless of
the compression type if the user chooses a nonzero dictionary size.
During compaction, computes the dictionary by randomly sampling the first
output file in each subcompaction. It pre-computes the intervals to sample
by assuming the output file will have the maximum allowable length. In case
the file is smaller, some of the pre-computed sampling intervals can be beyond
end-of-file, in which case we skip over those samples and the dictionary will
be a bit smaller. After the dictionary is generated using the first file in a
subcompaction, it is loaded into the compression library before writing each
block in each subsequent file of that subcompaction.
On the read path, gets the dictionary from the metablock, if it exists. Then,
loads that dictionary into the compression library before reading each block.
Test Plan: new unit test
Reviewers: yhchiang, IslamAbdelRahman, cyan, sdong
Reviewed By: sdong
Subscribers: andrewkr, yoshinorim, kradhakrishnan, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D52287
2016-04-28 02:36:03 +02:00
|
|
|
void WriteBlock(BlockBuilder* block, BlockHandle* handle, bool is_data_block);
|
|
|
|
|
Compaction Support for Range Deletion
Summary:
This diff introduces RangeDelAggregator, which takes ownership of iterators
provided to it via AddTombstones(). The tombstones are organized in a two-level
map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data
copy by holding Slices returned by the iterator, which remain valid thanks to pinning.
For compaction, we create a hierarchical range tombstone iterator with structure
matching the iterator over compaction input data. An aggregator based on that
iterator is used by CompactionIterator to determine which keys are covered by
range tombstones. In case of merge operand, the same aggregator is used by
MergeHelper. Upon finishing each file in the compaction, relevant range tombstones
are added to the output file's range tombstone metablock and file boundaries are
updated accordingly.
To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete()
considers tombstones in the key's snapshot stripe. When this function is used outside of
compaction, it also checks newer stripes, which can contain covering tombstones. Currently
the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges
within a stripe such that binary search can be used.
RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range
to a new table's range tombstone meta-block. Since range tombstones may fall in the gap
between files, we may need to extend some files' key-ranges. The strategy is (1) first file
extends as far left as possible and other files do not extend left, (2) all files extend right
until either the start of the next file or the end of the last range tombstone in the gap,
whichever comes first.
One other notable change is adding release/move semantics to ScopedArenaIterator
such that it can be used to transfer ownership of an arena-allocated iterator, similar to
how unique_ptr is used for malloc'd data.
Depends on D61473
Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927
Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark
Reviewed By: lightmark
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D62205
2016-10-18 21:04:56 +02:00
|
|
|
// Compress and write block content to the file.
|
Shared dictionary compression using reference block
Summary:
This adds a new metablock containing a shared dictionary that is used
to compress all data blocks in the SST file. The size of the shared dictionary
is configurable in CompressionOptions and defaults to 0. It's currently only
used for zlib/lz4/lz4hc, but the block will be stored in the SST regardless of
the compression type if the user chooses a nonzero dictionary size.
During compaction, computes the dictionary by randomly sampling the first
output file in each subcompaction. It pre-computes the intervals to sample
by assuming the output file will have the maximum allowable length. In case
the file is smaller, some of the pre-computed sampling intervals can be beyond
end-of-file, in which case we skip over those samples and the dictionary will
be a bit smaller. After the dictionary is generated using the first file in a
subcompaction, it is loaded into the compression library before writing each
block in each subsequent file of that subcompaction.
On the read path, gets the dictionary from the metablock, if it exists. Then,
loads that dictionary into the compression library before reading each block.
Test Plan: new unit test
Reviewers: yhchiang, IslamAbdelRahman, cyan, sdong
Reviewed By: sdong
Subscribers: andrewkr, yoshinorim, kradhakrishnan, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D52287
2016-04-28 02:36:03 +02:00
|
|
|
void WriteBlock(const Slice& block_contents, BlockHandle* handle,
|
|
|
|
bool is_data_block);
|
Compaction Support for Range Deletion
Summary:
This diff introduces RangeDelAggregator, which takes ownership of iterators
provided to it via AddTombstones(). The tombstones are organized in a two-level
map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data
copy by holding Slices returned by the iterator, which remain valid thanks to pinning.
For compaction, we create a hierarchical range tombstone iterator with structure
matching the iterator over compaction input data. An aggregator based on that
iterator is used by CompactionIterator to determine which keys are covered by
range tombstones. In case of merge operand, the same aggregator is used by
MergeHelper. Upon finishing each file in the compaction, relevant range tombstones
are added to the output file's range tombstone metablock and file boundaries are
updated accordingly.
To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete()
considers tombstones in the key's snapshot stripe. When this function is used outside of
compaction, it also checks newer stripes, which can contain covering tombstones. Currently
the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges
within a stripe such that binary search can be used.
RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range
to a new table's range tombstone meta-block. Since range tombstones may fall in the gap
between files, we may need to extend some files' key-ranges. The strategy is (1) first file
extends as far left as possible and other files do not extend left, (2) all files extend right
until either the start of the next file or the end of the last range tombstone in the gap,
whichever comes first.
One other notable change is adding release/move semantics to ScopedArenaIterator
such that it can be used to transfer ownership of an arena-allocated iterator, similar to
how unique_ptr is used for malloc'd data.
Depends on D61473
Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927
Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark
Reviewed By: lightmark
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D62205
2016-10-18 21:04:56 +02:00
|
|
|
// Directly write data to the file.
|
2018-03-27 05:14:24 +02:00
|
|
|
void WriteRawBlock(const Slice& data, CompressionType, BlockHandle* handle,
|
|
|
|
bool is_data_block = false);
|
2013-09-02 08:23:40 +02:00
|
|
|
Status InsertBlockInCache(const Slice& block_contents,
|
2014-03-01 03:19:07 +01:00
|
|
|
const CompressionType type,
|
|
|
|
const BlockHandle* handle);
|
2018-07-20 18:00:33 +02:00
|
|
|
|
|
|
|
void WriteFilterBlock(MetaIndexBuilder* meta_index_builder);
|
|
|
|
void WriteIndexBlock(MetaIndexBuilder* meta_index_builder,
|
|
|
|
BlockHandle* index_block_handle);
|
|
|
|
void WritePropertiesBlock(MetaIndexBuilder* meta_index_builder);
|
|
|
|
void WriteCompressionDictBlock(MetaIndexBuilder* meta_index_builder);
|
|
|
|
void WriteRangeDelBlock(MetaIndexBuilder* meta_index_builder);
|
2018-12-07 22:15:09 +01:00
|
|
|
void WriteFooter(BlockHandle& metaindex_block_handle,
|
|
|
|
BlockHandle& index_block_handle);
|
2018-07-20 18:00:33 +02:00
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
struct Rep;
|
TablePropertiesCollectorFactory
Summary:
This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options.
Here's description of task #4296714:
I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB.
For example, this table has 3155 entries and 1391828 deleted keys.
The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for.
Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API.
In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe.
Test Plan:
Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one).
Also, all other tests
Reviewers: sdong, dhruba, haobo, kailiu
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18579
2014-05-13 21:30:55 +02:00
|
|
|
class BlockBasedTablePropertiesCollectorFactory;
|
2014-03-01 03:19:07 +01:00
|
|
|
class BlockBasedTablePropertiesCollector;
|
2011-03-18 23:37:00 +01:00
|
|
|
Rep* rep_;
|
2013-10-29 01:54:09 +01:00
|
|
|
|
|
|
|
// Advanced operation: flush any buffered key/value pairs to file.
|
|
|
|
// Can be used to ensure that two adjacent entries never live in
|
|
|
|
// the same data block. Most clients should not need to use this method.
|
|
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
|
|
void Flush();
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2014-06-09 21:26:09 +02:00
|
|
|
// Some compression libraries fail when the raw size is bigger than int. If
|
|
|
|
// uncompressed size is bigger than kCompressionSizeLimit, don't compress it
|
|
|
|
const uint64_t kCompressionSizeLimit = std::numeric_limits<int>::max();
|
2011-03-18 23:37:00 +01:00
|
|
|
};
|
|
|
|
|
2019-01-19 04:10:17 +01:00
|
|
|
Slice CompressBlock(const Slice& raw, const CompressionInfo& info,
|
2016-08-01 23:50:19 +02:00
|
|
|
CompressionType* type, uint32_t format_version,
|
2019-03-18 20:07:35 +01:00
|
|
|
bool do_sample, std::string* compressed_output,
|
|
|
|
std::string* sampled_output_fast,
|
|
|
|
std::string* sampled_output_slow);
|
2016-08-01 23:50:19 +02:00
|
|
|
|
2020-02-20 21:07:53 +01:00
|
|
|
} // namespace ROCKSDB_NAMESPACE
|