Revision d3d20dcdca9dc79d893a03dfa611fb1055c28f96 authored by Sagar Vemuri on 11 April 2019, 02:24:25 UTC, committed by Facebook Github Bot on 11 April 2019, 02:31:18 UTC
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
1 parent ef0fc1b
block_prefix_index.h
// 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).
#pragma once
#include <stdint.h>
#include "rocksdb/status.h"
namespace rocksdb {
class Comparator;
class Iterator;
class Slice;
class SliceTransform;
// Build a hash-based index to speed up the lookup for "index block".
// BlockHashIndex accepts a key and, if found, returns its restart index within
// that index block.
class BlockPrefixIndex {
public:
// Maps a key to a list of data blocks that could potentially contain
// the key, based on the prefix.
// Returns the total number of relevant blocks, 0 means the key does
// not exist.
uint32_t GetBlocks(const Slice& key, uint32_t** blocks);
size_t ApproximateMemoryUsage() const {
return sizeof(BlockPrefixIndex) +
(num_block_array_buffer_entries_ + num_buckets_) * sizeof(uint32_t);
}
// Create hash index by reading from the metadata blocks.
// @params prefixes: a sequence of prefixes.
// @params prefix_meta: contains the "metadata" to of the prefixes.
static Status Create(const SliceTransform* hash_key_extractor,
const Slice& prefixes, const Slice& prefix_meta,
BlockPrefixIndex** prefix_index);
~BlockPrefixIndex() {
delete[] buckets_;
delete[] block_array_buffer_;
}
private:
class Builder;
friend Builder;
BlockPrefixIndex(const SliceTransform* internal_prefix_extractor,
uint32_t num_buckets, uint32_t* buckets,
uint32_t num_block_array_buffer_entries,
uint32_t* block_array_buffer)
: internal_prefix_extractor_(internal_prefix_extractor),
num_buckets_(num_buckets),
num_block_array_buffer_entries_(num_block_array_buffer_entries),
buckets_(buckets),
block_array_buffer_(block_array_buffer) {}
const SliceTransform* internal_prefix_extractor_;
uint32_t num_buckets_;
uint32_t num_block_array_buffer_entries_;
uint32_t* buckets_;
uint32_t* block_array_buffer_;
};
} // namespace rocksdb
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...