mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 11:43:49 +00:00
f02c708aa3
Summary: This PR is the first step for Issue https://github.com/facebook/rocksdb/issues/4811. Currently compaction output files are cut at point keys, and the decision is made mainly in `CompactionOutputs::ShouldStopBefore()`. This makes it possible for range tombstones to cause large compactions that does not respect `max_compaction_bytes`. For example, we can have a large range tombstone that overlaps with too many files from the next level. Another example is when there is a gap between a range tombstone and another key. The first issue may be more acceptable, as a lot of data is deleted. This PR address the second issue by calling `ShouldStopBefore()` for range tombstone start keys. The main change is for `CompactionIterator` to emit range tombstone start keys to be processed by `CompactionOutputs`. A new `CompactionMergingIterator` is introduced and only used under `CompactionIterator` for this purpose. Further improvement after this PR include 1) cut compaction output at some grandparent boundary key instead of at the next point key or range tombstone start key and 2) cut compaction output file within a large range tombstone (it may be easier and reasonable to only do it for range tombstones at the end of a compaction output). Pull Request resolved: https://github.com/facebook/rocksdb/pull/10802 Test Plan: - added unit tests in db_range_del_test. - stress test: `python3 tools/db_crashtest.py whitebox --[simple|enable_ts] --verify_iterator_with_expected_state_one_in=5 --delrangepercent=5 --prefixpercent=2 --writepercent=58 --readpercen=21 --duration=36000 --range_deletion_width=1000000` Reviewed By: ajkr, jay-zhuang Differential Revision: D40308827 Pulled By: cbi42 fbshipit-source-id: a8fd6f70a3f09d0ef7a40e006f6c964bba8c00df
96 lines
2.3 KiB
C++
96 lines
2.3 KiB
C++
// 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 <string>
|
|
#include <vector>
|
|
|
|
#include "db/dbformat.h"
|
|
#include "rocksdb/iterator.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "table/internal_iterator.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class HistoryTrimmingIterator : public InternalIterator {
|
|
public:
|
|
explicit HistoryTrimmingIterator(InternalIterator* input,
|
|
const Comparator* cmp, const std::string& ts)
|
|
: input_(input), filter_ts_(ts), cmp_(cmp) {
|
|
assert(cmp_->timestamp_size() > 0 && !ts.empty());
|
|
}
|
|
|
|
bool filter() const {
|
|
if (!input_->Valid()) {
|
|
return true;
|
|
}
|
|
Slice current_ts = ExtractTimestampFromKey(key(), cmp_->timestamp_size());
|
|
return cmp_->CompareTimestamp(current_ts, Slice(filter_ts_)) <= 0;
|
|
}
|
|
|
|
bool Valid() const override { return input_->Valid(); }
|
|
|
|
void SeekToFirst() override {
|
|
input_->SeekToFirst();
|
|
while (!filter()) {
|
|
input_->Next();
|
|
}
|
|
}
|
|
|
|
void SeekToLast() override {
|
|
input_->SeekToLast();
|
|
while (!filter()) {
|
|
input_->Prev();
|
|
}
|
|
}
|
|
|
|
void Seek(const Slice& target) override {
|
|
input_->Seek(target);
|
|
while (!filter()) {
|
|
input_->Next();
|
|
}
|
|
}
|
|
|
|
void SeekForPrev(const Slice& target) override {
|
|
input_->SeekForPrev(target);
|
|
while (!filter()) {
|
|
input_->Prev();
|
|
}
|
|
}
|
|
|
|
void Next() override {
|
|
do {
|
|
input_->Next();
|
|
} while (!filter());
|
|
}
|
|
|
|
void Prev() override {
|
|
do {
|
|
input_->Prev();
|
|
} while (!filter());
|
|
}
|
|
|
|
Slice key() const override { return input_->key(); }
|
|
|
|
Slice value() const override { return input_->value(); }
|
|
|
|
Status status() const override { return input_->status(); }
|
|
|
|
bool IsKeyPinned() const override { return input_->IsKeyPinned(); }
|
|
|
|
bool IsValuePinned() const override { return input_->IsValuePinned(); }
|
|
|
|
bool IsDeleteRangeSentinelKey() const override {
|
|
return input_->IsDeleteRangeSentinelKey();
|
|
}
|
|
|
|
private:
|
|
InternalIterator* input_;
|
|
const std::string filter_ts_;
|
|
const Comparator* const cmp_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|