6fbe96baf8
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
163 lines
6.1 KiB
C++
163 lines
6.1 KiB
C++
// 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.
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// 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.
|
|
#pragma once
|
|
|
|
#include <algorithm>
|
|
#include <deque>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#include "db/compaction.h"
|
|
#include "db/merge_helper.h"
|
|
#include "db/pinned_iterators_manager.h"
|
|
#include "db/range_del_aggregator.h"
|
|
#include "rocksdb/compaction_filter.h"
|
|
#include "util/log_buffer.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
struct CompactionIteratorStats {
|
|
// Compaction statistics
|
|
int64_t num_record_drop_user = 0;
|
|
int64_t num_record_drop_hidden = 0;
|
|
int64_t num_record_drop_obsolete = 0;
|
|
uint64_t total_filter_time = 0;
|
|
|
|
// Input statistics
|
|
// TODO(noetzli): The stats are incomplete. They are lacking everything
|
|
// consumed by MergeHelper.
|
|
uint64_t num_input_records = 0;
|
|
uint64_t num_input_deletion_records = 0;
|
|
uint64_t num_input_corrupt_records = 0;
|
|
uint64_t total_input_raw_key_bytes = 0;
|
|
uint64_t total_input_raw_value_bytes = 0;
|
|
|
|
// Single-Delete diagnostics for exceptional situations
|
|
uint64_t num_single_del_fallthru = 0;
|
|
uint64_t num_single_del_mismatch = 0;
|
|
};
|
|
|
|
class CompactionIterator {
|
|
public:
|
|
CompactionIterator(InternalIterator* input, const Comparator* cmp,
|
|
MergeHelper* merge_helper, SequenceNumber last_sequence,
|
|
std::vector<SequenceNumber>* snapshots,
|
|
SequenceNumber earliest_write_conflict_snapshot, Env* env,
|
|
bool expect_valid_internal_key,
|
|
RangeDelAggregator* range_del_agg,
|
|
const Compaction* compaction = nullptr,
|
|
const CompactionFilter* compaction_filter = nullptr,
|
|
LogBuffer* log_buffer = nullptr);
|
|
|
|
~CompactionIterator();
|
|
|
|
void ResetRecordCounts();
|
|
|
|
// Seek to the beginning of the compaction iterator output.
|
|
//
|
|
// REQUIRED: Call only once.
|
|
void SeekToFirst();
|
|
|
|
// Produces the next record in the compaction.
|
|
//
|
|
// REQUIRED: SeekToFirst() has been called.
|
|
void Next();
|
|
|
|
// Getters
|
|
const Slice& key() const { return key_; }
|
|
const Slice& value() const { return value_; }
|
|
const Status& status() const { return status_; }
|
|
const ParsedInternalKey& ikey() const { return ikey_; }
|
|
bool Valid() const { return valid_; }
|
|
const Slice& user_key() const { return current_user_key_; }
|
|
const CompactionIteratorStats& iter_stats() const { return iter_stats_; }
|
|
|
|
private:
|
|
// Processes the input stream to find the next output
|
|
void NextFromInput();
|
|
|
|
// Do last preparations before presenting the output to the callee. At this
|
|
// point this only zeroes out the sequence number if possible for better
|
|
// compression.
|
|
void PrepareOutput();
|
|
|
|
// Given a sequence number, return the sequence number of the
|
|
// earliest snapshot that this sequence number is visible in.
|
|
// The snapshots themselves are arranged in ascending order of
|
|
// sequence numbers.
|
|
// Employ a sequential search because the total number of
|
|
// snapshots are typically small.
|
|
inline SequenceNumber findEarliestVisibleSnapshot(
|
|
SequenceNumber in, SequenceNumber* prev_snapshot);
|
|
|
|
InternalIterator* input_;
|
|
const Comparator* cmp_;
|
|
MergeHelper* merge_helper_;
|
|
const std::vector<SequenceNumber>* snapshots_;
|
|
const SequenceNumber earliest_write_conflict_snapshot_;
|
|
Env* env_;
|
|
bool expect_valid_internal_key_;
|
|
RangeDelAggregator* range_del_agg_;
|
|
const Compaction* compaction_;
|
|
const CompactionFilter* compaction_filter_;
|
|
LogBuffer* log_buffer_;
|
|
bool bottommost_level_;
|
|
bool valid_ = false;
|
|
bool visible_at_tip_;
|
|
SequenceNumber earliest_snapshot_;
|
|
SequenceNumber latest_snapshot_;
|
|
bool ignore_snapshots_;
|
|
|
|
// State
|
|
//
|
|
// Points to a copy of the current compaction iterator output (current_key_)
|
|
// if valid_.
|
|
Slice key_;
|
|
// Points to the value in the underlying iterator that corresponds to the
|
|
// current output.
|
|
Slice value_;
|
|
// The status is OK unless compaction iterator encounters a merge operand
|
|
// while not having a merge operator defined.
|
|
Status status_;
|
|
// Stores the user key, sequence number and type of the current compaction
|
|
// iterator output (or current key in the underlying iterator during
|
|
// NextFromInput()).
|
|
ParsedInternalKey ikey_;
|
|
// Stores whether ikey_.user_key is valid. If set to false, the user key is
|
|
// not compared against the current key in the underlying iterator.
|
|
bool has_current_user_key_ = false;
|
|
bool at_next_ = false; // If false, the iterator
|
|
// Holds a copy of the current compaction iterator output (or current key in
|
|
// the underlying iterator during NextFromInput()).
|
|
IterKey current_key_;
|
|
Slice current_user_key_;
|
|
SequenceNumber current_user_key_sequence_;
|
|
SequenceNumber current_user_key_snapshot_;
|
|
|
|
// True if the iterator has already returned a record for the current key.
|
|
bool has_outputted_key_ = false;
|
|
|
|
// truncated the value of the next key and output it without applying any
|
|
// compaction rules. This is used for outputting a put after a single delete.
|
|
bool clear_and_output_next_key_ = false;
|
|
|
|
MergeOutputIterator merge_out_iter_;
|
|
// PinnedIteratorsManager used to pin input_ Iterator blocks while reading
|
|
// merge operands and then releasing them after consuming them.
|
|
PinnedIteratorsManager pinned_iters_mgr_;
|
|
std::string compaction_filter_value_;
|
|
// "level_ptrs" holds indices that remember which file of an associated
|
|
// level we were last checking during the last call to compaction->
|
|
// KeyNotExistsBeyondOutputLevel(). This allows future calls to the function
|
|
// to pick off where it left off since each subcompaction's key range is
|
|
// increasing so a later call to the function must be looking for a key that
|
|
// is in or beyond the last file checked during the previous call
|
|
std::vector<size_t> level_ptrs_;
|
|
CompactionIteratorStats iter_stats_;
|
|
};
|
|
} // namespace rocksdb
|