ea5e649225
Summary: Problem The TEST_WaitForCompact in TimestampCompatibleCompactionTest.UdtTombstoneCollapsingTest would sometimes run forever, indicating an infinite compaction loop. Issue https://github.com/facebook/rocksdb/issues/14223 Root Cause In ComputeBottommostFilesMarkedForCompaction(), files were marked for bottommost compaction based only on the condition largest_seqno < oldest_snapshot_seqnum. However, for User-Defined Timestamps (UDT) columns, compaction can only zero sequence numbers when the file's maximum timestamp is below full_history_ts_low. When timestamps were above this threshold: 1. File gets marked for compaction (seqno condition met) 2. Compaction runs but cannot zero seqno (timestamp condition not met) 3. Output file immediately gets re-marked for compaction 4. Infinite loop Solution Added timestamp range tracking to FileMetaData and updated the marking logic to check timestamps before marking files. Pull Request resolved: https://github.com/facebook/rocksdb/pull/14228 Test Plan: Unit test Reviewed By: pdillinger Differential Revision: D90586045 Pulled By: xingbowang fbshipit-source-id: addfa4f988db8c87fb513a1bf58ee54623a6c210
84 lines
3.6 KiB
C++
84 lines
3.6 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).
|
|
// 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
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
|
|
#include "db/internal_stats.h"
|
|
#include "db/range_tombstone_fragmenter.h"
|
|
#include "db/seqno_to_time_mapping.h"
|
|
#include "db/table_properties_collector.h"
|
|
#include "db/version_set.h"
|
|
#include "logging/event_logger.h"
|
|
#include "options/cf_options.h"
|
|
#include "rocksdb/comparator.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/listener.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/status.h"
|
|
#include "rocksdb/table_properties.h"
|
|
#include "rocksdb/types.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
struct FileMetaData;
|
|
|
|
class VersionSet;
|
|
class BlobFileAddition;
|
|
class SnapshotChecker;
|
|
class TableCache;
|
|
class TableBuilder;
|
|
class WritableFileWriter;
|
|
class BlobFileCompletionCallback;
|
|
|
|
// Convenience function for NewTableBuilder on the embedded table_factory.
|
|
TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
|
|
WritableFileWriter* file);
|
|
|
|
// Extract min/max timestamps from table properties and populate FileMetaData.
|
|
// This is used by both flush (BuildTable) and compaction (CompactionOutputs)
|
|
// to populate timestamp range in FileMetaData from the TimestampTableProperties
|
|
// collector output.
|
|
void ExtractTimestampFromTableProperties(const TableProperties& tp,
|
|
FileMetaData* meta);
|
|
|
|
// Build a Table file from the contents of *iter. The generated file
|
|
// will be named according to number specified in meta. On success, the rest of
|
|
// *meta will be filled with metadata about the generated table.
|
|
// If no data is present in *iter, meta->file_size will be set to
|
|
// zero, and no Table file will be produced.
|
|
//
|
|
// @param column_family_name Name of the column family that is also identified
|
|
// by column_family_id, or empty string if unknown.
|
|
// @param flush_stats treat flush as level 0 compaction in internal stats
|
|
Status BuildTable(
|
|
const std::string& dbname, VersionSet* versions,
|
|
const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
|
|
const FileOptions& file_options, TableCache* table_cache,
|
|
InternalIterator* iter,
|
|
std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
|
|
range_del_iters,
|
|
FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
|
|
std::vector<SequenceNumber> snapshots, SequenceNumber earliest_snapshot,
|
|
SequenceNumber earliest_write_conflict_snapshot,
|
|
SequenceNumber job_snapshot, SnapshotChecker* snapshot_checker,
|
|
bool paranoid_file_checks, InternalStats* internal_stats,
|
|
IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
|
|
BlobFileCreationReason blob_creation_reason,
|
|
UnownedPtr<const SeqnoToTimeMapping> seqno_to_time_mapping,
|
|
EventLogger* event_logger = nullptr, int job_id = 0,
|
|
TableProperties* table_properties = nullptr,
|
|
Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
|
|
const std::string* full_history_ts_low = nullptr,
|
|
BlobFileCompletionCallback* blob_callback = nullptr,
|
|
Version* version = nullptr, uint64_t* memtable_payload_bytes = nullptr,
|
|
uint64_t* memtable_garbage_bytes = nullptr,
|
|
InternalStats::CompactionStats* flush_stats = nullptr);
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|