rocksdb/table/merging_iterator.h
Peter Dillinger 39455974cb Fix possible double-free on TruncatedRangeDelIterator (#12805)
Summary:
Not sure where or how it happens, but using a recent CircleCI failure I got a reliable db_stress reproducer.

Using std::unique_ptr appropriately for managing them has apparently (and unsurprisingly) fixed the problem without needing to know exactly where the problem was.

Suggested follow-up:
* Three or even four levels of pointers is very confusing to work with. Surely this part can be cleaned up to be simpler.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12805

Test Plan:
Reproducer passes, plus ASAN test and crash test runs. I don't think it's worth the extra work to track down the details and create a careful unit test.

```
./db_stress --WAL_size_limit_MB=1 --WAL_ttl_seconds=60 --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --adm_policy=2 --advise_random_on_open=1 --allow_data_in_errors=True --allow_fallocate=1 --async_io=0 --auto_readahead_size=1 --avoid_flush_during_recovery=0 --avoid_flush_during_shutdown=1 --avoid_unnecessary_blocking_io=1 --backup_max_size=104857600 --backup_one_in=100000 --batch_protection_bytes_per_key=0 --bgerror_resume_retry_interval=1000000 --block_align=1 --block_protection_bytes_per_key=4 --block_size=16384 --bloom_before_level=2147483646 --bloom_bits=15 --bottommost_compression_type=none --bottommost_file_compaction_delay=3600 --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_index_and_filter_blocks_with_high_priority=0 --cache_size=33554432 --cache_type=tiered_lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=0 --charge_table_reader=0 --check_multiget_consistency=1 --check_multiget_entity_consistency=1 --checkpoint_one_in=10000 --checksum_type=kxxHash --clear_column_family_one_in=0 --compact_files_one_in=1000000 --compact_range_one_in=1000 --compaction_pri=0 --compaction_readahead_size=0 --compaction_ttl=0 --compress_format_version=2 --compressed_secondary_cache_ratio=0.2 --compressed_secondary_cache_size=0 --compression_checksum=0 --compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 --compression_parallel_threads=1 --compression_type=none --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --daily_offpeak_time_utc= --data_block_index_type=0 --db=/dev/shm/rocksdb.gpxs/rocksdb_crashtest_blackbox --db_write_buffer_size=0 --default_temperature=kWarm --default_write_temperature=kCold --delete_obsolete_files_period_micros=21600000000 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_file_deletions_one_in=10000 --disable_manual_compaction_one_in=1000000 --disable_wal=0 --dump_malloc_stats=1 --enable_checksum_handoff=1 --enable_compaction_filter=0 --enable_custom_split_merge=0 --enable_do_not_compress_roles=0 --enable_index_compression=0 --enable_memtable_insert_with_hint_prefix_extractor=0 --enable_pipelined_write=1 --enable_sst_partitioner_factory=0 --enable_thread_tracking=1 --enable_write_thread_adaptive_yield=0 --error_recovery_with_no_fault_injection=0 --expected_values_dir=/dev/shm/rocksdb.gpxs/rocksdb_crashtest_expected --fail_if_options_file_error=0 --fifo_allow_compaction=0 --file_checksum_impl=none --fill_cache=1 --flush_one_in=1000000 --format_version=3 --get_all_column_family_metadata_one_in=1000000 --get_current_wal_file_one_in=0 --get_live_files_apis_one_in=10000 --get_properties_of_all_tables_one_in=100000 --get_property_one_in=100000 --get_sorted_wal_files_one_in=0 --hard_pending_compaction_bytes_limit=274877906944 --high_pri_pool_ratio=0 --index_block_restart_interval=4 --index_shortening=0 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=16384 --inplace_update_support=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --key_may_exist_one_in=100 --last_level_temperature=kHot --level_compaction_dynamic_level_bytes=0 --lock_wal_one_in=1000000 --log_file_time_to_roll=0 --log_readahead_size=0 --long_running_snapshots=1 --low_pri_pool_ratio=0 --lowest_used_cache_tier=2 --manifest_preallocation_size=5120 --manual_wal_flush_one_in=1000 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=16384 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=2500000 --max_key_len=3 --max_log_file_size=0 --max_manifest_file_size=1073741824 --max_sequential_skip_in_iterations=1 --max_total_wal_size=0 --max_write_batch_group_size_bytes=16 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_insert_hint_per_batch=1 --memtable_max_range_deletions=100 --memtable_prefix_bloom_size_ratio=0 --memtable_protection_bytes_per_key=4 --memtable_whole_key_filtering=0 --memtablerep=skip_list --metadata_charge_policy=0 --metadata_read_fault_one_in=32 --metadata_write_fault_one_in=0 --min_write_buffer_number_to_merge=2 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=100 --open_metadata_read_fault_one_in=0 --open_metadata_write_fault_one_in=8 --open_read_fault_one_in=0 --open_write_fault_one_in=16 --ops_per_thread=100000000 --optimize_filters_for_hits=1 --optimize_filters_for_memory=0 --optimize_multiget_for_io=1 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=1 --pause_background_one_in=1000000 --periodic_compaction_seconds=0 --prefix_size=-1 --prefixpercent=0 --prepopulate_block_cache=1 --preserve_internal_time_seconds=60 --progress_reports=0 --promote_l0_one_in=0 --read_amp_bytes_per_bit=0 --read_fault_one_in=32 --readahead_size=524288 --readpercent=50 --recycle_log_file_num=1 --reopen=0 --report_bg_io_stats=1 --reset_stats_one_in=10000 --sample_for_compression=5 --secondary_cache_fault_one_in=32 --secondary_cache_uri= --set_options_one_in=10000 --skip_stats_update_on_db_open=0 --snapshot_hold_ops=100000 --soft_pending_compaction_bytes_limit=68719476736 --sqfc_name=bar --sqfc_version=1 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=0 --stats_history_buffer_size=1048576 --strict_bytes_per_sync=1 --subcompactions=3 --sync=0 --sync_fault_injection=1 --table_cache_numshardbits=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --test_cf_consistency=1 --top_level_index_pinning=1 --uncache_aggressiveness=5 --universal_max_read_amp=-1 --unpartitioned_pinning=2 --use_adaptive_mutex=0 --use_adaptive_mutex_lru=0 --use_attribute_group=1 --use_delta_encoding=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_get_entity=0 --use_merge=0 --use_multi_cf_iterator=0 --use_multi_get_entity=0 --use_multiget=1 --use_put_entity_one_in=1 --use_sqfc_for_range_queries=1 --use_timed_put_one_in=0 --use_write_buffer_manager=0 --user_timestamp_size=0 --value_size_mult=32 --verification_only=0 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_compression=1 --verify_db_one_in=100000 --verify_file_checksums_one_in=0 --verify_iterator_with_expected_state_one_in=0 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=0 --wal_compression=none --write_buffer_size=1048576 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=35
```

Reviewed By: cbi42

Differential Revision: D58958390

Pulled By: pdillinger

fbshipit-source-id: 1271cfdcc3c574f78cd59f3c68148f7ed4a19c47
2024-06-24 11:51:16 -07:00

101 lines
4.3 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).
//
// 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 "db/range_del_aggregator.h"
#include "rocksdb/slice.h"
#include "rocksdb/types.h"
#include "table/iterator_wrapper.h"
namespace ROCKSDB_NAMESPACE {
class Arena;
class ArenaWrappedDBIter;
class InternalKeyComparator;
template <class TValue>
class InternalIteratorBase;
using InternalIterator = InternalIteratorBase<Slice>;
// Return an iterator that provides the union of the data in
// children[0,n-1]. Takes ownership of the child iterators and
// will delete them when the result iterator is deleted.
//
// The result does no duplicate suppression. I.e., if a particular
// key is present in K child iterators, it will be yielded K times.
//
// REQUIRES: n >= 0
InternalIterator* NewMergingIterator(const InternalKeyComparator* comparator,
InternalIterator** children, int n,
Arena* arena = nullptr,
bool prefix_seek_mode = false);
// The iterator returned by NewMergingIterator() and
// MergeIteratorBuilder::Finish(). MergingIterator handles the merging of data
// from different point and/or range tombstone iterators.
class MergingIterator;
// A builder class to for an iterator that provides the union of data
// of input iterators. Two APIs are provided to add input iterators. User should
// only call one of them exclusively depending on if range tombstone should be
// processed.
class MergeIteratorBuilder {
public:
// comparator: the comparator used in merging comparator
// arena: where the merging iterator needs to be allocated from.
explicit MergeIteratorBuilder(const InternalKeyComparator* comparator,
Arena* arena, bool prefix_seek_mode = false,
const Slice* iterate_upper_bound = nullptr);
~MergeIteratorBuilder();
// Add point key iterator `iter` to the merging iterator.
void AddIterator(InternalIterator* iter);
// Add a point key iterator and a range tombstone iterator.
// `tombstone_iter_ptr` should and only be set by LevelIterator.
// *tombstone_iter_ptr will be set to where the merging iterator stores
// `tombstone_iter` when MergeIteratorBuilder::Finish() is called. This is
// used by LevelIterator to update range tombstone iters when switching to a
// different SST file. If a single point iterator with a nullptr range
// tombstone iterator is provided, and the point iterator is not a level
// iterator, then this builder will return the point iterator directly,
// instead of creating a merging iterator on top of it. Internally, if all
// point iterators are not LevelIterator, then range tombstone iterator is
// only added to the merging iter if there is a non-null `tombstone_iter`.
void AddPointAndTombstoneIterator(
InternalIterator* point_iter,
std::unique_ptr<TruncatedRangeDelIterator>&& tombstone_iter,
std::unique_ptr<TruncatedRangeDelIterator>** tombstone_iter_ptr =
nullptr);
// Get arena used to build the merging iterator. It is called one a child
// iterator needs to be allocated.
Arena* GetArena() { return arena; }
// Return the result merging iterator.
// If db_iter is not nullptr, then db_iter->SetMemtableRangetombstoneIter()
// will be called with pointer to where the merging iterator
// stores the memtable range tombstone iterator.
// This is used for DB iterator to refresh memtable range tombstones.
InternalIterator* Finish(ArenaWrappedDBIter* db_iter = nullptr);
private:
MergingIterator* merge_iter;
InternalIterator* first_iter;
bool use_merging_iter;
Arena* arena;
// Used to set LevelIterator.range_tombstone_iter_.
// See AddRangeTombstoneIterator() implementation for more detail.
std::vector<std::pair<size_t, std::unique_ptr<TruncatedRangeDelIterator>**>>
range_del_iter_ptrs_;
};
} // namespace ROCKSDB_NAMESPACE