Do not drop unsynced data during reopen in stress test (#11731)

Summary:
Currently the stress test does not support restoring expected state (to a specific sequence number) when there is unsynced data loss during the reopen phase. This causes a few internal stress test failure with errors like inconsistent value. This PR disables dropping unsynced data during reopen to avoid failures due to this issue. We can re-enable later after we decide to support unsynced data loss during DB reopen in stress test.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11731

Test Plan:
* Running this test a few times can fail for inconsistent value before this change
```
./db_stress --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --allow_concurrent_memtable_write=1 --allow_data_in_errors=True --async_io=0 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --block_protection_bytes_per_key=8 --block_size=16384 --bloom_bits=20.57166126835524 --bottommost_compression_type=disable --bytes_per_sync=262144 --cache_index_and_filter_blocks=1 --cache_size=8388608 --cache_type=auto_hyper_clock_cache --charge_compression_dictionary_building_buffer=1 --charge_file_metadata=1 --charge_filter_construction=0 --charge_table_reader=1 --checkpoint_one_in=0 --checksum_type=kxxHash --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=1000000 --compact_range_one_in=1000000 --compaction_pri=3 --compaction_style=1 --compaction_ttl=100 --compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 --compression_parallel_threads=1 --compression_type=zstd --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox --db_write_buffer_size=0 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_wal=0 --enable_compaction_filter=0 --enable_pipelined_write=1 --enable_thread_tracking=0 --expected_values_dir=/dev/shm/rocksdb_test/rocksdb_crashtest_expected --fail_if_options_file_error=1 --fifo_allow_compaction=1 --file_checksum_impl=big --flush_one_in=1000000 --format_version=3 --get_current_wal_file_one_in=0 --get_live_files_one_in=1000000 --get_property_one_in=1000000 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=6 --index_type=3 --ingest_external_file_one_in=0 --initial_auto_readahead_size=16384 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=1 --lock_wal_one_in=1000000 --log2_keys_per_lock=10 --long_running_snapshots=1 --manual_wal_flush_one_in=1000000 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=0 --max_background_compactions=1 --max_bytes_for_level_base=67108864 --max_key=25000000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=16777216 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_max_range_deletions=100 --memtable_prefix_bloom_size_ratio=0 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=0 --memtablerep=skip_list --min_write_buffer_number_to_merge=2 --mmap_read=0 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=1 --open_files=-1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=5 --open_write_fault_one_in=0 --ops_per_thread=200000 --optimize_filters_for_memory=0 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=3 --pause_background_one_in=1000000 --periodic_compaction_seconds=10 --prefix_size=-1 --prefixpercent=0 --prepopulate_block_cache=1 --preserve_internal_time_seconds=0 --progress_reports=0 --read_fault_one_in=1000 --readahead_size=524288 --readpercent=50 --recycle_log_file_num=0 --reopen=20 --ribbon_starting_level=0 --secondary_cache_fault_one_in=32 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=10 --subcompactions=3 --sync=0 --sync_fault_injection=1 --target_file_size_base=16777216 --target_file_size_multiplier=1 --test_batches_snapshots=0 --top_level_index_pinning=2 --unpartitioned_pinning=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_get_entity=1 --use_merge=0 --use_multi_get_entity=0 --use_multiget=1 --use_put_entity_one_in=1 --user_timestamp_size=0 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_db_one_in=100000 --verify_file_checksums_one_in=1000000 --verify_iterator_with_expected_state_one_in=5 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=524288 --wal_compression=zstd --write_buffer_size=33554432 --write_dbid_to_manifest=1 --writepercent=35```

Reviewed By: hx235

Differential Revision: D48537494

Pulled By: cbi42

fbshipit-source-id: ddae21b9bb6ee8d67229121f58513e95f7ef6d8d

db_stress_tool/db_stress_test_base.cc

@@ -2562,7 +2562,7 @@ void StressTest::PrintEnv() const {
   fprintf(stdout, "------------------------------------------------\n");
 }
 
-void StressTest::Open(SharedState* shared) {
+void StressTest::Open(SharedState* shared, bool reopen) {
   assert(db_ == nullptr);
   assert(txn_db_ == nullptr);
   assert(optimistic_txn_db_ == nullptr);
@@ -2777,15 +2777,20 @@ void StressTest::Open(SharedState* shared) {
             ingest_write_error = false;
             ingest_read_error = false;
 
-            Random rand(static_cast<uint32_t>(FLAGS_seed));
-            if (rand.OneIn(2)) {
-              fault_fs_guard->DeleteFilesCreatedAfterLastDirSync(IOOptions(),
-                                                                 nullptr);
-            }
-            if (rand.OneIn(3)) {
-              fault_fs_guard->DropUnsyncedFileData();
-            } else if (rand.OneIn(2)) {
-              fault_fs_guard->DropRandomUnsyncedFileData(&rand);
+            // TODO: Unsynced data loss during DB reopen is not supported yet in
+            //  stress test. Will need to recreate expected state if we decide
+            //  to support unsynced data loss during DB reopen.
+            if (!reopen) {
+              Random rand(static_cast<uint32_t>(FLAGS_seed));
+              if (rand.OneIn(2)) {
+                fault_fs_guard->DeleteFilesCreatedAfterLastDirSync(IOOptions(),
+                                                                   nullptr);
+              }
+              if (rand.OneIn(3)) {
+                fault_fs_guard->DropUnsyncedFileData();
+              } else if (rand.OneIn(2)) {
+                fault_fs_guard->DropRandomUnsyncedFileData(&rand);
+              }
             }
             continue;
           }
@@ -2940,7 +2945,7 @@ void StressTest::Reopen(ThreadState* thread) {
   auto now = clock_->NowMicros();
   fprintf(stdout, "%s Reopening database for the %dth time\n",
           clock_->TimeToString(now / 1000000).c_str(), num_times_reopened_);
-  Open(thread->shared);
+  Open(thread->shared, /*reopen=*/true);
 
   if ((FLAGS_sync_fault_injection || FLAGS_disable_wal ||
        FLAGS_manual_wal_flush_one_in > 0) &&

db_stress_tool/db_stress_test_base.h

@@ -241,7 +241,7 @@ class StressTest {
 
   void PrintEnv() const;
 
-  void Open(SharedState* shared);
+  void Open(SharedState* shared, bool reopen = false);
 
   void Reopen(ThreadState* thread);