Mark files for compaction in stress/crash tests (#7231)

Summary:
The mechanism to mark files for compaction is most commonly used in
delete-triggered compaction. This PR adds an option to exercise the
marking mechanism on random files created by db_stress. This PR also
enables that option in db_crashtest.py on its db_stress runs at random.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/7231

Test Plan:
- ran some minified crash tests; verified they succeed and we see `"compaction_reason": "FilesMarkedForCompaction"` regularly in the logs.

```
$ TEST_TMPDIR=/dev/shm python tools/db_crashtest.py blackbox --duration=600 --interval=30 --max_key=10000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33
$ TEST_TMPDIR=/dev/shm python tools/db_crashtest.py whitebox --duration=600 --interval=30 --max_key=1000000 --write_buffer_size=1048576 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --value_size_mult=33 --random_kill_odd=8887
```

Reviewed By: anand1976

Differential Revision: D23025156

Pulled By: ajkr

fbshipit-source-id: a404c467ebc12afa94dae35956ea9b372f592a96

db_stress_tool/db_stress_common.h

@@ -179,6 +179,7 @@ DECLARE_int32(ingest_external_file_one_in);
 DECLARE_int32(ingest_external_file_width);
 DECLARE_int32(compact_files_one_in);
 DECLARE_int32(compact_range_one_in);
+DECLARE_int32(mark_for_compaction_one_file_in);
 DECLARE_int32(flush_one_in);
 DECLARE_int32(pause_background_one_in);
 DECLARE_int32(compact_range_width);

db_stress_tool/db_stress_gflags.cc

@@ -500,6 +500,12 @@ DEFINE_int32(compact_range_one_in, 0,
              "If non-zero, then CompactRange() will be called once for every N "
              "operations on average.  0 indicates CompactRange() is disabled.");
 
+DEFINE_int32(mark_for_compaction_one_file_in, 0,
+             "A `TablePropertiesCollectorFactory` will be registered, which "
+             "creates a `TablePropertiesCollector` with `NeedCompact()` "
+             "returning true once for every N files on average. 0 or negative "
+             "mean `NeedCompact()` always returns false.");
+
 DEFINE_int32(flush_one_in, 0,
              "If non-zero, then Flush() will be called once for every N ops "
              "on average.  0 indicates calls to Flush() are disabled.");

db_stress_tool/db_stress_table_properties_collector.h

@@ -0,0 +1,64 @@
+//  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 "rocksdb/table.h"
+#include "util/gflags_compat.h"
+
+DECLARE_int32(mark_for_compaction_one_file_in);
+
+namespace ROCKSDB_NAMESPACE {
+
+// A `DbStressTablePropertiesCollector` ignores what keys/values were added to
+// the table, adds no properties to the table, and decides at random whether the
+// table will be marked for compaction according to
+// `FLAGS_mark_for_compaction_one_file_in`.
+class DbStressTablePropertiesCollector : public TablePropertiesCollector {
+ public:
+  DbStressTablePropertiesCollector()
+      : need_compact_(Random::GetTLSInstance()->OneInOpt(
+            FLAGS_mark_for_compaction_one_file_in)) {}
+
+  virtual Status AddUserKey(const Slice& /* key */, const Slice& /* value */,
+                            EntryType /*type*/, SequenceNumber /*seq*/,
+                            uint64_t /*file_size*/) override {
+    return Status::OK();
+  }
+
+  virtual Status Finish(UserCollectedProperties* /* properties */) override {
+    return Status::OK();
+  }
+
+  virtual UserCollectedProperties GetReadableProperties() const override {
+    return UserCollectedProperties{};
+  }
+
+  virtual const char* Name() const override {
+    return "DbStressTablePropertiesCollector";
+  }
+
+  virtual bool NeedCompact() const override { return need_compact_; }
+
+ private:
+  const bool need_compact_;
+};
+
+// A `DbStressTablePropertiesCollectorFactory` creates
+// `DbStressTablePropertiesCollectorFactory`s.
+class DbStressTablePropertiesCollectorFactory
+    : public TablePropertiesCollectorFactory {
+ public:
+  virtual TablePropertiesCollector* CreateTablePropertiesCollector(
+      TablePropertiesCollectorFactory::Context /* context */) override {
+    return new DbStressTablePropertiesCollector();
+  }
+
+  virtual const char* Name() const override {
+    return "DbStressTablePropertiesCollectorFactory";
+  }
+};
+
+}  // namespace ROCKSDB_NAMESPACE

db_stress_tool/db_stress_test_base.cc

@@ -12,6 +12,7 @@
 #include "db_stress_tool/db_stress_common.h"
 #include "db_stress_tool/db_stress_compaction_filter.h"
 #include "db_stress_tool/db_stress_driver.h"
+#include "db_stress_tool/db_stress_table_properties_collector.h"
 #include "rocksdb/convenience.h"
 #include "rocksdb/sst_file_manager.h"
 #include "util/cast_util.h"
@@ -2015,6 +2016,8 @@ void StressTest::Open() {
     options_.compaction_filter_factory =
         std::make_shared<DbStressCompactionFilterFactory>();
   }
+  options_.table_properties_collector_factories.emplace_back(
+      std::make_shared<DbStressTablePropertiesCollectorFactory>());
 
   options_.best_efforts_recovery = FLAGS_best_efforts_recovery;
 

tools/db_crashtest.py

@@ -66,6 +66,7 @@ default_params = {
     # Temporarily disable hash index
     "index_type": lambda: random.choice([0, 0, 0, 2, 2, 3]),
     "iterpercent": 10,
+    "mark_for_compaction_one_file_in": lambda: 10 * random.randint(0, 1),
     "max_background_compactions": 20,
     "max_bytes_for_level_base": 10485760,
     "max_key": 100000000,