Vary bloom_bits in db_crashtest (#6103)

Summary:
Especially with non-integral bits/key now supported,
db_crashtest should vary the bloom_bits configuration. The probabilities
look like this:

1/2 chance of a uniform int from 0 to 19. This includes overall 1/40
chance of 0 which disables the bloom filter.

1/2 chance of a float from a lognormal distribution with a median of 10.
This always produces positive values but with a decent chance of < 1
(overall ~1/40) or > 100 (overall ~1/40), the enforced/coerced
implementation limits.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6103

Test Plan:
start 'make blackbox_crash_test' several times and look at
configuration output

Differential Revision: D18734877

Pulled By: pdillinger

fbshipit-source-id: 4a38cb057d3b3fc1327f93199f65b9a9ffbd7316

db_stress_tool/db_stress_common.h

@@ -133,7 +133,7 @@ DECLARE_uint64(compaction_ttl);
 DECLARE_bool(allow_concurrent_memtable_write);
 DECLARE_bool(enable_write_thread_adaptive_yield);
 DECLARE_int32(reopen);
-DECLARE_int32(bloom_bits);
+DECLARE_double(bloom_bits);
 DECLARE_bool(use_block_based_filter);
 DECLARE_bool(partition_filters);
 DECLARE_int32(index_type);
@@ -342,6 +342,17 @@ extern inline std::string StringToHex(const std::string& str) {
   return result;
 }
 
+// Unified output format for double parameters
+extern inline std::string FormatDoubleParam(double param) {
+  return std::to_string(param);
+}
+
+// Make sure that double parameter is a value we can reproduce by
+// re-inputting the value printed.
+extern inline void SanitizeDoubleParam(double* param) {
+  *param = std::atof(FormatDoubleParam(*param).c_str());
+}
+
 extern void PoolSizeChangeThread(void* v);
 
 extern void PrintKeyValue(int cf, uint64_t key, const char* value, size_t sz);

db_stress_tool/db_stress_gflags.cc

@@ -275,9 +275,9 @@ DEFINE_int32(reopen, 10, "Number of times database reopens");
 static const bool FLAGS_reopen_dummy __attribute__((__unused__)) =
     RegisterFlagValidator(&FLAGS_reopen, &ValidateInt32Positive);
 
-DEFINE_int32(bloom_bits, 10,
-             "Bloom filter bits per key. "
-             "Negative means use default settings.");
+DEFINE_double(bloom_bits, 10,
+              "Bloom filter bits per key. "
+              "Negative means use default settings.");
 
 DEFINE_bool(use_block_based_filter, false,
             "use block based filter"

db_stress_tool/db_stress_test_base.cc

@@ -1310,6 +1310,8 @@ void StressTest::PrintEnv() const {
   fprintf(stdout, "Compression               : %s\n", compression.c_str());
   std::string checksum = ChecksumTypeToString(FLAGS_checksum_type_e);
   fprintf(stdout, "Checksum type             : %s\n", checksum.c_str());
+  fprintf(stdout, "Bloom bits / key          : %s\n",
+          FormatDoubleParam(FLAGS_bloom_bits).c_str());
   fprintf(stdout, "Max subcompactions        : %" PRIu64 "\n",
           FLAGS_subcompactions);
   fprintf(stdout, "Use MultiGet              : %s\n",

db_stress_tool/db_stress_tool.cc

@@ -34,6 +34,10 @@ int db_stress_tool(int argc, char** argv) {
                   " [OPTIONS]...");
   ParseCommandLineFlags(&argc, &argv, true);
 
+  SanitizeDoubleParam(&FLAGS_bloom_bits);
+  SanitizeDoubleParam(&FLAGS_memtable_prefix_bloom_size_ratio);
+  SanitizeDoubleParam(&FLAGS_max_bytes_for_level_multiplier);
+
   if (FLAGS_statistics) {
     dbstats = rocksdb::CreateDBStatistics();
     if (FLAGS_enable_secondary) {

tools/db_crashtest.py

@@ -25,6 +25,8 @@ expected_values_file = tempfile.NamedTemporaryFile()
 default_params = {
     "acquire_snapshot_one_in": 10000,
     "block_size": 16384,
+    "bloom_bits": lambda: random.choice([random.randint(0,19),
+                                         random.lognormvariate(2.3, 1.3)]),
     "cache_index_and_filter_blocks": lambda: random.randint(0, 1),
     "cache_size": 1048576,
     "checkpoint_one_in": 1000000,