Add --slow_usecs option to determine when long op message is printed (#9732)

Summary:
This adds the --slow_usecs option with a default value of 1M. Operations that
take this much time have a message printed when --histogram=1, --stats_interval=0
and --stats_interval_seconds=0. The current code hardwired this to 20,000 usecs
and for some stress tests that reduced throughput by 20% or more.

This is for https://github.com/facebook/rocksdb/issues/9620

Pull Request resolved: https://github.com/facebook/rocksdb/pull/9732

Test Plan:
./db_bench --benchmarks=fillrandom,readrandom --compression_type=lz4 --slow_usecs=100 --histogram=1
./db_bench --benchmarks=fillrandom,readrandom --compression_type=lz4 --slow_usecs=100000 --histogram=1

Reviewed By: jay-zhuang

Differential Revision: D35121522

Pulled By: mdcallag

fbshipit-source-id: daf27f937efd748980545d6395db332712fc078b

tools/db_bench_tool.cc

@@ -1240,6 +1240,10 @@ DEFINE_int64(stats_interval_seconds, 0, "Report stats every N seconds. This "
 DEFINE_int32(stats_per_interval, 0, "Reports additional stats per interval when"
              " this is greater than 0.");
 
+DEFINE_uint64(slow_usecs, 1000000,
+              "A message is printed for operations that "
+              "take at least this many microseconds.");
+
 DEFINE_int64(report_interval_seconds, 0,
              "If greater than zero, it will write simple stats in CSV format "
              "to --report_file every N seconds");
@@ -2145,7 +2149,7 @@ class Stats {
       }
       hist_[op_type]->Add(micros);
 
-      if (micros > 20000 && !FLAGS_stats_interval) {
+      if (micros >= FLAGS_slow_usecs && !FLAGS_stats_interval) {
         fprintf(stderr, "long op: %" PRIu64 " micros%30s\r", micros, "");
         fflush(stderr);
       }