perf stat: Add --sync/-S option
--sync will tell perf stat to run sync() before starting a command.
This allows IO-heavy tests to be used with --repeat, without one
iteration impacting the other.
Elapsed time will stabilize for example:
before: 3.971525714 seconds time elapsed ( +- 8.56% )
after: 3.211098537 seconds time elapsed ( +- 1.52% )
So measurements will be more accurate.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/n/tip-7y40wib8n1eqio7hjpn1dsrm@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 003caa8..5658a77 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -128,6 +128,7 @@
static pid_t child_pid = -1;
static bool null_run = false;
static bool detailed_run = false;
+static bool sync_run = false;
static bool big_num = true;
static int big_num_opt = -1;
static const char *cpu_list;
@@ -819,6 +820,8 @@
"null run - dont start any counters"),
OPT_BOOLEAN('d', "detailed", &detailed_run,
"detailed run - start a lot of events"),
+ OPT_BOOLEAN('S', "sync", &sync_run,
+ "call sync() before starting a run"),
OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
"print large numbers with thousands\' separators",
stat__set_big_num),
@@ -944,6 +947,10 @@
for (run_idx = 0; run_idx < run_count; run_idx++) {
if (run_count != 1 && verbose)
fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
+
+ if (sync_run)
+ sync();
+
status = run_perf_stat(argc, argv);
}