perf tests: Run tests in parallel by default

Switch from running tests sequentially to running in parallel by
default. Change the opt-in '-p' or '--parallel' flag to '-S' or
'--sequential'.

On an 8 core tigerlake an address sanitizer run time changes from:

  326.54user 622.73system 6:59.91elapsed 226%CPU

to:

  973.02user 583.98system 3:01.17elapsed 859%CPU

So over twice as fast, saving 4 minutes.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240301174711.2646944-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 10 insertions, 7 deletions

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index ddb2f4e38ea5..73f53b02f733 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -39,8 +39,8 @@
  * making them easier to debug.
  */
 static bool dont_fork;
-/* Fork the tests in parallel and then wait for their completion. */
-static bool parallel;
+/* Don't fork the tests in parallel and wait for their completion. */
+static bool sequential;
 const char *dso_to_test;
 const char *test_objdump_path = "objdump";
 
@@ -374,7 +374,7 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 	}
 	(*child)->process.no_exec_cmd = run_test_child;
 	err = start_command(&(*child)->process);
-	if (err || parallel)
+	if (err || !sequential)
 		return  err;
 	return finish_test(*child, width);
 }
@@ -440,7 +440,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			int err = start_test(t, curr, -1, &child_tests[child_test_num++], width);
 
 			if (err) {
-				/* TODO: if parallel waitpid the already forked children. */
+				/* TODO: if !sequential waitpid the already forked children. */
 				free(child_tests);
 				return err;
 			}
@@ -460,7 +460,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 	}
 	for (i = 0; i < child_test_num; i++) {
-		if (parallel) {
+		if (!sequential) {
 			int ret  = finish_test(child_tests[i], width);
 
 			if (ret)
@@ -536,8 +536,8 @@ int cmd_test(int argc, const char **argv)
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('F', "dont-fork", &dont_fork,
 		    "Do not fork for testcase"),
-	OPT_BOOLEAN('p', "parallel", &parallel,
-		    "Run the tests altogether in parallel"),
+	OPT_BOOLEAN('S', "sequential", &sequential,
+		    "Run the tests one after another rather than in parallel"),
 	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"),
 	OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"),
 	OPT_STRING(0, "objdump", &test_objdump_path, "path",
@@ -564,6 +564,9 @@ int cmd_test(int argc, const char **argv)
 	if (workload)
 		return run_workload(workload, argc, argv);
 
+	if (dont_fork)
+		sequential = true;
+
 	symbol_conf.priv_size = sizeof(int);
 	symbol_conf.try_vmlinux_path = true;