[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAP-5=fU7PNEDgOg=cFKkSMgHe7_Xbi5Y9k6yPoAwOpN-Uwdp7A@mail.gmail.com>
Date: Wed, 20 Mar 2024 08:58:37 -0700
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>,
James Clark <james.clark@....com>, Kan Liang <kan.liang@...ux.intel.com>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v1] perf tests: Run tests in parallel by default
On Fri, Mar 1, 2024 at 9:47 AM Ian Rogers <irogers@...gle.com> wrote:
>
> 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@...gle.com>
Ping.
Thanks,
Ian
> ---
> This change is on top of the test fixes in:
> https://lore.kernel.org/lkml/20240301074639.2260708-1-irogers@google.com/
> ---
> tools/perf/tests/builtin-test.c | 17 ++++++++++-------
> 1 file 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", ¶llel,
> - "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;
>
> --
> 2.44.0.278.ge034bb2e1d-goog
>
Powered by blists - more mailing lists