* [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew
@ 2025-09-04 6:41 Li Wang via ltp
2025-09-04 7:20 ` Andrea Cervesato via ltp
2025-09-04 9:48 ` Petr Vorel
0 siblings, 2 replies; 6+ messages in thread
From: Li Wang via ltp @ 2025-09-04 6:41 UTC (permalink / raw)
To: ltp
Previously, thread synchronization in sched_football only relied on a
thread_barrier. This ensured that all threads were created before the
referee started the game, but did not fully prevent offense threads from
getting a scheduling opportunity before defense threads were migrated,
leading to occasional non-zero final ball positions on kvm or debug kernels.
This patch introduces an explicit `kickoff_flag`:
* All player threads (offense, defense, fans) wait at the barrier and
then spin until the referee sets `kickoff_flag`. This reduces kernel
scheduling skew, as threads only proceed once the referee explicitly
signals the kickoff.
* The referee now:
- Waits at the barrier.
- Clears the ball position.
- Sets `kickoff_flag` to start the ball.
* Game termination is also slightly reordered (by Cyril):
- Final ball position is read before `game_over` is set,
avoiding a race where the ball could still move right after
defense threads stop.
* Only test on RT-kernels.
This makes startup sequencing more deterministic while still allowing
some nondeterminism, which is intentional for testing scheduler
behavior under load.
Signed-off-by: Li Wang <liwang@redhat.com>
Signed-off-by: Cyril Hrubis <chrubis@suse.cz>
Cc: Andrea Cervesato <andrea.cervesato@suse.com>
---
| 27 ++++++++++++++-----
1 file changed, 21 insertions(+), 6 deletions(-)
--git a/testcases/realtime/func/sched_football/sched_football.c b/testcases/realtime/func/sched_football/sched_football.c
index 0617bdb87..97ac9d413 100644
--- a/testcases/realtime/func/sched_football/sched_football.c
+++ b/testcases/realtime/func/sched_football/sched_football.c
@@ -44,6 +44,7 @@
static tst_atomic_t the_ball;
static int players_per_team = 0;
static int game_length = DEF_GAME_LENGTH;
+static tst_atomic_t kickoff_flag;
static tst_atomic_t game_over;
static char *str_game_length;
@@ -55,6 +56,9 @@ void *thread_fan(void *arg LTP_ATTRIBUTE_UNUSED)
{
prctl(PR_SET_NAME, "crazy_fan", 0, 0, 0);
pthread_barrier_wait(&start_barrier);
+ while (!tst_atomic_load(&kickoff_flag))
+ ;
+
/*occasionally wake up and run across the field */
while (!tst_atomic_load(&game_over)) {
struct timespec start, stop;
@@ -80,6 +84,9 @@ void *thread_defense(void *arg LTP_ATTRIBUTE_UNUSED)
{
prctl(PR_SET_NAME, "defense", 0, 0, 0);
pthread_barrier_wait(&start_barrier);
+ while (!tst_atomic_load(&kickoff_flag))
+ ;
+
/*keep the ball from being moved */
while (!tst_atomic_load(&game_over)) {
}
@@ -92,6 +99,9 @@ void *thread_offense(void *arg LTP_ATTRIBUTE_UNUSED)
{
prctl(PR_SET_NAME, "offense", 0, 0, 0);
pthread_barrier_wait(&start_barrier);
+ while (!tst_atomic_load(&kickoff_flag))
+ ;
+
while (!tst_atomic_load(&game_over)) {
tst_atomic_add_return(1, &the_ball); /* move the ball ahead one yard */
}
@@ -115,9 +125,10 @@ void referee(int game_length)
now = start;
/* Start the game! */
- tst_atomic_store(0, &the_ball);
- pthread_barrier_wait(&start_barrier);
atrace_marker_write("sched_football", "Game_started!");
+ pthread_barrier_wait(&start_barrier);
+ tst_atomic_store(0, &the_ball);
+ tst_atomic_store(1, &kickoff_flag);
/* Watch the game */
while ((now.tv_sec - start.tv_sec) < game_length) {
@@ -125,14 +136,14 @@ void referee(int game_length)
gettimeofday(&now, NULL);
}
- /* Stop the game! */
- tst_atomic_store(1, &game_over);
- atrace_marker_write("sched_football", "Game_Over!");
-
/* Blow the whistle */
final_ball = tst_atomic_load(&the_ball);
tst_res(TINFO, "Final ball position: %d", final_ball);
+ /* Stop the game! */
+ tst_atomic_store(1, &game_over);
+ atrace_marker_write("sched_football", "Game_Over!");
+
TST_EXP_EXPR(final_ball == 0);
}
@@ -154,6 +165,7 @@ static void do_test(void)
/* We're the ref, so set our priority right */
param.sched_priority = sched_get_priority_min(SCHED_FIFO) + 80;
sched_setscheduler(0, SCHED_FIFO, ¶m);
+ tst_atomic_store(0, &kickoff_flag);
/*
* Start the offense
@@ -186,6 +198,9 @@ static void do_test(void)
static void do_setup(void)
{
+ if (!tst_check_preempt_rt())
+ tst_brk(TCONF, "Test requires real-time kernel");
+
if (tst_parse_int(str_game_length, &game_length, 1, INT_MAX))
tst_brk(TBROK, "Invalid game length '%s'", str_game_length);
--
2.51.0
--
Mailing list info: https://lists.linux.it/listinfo/ltp
^ permalink raw reply related [flat|nested] 6+ messages in thread* Re: [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew
2025-09-04 6:41 [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew Li Wang via ltp
@ 2025-09-04 7:20 ` Andrea Cervesato via ltp
2025-09-04 9:48 ` Petr Vorel
1 sibling, 0 replies; 6+ messages in thread
From: Andrea Cervesato via ltp @ 2025-09-04 7:20 UTC (permalink / raw)
To: Li Wang, ltp
Hi!
Tested-by: Andrea Cervesato <andrea.cervesato@suse.com>
- Andrea
--
Mailing list info: https://lists.linux.it/listinfo/ltp
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew
2025-09-04 6:41 [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew Li Wang via ltp
2025-09-04 7:20 ` Andrea Cervesato via ltp
@ 2025-09-04 9:48 ` Petr Vorel
2025-09-04 9:54 ` Cyril Hrubis
1 sibling, 1 reply; 6+ messages in thread
From: Petr Vorel @ 2025-09-04 9:48 UTC (permalink / raw)
To: Li Wang; +Cc: ltp
Hi Li,
...
> static void do_setup(void)
> {
> + if (!tst_check_preempt_rt())
> + tst_brk(TCONF, "Test requires real-time kernel");
I guess this itself fix many false positives :). I'm ok with requesting RT
kernel, but just to remind the claim originated from Cyril [1] "sched_football
is useful not only for testing realtime". So was Cyril wrong?
(I'm ok to keep the test in runtest/sched even requesting RT kernel, because
runtest/sched and other LTP tests are run on both RT and non-RT.
The rest LGTM, thanks for stabilising the test.
Reviewed-by: Petr Vorel <pvorel@suse.cz>
Kind regards,
Petr
[1] https://github.com/linux-test-project/ltp/commit/3a8e38fc2c46c886525bbb708dff462c6b633d32
--
Mailing list info: https://lists.linux.it/listinfo/ltp
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew
2025-09-04 9:48 ` Petr Vorel
@ 2025-09-04 9:54 ` Cyril Hrubis
2025-09-04 10:04 ` Li Wang via ltp
0 siblings, 1 reply; 6+ messages in thread
From: Cyril Hrubis @ 2025-09-04 9:54 UTC (permalink / raw)
To: Petr Vorel; +Cc: ltp
Hi!
> > static void do_setup(void)
> > {
> > + if (!tst_check_preempt_rt())
> > + tst_brk(TCONF, "Test requires real-time kernel");
>
> I guess this itself fix many false positives :). I'm ok with requesting RT
> kernel, but just to remind the claim originated from Cyril [1] "sched_football
> is useful not only for testing realtime". So was Cyril wrong?
No Cyril wasn't wrong. The realtime schedulling priorities in kernel are
completely different thing from realtime kernel patchset.
--
Cyril Hrubis
chrubis@suse.cz
--
Mailing list info: https://lists.linux.it/listinfo/ltp
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew
2025-09-04 9:54 ` Cyril Hrubis
@ 2025-09-04 10:04 ` Li Wang via ltp
2025-09-04 10:08 ` Cyril Hrubis
0 siblings, 1 reply; 6+ messages in thread
From: Li Wang via ltp @ 2025-09-04 10:04 UTC (permalink / raw)
To: Cyril Hrubis; +Cc: ltp
On Thu, Sep 4, 2025 at 5:53 PM Cyril Hrubis <chrubis@suse.cz> wrote:
> Hi!
> > > static void do_setup(void)
> > > {
> > > + if (!tst_check_preempt_rt())
> > > + tst_brk(TCONF, "Test requires real-time kernel");
> >
> > I guess this itself fix many false positives :). I'm ok with requesting
> RT
> > kernel, but just to remind the claim originated from Cyril [1]
> "sched_football
> > is useful not only for testing realtime". So was Cyril wrong?
>
> No Cyril wasn't wrong. The realtime schedulling priorities in kernel are
> completely different thing from realtime kernel patchset.
>
Yes, we can set up processes with SCHED_FIFO or SCHED_RR policies
on the stock kernel, but it's not the same thing as the PREEMPT_RT kernel.
I guess we don't need to do more tries on test with
sched_setscheduler(pid, SCHED_FIFO) situation just to avoid false positives,
because there might be no perfect solution.
So I'd prefer to keep sched_football tested only on real-time kernels.
--
Regards,
Li Wang
--
Mailing list info: https://lists.linux.it/listinfo/ltp
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew
2025-09-04 10:04 ` Li Wang via ltp
@ 2025-09-04 10:08 ` Cyril Hrubis
0 siblings, 0 replies; 6+ messages in thread
From: Cyril Hrubis @ 2025-09-04 10:08 UTC (permalink / raw)
To: Li Wang; +Cc: ltp
Hi!
> > No Cyril wasn't wrong. The realtime schedulling priorities in kernel are
> > completely different thing from realtime kernel patchset.
> >
>
> Yes, we can set up processes with SCHED_FIFO or SCHED_RR policies
> on the stock kernel, but it's not the same thing as the PREEMPT_RT kernel.
Honestly it is, the difference with PREEMT_RT is that the scheduller is
more aggressive, which probably explains why things settle down into a
steady state faster after the barrier.
--
Cyril Hrubis
chrubis@suse.cz
--
Mailing list info: https://lists.linux.it/listinfo/ltp
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2025-09-04 10:07 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-09-04 6:41 [LTP] [PATCH] sched_football: synchronize with kickoff flag to reduce skew Li Wang via ltp
2025-09-04 7:20 ` Andrea Cervesato via ltp
2025-09-04 9:48 ` Petr Vorel
2025-09-04 9:54 ` Cyril Hrubis
2025-09-04 10:04 ` Li Wang via ltp
2025-09-04 10:08 ` Cyril Hrubis
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox