Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
1
fork

Configure Feed

Select the types of activity you want to include in your feed.

sched/core: Tweak wait_task_inactive() to force dequeue sched_delayed tasks

It was reported that in 6.12, smpboot_create_threads() was
taking much longer then in 6.6.

I narrowed down the call path to:
smpboot_create_threads()
-> kthread_create_on_cpu()
-> kthread_bind()
-> __kthread_bind_mask()
->wait_task_inactive()

Where in wait_task_inactive() we were regularly hitting the
queued case, which sets a 1 tick timeout, which when called
multiple times in a row, accumulates quickly into a long
delay.

I noticed disabling the DELAY_DEQUEUE sched feature recovered
the performance, and it seems the newly create tasks are usually
sched_delayed and left on the runqueue.

So in wait_task_inactive() when we see the task
p->se.sched_delayed, manually dequeue the sched_delayed task
with DEQUEUE_DELAYED, so we don't have to constantly wait a
tick.

Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue")
Reported-by: peter-yc.chang@mediatek.com
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20250429150736.3778580-1-jstultz@google.com

authored by

John Stultz and committed by
Peter Zijlstra
b7ca5743 c70fc32f

+6
+6
kernel/sched/core.c
··· 2283 2283 * just go back and repeat. 2284 2284 */ 2285 2285 rq = task_rq_lock(p, &rf); 2286 + /* 2287 + * If task is sched_delayed, force dequeue it, to avoid always 2288 + * hitting the tick timeout in the queued case 2289 + */ 2290 + if (p->se.sched_delayed) 2291 + dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); 2286 2292 trace_sched_wait_task(p); 2287 2293 running = task_on_cpu(rq, p); 2288 2294 queued = task_on_rq_queued(p);