public inbox for [email protected]
 help / color / mirror / Atom feed
* [PATCH] io_uring/sqpoll: Do not set PF_NO_SETAFFINITY on sqpoll threads
@ 2023-03-14 18:33 Michal Koutný
  2023-03-15 12:51 ` Jens Axboe
  0 siblings, 1 reply; 2+ messages in thread
From: Michal Koutný @ 2023-03-14 18:33 UTC (permalink / raw)
  To: io-uring
  Cc: linux-kernel, cgroups, Jens Axboe, Pavel Begunkov, Daniel Dao,
	Waiman Long

Users may specify a CPU where the sqpoll thread would run. This may
conflict with cpuset operations because of strict PF_NO_SETAFFINITY
requirement. That flag is unnecessary for polling "kernel" threads, see
the reasoning in commit 01e68ce08a30 ("io_uring/io-wq: stop setting
PF_NO_SETAFFINITY on io-wq workers"). Drop the flag on poll threads too.

Fixes: 01e68ce08a30 ("io_uring/io-wq: stop setting PF_NO_SETAFFINITY on io-wq workers")
Link: https://lore.kernel.org/all/20230314162559.pnyxdllzgw7jozgx@blackpad/
Signed-off-by: Michal Koutný <[email protected]>
---
 io_uring/sqpoll.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 0119d3f1a556..9db4bc1f521a 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -233,7 +233,6 @@ static int io_sq_thread(void *data)
 		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
 	else
 		set_cpus_allowed_ptr(current, cpu_online_mask);
-	current->flags |= PF_NO_SETAFFINITY;
 
 	mutex_lock(&sqd->lock);
 	while (1) {
-- 
2.39.2


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH] io_uring/sqpoll: Do not set PF_NO_SETAFFINITY on sqpoll threads
  2023-03-14 18:33 [PATCH] io_uring/sqpoll: Do not set PF_NO_SETAFFINITY on sqpoll threads Michal Koutný
@ 2023-03-15 12:51 ` Jens Axboe
  0 siblings, 0 replies; 2+ messages in thread
From: Jens Axboe @ 2023-03-15 12:51 UTC (permalink / raw)
  To: io-uring, Michal Koutný
  Cc: linux-kernel, cgroups, Pavel Begunkov, Daniel Dao, Waiman Long


On Tue, 14 Mar 2023 19:33:32 +0100, Michal Koutný wrote:
> Users may specify a CPU where the sqpoll thread would run. This may
> conflict with cpuset operations because of strict PF_NO_SETAFFINITY
> requirement. That flag is unnecessary for polling "kernel" threads, see
> the reasoning in commit 01e68ce08a30 ("io_uring/io-wq: stop setting
> PF_NO_SETAFFINITY on io-wq workers"). Drop the flag on poll threads too.
> 
> 
> [...]

Applied, thanks!

[1/1] io_uring/sqpoll: Do not set PF_NO_SETAFFINITY on sqpoll threads
      commit: a5fc1441af7719e93dc7a638a960befb694ade89

Best regards,
-- 
Jens Axboe




^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2023-03-15 12:51 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2023-03-14 18:33 [PATCH] io_uring/sqpoll: Do not set PF_NO_SETAFFINITY on sqpoll threads Michal Koutný
2023-03-15 12:51 ` Jens Axboe

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox