public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [patch] BFS 421: remove global runqueue lock in running tick
@ 2012-06-08 13:37 Hillf Danton
  2012-06-08 13:45 ` Chen
  0 siblings, 1 reply; 3+ messages in thread
From: Hillf Danton @ 2012-06-08 13:37 UTC (permalink / raw)
  To: LKML, Hillf Danton

We simply deschedule current, with no bother grabbing global lock, since IPI,
if triggered by preempt, could not change our result, like no schedule when
preempt enabled.

	preempt_enable_no_resched();
	if (unlikely(need_resched()))
		goto need_resched;


--- a/kernel/sched/bfs.c	Wed Jun  6 21:02:50 2012
+++ b/kernel/sched/bfs.c	Fri Jun  8 21:17:24 2012
@@ -2784,11 +2784,13 @@ static void task_running_tick(struct rq
 	} else if (rq->rq_time_slice >= RESCHED_US)
 			return;

-	/* p->time_slice < RESCHED_US. We only modify task_struct under grq lock */
+	/*
+	 * With irq disabled, current is descheduled without global lock
+	 * held and IPI cared.
+	 */
 	p = rq->curr;
-	grq_lock();
-	set_tsk_need_resched(p);
-	grq_unlock();
+	if (!test_tsk_need_resched(p))
+		set_tsk_need_resched(p);
 }


--

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [patch] BFS 421: remove global runqueue lock in running tick
  2012-06-08 13:37 [patch] BFS 421: remove global runqueue lock in running tick Hillf Danton
@ 2012-06-08 13:45 ` Chen
  2012-06-08 16:47   ` Heinz Diehl
  0 siblings, 1 reply; 3+ messages in thread
From: Chen @ 2012-06-08 13:45 UTC (permalink / raw)
  Cc: linux-kernel

Still, you haven't produced any usable patch. LOL

On Fri, Jun 8, 2012 at 9:37 PM, Hillf Danton <dhillf@gmail.com> wrote:
> We simply deschedule current, with no bother grabbing global lock, since IPI,
> if triggered by preempt, could not change our result, like no schedule when
> preempt enabled.
>
>        preempt_enable_no_resched();
>        if (unlikely(need_resched()))
>                goto need_resched;
>
>
> --- a/kernel/sched/bfs.c        Wed Jun  6 21:02:50 2012
> +++ b/kernel/sched/bfs.c        Fri Jun  8 21:17:24 2012
> @@ -2784,11 +2784,13 @@ static void task_running_tick(struct rq
>        } else if (rq->rq_time_slice >= RESCHED_US)
>                        return;
>
> -       /* p->time_slice < RESCHED_US. We only modify task_struct under grq lock */
> +       /*
> +        * With irq disabled, current is descheduled without global lock
> +        * held and IPI cared.
> +        */
>        p = rq->curr;
> -       grq_lock();
> -       set_tsk_need_resched(p);
> -       grq_unlock();
> +       if (!test_tsk_need_resched(p))
> +               set_tsk_need_resched(p);
>  }
>
>
> --
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [patch] BFS 421: remove global runqueue lock in running tick
  2012-06-08 13:45 ` Chen
@ 2012-06-08 16:47   ` Heinz Diehl
  0 siblings, 0 replies; 3+ messages in thread
From: Heinz Diehl @ 2012-06-08 16:47 UTC (permalink / raw)
  To: linux-kernel

On 08.06.2012, Chen wrote: 

> Still, you haven't produced any usable patch. LOL

...and Con Kolivas released BFS 4.22 some days ago..


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2012-06-08 16:47 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-06-08 13:37 [patch] BFS 421: remove global runqueue lock in running tick Hillf Danton
2012-06-08 13:45 ` Chen
2012-06-08 16:47   ` Heinz Diehl

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