2011-04-23 13:39:42

by Hillf Danton

Subject: [PATCH] sched: try to rewrite tg_has_rt_tasks()

It is reshuffled not based upon scanning the list of existing threads
but upon the relevant info carried by the input task group. Compared
with the original, it is simpler, and nothing important is missed.

Signed-off-by: Hillf Danton <[email protected]>
---

--- a/kernel/sched.c 2011-03-30 03:09:48.000000000 +0800
+++ b/kernel/sched.c 2011-04-23 21:48:14.000000000 +0800
@@ -8756,13 +8756,11 @@ static unsigned long to_ratio(u64 period
/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
- struct task_struct *g, *p;
-
- do_each_thread(g, p) {
- if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+ int cpu;
+ for_each_online_cpu(cpu) {
+ if (tg->rt_rq[cpu]->rt_nr_running != 0)
return 1;
- } while_each_thread(g, p);
-
+ }
return 0;
}

2011-04-23 14:11:33

by Yong Zhang

Subject: Re: [PATCH] sched: try to rewrite tg_has_rt_tasks()

On Sat, Apr 23, 2011 at 09:39:40PM +0800, Hillf Danton wrote:
> It is reshuffled not based upon scanning the list of existing threads
> but upon the relevant info carried by the input task group. Compared
> with the original, it is simpler, and nothing important is missed.

Oh, no.

There may be sleep task which is attach this group.

Thanks,
Yong

>
> Signed-off-by: Hillf Danton <[email protected]>
> ---
>
> --- a/kernel/sched.c 2011-03-30 03:09:48.000000000 +0800
> +++ b/kernel/sched.c 2011-04-23 21:48:14.000000000 +0800
> @@ -8756,13 +8756,11 @@ static unsigned long to_ratio(u64 period
> /* Must be called with tasklist_lock held */
> static inline int tg_has_rt_tasks(struct task_group *tg)
> {
> - struct task_struct *g, *p;
> -
> - do_each_thread(g, p) {
> - if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
> + int cpu;
> + for_each_online_cpu(cpu) {
> + if (tg->rt_rq[cpu]->rt_nr_running != 0)
> return 1;
> - } while_each_thread(g, p);
> -
> + }
> return 0;
> }
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/

2011-04-23 14:19:21

by Hillf Danton

Subject: Re: [PATCH] sched: try to rewrite tg_has_rt_tasks()

On Sat, Apr 23, 2011 at 10:11 PM, Yong Zhang <[email protected]> wrote:
> On Sat, Apr 23, 2011 at 09:39:40PM +0800, Hillf Danton wrote:
>> It is reshuffled not based upon scanning the list of existing threads
>> but upon the relevant info carried by the input task group. Compared
>> with the original, it is simpler, and nothing important is missed.
>
> Oh, no.
>
> There may be sleep task which is attach this group.
>

Would you please say a few more words about the "sleep task"?

Thanks
Hillf

2011-04-23 14:31:44

by Yong Zhang

Subject: Re: [PATCH] sched: try to rewrite tg_has_rt_tasks()

On Sat, Apr 23, 2011 at 10:19:19PM +0800, Hillf Danton wrote:
> On Sat, Apr 23, 2011 at 10:11 PM, Yong Zhang <[email protected]> wrote:
> > On Sat, Apr 23, 2011 at 09:39:40PM +0800, Hillf Danton wrote:
> >> It is reshuffled not based upon scanning the list of existing threads
> >> but upon the relevant info carried by the input task group. Compared
> >> with the original, it is simpler, and nothing important is missed.
> >
> > Oh, no.
> >
> > There may be sleep task which is attach this group.
> >
>
> Would you please say a few more words about the "sleep task"?

Only RUNNING task is counted to rt_nr_running, SLEEP task
is not on the run queue.

Thanks,
Yong