Re: [performance bug] volanomark regression on 37-rc1

[Nikhil Rao]

On Tue, Nov 16, 2010 at 9:32 AM, Mike Galbraith <efault@xxxxxx> wrote:
> On Tue, 2010-11-16 at 08:31 -0800, Nikhil Rao wrote:
>> On Tue, Nov 16, 2010 at 7:26 AM, Mike Galbraith <efault@xxxxxx> wrote:
>> > On Tue, 2010-11-16 at 20:38 +0600, Rakib Mullick wrote:
>> >
>> >> Does VolanoMark is used for scheduler benchmarking? If I'm not wrong,
>> >> I don't think it directly relates to scheduler benchmarking.
>> >
>> > It's not generally considered to be a wonderful benchmark, but it is a
>> > good indicator, and worth keeping an eye on IMHO.
>> >
>> > I don't recall whether that patch works with the idle testcase without
>> > resetting the throttle, or if it's only a bit less effective. ÂIf it's
>> > only a little less effective, I'd be inclined to just whack the reset as
>> > Alex did. ÂWhatever is done has to prevent high frequency balancing.
>> >
>>
>> >From what I recall, I think removing the reset makes the original
>> patch a little less effective. I agree that we can remove the reset if
>> it hurts high frequency balancing.
>
> Ok, let's do that. ÂI added your ack, OK?
>

Yes, thanks for the patch.

> From: Alex Shi <alex.shi@xxxxxxxxx>
> Date: Tue, 16 Nov 2010 17:34:02 +0800
>
> Â Âsched: volanomark regression fix
>
> Â ÂCommit fab4762 triggers excessive idle balancing, causing a ~30% loss in
> Â Âvolanomark throughput. ÂRemove idle balancing throttle reset.
>
> Â ÂSigned-off-by: Mike Galbraith <efault@xxxxxx>
> Â ÂAcked-by: Nikhil Rao <ncrao@xxxxxxxxxx>
> Â ÂReported-by: Alex Shi <alex.shi@xxxxxxxxx>
> Â ÂCc: Ingo Molnar <mingo@xxxxxxx>
> Â ÂCc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> Â ÂLKML-Reference: <new-submission>
>
> ---
> Âkernel/sched_fair.c | Â Â4 ----
> Â1 file changed, 4 deletions(-)
>
> Index: linux-2.6/kernel/sched_fair.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched_fair.c
> +++ linux-2.6/kernel/sched_fair.c
> @@ -1758,10 +1758,6 @@ static void pull_task(struct rq *src_rq,
> Â Â Â Âset_task_cpu(p, this_cpu);
> Â Â Â Âactivate_task(this_rq, p, 0);
> Â Â Â Âcheck_preempt_curr(this_rq, p, 0);
> -
> - Â Â Â /* re-arm NEWIDLE balancing when moving tasks */
> - Â Â Â src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
> - Â Â Â this_rq->idle_stamp = 0;
> Â}
>
> Â/*
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/