Re: [PATCH] x86,sched: Fix sched_smt_power_savings totally broken

From: Vincent Guittot
Date: Mon Jan 09 2012 - 09:29:44 EST


Hi Peter,

I'm also using sched_mc level for doing powersaving load balance on
ARM platform and we have real benefits.

On 9 January 2012 12:12, Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> wrote:
> On Mon, 2012-01-09 at 19:14 -0500, Youquan Song wrote:
>> > Yes it is.. also that knob should die! Like i've been saying for way too
>> > long. I'm >< close to committing a patch removing all the power_saving
>> > magic from the scheduler.
>> Sorry. I do not notice it.
>
> I hadn't posted it before, but just about every time people post
> something related to smt/mc power balancing I say this needs to get
> cleaned up. Since telling people doesn't seem to have any effect what so
> ever, stronger measures are needed.
>
>> But currently in many real tests, the knob prove to save power in semi-idle system.
>> They are useful in many user scenarios currently.
>
> I'm not saying the stuff is without merit, I'm just saying that a) the
> interface is utter crap and b) nobody seems to spend enough time on it
> to 1) understand the load-balancer so that 2) he can integrate the power
> saving stuff properly.
>
> Instead I get one sporadic band-aid after another.
>

I can also help to on the topic

> Also, fundamentally, the split between {smt/mc/numa/book}_power_savings
> is completely and fundamentally broken, nobody cares about the actual
> topology.

We might modify the way we choose between power or performance mode
because it's not always a matter of gathering or spreading tasks on
cpus but until we found a best interface it's the way to enable
powersaving mode

> --
> 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/
--
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/