[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20071116104557.GA5453@elte.hu>
Date: Fri, 16 Nov 2007 11:45:57 +0100
From: Ingo Molnar <mingo@...e.hu>
To: Micah Dowty <micah@...are.com>
Cc: Christoph Lameter <clameter@....com>,
Kyle Moffett <mrmacman_g4@....com>,
Cyrus Massoumi <cyrusm@....net>,
LKML Kernel <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...l.org>, Mike Galbraith <efault@....de>,
Paul Menage <menage@...gle.com>,
Dmitry Adamushko <dmitry.adamushko@...il.com>,
Peter Williams <pwil3058@...pond.net.au>
Subject: Re: High priority tasks break SMP balancer?
* Micah Dowty <micah@...are.com> wrote:
> On Fri, Nov 16, 2007 at 07:07:00AM +0100, Ingo Molnar wrote:
> > > My best guess is that this has something to do with the timing with
> > > which we sample the CPU's instantaneous load when calculating the load
> > > averages.. but I still understand only the basics of the scheduler and
> > > SMP balancer. All I really know for sure at this point regarding your
> > > patch is that git-bisect found it for me.
> >
> > hm, your code uses timeouts for this, right? The CPU load average that
> > is used for SMP load balancing is sampled from the scheduler tick - and
> > has been sampled from the scheduler tick for eons. v2.6.23 defaulted to
> > a different method but v2.6.24 samples it from the tick again. So my
> > guess is, your testcode behave similarly on 2.6.22 too, correct?
>
> My sample program (and the VMware code which I originally observed
> this behaviour with) wakes up frequently using /dev/rtc.
>
> I know the problem occurs on 2.6.20 and 2.6.23.1. I haven't tried
> 2.6.22 yet, but I'll do so as soon as I can.
ok, if you see it on .20 then no need to try .22.
Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists