Re: [GIT PULL] adaptive spinning mutexes

From: Andrew Morton
Date: Wed Jan 14 2009 - 15:46:10 EST


On Wed, 14 Jan 2009 21:27:36 +0100
Ingo Molnar <mingo@xxxxxxx> wrote:

>
> * Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> wrote:
>
> > On Wed, 2009-01-14 at 11:36 -0800, Andrew Morton wrote:
> >
> > > Do people enable CONFIG_SCHED_DEBUG?
> >
> > Well, I have it always enabled, but I've honestly no idea if that makes
> > me weird.
> >
> > > CONFIG_DEBUG_MUTEXES=n, CONFIG_SCHED_DEBUG=y is getting to be a pretty
> > > small subset?
> >
> > Could be, do you fancy me doing a sysctl? shouldn't be hard.
>
> i dunno, why another fancy sysctl for something that fits quite nicely
> into the existing sched_features scheme that we've been using for such
> purposes for the past 3-4 kernel releases?
>
> we always provided various toggles for new scheduler features via
> /sys/debug/sched_features, so that people can do performance regression
> testing, and it works quite well.
>

If we know that this control will be reliably available in packaged
kernels then fine. But how to we arrange for that?
--
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/