Re: Scheduler(?) regression from 2.6.22 to 2.6.24 for short-livedthreads

[Olof Johansson]

On Sat, Feb 09, 2008 at 01:08:30AM +0100, Ingo Molnar wrote:
> 
> * Olof Johansson <olof@xxxxxxxxx> wrote:
> 
> > 2.6.22: 3332 ms
> > 2.6.23: 4397 ms
> > 2.6.24: 8953 ms
> > 2.6.24-git19: 8986 ms
> 
> if you enable SCHED_DEBUG, and subtract 4 from the value of 
> /proc/sys/kernel/sched_features, does it get any better?
> 
> if not, does writing 0 into /proc/sys/kernel/sched_features have any 
> impact?

Doesn't seem to make a difference, either of them. I can unfortunately
not retest on x86 at the moment, only powerpc. But it made no noticable
difference in runtime w/ pasemi_defconfig and current mainline.


-Olof
--
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/