Re: [BENCHMARK] 2.5.48-mm1 with contest

From: Andrew Morton (akpm@digeo.com)
Date: Tue Nov 19 2002 - 16:53:43 EST


Robert Love wrote:
>
> On Tue, 2002-11-19 at 16:28, Con Kolivas wrote:
>
> > xtar_load:
> > Kernel [runs] Time CPU% Loads LCPU% Ratio
> > 2.5.48 [5] 184.4 41 2 6 2.52
> > 2.5.48-mm1 [5] 210.7 35 2 6 2.88
> >
> > read_load:
> > Kernel [runs] Time CPU% Loads LCPU% Ratio
> > 2.5.48 [5] 102.9 74 6 4 1.41
> > 2.5.48-mm1 [5] 256.7 29 11 2 3.51*
>
> What changed, Andrew?
>
> Wall time is up but CPU is down... spending more time on I/O?

Big changes in the IO scheduler. I have not really sat down
and looked at the effects of those changes - Jens keeps on
changing it, and I keep on diddling the queue sizes. So it
has only really been "stability tested" at this time.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sat Nov 23 2002 - 22:00:29 EST