Re: [BENCHMARK] 2.5.48-mm1 with contest

[Andrew Morton]

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.