On Mon, 2007-05-28 at 14:53 +0200, Tristan Gingold wrote:
> On Thu, May 10, 2007 at 02:15:34PM -0600, Alex Williamson wrote:
> > On Wed, 2007-05-09 at 06:10 +0200, Tristan Gingold wrote:
> > > Hi,
> > >
> > > a stripped-down version of a previous patch: reimplement
> vcpu_get_psr.
> > >
> > > Should be a noop, I don't think performance should be affected.
> >
> > Unfortunately...
> >
> > with patch:
> >
> > real 6m0.483s
> > user 21m10.680s
> > sys 1m18.470s
> >
> > without patch:
> >
> > real 4m47.767s
> > user 16m55.060s
> > sys 0m53.240s
>
> Hi,
>
> I can now reproduce this slow-down.
>
> However I don't understand your figures: how can real time be less than user
> time ? Isn't real time the elapsed time ?
Parallel build, -j4. The real time is the elapsed time, user is
cumulative across all 4 CPUs. Thanks,
Alex
--
Alex Williamson HP Open Source & Linux Org.
_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel
|