Re: [BENCHMARK] 2.5.74-mm1 with contest
jw schultz (jw@pegasys.ws)
Thu, 3 Jul 2003 18:08:08 -0700
On Fri, Jul 04, 2003 at 01:32:55AM +1000, Con Kolivas wrote:
> Here are contest benchmarks for 2.5.74-mm1 with my scheduler tweaks:
>
[snip]
>
> A little more here, a little less there. No major changes except for dbench
> load which appears to have significantly shorter compile times. As kernel
> compiles are not by their nature "interactive", these results are expected.
> It is nice to see that it doesn't appear to starve any load unecessarily as
> well.
>
> Contest can show the kernel's ability to perform in the setting of different
> loads without being choked, but will not show if your audio application will
> get to play when it wants to, nor whether your windows will move around the
> screen smoothly.
>
> Con
>
> P.S. Does anyone see the irony in the fact that my own benchmark won't show
> that my patch does anything?
I see no irony, and much value, in your benchmark showing
that your patch doesn't break server performance.
Perhaps a load that generated X events to move a window
around in an ellipse or polygon would show some effects of
your patch.
--
________________________________________________________________
J.W. Schultz Pegasystems Technologies
email address: jw@pegasys.ws
Remember Cernan and Schmitt
-
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/