Re: [BENCHMARK] 2.5.74-mm1 with contest

[jw schultz <jw@pegasys.ws>]

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