Re: [RFC] Orthogonal Interactivity Patches

[Con Kolivas]

Addendum

On Mon, 25 Aug 2003 13:22, Con Kolivas wrote:
> default scheduler. The remaining issue is that application startup will be
> slower than the vanilla scheduler (your mileage may vary) under load, but I
> feel not unacceptably so as a tradeoff. 

I'm experimenting with a kind of central tendency with tasks that have not yet 
declared themselves high or low credit by weighting down the cpu run time 
when their credit is neither high nor low. Hopefully this can speed up 
application startup under load without too much general slowdown by current 
cpu hogs.

Con

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/