Messages in this thread |  | | | Date | Mon, 28 Sep 1998 07:35:48 +0200 (CEST) | | From | "Michael L. Galbraith" <> | | Subject | Re: [PATCH] scheduler patch, faster still |
| |
On Sun, 27 Sep 1998 yodaiken@chelm.cs.nmt.edu wrote:
> > Do you have a result with an instrumented schedule()? If not, why not? >
Hi,
These are from a fully instrumented kernel. (and with Rik's patch)
%TotTime TotUsecs AvgUsecs Calls Switch from/to pid x2 2.4275% 20671.09 2.07 10001 c0112223 schedule p234s235 2.5050% 21331.38 2.13 9999 c0112223 schedule p235s234 x10 0.1530% 2373.03 6.52 364 c0112223 schedule p268s265 0.1956% 3033.78 8.31 365 c0112223 schedule p265s268 0.3469% 5381.37 6.05 889 c0112223 schedule p269s265 0.4172% 6471.55 7.28 889 c0112223 schedule p265s269 1.9078% 29596.57 6.69 4423 c0112223 schedule p267s265 2.0161% 31276.17 7.07 4423 c0112223 schedule p265s267 2.7864% 43225.69 6.65 6502 c0112223 schedule p266s265 2.8915% 44856.39 6.90 6501 c0112223 schedule p265s266 7.8522% 121812.09 12.20 9988 c0112223 schedule p275s264 7.9070% 122662.42 12.28 9989 c0112223 schedule p264s275
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
|  |