Re: Measured overhead of timer interrupts

Artur Skawina (skawina@geocities.com)
Sat, 24 Jul 1999 14:20:28 +0200

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Paul Barton-Davis: "Re: real-time threaded IO with low latency (audio)"
Previous message: Rik van Riel: "Re: low priority soft RT?"

> > Hmm, I raytraced an image running three kernels differing only
> > in HZ value (+the HZ masquerading stuff). This is what i got:

> Those results look a bit strange: when increasing HZ 8 times, you get

I didn't fix the scaling before running the first HZ=1024 test.
After fixing the problem the numbers are:

100: 8.65user 0.00system 0:08.65elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
1024: 8.66user 0.01system 0:08.72elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k

So the HZ change from 100 to 1024 means only a ~0.8% slowdown for the
raytracer - looks much better now. All stability problems have magically
disappeared after upgrading to 2.3.12pre1 ;)

-
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/

Next message: Paul Barton-Davis: "Re: real-time threaded IO with low latency (audio)"
Previous message: Rik van Riel: "Re: low priority soft RT?"