Re: Measured overhead of timer interrupts

Artur Skawina (skawina@geocities.com)
Mon, 19 Jul 1999 23:52:53 +0200

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Donald Becker: "Re: Via-Rhine driver update breaks it on Alpha"
Previous message: Jeremy Fitzhardinge: "Re: [RFC] - Some notions that I would like comments on"
Maybe in reply to: Jamie Lokier: "Measured overhead of timer interrupts"

> > > what i would be interested in seeing is: the time it takes to
> > > run a cpu bound app (eg raytracing am image) with HZ=100 and HZ=1024.
> > > That would give a more realistic approximation of the overhead that
> > > increasing HZ adds.
> >
> > Then do the bench, nobody prevents you from doing so.

the point was more that the #s presented in this thread were not very
relevant.

> Should HZ=1024 be safe on x86?
>
> If it's not completely safe, what do I need to fix and submit patches for
> so that we can be HZ=1024 on x86 for 2.4? :)

i'd start by looking at eg

http://www.garloff.de/kurt/linux/222-400hz.diff

-
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: Donald Becker: "Re: Via-Rhine driver update breaks it on Alpha"
Previous message: Jeremy Fitzhardinge: "Re: [RFC] - Some notions that I would like comments on"
Maybe in reply to: Jamie Lokier: "Measured overhead of timer interrupts"