Re: IOAPIC and 8254

From: Richard B. Johnson (root@chaos.analogic.com)
Date: Wed Mar 08 2000 - 21:48:00 EST


On Wed, 8 Mar 2000, Horst von Brand wrote:

> David Woodhouse <dwmw2@infradead.org> said:
>
> [...]
>
> > Alternatively we could just stop exporting timing information to userland in
> > units of HZ.
>
> I vote for this. Userland has no business with HZ; and you could very well
> envision a ssytem where HZ changes (OS sees high CPU bound load ==> HZ goes
> up; load gets more interactive ==> HZ goes down; CPU speeding up/down
> (Crusoe)) or even has no real global meaning anymore ("HZ" depends on the
> specific use)
> --
> Horst von Brand vonbrand@sleipnir.valparaiso.cl
> Casilla 9G, Viņa del Mar, Chile +56 32 672616

Doesn't POSIX require something to relate to 'clock()' ? I looked at
time.h and timebits.h and, for the 'C' headers I have, it seems to be
implied. Or is clock() not required?

Cheers,
Dick Johnson

Penguin : Linux version 2.3.41 on an i686 machine (800.63 BogoMips).

-
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/



This archive was generated by hypermail 2b29 : Wed Mar 15 2000 - 21:00:15 EST