Re: idle priority

Rik van Riel (H.H.vanRiel@phys.uu.nl)
Tue, 11 Aug 1998 17:35:20 +0200 (CEST)

On Tue, 11 Aug 1998, MOLNAR Ingo wrote:
> On Mon, 10 Aug 1998, Rik van Riel wrote:
>
> > - we want to change schedule_idle() to immediately replace a
> > SCHED_IDLE process when something else is runnable
>
> (this was done this way in the original version of schedule_idle(). Also
> it is not by accident that the current version is #if 0-ed out)

That version only took into account the idle tasks, and not
processes running at SCHED_IDLE...

> > - we want _long_ timeslices to maximize speed and to minimize
> > impact on cache/memory/etc. (say 1 minute)
>
> doing a full cacheflush takes some ~2 millisecs on most x86 boxes. ie the
> default 200 msecs timeslice is OK. Also even though they are SCHED_IDLE,
> it does not mean rc5 clients want to time out on network connections
> just because they happen to have a 1 minute timeslice each ...

I hadn't considered this... OTOH, it might be desirable for
large simulations to have 'slices' of 15 minutes so that only
one of these will be in memory at once (when memory pressure
is high).

Rik.
+-------------------------------------------------------------------+
| Linux memory management tour guide. H.H.vanRiel@phys.uu.nl |
| Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ |
+-------------------------------------------------------------------+

-
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.altern.org/andrebalsa/doc/lkml-faq.html