Re: [BENCHMARK] scheduler tunables with contest - prio_bonus_ratio

From: Andrew Morton (akpm@digeo.com)
Date: Thu Dec 19 2002 - 19:02:34 EST


Robert Love wrote:
>
> On Thu, 2002-12-19 at 18:18, Andrew Morton wrote:
>
> > That is too often not the case.
>
> I knew you would say that!
>
> > I can get the desktop machine working about as comfortably
> > as 2.4.19 with:
> >
> > # echo 10 > max_timeslice
> > # echo 0 > prio_bonus_ratio
> >
> > ie: disabling all the fancy new scheduler features :(
> >
> > Dropping max_timeslice fixes the enormous stalls which happen
> > when an interactive process gets incorrectly identified as a
> > cpu hog. (OK, that's expected)
>
> Curious why you need to drop max_timeslice, too.

What Con said. When the scheduler makes an inappropriate decision,
shortening the timeslice minimises its impact.

> Did you do that _before_ changing the interactivity estimator?

I disabled the estimator first. The result was amazingly bad ;)

> Dropping max_timeslice
> closer to min_timeslice would do away with a lot of effect of the
> interactivity estimator, since bonuses and penalties would be less
> apparent.

Yup. One good test is to keep rebuilding a kernel all the time,
then just *use* the system. Setting max_timeslice=10, prio_bonus=10
works better still. prio_bonus=25 has small-but-odd lags.
 
> There would still be (a) the improved priority given to interactive
> processes and (b) the reinsertion into the active away done to
> interactive processes.
>
> Setting prio_bonus_ratio to zero would finish off (a) and (b). It would
> also accomplish the effect of setting max_timeslice low, without
> actually doing it.
>
> Thus, can you try putting max_timeslice back to 300? You would never
> actually use that range, mind you, except for niced/real-time
> processes. But at least then the default timeslice would be a saner
> 100ms.

prio_bonus=0, max_timeslice=300 is awful. Try it...
 
> ...
> But that in no way precludes not fixing what we have, because good
> algorithms should not require tuning for common cases. Period.

hm. Good luck ;)

This is a situation in which one is prepares to throw away some cycles
to achieve a desired effect.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Mon Dec 23 2002 - 22:00:25 EST