Re: Linux 2.6.0-test6

[Nick Piggin]

Rob Landley wrote:

> On Sunday 28 September 2003 02:03, Con Kolivas wrote:
>
> > On Sun, 28 Sep 2003 11:27, Linus Torvalds wrote:
> >
> > > from Andrew Morton. Most notably perhaps Con's scheduler changes that
> > > have been discussed extensively and made it into the -mm tree for
> > > testing.
> > For those who are trying this for the first time, please note that the
> > scheduler has been tuned to tell the difference between tasks of the _same_
> > nice level. This means do NOT renice X or it will make audio skip unless
> > you also renice your audio application by the same amount. Lots of
> > distributions have done this for the old 2.4 scheduler which could not
> > treat equal "nice" levels as differently as the new scheduler does and 2.6
> > shouldn't need special treatment.
> >
> > So for testing note the following points:
> >
> > Make sure X is NOT reniced to -10 as many distributions are doing.
> > Some shells spawn processes at nice +5 by default and this will make audio
> > apps suffer.
> > Make sure your hard disk, graphics card and audio card are performing at
> > equal standard to your 2.4 kernel (ie dma is working, graphics is fully
> > accelerated etc).
>
> I.E. with your new scheduler, priority levels actually have enough of an 
> effect now that things that aren't reniced can be noticeably starved by 
> things that are.

AFAIK, Con's scheduler doesn't change the nice implementation at all.
Possibly some of his changes amplify its problems, or, more likely they
remove most other scheduler problems leaving this one noticable.

If X is running at -20, and xmms at +19, xmms is supposed to still get
5% of the CPU. Should be enough to run fine. Unfortunately this is
achieved by giving X very large timeslices, so xmms's scheduling latency
becomes large. The interactivity bonuses don't help, either.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/