ppc32: Weird process scheduling behaviour with 2.6.24-rc

[Michel Dänzer]

On Fri, 2008-01-25 at 12:34 +0100, Michel Dänzer wrote:
> On Fri, 2008-01-25 at 17:54 +1100, Benjamin Herrenschmidt wrote:
> > On Wed, 2008-01-23 at 13:42 +0100, Peter Zijlstra wrote:
> > > Another question, do you have:
> > >   CONFIG_FAIR_GROUP_SCHED=y
> > > 
> > > if so, does flipping that off have any effect?
> > 
> > Yes.
> > 
> > Here, I do the test of running 4 times the repro-case provided by Michel
> > with nice 19 and a dd eating CPU with nice 0.
> > 
> > Without this option, I get the dd at 100% and the nice 19 shells down
> > below it with whatever is left of the CPUs.
> > 
> > With this option, dd gets about 50% of one CPU and the niced processes
> > still get most of the time.
> 
> Hmm, interesting. As I said before, I thought I had tested with this
> disabled and not seen a difference, but I'll try again to confirm.

So, 2.6.24 final is indeed much better with this disabled, but still not
as good as 2.6.23: While I can reliably move a window again while the
infinite loop is running, it still stutters badly every couple of
seconds. With 2.6.23 this is smooth all the time.


-- 
Earthling Michel Dänzer           |          http://tungstengraphics.com
Libre software enthusiast         |          Debian, X and DRI developer