Re: [patch] voluntary-preempt-2.6.9-rc1-bk4-R0

[Ingo Molnar <mingo@elte.hu>]

* Lee Revell <rlrevell@joe-job.com> wrote:

> > vanilla kernel 2.6.8.1 would be quite interesting to get a few charts of
> > - especially if your measurement methodology has changed.
> 
> OK, I will give this a shot.  Now that the VP patches are stabilizing
> I will be doing more profiling.  I also want to try the -mm kernel,
> this has some interesting differences from the stock kernel.  For
> example I measured about a 10% improvement with the old method, which
> implies a big performance gain.

the -mm kernel used to have additional *-latency-fix patches that were
done based on the initial preemption-timing patch in -mm and partly
based on early VP discussions and findings. I recently reviewed and
merged the 2-3 missing ones into VP. Andrew has dropped these patches
meanwhile and i expect to submit the cleaner and more complete solution
that is in VP.

So i'd expect -mm to still perform better than vanilla (it usually
does), but if that big 10% difference in latencies doesnt show up
anymore i'd attribute it to the shuffling around of latency related
patches, not some genuine deficiency in -mm.

	Ingo