Re: [git pull] scheduler changes for v2.6.26

[Frans Pop <elendil@planet.nl>]

On Monday 21 April 2008, you wrote:
> * Frans Pop <elendil@planet.nl> wrote:
> > Ingo Molnar wrote:
> > > Ingo Molnar (12):
> > >       sched: re-do "sched: fix fair sleepers"
> >
> > Has the regression [1] that was traced to this change been fixed now?
> >
> > The regression was confirmed to be also present in sched-devel.git at
> > the time of -rc8, so I'd expect it still to be valid unless of course
> > the cause was found since then.
>
> Peter reported a similar interactivity problem to be gone, so lets
> re-try this again - the change makes sense and if you see problems it's
> hiding something we really want to fix.

IIRC he mentioned seeing something himself during 2.6.25, but we'd already 
established that was unrelated to what I was seeing as his workaround 
(booting with nohz) did not work for me.

I can again reproduce the issue with sched-devel/latest :-(
latencytop regularly reports 500-700 msec latencies for amarokapp again 
while compiling glibc.

I expect that means it's also back in mainline?
What would be preferred for bugzilla: reopening the existing report (#10428) 
or opening a new one?

> It would be nice if you could 
> try sched-devel/latest because it has an improved ftrace "sched_switch"
> tracer where you can generate much longer traces of this incident. Try
> the new /debug/trace_entries runtime tunable.

I'll try to get the trace and will reply on the private thread we had.
I may need additional instructions though.

Cheers,
FJP