Re: [RFC][PATCH 00/14] sched/fair: A bit of a cgroup/PELT overhaul (again)..

[Peter Zijlstra]

On Tue, May 16, 2017 at 06:02:17PM -0400, Tejun Heo wrote:
> Hello,
> 
> On Fri, May 12, 2017 at 06:44:16PM +0200, Peter Zijlstra wrote:
> > 
> > Hi all,
> > 
> > So after staring at all that PELT stuff and working my way through it again:
> > 
> >   https://lkml.kernel.org/r/20170505154117.6zldxuki2fgyo53n@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
> > 
> > I started doing some patches to fix some of the identified broken.
> > 
> > So here are a few too many patches that do:
> > 
> >  - fix 'reweight_entity' to instantly propagate the change in se->load.weight.
> > 
> >  - rewrite/fix the propagate on migrate (attach/detach)
> > 
> >  - introduce the hierarchical runnable_load_avg, as proposed by Tejun.
> > 
> >  - synchronous detach for runnable migrates
> > 
> >  - aligns the PELT windows between a cfs_rq and all its se's
> > 
> >  - deals with random fallout from the above (some of this needs folding back
> >    and reordering, but its all well past the point I should post this anyway).
> 
> The schbench results look good here.  I'll put it under more realistic
> test tomorrow and see how it performs.

Josef reported some problems with these patches and narrowed it down to:

  "sched/fair: Remove se->load.weight from se->avg.load_sum"

I'm currently stuck chasing a regression in other code, but I'll try and
get back to this shortly.