Re: [RFC] sched: unused cpu in affine workload

[Jiri Olsa]

On Mon, Apr 04, 2016 at 11:34:50PM +0200, Peter Zijlstra wrote:
> On Mon, Apr 04, 2016 at 03:45:16PM -0400, Rik van Riel wrote:
> > An optimal solution is NP hard.
> > 
> > Heuristics that "move tasks with pressure" may be
> > much more doable, and lead to perfectly satisfactory
> > results, especially if most migrations happen within
> > a socket (and the same shared L3 cache).
> 
> Right; trick will be finding something that mostly works without making
> the regular balance paths increase in complexity.
> 
> As per the argument in kernel/sched/fair.c:5694 the current
> load-balancing averages out to O(n), and I would very much like to keep
> it that way.

guys, thanks a lot for all the thoughts and suggestions,
I'll try to come up with something

jirka