On Thu, 3 Mar 2016, Thomas Gleixner wrote:
> On Thu, 3 Mar 2016, Peter Zijlstra wrote:
> > > +++ b/kernel/sched/core.c
> > > @@ -5726,23 +5726,6 @@ static int sched_cpu_active(struct notif
> > > case CPU_STARTING:
> > > set_cpu_rq_start_time();
> >
> > If we stick that in notify_starting() we can kill all of this.
>
> Yep. I'm going to kill that one by one :)
After I'm done fixing the wreckage which is caused by moving set_active()
alone. The numa and cpuset muck rely on it ....
But now that we can delay random workload on the upcoming/outgoing cpu we can
move that stuff alltogether.
Thanks,
tglx
