Re: [PATCHv2 3/7] sched/fair: Consider misfit tasks when load-balancing

[Peter Zijlstra]

On Thu, Mar 15, 2018 at 02:47:00PM +0000, Morten Rasmussen wrote:
> +	/*
> +	 * Don't try to pull misfit tasks we can't help.
> +	 */
> +	if (sgs->group_type == group_misfit_task &&
> +	    (!group_smaller_cpu_capacity(sg, sds->local) ||
> +	     !group_has_capacity(env, &sds->local_stat)))
> +		return false;
> +

I think that has the same 'problem' as last time, right? Since
group_smaller_cpu_capacity() is affected by RT/IRQ pressure.

We should have a comment stating this and preferably explaining why that
is ok.