Re: [PATCH] sched, fair: Allow a small degree of load imbalance between SD_NUMA domains v2

[Peter Zijlstra]

On Tue, Jan 07, 2020 at 11:42:11AM +0000, Mel Gorman wrote:
> On Tue, Jan 07, 2020 at 12:22:55PM +0100, Peter Zijlstra wrote:

> > > +		/* Consider allowing a small imbalance between NUMA groups */
> > > +		if (env->sd->flags & SD_NUMA) {
> > > +			struct sched_domain *child = env->sd->child;
> > 
> > This assumes sd-child exists, which should be true for NUMA domains I
> > suppose.
> > 
> 
> I would be stunned if it was not. What sort of NUMA domain would not have
> child domains? Does a memory-only NUMA node with no CPUs even generate
> a scheduler domain? If it does, then I guess the check is necessary.

I think it's fine, it was just my paranoia triggering. At the very least
we'll have the single CPU domain there.