Re: [PATCH v3 06/10] sched/fair: Use the prefer_sibling flag of the current sched domain

[Ricardo Neri]

On Fri, Feb 10, 2023 at 05:12:30PM +0000, Valentin Schneider wrote:
> On 10/02/23 17:53, Peter Zijlstra wrote:
> > On Fri, Feb 10, 2023 at 02:54:56PM +0000, Valentin Schneider wrote:
> >
> >> So something like have SD_PREFER_SIBLING affect the SD it's on (and not
> >> its parent), but remove it from the lowest non-degenerated topology level?
> >
> > So I was rather confused about the whole moving it between levels things
> > this morning -- conceptually, prefer siblings says you want to try
> > sibling domains before filling up your current domain. Now, balancing
> > between siblings happens one level up, hence looking at child->flags
> > makes perfect sense.
> >
> > But looking at the current domain and still calling it prefer sibling
> > makes absolutely no sense what so ever.
> >
> 
> True :-)
> 
> > In that confusion I think I also got the polarity wrong, I thought you
> > wanted to kill prefer_sibling for the assymetric SMT cases, instead you
> > want to force enable it as long as there is one SMT child around.

Exactly.

> >
> > Whichever way around it we do it, I'm thinking perhaps some renaming
> > might be in order to clarify things.
> >
> > How about adding a flag SD_SPREAD_TASKS, which is the effective toggle
> > of the behaviour, but have it be set by children with SD_PREFER_SIBLING
> > or something.
> >
> 
> Or entirely bin SD_PREFER_SIBLING and stick with SD_SPREAD_TASKS, but yeah
> something along those lines.

I sense a consesus towards SD_SPREAD_TASKS.

> 
> > OTOH, there's also
> >
> >   if (busiest->group_weight == 1 || sds->prefer_sibling) {
> >
> > which explicitly also takes the group-of-one (the !child case) into
> > account, but that's not consistently done.
> >
> >       sds->prefer_sibling = !child || child->flags & SD_PREFER_SIBLING;

This would need a special provision for SD_ASYM_CPUCAPACITY.

> >
> > seems an interesting option,
> 
> > except perhaps ASYM_CPUCAPACITY -- I
> > forget, can CPUs of different capacity be in the same leaf domain? With
> > big.LITTLE I think not, they had their own cache domains and so you get
> > at least MC domains per capacity, but DynamiQ might have totally wrecked
> > that party.
> 
> Yeah, newer systems can have different capacities in one MC domain, cf:
> 
>   b7a331615d25 ("sched/fair: Add asymmetric CPU capacity wakeup scan")
> 
> >
> >> (+ add it to the first NUMA level to keep things as they are, even if TBF I
> >> find relying on it for NUMA balancing a bit odd).
> >
> > Arguably it ought to perhaps be one of those node_reclaim_distance
> > things. The thing is that NUMA-1 is often fairly quick, esp. these days
> > where it's basically on die numa.

To conserve the current behavior the NUMA level would need to have
SD_SPREAD_TASKS. It will be cleared along with SD_BALANCE_{EXEC, FORK} and
SD_WAKE_AFFINE if the numa distance is larger than node_reclaim_distance,
yes?

Thanks and BR,
Ricardo