Messages in this thread | | | Subject | Re: [PATCH] sched/fair: Optimize select_idle_cpu | From | Valentin Schneider <> | Date | Fri, 13 Dec 2019 12:20:03 +0000 |
| |
On 13/12/2019 12:09, Peter Zijlstra wrote: >> Like you said the gains here would probably be small - the highest SMT >> count I'm aware of is SMT8 (POWER9). Still, if we end up with both >> select_idle_core() and select_idle_cpu() using that pattern, it would make >> sense IMO to align select_idle_smt() with those. > > The cpumask_and() operation added would also have cost. I really don't > see that paying off. > > The other sites have the problem that we combine an iteration limit with > affinity constraints. This loop doesn't do that and therefore doesn't > suffer the problem. >
select_idle_core() doesn't really have an iteration limit, right? That being said, yeah, the cpumask_and() for e.g. SMT2 systems would be mostly wasteful.
| |