Messages in this thread | | | From | Valentin Schneider <> | Subject | Re: [PATCH v4 3/3] sched/fair: Introduce a CPU capacity comparison helper | Date | Tue, 06 Apr 2021 16:59:26 +0100 |
| |
On 06/04/21 17:37, Dietmar Eggemann wrote: > On 01/04/2021 21:30, Valentin Schneider wrote: >> While at it, replace group_smaller_{min, max}_cpu_capacity() with >> comparisons of the source group's min/max capacity and the destination >> CPU's capacity. > > IMHO, you haven't mentioned why you replace local sched group with dst > CPU. I can see that only the capacity of the dst CPU makes really sense > here. Might be worth mentioning in the patch header why. There is some > of it in v3 6/7 but that's a different change. >
Right, some of it got lost in the shuffling. This was a separate change in v1 (4/8). I can reuse that changelog into:
""" Also note that comparing capacity extrema of local and source sched_group's doesn't make much sense when at the day of the day the imbalance will be pulled by a known env->dst_cpu, whose capacity can be anywhere within the local group's capacity extrema.
While at it, replace group_smaller_{min, max}_cpu_capacity() with comparisons of the source group's min/max capacity and the destination CPU's capacity. """
> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> > > [...]
| |