Messages in this thread | | | From | Valentin Schneider <> | Subject | Re: [PATCH] sched/fair: improve spreading of utilization | Date | Fri, 13 Mar 2020 16:57:54 +0000 |
| |
On Fri, Mar 13 2020, Vincent Guittot wrote:
>> Good point on the capacity reduction vs group_is_overloaded. >> >> That said, can't we also reach this with migrate_task? Say the local > > The test has only been added for migrate_util so migrate_task is not impacted > >> group is entirely idle, and the busiest group has a few non-idle CPUs >> but they all have at most 1 running task. AFAICT we would still go to >> calculate_imbalance(), and try to balance out the number of idle CPUs. > > such case is handled by migrate_task when we try to even the number of > tasks between groups > >> >> If the migration_type is migrate_util, that can't happen because of this >> change. Since we have this progressive balancing strategy (tasks -> util >> -> load), it's a bit odd to have this "gap" in the middle where we get >> one less possibility to trigger active balance, don't you think? That >> is, providing I didn't say nonsense again :) > > Right now, I can't think of a use case that could trigger such > situation because we use migrate_util when source is overloaded which > means that there is at least one waiting task and we favor this task > in priority >
Right, what I was trying to say is that AIUI migration_type == migrate_task with <= 1 running task per CPU in the busiest group can *currently* lead to a balance attempt, and thus a potential active balance.
Consider a local group of 4 idle CPUs, and a busiest group of 3 busy 1 idle CPUs, each busy having only 1 running task. That busiest group would be group_has_spare, so we would compute an imbalance of (4-1) / 2 == 1 task to move. We'll proceed with the load balance, but we'll only move things if we go through an active_balance.
My point is that if we prevent this for migrate_util, it would make sense to prevent it for migrate_task, but it's not straightforward since we have things like ASYM_PACKING.
>> >> It's not a super big deal, but I think it's nice if we can maintain a >> consistent / gradual migration policy. >> >> >> >> >> > might be hard to notice in benchmarks.
| |