On Fri, Jan 08 2021 at 12:46, Peter Zijlstra wrote:
> On Sat, Dec 26, 2020 at 10:51:08AM +0800, Lai Jiangshan wrote:
>> From: Lai Jiangshan <[email protected]>
>>
>> 06249738a41a ("workqueue: Manually break affinity on hotplug")
>> said that scheduler will not force break affinity for us.
>
> So I've been looking at this the past day or so, and the more I look,
> the more I think commit:
>
> 1cf12e08bc4d ("sched/hotplug: Consolidate task migration on CPU unplug")
>
> is a real problem and we need to revert it (at least for now).
>
> Let me attempt a brain dump:
>
> - the assumption that per-cpu kernel threads are 'well behaved' on
> hot-plug has, I think, been proven incorrect, it's far worse than
> just bounded workqueue. Therefore, it makes sense to provide the old
> semantics.
I disagree. Per-cpu kernel threads which are magically stopped during
hotplug and then migrated to a random other CPU are just wrong.
We really need to fix that and not proliferate the sloppy and ill
defined behaviour.
Thanks,
tglx
