Re: [patch] sched: prevent bound kthreads from changing cpus_allowed

[Max Krasnyansky <maxk@qualcomm.com>]

Oleg Nesterov wrote:
> On 06/10, Max Krasnyansky wrote:
>> Peter Zijlstra wrote:
>>> Per cpu workqueues should stay on their cpu.
>>>
>>> What you're really looking for is a more fine grained alternative to
>>> flush_workqueue().
>> Actually I had a discussion on that with Oleg Nesterov. If you remember my
>> original solution (ie centralized cpu_isolate_map) was to completely redirect
>> work onto other cpus. Then you pointed out that it's the flush_() that really
>> makes the box stuck. So I started thinking about redoing the flush. While
>> looking at the code I realized that if I only change the flush_() then queued
>> work can get stale so to speak. ie Machine does not get stuck but some work
>> submitted on the isolated cpus will sit there for a long time. Oleg pointed
>> out exact same thing. So the simplest solution that does not require any
>> surgery to the workqueue is to just move the threads to other cpus.
> 
> Cough... I'd like to mention that I _personally agree with Peter, cwq->thread's
> should stay on their cpu.
I never argued against the _should stay_ ;-). What I'm arguing against is the
_must stay_ which is a big difference. I'll start a separate thread on this.

> I just meant that from the workqueue.c pov it is (afaics) OK to move cwq->thread
> to other CPUs, in a sense that this shouldn't add races or hotplug problems, etc.
Yep. That's what I was referring to in the explanation that I send to Peter.

> But still this doesn't look right to me.
Yeah, it's all about perceptions. We'll fix that ;-).

Max