[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <4FBE288F.8060802@linux.vnet.ibm.com>
Date: Thu, 24 May 2012 17:54:47 +0530
From: "Srivatsa S. Bhat" <srivatsa.bhat@...ux.vnet.ibm.com>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>
CC: mingo@...nel.org, pjt@...gle.com, paul@...lmenage.org,
akpm@...ux-foundation.org, rjw@...k.pl, nacc@...ibm.com,
rientjes@...gle.com, paulmck@...ux.vnet.ibm.com,
tglx@...utronix.de, seto.hidetoshi@...fujitsu.com, tj@...nel.org,
mschmidt@...hat.com, berrange@...hat.com,
nikunj@...ux.vnet.ibm.com, vatsa@...ux.vnet.ibm.com,
liuj97@...il.com, linux-kernel@...r.kernel.org,
linux-pm@...r.kernel.org
Subject: Re: [PATCH v5 4/5] cpusets: Update tasks' cpus_allowed mask upon
updates to root cpuset
On 05/24/2012 05:28 PM, Peter Zijlstra wrote:
> On Thu, 2012-05-24 at 15:14 +0530, Srivatsa S. Bhat wrote:
>
>> Sorry, my bad, I hadn't considered that. Thanks for pointing it out!
>>
>> So, I am wondering how we ought to deal with CPU hotplug for tasks attached
>> to the root cpuset..
>
> By not doing anything at all. If a task is in the root set it is
> supposed to behave as it cpusets don't exist.
>
>> Considering tasks attached to the root cpuset, if a cpu present in a task's
>> cpus_allowed mask goes offline, it should be removed from that mask right?
>
> Nope, that shouldn't happen. We only reset the mask if all cpus in the
> affinity mask go away. This is where task affinity and cpusets differ.
>
>> And if that cpu comes back online, it should not be put back to the task's
>> cpus_allowed mask (just like we don't put back cpus in non-root cpusets).
>
> Online shouldn't ever change anything.
>
>> Is the above understanding correct?
>
> Nope.
>
>> In the current kernel, during cpu hotplug, we don't touch cpus_allowed mask
>> of the tasks attached to the root cpuset at all.. Whereas we update the
>> cpus_allowed mask of tasks belonging to non-root cpusets, during cpu offline.
>>
>> So, is this differentiation intended?
>
> Yes, although arguably the cpuset case is 'weird' in that it came later
> and didn't mirror the cpu affinity semantics.
>
> Tasks aren't attached to the root cpuset, they live there because
> there's no other place to be when you don't use cpusets. This very much
> means that tasks in the root set should behave as if cpusets didn't
> exist.
>
Ok, got it.. that logic makes sense. Thanks a lot for the explanation!
I will resubmit this patchset without patch 4/5 then, if you don't have any
other objections.
Regards,
Srivatsa S. Bhat
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists