On 2013/6/6 3:45, Tejun Heo wrote:
> Hello, Li.
>
> On Wed, Jun 05, 2013 at 05:16:24PM +0800, Li Zefan wrote:
>> @@ -1425,7 +1435,6 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
>> * Change mm, possibly for multiple threads in a threadgroup. This is
>> * expensive and may sleep.
>> */
>> - cpuset_attach_nodemask_to = cs->mems_allowed;
>> mm = get_task_mm(leader);
>> if (mm) {
>> mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
>
> This looks a bit suspicious to me. Now we're setting mm's nodemask to
> guarantee_online_mems() output rather than cs->mems_allowed. Is this
> change intended? If so, it probably deserves an explanation in the
> description?
>
It's possible that cs->mems_allowed is empty, but I should have left
it as it is, as it's not related to this patch.
_______________________________________________
Containers mailing list
Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/containers
