Messages in this thread | | | Date | Thu, 25 Feb 2010 09:18:14 +0800 | From | Miao Xie <> | Subject | Re: [regression] cpuset,mm: update tasks' mems_allowed in time (58568d2) |
| |
on 2010-2-25 5:08, David Rientjes wrote: > On Wed, 24 Feb 2010, Miao Xie wrote: > >> I think it is not a big deal because it is safe and doesn't cause any problem. >> Beside that, task->cpus_allowed is initialized to cpu_possible_mask on the no-cpuset >> kernel, so using cpu_possible_mask to initialize task->cpus_allowed is reasonable. >> (top cpuset is a special cpuset, isn't it?) >> > > I'm suprised that I can create a descendant cpuset of top_cpuset that > cannot include all of its parents' cpus and that the root cpuset's cpus > mask doesn't change when cpus are onlined/offlined. >
top cpuset's cpus is consistent with cpu_online_mask because the kernel changes it when doing cpu hotplug. So the problem which you said doesn't exist.
Just cpus_allowed of all tasks in the top cpuset is initialized to cpu_possible_mask in order to avoid updating them when doing cpu hotplug.
| |