On Wed, Jun 12, 2019 at 09:02:44AM -0700, Tejun Heo wrote: > On Wed, Jun 12, 2019 at 11:50:48AM -0400, Joel Savitz wrote: > > In the case that a process is constrained by taskset(1) (i.e. > > sched_setaffinity(2)) to a subset of available cpus, and all of those are > > subsequently offlined, the scheduler will set tsk->cpus_allowed to > > the current value of task_cs(tsk)->effective_cpus. > > > > This is done via a call to do_set_cpus_allowed() in the context of > > cpuset_cpus_allowed_fallback() made by the scheduler when this case is > > detected. This is the only call made to cpuset_cpus_allowed_fallback() > > in the latest mainline kernel. > > > > However, this is not sane behavior. > > While not perfect (we'll need to stop updating task's cpumask from > cpuset to make), this is still a signifcant improvement. > > Acked-by: Tejun Heo <tj@xxxxxxxxxx> > > If there's no objection, I'll route it through the cgroup tree. Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
