On Thu, Nov 19, 2020 at 09:29:22AM +0000, Quentin Perret wrote: > On Friday 13 Nov 2020 at 09:37:14 (+0000), Will Deacon wrote: > > If the scheduler cannot find an allowed CPU for a task, > > cpuset_cpus_allowed_fallback() will widen the affinity to cpu_possible_mask > > if cgroup v1 is in use. > > > > In preparation for allowing architectures to provide their own fallback > > mask, just return early if we're not using cgroup v2 and allow > > select_fallback_rq() to figure out the mask by itself. > > > > Cc: Li Zefan <lizefan@xxxxxxxxxx> > > Cc: Tejun Heo <tj@xxxxxxxxxx> > > Cc: Johannes Weiner <hannes@xxxxxxxxxxx> > > Signed-off-by: Will Deacon <will@xxxxxxxxxx> > > That makes select_fallback_rq() slightly more expensive if you're using > cgroup v1, but I don't expect that be really measurable in real-world > workloads, so: > > Reviewed-by: Quentin Perret <qperret@xxxxxxxxxx> Cheers! Will
