* Valentin Schneider <vschneid@xxxxxxxxxx> wrote: > > sched/deadline.c has something very similar, does that need updating > > too? > > Hm I think so yes: > - push_dl_task() is an obvious noop if the pushable tree is empty > - pull_dl_task() can be kicked if !rq->dl.overloaded, which similarly to rt > is driven by nr_migratory but could be boiled down to having pushable > tasks (due to the nr_cpus_allowed > 1 constraint). > > Lemme poke at it. For reference, the matching DL change now lives in tip:sched/core as: 177f608a4c82 ("sched/deadline: Make dl_rq->pushable_dl_tasks update drive dl_rq->overloaded") Thanks, Ingo