On 21 June 2016 at 14:47, Peter Zijlstra <pet...@infradead.org> wrote: > On Tue, Jun 21, 2016 at 02:36:46PM +0200, Vincent Guittot wrote: >> On 21 June 2016 at 13:43, Peter Zijlstra <pet...@infradead.org> wrote: >> > On Mon, Jun 20, 2016 at 11:23:39AM +0200, Vincent Guittot wrote: >> > >> >> Don't we have to do a complete attach with attach_task_cfs_rq instead >> >> of just the load_avg ? to set also depth ? >> > >> > Hmm, yes, your sched_set_group() change seems to have munged this. >> > >> >> I think that it was done by the attach_task_cfs_rq during the activate_task. >> Now, the attach is done in post_init_entity_util_avg. Can't we just >> set the depth in post_init_entity_util_avg ? > > Yes, I actually had that patch for a little while. > > But since its cgroup specific, I felt it should be in the cgroup code, > hence the current patch.
that's a fair point
