Re: [RFC PATCH 2/3] sched/fair: Sync se with root cfs_rq

2016-06-06 Thread Vincent Guittot
Hi Dietmar, On 1 June 2016 at 21:39, Dietmar Eggemann wrote: > Since task utilization is accrued only on the root cfs_rq, there are a > couple of places where the se has to be synced with the root cfs_rq: > > (1) The root cfs_rq has to be updated in attach_entity_load_avg() for > an se repres

Re: [RFC PATCH 2/3] sched/fair: Sync se with root cfs_rq

2016-06-06 Thread Dietmar Eggemann
On 06/06/16 03:59, Leo Yan wrote: > On Wed, Jun 01, 2016 at 08:39:21PM +0100, Dietmar Eggemann wrote: [...] >> @@ -2995,8 +2997,16 @@ static void attach_entity_load_avg(struct cfs_rq >> *cfs_rq, struct sched_entity *s >> if (!entity_is_task(se)) >> return; >> >> -rq_of(

Re: [RFC PATCH 2/3] sched/fair: Sync se with root cfs_rq

2016-06-05 Thread Leo Yan
On Wed, Jun 01, 2016 at 08:39:21PM +0100, Dietmar Eggemann wrote: > Since task utilization is accrued only on the root cfs_rq, there are a > couple of places where the se has to be synced with the root cfs_rq: > > (1) The root cfs_rq has to be updated in attach_entity_load_avg() for > an se re

[RFC PATCH 2/3] sched/fair: Sync se with root cfs_rq

2016-06-01 Thread Dietmar Eggemann
Since task utilization is accrued only on the root cfs_rq, there are a couple of places where the se has to be synced with the root cfs_rq: (1) The root cfs_rq has to be updated in attach_entity_load_avg() for an se representing a task in a tg other than the root tg before the se utilizati