Re: [PATCH v5 08/12] sched: move cfs task on a CPU with higher capacity

On 11 September 2014 12:07, Peter Zijlstra peterz@infradead.org wrote:

On Tue, Aug 26, 2014 at 01:06:51PM +0200, Vincent Guittot wrote:

...

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 18db43e..60ae1ce 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6049,6 +6049,14 @@ static bool update_sd_pick_busiest(struct lb_env *env, return true; }

• /*
  

•  * The group capacity is reduced probably because of activity from other
  

•  * sched class or interrupts which use part of the available capacity
  

•  */
  

• if ((sg->sgc->capacity_orig * 100) > (sgs->group_capacity *
  

•                         env->sd->imbalance_pct))
  

•         return true;
  

• return false;
  

}

This is unlikely to have worked as intended. You will never reach this, except on PowerPC >= 7. All other machines will have bailed at the !ASYM_PACKING check above this.

Ah yes, i miss that change while rebasing on rik patches. My use case fall in this wider test now that we always select a busiest group