| Subject | Re: [patch 12/16] sched: prevent interactions with throttled entities | From | Peter Zijlstra <> | Date | Thu, 23 Jun 2011 13:49:19 +0200 |
| |
On Tue, 2011-06-21 at 00:17 -0700, Paul Turner wrote: > @@ -2635,8 +2704,10 @@ static int update_shares_cpu(struct task > > raw_spin_lock_irqsave(&rq->lock, flags); > > - update_rq_clock(rq); > - update_cfs_load(cfs_rq, 1); > + if (!throttled_hierarchy(cfs_rq)) { > + update_rq_clock(rq); > + update_cfs_load(cfs_rq, 1); > + } > > /*
OK, so we can't contribute to load since we're throttled, but tg->load_weight might have changed meanwhile?
Also, update_cfs_shares()->reweight_entity() can dequeue/enqueue the entity, doesn't that require an up-to-date rq->clock?
|