FWIW, good to see progress, still waiting for you guys to agree :-)
On Mon, Jul 01, 2019 at 01:15:44PM -0700, [email protected] wrote: > - Taking up-to-every rq->lock is bad and expensive and 5ms may be too > short a delay for this. I haven't tried microbenchmarks on the cost of > this vs min_cfs_rq_runtime = 0 vs baseline. Yes, that's tricky, SGI/HPE have definite ideas about that. > @@ -4781,12 +4790,41 @@ static __always_inline void > return_cfs_rq_runtime(struct cfs_rq *cfs_rq) > */ > static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) > { > - u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); > + u64 runtime = 0; > unsigned long flags; > u64 expires; > + struct cfs_rq *cfs_rq, *temp; > + LIST_HEAD(temp_head); > + > + local_irq_save(flags); > + > + raw_spin_lock(&cfs_b->lock); > + cfs_b->slack_started = false; > + list_splice_init(&cfs_b->slack_cfs_rq, &temp_head); > + raw_spin_unlock(&cfs_b->lock); > + > + > + /* Gather all left over runtime from all rqs */ > + list_for_each_entry_safe(cfs_rq, temp, &temp_head, slack_list) { > + struct rq *rq = rq_of(cfs_rq); > + struct rq_flags rf; > + > + rq_lock(rq, &rf); > + > + raw_spin_lock(&cfs_b->lock); > + list_del_init(&cfs_rq->slack_list); > + if (!cfs_rq->nr_running && cfs_rq->runtime_remaining > 0 && > + cfs_rq->runtime_expires == cfs_b->runtime_expires) { > + cfs_b->runtime += cfs_rq->runtime_remaining; > + cfs_rq->runtime_remaining = 0; > + } > + raw_spin_unlock(&cfs_b->lock); > + > + rq_unlock(rq, &rf); > + } But worse still, you take possibly every rq->lock without ever re-enabling IRQs. > > /* confirm we're still not at a refresh boundary */ > - raw_spin_lock_irqsave(&cfs_b->lock, flags); > + raw_spin_lock(&cfs_b->lock); > cfs_b->slack_started = false; > if (cfs_b->distribute_running) { > raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
