On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index ea74d43924b2..b71557be6b42 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4885,6 +4885,8 @@ static enum hrtimer_restart
> sched_cfs_slack_timer(struct hrtimer *timer)
> return HRTIMER_NORESTART;
> }
>
> +extern const u64 max_cfs_quota_period;
> +
> static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
> {
> struct cfs_bandwidth *cfs_b =
> @@ -4892,6 +4894,7 @@ static enum hrtimer_restart
> sched_cfs_period_timer(struct hrtimer *timer)
> unsigned long flags;
> int overrun;
> int idle = 0;
> + int count = 0;
>
> raw_spin_lock_irqsave(&cfs_b->lock, flags);
> for (;;) {
> @@ -4899,6 +4902,28 @@ static enum hrtimer_restart
> sched_cfs_period_timer(struct hrtimer *timer)
> if (!overrun)
> break;
>
> + if (++count > 3) {
> + u64 new, old = ktime_to_ns(cfs_b->period);
> +
> + new = (old * 147) / 128; /* ~115% */
> + new = min(new, max_cfs_quota_period);
Also, we can still engineer things to come unstuck; if we explicitly
configure period at 1e9 and then set a really small quota and then
create this insane amount of cgroups you have..
this code has no room to manouvre left.
Do we want to do anything about that? Or leave it as is, don't do that
then?
> +
> + cfs_b->period = ns_to_ktime(new);
> +
> + /* since max is 1s, this is limited to 1e9^2, which
> fits in u64 */
> + cfs_b->quota *= new;
> + cfs_b->quota /= old;
> +
> + pr_warn_ratelimited(
> + "cfs_period_timer[cpu%d]: period too short, scaling up (new
> cfs_period_us %lld, cfs_quota_us = %lld)\n",
> + smp_processor_id(),
> + new/NSEC_PER_USEC,
> + cfs_b->quota/NSEC_PER_USEC);
> +
> + /* reset count so we don't come right back in here */
> + count = 0;
> + }
> +
> idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
> }
> if (idle)
