Re: [PATCH] sched/fair: Prevent cfs_rq from being unthrottled with zero runtime_remaining

[K Prateek Nayak]

Hello Aaron,

On 9/30/2025 1:26 PM, Aaron Lu wrote:
> On Mon, Sep 29, 2025 at 03:04:03PM +0530, K Prateek Nayak wrote:
> ... ...
>> Can we instead do a check_enqueue_throttle() in enqueue_throttled_task()
>> if we find cfs_rq->throttled_limbo_list to be empty?
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 18a30ae35441..fd2d4dad9c27 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -5872,6 +5872,8 @@ static bool enqueue_throttled_task(struct task_struct *p)
>>  	 */
>>  	if (throttled_hierarchy(cfs_rq) &&
>>  	    !task_current_donor(rq_of(cfs_rq), p)) {
>                 /*
>                  * Make sure to throttle this cfs_rq or it can be unthrottled
>                  * with no runtime_remaining and gets throttled again on its
>                  * unthrottle path.
>                  */
>> +		if (list_empty(&cfs_rq->throttled_limbo_list))
>> +			check_enqueue_throttle(cfs_rq);
> 
> BTW, do you think a comment is needed? Something like the above, not
> sure if it's too redundant though, feel free to let me know your
> thoughts, thanks.

Now that I'm looking at it again, I think we should actually do a:

    for_each_entity(se)
        check_enqueue_throttle(cfs_rq_of(se));

The reason being, we can have:

    root -> A (throttled) -> B -> C

Consider B has runtime_remaining = 0, and subsequently a throttled task
is queued onto C. Ideally, we should start the B/W timer for B at that
point but we bail out after queuing it on C. Thoughts?

Since we only catch up to the 0 runtime_remaining point, it should be
fine.

The comment can perhaps be something like:

	/*
	 * If this is the first enqueue on throttled hierarchy,
	 * ensure bandwidth is available when the hierarchy is
	 * unthrottled. check_enqueue_throttle() will ensure
	 * either some bandwidth is available, or will throttle
	 * the cfs_rq and queue the bandwidth timer.
	 */

> 
>>  		list_add(&p->throttle_node, &cfs_rq->throttled_limbo_list);
>>  		return true;
>>  	}
>> ---

-- 
Thanks and Regards,
Prateek