Re: sched/fair: which tasks should nr_pref_llc_running be compared against?

[Chen Yu]

On Tue, Sep 01, 2026 at 01:42:58PM -0700, Tim Chen wrote:
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 8dff37059faf..84c068f1deec 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1549,7 +1549,13 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
>  
>  	pref_llc_queued = (pref_llc == task_llc(p));
>  	rq->nr_llc_running++;
> -	rq->nr_pref_llc_running += pref_llc_queued;

Since the logic in
account_llc_enqueue()/account_llc_dequeue()/
account_llc_delayed()/account_llc_requeue_delayed() are very
similar, can we introduce one helper for them:
static void account_llc_pref_running(struct rq *rq, struct task_struct *p, int delta)
{
       if (p->pref_llc_queued && !p->se.sched_delayed)
               rq->nr_pref_llc_running += delta;
}

> +	/*
> +	 * If the task is being migrated while delay dequeued, keep it out
> +	 * of the runnable-domain nr_pref_llc_running; clear_delayed() ->
> +	 * account_llc_requeue_delayed() re-adds it when it wakes.
> +	 */
> +	if (!p->se.sched_delayed)
> +		rq->nr_pref_llc_running += pref_llc_queued;
>

put after p->pref_llc_queued = pref_llc_queued;
account_llc_pref_running(rq, p, 1)

>  	/*
>  	 * Record whether p is enqueued on its preferred
> @@ -1583,7 +1589,14 @@ static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
>  
>  	rq->nr_llc_running--;
>  	if (p->pref_llc_queued) {
> -		rq->nr_pref_llc_running--;
> +		/*
> +		 * If the task is being finally dequeued while still delayed,
> +		 * set_delayed() already removed it from nr_pref_llc_running;
> +		 * skip here to avoid underflow. Clearing pref_llc_queued also
> +		 * stops the subsequent clear_delayed() from re-adding it.
> +		 */
> +		if (!p->se.sched_delayed)
> +			rq->nr_pref_llc_running--;

account_llc_pref_running(rq, p, -1)

> +static void account_llc_delayed(struct rq *rq, struct task_struct *p)
> +{
> +	if (p->pref_llc_queued)
> +		rq->nr_pref_llc_running--;
> +}
> +
> +/* A delay-dequeued task becoming runnable again rejoins the count. */
> +static void account_llc_requeue_delayed(struct rq *rq, struct task_struct *p)
> +{
> +	if (p->pref_llc_queued)
> +		rq->nr_pref_llc_running++;
> +}
> +

Do not need above anymore.

>  
> +static void account_llc_delayed(struct rq *rq, struct task_struct *p) {}
> +
> +static void account_llc_requeue_delayed(struct rq *rq, struct task_struct *p) {}
> +
>  #endif /* CONFIG_SCHED_CACHE */
>  
>  /*
> @@ -6392,6 +6427,13 @@ static void set_delayed(struct sched_entity *se)
>  	if (!entity_is_task(se))
>  		return;
>  
> +	/*
> +	 * A delayed task is queued but no longer runnable. Drop it from
> +	 * nr_pref_llc_running so that counter keeps runnable semantics and
> +	 * stays comparable with h_nr_runnable in alb_break_llc().
> +	 */
> +	account_llc_delayed(rq_of(cfs_rq_of(se)), task_of(se));
> +

Added before the se->sched_delayed is set:
account_llc_pref_running(rq_of(cfs_rq_of(se)), task_of(se), -1);
se->sched_delayed = 1;

>  	for_each_sched_entity(se) {
>  		struct cfs_rq *cfs_rq = cfs_rq_of(se);
>  
> @@ -6412,6 +6454,13 @@ static void clear_delayed(struct sched_entity *se)
>  	if (!entity_is_task(se))
>  		return;
>  
> +	/*
> +	 * Re-add on wake (requeue_delayed_entity). On the final delayed
> +	 * dequeue, account_llc_dequeue() has already cleared pref_llc_queued,
> +	 * so this correctly does nothing.
> +	 */
> +	account_llc_requeue_delayed(rq_of(cfs_rq_of(se)), task_of(se));
> +

account_llc_pref_running(rq_of(cfs_rq_of(se)), task_of(se), 1);

thanks,
Chenyu
>  	for_each_sched_entity(se) {
>  		struct cfs_rq *cfs_rq = cfs_rq_of(se);
>  
> -- 
> 2.32.0
> 
> 
>