Re: [PATCH 1/7 v5] sched/fair: Filter false overloaded_group case for EAS

[K Prateek Nayak]

Hello Vincent,

On 3/3/2025 2:35 AM, Vincent Guittot wrote:
> With EAS, a group should be set overloaded if at least 1 CPU in the group
> is overutilized but it can happen that a CPU is fully utilized by tasks
> because of clamping the compute capacity of the CPU. In such case, the CPU
> is not overutilized and as a result should not be set overloaded as well.
>
> group_overloaded being a higher priority than group_misfit, such group can
> be selected as the busiest group instead of a group with a mistfit task
> and prevents load_balance to select the CPU with the misfit task to pull
> the latter on a fitting CPU.
>
> Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> Tested-by: Pierre Gondois <pierre.gondois@xxxxxxx>
> ---
>   kernel/sched/fair.c | 12 +++++++++++-
>   1 file changed, 11 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 857808da23d8..d3d1a2ba6b1a 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -9931,6 +9931,7 @@ struct sg_lb_stats {
>   	unsigned int group_asym_packing;	/* Tasks should be moved to preferred CPU */
>   	unsigned int group_smt_balance;		/* Task on busy SMT be moved */
>   	unsigned long group_misfit_task_load;	/* A CPU has a task too big for its capacity */
> +	unsigned int group_overutilized;	/* At least one CPU is overutilized in the group */
>   #ifdef CONFIG_NUMA_BALANCING
>   	unsigned int nr_numa_running;
>   	unsigned int nr_preferred_running;
> @@ -10163,6 +10164,13 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
>   static inline bool
>   group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
>   {
> +	/*
> +	 * With EAS and uclamp, 1 CPU in the group must be overutilized to
> +	 * consider the group overloaded.
> +	 */
> +	if (sched_energy_enabled() && !sgs->group_overutilized)
> +		return false;
> +
>   	if (sgs->sum_nr_running <= sgs->group_weight)
>   		return false;
>   
> @@ -10374,8 +10382,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
>   		nr_running = rq->nr_running;
>   		sgs->sum_nr_running += nr_running;
>   
> -		if (cpu_overutilized(i))
> +		if (cpu_overutilized(i)) {
>   			*sg_overutilized = 1;

Since sgs->overutilized is tracking the overutilized status, can we get
avoid passing the "sg_overutilized" pointer to update_sg_lb_stats() and
just use the sg->overutilized in update_sd_lb_stats()?

Something like below:

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 857808da23d8..de4a7e19d383 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10346,14 +10346,12 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd)
  * @group: sched_group whose statistics are to be updated.
  * @sgs: variable to hold the statistics for this group.
  * @sg_overloaded: sched_group is overloaded
- * @sg_overutilized: sched_group is overutilized
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
 				      struct sd_lb_stats *sds,
 				      struct sched_group *group,
 				      struct sg_lb_stats *sgs,
-				      bool *sg_overloaded,
-				      bool *sg_overutilized)
+				      bool *sg_overloaded)
 {
 	int i, nr_running, local_group, sd_flags = env->sd->flags;
 	bool balancing_at_rd = !env->sd->parent;
@@ -10375,7 +10373,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->sum_nr_running += nr_running;
 
 		if (cpu_overutilized(i))
-			*sg_overutilized = 1;
+			sgs->group_overutilized = 1;
 
 		/*
 		 * No need to call idle_cpu() if nr_running is not 0
@@ -11046,7 +11044,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 				update_group_capacity(env->sd, env->dst_cpu);
 		}
 
-		update_sg_lb_stats(env, sds, sg, sgs, &sg_overloaded, &sg_overutilized);
+		update_sg_lb_stats(env, sds, sg, sgs, &sg_overloaded);
 
 		if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
@@ -11056,6 +11054,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		/* Now, start updating sd_lb_stats */
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
+		sg_overutilized |= sgs->group_overutilized;
 
 		sum_util += sgs->group_util;
 		sg = sg->next;
--
Thanks and Regards,
Prateek

> +			sgs->group_overutilized = 1;
> +		}
>   
>   		/*
>   		 * No need to call idle_cpu() if nr_running is not 0