Re: [PATCH 10/19] sched/fair: Prioritize tasks preferring destination LLC during balancing

[Peter Zijlstra]

On Sat, Oct 11, 2025 at 11:24:47AM -0700, Tim Chen wrote:
> During LLC load balancing, first check for tasks that prefer the
> destination LLC and balance them to it before others.
> 
> Mark source sched groups containing tasks preferring non local LLCs
> with the group_llc_balance flag. This ensures the load balancer later
> pulls or pushes these tasks toward their preferred LLCs.
> 
> Co-developed-by: Chen Yu <yu.c.chen@xxxxxxxxx>
> Signed-off-by: Chen Yu <yu.c.chen@xxxxxxxxx>
> Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
> ---

For me this patch is cut too fine; it only sets group_llc_balance but
then we don't see how it is used.

>  kernel/sched/fair.c | 43 +++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 41 insertions(+), 2 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index cbd1e97bca4b..af7b578eaa06 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -9822,8 +9822,7 @@ static __maybe_unused enum llc_mig can_migrate_llc_task(int src_cpu, int dst_cpu
>  	else
>  		return mig_unrestricted;
>  
> -	return can_migrate_llc(src_cpu, dst_cpu,
> -			       task_util(p), to_pref);
> +	return can_migrate_llc(src_cpu, dst_cpu, task_util(p), to_pref);
>  }
>  
>  #else
> @@ -10394,6 +10393,7 @@ struct sg_lb_stats {
>  	enum group_type group_type;
>  	unsigned int group_asym_packing;	/* Tasks should be moved to preferred CPU */
>  	unsigned int group_smt_balance;		/* Task on busy SMT be moved */
> +	unsigned int group_llc_balance;		/* Tasks should be moved to preferred LLC */
>  	unsigned long group_misfit_task_load;	/* A CPU has a task too big for its capacity */
>  #ifdef CONFIG_NUMA_BALANCING
>  	unsigned int nr_numa_running;
> @@ -10849,11 +10849,45 @@ static void record_sg_llc_stats(struct lb_env *env,
>  	if (unlikely(READ_ONCE(sd_share->capacity) != sgs->group_capacity))
>  		WRITE_ONCE(sd_share->capacity, sgs->group_capacity);
>  }
> +
> +/*
> + * Do LLC balance on sched group that contains LLC, and have tasks preferring
> + * to run on LLC in idle dst_cpu.
> + */
> +static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs,
> +			       struct sched_group *group)
> +{
> +	struct sched_domain *child = env->sd->child;
> +	int llc;
> +
> +	if (!sched_cache_enabled())
> +		return false;
> +
> +	if (env->sd->flags & SD_SHARE_LLC)
> +		return false;
> +
> +	/* only care about task migration among LLCs */
> +	if (child && !(child->flags & SD_SHARE_LLC))
> +		return false;
> +
> +	llc = llc_idx(env->dst_cpu);
> +	if (sgs->nr_pref_llc[llc] > 0 &&

Nit: s/> 0// would be the same, right?

> +	    can_migrate_llc(env->src_cpu, env->dst_cpu, 0, true) == mig_llc)
> +		return true;
> +
> +	return false;
> +}
>  #else
>  static inline void record_sg_llc_stats(struct lb_env *env, struct sg_lb_stats *sgs,
>  				       struct sched_group *group)
>  {
>  }
> +
> +static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs,
> +			       struct sched_group *group)
> +{
> +	return false;
> +}
>  #endif
>  
>  /**
> @@ -10954,6 +10988,11 @@ static inline void update_sg_lb_stats(struct lb_env *env,
>  	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
>  
>  	record_sg_llc_stats(env, sgs, group);
> +
> +	/* Check for tasks in this group can be moved to their preferred LLC */
> +	if (!local_group && llc_balance(env, sgs, group))
> +		sgs->group_llc_balance = 1;

We now have 3 (or so) branches that start with:

	if (!local_group &&

perhaps collate that some?

> +
>  	/* Computing avg_load makes sense only when group is overloaded */
>  	if (sgs->group_type == group_overloaded)
>  		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
> -- 
> 2.32.0
>