Re: [PATCH v2 05/23] sched/cache: Assign preferred LLC ID to processes

[Vern Hao]

On 2025/12/4 07:07, Tim Chen wrote:
> With cache-aware scheduling enabled, each task is assigned a
> preferred LLC ID. This allows quick identification of the LLC domain
> where the task prefers to run, similar to numa_preferred_nid in
> NUMA balancing.
>
> Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
> ---
>
> Notes:
>      v1->v2: Align preferred LLC with NUMA balancing's preferred node.
>
>   include/linux/sched.h |  1 +
>   init/init_task.c      |  3 +++
>   kernel/sched/fair.c   | 18 ++++++++++++++++++
>   3 files changed, 22 insertions(+)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 278b529c91df..1ad46220cd04 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1408,6 +1408,7 @@ struct task_struct {
>   
>   #ifdef CONFIG_SCHED_CACHE
>   	struct callback_head		cache_work;
> +	int				preferred_llc;
>   #endif
>   
>   #ifdef CONFIG_RSEQ
> diff --git a/init/init_task.c b/init/init_task.c
> index a55e2189206f..44bae72b5b7d 100644
> --- a/init/init_task.c
> +++ b/init/init_task.c
> @@ -191,6 +191,9 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
>   	.numa_group	= NULL,
>   	.numa_faults	= NULL,
>   #endif
> +#ifdef CONFIG_SCHED_CACHE
> +	.preferred_llc  = -1,
> +#endif
>   #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
>   	.kasan_depth	= 1,
>   #endif
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 0a3918269906..10cec83f65d5 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1300,6 +1300,7 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
>   	struct mm_struct *mm = p->mm;
>   	struct mm_sched *pcpu_sched;
>   	unsigned long epoch;
> +	int mm_sched_llc = -1;
>   
>   	if (!sched_cache_enabled())
>   		return;
> @@ -1330,6 +1331,23 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
>   		if (mm->mm_sched_cpu != -1)
>   			mm->mm_sched_cpu = -1;
>   	}
> +
> +	if (mm->mm_sched_cpu != -1) {
> +		mm_sched_llc = llc_id(mm->mm_sched_cpu);
> +
> +#ifdef CONFIG_NUMA_BALANCING
> +		/*
> +		 * Don't assign preferred LLC if it
> +		 * conflicts with NUMA balancing.
> +		 */
> +		if (p->numa_preferred_nid >= 0 &&

I wonder if the restriction here shouldn't be so strict. In Mel Gorman's 
patch (e496132ebedd sched/fair: Adjust the allowed NUMA imbalance when 
SD_NUMA spans multiple LLCs), the value of the 'imb_numa_nr' is checked 
to determine if |SD_NUMA| imbalance is allowed. Could we use this same 
check to decide whether or not to perform a cross-numa migration?

> +		    cpu_to_node(mm->mm_sched_cpu) != p->numa_preferred_nid)
> +			mm_sched_llc = -1;
> +#endif
> +	}
> +
> +	if (p->preferred_llc != mm_sched_llc)
> +		p->preferred_llc = mm_sched_llc;
>   }
>   
>   static void task_tick_cache(struct rq *rq, struct task_struct *p)