Re: [PATCH v2 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning

[Libo Chen <libo.chen@oracle.com>]

forgot to add Steven Rostedt.

On 3/26/25 17:23, Libo Chen wrote:
> Unlike sched_skip_vma_numa tracepoint which tracks skipped VMAs, this
> tracks the task subjected to cpuset.mems pinning and prints out its
> allowed memory node mask.
> ---
>  include/trace/events/sched.h | 31 +++++++++++++++++++++++++++++++
>  kernel/sched/fair.c          |  4 +++-
>  2 files changed, 34 insertions(+), 1 deletion(-)
> 
> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
> index bfd97cce40a1a..133d9a671734a 100644
> --- a/include/trace/events/sched.h
> +++ b/include/trace/events/sched.h
> @@ -745,6 +745,37 @@ TRACE_EVENT(sched_skip_vma_numa,
>  		  __entry->vm_end,
>  		  __print_symbolic(__entry->reason, NUMAB_SKIP_REASON))
>  );
> +
> +TRACE_EVENT(sched_skip_cpuset_numa,
> +
> +	TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr),
> +
> +	TP_ARGS(tsk, mem_allowed_ptr),
> +
> +	TP_STRUCT__entry(
> +		__array( char,		comm,		TASK_COMM_LEN		)
> +		__field( pid_t,		pid					)
> +		__field( pid_t,		tgid					)
> +		__field( pid_t,		ngid					)
> +		__array( unsigned long, mem_allowed, BITS_TO_LONGS(MAX_NUMNODES))
> +	),
> +
> +	TP_fast_assign(
> +		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
> +		__entry->pid		 = task_pid_nr(tsk);
> +		__entry->tgid		 = task_tgid_nr(tsk);
> +		__entry->ngid		 = task_numa_group_id(tsk);
> +		memcpy(__entry->mem_allowed, mem_allowed_ptr->bits,
> +		       sizeof(__entry->mem_allowed));
> +	),
> +
> +	TP_printk("comm=%s pid=%d tgid=%d ngid=%d mem_node_allowed_mask=%lx",


I cannot find a way to print out nodemask_t nicely here with %*pbl.
So I fall back to just raw hex value. Will be grateful if someone
knows a better way to print nodemask nicely in a tracepoint  


> +		  __entry->comm,
> +		  __entry->pid,
> +		  __entry->tgid,
> +		  __entry->ngid,
> +		  __entry->mem_allowed[0])
> +);
>  #endif /* CONFIG_NUMA_BALANCING */
>  
>  /*
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 6f405e00c9c7e..a98842a96eda0 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -3333,8 +3333,10 @@ static void task_numa_work(struct callback_head *work)
>  	 * Memory is pinned to only one NUMA node via cpuset.mems, naturally
>  	 * no page can be migrated.
>  	 */
> -	if (nodes_weight(cpuset_current_mems_allowed) == 1)
> +	if (nodes_weight(cpuset_current_mems_allowed) == 1) {
> +		trace_sched_skip_cpuset_numa(current, &cpuset_current_mems_allowed);
>  		return;
> +	}
>  
>  	if (!mm->numa_next_scan) {
>  		mm->numa_next_scan = now +