Re: [RFC PATCH 2/4] sched/fair: Make tg->load_avg per node

[Yury Norov]

On Wed, Jul 19, 2023 at 01:53:58PM +0200, Peter Zijlstra wrote:
> On Tue, Jul 18, 2023 at 09:41:18PM +0800, Aaron Lu wrote:
> > +#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
> > +static inline long tg_load_avg(struct task_group *tg)
> > +{
> > +	long load_avg = 0;
> > +	int i;
> > +
> > +	/*
> > +	 * The only path that can give us a root_task_group
> > +	 * here is from print_cfs_rq() thus unlikely.
> > +	 */
> > +	if (unlikely(tg == &root_task_group))
> > +		return 0;
> > +
> > +	for_each_node(i)
> > +		load_avg += atomic_long_read(&tg->node_info[i]->load_avg);
> > +
> > +	return load_avg;
> > +}
> > +#endif
> 
> So I was working on something else numa and noticed that for_each_node()
> (and most of the nodemask stuff) is quite moronic, afaict we should do
> something like the below.
> 
> I now see Mike added the nr_node_ids thing fairly recent, but given
> distros have NODES_SHIFT=10 and actual machines typically only have <=4
> nodes, this would save a factor of 256 scanning.
> 
> Specifically, your for_each_node() would scan the full 1024 bit bitmap
> looking for more bits that would never be there.
> 
> ---
> 
> diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
> index 8d07116caaf1..c23c0889b8cf 100644
> --- a/include/linux/nodemask.h
> +++ b/include/linux/nodemask.h
> @@ -109,7 +109,7 @@ extern nodemask_t _unused_nodemask_arg_;
>  				__nodemask_pr_bits(maskp)
>  static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
>  {
> -	return m ? MAX_NUMNODES : 0;
> +	return m ? nr_node_ids : 0;
>  }
>  static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
>  {
> @@ -137,13 +137,13 @@ static inline void __node_clear(int node, volatile nodemask_t *dstp)
>  	clear_bit(node, dstp->bits);
>  }
>  
> -#define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
> +#define nodes_setall(dst) __nodes_setall(&(dst), nr_node_ids)
>  static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
>  {
>  	bitmap_fill(dstp->bits, nbits);
>  }
>  
> -#define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
> +#define nodes_clear(dst) __nodes_clear(&(dst), nr_node_ids)
>  static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
>  {
>  	bitmap_zero(dstp->bits, nbits);
> @@ -160,7 +160,7 @@ static inline bool __node_test_and_set(int node, nodemask_t *addr)
>  }
>  
>  #define nodes_and(dst, src1, src2) \
> -			__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
> +			__nodes_and(&(dst), &(src1), &(src2), nr_node_ids)
>  static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {

This would break small_const_nbits() optimization for those configuring
their kernels properly. This is very similar to cpumasks and nr_cpu_ids
problem.

See 596ff4a09b8 ("cpumask: re-introduce constant-sized cpumask optimizations")

Thanks,
Yury