Re: [PATCH v2 2/5] mm: Extends local cpu counter vm_diff_nodestat from s8 to s16

[Michal Hocko]

On Tue 19-12-17 14:39:23, Kemi Wang wrote:
> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> limitation of global counters update frequency, especially for those
> monotone increasing type of counters like NUMA counters with more and more
> cpus/nodes. This patch extends the type of vm_diff_nodestat from s8 to s16
> without any functionality change.
> 
>                                  before     after
> sizeof(struct per_cpu_nodestat)    28         68

So it is 40B * num_cpus * num_nodes. Nothing really catastrophic IMHO
but the changelog is a bit silent about any numbers. This is a
performance optimization so it should better give us some.
 
> Signed-off-by: Kemi Wang <kemi.wang@xxxxxxxxx>
> ---
>  include/linux/mmzone.h |  4 ++--
>  mm/vmstat.c            | 16 ++++++++--------
>  2 files changed, 10 insertions(+), 10 deletions(-)
> 
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index c06d880..2da6b6f 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -289,8 +289,8 @@ struct per_cpu_pageset {
>  };
>  
>  struct per_cpu_nodestat {
> -	s8 stat_threshold;
> -	s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
> +	s16 stat_threshold;
> +	s16 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
>  };
>  
>  #endif /* !__GENERATING_BOUNDS.H */
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 1dd12ae..9c681cc 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -332,7 +332,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
>  				long delta)
>  {
>  	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
> -	s8 __percpu *p = pcp->vm_node_stat_diff + item;
> +	s16 __percpu *p = pcp->vm_node_stat_diff + item;
>  	long x;
>  	long t;
>  
> @@ -390,13 +390,13 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
>  void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
>  {
>  	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
> -	s8 __percpu *p = pcp->vm_node_stat_diff + item;
> -	s8 v, t;
> +	s16 __percpu *p = pcp->vm_node_stat_diff + item;
> +	s16 v, t;
>  
>  	v = __this_cpu_inc_return(*p);
>  	t = __this_cpu_read(pcp->stat_threshold);
>  	if (unlikely(v > t)) {
> -		s8 overstep = t >> 1;
> +		s16 overstep = t >> 1;
>  
>  		node_page_state_add(v + overstep, pgdat, item);
>  		__this_cpu_write(*p, -overstep);
> @@ -434,13 +434,13 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
>  void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
>  {
>  	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
> -	s8 __percpu *p = pcp->vm_node_stat_diff + item;
> -	s8 v, t;
> +	s16 __percpu *p = pcp->vm_node_stat_diff + item;
> +	s16 v, t;
>  
>  	v = __this_cpu_dec_return(*p);
>  	t = __this_cpu_read(pcp->stat_threshold);
>  	if (unlikely(v < - t)) {
> -		s8 overstep = t >> 1;
> +		s16 overstep = t >> 1;
>  
>  		node_page_state_add(v - overstep, pgdat, item);
>  		__this_cpu_write(*p, overstep);
> @@ -533,7 +533,7 @@ static inline void mod_node_state(struct pglist_data *pgdat,
>         enum node_stat_item item, int delta, int overstep_mode)
>  {
>  	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
> -	s8 __percpu *p = pcp->vm_node_stat_diff + item;
> +	s16 __percpu *p = pcp->vm_node_stat_diff + item;
>  	long o, n, t, z;
>  
>  	do {
> -- 
> 2.7.4
> 

-- 
Michal Hocko
SUSE Labs