Re: [PATCH] mm: memcontrol: optimize per-lruvec stats counter memory usage

[Michal Hocko <mhocko@suse.com>]

On Sun 06-12-20 16:56:39, Muchun Song wrote:
> The vmstat threshold is 32 (MEMCG_CHARGE_BATCH), so the type of s32
> of lruvec_stat_cpu is enough. And introduce struct per_cpu_lruvec_stat
> to optimize memory usage.

How much savings are we talking about here? I am not deeply familiar
with the pcp allocator but can it compact smaller data types much
better?

> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  include/linux/memcontrol.h | 6 +++++-
>  mm/memcontrol.c            | 2 +-
>  2 files changed, 6 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index f9a496c4eac7..34cf119976b1 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -92,6 +92,10 @@ struct lruvec_stat {
>  	long count[NR_VM_NODE_STAT_ITEMS];
>  };
>  
> +struct per_cpu_lruvec_stat {
> +	s32 count[NR_VM_NODE_STAT_ITEMS];
> +};
> +
>  /*
>   * Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
>   * which have elements charged to this memcg.
> @@ -111,7 +115,7 @@ struct mem_cgroup_per_node {
>  	struct lruvec_stat __percpu *lruvec_stat_local;
>  
>  	/* Subtree VM stats (batched updates) */
> -	struct lruvec_stat __percpu *lruvec_stat_cpu;
> +	struct per_cpu_lruvec_stat __percpu *lruvec_stat_cpu;
>  	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
>  
>  	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 49fbcf003bf5..c874ea37b05d 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -5184,7 +5184,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
>  		return 1;
>  	}
>  
> -	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat,
> +	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct per_cpu_lruvec_stat,
>  					       GFP_KERNEL_ACCOUNT);
>  	if (!pn->lruvec_stat_cpu) {
>  		free_percpu(pn->lruvec_stat_local);
> -- 
> 2.11.0

-- 
Michal Hocko
SUSE Labs