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 <songmuc...@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
