On Tue, Dec 8, 2020 at 1:53 AM Muchun Song <songmuchun@xxxxxxxxxxxxx> 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.
>
> The size of struct lruvec_stat is 304 bytes on 64 bits system. As it
> is a per-cpu structure. So with this patch, we can save 304 / 2 * ncpu
> bytes per-memcg per-node where ncpu is the number of the possible CPU.
> If there are c memory cgroup (include dying cgroup) and n NUMA node in
> the system. Finally, we can save (152 * ncpu * c * n) bytes.
>
> Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Few nits below:
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> ---
> Changes in v1 -> v2:
> - Update the commit log to point out how many bytes that we can save.
>
> include/linux/memcontrol.h | 6 +++++-
> mm/memcontrol.c | 10 +++++++++-
> 2 files changed, 14 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 3febf64d1b80..290d6ec8535a 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 {
lruvec_stat is also per-cpu, so the name per_cpu_lruvec_stat does not
really tell why it is different from lruvec. Maybe name is
batched_lruvec_stat or something else.
> + 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;
A comment for the above why it still needs to be lruvec_stat.
>
> /* 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 eec44918d373..da6dc6ca388d 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -5198,7 +5198,7 @@ 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);
> @@ -7089,6 +7089,14 @@ static int __init mem_cgroup_init(void)
> {
> int cpu, node;
>
> + /*
> + * Currently s32 type (can refer to struct per_cpu_lruvec_stat) is
> + * used for per-memcg-per-cpu caching of per-node statistics. In order
> + * to work fine, we should make sure that the overfill threshold can't
> + * exceed S32_MAX / PAGE_SIZE.
> + */
> + BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);
> +
> cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
> memcg_hotplug_cpu_dead);
>
> --
> 2.11.0
>
