Re: [PATCH V3 6/7] Enable per-memcg background reclaim.

[Ying Han <yinghan@xxxxxxxxxx>]

On Wed, Apr 13, 2011 at 2:05 AM, KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:

On Wed, 13 Apr 2011 00:03:06 -0700
Ying Han <yinghan@xxxxxxxxxx> wrote:

> By default the per-memcg background reclaim is disabled when the limit_in_bytes
> is set the maximum or the wmark_ratio is 0. The kswapd_run() is called when the
> memcg is being resized, and kswapd_stop() is called when the memcg is being
> deleted.
>
> The per-memcg kswapd is waked up based on the usage and low_wmark, which is
> checked once per 1024 increments per cpu. The memcg's kswapd is waked up if the
> usage is larger than the low_wmark.
>
> changelog v3..v2:
> 1. some clean-ups
>
> changelog v2..v1:
> 1. start/stop the per-cgroup kswapd at create/delete cgroup stage.
> 2. remove checking the wmark from per-page charging. now it checks the wmark
> periodically based on the event counter.
>
> Signed-off-by: Ying Han <yinghan@xxxxxxxxxx>

This event logic seems to make sense.

> ---
>  mm/memcontrol.c |   37 +++++++++++++++++++++++++++++++++++++
>  1 files changed, 37 insertions(+), 0 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index efeade3..bfa8646 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -105,10 +105,12 @@ enum mem_cgroup_events_index {
>  enum mem_cgroup_events_target {
>       MEM_CGROUP_TARGET_THRESH,
>       MEM_CGROUP_TARGET_SOFTLIMIT,
> +     MEM_CGROUP_WMARK_EVENTS_THRESH,
>       MEM_CGROUP_NTARGETS,
>  };
>  #define THRESHOLDS_EVENTS_TARGET (128)
>  #define SOFTLIMIT_EVENTS_TARGET (1024)
> +#define WMARK_EVENTS_TARGET (1024)
>
>  struct mem_cgroup_stat_cpu {
>       long count[MEM_CGROUP_STAT_NSTATS];
> @@ -366,6 +368,7 @@ static void mem_cgroup_put(struct mem_cgroup *mem);
>  static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
>  static void drain_all_stock_async(void);
>  static unsigned long get_wmark_ratio(struct mem_cgroup *mem);
> +static void wake_memcg_kswapd(struct mem_cgroup *mem);
>
>  static struct mem_cgroup_per_zone *
>  mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
> @@ -545,6 +548,12 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
>       return mz;
>  }
>
> +static void mem_cgroup_check_wmark(struct mem_cgroup *mem)
> +{
> +     if (!mem_cgroup_watermark_ok(mem, CHARGE_WMARK_LOW))
> +             wake_memcg_kswapd(mem);
> +}
> +
>  /*
>   * Implementation Note: reading percpu statistics for memcg.
>   *
> @@ -675,6 +684,9 @@ static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target)
>       case MEM_CGROUP_TARGET_SOFTLIMIT:
>               next = val + SOFTLIMIT_EVENTS_TARGET;
>               break;
> +     case MEM_CGROUP_WMARK_EVENTS_THRESH:
> +             next = val + WMARK_EVENTS_TARGET;
> +             break;
>       default:
>               return;
>       }
> @@ -698,6 +710,10 @@ static void memcg_check_events(struct mem_cgroup *mem, struct page *page)
>                       __mem_cgroup_target_update(mem,
>                               MEM_CGROUP_TARGET_SOFTLIMIT);
>               }
> +             if (unlikely(__memcg_event_check(mem,
> +                     MEM_CGROUP_WMARK_EVENTS_THRESH))){
> +                     mem_cgroup_check_wmark(mem);
> +             }
>       }
>  }
>
> @@ -3384,6 +3400,10 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
>       if (!ret && enlarge)
>               memcg_oom_recover(memcg);
>
> +     if (!mem_cgroup_is_root(memcg) && !memcg->kswapd_wait &&
> +                     memcg->wmark_ratio)
> +             kswapd_run(0, memcg);
> +

Isn't it enough to have trigger in charge() path ?

why? kswapd_run() is to create the kswapd thread for the memcg. If the memcg's limit doesn't change from the initial value, we don't want to create a kswapd thread for it. Only if the limit_in_byte is being changed. Adding the hook in the charge path sounds too much overhead to the hotpath.

However, I might need to add checks here, where if the limit_in_byte is set to RESOURCE_MAX.

rather than here, I think we should check _move_task(). It changes res usage
dramatically without updating events.

I see both the mem_cgroup_charge_statistics() and memcg_check_events()  are being called in mem_cgroup_move_account(). Am i missing anything here?

Thanks

--Ying

 

Thanks,
-Kame

>       return ret;
>  }
>
> @@ -4680,6 +4700,7 @@ static void __mem_cgroup_free(struct mem_cgroup *mem)
>  {
>       int node;
>
> +     kswapd_stop(0, mem);
>       mem_cgroup_remove_from_trees(mem);
>       free_css_id(&mem_cgroup_subsys, &mem->css);
>

I think kswapd should stop at mem_cgroup_destroy(). No more tasks will use
this memcg after _destroy().

I made the change. 

Thanks,
-Kame

> @@ -4786,6 +4807,22 @@ int mem_cgroup_last_scanned_node(struct mem_cgroup *mem)
>       return mem->last_scanned_node;
>  }
>
> +static inline
> +void wake_memcg_kswapd(struct mem_cgroup *mem)
> +{
> +     wait_queue_head_t *wait;
> +
> +     if (!mem || !mem->wmark_ratio)
> +             return;
> +
> +     wait = mem->kswapd_wait;
> +
> +     if (!wait || !waitqueue_active(wait))
> +             return;
> +
> +     wake_up_interruptible(wait);
> +}
> +
>  static int mem_cgroup_soft_limit_tree_init(void)
>  {
>       struct mem_cgroup_tree_per_node *rtpn;
> --
> 1.7.3.1
>

> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
> Don't email: <a href="" href="mailto:dont@xxxxxxxxx">dont@xxxxxxxxx"> email@xxxxxxxxx </a>
>