Re: [PATCH 1/7] vmscan: also shrink slab in memcg pressure

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



(2013/02/08 22:07), Glauber Costa wrote:
> Without the surrounding infrastructure, this patch is a bit of a hammer:
> it will basically shrink objects from all memcgs under memcg pressure.
> At least, however, we will keep the scan limited to the shrinkers marked
> as per-memcg.
> 
> Future patches will implement the in-shrinker logic to filter objects
> based on its memcg association.
> 
> Signed-off-by: Glauber Costa <glommer@xxxxxxxxxxxxx>
> Cc: Dave Chinner <dchinner@xxxxxxxxxx>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Rik van Riel <riel@xxxxxxxxxx>
> Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> Cc: Michal Hocko <mhocko@xxxxxxx>
> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> ---
>   include/linux/memcontrol.h | 16 ++++++++++++++++
>   include/linux/shrinker.h   |  4 ++++
>   mm/memcontrol.c            | 11 ++++++++++-
>   mm/vmscan.c                | 41 ++++++++++++++++++++++++++++++++++++++---
>   4 files changed, 68 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 0108a56..b7de557 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -200,6 +200,9 @@ void mem_cgroup_split_huge_fixup(struct page *head);
>   bool mem_cgroup_bad_page_check(struct page *page);
>   void mem_cgroup_print_bad_page(struct page *page);
>   #endif
> +
> +unsigned long
> +memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone);
>   #else /* CONFIG_MEMCG */
>   struct mem_cgroup;
>   
> @@ -384,6 +387,11 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
>   				struct page *newpage)
>   {
>   }
> +
> +static inline unsigned long
> +memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone)
> +{
> +}
>   #endif /* CONFIG_MEMCG */
>   
>   #if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
> @@ -436,6 +444,8 @@ static inline bool memcg_kmem_enabled(void)
>   	return static_key_false(&memcg_kmem_enabled_key);
>   }
>   
> +bool memcg_kmem_is_active(struct mem_cgroup *memcg);
> +
>   /*
>    * In general, we'll do everything in our power to not incur in any overhead
>    * for non-memcg users for the kmem functions. Not even a function call, if we
> @@ -569,6 +579,12 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
>   	return __memcg_kmem_get_cache(cachep, gfp);
>   }
>   #else
> +
> +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
> +{
> +	return false;
> +}
> +
>   #define for_each_memcg_cache_index(_idx)	\
>   	for (; NULL; )
>   
> diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
> index d4636a0..a767f2e 100644
> --- a/include/linux/shrinker.h
> +++ b/include/linux/shrinker.h
> @@ -20,6 +20,9 @@ struct shrink_control {
>   
>   	/* shrink from these nodes */
>   	nodemask_t nodes_to_scan;
> +
> +	/* reclaim from this memcg only (if not NULL) */
> +	struct mem_cgroup *target_mem_cgroup;
>   };
>   
>   /*
> @@ -45,6 +48,7 @@ struct shrinker {
>   
>   	int seeks;	/* seeks to recreate an obj */
>   	long batch;	/* reclaim batch size, 0 = default */
> +	bool memcg_shrinker;
>   

What is this boolean for ? When is this set ?

>   	/* These are for internal use */
>   	struct list_head list;
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 3817460..b1d4dfa 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -442,7 +442,7 @@ static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
>   	set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
>   }
>   
> -static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
> +bool memcg_kmem_is_active(struct mem_cgroup *memcg)
>   {
>   	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
>   }
> @@ -991,6 +991,15 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
>   	return ret;
>   }
>   
> +unsigned long
> +memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone)
> +{
> +	int nid = zone_to_nid(zone);
> +	int zid = zone_idx(zone);
> +
> +	return mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, LRU_ALL);
> +}
> +
>   static unsigned long
>   mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
>   			int nid, unsigned int lru_mask)
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6d96280..8af0e2b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -138,11 +138,42 @@ static bool global_reclaim(struct scan_control *sc)
>   {
>   	return !sc->target_mem_cgroup;
>   }
> +
> +/*
> + * kmem reclaim should usually not be triggered when we are doing targetted
> + * reclaim. It is only valid when global reclaim is triggered, or when the
> + * underlying memcg has kmem objects.
> + */
> +static bool has_kmem_reclaim(struct scan_control *sc)
> +{
> +	return !sc->target_mem_cgroup ||
> +	(sc->target_mem_cgroup && memcg_kmem_is_active(sc->target_mem_cgroup));
> +}
> +
> +static unsigned long
> +zone_nr_reclaimable_pages(struct scan_control *sc, struct zone *zone)
> +{
> +	if (global_reclaim(sc))
> +		return zone_reclaimable_pages(zone);
> +	return memcg_zone_reclaimable_pages(sc->target_mem_cgroup, zone);
> +}
> +
>   #else
>   static bool global_reclaim(struct scan_control *sc)
>   {
>   	return true;
>   }
> +
> +static bool has_kmem_reclaim(struct scan_control *sc)
> +{
> +	return true;
> +}
> +
> +static unsigned long
> +zone_nr_reclaimable_pages(struct scan_control *sc, struct zone *zone)
> +{
> +	return zone_reclaimable_pages(zone);
> +}
>   #endif

Can't be in a devided patch ?

>   
>   static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
> @@ -221,6 +252,9 @@ unsigned long shrink_slab(struct shrink_control *sc,
>   		long batch_size = shrinker->batch ? shrinker->batch
>   						  : SHRINK_BATCH;
>   
> +		if (!shrinker->memcg_shrinker && sc->target_mem_cgroup)
> +			continue;
> +

What does this mean ?

>   		max_pass = shrinker->count_objects(shrinker, sc);
>   		WARN_ON(max_pass < 0);
>   		if (max_pass <= 0)
> @@ -2170,9 +2204,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
>   
>   		/*
>   		 * Don't shrink slabs when reclaiming memory from
> -		 * over limit cgroups
> +		 * over limit cgroups, unless we know they have kmem objects
>   		 */
> -		if (global_reclaim(sc)) {
> +		if (has_kmem_reclaim(sc)) {
>   			unsigned long lru_pages = 0;
>   
>   			nodes_clear(shrink->nodes_to_scan);
> @@ -2181,7 +2215,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
>   				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
>   					continue;
>   
> -				lru_pages += zone_reclaimable_pages(zone);
> +				lru_pages += zone_nr_reclaimable_pages(sc, zone);
>   				node_set(zone_to_nid(zone),
>   					 shrink->nodes_to_scan);
>   			}
> @@ -2443,6 +2477,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
>   	};
>   	struct shrink_control shrink = {
>   		.gfp_mask = sc.gfp_mask,
> +		.target_mem_cgroup = memcg,
>   	};
>   
>   	/*
> 

Thanks,
-Kame

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux