From cb731d6c62bbc2f890b08ea3d0386d5dad887326 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:58:54 -0800 Subject: [PATCH] vmscan: per memory cgroup slab shrinkers This patch adds SHRINKER_MEMCG_AWARE flag. If a shrinker has this flag set, it will be called per memory cgroup. The memory cgroup to scan objects from is passed in shrink_control->memcg. If the memory cgroup is NULL, a memcg aware shrinker is supposed to scan objects from the global list. Unaware shrinkers are only called on global pressure with memcg=NULL. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/drop_caches.c | 14 ------- include/linux/memcontrol.h | 7 ++++ include/linux/mm.h | 5 +-- include/linux/shrinker.h | 6 ++- mm/memcontrol.c | 2 +- mm/memory-failure.c | 11 +---- mm/vmscan.c | 85 ++++++++++++++++++++++++++++---------- 7 files changed, 80 insertions(+), 50 deletions(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 2bc2c87f35e7..5718cb9f7273 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -37,20 +37,6 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) iput(toput_inode); } -static void drop_slab(void) -{ - int nr_objects; - - do { - int nid; - - nr_objects = 0; - for_each_online_node(nid) - nr_objects += shrink_node_slabs(GFP_KERNEL, nid, - 1000, 1000); - } while (nr_objects > 10); -} - int drop_caches_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6cfd934c7c9b..54992fe0959f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -413,6 +413,8 @@ 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 @@ -542,6 +544,11 @@ static inline bool memcg_kmem_enabled(void) return false; } +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) +{ + return false; +} + static inline bool memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) { diff --git a/include/linux/mm.h b/include/linux/mm.h index a4d24f3c5430..af4ff88a11e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2168,9 +2168,8 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); #endif -unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, - unsigned long nr_scanned, - unsigned long nr_eligible); +void drop_slab(void); +void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index f4aee75f00b1..4fcacd915d45 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -20,6 +20,9 @@ struct shrink_control { /* current node being shrunk (for NUMA aware shrinkers) */ int nid; + + /* current memcg being shrunk (for memcg aware shrinkers) */ + struct mem_cgroup *memcg; }; #define SHRINK_STOP (~0UL) @@ -61,7 +64,8 @@ struct shrinker { #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ /* Flags */ -#define SHRINKER_NUMA_AWARE (1 << 0) +#define SHRINKER_NUMA_AWARE (1 << 0) +#define SHRINKER_MEMCG_AWARE (1 << 1) extern int register_shrinker(struct shrinker *); extern void unregister_shrinker(struct shrinker *); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 095c1f96fbec..3c2a1a8286ac 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -352,7 +352,7 @@ struct mem_cgroup { }; #ifdef CONFIG_MEMCG_KMEM -static bool memcg_kmem_is_active(struct mem_cgroup *memcg) +bool memcg_kmem_is_active(struct mem_cgroup *memcg) { return memcg->kmemcg_id >= 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index feb803bf3443..1a735fad2a13 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -242,15 +242,8 @@ void shake_page(struct page *p, int access) * Only call shrink_node_slabs here (which would also shrink * other caches) if access is not potentially fatal. */ - if (access) { - int nr; - int nid = page_to_nid(p); - do { - nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000); - if (page_count(p) == 1) - break; - } while (nr > 10); - } + if (access) + drop_slab_node(page_to_nid(p)); } EXPORT_SYMBOL_GPL(shake_page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 8e645ee52045..803886b8e353 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -232,10 +232,10 @@ EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 -static unsigned long shrink_slabs(struct shrink_control *shrinkctl, - struct shrinker *shrinker, - unsigned long nr_scanned, - unsigned long nr_eligible) +static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, + struct shrinker *shrinker, + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long freed = 0; unsigned long long delta; @@ -344,9 +344,10 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl, } /** - * shrink_node_slabs - shrink slab caches of a given node + * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target + * @memcg: memory cgroup whose slab caches to target * @nr_scanned: pressure numerator * @nr_eligible: pressure denominator * @@ -355,6 +356,12 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl, * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * + * @memcg specifies the memory cgroup to target. If it is not NULL, + * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan + * objects from the memory cgroup specified. Otherwise all shrinkers + * are called, and memcg aware shrinkers are supposed to scan the + * global list then. + * * @nr_scanned and @nr_eligible form a ratio that indicate how much of * the available objects should be scanned. Page reclaim for example * passes the number of pages scanned and the number of pages on the @@ -365,13 +372,17 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl, * * Returns the number of reclaimed slab objects. */ -unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, - unsigned long nr_scanned, - unsigned long nr_eligible) +static unsigned long shrink_slab(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, + unsigned long nr_scanned, + unsigned long nr_eligible) { struct shrinker *shrinker; unsigned long freed = 0; + if (memcg && !memcg_kmem_is_active(memcg)) + return 0; + if (nr_scanned == 0) nr_scanned = SWAP_CLUSTER_MAX; @@ -390,12 +401,16 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, + .memcg = memcg, }; + if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE)) + continue; + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) sc.nid = 0; - freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible); + freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); } up_read(&shrinker_rwsem); @@ -404,6 +419,29 @@ out: return freed; } +void drop_slab_node(int nid) +{ + unsigned long freed; + + do { + struct mem_cgroup *memcg = NULL; + + freed = 0; + do { + freed += shrink_slab(GFP_KERNEL, nid, memcg, + 1000, 1000); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); + } while (freed > 10); +} + +void drop_slab(void) +{ + int nid; + + for_each_online_node(nid) + drop_slab_node(nid); +} + static inline int is_page_cache_freeable(struct page *page) { /* @@ -2276,6 +2314,7 @@ static inline bool should_continue_reclaim(struct zone *zone, static bool shrink_zone(struct zone *zone, struct scan_control *sc, bool is_classzone) { + struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; bool reclaimable = false; @@ -2294,6 +2333,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, memcg = mem_cgroup_iter(root, NULL, &reclaim); do { unsigned long lru_pages; + unsigned long scanned; struct lruvec *lruvec; int swappiness; @@ -2305,10 +2345,16 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); + scanned = sc->nr_scanned; shrink_lruvec(lruvec, swappiness, sc, &lru_pages); zone_lru_pages += lru_pages; + if (memcg && is_classzone) + shrink_slab(sc->gfp_mask, zone_to_nid(zone), + memcg, sc->nr_scanned - scanned, + lru_pages); + /* * Direct reclaim and kswapd have to scan all memory * cgroups to fulfill the overall scan target for the @@ -2330,19 +2376,14 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, * Shrink the slab caches in the same proportion that * the eligible LRU pages were scanned. */ - if (global_reclaim(sc) && is_classzone) { - struct reclaim_state *reclaim_state; - - shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone), - sc->nr_scanned - nr_scanned, - zone_lru_pages); - - reclaim_state = current->reclaim_state; - if (reclaim_state) { - sc->nr_reclaimed += - reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } + if (global_reclaim(sc) && is_classzone) + shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL, + sc->nr_scanned - nr_scanned, + zone_lru_pages); + + if (reclaim_state) { + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; } vmpressure(sc->gfp_mask, sc->target_mem_cgroup, -- 2.34.1