From 86d9f48534e800e4d62cdc1b5aaf539f4c1d47d6 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Thu, 27 Oct 2016 17:46:18 -0700 Subject: mm/slab: fix kmemcg cache creation delayed issue There is a bug report that SLAB makes extreme load average due to over 2000 kworker thread. https://bugzilla.kernel.org/show_bug.cgi?id=172981 This issue is caused by kmemcg feature that try to create new set of kmem_caches for each memcg. Recently, kmem_cache creation is slowed by synchronize_sched() and futher kmem_cache creation is also delayed since kmem_cache creation is synchronized by a global slab_mutex lock. So, the number of kworker that try to create kmem_cache increases quietly. synchronize_sched() is for lockless access to node's shared array but it's not needed when a new kmem_cache is created. So, this patch rules out that case. Fixes: 801faf0db894 ("mm/slab: lockless decision to grow cache") Link: http://lkml.kernel.org/r/1475734855-4837-1-git-send-email-iamjoonsoo.kim@lge.com Reported-by: Doug Smythies Tested-by: Doug Smythies Signed-off-by: Joonsoo Kim Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/slab.c') diff --git a/mm/slab.c b/mm/slab.c index 090fb26b3a39..c451e3f6bbf6 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -966,7 +966,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, * guaranteed to be valid until irq is re-enabled, because it will be * freed after synchronize_sched(). */ - if (force_change) + if (old_shared && force_change) synchronize_sched(); fail: -- cgit v1.2.3-59-g8ed1b From 07a63c41fa1f6533f5668e5b33a295bfd63aa534 Mon Sep 17 00:00:00 2001 From: Aruna Ramakrishna Date: Thu, 27 Oct 2016 17:46:32 -0700 Subject: mm/slab: improve performance of gathering slabinfo stats On large systems, when some slab caches grow to millions of objects (and many gigabytes), running 'cat /proc/slabinfo' can take up to 1-2 seconds. During this time, interrupts are disabled while walking the slab lists (slabs_full, slabs_partial, and slabs_free) for each node, and this sometimes causes timeouts in other drivers (for instance, Infiniband). This patch optimizes 'cat /proc/slabinfo' by maintaining a counter for total number of allocated slabs per node, per cache. This counter is updated when a slab is created or destroyed. This enables us to skip traversing the slabs_full list while gathering slabinfo statistics, and since slabs_full tends to be the biggest list when the cache is large, it results in a dramatic performance improvement. Getting slabinfo statistics now only requires walking the slabs_free and slabs_partial lists, and those lists are usually much smaller than slabs_full. We tested this after growing the dentry cache to 70GB, and the performance improved from 2s to 5ms. Link: http://lkml.kernel.org/r/1472517876-26814-1-git-send-email-aruna.ramakrishna@oracle.com Signed-off-by: Aruna Ramakrishna Acked-by: David Rientjes Cc: Mike Kravetz Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 43 +++++++++++++++++++++++++++---------------- mm/slab.h | 1 + 2 files changed, 28 insertions(+), 16 deletions(-) (limited to 'mm/slab.c') diff --git a/mm/slab.c b/mm/slab.c index c451e3f6bbf6..0b0550ca85b4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -233,6 +233,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent) spin_lock_init(&parent->list_lock); parent->free_objects = 0; parent->free_touched = 0; + parent->num_slabs = 0; } #define MAKE_LIST(cachep, listp, slab, nodeid) \ @@ -1382,24 +1383,27 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) for_each_kmem_cache_node(cachep, node, n) { unsigned long active_objs = 0, num_objs = 0, free_objects = 0; unsigned long active_slabs = 0, num_slabs = 0; + unsigned long num_slabs_partial = 0, num_slabs_free = 0; + unsigned long num_slabs_full; spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->slabs_full, lru) { - active_objs += cachep->num; - active_slabs++; - } + num_slabs = n->num_slabs; list_for_each_entry(page, &n->slabs_partial, lru) { active_objs += page->active; - active_slabs++; + num_slabs_partial++; } list_for_each_entry(page, &n->slabs_free, lru) - num_slabs++; + num_slabs_free++; free_objects += n->free_objects; spin_unlock_irqrestore(&n->list_lock, flags); - num_slabs += active_slabs; num_objs = num_slabs * cachep->num; + active_slabs = num_slabs - num_slabs_free; + num_slabs_full = num_slabs - + (num_slabs_partial + num_slabs_free); + active_objs += (num_slabs_full * cachep->num); + pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n", node, active_slabs, num_slabs, active_objs, num_objs, free_objects); @@ -2314,6 +2318,7 @@ static int drain_freelist(struct kmem_cache *cache, page = list_entry(p, struct page, lru); list_del(&page->lru); + n->num_slabs--; /* * Safe to drop the lock. The slab is no longer linked * to the cache. @@ -2752,6 +2757,8 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) list_add_tail(&page->lru, &(n->slabs_free)); else fixup_slab_list(cachep, n, page, &list); + + n->num_slabs++; STATS_INC_GROWN(cachep); n->free_objects += cachep->num - page->active; spin_unlock(&n->list_lock); @@ -3443,6 +3450,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp, page = list_last_entry(&n->slabs_free, struct page, lru); list_move(&page->lru, list); + n->num_slabs--; } } @@ -4099,6 +4107,8 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) unsigned long num_objs; unsigned long active_slabs = 0; unsigned long num_slabs, free_objects = 0, shared_avail = 0; + unsigned long num_slabs_partial = 0, num_slabs_free = 0; + unsigned long num_slabs_full = 0; const char *name; char *error = NULL; int node; @@ -4111,33 +4121,34 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) check_irq_on(); spin_lock_irq(&n->list_lock); - list_for_each_entry(page, &n->slabs_full, lru) { - if (page->active != cachep->num && !error) - error = "slabs_full accounting error"; - active_objs += cachep->num; - active_slabs++; - } + num_slabs += n->num_slabs; + list_for_each_entry(page, &n->slabs_partial, lru) { if (page->active == cachep->num && !error) error = "slabs_partial accounting error"; if (!page->active && !error) error = "slabs_partial accounting error"; active_objs += page->active; - active_slabs++; + num_slabs_partial++; } + list_for_each_entry(page, &n->slabs_free, lru) { if (page->active && !error) error = "slabs_free accounting error"; - num_slabs++; + num_slabs_free++; } + free_objects += n->free_objects; if (n->shared) shared_avail += n->shared->avail; spin_unlock_irq(&n->list_lock); } - num_slabs += active_slabs; num_objs = num_slabs * cachep->num; + active_slabs = num_slabs - num_slabs_free; + num_slabs_full = num_slabs - (num_slabs_partial + num_slabs_free); + active_objs += (num_slabs_full * cachep->num); + if (num_objs - active_objs != free_objects && !error) error = "free_objects accounting error"; diff --git a/mm/slab.h b/mm/slab.h index 9653f2e2591a..bc05fdc3edce 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -432,6 +432,7 @@ struct kmem_cache_node { struct list_head slabs_partial; /* partial list first, better asm code */ struct list_head slabs_full; struct list_head slabs_free; + unsigned long num_slabs; unsigned long free_objects; unsigned int free_limit; unsigned int colour_next; /* Per-node cache coloring */ -- cgit v1.2.3-59-g8ed1b