On Wed, Jan 28, 2015 at 10:33:50AM -0600, Christoph Lameter wrote: > On Wed, 28 Jan 2015, Vladimir Davydov wrote: > > > @@ -3419,6 +3420,9 @@ int __kmem_cache_shrink(struct kmem_cache *s) > > for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) > > list_splice_init(promote + i, &n->partial); > > > > + if (n->nr_partial || slabs_node(s, node)) > > The total number of slabs obtained via slabs_node always contains the > number of partial ones. So no need to check n->nr_partial. Yeah, right. In addition to that I misplaced the check - it should go after discard_slab, where we decrement nr_slabs. Here goes the updated patch: From: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> Subject: [PATCH] slub: fix kmem_cache_shrink return value It is supposed to return 0 if the cache has no remaining objects and 1 otherwise, while currently it always returns 0. Fix it. Signed-off-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> --- mm/slub.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/slub.c b/mm/slub.c index dbf9334b6a5c..5626588db884 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3379,6 +3379,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) LIST_HEAD(discard); struct list_head promote[SHRINK_PROMOTE_MAX]; unsigned long flags; + int ret = 0; for (i = 0; i < SHRINK_PROMOTE_MAX; i++) INIT_LIST_HEAD(promote + i); @@ -3424,9 +3425,12 @@ int __kmem_cache_shrink(struct kmem_cache *s) /* Release empty slabs */ list_for_each_entry_safe(page, t, &discard, lru) discard_slab(s, page); + + if (slabs_node(s, node)) + ret = 1; } - return 0; + return ret; } static int slab_mem_going_offline_callback(void *arg) -- 1.7.10.4 -- 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/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>