diff options
| author | Alexander Duyck <alexander.h.duyck@intel.com> | 2010-05-21 14:41:35 -0700 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@suse.de> | 2010-07-05 11:22:37 -0700 |
| commit | 68b99fb8e1e21209c9cad878e99947613e445777 (patch) | |
| tree | 1b389b662906c5acddcc707cf78ee561581684eb /mm | |
| parent | 0d28a228f4fc8d88deaafa4c284385271a84da5c (diff) | |
slub: move kmem_cache_node into it's own cacheline
commit 73367bd8eef4f4eb311005886aaa916013073265 upstream.
This patch is meant to improve the performance of SLUB by moving the local
kmem_cache_node lock into it's own cacheline separate from kmem_cache.
This is accomplished by simply removing the local_node when NUMA is enabled.
On my system with 2 nodes I saw around a 5% performance increase w/
hackbench times dropping from 6.2 seconds to 5.9 seconds on average. I
suspect the performance gain would increase as the number of nodes
increases, but I do not have the data to currently back that up.
Bugzilla-Reference: http://bugzilla.kernel.org/show_bug.cgi?id=15713
Reported-by: Alex Shi <alex.shi@intel.com>
Tested-by: Alex Shi <alex.shi@intel.com>
Acked-by: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/slub.c | 33 |
1 files changed, 11 insertions, 22 deletions
diff --git a/mm/slub.c b/mm/slub.c index d2a54fe71ea2..6cf6be7e6850 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2141,7 +2141,7 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = s->node[node]; - if (n && n != &s->local_node) + if (n) kmem_cache_free(kmalloc_caches, n); s->node[node] = NULL; } @@ -2150,33 +2150,22 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) { int node; - int local_node; - - if (slab_state >= UP && (s < kmalloc_caches || - s >= kmalloc_caches + KMALLOC_CACHES)) - local_node = page_to_nid(virt_to_page(s)); - else - local_node = 0; for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n; - if (local_node == node) - n = &s->local_node; - else { - if (slab_state == DOWN) { - early_kmem_cache_node_alloc(gfpflags, node); - continue; - } - n = kmem_cache_alloc_node(kmalloc_caches, - gfpflags, node); - - if (!n) { - free_kmem_cache_nodes(s); - return 0; - } + if (slab_state == DOWN) { + early_kmem_cache_node_alloc(gfpflags, node); + continue; + } + n = kmem_cache_alloc_node(kmalloc_caches, + gfpflags, node); + if (!n) { + free_kmem_cache_nodes(s); + return 0; } + s->node[node] = n; init_kmem_cache_node(n, s); } |