On Wed, Apr 14, 2010 at 6:37 AM, David Rientjes <rientjes@xxxxxxxxxx> wrote: > On Wed, 14 Apr 2010, Minchan Kim wrote: > >> alloc_slab_page never calls alloc_pages_node with -1. >> It means node's validity check is unnecessary. >> So we can use alloc_pages_exact_node instead of alloc_pages_node. >> It could avoid comparison and branch as 6484eb3e2a81807722 tried. >> >> Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx> >> Signed-off-by: Minchan Kim <minchan.kim@xxxxxxxxx> >> --- >> mm/slub.c | 2 +- >> 1 files changed, 1 insertions(+), 1 deletions(-) >> >> diff --git a/mm/slub.c b/mm/slub.c >> index b364844..9984165 100644 >> --- a/mm/slub.c >> +++ b/mm/slub.c >> @@ -1084,7 +1084,7 @@ static inline struct page *alloc_slab_page(gfp_t flags, int node, >> if (node == -1) >> return alloc_pages(flags, order); >> else >> - return alloc_pages_node(node, flags, order); >> + return alloc_pages_exact_node(node, flags, order); >> } >> >> static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) > > Slub changes need to go through its maintainer, Pekka Enberg > <penberg@xxxxxxxxxxxxxx>. Thanks, David. It was by mistake. Pekka. This changlog is bad. I will change it with following as when I send v2. "alloc_slab_page always checks nid == -1, so alloc_page_node can't be called with -1. It means node's validity check in alloc_pages_node is unnecessary. So we can use alloc_pages_exact_node instead of alloc_pages_node. It could avoid comparison and branch as 6484eb3e2a81807722 tried." Thanks. -- Kind regards, Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href