slab: skip calling cache_free_alien() when the platform is not numa capable

Skip calling cache_free_alien() when the platform is not numa capable.
This will avoid cache misses that happen while accessing slabp (which is
per page memory reference) to get nodeid.  Instead use a global variable to
skip the call, which is mostly likely to be present in the cache.

This gives a 0.8% performance boost with the database oltp workload on a
quad-core SMP platform and by any means the number is not small :)

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/slab.c b/mm/slab.c
index a684778b2b41af38e06aa47e5fe66a7a988ad4c7..6f6abef83a1af82432305245755ab690c8363081 100644 (file)
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -883,6 +883,7 @@ static void __slab_error(const char *function, struct kmem_cache *cachep,
   */
 
 static int use_alien_caches __read_mostly = 1;
+static int numa_platform __read_mostly = 1;
 static int __init noaliencache_setup(char *s)
 {
        use_alien_caches = 0;
@@ -1399,8 +1400,10 @@ void __init kmem_cache_init(void)
        int order;
        int node;
 
-       if (num_possible_nodes() == 1)
+       if (num_possible_nodes() == 1) {
                use_alien_caches = 0;
+               numa_platform = 0;
+       }
 
        for (i = 0; i < NUM_INIT_LISTS; i++) {
                kmem_list3_init(&initkmem_list3[i]);
@@ -3558,7 +3561,14 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
        check_irq_off();
        objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
 
-       if (cache_free_alien(cachep, objp))
+       /*
+        * Skip calling cache_free_alien() when the platform is not numa.
+        * This will avoid cache misses that happen while accessing slabp (which
+        * is per page memory  reference) to get nodeid. Instead use a global
+        * variable to skip the call, which is mostly likely to be present in
+        * the cache.
+        */
+       if (numa_platform && cache_free_alien(cachep, objp))
                return;
 
        if (likely(ac->avail < ac->limit)) {