On Tue, Apr 12, 2016 at 11:38:39AM -0500, Christoph Lameter wrote: > On Tue, 12 Apr 2016, [email protected] wrote: > > > @@ -2222,6 +2241,7 @@ static void drain_cpu_caches(struct kmem_cache > > *cachep) > > { > > struct kmem_cache_node *n; > > int node; > > + LIST_HEAD(list); > > > > on_each_cpu(do_drain, cachep, 1); > > check_irq_on(); > > @@ -2229,8 +2249,13 @@ static void drain_cpu_caches(struct kmem_cache > > *cachep) > > if (n->alien) > > drain_alien_cache(cachep, n->alien); > > > > - for_each_kmem_cache_node(cachep, node, n) > > - drain_array(cachep, n, n->shared, 1, node); > > + for_each_kmem_cache_node(cachep, node, n) { > > + spin_lock_irq(&n->list_lock); > > + drain_array_locked(cachep, n->shared, node, true, &list); > > + spin_unlock_irq(&n->list_lock); > > + > > + slabs_destroy(cachep, &list); > > Can the slabs_destroy() call be moved outside of the loop? It may be > faster then?
Yes, it can. But, I'd prefer to call it on each node. It would be better for cache although it would be marginal. Thanks.
