From 7c2e132c54c79af4e524154074b9a02c3c0d6072 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 7 Jan 2008 23:20:27 -0800 Subject: [PATCH] Add parameter to add_partial to avoid having two functions Add a parameter to add_partial instead of having separate functions. The parameter allows a more detailed control of where the slab pages is placed in the partial queues. If we put slabs back to the front then they are likely immediately used for allocations. If they are put at the end then we can maximize the time that the partial slabs spent without being subject to allocations. When deactivating slab we can put the slabs that had remote objects freed (we can see that because objects were put on the freelist that requires locks) to them at the end of the list so that the cachelines of remote processors can cool down. Slabs that had objects from the local cpu freed to them (objects exist in the lockless freelist) are put in the front of the list to be reused ASAP in order to exploit the cache hot state of the local cpu. Patch seems to slightly improve tbench speed (1-2%). Signed-off-by: Christoph Lameter Reviewed-by: Pekka Enberg Signed-off-by: Andrew Morton --- mm/slub.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 5146e2779c..e160f28ab0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1198,19 +1198,15 @@ static __always_inline int slab_trylock(struct page *page) /* * Management of partially allocated slabs */ -static void add_partial_tail(struct kmem_cache_node *n, struct page *page) +static void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) { spin_lock(&n->list_lock); n->nr_partial++; - list_add_tail(&page->lru, &n->partial); - spin_unlock(&n->list_lock); -} - -static void add_partial(struct kmem_cache_node *n, struct page *page) -{ - spin_lock(&n->list_lock); - n->nr_partial++; - list_add(&page->lru, &n->partial); + if (tail) + list_add_tail(&page->lru, &n->partial); + else + list_add(&page->lru, &n->partial); spin_unlock(&n->list_lock); } @@ -1339,7 +1335,7 @@ static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node) * * On exit the slab lock will have been dropped. */ -static void unfreeze_slab(struct kmem_cache *s, struct page *page) +static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); @@ -1347,7 +1343,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page) if (page->inuse) { if (page->freelist) - add_partial(n, page); + add_partial(n, page, tail); else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER)) add_full(n, page); slab_unlock(page); @@ -1362,7 +1358,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page) * partial list stays small. kmem_cache_shrink can * reclaim empty slabs from the partial list. */ - add_partial_tail(n, page); + add_partial(n, page, 1); slab_unlock(page); } else { slab_unlock(page); @@ -1377,6 +1373,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page) static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { struct page *page = c->page; + int tail = 1; /* * Merge cpu freelist into freelist. Typically we get here * because both freelists are empty. So this is unlikely @@ -1385,6 +1382,8 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) while (unlikely(c->freelist)) { void **object; + tail = 0; /* Hot objects. Put the slab first */ + /* Retrieve object from cpu_freelist */ object = c->freelist; c->freelist = c->freelist[c->offset]; @@ -1395,7 +1394,7 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) page->inuse--; } c->page = NULL; - unfreeze_slab(s, page); + unfreeze_slab(s, page, tail); } static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) @@ -1617,7 +1616,7 @@ checks_ok: * then add it. */ if (unlikely(!prior)) - add_partial_tail(get_node(s, page_to_nid(page)), page); + add_partial(get_node(s, page_to_nid(page)), page, 1); out_unlock: slab_unlock(page); @@ -2025,7 +2024,7 @@ static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags, #endif init_kmem_cache_node(n); atomic_long_inc(&n->nr_slabs); - add_partial(n, page); + add_partial(n, page, 0); return n; } -- 2.39.5