SLUB: [RFC] Per cpu partial lists V3

Index: linux-2.6/mm/slub.c
===================================================================
@@ -2968,13 +2968,13 @@ static void list_slab_objects(struct kme
 
 /*
  * Attempt to free all partial slabs on a node.
+ * This is called from kmem_cache_close(). We must be the last thread
+ * using the cache and therefore we do not need to lock anymore.
  */
 static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
-	unsigned long flags;
 	struct page *page, *h;
 
-	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
 			remove_partial(n, page);

@@ -2984,7 +2984,6 @@ static void free_partial(struct kmem_cac
 				"Objects remaining on kmem_cache_close()");
 		}
 	}
-	spin_unlock_irqrestore(&n->list_lock, flags);
 }
 
 /*

@@ -3018,6 +3017,7 @@ void kmem_cache_destroy(struct kmem_cach
 	s->refcount--;
 	if (!s->refcount) {
 		list_del(&s->list);
+		up_write(&slub_lock);
 		if (kmem_cache_close(s)) {
 			printk(KERN_ERR "SLUB %s: %s called for cache that "
 				"still has objects.\n", s->name, __func__);

@@ -3026,8 +3026,8 @@ void kmem_cache_destroy(struct kmem_cach
 		if (s->flags & SLAB_DESTROY_BY_RCU)
 			rcu_barrier();
 		sysfs_slab_remove(s);
-	}
-	up_write(&slub_lock);
+	} else
+		up_write(&slub_lock);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 

@@ -3345,23 +3345,23 @@ int kmem_cache_shrink(struct kmem_cache
 		 * list_lock. page->inuse here is the upper limit.
 		 */
 		list_for_each_entry_safe(page, t, &n->partial, lru) {
-			if (!page->inuse) {
-				remove_partial(n, page);
-				discard_slab(s, page);
-			} else {
-				list_move(&page->lru,
-				slabs_by_inuse + page->inuse);
-			}
+			list_move(&page->lru, slabs_by_inuse + page->inuse);
+			if (!page->inuse)
+				n->nr_partial--;
 		}
 
 		/*
 		 * Rebuild the partial list with the slabs filled up most
 		 * first and the least used slabs at the end.
 		 */
-		for (i = objects - 1; i >= 0; i--)
+		for (i = objects - 1; i > 0; i--)
 			list_splice(slabs_by_inuse + i, n->partial.prev);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
+
+		/* Release empty slabs */
+		list_for_each_entry_safe(page, t, slabs_by_inuse, lru)
+			discard_slab(s, page);
 	}
 
 	kfree(slabs_by_inuse);

Index: linux-2.6/mm/slub.c
===================================================================
@@ -2064,9 +2064,6 @@ static void *__slab_alloc(struct kmem_ca
 	c = this_cpu_ptr(s->cpu_slab);
 #endif
 
-	/* We handle __GFP_ZERO in the caller */
-	gfpflags &= ~__GFP_ZERO;
-
 	page = c->page;
 	if (!page)
 		goto new_slab;

@@ -2163,7 +2160,6 @@ debug:
 
 	c->freelist = get_freepointer(s, object);
 	deactivate_slab(s, c);
-	c->page = NULL;
 	c->node = NUMA_NO_NODE;
 	local_irq_restore(flags);
 	return object;

Index: linux-2.6/mm/slub.c
===================================================================
@@ -1447,7 +1447,7 @@ static struct page *new_slab(struct kmem
 	set_freepointer(s, last, NULL);
 
 	page->freelist = start;
-	page->inuse = 0;
+	page->inuse = page->objects;
 	page->frozen = 1;
 out:
 	return page;

@@ -2139,7 +2139,6 @@ new_slab:
 		 */
 		object = page->freelist;
 		page->freelist = NULL;
-		page->inuse = page->objects;
 
 		stat(s, ALLOC_SLAB);
 		c->node = page_to_nid(page);

@@ -2679,7 +2678,7 @@ static void early_kmem_cache_node_alloc(
 	n = page->freelist;
 	BUG_ON(!n);
 	page->freelist = get_freepointer(kmem_cache_node, n);
-	page->inuse++;
+	page->inuse = 1;
 	page->frozen = 0;
 	kmem_cache_node->node[node] = n;
 #ifdef CONFIG_SLUB_DEBUG

Index: linux-2.6/mm/slub.c
===================================================================
@@ -1557,7 +1557,8 @@ static inline void remove_partial(struct
  * Must hold list_lock.
  */
 static inline int acquire_slab(struct kmem_cache *s,
-		struct kmem_cache_node *n, struct page *page)
+		struct kmem_cache_node *n, struct page *page,
+		struct kmem_cache_cpu *c)
 {
 	void *freelist;
 	unsigned long counters;

@@ -1586,9 +1587,9 @@ static inline int acquire_slab(struct km
 
 	if (freelist) {
 		/* Populate the per cpu freelist */
-		this_cpu_write(s->cpu_slab->freelist, freelist);
-		this_cpu_write(s->cpu_slab->page, page);
-		this_cpu_write(s->cpu_slab->node, page_to_nid(page));
+		c->freelist = freelist;
+		c->page = page;
+		c->node = page_to_nid(page);
 		return 1;
 	} else {
 		/*

@@ -1606,7 +1607,7 @@ static inline int acquire_slab(struct km
  * Try to allocate a partial slab from a specific node.
  */
 static struct page *get_partial_node(struct kmem_cache *s,
-					struct kmem_cache_node *n)
+		struct kmem_cache_node *n, struct kmem_cache_cpu *c)
 {
 	struct page *page;
 

@@ -1621,7 +1622,7 @@ static struct page *get_partial_node(str
 
 	spin_lock(&n->list_lock);
 	list_for_each_entry(page, &n->partial, lru)
-		if (acquire_slab(s, n, page))
+		if (acquire_slab(s, n, page, c))
 			goto out;
 	page = NULL;
 out:

@@ -1632,7 +1633,8 @@ out:
 /*
  * Get a page from somewhere. Search in increasing NUMA distances.
  */
-static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
+static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags,
+		struct kmem_cache_cpu *c)
 {
 #ifdef CONFIG_NUMA
 	struct zonelist *zonelist;

@@ -1672,7 +1674,7 @@ static struct page *get_any_partial(stru
 
 		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
 				n->nr_partial > s->min_partial) {
-			page = get_partial_node(s, n);
+			page = get_partial_node(s, n, c);
 			if (page) {
 				put_mems_allowed();
 				return page;

@@ -1687,16 +1689,17 @@ static struct page *get_any_partial(stru
 /*
  * Get a partial page, lock it and return it.
  */
-static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
+static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node,
+		struct kmem_cache_cpu *c)
 {
 	struct page *page;
 	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
-	page = get_partial_node(s, get_node(s, searchnode));
+	page = get_partial_node(s, get_node(s, searchnode), c);
 	if (page || node != NUMA_NO_NODE)
 		return page;
 
-	return get_any_partial(s, flags);
+	return get_any_partial(s, flags, c);
 }
 
 #ifdef CONFIG_PREEMPT

@@ -1765,9 +1768,6 @@ void init_kmem_cache_cpus(struct kmem_ca
 	for_each_possible_cpu(cpu)
 		per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
 }
-/*
- * Remove the cpu slab
- */
 
 /*
  * Remove the cpu slab

@@ -2116,7 +2116,7 @@ load_freelist:
 	return object;
 
 new_slab:
-	page = get_partial(s, gfpflags, node);
+	page = get_partial(s, gfpflags, node, c);
 	if (page) {
 		stat(s, ALLOC_FROM_PARTIAL);
 		object = c->freelist;

Index: linux-2.6/mm/slub.c
===================================================================
@@ -1554,9 +1554,11 @@ static inline void remove_partial(struct
  * Lock slab, remove from the partial list and put the object into the
  * per cpu freelist.
  *
+ * Returns a list of objects or NULL if it fails.
+ *
  * Must hold list_lock.
  */
-static inline int acquire_slab(struct kmem_cache *s,
+static inline void *acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page,
 		struct kmem_cache_cpu *c)
 {

@@ -1587,10 +1589,11 @@ static inline int acquire_slab(struct km
 
 	if (freelist) {
 		/* Populate the per cpu freelist */
-		c->freelist = freelist;
 		c->page = page;
 		c->node = page_to_nid(page);
-		return 1;
+		stat(s, ALLOC_FROM_PARTIAL);
+
+		return freelist;
 	} else {
 		/*
 		 * Slab page came from the wrong list. No object to allocate

@@ -1599,17 +1602,18 @@ static inline int acquire_slab(struct km
 		 */
 		printk(KERN_ERR "SLUB: %s : Page without available objects on"
 			" partial list\n", s->name);
-		return 0;
+		return NULL;
 	}
 }
 
 /*
  * Try to allocate a partial slab from a specific node.
  */
-static struct page *get_partial_node(struct kmem_cache *s,
+static void *get_partial_node(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct kmem_cache_cpu *c)
 {
 	struct page *page;
+	void *object;
 
 	/*
 	 * Racy check. If we mistakenly see no partial slabs then we

@@ -1621,13 +1625,15 @@ static struct page *get_partial_node(str
 		return NULL;
 
 	spin_lock(&n->list_lock);
-	list_for_each_entry(page, &n->partial, lru)
-		if (acquire_slab(s, n, page, c))
+	list_for_each_entry(page, &n->partial, lru) {
+		object = acquire_slab(s, n, page, c);
+		if (object)
 			goto out;
-	page = NULL;
+	}
+	object = NULL;
 out:
 	spin_unlock(&n->list_lock);
-	return page;
+	return object;
 }
 
 /*

@@ -1641,7 +1647,7 @@ static struct page *get_any_partial(stru
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
-	struct page *page;
+	void *object;
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between

@@ -1674,10 +1680,10 @@ static struct page *get_any_partial(stru
 
 		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
 				n->nr_partial > s->min_partial) {
-			page = get_partial_node(s, n, c);
-			if (page) {
+			object = get_partial_node(s, n, c);
+			if (object) {
 				put_mems_allowed();
-				return page;
+				return object;
 			}
 		}
 	}

@@ -1689,15 +1695,15 @@ static struct page *get_any_partial(stru
 /*
  * Get a partial page, lock it and return it.
  */
-static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node,
+static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 		struct kmem_cache_cpu *c)
 {
-	struct page *page;
+	void *object;
 	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
-	page = get_partial_node(s, get_node(s, searchnode), c);
-	if (page || node != NUMA_NO_NODE)
-		return page;
+	object = get_partial_node(s, get_node(s, searchnode), c);
+	if (object || node != NUMA_NO_NODE)
+		return object;
 
 	return get_any_partial(s, flags, c);
 }

@@ -2027,6 +2033,35 @@ slab_out_of_memory(struct kmem_cache *s,
 	}
 }
 
+static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
+			int node, struct kmem_cache_cpu **pc)
+{
+	void *object;
+	struct kmem_cache_cpu *c;
+	struct page *page = new_slab(s, flags, node);
+
+	if (page) {
+		c = __this_cpu_ptr(s->cpu_slab);
+		if (c->page)
+			flush_slab(s, c);
+
+		/*
+		 * No other reference to the page yet so we can
+		 * muck around with it freely without cmpxchg
+		 */
+		object = page->freelist;
+		page->freelist = NULL;
+
+		stat(s, ALLOC_SLAB);
+		c->node = page_to_nid(page);
+		c->page = page;
+		*pc = c;
+	} else
+		object = NULL;
+
+	return object;
+}
+
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.

@@ -2049,7 +2084,6 @@ static void *__slab_alloc(struct kmem_ca
 			  unsigned long addr, struct kmem_cache_cpu *c)
 {
 	void **object;
-	struct page *page;
 	unsigned long flags;
 	struct page new;
 	unsigned long counters;

@@ -2064,8 +2098,7 @@ static void *__slab_alloc(struct kmem_ca
 	c = this_cpu_ptr(s->cpu_slab);
 #endif
 
-	page = c->page;
-	if (!page)
+	if (!c->page)
 		goto new_slab;
 
 	if (unlikely(!node_match(c, node))) {

@@ -2077,8 +2110,8 @@ static void *__slab_alloc(struct kmem_ca
 	stat(s, ALLOC_SLOWPATH);
 
 	do {
-		object = page->freelist;
-		counters = page->counters;
+		object = c->page->freelist;
+		counters = c->page->counters;
 		new.counters = counters;
 		VM_BUG_ON(!new.frozen);
 

@@ -2090,12 +2123,12 @@ static void *__slab_alloc(struct kmem_ca
 		 *
 		 * If there are objects left then we retrieve them
 		 * and use them to refill the per cpu queue.
-		*/
+		 */
 
-		new.inuse = page->objects;
+		new.inuse = c->page->objects;
 		new.frozen = object != NULL;
 
-	} while (!__cmpxchg_double_slab(s, page,
+	} while (!__cmpxchg_double_slab(s, c->page,
 			object, counters,
 			NULL, new.counters,
 			"__slab_alloc"));

@@ -2109,53 +2142,33 @@ static void *__slab_alloc(struct kmem_ca
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
-	VM_BUG_ON(!page->frozen);
 	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);
 	return object;
 
 new_slab:
-	page = get_partial(s, gfpflags, node, c);
-	if (page) {
-		stat(s, ALLOC_FROM_PARTIAL);
-		object = c->freelist;
+	object = get_partial(s, gfpflags, node, c);
 
-		if (kmem_cache_debug(s))
-			goto debug;
-		goto load_freelist;
-	}
+	if (unlikely(!object)) {
 
-	page = new_slab(s, gfpflags, node);
+		object = new_slab_objects(s, gfpflags, node, &c);
 
-	if (page) {
-		c = __this_cpu_ptr(s->cpu_slab);
-		if (c->page)
-			flush_slab(s, c);
+		if (unlikely(!object)) {
+			if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+				slab_out_of_memory(s, gfpflags, node);
 
-		/*
-		 * No other reference to the page yet so we can
-		 * muck around with it freely without cmpxchg
-		 */
-		object = page->freelist;
-		page->freelist = NULL;
-
-		stat(s, ALLOC_SLAB);
-		c->node = page_to_nid(page);
-		c->page = page;
+			local_irq_restore(flags);
+			return NULL;
+		}
+	}
 
-		if (kmem_cache_debug(s))
-			goto debug;
+	if (likely(!kmem_cache_debug(s)))
 		goto load_freelist;
-	}
-	if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
-		slab_out_of_memory(s, gfpflags, node);
-	local_irq_restore(flags);
-	return NULL;
 
-debug:
-	if (!object || !alloc_debug_processing(s, page, object, addr))
-		goto new_slab;
+	/* Only entered in the debug case */
+	if (!alloc_debug_processing(s, c->page, object, addr))
+		goto new_slab;	/* Slab failed checks. Next slab needed */
 
 	c->freelist = get_freepointer(s, object);
 	deactivate_slab(s, c);

Index: linux-2.6/include/linux/slub_def.h
===================================================================
@@ -36,6 +36,8 @@ enum stat_item {
 	ORDER_FALLBACK,		/* Number of times fallback was necessary */
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
 	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
+	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
+	CPU_PARTIAL_FREE,	/* USed cpu partial on free */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {

@@ -46,6 +48,7 @@ struct kmem_cache_cpu {
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
 #endif
+	struct page *partial[];	/* Partially allocated frozen slabs */
 };
 
 struct kmem_cache_node {

@@ -79,6 +82,7 @@ struct kmem_cache {
 	int size;		/* The size of an object including meta data */
 	int objsize;		/* The size of an object without meta data */
 	int offset;		/* Free pointer offset. */
+	int cpu_partial;	/* Number of per cpu partial pages to keep around */
 	struct kmem_cache_order_objects oo;
 
 	/* Allocation and freeing of slabs */

504 lines not on this page · raw message

Index: linux-2.6/include/linux/slub_def.h
===================================================================
@@ -36,12 +36,15 @@ enum stat_item {
 	ORDER_FALLBACK,		/* Number of times fallback was necessary */
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
 	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
+	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
+	CPU_PARTIAL_FREE,	/* USed cpu partial on free */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {
 	void **freelist;	/* Pointer to next available object */
 	unsigned long tid;	/* Globally unique transaction id */
 	struct page *page;	/* The slab from which we are allocating */
+	struct page *partial;	/* Partially allocated frozen slabs */
 	int node;		/* The node of the page (or -1 for debug) */
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];

@@ -79,6 +82,7 @@ struct kmem_cache {
 	int size;		/* The size of an object including meta data */
 	int objsize;		/* The size of an object without meta data */
 	int offset;		/* Free pointer offset. */
+	int cpu_partial;	/* Number of per cpu partial pages to keep around */
 	struct kmem_cache_order_objects oo;
 
 	/* Allocation and freeing of slabs */

474 lines not on this page · raw message

Index: linux-2.6/include/linux/mm_types.h
===================================================================
@@ -79,9 +79,16 @@ struct page {
 	};
 
 	/* Third double word block */
-	struct list_head lru;		/* Pageout list, eg. active_list
+	union {
+		struct list_head lru;	/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
 					 */
+		struct {		/* SLUB pages in frozen state */
+			struct page *next;	/* Next partial slab */
+			short int pages;	/* Nr of partial slabs left */
+			short int pobjects;	/* Approximate # of objects */
+		};
+	};
 
 	/* Remainder is not double word aligned */
 	union {

Index: linux-2.6/tools/slub/slabinfo.c
===================================================================
@@ -42,6 +42,7 @@ struct slabinfo {
 	unsigned long deactivate_remote_frees, order_fallback;
 	unsigned long cmpxchg_double_cpu_fail, cmpxchg_double_fail;
 	unsigned long alloc_node_mismatch, deactivate_bypass;
+	unsigned long cpu_partial_alloc, cpu_partial_free;
 	int numa[MAX_NODES];
 	int numa_partial[MAX_NODES];
 } slabinfo[MAX_SLABS];

@@ -455,6 +456,11 @@ static void slab_stats(struct slabinfo *
 		s->alloc_from_partial * 100 / total_alloc,
 		s->free_remove_partial * 100 / total_free);
 
+	printf("Cpu partial list     %8lu %8lu %3lu %3lu\n",
+		s->cpu_partial_alloc, s->cpu_partial_free,
+		s->cpu_partial_alloc * 100 / total_alloc,
+		s->cpu_partial_free * 100 / total_free);
+
 	printf("RemoteObj/SlabFrozen %8lu %8lu %3lu %3lu\n",
 		s->deactivate_remote_frees, s->free_frozen,
 		s->deactivate_remote_frees * 100 / total_alloc,

@@ -1209,6 +1215,8 @@ static void read_slab_dir(void)
 			slab->order_fallback = get_obj("order_fallback");
 			slab->cmpxchg_double_cpu_fail = get_obj("cmpxchg_double_cpu_fail");
 			slab->cmpxchg_double_fail = get_obj("cmpxchg_double_fail");
+			slab->cpu_partial_alloc = get_obj("cpu_partial_alloc");
+			slab->cpu_partial_free = get_obj("cpu_partial_free");
 			slab->alloc_node_mismatch = get_obj("alloc_node_mismatch");
 			slab->deactivate_bypass = get_obj("deactivate_bypass");
 			chdir("..");