Re: [RFC PATCH 2/3] topology: support node_numa_mem() for determining the fallback node

[Christoph Lameter <cl@linux.com>]

Here is another patch with some fixes. The additional logic is only
compiled in if CONFIG_HAVE_MEMORYLESS_NODES is set.

Subject: slub: Memoryless node support

Support memoryless nodes by tracking which allocations are failing.
Allocations targeted to the nodes without memory fall back to the
current available per cpu objects and if that is not available will
create a new slab using the page allocator to fallback from the
memoryless node to some other node.

Signed-off-by: Christoph Lameter <cl@linux.com>

Index: linux/mm/slub.c
===================================================================
--- linux.orig/mm/slub.c	2014-02-12 16:07:48.957869570 -0600
+++ linux/mm/slub.c	2014-02-12 16:09:22.198928260 -0600
@@ -134,6 +134,10 @@ static inline bool kmem_cache_has_cpu_pa
 #endif
 }

+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+static nodemask_t empty_nodes;
+#endif
+
 /*
  * Issues still to be resolved:
  *
@@ -1405,16 +1409,28 @@ static struct page *new_slab(struct kmem
 	void *last;
 	void *p;
 	int order;
+	int alloc_node;

 	BUG_ON(flags & GFP_SLAB_BUG_MASK);

 	page = allocate_slab(s,
 		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
-	if (!page)
+	if (!page) {
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+		if (node != NUMA_NO_NODE)
+			node_set(node, empty_nodes);
+#endif
 		goto out;
+	}

 	order = compound_order(page);
-	inc_slabs_node(s, page_to_nid(page), page->objects);
+	alloc_node = page_to_nid(page);
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+	node_clear(alloc_node, empty_nodes);
+	if (node != NUMA_NO_NODE && alloc_node != node)
+		node_set(node, empty_nodes);
+#endif
+	inc_slabs_node(s, alloc_node, page->objects);
 	memcg_bind_pages(s, order);
 	page->slab_cache = s;
 	__SetPageSlab(page);
@@ -1722,7 +1738,7 @@ static void *get_partial(struct kmem_cac
 		struct kmem_cache_cpu *c)
 {
 	void *object;
-	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
+	int searchnode = (node == NUMA_NO_NODE) ? numa_mem_id() : node;

 	object = get_partial_node(s, get_node(s, searchnode), c, flags);
 	if (object || node != NUMA_NO_NODE)
@@ -2117,8 +2133,19 @@ static void flush_all(struct kmem_cache
 static inline int node_match(struct page *page, int node)
 {
 #ifdef CONFIG_NUMA
-	if (!page || (node != NUMA_NO_NODE && page_to_nid(page) != node))
+	int page_node = page_to_nid(page);
+
+	if (!page)
 		return 0;
+
+	if (node != NUMA_NO_NODE) {
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+		if (node_isset(node, empty_nodes))
+			return 1;
+#endif
+		if (page_node != node)
+			return 0;
+	}
 #endif
 	return 1;
 }

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>