[PATCH v3] mm: SLAB Out-of-memory diagnostics

[Rafael Aquini]

Following the example at mm/slub.c, add out-of-memory diagnostics to the
SLAB allocator to help on debugging certain OOM conditions.

An example print out looks like this:

  <snip page allocator out-of-memory message>
  SLAB: Unable to allocate memory on node 0 (gfp=0x11200)
    cache: bio-0, object size: 192, order: 0
    node 0: slabs: 3/3, objs: 60/60, free: 0

Signed-off-by: Rafael Aquini <aquini@xxxxxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
---
v2:
* drop the sysctl knob to override __GFP_NOWARN allocation flag (Pekka, David)

v3:
* adjust the print output to match slub's warning printout (WANG Cong)

 mm/slab.c |   51 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 50 insertions(+), 1 deletions(-)

diff --git a/mm/slab.c b/mm/slab.c
index f0bd785..cda1ff6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1731,6 +1731,52 @@ static int __init cpucache_init(void)
 }
 __initcall(cpucache_init);
 
+static noinline void
+slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
+{
+	struct kmem_list3 *l3;
+	struct slab *slabp;
+	unsigned long flags;
+	int node;
+
+	printk(KERN_WARNING
+		"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
+		nodeid, gfpflags);
+	printk(KERN_WARNING "  cache: %s, object size: %d, order: %d\n",
+		cachep->name, cachep->buffer_size, cachep->gfporder);
+
+	for_each_online_node(node) {
+		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
+		unsigned long active_slabs = 0, num_slabs = 0;
+
+		l3 = cachep->nodelists[node];
+		if (!l3)
+			continue;
+
+		spin_lock_irqsave(&l3->list_lock, flags);
+		list_for_each_entry(slabp, &l3->slabs_full, list) {
+			active_objs += cachep->num;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_partial, list) {
+			active_objs += slabp->inuse;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_free, list)
+			num_slabs++;
+
+		free_objects += l3->free_objects;
+		spin_unlock_irqrestore(&l3->list_lock, flags);
+
+		num_slabs += active_slabs;
+		num_objs = num_slabs * cachep->num;
+		printk(KERN_WARNING
+			"  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
+			node, active_slabs, num_slabs, active_objs, num_objs,
+			free_objects);
+	}
+}
+
 /*
  * Interface to system's page allocator. No need to hold the cache-lock.
  *
@@ -1757,8 +1803,11 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		flags |= __GFP_RECLAIMABLE;
 
 	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
-	if (!page)
+	if (!page) {
+		if (!(flags & __GFP_NOWARN) && printk_ratelimit())
+			slab_out_of_memory(cachep, flags, nodeid);
 		return NULL;
+	}
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-- 
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/