cpusets: new round-robin rotor for SLAB allocations

We have observed several workloads running on multi-node systems where
memory is assigned unevenly across the nodes in the system.  There are
numerous reasons for this but one is the round-robin rotor in
cpuset_mem_spread_node().

For example, a simple test that writes a multi-page file will allocate
pages on nodes 0 2 4 6 ...  Odd nodes are skipped.  (Sometimes it
allocates on odd nodes & skips even nodes).

An example is shown below.  The program "lfile" writes a file consisting
of 10 pages.  The program then mmaps the file & uses get_mempolicy(...,
MPOL_F_NODE) to determine the nodes where the file pages were allocated.
The output is shown below:

	# ./lfile
	 allocated on nodes: 2 4 6 0 1 2 6 0 2

There is a single rotor that is used for allocating both file pages & slab
pages.  Writing the file allocates both a data page & a slab page
(buffer_head).  This advances the RR rotor 2 nodes for each page
allocated.

A quick confirmation seems to confirm this is the cause of the uneven
allocation:

	# echo 0 >/dev/cpuset/memory_spread_slab
	# ./lfile
	 allocated on nodes: 6 7 8 9 0 1 2 3 4 5

This patch introduces a second rotor that is used for slab allocations.

Signed-off-by: Jack Steiner <[email protected]>
Acked-by: Christoph Lameter <[email protected]>
Cc: Pekka Enberg <[email protected]>
Cc: Paul Menage <[email protected]>
Cc: Jack Steiner <[email protected]>
Cc: Robin Holt <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/cpuset.h

@@ -69,6 +69,7 @@ extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
 
 extern int cpuset_mem_spread_node(void);
+extern int cpuset_slab_spread_node(void);
 
 static inline int cpuset_do_page_mem_spread(void)
 {
@@ -194,6 +195,11 @@ static inline int cpuset_mem_spread_node(void)
 	return 0;
 }
 
+static inline int cpuset_slab_spread_node(void)
+{
+	return 0;
+}
+
 static inline int cpuset_do_page_mem_spread(void)
 {
 	return 0;

include/linux/sched.h

@@ -1423,6 +1423,7 @@ struct task_struct {
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
 	int mems_allowed_change_disable;
 	int cpuset_mem_spread_rotor;
+	int cpuset_slab_spread_rotor;
 #endif
 #ifdef CONFIG_CGROUPS
 	/* Control Group info protected by css_set_lock */

kernel/cpuset.c

@@ -2469,7 +2469,8 @@ void cpuset_unlock(void)
 }
 
 /**
- * cpuset_mem_spread_node() - On which node to begin search for a page
+ * cpuset_mem_spread_node() - On which node to begin search for a file page
+ * cpuset_slab_spread_node() - On which node to begin search for a slab page
  *
  * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
  * tasks in a cpuset with is_spread_page or is_spread_slab set),
@@ -2494,16 +2495,27 @@ void cpuset_unlock(void)
  * See kmem_cache_alloc_node().
  */
 
-int cpuset_mem_spread_node(void)
+static int cpuset_spread_node(int *rotor)
 {
 	int node;
 
-	node = next_node(current->cpuset_mem_spread_rotor, current->mems_allowed);
+	node = next_node(*rotor, current->mems_allowed);
 	if (node == MAX_NUMNODES)
 		node = first_node(current->mems_allowed);
-	current->cpuset_mem_spread_rotor = node;
+	*rotor = node;
 	return node;
 }
+
+int cpuset_mem_spread_node(void)
+{
+	return cpuset_spread_node(&current->cpuset_mem_spread_rotor);
+}
+
+int cpuset_slab_spread_node(void)
+{
+	return cpuset_spread_node(&current->cpuset_slab_spread_rotor);
+}
+
 EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
 
 /**

mm/slab.c

@@ -3219,7 +3219,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	nid_alloc = nid_here = numa_node_id();
 	get_mems_allowed();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
-		nid_alloc = cpuset_mem_spread_node();
+		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
 		nid_alloc = slab_node(current->mempolicy);
 	put_mems_allowed();