cpusets: randomize node rotor used in cpuset_mem_spread_node()

Some workloads that create a large number of small files tend to assign
too many pages to node 0 (multi-node systems).  Part of the reason is that
the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at
node 0 for newly created tasks.

This patch changes the rotor to be initialized to a random node number of
the cpuset.

[[email protected]: fix layout]
[[email protected]: Define stub numa_random() for !NUMA configuration]
Signed-off-by: Jack Steiner <[email protected]>
Signed-off-by: Lee Schermerhorn <[email protected]>
Cc: 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]>

arch/x86/mm/numa.c

@@ -2,6 +2,7 @@
 #include <linux/topology.h>
 #include <linux/module.h>
 #include <linux/bootmem.h>
+#include <linux/random.h>
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 # define DBG(x...) printk(KERN_DEBUG x)
@@ -65,3 +66,19 @@ const struct cpumask *cpumask_of_node(int node)
 }
 EXPORT_SYMBOL(cpumask_of_node);
 #endif
+
+/*
+ * Return the bit number of a random bit set in the nodemask.
+ *   (returns -1 if nodemask is empty)
+ */
+int __node_random(const nodemask_t *maskp)
+{
+	int w, bit = -1;
+
+	w = nodes_weight(*maskp);
+	if (w)
+		bit = bitmap_ord_to_pos(maskp->bits,
+			get_random_int() % w, MAX_NUMNODES);
+	return bit;
+}
+EXPORT_SYMBOL(__node_random);

include/linux/bitmap.h

@@ -141,6 +141,7 @@ extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order);
 extern void bitmap_release_region(unsigned long *bitmap, int pos, int order);
 extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order);
 extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
+extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
 
 #define BITMAP_LAST_WORD_MASK(nbits)					\
 (									\

include/linux/nodemask.h

@@ -66,6 +66,8 @@
  * int num_online_nodes()		Number of online Nodes
  * int num_possible_nodes()		Number of all possible Nodes
  *
+ * int node_random(mask)		Random node with set bit in mask
+ *
  * int node_online(node)		Is some node online?
  * int node_possible(node)		Is some node possible?
  *
@@ -430,6 +432,10 @@ static inline void node_set_offline(int nid)
 	node_clear_state(nid, N_ONLINE);
 	nr_online_nodes = num_node_state(N_ONLINE);
 }
+
+#define node_random(mask) __node_random(&(mask))
+extern int __node_random(const nodemask_t *maskp);
+
 #else
 
 static inline int node_state(int node, enum node_states state)
@@ -460,6 +466,8 @@ static inline int num_node_state(enum node_states state)
 
 #define node_set_online(node)	   node_set_state((node), N_ONLINE)
 #define node_set_offline(node)	   node_clear_state((node), N_ONLINE)
+
+static inline int node_random(const nodemask_t mask) { return 0; }
 #endif
 
 #define node_online_map 	node_states[N_ONLINE]

kernel/fork.c

@@ -1079,6 +1079,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
  	}
 	mpol_fix_fork_child_flag(p);
 #endif
+#ifdef CONFIG_CPUSETS
+	p->cpuset_mem_spread_rotor = node_random(p->mems_allowed);
+	p->cpuset_slab_spread_rotor = node_random(p->mems_allowed);
+#endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW

lib/bitmap.c

@@ -672,7 +672,7 @@ static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
  *
  * The bit positions 0 through @bits are valid positions in @buf.
  */
-static int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
+int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
 {
 	int pos = 0;