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.

[akpm@linux-foundation.org: fix layout]
[Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration]
Signed-off-by: Jack Steiner <steiner@sgi.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Paul Menage <menage@google.com>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Conflicts:

	arch/x86/mm/numa.c

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index ebcef8d01f4b34dc57a28cafa9b10d028973a649..4a09007994ab9f3933f5029fa16f5e1935320569 100644 (file)
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -11,6 +11,7 @@
 #include <linux/nodemask.h>
 #include <linux/sched.h>
 #include <linux/topology.h>
+#include <linux/random.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
@@ -826,3 +827,19 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #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);

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index dcafe0bf0005ac11e10dbcb0f3cc6f756221e60e..3bac44cce142c94f2a5d40ab5699a07bd7aff59f 100644 (file)
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -144,6 +144,7 @@ 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)                                   \
 (                                                                      \

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index dba35e413371e599045d41134003a1ef8713fd38..8a8f1d09c1336dce6076335b5a181c5bfc131120 100644 (file)
--- a/include/linux/nodemask.h
+++ b/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]

diff --git a/kernel/fork.c b/kernel/fork.c
index 4712e3e5578e17544552d49f91e3960358a44a72..9352dc2696144f31cd12cd1b37eabbb627567dbe 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1179,6 +1179,10 @@ 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

diff --git a/lib/bitmap.c b/lib/bitmap.c
index 3f3b68199d744bd4fc9b94dcb9ca6e831502b0f2..37ef4b048795463a46a98702fd5bf780c1b59060 100644 (file)
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -756,7 +756,7 @@ 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;