summaryrefslogtreecommitdiff
path: root/mm/mempolicy.c
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.cz>2011-07-26 16:08:30 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-07-26 16:49:43 -0700
commit778d3b0ff0654ad7092bf823fd32010066b12365 (patch)
treecd0073d8c513e1c56fd6950c4ec985f16fd004ad /mm/mempolicy.c
parent8521fc50d433507a7cdc96bec280f9e5888a54cc (diff)
downloadkernel-common-778d3b0ff0654ad7092bf823fd32010066b12365.tar.gz
kernel-common-778d3b0ff0654ad7092bf823fd32010066b12365.tar.bz2
kernel-common-778d3b0ff0654ad7092bf823fd32010066b12365.zip
cpusets: randomize node rotor used in cpuset_mem_spread_node()
[ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] 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] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.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> Cc: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: David Rientjes <rientjes@google.com> Cc: Jack Steiner <steiner@sgi.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Menage <menage@google.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r--mm/mempolicy.c16
1 files changed, 16 insertions, 0 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e7fb9d25c54e..8b57173c1dd5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -93,6 +93,7 @@
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
+#include <linux/random.h>
#include "internal.h"
@@ -1645,6 +1646,21 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
return interleave_nodes(pol);
}
+/*
+ * 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;
+}
+
#ifdef CONFIG_HUGETLBFS
/*
* huge_zonelist(@vma, @addr, @gfp_flags, @mpol)