summaryrefslogtreecommitdiffstats
path: root/kernel/cpuset.c
diff options
context:
space:
mode:
authorJack Steiner <steiner@sgi.com>2010-05-26 14:42:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-27 09:12:44 -0700
commit6adef3ebe570bcde67fd6c16101451ddde5712b5 (patch)
tree0f60e2a4d01850ae33aee6cefc7a59845ede89a0 /kernel/cpuset.c
parent2c488db27b614816024e7994117f599337de0f34 (diff)
downloadlinux-6adef3ebe570bcde67fd6c16101451ddde5712b5.tar.gz
linux-6adef3ebe570bcde67fd6c16101451ddde5712b5.tar.bz2
linux-6adef3ebe570bcde67fd6c16101451ddde5712b5.zip
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 <steiner@sgi.com> Acked-by: 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>
Diffstat (limited to 'kernel/cpuset.c')
-rw-r--r--kernel/cpuset.c20
1 files changed, 16 insertions, 4 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 61d6af7fa676..02b9611eadde 100644
--- a/kernel/cpuset.c
+++ b/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);
/**