[PATCH 51/63] sched: numa: Prevent parallel updates to group stats during placement

From: Mel Gorman
Date: Mon Oct 07 2013 - 06:31:59 EST


Having multiple tasks in a group go through task_numa_placement
simultaneously can lead to a task picking a wrong node to run on, because
the group stats may be in the middle of an update. This patch avoids
parallel updates by holding the numa_group lock during placement
decisions.

Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
---
kernel/sched/fair.c | 35 +++++++++++++++++++++++------------
1 file changed, 23 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d5873e5..dc0c376 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1233,6 +1233,7 @@ static void task_numa_placement(struct task_struct *p)
{
int seq, nid, max_nid = -1, max_group_nid = -1;
unsigned long max_faults = 0, max_group_faults = 0;
+ spinlock_t *group_lock = NULL;

seq = ACCESS_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
@@ -1241,6 +1242,12 @@ static void task_numa_placement(struct task_struct *p)
p->numa_migrate_seq++;
p->numa_scan_period_max = task_scan_max(p);

+ /* If the task is part of a group prevent parallel updates to group stats */
+ if (p->numa_group) {
+ group_lock = &p->numa_group->lock;
+ spin_lock(group_lock);
+ }
+
/* Find the node with the highest number of faults */
for_each_online_node(nid) {
unsigned long faults = 0, group_faults = 0;
@@ -1279,20 +1286,24 @@ static void task_numa_placement(struct task_struct *p)
}
}

- /*
- * If the preferred task and group nids are different,
- * iterate over the nodes again to find the best place.
- */
- if (p->numa_group && max_nid != max_group_nid) {
- unsigned long weight, max_weight = 0;
-
- for_each_online_node(nid) {
- weight = task_weight(p, nid) + group_weight(p, nid);
- if (weight > max_weight) {
- max_weight = weight;
- max_nid = nid;
+ if (p->numa_group) {
+ /*
+ * If the preferred task and group nids are different,
+ * iterate over the nodes again to find the best place.
+ */
+ if (max_nid != max_group_nid) {
+ unsigned long weight, max_weight = 0;
+
+ for_each_online_node(nid) {
+ weight = task_weight(p, nid) + group_weight(p, nid);
+ if (weight > max_weight) {
+ max_weight = weight;
+ max_nid = nid;
+ }
}
}
+
+ spin_unlock(group_lock);
}

/* Preferred node as the node with the most faults */
--
1.8.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/