sched: Add SD_PREFER_SIBLING

Do the placement thing using SD flags.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083825.897028974@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 13 insertions, 1 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 584a122b553c..9d64cec9ae1d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3811,9 +3811,13 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         const struct cpumask *cpus, int *balance,
                         struct sd_lb_stats *sds)
 {
+        struct sched_domain *child = sd->child;
         struct sched_group *group = sd->groups;
         struct sg_lb_stats sgs;
-        int load_idx;
+        int load_idx, prefer_sibling = 0;
+
+        if (child && child->flags & SD_PREFER_SIBLING)
+                prefer_sibling = 1;
 
         init_sd_power_savings_stats(sd, sds, idle);
         load_idx = get_sd_load_idx(sd, idle);
@@ -3833,6 +3837,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                 sds->total_load += sgs.group_load;
                 sds->total_pwr += group->__cpu_power;
 
+                /*
+                 * In case the child domain prefers tasks go to siblings
+                 * first, lower the group capacity to one so that we'll try
+                 * and move all the excess tasks away.
+                 */
+                if (prefer_sibling)
+                        sgs.group_capacity = 1;
+
                 if (local_group) {
                         sds->this_load = sgs.avg_load;
                         sds->this = group;