sched: Add SD_PREFER_LOCAL

And turn it on for NUMA and MC domains. This improves
locality in balancing decisions by keeping up to
capacity amount of tasks local before looking for idle
CPUs. (and twice the capacity if SD_POWERSAVINGS_BALANCE
is set.)

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 5 insertions, 2 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 280892e9d85..a37f311f436 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1360,7 +1360,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int flags)
                  * If power savings logic is enabled for a domain, see if we
                  * are not overloaded, if so, don't balance wider.
                  */
-                if (tmp->flags & SD_POWERSAVINGS_BALANCE) {
+                if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) {
                         unsigned long power = 0;
                         unsigned long nr_running = 0;
                         unsigned long capacity;
@@ -1373,7 +1373,10 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int flags)
 
                         capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
 
-                        if (nr_running/2 < capacity)
+                        if (tmp->flags & SD_POWERSAVINGS_BALANCE)
+                                nr_running /= 2;
+
+                        if (nr_running < capacity)
                                 break;
                 }