sched/numa: Increment numa_migrate_seq when task runs in correct location
authorRik van Riel <riel@redhat.com>
Mon, 7 Oct 2013 10:29:12 +0000 (11:29 +0100)
committerIngo Molnar <mingo@kernel.org>
Wed, 9 Oct 2013 10:40:41 +0000 (12:40 +0200)
When a task is already running on its preferred node, increment
numa_migrate_seq to indicate that the task is settled if migration is
temporarily disabled, and memory should migrate towards it.

Signed-off-by: Rik van Riel <riel@redhat.com>
[ Only increment migrate_seq if migration temporarily disabled. ]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-35-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/sched/fair.c

index f84ac3fb581bd6d847c7dac34ae7e6d3a7a029e5..de9b4d8eb853bd2230488a1601608d487812c195 100644 (file)
@@ -1016,8 +1016,16 @@ static void numa_migrate_preferred(struct task_struct *p)
 {
        /* Success if task is already running on preferred CPU */
        p->numa_migrate_retry = 0;
-       if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+       if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid) {
+               /*
+                * If migration is temporarily disabled due to a task migration
+                * then re-enable it now as the task is running on its
+                * preferred node and memory should migrate locally
+                */
+               if (!p->numa_migrate_seq)
+                       p->numa_migrate_seq++;
                return;
+       }
 
        /* This task has no NUMA fault statistics yet */
        if (unlikely(p->numa_preferred_nid == -1))