sched/numa: Always try to migrate to preferred node at task_numa_placement() time
authorRik van Riel <riel@redhat.com>
Wed, 4 Jun 2014 20:33:15 +0000 (16:33 -0400)
committerIngo Molnar <mingo@kernel.org>
Wed, 18 Jun 2014 16:29:58 +0000 (18:29 +0200)
commitbb97fc31647539f1f102eed646a95e200160a150
tree69a009dd0824b95572aab9c622357c032ea3c1cc
parenta43455a1d572daf7b730fe12eb747d1e17411365
sched/numa: Always try to migrate to preferred node at task_numa_placement() time

It is possible that at task_numa_placement() time, the task's
numa_preferred_nid does not change, but the task is not
actually running on the preferred node at the time.

In that case, we still want to attempt migration to the
preferred node.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140604163315.1dbc7b56@cuia.bos.redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/sched/fair.c