From db015daedb56251b73f956f70b3b8813f80d8ee1 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 23 Jun 2014 11:41:34 -0400 Subject: [PATCH] sched/numa: Rework best node setting in task_numa_migrate() Fix up the best node setting in task_numa_migrate() to deal with a task in a pseudo-interleaved NUMA group, which is already running in the best location. Set the task's preferred nid to the current nid, so task migration is not retried at a high rate. Signed-off-by: Rik van Riel Cc: mgorman@suse.de Cc: chegu_vinod@hp.com Cc: Linus Torvalds Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1403538095-31256-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9d1734a..7bb2f46 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1354,10 +1354,6 @@ static int task_numa_migrate(struct task_struct *p) } } - /* No better CPU than the current one was found. */ - if (env.best_cpu == -1) - return -EAGAIN; - /* * If the task is part of a workload that spans multiple NUMA nodes, * and is migrating into one of the workload's active nodes, remember @@ -1366,8 +1362,19 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes)) - sched_setnuma(p, env.dst_nid); + if (p->numa_group) { + if (env.best_cpu == -1) + nid = env.src_nid; + else + nid = env.dst_nid; + + if (node_isset(nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); + } + + /* No better CPU than the current one was found. */ + if (env.best_cpu == -1) + return -EAGAIN; /* * Reset the scan period if the task is being rescheduled on an -- 2.7.4