From ba7e5a279e72f4b246dc7a419ac707e1936ede3e Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 4 Sep 2014 16:35:30 -0400 Subject: [PATCH] sched/numa: Use select_idle_sibling() to select a destination for task_numa_move() The code in task_numa_compare() will only examine at most one idle CPU per node, because they all have the same score. However, some idle CPUs are better candidates than others, due to busy or idle SMT siblings, etc... The scheduler has logic to find the best CPU within an LLC to place a task. The NUMA code should probably use it. This seems to reduce the standard deviation for single instance SPECjbb2005 with a low warehouse count on my 4 node test system. Signed-off-by: Rik van Riel Signed-off-by: Peter Zijlstra (Intel) Cc: mgorman@suse.de Cc: Mike Galbraith Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140904163530.189d410a@cuia.bos.redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index be9e97b0d76f..96e7147044bb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -665,6 +665,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP +static int select_idle_sibling(struct task_struct *p, int cpu); static unsigned long task_h_load(struct task_struct *p); static inline void __update_task_entity_contrib(struct sched_entity *se); @@ -1257,6 +1258,13 @@ balance: if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; + /* + * One idle CPU per node is evaluated for a task numa move. + * Call select_idle_sibling to maybe find a better one. + */ + if (!cur) + env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); + assign: task_numa_assign(env, cur, imp); unlock: -- 2.20.1