From 13ede33150877d44756171e33570076882b17b0b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 20 May 2022 11:35:17 +0100 Subject: sched/numa: Do not swap tasks between nodes when spare capacity is available If a destination node has spare capacity but there is an imbalance then two tasks are selected for swapping. If the tasks have no numa group or are within the same NUMA group, it's simply shuffling tasks around without having any impact on the compute imbalance. Instead, it's just punishing one task to help another. Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Tested-by: K Prateek Nayak Link: https://lore.kernel.org/r/20220520103519.1863-3-mgorman@techsingularity.net --- kernel/sched/fair.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 51836efe5931..23da36c9cacb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1790,6 +1790,15 @@ static bool task_numa_compare(struct task_numa_env *env, */ cur_ng = rcu_dereference(cur->numa_group); if (cur_ng == p_ng) { + /* + * Do not swap within a group or between tasks that have + * no group if there is spare capacity. Swapping does + * not address the load imbalance and helps one task at + * the cost of punishing another. + */ + if (env->dst_stats.node_type == node_has_spare) + goto unlock; + imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* -- cgit v1.2.3