summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMel Gorman <mgorman@techsingularity.net>2022-05-20 11:35:17 +0100
committerPeter Zijlstra <peterz@infradead.org>2022-06-13 10:29:59 +0200
commit13ede33150877d44756171e33570076882b17b0b (patch)
treec1ed544c0396affd5bb7a68be5e6e5cd01e34993
parent70ce3ea9aa4ed901c8a90de667df5ef307766e71 (diff)
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 <mgorman@techsingularity.net> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: K Prateek Nayak <kprateek.nayak@amd.com> Link: https://lore.kernel.org/r/20220520103519.1863-3-mgorman@techsingularity.net
-rw-r--r--kernel/sched/fair.c9
1 files changed, 9 insertions, 0 deletions
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);
/*