[PATCH 2/2] sched,numa: fix numa capacity computation

[riel@redhat.com]

From: Rik van Riel <riel@redhat.com>

Commit c61037e9 fixes the phenomenon of 'fantom' cores due to
N*frac(smt_power) >= 1 by limiting the capacity to the actual
number of cores in the load balancing code.

This patch applies the same correction to the NUMA balancing
code.

Signed-off-by: Rik van Riel <riel@redhat.com>
---
 kernel/sched/fair.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 678ed03..376bc07c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1038,7 +1038,8 @@ struct numa_stats {
  */
 static void update_numa_stats(struct numa_stats *ns, int nid)
 {
-	int cpu, cpus = 0;
+	int smt, cpu, cpus = 0;
+	unsigned long capacity;
 
 	memset(ns, 0, sizeof(*ns));
 	for_each_cpu(cpu, cpumask_of_node(nid)) {
@@ -1062,8 +1063,12 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	if (!cpus)
 		return;
 
-	ns->task_capacity =
-		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE);
+	/* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */
+	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
+	capacity = cpus / smt; /* cores */
+
+	ns->task_capacity = min_t(unsigned, capacity,
+		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
 	ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
 }
 
-- 
1.9.3