[PATCH v4] sched: sync with the prev cfs when changing cgroup within a cpu

[Byungchul Park]

current code seems to be wrong with cfs_rq's avg loads when changing
a task's cgroup(=cfs_rq) to another. i tested with "echo pid > cgroup" and
found that e.g. cfs_rq->avg.load_avg became larger and larger whenever i
changed a cgroup to another again and again.

we have to sync se's average load with both *prev* cfs_rq and next cfs_rq
when changing its group.

Signed-off-by: Byungchul Park <byungchul.park@xxxxxxx>
---
 kernel/sched/fair.c |   34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2a33d7b..979ca2c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8017,23 +8017,37 @@ static void task_move_group_fair(struct task_struct *p, int queued)
 	if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING))
 		queued = 1;
 
+	cfs_rq = cfs_rq_of(se);
 	if (!queued)
-		se->vruntime -= cfs_rq_of(se)->min_vruntime;
+		se->vruntime -= cfs_rq->min_vruntime;
+
+#ifdef CONFIG_SMP
+	/* synchronize task with its prev cfs_rq */
+	if (!queued)
+		__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+				&se->avg, se->on_rq * scale_load_down(se->load.weight),
+				cfs_rq->curr == se, NULL);
+
+	/* remove our load when we leave */
+	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
+	cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
+	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
+	cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+#endif
 	set_task_rq(p, task_cpu(p));
 	se->depth = se->parent ? se->parent->depth + 1 : 0;
-	if (!queued) {
-		cfs_rq = cfs_rq_of(se);
+	cfs_rq = cfs_rq_of(se);
+	if (!queued)
 		se->vruntime += cfs_rq->min_vruntime;
 
 #ifdef CONFIG_SMP
-		/* Virtually synchronize task with its new cfs_rq */
-		p->se.avg.last_update_time = cfs_rq->avg.last_update_time;
-		cfs_rq->avg.load_avg += p->se.avg.load_avg;
-		cfs_rq->avg.load_sum += p->se.avg.load_sum;
-		cfs_rq->avg.util_avg += p->se.avg.util_avg;
-		cfs_rq->avg.util_sum += p->se.avg.util_sum;
+	/* Virtually synchronize task with its new cfs_rq */
+	p->se.avg.last_update_time = cfs_rq->avg.last_update_time;
+	cfs_rq->avg.load_avg += p->se.avg.load_avg;
+	cfs_rq->avg.load_sum += p->se.avg.load_sum;
+	cfs_rq->avg.util_avg += p->se.avg.util_avg;
+	cfs_rq->avg.util_sum += p->se.avg.util_sum;
 #endif
-	}
 }
 
 void free_fair_sched_group(struct task_group *tg)
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/