Messages in this thread Patch in this message | | | From | byungchul.park@lge ... | Subject | [PATCH v3 3/5] sched: sync a se with prev cfs_rq when changing cgroup | Date | Wed, 19 Aug 2015 15:47:14 +0900 |
| |
From: Byungchul Park <byungchul.park@lge.com>
current code is wrong with cfs_rq's average load when changing a task's 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 changing 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 cgroup.
Signed-off-by: Byungchul Park <byungchul.park@lge.com> --- kernel/sched/fair.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 191d9be..1be042a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8040,8 +8040,14 @@ 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 */ + detach_entity_load_avg(cfs_rq, se); +#endif set_task_rq(p, task_cpu(p)); se->depth = se->parent ? se->parent->depth + 1 : 0; cfs_rq = cfs_rq_of(se); -- 1.7.9.5
| |