Re: [PATCH v5 6/7] sched: consider runnable load average in move_tasks

[Alex Shi <alex.shi@intel.com>]

Paul,

I am wondering if the following patch needed.
The wakeuped migrated task will __synchronize_entity_decay(se); in migrate_task_fair,
then it needs to set `se->avg.last_runnable_update -= (-se->avg.decay_count) << 20'
before update_entity_load_avg, in order to avoid slept time is updated twice for 
se.avg.load_avg_contrib in both __syncchronize and update_entity_load_avg.

but if the slept task is waked up from self cpu, it miss the last_runnable_update before
 update_entity_load_avg(se, 0, 1), so the slept time was used twice in both functions.
Is that right?

Regards
Alex
---
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a80ae94..1b49e97 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1532,7 +1532,8 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
                }
                wakeup = 0;
        } else {
-               __synchronize_entity_decay(se);
+               se->avg.last_runnable_update += __synchronize_entity_decay(se)
+                                                       << 20;
        }
 
        /* migrated tasks did not contribute to our blocked load */
        if (wakeup) {
                subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib);                                                 
                update_entity_load_avg(se, 0, 1);                                                                                
        }


-- 
Thanks
    Alex