Messages in this thread | | | From | Steve Muckle <> | Subject | PELT initial task load and wake_up_new_task() | Date | Fri, 11 Dec 2015 18:01:45 -0800 |
| |
In init_entity_runnable_average() the last_update_time is initialized to zero. The task is given max load and utilization as a pessimistic initial estimate.
But if in wake_up_new_task() the task is placed on a CPU other than where it was created, __update_load_avg() will be called via set_task_cpu() -> migrate_task_rq_fair() -> remove_entity_load_avg().
Since last_update_time is zero the delta will be huge and the task's load will be entirely decayed away before it is enqueued at the destination CPU.
If last_update_time is initialized to cfs_rq_clock_task() the load will not go away, but it will also then be subtracted from the original CPU in remove_entity_load_avg() if the task is placed on a different CPU, which is bad since it was never added there before.
Thinking about this more it seemed questionable to treat the assignment of a task to a new CPU in wake_up_new_task() as a migration given that the task has never executed previously. Would it make sense to call __set_task_cpu() there instead of set_task_cpu()?
thanks, Steve
| |