place_entity() update se->vruntime question | |
| [Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] | |
Hi all, when a process was wakeup by try_to_wake_up(),it will call activate_task()to move a task into the run queue,and the parameter "wakeup=1". enqueue_task_fair() will call enqueue_entity() to place the schedule entity to the proper cfs_rq.it will at last call place_entity() with parameter "initial=0". As my understanding,the waken up schedule entity has smaller vruntime than the cfs_rq->min_runtime.But the debug information show that's random. So i would like to ask some kind guy,when did " se->vruntime > cfs_rq->min_vruntime "? I guess the new waken up process may migrate to another cfs_rq,and its vruntime bigger than that cfs_rq. Also if CONFIG_FAIR_GROUP_SCHED=y,the enqueue_task_fair() maybe traverse se and its parents ,then parameter "wakeup = 1".Then the parent schedule entity may has larger vruntime than its cfs_rq,it stands for a group. Could any one give some suggestion? Thanks in advance. --wxc200 -- To unsubscribe from this list: send the line "unsubscribe linux-newbie" 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.linux-learn.org/faqs
[Site Home] [Audio] [Hams] [Kernel Newbies] [Memory] [Security] [Netfilter] [Bugtraq] [Writing Drivers] [Photo] [Yosemite Photos] [Yosemite News] [MIPS Linux] [ARM Linux] [Linux Security] [Linux RAID] [Samba] [Video 4 Linux] [Linux Resources] [Fedora Users]
![]() |