lkml.org 
[lkml]   [2011]   [Jun]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH] sched: update cpupri for runqueue when its priority changes
From
On Sun, Jun 19, 2011 at 1:11 AM, Steven Rostedt <rostedt@goodmis.org> wrote:
>> There are two cases that NULL is returned in _pick_next_task_rt(), it is the
>> second case, after checking rt_rq->rt_nr_running, that is captured, and if
>> NULL is returned in the second case, the CPU priority does change.
>
> The two cases are:
>
> 1) no rt task exists
> 2) the runqueue is throttled.
>
> We already talked about the throttled case. The case where no rt task
> exists means that the last rt task has been dequeued. When that happens,
> the cpupri is updated then. I don't see any bug. There's no need to
> update cpupri at this point.
>

In case 2) , the CPU will be held then by non-RT task, and we have to
update priority.

I understand 1) and 2) to be, there has RT tasks on runqueue but they
could not run at the moment.

If throttled RQ == no RT tasks, please drop this patch directly.

>>
>> In another scenario that has little with {en, de}queue, as shown by
>> requeue_task_rt(), the CPU priority will change if other RT tasks exist.
>>
>
> The requeue_task_rt() does not change the priority of the CPU. It just
> updates the task in its order of placement in the queue of other tasks
> of the same priority.
>

You are right, updating CPU priority for requeue is unnecessary.

thanks
Hillf


\
 
 \ /
  Last update: 2011-06-19 10:37    [W:0.721 / U:0.036 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site