Re: [PATCH 1/1] scheduler: minor improvement to pick_next_highest_task_rt in linux-3.3

[Steven Rostedt <rostedt@goodmis.org>]

On Mon, 2012-03-19 at 22:26 +0000, Michael J. Wang wrote:
> From: Michael J Wang <mjwang@broadcom.com>
> 
> Avoid extra work by continuing on to the next rt_rq if the highest prio task in current rt_rq is the same priority as our candidate task.
> 
> Signed-off-by: Michael J Wang <mjwang@broadcom.com>
> 
> ---
> 
> More detailed explanation:  if next is not NULL, then we have found a candidate task, and its priority is next->prio.  Now we are looking for an even higher priority task in the other rt_rq's.  idx is the highest priority in the current candidate rt_rq.  In the current 3.3 code, if idx is equal to next->prio, we would start scanning the tasks in that rt_rq and replace the current candidate task with a task from that rt_rq.  But the new task would only have a priority that is equal to our previous candidate task, so we have not advanced our goal of finding a higher prio task.  So we should avoid the extra work by continuing on to the next rt_rq if idx is equal to next->prio.
> 
> --- linux-3.3/kernel/sched/rt.c.orig	2012-03-18 16:15:34.000000000 -0700
> +++ linux-3.3/kernel/sched/rt.c	2012-03-19 14:52:54.585391702 -0700
> @@ -1403,7 +1403,7 @@ static struct task_struct *pick_next_hig
>  next_idx:
>  		if (idx >= MAX_RT_PRIO)
>  			continue;
> -		if (next && next->prio < idx)
> +		if (next && next->prio <= idx)
>  			continue;
>  		list_for_each_entry(rt_se, array->queue + idx, run_list) {
>  			struct task_struct *p;

Acked-by: Steven Rostedt <rostedt@goodmis.org>

-- Steve