Re: scheduler oddity [bug?]

[Mike Galbraith <efault@gmx.de>]

On Sun, 2009-03-08 at 11:19 +0100, Peter Zijlstra wrote:

> Wouldn't something like the below be more suited:
> 
> diff --git a/kernel/sched.c b/kernel/sched.c
> index 89e2ca0..94c8b02 100644
> --- a/kernel/sched.c
> +++ b/kernel/sched.c
> @@ -2501,7 +2501,7 @@ static void __sched_fork(struct task_struct *p)
>  	p->se.prev_sum_exec_runtime	= 0;
>  	p->se.nr_migrations		= 0;
>  	p->se.last_wakeup		= 0;
> -	p->se.avg_overlap		= 0;
> +	p->se.avg_overlap		= sysctl_sched_migration_cost;
>  	p->se.start_runtime		= 0;
>  	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
>  

Dunno exactly what we need to do here.  My hacklet certainly ain't it,
but I suspect this isn't going to work out either.  Having tasks begin
life at zero or sysctl_sched_migration_cost won't matter much methinks.

	-Mike