Re: [PATCH] for SCHED_ULE & libpthread issue (was Re: I like SCHED_4BSD)

On Wed, 17 Mar 2004 18:30:45 -0800
"David O'Brien" <obrien_at_freebsd.org> wrote:

> Do people think we should commit this?
>  
> > --- sched_ule.c.orig	Fri Feb 13 05:24:48 2004
> > +++ sched_ule.c	Fri Feb 13 05:37:53 2004
> > _at__at_ -186,7 +186,7 _at__at_
> >  #define	SCHED_INTERACTIVE(kg)						\
> >      (sched_interact_score(kg) < SCHED_INTERACT_THRESH)
> >  #define	SCHED_CURR(kg, ke)						\
> > -    (ke->ke_thread->td_priority != kg->kg_user_pri ||			\
> > +    (ke->ke_thread->td_priority < kg->kg_user_pri ||			\
> >      SCHED_INTERACTIVE(kg))
> >  
> >  /*
> > _at__at_ -1166,11 +1166,8 _at__at_
> >  	 */
> >  	if ((ke->ke_flags & KEF_ASSIGNED) == 0) {
> >  		if (TD_IS_RUNNING(td)) {
> > -			if (td->td_proc->p_flag & P_SA) {
> > -				kseq_load_rem(KSEQ_CPU(ke->ke_cpu), ke);
> > -				setrunqueue(td);
> > -			} else 
> > -				kseq_runq_add(KSEQ_SELF(), ke);
> > +			kseq_load_rem(KSEQ_CPU(ke->ke_cpu), ke);
> > +			setrunqueue(td);

If it makes the situation better, why not? It sounds likes it works well
for Peter, Brian and Arjan. I have not tested it though.