Who can commit this.. kse vs ULE

[Julian Elischer]

On Sun, 21 Mar 2004, Scott Long wrote:

> 
> This is a qualitative statement.  What exactly is the problem, on a
> technical level?

This is how it was described to me..

Obrien just committedit..



> 
> Scott
> 
> On Sun, 21 Mar 2004, Julian Elischer wrote:
> 
> > ULE makes KSE threaded processes slow, unresposive and soemtimes
> > unusably so.
> >
> > On Sun, 21 Mar 2004, Scott Long wrote:
> >
> > > Thanks.  What is the problem that is referred to in the email?  This
> > > patch looks to be a hack.
> > >
> > > Scott
> > >
> > > Julian Elischer wrote:
> > > > Scott here's the patch I mentioned...
> > > > ---------- Forwarded message ----------
> > > > Date: Wed, 17 Mar 2004 18:30:45 -0800
> > > > From: David O'Brien <obrien at freebsd.org>
> > > > To: Taku YAMAMOTO <taku at cent.saitama-u.ac.jp>
> > > > Cc: freebsd-current at freebsd.org
> > > > Subject: Re: [PATCH] for SCHED_ULE & libpthread issue (was Re: I like
> > > >
> > > > 	SCHED_4BSD)
> > > >
> > > > On Fri, Mar 12, 2004 at 09:23:47AM +0900, Taku YAMAMOTO wrote:
> > > >
> > > >>Until the problem is fully addressed, I will propose following patch
> > > >>to be applied. (the least intrusive one attached in the former message)
> > > >
> > > >
> > > > 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
> > > > @@ -186,7 +186,7 @@
> > > > #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))
> > > >
> > > >  /*
> > > > @@ -1166,11 +1166,8 @@
> > > >  	 */
> > > >  	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);
> > > > _______________________________________________
> > > > freebsd-current at freebsd.org mailing list
> > > > http://lists.freebsd.org/mailman/listinfo/freebsd-current
> > > > To unsubscribe, send any mail to "freebsd-current-unsubscribe at freebsd.org"
> > > >
> > > >
> > >
> > >
> > >
> >
> >
> >
>