From owner-freebsd-current@FreeBSD.ORG  Wed Jun 23 01:25:15 2004
Return-Path: <owner-freebsd-current@FreeBSD.ORG>
Delivered-To: freebsd-current@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP
	id 23E6516A4CE; Wed, 23 Jun 2004 01:25:15 +0000 (GMT)
Received: from mail.pcnet.com (mail.pcnet.com [204.213.232.4])
	by mx1.FreeBSD.org (Postfix) with ESMTP
	id B4FA043D1F; Wed, 23 Jun 2004 01:25:14 +0000 (GMT)
	(envelope-from eischen@vigrid.com)
Received: from mail.pcnet.com (mail.pcnet.com [204.213.232.4])
	by mail.pcnet.com (8.12.10/8.12.1) with ESMTP id i5N1P3on018376;
	Tue, 22 Jun 2004 21:25:03 -0400 (EDT)
Date: Tue, 22 Jun 2004 21:25:03 -0400 (EDT)
From: Daniel Eischen <eischen@vigrid.com>
X-Sender: eischen@pcnet5.pcnet.com
To: Julian Elischer <julian@elischer.org>
In-Reply-To: <Pine.BSF.4.21.0406221708100.54870-100000@InterJet.elischer.org>
Message-ID: <Pine.GSO.4.10.10406222055010.11528-100000@pcnet5.pcnet.com>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
cc: freebsd-current@freebsd.org
cc: Bosko Milekic <bmilekic@freebsd.org>
Subject: Re: ithread priority question...
X-BeenThere: freebsd-current@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
Reply-To: deischen@freebsd.org
List-Id: Discussions about the use of FreeBSD-current
	<freebsd-current.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-current>,
	<mailto:freebsd-current-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-current>
List-Post: <mailto:freebsd-current@freebsd.org>
List-Help: <mailto:freebsd-current-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-current>,
	<mailto:freebsd-current-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 23 Jun 2004 01:25:15 -0000

On Tue, 22 Jun 2004, Julian Elischer wrote:
> 
> On Tue, 22 Jun 2004, Bosko Milekic wrote:
> 
> > 
> >   I'm obviously talking nonsense below.  Sorry.
> > 
> >   The real explanation is that they are put on a runqueue when executed:
> > 
> >         if (TD_AWAITING_INTR(td)) {
> >                 CTR2(KTR_INTR, "%s: setrunqueue %d", __func__, p->p_pid);
> >                 TD_CLR_IWAIT(td);
> >                 setrunqueue(td);
> >                 if (do_switch &&
> >                     (ctd->td_critnest == 1) ) {
> > ...
> > 
> >   Sorry again!
> 
> yes.. the question is.. does it make sense in a world with multiple
> schedulers to multiply set the priority of each ithread to
> (inumber * RQ_PPQ)?
> 
> It happens to work with 4bsd and probably with ULE
> but it wouldn't make a lot of sense with (say) a monte-carlo scheduler
> that may not have run queues as such (such as Luigi did) or any
> scheduler for which RQ_PPQ was not a constant.

It seems the schedulers should need to know about whether
threads are interrupt threads or not, but any priority
boost for them should be hidden in the scheduler.
I think the thread priority must reflect the fact that
it is an ithread (or not) or else priority inheritence
(or lending, whatever) isn't going to take ithread
importance into consideration.

It'd be nice to have only the schedulers deal with priority.
One could then write a scheduler that uses priorities in the
proper ordering (highest number = highest priority)!

-- 
DE