From owner-freebsd-performance@FreeBSD.ORG  Fri Feb  1 21:40:29 2008
Return-Path: <owner-freebsd-performance@FreeBSD.ORG>
Delivered-To: freebsd-performance@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id 9392E16A417
	for <freebsd-performance@freebsd.org>;
	Fri,  1 Feb 2008 21:40:29 +0000 (UTC)
	(envelope-from freebsd@sopwith.solgatos.com)
Received: from schitzo.solgatos.com
	(pool-96-225-216-68.ptldor.fios.verizon.net [96.225.216.68])
	by mx1.freebsd.org (Postfix) with ESMTP id 5ECF513C442
	for <freebsd-performance@freebsd.org>;
	Fri,  1 Feb 2008 21:40:29 +0000 (UTC)
	(envelope-from freebsd@sopwith.solgatos.com)
Received: from schitzo.solgatos.com (localhost.home.localnet [127.0.0.1])
	by schitzo.solgatos.com (8.14.1/8.13.8) with ESMTP id m11LeSAs013959;
	Fri, 1 Feb 2008 13:40:28 -0800
Received: from sopwith.solgatos.com (uucp@localhost)
	by schitzo.solgatos.com (8.14.1/8.13.4/Submit) with UUCP id
	m11LeSC1013956; Fri, 1 Feb 2008 13:40:28 -0800
Received: from localhost by sopwith.solgatos.com (8.8.8/6.24)
	id VAA00426; Fri, 1 Feb 2008 21:39:15 GMT
Message-Id: <200802012139.VAA00426@sopwith.solgatos.com>
To: "Steven Hartland" <killing@multiplay.co.uk>
In-reply-to: Your message of "Fri, 01 Feb 2008 13:57:09 GMT."
	<018701c864da$57020f20$b6db87d4@multiplay.co.uk> 
Date: Fri, 01 Feb 2008 13:39:15 +0000
From: Dieter <freebsd@sopwith.solgatos.com>
Cc: freebsd-performance@freebsd.org
Subject: Re: newfs locks entire machine for 20seconds 
X-BeenThere: freebsd-performance@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Performance/tuning <freebsd-performance.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-performance>,
	<mailto:freebsd-performance-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-performance>
List-Post: <mailto:freebsd-performance@freebsd.org>
List-Help: <mailto:freebsd-performance-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-performance>,
	<mailto:freebsd-performance-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 01 Feb 2008 21:40:29 -0000

> >> Wait - if it returns EAGAIN for a while, then look at that code above. 
> >> It will hold the sysctl lock for some indefinite amount of time.  Maybe 
> >> it should look like this instead:
> >> 
> >> 
> >>    do {
> >>        SYSCTL_LOCK();
> >>        req.oldidx = 0;
> >>        req.newidx = 0;
> >>        error = sysctl_root(0, name, namelen, &req);
> >>        SYSCTL_UNLOCK();
> >>    } while (error == EAGAIN);
> >> 
> >>    if (req.lock == REQ_WIRED && req.validlen > 0)
> >>        vsunlock(req.oldptr, req.validlen);
> >> 
> > 
> > Tried no difference unfortunately, possibly its give the closeness
> > of the lock unlock its just reacquiring the lock straight after releasing
> > it hence not giving the other thread chance to run / obtain the lock?
> 
> In an attempt to prove this is in fact the issue I've tried with the
> locking around this code removed, yes dangerous but just as a test :)
> It does indeed prevent the extended lockup so this is the right area.

Would adding a call to cpu_switch() be appropriate here?