From owner-freebsd-geom@FreeBSD.ORG  Tue Jan  9 14:17:32 2007
Return-Path: <owner-freebsd-geom@FreeBSD.ORG>
X-Original-To: freebsd-geom@freebsd.org
Delivered-To: freebsd-geom@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52])
	by hub.freebsd.org (Postfix) with ESMTP id C074316A403
	for <freebsd-geom@freebsd.org>; Tue,  9 Jan 2007 14:17:32 +0000 (UTC)
	(envelope-from bashr@comcast.net)
Received: from rwcrmhc13.comcast.net (rwcrmhc13.comcast.net [216.148.227.153])
	by mx1.freebsd.org (Postfix) with ESMTP id B04F313C45D
	for <freebsd-geom@freebsd.org>; Tue,  9 Jan 2007 14:17:32 +0000 (UTC)
	(envelope-from bashr@comcast.net)
Received: from [149.28.227.65] (unknown[149.28.227.65])
	by comcast.net (rwcrmhc13) with ESMTP
	id <20070109140450m1300i24k4e>; Tue, 9 Jan 2007 14:04:50 +0000
Message-ID: <45A3A101.2000203@comcast.net>
Date: Tue, 09 Jan 2007 09:04:49 -0500
From: bashr <bashr@comcast.net>
User-Agent: Thunderbird 1.5.0.8 (X11/20061123)
MIME-Version: 1.0
To: freebsd-geom@freebsd.org
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Subject: FAILURE - out of memory in start
X-BeenThere: freebsd-geom@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
Reply-To: bashr@comcast.net
List-Id: GEOM-specific discussions and implementations
	<freebsd-geom.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-geom>,
	<mailto:freebsd-geom-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-geom>
List-Post: <mailto:freebsd-geom@freebsd.org>
List-Help: <mailto:freebsd-geom-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-geom>,
	<mailto:freebsd-geom-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Tue, 09 Jan 2007 14:17:32 -0000

Messages like the following are regularly logged on this server for each 
of the four installed hd's:
+ad4: FAILURE - out of memory in start
They did not occur before implementation of a gmirror of gstripes. 
Occurrances of failures do not correspond with times of heavy load. 
Such failures were mentioned on freebsd-geom in Aug 2005, but without a 
resolution that I could find. Setting vm.kmem_size_scale=2, as suggested 
elsewhere does not solve the problem.

Any advice or suggestions will be much appreciated.  Here is some more info:

 >gmirror status
         Name    Status  Components
mirror/gm0s1  COMPLETE  ad2s1
                         ad4s1
                         ad6s1
                         ad8s1
mirror/gm0s2  COMPLETE  stripe/st1s1
                         stripe/st0s1

 > gstripe status
         Name  Status  Components
stripe/st1s1      UP  ad2s3
                       ad4s3
stripe/st0s1      UP  ad6s3
                       ad8s3

 > mount
/dev/mirror/gm0s1a on / (ufs, local, soft-updates)
devfs on /dev (devfs, local)
/dev/mirror/gm0s2a on /var (ufs, local, nosuid, soft-updates)
/dev/mirror/gm0s2d on /tmp (ufs, local, nosuid, soft-updates)
/dev/mirror/gm0s2e on /usr (ufs, local, soft-updates)
/dev/mirror/gm0s2f on /usr/home (ufs, local, nosuid, soft-updates)
linprocfs on /usr/compat/linux/proc (linprocfs, local)

 > uname -a
FreeBSD ***.***.*** 6.2-PRERELEASE FreeBSD 6.2-PRERELEASE #0: Tue Dec 12 
13:30:20 EST 2006     ***@***.***.***:/usr/obj/usr/src/sys/GENERIC  i386