From owner-freebsd-fs@FreeBSD.ORG Thu May 19 14:55:55 2011 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4EE2C106564A; Thu, 19 May 2011 14:55:55 +0000 (UTC) (envelope-from jwd@SlowBlink.Com) Received: from nmail.slowblink.com (rrcs-24-199-145-34.midsouth.biz.rr.com [24.199.145.34]) by mx1.freebsd.org (Postfix) with ESMTP id 10FC08FC14; Thu, 19 May 2011 14:55:54 +0000 (UTC) Received: from nmail.slowblink.com (localhost [127.0.0.1]) by nmail.slowblink.com (8.14.3/8.14.3) with ESMTP id p4JEdZEQ083204; Thu, 19 May 2011 10:39:35 -0400 (EDT) (envelope-from jwd@nmail.slowblink.com) Received: (from jwd@localhost) by nmail.slowblink.com (8.14.3/8.14.3/Submit) id p4JEdZmd083203; Thu, 19 May 2011 10:39:35 -0400 (EDT) (envelope-from jwd) Date: Thu, 19 May 2011 10:39:35 -0400 From: John D To: freebsd-fs@freebsd.org, freebsd-geom@freebsd.org Message-ID: <20110519143935.GA83122@slowblink.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.3i Cc: Subject: LSI 9200-8e/gmultipath/ZFS cable pull kernel crash X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 19 May 2011 14:55:55 -0000 Hi Folks, Looking for a bit of help to debug a sas interconnect, gmultipath, and zfs filesystem crash when the 2nd cable is pulled. Apologies for the cross post to geom & fs, hoped I would catch the right folks. In general, I have two systems each with an LSI 9200-8e sas hba installed. Each adapter has two cables going to shelf 1, then to shelf 2, then to the second system. System1 <---> Shelf1 <---> Shelf2 <---> System2 System1 <---> Shelf1 <---> Shelf2 <---> System2 Typical stuff, system1 & 2 are carp'd together, if one system goes down, the second zfs imports the pools and takes over. If I do a test pull of one of the cables, multipath removes the failed providers correctly with no interupt to the filesystem. Reinstalling the cable causes the providers to be re-integrated. This cable can be pull/reinstalled multiple times with no problem. However, pulling the 2nd causes a kernel crash. I have the configuration/logs/screen shots here: http://people.freebsd.org/~jwd/lsi_gmultipath_zfs.html I can replicate the problem on demand. Any help debugging this problem is appreciated. Thanks! john