From owner-freebsd-geom@FreeBSD.ORG Fri May 20 00:08:11 2011 Return-Path: Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3CE4B1065686 for ; Fri, 20 May 2011 00:08:11 +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 EF0D78FC12 for ; Fri, 20 May 2011 00:08:10 +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 p4K089kE085993; Thu, 19 May 2011 20:08:10 -0400 (EDT) (envelope-from jwd@nmail.slowblink.com) Received: (from jwd@localhost) by nmail.slowblink.com (8.14.3/8.14.3/Submit) id p4K089XQ085992; Thu, 19 May 2011 20:08:09 -0400 (EDT) (envelope-from jwd) Date: Thu, 19 May 2011 20:08:09 -0400 From: John De Boskey To: mjacob@freebsd.org Message-ID: <20110520000809.GA85914@slowblink.com> References: <20110519143935.GA83122@slowblink.com> <20110519212022.GA84918@slowblink.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.3i Cc: freebsd-geom@freebsd.org Subject: Re: LSI 9200-8e/gmultipath/ZFS cable pull kernel crash X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 20 May 2011 00:08:11 -0000 ----- Matthew Jacob's Original Message ----- > >dd if=/dev/zero bs=1m | mbuffer -m 64m -o /lsi/bigfile > > > >with mbuffer reporting the following > > > >in @ 697 MiB/s, out @ 697 MiB/s, 11.8 GiB total, buffer 100% full > > > >when I pull the cable. Playing with it today, I'm wondering if the > >1st cable actually has any active providers on it (luck of the > >draw that I pulled it first), and the 2nd has all the active > >providers on it. I have not explicity tried to balance the i/o > >on the two cables with gmultipath rotate. > > > >Having a bit of trouble getting a good objdump of g_multipath.o > >so I may do a new src update. Sources are up-to-date as of revision 222104. buildworld/buildkernel. I'll rerun tests and pull the cables. > I had to do a wad of changes at Panasas to cover this kind of case. I have > had some troubles getting these changes into -head (lack of time, > differences from the RELENG_7 code I was working with, etc), but I think > that there are still issues at play here. Do you still have changes to integrate? Anything I can do to help? Any best debugging practices for this area? Sorry, lots of questions. Thx