From owner-freebsd-geom@FreeBSD.ORG Thu Nov 10 17:36:02 2005 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F24E316A41F; Thu, 10 Nov 2005 17:36:01 +0000 (GMT) (envelope-from djh@nebcorp.com) Received: from ratchet.nebcorp.com (ratchet.nebcorp.com [205.217.153.72]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8E5FD43D58; Thu, 10 Nov 2005 17:36:00 +0000 (GMT) (envelope-from djh@nebcorp.com) Received: by ratchet.nebcorp.com (Postfix, from userid 1014) id 4F56BD983B; Thu, 10 Nov 2005 09:36:00 -0800 (PST) Date: Thu, 10 Nov 2005 09:36:00 -0800 From: Danny Howard To: Pawel Jakub Dawidek Message-ID: <20051110173600.GA23887@ratchet.nebcorp.com> References: <32275093.1131627986609.JavaMail.root@vms170.mailsrvcs.net> <5582.1131630495@critter.freebsd.dk> <20051110140113.GC29291@garage.freebsd.pl> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20051110140113.GC29291@garage.freebsd.pl> User-Agent: Mutt/1.4.2.1i X-Loop: djhoward@uiuc.edu Cc: freebsd-hackers@freebsd.org, Poul-Henning Kamp , babkin@users.sf.net, freebsd-geom@freebsd.org Subject: Re: GEOM for multipath? How? 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: Thu, 10 Nov 2005 17:36:02 -0000 On Thu, Nov 10, 2005 at 03:01:13PM +0100, Pawel Jakub Dawidek wrote: > On Thu, Nov 10, 2005 at 02:48:15PM +0100, Poul-Henning Kamp wrote: > +> In message <32275093.1131627986609.JavaMail.root@vms170.mailsrvcs.net>, Sergey > +> Babkin writes: > +> >QLogic worked fine in multi-path configuration with UnixWare. > +> >I think LSI and Adaptec did too. The only trick is to make sure > +> >that the IRQs of the cards are not shared between the cards or with > +> >any other device. > +> > +> I suspect it is not the card as much as the driver, but I am not sure. > > I was able to modify the driver in a way multipathing started to work > (no more hanging request when path was disconnected). It was hackish, > but worked, so I'm quite sure it's driver's fault. Well, it is good to hear that multipathing is working in some cases. But, and I don't mean to troll or flame, just get my job done, it sounds like if I want MP on the production database, I should stick with the Red Hat this time around, eh? Hopefully I can get some infrastructure to test on sometime. It would be neat if MP on FreeBDS was very straightforward. It would be neater still if I could make some small contribution to everyone elses' efforts to make it happen. :) Thanks, -danny -- http://dannyman.toldme.com/