From owner-freebsd-hackers Wed Feb 25 11:03:43 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA20046 for freebsd-hackers-outgoing; Wed, 25 Feb 1998 11:03:43 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from uni4nn.gn.iaf.nl (osmium.gn.iaf.nl [193.67.144.12]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id LAA20032; Wed, 25 Feb 1998 11:03:31 -0800 (PST) (envelope-from wilko@yedi.iaf.nl) Received: by uni4nn.gn.iaf.nl with UUCP id AA14666 (5.67b/IDA-1.5); Wed, 25 Feb 1998 20:03:24 +0100 Received: (from wilko@localhost) by yedi.iaf.nl (8.8.7/8.6.12) id TAA01401; Wed, 25 Feb 1998 19:35:56 +0100 (MET) From: Wilko Bulte Message-Id: <199802251835.TAA01401@yedi.iaf.nl> Subject: Re: SCSI Bus redundancy... In-Reply-To: <199802251354.FAA18637@silvia.HIP.Berkeley.EDU> from Satoshi Asami at "Feb 25, 98 05:54:20 am" To: scsi@FreeBSD.ORG Date: Wed, 25 Feb 1998 19:35:56 +0100 (MET) Cc: tom@sdf.com, blkirk@float.eli.net, hackers@FreeBSD.ORG, scsi@FreeBSD.ORG X-Organisation: Private FreeBSD site - Arnhem, The Netherlands X-Pgp-Info: PGP public key at 'finger wilko@freefall.freebsd.org' X-Mailer: ELM [version 2.4ME+ PL32 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG As Satoshi Asami wrote... > (Redirected to -scsi) > > * SCSI adapter rarely fail. > > I've seen one that fried itself. Adaptec 3940UW (the fried chip was > actually the PCI-PCI bridge). > > * It is possible to have up to two host adapters per channel. > > Yes. We've tried it before, with a couple of patches from Justin > (since merged to the main source), we could get it to work. (The same > single-ended controllers as above.) And cross your fingers that the device vendor has correctly implemented multiple initiator support. Although the SCSI standard says they should this is in no way guaranteed to work. Crappy firmware is plentiful. > * Someone the freebsd-scsi list is working on this. Rather than a simple > * backup design, he is working on simultanous use of both host adapters at > * the same time, by two separate computers. The two systems communicate to > * make sure they don't step on each others toes when accessing the disks. > * The idea is to make a fully fault-tolerant cluster. > > We're working on something similar, although not as extensible as what > you described. The plan is to have all disks mounted read-only from > both systems during normal operation. When there is a write, it first > gets unmounted from one machine before it gets written on the other. Who will write the CFS ? ;-) (cluster file system) Wilko _ ______________________________________________________________________ | / o / / _ Bulte email: wilko @ yedi.iaf.nl http://www.tcja.nl/~wilko |/|/ / / /( (_) Arnhem, The Netherlands - Do, or do not. There is no 'try' --------------- Support your local daemons: run [Free,Net,Open]BSD Unix -- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message