Date: Fri, 6 Mar 1998 17:35:47 +1030 From: Greg Lehey <grog@lemis.com> To: Karl Denninger <karl@mcs.net>, Niall Smart <njs3@doc.ic.ac.uk> Cc: hackers@FreeBSD.ORG Subject: Re: SCSI Bus redundancy... Message-ID: <19980306173547.64725@freebie.lemis.com> In-Reply-To: <19980305125911.15755@mcs.net>; from Karl Denninger on Thu, Mar 05, 1998 at 12:59:11PM -0600 References: <karl@mcs.net> <E0yAfoG-0000sB-00@oak65.doc.ic.ac.uk> <19980305125911.15755@mcs.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, 5 March 1998 at 12:59:11 -0600, Karl Denninger wrote: > On Thu, Mar 05, 1998 at 06:56:00PM +0000, Niall Smart wrote: >> On Mar 5, 12:09pm, Karl Denninger wrote: >>> Subject: Re: SCSI Bus redundancy... >>> >>> 1) The devices on the RAID arrays are high-availability required machines >>> (ie: primary NFS fileservers, News service, and the authentication >>> database machines). NONE OF THESE can afford to be down or crash. >> >> "NONE OF THESE"? Ever heard of Stratus Computer Corporation? >> >> Niall > > Actually, if I didn't care about the cost, Tandem makes some very good > fault-tolerant machines. Of course the problem is "if you don't care about > the cost". > > Reality is that building something 100% fail-proof is just not economically > justified in the ISP business. In other lines of work, it is. > > However, being able to swap a CPU in 5 minutes (the only non-redundant > component) Are you talking about Tandem? CPUs have always been redundant. Greg To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980306173547.64725>