From owner-freebsd-hackers Tue Feb 15 17: 9:57 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by builder.freebsd.org (Postfix) with ESMTP id 880524B63; Tue, 15 Feb 2000 16:23:13 -0800 (PST) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id QAA46284; Tue, 15 Feb 2000 16:22:19 -0800 (PST) (envelope-from dillon) Date: Tue, 15 Feb 2000 16:22:19 -0800 (PST) From: Matthew Dillon Message-Id: <200002160022.QAA46284@apollo.backplane.com> To: Joe Greco Cc: msmith@FreeBSD.ORG (Mike Smith), jgreco@ns.sol.net, hackers@FreeBSD.ORG Subject: Re: Filesystem size limit? References: <200002152131.PAA77222@aurora.sol.net> Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG : :> > > The scary thing about this posting is that Joe was able to construct his :> > > 1TB+ filesystem with *ONLY* 37 hard drives. :> > :> > 37? 38. And you, a programmer! ;-) And that gets you 1.9TB (disk mfr :> > counting-wise). I'd have loved to break 2TB but couldn't imagine how to :> > handle the required number of scsi busses without botchery. I could get :> > 1TB with only 20 drives. These _are_ 50GB drives. :> :> An AMI MegaRAID 1500 will give you sixty devices - four LVD channels. At :> 50GB a disk, that's ~3TB from a single card. Or you could go the FC :> route, but that's probably too expensive to be fun. : :I was under the impression that there were still device number limits with :the LVD spec. Besides, figuring out how to actually physically set up :more than 9 devices is a pain. The Kingston DS400 will do 9 devices, but :to do more, you then have to have another chassis with only 6 (for example). :Eats up space real quick :-( : :... Joe : :------------------------------------------------------------------------------- :Joe Greco - Systems Administrator jgreco@ns.sol.net Not with LVD. The whole point was to be able to have longer SCSI busses. LVD allows SCSI bus cable lengths up to 25 meters. With 16 devices the limit is 12 meters. That's 36 feet, folks! Of course, this is only true if *EVERY* device on the bus is a LVD device, so don't mix and match if you want to use long cables. This works for many reasons but the main one is that the electrical characteristics of a differential line pair are much, much, much easier to engineer for. All sorts of things work in your favor including but limited to noise generation, termination, and current paths. -Matt Matthew Dillon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message