From owner-freebsd-stable@FreeBSD.ORG Thu Jul 26 19:48:24 2007 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2E19D16A418 for ; Thu, 26 Jul 2007 19:48:24 +0000 (UTC) (envelope-from tom.hurst@clara.net) Received: from spork.qfe3.net (spork.qfe3.net [212.13.207.101]) by mx1.freebsd.org (Postfix) with ESMTP id E571A13C459 for ; Thu, 26 Jul 2007 19:48:23 +0000 (UTC) (envelope-from tom.hurst@clara.net) Received: from [81.104.144.87] (helo=voi.aagh.net) by spork.qfe3.net with esmtp (Exim 4.66 (FreeBSD)) (envelope-from ) id 1IE9Jq-000OHz-Jt; Thu, 26 Jul 2007 20:48:18 +0100 Received: from freaky by voi.aagh.net with local (Exim 4.67 (FreeBSD)) (envelope-from ) id 1IE9Jq-000Muw-5z; Thu, 26 Jul 2007 20:48:18 +0100 Date: Thu, 26 Jul 2007 20:48:18 +0100 From: Thomas Hurst To: Josh Paetzel , freebsd-stable@freebsd.org, Daniel O'Connor , Bill Swingle Message-ID: <20070726194818.GB75432@voi.aagh.net> Mail-Followup-To: Josh Paetzel , freebsd-stable@freebsd.org, Daniel O'Connor , Bill Swingle References: <46A54B6F.9010100@dub.net> <20070724044208.GA79101@eos.sc1.parodius.com> <200707241518.35730.doconnor@gsoft.com.au> <200707241230.53119.josh@tcbug.org> <20070724182604.GA3759@eos.sc1.parodius.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070724182604.GA3759@eos.sc1.parodius.com> Organization: Not much. User-Agent: Mutt/1.5.15 (2007-04-06) Sender: Thomas Hurst Cc: Subject: Re: problems with Hitachi 1TB SATA drives X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 Jul 2007 19:48:24 -0000 * Jeremy Chadwick (koitsu@FreeBSD.org) wrote: > * I'm left questioning why a disk manufacturer would process drives > (by this I mean the manufacturing process) differently based on their > transport type. It would cost a *huge* amount of money to have > separate fabs for SCSI, SAS, and SATA/PATA. One one side you've got consumer drives, where price and capacity are king; you want cheap mass produced large, fairly slow disks, made for modest duty cycles. On the other you've got drives that live in servers in their thousands, running 24/7 on IO heavy workloads, where performance and reliability are king and price is far less important; you end up with smaller, sturdier platters, more powerful actuators and motors, and more extensive testing, not to mention slower growth in capacity. > * All this leads me to the topic of backups. Hard disks are growing > in capacity at a rate which the backup industry cannot follow. It's > getting to the point where you have to buy hard drives to back up the > data on other hard drives, but anyone with half a brain knows RAID is > not a replacement for backups. So you back up one disk to another using proper backup tools and not a RAID system. Have some disks off-site, some offline, and you end up with something that's "good enough" for most people. It'll do me until we get memory diamond, anyway ;) > * SCSI is outrageously expensive even in 2007. I have yet to see any > shred of justification for why SCSI costs so much *even today*. It > costs only a smidgen less than it did 15 years ago. They don't look that expensive to me; sure, when you compare capacity with SATA it's expensive, but the platters are several times smaller, they spin faster, they have better testing, fancier materials, smarter firmware... for a server, why wouldn't you spend a few times more for something with 4x faster seeks and 4x lower failure rates? I have servers with 28 disks and 12 disk RAID-0's. I'm happy to pay extra so I'm not replacing and rebuilding every week :) > * SCSI is on its way out. Seagate recently announced that > they'll no longer be supporting SCSI products, possibly by the end of > next year: > > "Seagate has announced that by next year they will no longer be > supporting SCSI product and will be moving customers to the SATA > interface." > http://www.horizontechnology.com/news/market/market_perspective_storage_04-11-2007.php > > I'm willing to bet others will follow suit. They almost certainly only mean U320; I severely doubt SAS is going anywhere. I really hope so, since Seagate are currently the only company making 15kRPM 2.5" SAS disks (afaik). I do find it surprising they're doing this so soon though. I would have thought they'd have long term support contracts for various server vendors who've only very recently started moving over to SAS. I guess they're expecting their stockpiles to keep people in replacements for the next few years. -- Thomas 'Freaky' Hurst http://hur.st/