From owner-freebsd-hackers Tue Mar 3 14:10:54 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA22452 for freebsd-hackers-outgoing; Tue, 3 Mar 1998 14:10:54 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from Kitten.mcs.com (Kitten.mcs.com [192.160.127.90]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id OAA22351 for ; Tue, 3 Mar 1998 14:10:28 -0800 (PST) (envelope-from karl@Mars.mcs.net) Received: from Mars.mcs.net (karl@Mars.mcs.net [192.160.127.85]) by Kitten.mcs.com (8.8.7/8.8.2) with ESMTP id QAA09216; Tue, 3 Mar 1998 16:10:27 -0600 (CST) Received: (from karl@localhost) by Mars.mcs.net (8.8.7/8.8.2) id QAA27069; Tue, 3 Mar 1998 16:10:26 -0600 (CST) Message-ID: <19980303161026.53326@mcs.net> Date: Tue, 3 Mar 1998 16:10:26 -0600 From: Karl Denninger To: shimon@simon-shapiro.org Cc: hackers@FreeBSD.ORG, Julian Elischer Subject: Re: SCSI Bus redundancy... References: <19980303155120.43579@mcs.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.84 In-Reply-To: ; from Simon Shapiro on Tue, Mar 03, 1998 at 02:09:56PM -0800 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Tue, Mar 03, 1998 at 02:09:56PM -0800, Simon Shapiro wrote: > > On 03-Mar-98 Karl Denninger wrote: > > ... > > > You want the heads off the active media surface and the write gate off > > *now* > > if you detect a power failure. > > ``now'' is a relative term. f you are writing a sector, you want ``now'' > to be ``just as soon as the sector is done''. > Power failure is not instantenous. It is a short event, but takes some > time. Those old drives that sported ``command completion'' lost less data > upon power failure than these new ``1,000,000 MTBF 10,000RPM as lnog as I do > not get warm even once'' drives. They also cost a lot more per megabyte, > vibrated real nice and loud and kept my garage warm ieven in the dead of > winter. Ah, the good old days... :-) Part of that is that these days, with the smaller form factors, there's no space to put the requisite capacitor to store enough energy to do it. Making this possible would mean either (1) using regenerative power, as some other folks have suggested, or, (2) making enough room for the capacitor :-) If you know the power drain from the electronics, its a simple matter to hold up the circuitry for the "N" milliseconds you need to complete the current operation and cleanly shut down. Making things smaller, unfortunately, has the side effect of making it tougher to store enough energy for this purpose and the idea of using regenerative power seems to have fallen out of favor. -- -- Karl Denninger (karl@MCS.Net)| MCSNet - Serving Chicagoland and Wisconsin http://www.mcs.net/ | T1's from $600 monthly to FULL DS-3 Service | NEW! K56Flex support on ALL modems Voice: [+1 312 803-MCS1 x219]| EXCLUSIVE NEW FEATURE ON ALL PERSONAL ACCOUNTS Fax: [+1 312 803-4929] | *SPAMBLOCK* Technology now included at no cost To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message