From owner-freebsd-hackers Thu Sep 21 22:26:29 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from mw2.texas.net (mw2.texas.net [206.127.30.12]) by hub.freebsd.org (Postfix) with ESMTP id 3B2D837B422 for ; Thu, 21 Sep 2000 22:26:27 -0700 (PDT) Received: from staff3.texas.net (staff3.texas.net [207.207.0.40]) by mw2.texas.net (2.4/2.4) with ESMTP id AAA19207; Fri, 22 Sep 2000 00:26:25 -0500 (CDT) Received: (from doug@localhost) by staff3.texas.net (8.9.3/8.9.2) id AAA84307; Fri, 22 Sep 2000 00:26:24 -0500 (CDT) (envelope-from doug@texas.net) Date: Fri, 22 Sep 2000 00:26:24 -0500 From: Douglas Swarin To: Warner Losh Cc: freebsd-hackers@freebsd.org Subject: Re: Frustration with SCSI system Message-ID: <20000922002624.A84288@staff.texas.net> References: <20000921182405.A82919@staff.texas.net> <20000920125128.F9141@fw.wintelcom.net> <20000921182405.A82919@staff.texas.net> <200009212344.RAA63251@harmony.village.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0i In-Reply-To: <200009212344.RAA63251@harmony.village.org>; from imp@village.org on Thu, Sep 21, 2000 at 05:44:32PM -0600 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Thu, Sep 21, 2000 at 05:44:32PM -0600, Warner Losh wrote: > In message <20000921182405.A82919@staff.texas.net> Douglas Swarin writes: > : Ideally, I would use one of the IDE flash-based drives on the market. One > : brand is SanDisk, and they take a standard IDE connector and fit into a > : 3.5" drive bay. You can get them very reasonably priced up to 128MB or > : so, which is just fine for a boot partition. Since flash drives have no > : moving parts, mechanical failure is not an issue, and since the root > : partition is not written to much, the flash will not wear out for a > : long time (flash cells wear out after about 100,000 writes; the flash > : drives do load balancing and stuff to ensure that the (many) cells in > : the drive are written to evenly). > > We use these devices heavily at Timing Solutions. Or rather we use > a IDE <-> CF adapter and haven't had any devices wear out. And some > of these devices have had rather heavy use. I think that it is closer > to 1 million writes per cell, but I don't have my spec sheets handy. > > Are you sure that they do write balancing? The indications I have > from the base chip technology is that they don't. I could have missed > that in the data sheets. It has been a little while since I looked at > them, so I might be misremembering. I can't seem to find the data > sheets I looked at before. > > In any event, this works well. I usually have / be read only. This > can be practacle if you don't have any users that desire to change > their passwords... Since I have serveral machines that have an > extremely limited number of users on, this works well. One can also > mount / rw if you need to do maintenance on it for whatever reason. I was being pessimistic as to the number of writes. I have heard figures in the range of a million writes per cell as well. The technology is always improving, of course. As to the write balancing, I've seen no hard technical data on it, but I've heard it quoted from many sources. So I may be completely wrong. A brief Google search gives http://www.embedded.com/98/9801spec.htm which mentions that ATA flash can indeed do such balancing about 1/3 of the way down the page (search for 'evenly' in the text). The technical term appears to be 'wear leveling'. But I digress. I'm glad to hear this method validated by someone with much more experience in the field. Doug To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message