Date: Sun, 23 Sep 2001 08:44:11 -0700 From: "Kevin Oberman" <oberman@es.net> To: "Chad R. Larson" <chad@DCFinc.com> Cc: "Daniel O'Connor" <doconnor@gsoft.com.au>, j mckitrick <jcm@FreeBSD-uk.eu.org>, freebsd-stable@FreeBSD.ORG, Nuno Teixeira <nuno.mailinglists@pt-quorum.com>, "David W. Chapman Jr." <dwcjr@inethouston.net> Subject: Re: hw.ata.wc && hw.ata.tags && softupdates short question Message-ID: <200109231544.f8NFiBR01658@ptavv.es.net> In-Reply-To: Your message of "Sat, 22 Sep 2001 18:20:52 PDT." <20010922182052.B16388@freeway.dcfinc.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Chad, Many older removable SMD drives had enough momentum to keep spinning for minutes and used a dummy load across the motor to stop in a reasonable time. The big issue with these drives was parking the massive voice coil mounted heads stack. This took a LOT of energy and CDC drives used the capacitor bank to do the job, but some smaller drives (Diablo, Century) did use the motor as a generator. Of course, this was not an attempt to flush 2 MB of cache. They only had 512 bytes of cache to contain one sector of data and this was written out before the heads retracted on most disks. These drives lacked a smart controller and any drive optimization was entirely done in the driver. Modern ATA disks are tiny. The momentum in a spinning disk is also tiny and I doubt you could get enough energy to flush the entire cache with multiple seeks and many rotations at near full speed required to do the job. I strongly suspect that capacitance is the only game in town. R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200109231544.f8NFiBR01658>