Date: Fri, 7 Apr 2000 18:21:36 +0400 (MSD) From: "Aleksandr A.Babaylov" <babolo@links.ru> To: Bob.Gorichanaz@midata.com Cc: hackers@FreeBSD.ORG Subject: Re: bad memory patch? Message-ID: <200004071421.SAA07914@aaz.links.ru> In-Reply-To: <OF2F5C4FC5.C68B571C-ON862568BA.0045E942@midata.com> from "Bob.Gorichanaz@midata.com" at "Apr 7, 0 07:46:24 am"
next in thread | previous in thread | raw e-mail | index | archive | help
Bob.Gorichanaz@midata.com writes: > Maybe I'm mis-understanding something, > but isn't this situation analagous to bad sectors > on a hard drive? Yes it is not. > Isn't this similar, at least in theory, to remapping dead > sectors and continuing to use the drive? > (except that the disk's onboard controller handles the > mapping instead of the OS) Difference is in fault model. hard drive surface fault can only grows to some more bits, which usually resides in the same sector or affect low quantity of another sectors. Every DRAM bit fault affect common for many bits circuitry first before anoter bit fault occur. And remember, such a fault affect mostly far bits (in another words and pages) > Not trying to push this idea one way or the other, I'm just curious as to > WHY so many people > think this is a "bad idea" > -=bob=- > Warner Losh <imp@village.org>@FreeBSD.ORG on 04/06/2000 04:58:59 PM > > To: J McKitrick <jcm@freebsd-uk.eu.org> > > Subject: Re: bad memory patch? > > In message <20000406164114.B29984@dogma.freebsd-uk.eu.org> J McKitrick > writes: > : Sounds like sometheing we could use, eh? > I don't think so. Strikes me a a hugely *BAD* idea. If you have bad > memory, replace it, don't work around it. PS sorry bad English -- @BABOLO http://links.ru/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200004071421.SAA07914>