From owner-freebsd-current@FreeBSD.ORG Tue Jan 6 22:14:46 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 604DF16A4CE; Tue, 6 Jan 2004 22:14:46 -0800 (PST) Received: from gate.bitblocks.com (bitblocks.com [209.204.185.216]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7BF8243D39; Tue, 6 Jan 2004 22:14:45 -0800 (PST) (envelope-from bakul@bitblocks.com) Received: from bitblocks.com (localhost [127.0.0.1]) by gate.bitblocks.com (8.12.10/8.12.10) with ESMTP id i076Eiic069468; Tue, 6 Jan 2004 22:14:44 -0800 (PST) (envelope-from bakul@bitblocks.com) Message-Id: <200401070614.i076Eiic069468@gate.bitblocks.com> To: "Daniel O'Connor" In-reply-to: Your message of "Wed, 07 Jan 2004 16:12:57 +1030." <200401071612.57398.doconnor@gsoft.com.au> Date: Tue, 06 Jan 2004 22:14:44 -0800 From: Bakul Shah cc: Don Lewis cc: freebsd-current@freebsd.org cc: yurtesen@ispro.net.tr Subject: Re: FreeBSD Crashes with AMD X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 07 Jan 2004 06:14:46 -0000 > ECC RAM is nice, but it is considerably more expensive (especially when you > consider you need to buy 'server' motherboards to use it), and it can get > undetectable faults too :) This is not as bad as it used to be. From compugeeks: 512MB DDR PC3200 ECC : $86.50 512MB DDR PC3200 : $65.50 For 64 bit memory ECC is as cheap as parity. There are quite a few motherboards that 'support' ECC. See for example, http://www.anime.net/~goemon/linux-ecc/ Though, not all are built well enough. Standard ECC is also called SECDED: Single bit Error Correcting, Double bit Error Detecting. All memory errors are pretty uncommon but of those one bit errors are the most common. FreeBSD *needs* to have ECC since it is already such a reliable OS -- you don't want your uptime spoiled by a memory failure, do you?:-)