From owner-freebsd-hackers@FreeBSD.ORG Tue Aug 10 22:06:48 2004 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4FD6216A4CE for ; Tue, 10 Aug 2004 22:06:48 +0000 (GMT) Received: from minerva.int.gov.br (nat.int.gov.br [200.20.196.226]) by mx1.FreeBSD.org (Postfix) with ESMTP id C2DA743D2D for ; Tue, 10 Aug 2004 22:06:46 +0000 (GMT) (envelope-from jonny@jonny.eng.br) Received: from jonny.eng.br (jonny.int.gov.br [10.0.8.17]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by minerva.int.gov.br (Postfix) with ESMTP id 8D9D5BE516 for ; Tue, 10 Aug 2004 19:06:44 -0300 (BRT) Message-ID: <411946F4.7030508@jonny.eng.br> Date: Tue, 10 Aug 2004 19:06:44 -0300 From: =?ISO-8859-1?Q?Jo=E3o_Carlos_Mendes_Lu=EDs?= User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.6) Gecko/20040113 X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-hackers@freebsd.org References: <20040809094325.6F8D443D1F@mx1.FreeBSD.org> <20040810111749.GA48836@grummit.biaix.org> In-Reply-To: <20040810111749.GA48836@grummit.biaix.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Subject: Realtime memory testing - Was: Re: how to logically disable memory X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 10 Aug 2004 22:06:48 -0000 Porting is probably not an option, since the memory managers are very different. But the same idea could be applied. Indeed, in my college times, I had a class about memory testing procedures, and had an idea to patch the FreeBSD kernel to do realtime memory tests and lock bad memory. This way, the system would be a lot more stable, even with bad hardware (common in poor countries like Brasil). The solution is probably near the VM core. At that time I was thinking in changing the page mapper, but now I know this would just make the system more i386 specific, and the solution could be architecture generic. No, unfortunatly I never let this idea grow into a solution. Probably because I never got the guts to fully understand the FreeBSD VM engine. ;-) Joan Picanyol wrote: > * Danny Braniss [20040809 11:42]: > >>is there an 'easy' way to mark some memory as unusable? thanks, > > > Linux has BadRAM: http://rick.vanrein.org/linux/badram/index.html, I > think someone was thinking of porting it to FreeBSD... (or maybe it was > you ;) > > qvb