From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758924AbZKEVPY (ORCPT ); Thu, 5 Nov 2009 16:15:24 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758613AbZKEVPY (ORCPT ); Thu, 5 Nov 2009 16:15:24 -0500 Received: from web50101.mail.re2.yahoo.com ([206.190.38.29]:32183 "HELO web50101.mail.re2.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1758592AbZKEVPX convert rfc822-to-8bit (ORCPT ); Thu, 5 Nov 2009 16:15:23 -0500 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:X-YMail-OSG:Received:X-Mailer:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=GaWhu7ws4948PPKp3LXwzMOSchwWAZX7YiUK0glCGmZB6jUqTKvC4zjbEnx/lr2PkpwcNW9muhokEepdjw2R0nsmO6Jidl/hBTxjn68iE49lSBZubJtdKDRhdC1Cf66mudSc+RpRjmONYqwsrBG2uTgezhMAMwmtn8JsDRFxQFk=; Message-ID: <797900.98239.qm@web50101.mail.re2.yahoo.com> X-YMail-OSG: t6CjQscVM1lc64JVndNCyFh7BuWB4rhblQGGlfVy7wCb_Fxxh0dP.u2d7R8QfNPZk.4L24XCRXxmBlEYp3skJkB.qg9ZQiLJNNUAYmNUj75vS8RiqqNUFieK8U4VSLzilyxjAXkKeNCJqfsMgfbNxstD8VQ0oAK8wwb39wQcvU9IuvKtd8MehG1ep30Xjlp4j.R6iLt6U.sRAfjm.kVwzmFkIbwri8tmUhms9k2og1aHcjJe6Q5aTAi.U01Et4V.4DS4_wPMXp6g62IABcl7Dn9.0l.YlS8ivutM671P1OaH6_wD16wxXqVwBRmVO6mJcvf22FnuF0j_1UPDjxHKmuA9z8gXo27mqRBS22Sb9xNpMVt9OVf7PUk8d1pQ7RP1EqcBtcPDsxOBIQQarVJ7dDI.k2aLzfw9lz44p9mhahrBc7t1ol7Vge6feHcuWRMMpb2PJZLbKxa8vfAyMLEf5a4RXBr1vLyW X-Mailer: YahooMailClassic/8.1.6 YahooMailWebService/0.7.361.4 Date: Thu, 5 Nov 2009 13:15:28 -0800 (PST) From: Doug Thompson Subject: Re: [RFC] amd64_edac: syndromes loading To: "H. Peter Anvin" , Borislav Petkov Cc: Pavel Machek , Ingo Molnar , Thomas Gleixner , x86 , LKML In-Reply-To: <20091105132758.GC17984@aftab> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --- On Thu, 11/5/09, Borislav Petkov wrote: > From: Borislav Petkov > Subject: Re: [RFC] amd64_edac: syndromes loading > To: "H. Peter Anvin" > Cc: "Pavel Machek" , "Doug Thompson" , "Ingo Molnar" , "Thomas Gleixner" , "x86" , "LKML" > Date: Thursday, November 5, 2009, 6:27 AM > Hi, > > The good news is they've come up with a modified algorithm > which will > require a smaller table, roughly 1/4th the size of the > current 10K one. > Now, on a second thought and IMHO, we should simply add > another .c file > instantiating those two x4 and x8 tables statically and > linking them > into the edac code. This way you > > 1) don't have the additional complexity of adding firmware > handling code > and thus don't add a dependency on the firmware API > > 2) don't have to actually carry two firmware images with > the kernel > > See, the natural use case for those tables are big machines > which do not > care about 4K memory wasted in ECC decoding tables when the > recovery > from the missed early warnings of a failing DIMM module is > much more > expensive. very well put. when nodes that have 64 or 128 GIGA-bytes of RAM are involved, 4k or even 32kb "loss" is in the noise. Features vs costs is always something to weigh. In some cases loss of 4k in a 1 Gb machine might not be tolerated (though I accept it). doug t > > Hmm... ? > > -- > Regards/Gruss, > Boris. > > Operating | Advanced Micro Devices GmbH >   System  | Karl-Hammerschmidt-Str. 34, 85609 > Dornach b. München, Germany > Research | Geschäftsführer: Andrew Bowd, Thomas M. > McCoy, Giuliano Meroni >   Center  | Sitz: Dornach, Gemeinde Aschheim, > Landkreis München >   (OSRC)  | Registergericht München, HRB Nr. > 43632 > >