From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from sc8-sf-mx1-b.sourceforge.net ([10.3.1.11] helo=sc8-sf-mx1.sourceforge.net) by sc8-sf-list1.sourceforge.net with esmtp (Cipher TLSv1:DES-CBC3-SHA:168) (Exim 3.31-VA-mm2 #1 (Debian)) id 19zX0l-0000rM-00 for ; Wed, 17 Sep 2003 00:46:03 -0700 Received: from mailgate5.cinetic.de ([217.72.192.165]) by sc8-sf-mx1.sourceforge.net with esmtp (Exim 4.22) id 19zX0k-0004nz-BI for User-mode-linux-devel@lists.sourceforge.net; Wed, 17 Sep 2003 00:46:02 -0700 Message-Id: <200309170745.h8H7jVQ11917@mailgate5.cinetic.de> MIME-Version: 1.0 From: "Oliver Oppitz" Subject: Re: [uml-devel] UML and Execution Replay Content-Type: text/plain; charset="iso-8859-1" Sender: user-mode-linux-devel-admin@lists.sourceforge.net Errors-To: user-mode-linux-devel-admin@lists.sourceforge.net List-Help: List-Post: List-Subscribe: , List-Id: The user-mode Linux development list List-Unsubscribe: , List-Archive: Date: Wed, 17 Sep 2003 09:45:31 +0200 Content-Transfer-Encoding: quoted-printable To: "Patrick \"Petschge\" Kilian" , User-mode-linux-devel@lists.sourceforge.net "Patrick \"Petschge\" Kilian" =20 > The only problem is, that you have to replay the input with the exact=20 > correct timing. Yes, indeed that is the more tricky part. However, there are known techniqu= es for handling this. One involves a hardware instruction counter. Using th= is you can record exactly in what moment some input (e.g. an interrupt) was= received. Hardware instruction counters in current CPUs are however pretty= imprecise, in particular in x86. Motorola PowerPC 7410 is pretty precise. An alternative technique is called "unique marker". When there is an interr= upt you record some checksums over the register file, parts of the stack et= c. For the replay you insert breakpoint instructions at all places where an= interrupt had occured in the execution phase. By comparing the stored chec= ksum with the current register file/stack you can determine "where" in the = program flow you are. Obviously there is potential for ambiguity but not mu= ch. It works in practice. Henrik Thane at the MRTC (M=E4lardalen Real Time = Research Center, http://www.mrtc.mdh.se/) works on this.=20 Because I want to work on x86 I favour the latter approach.=20 Regards, Oliver ___________________________________________________________________________= ___ Es geht nicht mehr ohne Handy, aber geht es auch guenstiger? Ja, mit Call by Call vom Handy. http://handybycall.web.de/?mc=3D021103 ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf _______________________________________________ User-mode-linux-devel mailing list User-mode-linux-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel