From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763938AbXGFRuh (ORCPT ); Fri, 6 Jul 2007 13:50:37 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761137AbXGFRu3 (ORCPT ); Fri, 6 Jul 2007 13:50:29 -0400 Received: from mail.windriver.com ([147.11.1.11]:57305 "EHLO mail.wrs.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760967AbXGFRu3 (ORCPT ); Fri, 6 Jul 2007 13:50:29 -0400 Message-ID: <468E8106.8080801@windriver.com> Date: Fri, 06 Jul 2007 12:51:02 -0500 From: Jason Wessel User-Agent: Thunderbird 1.5.0.12 (X11/20070530) MIME-Version: 1.0 To: Tilman Schmidt CC: linux-kernel@vger.kernel.org, Andrew Morton , kgdb-bugreport@lists.sourceforge.net Subject: Re: kgdb Bad IO access References: <20070628034321.38c9f12b.akpm@linux-foundation.org> <468E4BA5.8010601@imap.cc> In-Reply-To: <468E4BA5.8010601@imap.cc> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 06 Jul 2007 17:50:11.0261 (UTC) FILETIME=[196A5ED0:01C7BFF6] Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Tilman Schmidt wrote: > Apart from that, the kernel runs fine, though its subjectively a bit > sluggish compared to 2.6.22-rc6-mm1 without kgdb. Its uname -a is: > Linux xenon 2.6.22-rc6-mm1-test4 #10 SMP PREEMPT Thu Jul 5 23:41:32 CEST 2007 i686 i686 i386 GNU/Linux > I didn't even try to actually do anything with kgdb, though. > > Do you have something that is more than subjective as a measure? Some app runs slower, or it boots x seconds slower? The only place I could foresee that kgdb could be eating extra cycles in the runtime case is from the die_notifier processing. Any kind of exception such as a page fault, trap etc... will have a few extra ops and checks of variables so as to determine if the debugger should take the exception. It looks to me like it would even benefit to add the check at the top of the notify hook for kgdb to exit immediately if the debugger is not attached. I have contemplated making some changes to KGDB so as to make the registration to the die_notifier to be dynamic with attaching and detaching of the debugger. If this is done, I would also make a change to allow for the case where the kernel would wait for the debugger to attach on any fatal fault. Jason.