From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 12273 invoked by alias); 20 Apr 2010 17:28:52 -0000 Received: (qmail 12251 invoked by uid 22791); 20 Apr 2010 17:28:48 -0000 X-SWARE-Spam-Status: No, hits=-6.9 required=5.0 tests=BAYES_00,RCVD_IN_DNSWL_HI,SPF_HELO_PASS,T_RP_MATCHES_RCVD X-Spam-Check-By: sourceware.org Received: from mx1.redhat.com (HELO mx1.redhat.com) (209.132.183.28) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Tue, 20 Apr 2010 17:28:44 +0000 Received: from int-mx01.intmail.prod.int.phx2.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id o3KHSdiK007696 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Tue, 20 Apr 2010 13:28:39 -0400 Received: from fche.csb (vpn-237-154.phx2.redhat.com [10.3.237.154]) by int-mx01.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id o3KHSdOl001034; Tue, 20 Apr 2010 13:28:39 -0400 Received: by fche.csb (Postfix, from userid 2569) id 6FE435810A; Tue, 20 Apr 2010 13:28:38 -0400 (EDT) To: Dominique Toupin Cc: , Subject: Re: Static/dynamic userspace/kernel trace References: <20100419141356.GC4823@redhat.com> From: fche@redhat.com (Frank Ch. Eigler) Date: Tue, 20 Apr 2010 17:28:00 -0000 In-Reply-To: (Dominique Toupin's message of "Mon, 19 Apr 2010 15:50:01 -0400") Message-ID: User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/21.4 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Mailing-List: contact gdb-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: gdb-owner@sourceware.org X-SW-Source: 2010-04/txt/msg00064.txt.bz2 Dominique Toupin writes: > I agree that GDB could use a better ptrace. Right. And since ptrace proper is needed as a backward compatibility measure, the kernel will in turn need something to multiplex/arbitrate between the different interfaces. So this is how we came to utrace years ago. > Regarding tracing, for me the main use case is to get the data out > of the system very fast and with very low overhead [...] Understood. That same approach underlies other tracing/performance tools. For systemtap, this has been more of an asymptotic case: something it can do too, with other tools providing some tough-to-beat performance (and sometimes usability) benchmarks. - FChE