From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 11242 invoked by alias); 5 Aug 2012 20:33:42 -0000 Received: (qmail 11235 invoked by uid 22791); 5 Aug 2012 20:33:42 -0000 X-SWARE-Spam-Status: No, hits=-6.9 required=5.0 tests=AWL,BAYES_00,KHOP_RCVD_UNTRUST,KHOP_THREADED,RCVD_IN_DNSWL_HI,RCVD_IN_HOSTKARMA_W,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; Sun, 05 Aug 2012 20:33:24 +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 (8.14.4/8.14.4) with ESMTP id q75KXNnK004473 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Sun, 5 Aug 2012 16:33:23 -0400 Received: from [10.3.113.47] (ovpn-113-47.phx2.redhat.com [10.3.113.47]) by int-mx01.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id q75KXNHV017524; Sun, 5 Aug 2012 16:33:23 -0400 Message-ID: <501ED893.9000603@redhat.com> Date: Sun, 05 Aug 2012 20:33:00 -0000 From: Josh Stone User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:14.0) Gecko/20120717 Thunderbird/14.0 MIME-Version: 1.0 To: halcyonic@gmail.com CC: systemtap@sourceware.org Subject: Re: atomicity of formatted output? References: <2788A1A0-479D-4244-BD2F-EEDA0DC48C89@eecs.harvard.edu> In-Reply-To: <2788A1A0-479D-4244-BD2F-EEDA0DC48C89@eecs.harvard.edu> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-IsSubscribed: yes Mailing-List: contact systemtap-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sourceware.org X-SW-Source: 2012-q3/txt/msg00156.txt.bz2 On 07/31/2012 10:10 PM, halcyonic@gmail.com wrote: > Sorry, couldn't find this anywhere obvious in the documentation: are > there any atomicity guarantees (even "best effort" ones) regarding > formatted output from inside probes? It looks to me like output from > different probes is being intermingled occasionally, even if every > probe only uses a single printf()...would it help to remove newlines > in the printf()? IIRC, we do try to keep things line-buffered, at least if you are outputting to a TTY. Can you provide an example script & workload where you see this intermingling? Josh