From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 3659 invoked by alias); 23 Jan 2017 16:05:39 -0000 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 Received: (qmail 3648 invoked by uid 89); 23 Jan 2017 16:05:38 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.4 required=5.0 tests=AWL,BAYES_00,FREEMAIL_FROM,RCVD_IN_DNSWL_NONE,SPF_PASS autolearn=ham version=3.3.2 spammy=Hx-languages-length:1530, H*i:sk:c418f59, H*f:sk:c418f59 X-HELO: mail-wm0-f67.google.com Received: from mail-wm0-f67.google.com (HELO mail-wm0-f67.google.com) (74.125.82.67) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Mon, 23 Jan 2017 16:05:32 +0000 Received: by mail-wm0-f67.google.com with SMTP id r126so27422817wmr.3 for ; Mon, 23 Jan 2017 08:05:31 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:in-reply-to:references:from:date :message-id:subject:to:cc; bh=7xMdgH++YL6nmfTiix+OZ0C13aTp3tCZ1G7F5gjQ7Ps=; b=QIDD4gFhc9XZf2AQMjBd9Q2PTC0pi4mE+HLlQyIvMKHHEakH6EcTFALGZeFTtK2eGZ C41SK+1NAHGnGEBQ1IkfBvSuA2axm5CGQ0FNbBMq1YYMiDHJoSdJddV5Xd15u3766iPN CzSsHTN0RSV7X/NOT6jVadmZftQgTsyWm/OD46rLj1jMqCabvr+HEZctUt87qwDBY8pL BhtlnpQ20DOMsQATw2IJIbMD19EefQLJstZi6wytRvwhZBxIg7Jo37oLaXJwccf4zpgO Jc7U3faykaM2bcoxKDsleUShLxpAn8Dt+sMWn25YQRki1jBduX3N5vX26vHM5ufYwx8i zVPQ== X-Gm-Message-State: AIkVDXIwRK7i7VpPsyjGKJl/GFq6+72yD9LaHxwJbwGwAw6HPRM5FyNtzHDpTy4BFxaeePPQAkoL/7r07oqI4Q== X-Received: by 10.28.174.14 with SMTP id x14mr13647925wme.75.1485187530129; Mon, 23 Jan 2017 08:05:30 -0800 (PST) MIME-Version: 1.0 Received: by 10.80.178.35 with HTTP; Mon, 23 Jan 2017 08:05:29 -0800 (PST) In-Reply-To: References: From: Geoffrey Blake Date: Mon, 23 Jan 2017 16:05:00 -0000 Message-ID: Subject: Re: Issues with @perf directives in systemtap 3.1 on Ubuntu 16.04LTS To: David Smith Cc: systemtap@sourceware.org Content-Type: text/plain; charset=UTF-8 X-SW-Source: 2017-q1/txt/msg00045.txt.bz2 The unmodified perf.stp script is working fine. The modification I made was to probe into a library function call by doing: process("path").library("path").funtion("func") { /* probe code */ } process("path").library("path").funtion("func").return { /* probe code */ } This is still yielding the @perf call giving me the same number on return all the time. Does @perf not work with library functions? Thanks, Geoff Blake On Mon, Jan 23, 2017 at 9:42 AM, David Smith wrote: > On 01/23/2017 07:50 AM, Geoffrey Blake wrote: >> Hi all, >> >> I have been trying to make use of the perf.stp example modified for my >> own program I am trying to profile. I set the perf.hw probes to be >> system wide by not supplying a process, but when my other probes >> trigger and I read the counters with the @perf() directive, the number >> returned for the counters is always the same junk number (it varies >> between runs, but never changes during a run). >> >> I am not sure what could be going on. I have tried the systemtap >> package that ships with Ubuntu 16.04LTS and compiled from the tip of >> the git repository. Both versions have the same failure. Any help >> would be appreciated on how to debug this further. > > Does the unmodified perf.stp example work on your system? How are you > running your modified example? > > -- > David Smith > dsmith@redhat.com > Red Hat > http://www.redhat.com > 256.217.0141 (direct) > 256.837.0057 (fax)