Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755757Ab0K2Xpq (ORCPT ); Mon, 29 Nov 2010 18:45:46 -0500 Received: from e23smtp08.au.ibm.com ([202.81.31.141]:33572 "EHLO e23smtp08.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753534Ab0K2Xpp (ORCPT ); Mon, 29 Nov 2010 18:45:45 -0500 Content-Type: text/plain; charset=UTF-8 Cc: Arnaldo Carvalho de Melo , linux-kernel , Paul Mackerras , Ingo Molnar Subject: Re: [PATCH 3/6] perf: Add timestamp to COMM and MMAP events From: Ian Munsie To: Peter Zijlstra In-reply-to: <1291031690.32004.20.camel@laptop> References: <1290490544-14349-1-git-send-email-imunsie@au1.ibm.com> <1290490544-14349-4-git-send-email-imunsie@au1.ibm.com> <1290510512.2072.387.camel@laptop> <20101123124121.GA11101@ghostprotocols.net> <20101125154718.GE15875@ghostprotocols.net> <1291009409-sup-4332@au1.ibm.com> <1291031690.32004.20.camel@laptop> Date: Tue, 30 Nov 2010 10:45:40 +1100 Message-Id: <1291073899-sup-7083@au1.ibm.com> User-Agent: Sup/0.11 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1338 Lines: 30 Hi Peter, Excerpts from Peter Zijlstra's message of Mon Nov 29 22:54:50 +1100 2010: > On Mon, 2010-11-29 at 17:06 +1100, Ian Munsie wrote: > > This goes away if PERF_SAMPLE_CPU is added to the mix so that the > > timestamps are offset from the first event of *their* CPU, otherwise > > time-epoch can go negative, as it has done here. > > How does that happen, I though the power7 sched_clock() was fully > synchronized and monotonic across all cores? Oh the timestamps coming from the kernel are fine, I should have been clearer in my email. This bug is purely restricted to the userspace code that prints them out - in the perf_session__print_tstamp function. It tries to print the timestamps out so that they start at 0 and if it doesn't know what CPU the events came from it uses the very first event it sees as epoch, but at the moment that is not necessarily going to be the earliest event. Thinking about it overnight, I realise that this should also go away if we sort them before printing things out at all, which is exactly what I'm proposing to do in my patches. Cheers, -Ian -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/