From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755092Ab1HCSDI (ORCPT ); Wed, 3 Aug 2011 14:03:08 -0400 Received: from db3ehsobe003.messaging.microsoft.com ([213.199.154.141]:45577 "EHLO DB3EHSOBE003.bigfish.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754255Ab1HCSDD (ORCPT ); Wed, 3 Aug 2011 14:03:03 -0400 X-SpamScore: -11 X-BigFish: VPS-11(zzbb2dK1432N98dKzz1202hzzz32i668h839h944h) X-Forefront-Antispam-Report: CIP:163.181.249.108;KIP:(null);UIP:(null);IPVD:NLI;H:ausb3twp01.amd.com;RD:none;EFVD:NLI X-WSS-ID: 0LPD5UE-01-1W5-02 X-M-MSG: Date: Wed, 3 Aug 2011 19:56:38 +0200 From: Robert Richter To: Michael Cree CC: Peter Zijlstra , Ingo Molnar , Arnaldo Carvalho de Melo , LKML , Lin Ming Subject: Re: [PATCH 6/7] perf, x86: Example code for AMD IBS Message-ID: <20110803175637.GN11795@erda.amd.com> References: <1311860812-28748-1-git-send-email-robert.richter@amd.com> <1311860812-28748-7-git-send-email-robert.richter@amd.com> <1311958729.5890.413.camel@twins> <20110801055008.GZ4590@erda.amd.com> <1312281474.1147.40.camel@twins> <4E39065C.6020801@orcon.net.nz> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <4E39065C.6020801@orcon.net.nz> User-Agent: Mutt/1.5.21 (2010-09-15) X-OriginatorOrg: amd.com Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 03.08.11 04:27:08, Michael Cree wrote: > On 02/08/11 22:37, Peter Zijlstra wrote: > > Possibly, but having just looked at the example again I don't really see > > it doing anything perf-record doesn't already do, so why does it deserve > > to live at all? I also got it running with perf-record with Lin's patch perf tool: Parse general/raw events from sysfs with no other changes using: perf record -R -e ibs_fetch:r0 -a -c 10000 What is missing here is a parser for the IBS sampling data that is very specific, which would be the perf-ibs-annotate tool you recommended. > > Initially I thought it was a record+report like example, some code > > interpreting the 'mess' that comes out of IBS would be most appreciated > > and I think we can even ship that as perf-ibs-report/perf-ibs-annotate > > or so (and if its still remotely similar to its Alpha precursor that > > might make the Alpha folks happy too). Yes, the example I wrote could use perf-record as backend. The parser for IBS could be part of perf-record, if we encode the pmu name (ibs_op/ibs_fetch) in perf.data. Then we don't neeed a special tool for IBS anymore. > Sure would be nice if the infrastructure to support ProfileMe mode > appeared in the perf. events subsystem. I am not going to go full out > to implement all the support needed for it because there are too few > users on Alpha to justify the effort. But if we could score an > implementation of ProfileMe mode with minimal effort on the back of an > AMD implementation that would make us happy. ProfileMe looks similar to IBS, so the above would fit there too. -Robert -- Advanced Micro Devices, Inc. Operating System Research Center