From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756789Ab3A0NPB (ORCPT ); Sun, 27 Jan 2013 08:15:01 -0500 Received: from mail-ea0-f177.google.com ([209.85.215.177]:49742 "EHLO mail-ea0-f177.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756712Ab3A0NO4 (ORCPT ); Sun, 27 Jan 2013 08:14:56 -0500 Date: Sun, 27 Jan 2013 14:14:51 +0100 From: Ingo Molnar To: Andi Kleen Cc: linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl, akpm@linux-foundation.org, acme@redhat.com, eranian@google.com, jolsa@redhat.com, namhyung@kernel.org, Andi Kleen Subject: Re: [PATCH 04/12] perf, x86: Support the TSX intx/intx_cp qualifiers v2 Message-ID: <20130127131451.GE3933@gmail.com> References: <1359151245-13179-1-git-send-email-andi@firstfloor.org> <1359151245-13179-5-git-send-email-andi@firstfloor.org> <20130126115402.GA13445@gmail.com> <20130126210000.GK30577@one.firstfloor.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130126210000.GK30577@one.firstfloor.org> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Andi Kleen wrote: > On Sat, Jan 26, 2013 at 12:54:02PM +0100, Ingo Molnar wrote: > > > > * Andi Kleen wrote: > > > > > From: Andi Kleen > > > > > > Implement the TSX transaction and checkpointed transaction > > > qualifiers for Haswell. This allows e.g. to profile the number > > > of cycles in transactions. > > > > The changelog should explain why this is a basic feature > > that is a must-have to have basic perf support. (i.e. > > default 'perf record', 'perf report', 'perf stat' and 'perf > > top' works and is meaningful.) > > The patch is not needed for primitive cycle sampling only. So please re-send a truly minimal hw-enabling series first, as requested - a minimal series that enables most of the everyday usecases. > These qualifiers are a fundamental feature for any TSX tuning. Any new, Haswell-specific profiling features should obviously be in a second (or third) series of patches. Thanks, Ingo