From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754903Ab1KHKd1 (ORCPT ); Tue, 8 Nov 2011 05:33:27 -0500 Received: from merlin.infradead.org ([205.233.59.134]:35705 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751285Ab1KHKdZ convert rfc822-to-8bit (ORCPT ); Tue, 8 Nov 2011 05:33:25 -0500 Subject: Re: [F.A.Q.] perf ABI backwards and forwards compatibility From: Peter Zijlstra To: Ingo Molnar Cc: "Ted Ts'o" , Pekka Enberg , "Frank Ch. Eigler" , Vince Weaver , Pekka Enberg , Anthony Liguori , Avi Kivity , "kvm@vger.kernel.org list" , "linux-kernel@vger.kernel.org List" , qemu-devel Developers , Alexander Graf , Blue Swirl , =?ISO-8859-1?Q?Am=E9rico?= Wang , Linus Torvalds , Arnaldo Carvalho de Melo Date: Tue, 08 Nov 2011 11:32:46 +0100 In-Reply-To: <20111108102235.GA1241@elte.hu> References: <20111106183132.GA4500@thunk.org> <20111106231953.GD4500@thunk.org> <20111107175942.GA9395@elte.hu> <20111107203514.GG24234@thunk.org> <20111108102235.GA1241@elte.hu> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT X-Mailer: Evolution 3.0.3- Message-ID: <1320748366.2244.15.camel@twins> Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2011-11-08 at 11:22 +0100, Ingo Molnar wrote: > > We do even more than that, the perf ABI is fully backwards *and* > forwards compatible: you can run older perf on newer ABIs and newer > perf on older ABIs. The ABI yes, the tool no, the tool very much relies on some newer ABI parts. Supporting fallbacks isn't always possible/wanted. From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [F.A.Q.] perf ABI backwards and forwards compatibility Date: Tue, 08 Nov 2011 11:32:46 +0100 Message-ID: <1320748366.2244.15.camel@twins> References: <20111106183132.GA4500@thunk.org> <20111106231953.GD4500@thunk.org> <20111107175942.GA9395@elte.hu> <20111107203514.GG24234@thunk.org> <20111108102235.GA1241@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Cc: Alexander Graf , Ted Ts'o , Arnaldo Carvalho de Melo , "kvm@vger.kernel.org list" , qemu-devel Developers , Vince Weaver , "linux-kernel@vger.kernel.org List" , Pekka Enberg , Blue Swirl , "Frank Ch. Eigler" , Pekka Enberg , Avi Kivity , =?ISO-8859-1?Q?Am=E9rico?= Wang , Linus Torvalds To: Ingo Molnar Return-path: In-Reply-To: <20111108102235.GA1241@elte.hu> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org Sender: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org List-Id: kvm.vger.kernel.org On Tue, 2011-11-08 at 11:22 +0100, Ingo Molnar wrote: >=20 > We do even more than that, the perf ABI is fully backwards *and*=20 > forwards compatible: you can run older perf on newer ABIs and newer=20 > perf on older ABIs.=20 The ABI yes, the tool no, the tool very much relies on some newer ABI parts. Supporting fallbacks isn't always possible/wanted. From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:41542) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1RNizY-0005fX-Bc for qemu-devel@nongnu.org; Tue, 08 Nov 2011 05:33:21 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1RNizX-0008EO-EX for qemu-devel@nongnu.org; Tue, 08 Nov 2011 05:33:20 -0500 Received: from merlin.infradead.org ([205.233.59.134]:58345) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1RNizX-0008DI-Bw for qemu-devel@nongnu.org; Tue, 08 Nov 2011 05:33:19 -0500 From: Peter Zijlstra Date: Tue, 08 Nov 2011 11:32:46 +0100 In-Reply-To: <20111108102235.GA1241@elte.hu> References: <20111106183132.GA4500@thunk.org> <20111106231953.GD4500@thunk.org> <20111107175942.GA9395@elte.hu> <20111107203514.GG24234@thunk.org> <20111108102235.GA1241@elte.hu> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Message-ID: <1320748366.2244.15.camel@twins> Mime-Version: 1.0 Subject: Re: [Qemu-devel] [F.A.Q.] perf ABI backwards and forwards compatibility List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Ingo Molnar Cc: Alexander Graf , Ted Ts'o , Arnaldo Carvalho de Melo , "kvm@vger.kernel.org list" , qemu-devel Developers , Vince Weaver , "linux-kernel@vger.kernel.org List" , Pekka Enberg , Blue Swirl , "Frank Ch. Eigler" , Pekka Enberg , Avi Kivity , =?ISO-8859-1?Q?Am=E9rico?= Wang , Linus Torvalds On Tue, 2011-11-08 at 11:22 +0100, Ingo Molnar wrote: >=20 > We do even more than that, the perf ABI is fully backwards *and*=20 > forwards compatible: you can run older perf on newer ABIs and newer=20 > perf on older ABIs.=20 The ABI yes, the tool no, the tool very much relies on some newer ABI parts. Supporting fallbacks isn't always possible/wanted.