From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752045AbaE1RJY (ORCPT ); Wed, 28 May 2014 13:09:24 -0400 Received: from bombadil.infradead.org ([198.137.202.9]:50154 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751402AbaE1RJX (ORCPT ); Wed, 28 May 2014 13:09:23 -0400 Date: Wed, 28 May 2014 19:09:13 +0200 From: Peter Zijlstra To: Andi Kleen Cc: Stephane Eranian , "Yan, Zheng" , LKML , "mingo@elte.hu" Subject: Re: [RFC PATCH 6/7] perf, x86: large PEBS interrupt threshold Message-ID: <20140528170913.GU30445@twins.programming.kicks-ass.net> References: <1401257890-30535-1-git-send-email-zheng.z.yan@intel.com> <1401257890-30535-7-git-send-email-zheng.z.yan@intel.com> <20140528081053.GP11096@twins.programming.kicks-ass.net> <20140528145831.GH29957@tassilo.jf.intel.com> <20140528165144.GK29957@tassilo.jf.intel.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="xCod2j9FiOMpaQ8M" Content-Disposition: inline In-Reply-To: <20140528165144.GK29957@tassilo.jf.intel.com> User-Agent: Mutt/1.5.21 (2012-12-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --xCod2j9FiOMpaQ8M Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, May 28, 2014 at 09:51:44AM -0700, Andi Kleen wrote: > > The only part I don't quite follow here is this: > > if (__test_and_set_bit(bit, (unsigned long *)&sta= tus)) > > continue; > >=20 > > Which seems to indicate the code is making sure each counter is > > processed only once. But it can only be processed once, if you have > > only one record. And if you have multiple, you want to be able to > > handle the same counter multiple times, at least once perf PEBS > > record. So I am a bit confused about this test. >=20 > Each PEBS record is only for a single counter overflow. So it > always should only be a single perf event. OK, so what Stephane said, that two counter's having their assist on the exact same cycle results in but a single record is false? That would be good. --xCod2j9FiOMpaQ8M Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAEBAgAGBQJThhg5AAoJEHZH4aRLwOS6dvoP/1Wk3dEW9oUTnS4ckohnA5ih Iwx8+tZwUPr43x/OTsl4YWe6fKTHltYCWcWjIOUnHmVXruRg5oF1ZPwivpzPJr8T JVVQ3/XqqbBWiV6eV0NbRmRLAix5BMCTJT3w9+vjKdAq4y1zsUxQl84RLS5ztThK a0f5Zg1aFSclJYg3YVUo9P+6FGhCVednd3SNiSD1l5FiqjNlo+GnfaDQOv/8tfAu rBfy/IEOUizijx90hojlbA4knOYCNef9ceNrTqbPJ2XZ5Wp9DDDN16lYZFek4WxA cuyQ9Ua8HiZVHldOLZZNaZlCCh5OYeagemihtCGDPM0Us95QLQ04Qrdqv0E/mdX7 MXBOt/c9ZG5Uf9tFXyub0FCnH3iQiBbJt6DCg8LW12MazTE3woH70f1ZUh+3dBFD GRlx69+ArkGDgUiKV4Tq3QFEyOFJHm/lBQLcDp0C57ezZSADFAXiSEgUw6cA4Szr KcPIYRkfWWDQ763l1G0aRuUuRewXT/FaEFDN8nQlt8qYXBL5tgg16CjRirQI8kXi tfbDKOP5l/58pUAVyVof0ITLgAob89668l7+bgWpJCifDzfwmBk2pSASdm1lpe6m D12PKSdU7H+aKKscIBHc75008QkUqCJ/g8ySwe125QEx0TnnzT348gjIfbyG/TO2 ptSH8jDjM6d8yKt2DPBd =IJ8y -----END PGP SIGNATURE----- --xCod2j9FiOMpaQ8M--