From mboxrd@z Thu Jan 1 00:00:00 1970 Content-Type: multipart/mixed; boundary="===============3957910083441725202==" MIME-Version: 1.0 From: Peter Zijlstra To: lkp@lists.01.org Subject: Re: [xfs] 68a9f5e700: aim7.jobs-per-min -13.6% regression Date: Wed, 17 Aug 2016 18:24:51 +0200 Message-ID: <20160817162451.GC24652@twins.programming.kicks-ass.net> In-Reply-To: <20160815050300.GA16267@gmail.com> List-Id: --===============3957910083441725202== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On Mon, Aug 15, 2016 at 07:03:00AM +0200, Ingo Molnar wrote: > = > * Linus Torvalds wrote: > = > > Make sure you actually use "perf record -e cycles:pp" or something > > that uses PEBS to get real profiles using CPU performance counters. > = > Btw., 'perf record -e cycles:pp' is the default now for modern versions > of perf tooling (on most x86 systems) - if you do 'perf record' it will > just use the most precise profiling mode available on that particular > CPU model. > = > If unsure you can check the event that was used, via: > = > triton:~> perf report --stdio 2>&1 | grep '# Samples' > # Samples: 27K of event 'cycles:pp' Problem here is that Dave is using a KVM thingy. Getting hardware counters in a guest is somewhat tricky but doable, but PEBS does not virtualize. --===============3957910083441725202==-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752899AbcHQQ0x (ORCPT ); Wed, 17 Aug 2016 12:26:53 -0400 Received: from bombadil.infradead.org ([198.137.202.9]:33560 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752106AbcHQQ0v (ORCPT ); Wed, 17 Aug 2016 12:26:51 -0400 Date: Wed, 17 Aug 2016 18:24:51 +0200 From: Peter Zijlstra To: Ingo Molnar Cc: Linus Torvalds , Dave Chinner , Tejun Heo , Wu Fengguang , "Kirill A. Shutemov" , Christoph Hellwig , "Huang, Ying" , LKML , Bob Peterson , LKP , Arnaldo Carvalho de Melo Subject: Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.6% regression Message-ID: <20160817162451.GC24652@twins.programming.kicks-ass.net> References: <20160812005442.GN19025@dastard> <20160812035645.GQ19025@dastard> <20160815004826.GW19025@dastard> <20160815022808.GX19025@dastard> <20160815050300.GA16267@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160815050300.GA16267@gmail.com> User-Agent: Mutt/1.5.23.1 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Aug 15, 2016 at 07:03:00AM +0200, Ingo Molnar wrote: > > * Linus Torvalds wrote: > > > Make sure you actually use "perf record -e cycles:pp" or something > > that uses PEBS to get real profiles using CPU performance counters. > > Btw., 'perf record -e cycles:pp' is the default now for modern versions > of perf tooling (on most x86 systems) - if you do 'perf record' it will > just use the most precise profiling mode available on that particular > CPU model. > > If unsure you can check the event that was used, via: > > triton:~> perf report --stdio 2>&1 | grep '# Samples' > # Samples: 27K of event 'cycles:pp' Problem here is that Dave is using a KVM thingy. Getting hardware counters in a guest is somewhat tricky but doable, but PEBS does not virtualize.