From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753721AbbJTW2v (ORCPT ); Tue, 20 Oct 2015 18:28:51 -0400 Received: from one.firstfloor.org ([193.170.194.197]:48037 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753471AbbJTW2r (ORCPT ); Tue, 20 Oct 2015 18:28:47 -0400 Date: Wed, 21 Oct 2015 00:28:44 +0200 From: Andi Kleen To: Peter Zijlstra Cc: Andi Kleen , linux-kernel@vger.kernel.org, Andi Kleen , Ingo Molnar , Thomas Gleixner Subject: Re: [PATCH] x86, perf: Use INST_RETIRED.PREC_DIST for cycles:pp on Skylake Message-ID: <20151020222844.GK3533@two.firstfloor.org> References: <1445295496-8550-1-git-send-email-andi@firstfloor.org> <20151020113608.GC17308@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20151020113608.GC17308@twins.programming.kicks-ass.net> 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 > Typically on workstations you do not, because there's only a single > user, but on servers it might be more common. The thing I expect to be > most common is having both a CPU wide and a per task cycle counter > enabled. With multiple users they would sample only their own processes. That works fine. The only thing that needs multiplexing is overlapping sampling. perf top also works fine because it doesn't use PEBS by default. > And you having killed the flag bits for PEBS events precludes people > from using this manually, right? I think we want to exempt .inv=1 > .cmask=16 from that general rule on general utility value. I don't want to do this for every event. It has caused problems in the past. There's also no reason to use the other events. > We could maybe abuse .precise_ip = 3 for this? I implemented this now, even though it's ugly. -Andi