From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760751AbcIWUfc (ORCPT ); Fri, 23 Sep 2016 16:35:32 -0400 Received: from merlin.infradead.org ([205.233.59.134]:51122 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760442AbcIWUfa (ORCPT ); Fri, 23 Sep 2016 16:35:30 -0400 Date: Fri, 23 Sep 2016 22:35:27 +0200 From: Peter Zijlstra To: Andi Kleen Cc: Alexander Shishkin , Ingo Molnar , linux-kernel@vger.kernel.org, vince@deater.net, eranian@google.com, Arnaldo Carvalho de Melo , tglx@linutronix.de Subject: Re: [RFC PATCH 0/6] perf: Add AUX data sampling Message-ID: <20160923203527.GR5008@twins.programming.kicks-ass.net> References: <20160923112726.5890-1-alexander.shishkin@linux.intel.com> <20160923114917.GI5008@twins.programming.kicks-ass.net> <20160923171943.GT3078@tassilo.jf.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160923171943.GT3078@tassilo.jf.intel.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 Fri, Sep 23, 2016 at 10:19:43AM -0700, Andi Kleen wrote: > On Fri, Sep 23, 2016 at 01:49:17PM +0200, Peter Zijlstra wrote: > > On Fri, Sep 23, 2016 at 02:27:20PM +0300, Alexander Shishkin wrote: > > > Hi Peter, > > > > > > This is an RFC, I'm not sending the tooling bits in this series, > > > although they can be found here [1]. > > > > > > This series introduces AUX data sampling for perf events, which in > > > case of our instruction/branch tracing PMUs like Intel PT, BTS, CS > > > ETM means execution flow history leading up to a perf event's > > > overflow. > > > > This fails to explain _WHY_ this is a good thing to have. What kind of > > analysis does this enable, and is that fully implemented in [1] (I > > didn't look). > > Think of it as a super LBR. (Near) all things LBR can do, PT can do > with much more branches for each sample. Clarify the 'near'? Should we then not expose it as a BRANCH_STACK? Expand on the down-sides of that. > Also long term execution recording of PT normally doesn't work well because the > sustained bandwidth is too high for perf and the disk to keep up > > Currently the main solution we have for that is the snapshot mode, but it > requires explicit instrumentation for someone to trigger snapshots. > > Sampling PT is an alternative that works for many use cases, and does > not rely on instrumentation. List a few use-cases on either side of that divide ? This really isn't rocket science, patches should come with justification, try and sell this stuff. Don't try and skimp on that.