From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753691AbaIHMcv (ORCPT ); Mon, 8 Sep 2014 08:32:51 -0400 Received: from mx1.redhat.com ([209.132.183.28]:40535 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751781AbaIHMcu (ORCPT ); Mon, 8 Sep 2014 08:32:50 -0400 Date: Mon, 8 Sep 2014 14:32:00 +0200 From: Jiri Olsa To: Peter Zijlstra Cc: Jiri Olsa , linux-kernel@vger.kernel.org, Andi Kleen , Arnaldo Carvalho de Melo , Corey Ashford , David Ahern , Frederic Weisbecker , Ingo Molnar , "Jen-Cheng(Tommy) Huang" , Namhyung Kim , Paul Mackerras , Stephane Eranian Subject: Re: [PATCH 1/9] perf: Remove redundant parent context check from context_equiv Message-ID: <20140908123200.GC17728@krava.brq.redhat.com> References: <1408977943-16594-1-git-send-email-jolsa@kernel.org> <1408977943-16594-2-git-send-email-jolsa@kernel.org> <20140902105036.GH5806@worktop.ger.corp.intel.com> <20140908094348.GB1172@krava.brq.redhat.com> <20140908094548.GA6758@twins.programming.kicks-ass.net> <20140908094855.GR3588@twins.programming.kicks-ass.net> <20140908100122.GS3588@twins.programming.kicks-ass.net> <20140908113958.GT3588@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20140908113958.GT3588@twins.programming.kicks-ass.net> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Sep 08, 2014 at 01:39:58PM +0200, Peter Zijlstra wrote: > On Mon, Sep 08, 2014 at 12:01:22PM +0200, Peter Zijlstra wrote: > > On Mon, Sep 08, 2014 at 11:48:55AM +0200, Peter Zijlstra wrote: > > > > > > The thing is; I don't understand those reasons. That commit log doesn't > > > > explain. > > > > > > Ah wait, I finally see. I think we want to fix that exit path, not > > > disallow the cloning. > > > > > > The thing is, by not allowing this optimization simple things like eg. > > > pipe-test say very expensive. > > > > So its 179033b3e064 ("perf: Add PERF_EVENT_STATE_EXIT state for events > > with exited task") that introduces the problem. Before that things would > > work correctly afaict. > > > > The exit would remove from the context but leave the event in existence. > > Both the fd and the inherited events would have references to it, only > > once those are gone do we destroy the actual event. > > I have another 'problem' with 179033b3e064. What if you 'want' to > continue monitoring after the initial task died? Eg. if you want to > monitor crap that unconditionally daemonizes. > > So at this point I would suggest we revert both 179033b3e064 and > 1f9a7268c67f so that the context switch optimization works again for > simple 2 task things (pipe-test). > > If we re-introduce 179033b3e064 (which I think makes sense) we need to > make sure it works with the context switch optimization (we could add > perf_event::task I think, it would clean up a few other things iirc) and > we'd have to make it conditional so we can still monitor daemons. > > Or am I totally missing things again? as I said in previous email I dont think the 179033b3e064 introduced the issue and I think we should keep 1f9a7268c67f to have correct numbers ;-) I'll think about the fix to keep non-cloned context in optimized switch jirka