From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753598AbbDHNpp (ORCPT ); Wed, 8 Apr 2015 09:45:45 -0400 Received: from mail.kernel.org ([198.145.29.136]:51473 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751394AbbDHNpo (ORCPT ); Wed, 8 Apr 2015 09:45:44 -0400 Date: Wed, 8 Apr 2015 10:45:45 -0300 From: Arnaldo Carvalho de Melo To: David Ahern Cc: Linux Kernel Mailing List , Don Zickus , Jiri Olsa , Joe Mario , Ingo Molnar Subject: Re: BUG: perf top enters loop synthesizing events for existing threads Message-ID: <20150408134545.GD5403@kernel.org> References: <20150408134251.GC5403@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150408134251.GC5403@kernel.org> X-Url: http://acmel.wordpress.com 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 Em Wed, Apr 08, 2015 at 10:42:51AM -0300, Arnaldo Carvalho de Melo escreveu: > Heads up, > > While testing some unrelated patches I noticed, in one of my > machines, that 'perf top', as root, is entering some sort of loop and > ends up consuming a lot of memory, making the system unresponsive, > bisected it down to: > > [acme@zoo linux]$ git bisect good > ca6c41c59b964d362823e80442e9e32c31106b29 is the first bad commit > commit ca6c41c59b964d362823e80442e9e32c31106b29 > Author: David Ahern > Date: Mon Mar 30 14:35:58 2015 -0600 > > perf tools: Fix ppid for synthesized fork events > > 363b785f38 added synthesized fork events and set a thread's parent id to > itself. Since we are already processing /proc//status the ppid can > be determined properly. Make it so. > > Signed-off-by: David Ahern > Acked-by: Don Zickus > Acked-by: Jiri Olsa > Cc: Joe Mario > Link: http://lkml.kernel.org/r/1427747758-18510-2-git-send-email-dsahern@gmail.com > Signed-off-by: Arnaldo Carvalho de Melo > > :040000 040000 24d479e4afbe95aaba882850473a870b6b3c7e87 > cc86fe0e51b5e8a66e8a23f934fd0c4ff0f8dcd6 M tools > [acme@zoo linux]$ > > > I also noticed that if I set /proc/sys/kernel/perf_event_paranoid to -1 > to run it as !root, then the problem "goes away", which I think probably > is explained by, as !root, not being able to parse some of the /proc > files for existing threads and thus not triggering the bug, still > investigating... > > I might need to revert it for this cycle... Just reverting it makes the symptoms go away, to works as before. Trying to understand the problem now. - Arnaldo