From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753979AbbCaAV7 (ORCPT <rfc822;w@1wt.eu>);
	Mon, 30 Mar 2015 20:21:59 -0400
Received: from lgeamrelo04.lge.com ([156.147.1.127]:44108 "EHLO
	lgeamrelo04.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753524AbbCaAV4 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 30 Mar 2015 20:21:56 -0400
X-Original-SENDERIP: 10.177.220.203
X-Original-MAILFROM: namhyung@kernel.org
Date: Tue, 31 Mar 2015 09:15:15 +0900
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>, David Ahern <dsahern@gmail.com>,
        Jiri Olsa <jolsa@kernel.org>, Stephane Eranian <eranian@google.com>,
        LKML <linux-kernel@vger.kernel.org>
Subject: Re: [BUG] segfault in perf-top -- thread refcnt
Message-ID: <20150331001515.GD32033@sejong>
References: <20150327201126.GM21510@kernel.org>
 <5515B9E6.5020007@gmail.com>
 <20150330080737.GD1413@krava>
 <20150330102220.GE1413@krava>
 <20150330112108.GG1413@krava>
 <20150330114907.GH1413@krava>
 <20150330124852.GA4507@danjae.kornet>
 <20150330125631.GI1413@krava>
 <CAM9d7chr8SuH+6Qoa2mmY2OdemD1KMmbUv_ODS7HLiiZ2xGYGg@mail.gmail.com>
 <20150330140239.GB32560@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20150330140239.GB32560@kernel.org>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Hi Arnaldo,

On Mon, Mar 30, 2015 at 11:02:39AM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Mar 30, 2015 at 10:06:35PM +0900, Namhyung Kim escreveu:
> > On Mon, Mar 30, 2015 at 9:56 PM, Jiri Olsa <jolsa@redhat.com> wrote:
> > > On Mon, Mar 30, 2015 at 09:48:52PM +0900, Namhyung Kim wrote:
> > >> > @@ -380,10 +381,13 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
> > >> >     if (!create)
> > >> >             return NULL;
> > >> >
> > >> > -   th = thread__new(pid, tid);
> > >> > +   th = thread__new(machine, pid, tid);
> > >> >     if (th != NULL) {
> > >> > +
> > >> > +           pthread_mutex_lock(&machine->threads_lock);
> > >> >             rb_link_node(&th->rb_node, parent, p);
> > >> >             rb_insert_color(&th->rb_node, &machine->threads);
> > >> > +           pthread_mutex_unlock(&machine->threads_lock);
> > >>
> > >> I think you also need to protect the rb tree traversal above.
> > >
> > > yep, I already have another version.. but it blows on another place ;-)
> > >
> > >>
> > >> But this makes every sample processing grabs and releases the lock so
> > >> might cause high overhead.  It can be a problem if such processing is
> > >> done parallelly like my multi-thread work. :-/
> > >
> > > yep.. perhaps instead of more locking we need to find a way where
> > > only single thread do the update on hists/threads
> > 
> > Agreed.
> > 
> > AFAIK the reason we do ref-counting is to cleanup dead/exited thread
> > for live session like perf top.  In that case we can somehow mark
> > to-be-deleted thread and kill it in a safe time/place..
> 
> Humm, you mean have another list node in struct threads and add threads
> to another dead_threads like list, i.e. one that is _really_ dead as no
> more refcounts point to it, and then amortize the costs of removing it
> from the rb_tree by removing multiple threads instead of just one?

Yes, I really want to avoid any overhead on the fastpath.  Instead of
refcnt, how about marking and deleting dead threads by the perf top's
display thread unless it's not a selected one?

Thanks,
Namhyung