public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To: Vince Weaver <vweaver1@eecs.utk.edu>
Cc: linux-kernel@vger.kernel.org,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Paul Mackerras <paulus@samba.org>, Ingo Molnar <mingo@elte.hu>,
	Corey Ashford <cjashfor@linux.vnet.ibm.com>,
	Stephane Eranian <eranian@google.com>
Subject: Re: perf: kernel memory leak when inherit enabled
Date: Mon, 14 Mar 2011 19:32:24 -0300	[thread overview]
Message-ID: <20110314223224.GD9388@ghostprotocols.net> (raw)
In-Reply-To: <alpine.DEB.2.00.1103141824190.13179@cl320.eecs.utk.edu>

Em Mon, Mar 14, 2011 at 06:27:19PM -0400, Vince Weaver escreveu:
> On Fri, 11 Mar 2011, Vince Weaver wrote:
> > 
> > While trying to use perf events with inherit enabled to profile some 
> > multi-threaded BLAS routines (using PAPI) I ended up out-of-memorying my 
> > machine.  It turns out you can quickly leak gigabytes of kernel memory
> > that isn't freed when the process exits.
> 
> I've bisected this.  There's a whole day I'll never see again. binutils 
> 2.21 and gcc-4.5 for the lose :(
> 
> Anyway this memory leak with inherit was introduced in 
>   4fd38e4595e


commit 4fd38e4595e2f6c9d27732c042a0e16b2753049c
Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date:   Thu May 6 17:31:38 2010 +0200

    perf: Fix exit() vs PERF_FORMAT_GROUP
    
    Both Stephane and Corey reported that PERF_FORMAT_GROUP didn't work
    as expected if the task the counters were attached to quit before
    the read() call.
    
    The cause is that we unconditionally destroy the grouping when we
    remove counters from their context. Fix this by only doing this when
    we free the counter itself.
    
    Reported-by: Corey Ashford <cjashfor@linux.vnet.ibm.com>
    Reported-by: Stephane Eranian <eranian@google.com>
    Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
    LKML-Reference: <1273160566.5605.404.camel@twins>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

- Arnaldo

  reply	other threads:[~2011-03-14 22:32 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-11 22:54 perf: kernel memory leak when inherit enabled Vince Weaver
2011-03-14 22:27 ` Vince Weaver
2011-03-14 22:32   ` Arnaldo Carvalho de Melo [this message]
2011-03-15  0:27     ` Vince Weaver
2011-03-15  2:26       ` Vince Weaver
2011-03-15 13:41         ` [PATCH] perf: Fix tear-down of inherited group events Peter Zijlstra
2011-03-15 16:09           ` Vince Weaver
2011-03-15 16:41             ` Peter Zijlstra
2011-03-16 13:59           ` [tip:perf/urgent] " tip-bot for Peter Zijlstra
2011-03-15  9:07   ` perf: kernel memory leak when inherit enabled Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20110314223224.GD9388@ghostprotocols.net \
    --to=acme@redhat.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=cjashfor@linux.vnet.ibm.com \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --cc=vweaver1@eecs.utk.edu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox