Date: Mon, 14 Mar 2011 22:26:17 -0400 (EDT)
From: Vince Weaver <vweaver1@eecs.utk.edu>
To: Arnaldo Carvalho de Melo <acme@redhat.com>
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
In-Reply-To: <alpine.DEB.2.00.1103142026350.16076@cl320.eecs.utk.edu>
Message-ID: <alpine.DEB.2.00.1103142224150.20209@cl320.eecs.utk.edu>
References: <alpine.DEB.2.00.1103111745070.15818@cl320.eecs.utk.edu> <alpine.DEB.2.00.1103141824190.13179@cl320.eecs.utk.edu> <20110314223224.GD9388@ghostprotocols.net> <alpine.DEB.2.00.1103142026350.16076@cl320.eecs.utk.edu>
User-Agent: Alpine 2.00 (DEB 1167 2008-08-23)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1438
Lines: 35

On Mon, 14 Mar 2011, Vince Weaver wrote:

> On Mon, 14 Mar 2011, Arnaldo Carvalho de Melo wrote:
> 
> > 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
> 
> This changeset was reverted already in 
> e3174cfd2a1e28fff774681f00a0eef3d31da970
> yet somehow that didn't fix the inherit mem-leak.

I see, a new fix was made immediately after the revert, 
   050735b08ca8a016bbace4445fa025b88fee770b
which probably immediately re-introduced the problem, which is why
git bisect didn't catch this.  I'm away from my test machine so I'll
have to wait until tomorrow before I can investigate more.

Vince
vweaver1@eecs.utk.edu
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/