From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: Huge memory leak in virtio, see kvm-Bugs-2989366 Date: Wed, 21 Apr 2010 11:25:58 +0300 Message-ID: <4BCEB696.2030009@redhat.com> References: <20100420222956.GA13218@moo.pl> <08761DCA-B8FA-41C8-A839-52E09BC06824@suse.de> <20100421075310.GA19155@moo.pl> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-2; format=flowed Content-Transfer-Encoding: 7bit Cc: Alexander Graf , kvm@vger.kernel.org To: Leszek Urbanski Return-path: Received: from mx1.redhat.com ([209.132.183.28]:32777 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752763Ab0DUI0G (ORCPT ); Wed, 21 Apr 2010 04:26:06 -0400 In-Reply-To: <20100421075310.GA19155@moo.pl> Sender: kvm-owner@vger.kernel.org List-ID: On 04/21/2010 10:53 AM, Leszek Urbanski wrote: > <08761DCA-B8FA-41C8-A839-52E09BC06824@suse.de>; from Alexander Graf on Wed, Apr 21, 2010 at 00:51:21 +0200 > > >>> -039b9000-5ccd0000 rw-p 00000000 00:00 0 >>> +039b9000-65803000 rw-p 00000000 00:00 0 >>> >>> (a heap leak?) >>> >>> I'm willing to debug further. The problem is 100% reproducible. >>> >> Certainly something malloc()'ed. It'd be great to send this through valgrind. Thanks to KVM the guest still runs natively, so the slowdown isn't _that_ bug through it. I'm also not a valgrind expert, but IIRC there was a separate memory allocation module. >> > Unfortunately, KVM guests with virtio won't even finish booting with valgrind. > The guest's kernel complains about I/O errors in the first sectors of the > virtio root device. > > You can try glibc's malloc tracing, see libc's mtrace(). -- error compiling committee.c: too many arguments to function