From mboxrd@z Thu Jan 1 00:00:00 1970 From: RW Subject: Re: Network shutdown under load Date: Fri, 05 Feb 2010 08:44:49 +0100 Message-ID: <4B6BCC71.1040609@tauceti.net> References: <4B6ACD27.20605@indigo-logiciels.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: kvm@vger.kernel.org To: Cedric Peltier Return-path: Received: from tauceti.net ([62.245.250.166]:40399 "EHLO www.tauceti.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753516Ab0BEHou (ORCPT ); Fri, 5 Feb 2010 02:44:50 -0500 In-Reply-To: <4B6ACD27.20605@indigo-logiciels.com> Sender: kvm-owner@vger.kernel.org List-ID: Hi, thanks for that! I've running a lot of hosts still running with kernel 2.6.30 and KVM 88 without problems. It seems that all qemu-kvm versions >=3D 0.11.0 have this problem incl. the latest 0.12.2. So if one of the enterprise distributions will choose one of this versions for inclusion in there enterprise products customers will definitley will get problems. This is definitley a showstopper if you can't do more then 30-50 MBit/s over some period of time. I think kernel 2.6.32 will be choosen by a lot of distributions but the problem still exists there as far as I've read the mailings here. Regards, Robert Cedric Peltier wrote: > Hi, > > We encoutered similar problem yesterday by upgrading a developpement > server from ubuntu 9.04 (kernel 2.6.28) to ubuntu 9.10 (kernel 2.6.31= ). > Going back under the kernel 2.6.28 was the solution for us until now.= =2E > > Regards, > > > C=E9dric PELTIER, soci=E9t=E9 Indigo > >