From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marcelo Tosatti Subject: Re: [PATCH 00/10] uq/master: irqchip-in-kernel support Date: Mon, 8 Mar 2010 17:56:40 -0300 Message-ID: <20100308205640.GB14679@amt.cnet> References: <1267215141-13629-1-git-send-email-glommer@redhat.com> <4B8FE0CC.4010103@siemens.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Glauber Costa , kvm@vger.kernel.org To: Jan Kiszka Return-path: Received: from mx1.redhat.com ([209.132.183.28]:11542 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752323Ab0CHU5V (ORCPT ); Mon, 8 Mar 2010 15:57:21 -0500 Content-Disposition: inline In-Reply-To: <4B8FE0CC.4010103@siemens.com> Sender: kvm-owner@vger.kernel.org List-ID: On Thu, Mar 04, 2010 at 05:33:16PM +0100, Jan Kiszka wrote: > Glauber Costa wrote: > > Hi guys, > > > > This is the same in-kernel irqchip support already posted to qemu-devel, > > just rebased, retested, etc. It passes my basic tests, so it seem to be > > still in good shape. > > > > It is provided against uq/master as part of the integration efforts > > Just as another heads-up: > > host->guest networking performance over slirp and non-virtio NICs > suffers with this irqchip support the same way as in qemu-kvm. It's not > a bug I expect to be directly related to these changes, but it is at > least triggered by them and should now really be addressed. Isnt it triggered by enablement of the iothread (and if so irqchip support is unrelated to the problem) ?