From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: Performance test result between per-vhost kthread disable and enable Date: Thu, 9 Dec 2010 15:34:31 +0200 Message-ID: <20101209133431.GA22628@redhat.com> References: <20101209133108.GB22460@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: tj@kernel.org, sri@us.ibm.com, Avi Kivity , kvm@vger.kernel.org To: lidong chen Return-path: Received: from mx1.redhat.com ([209.132.183.28]:7680 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750962Ab0LINe7 (ORCPT ); Thu, 9 Dec 2010 08:34:59 -0500 Content-Disposition: inline In-Reply-To: <20101209133108.GB22460@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Thu, Dec 09, 2010 at 03:31:08PM +0200, Michael S. Tsirkin wrote: > On Tue, Nov 23, 2010 at 10:13:43AM +0800, lidong chen wrote: > > I test the performance between per-vhost kthread disable and enable. > > > > Test method: > > Send the same traffic load between per-vhost kthread disable and > > enable, and compare the cpu rate of host os. > > I run five vm on kvm, each of them have five nic. > > the vhost version which per-vhost kthread disable we used is rhel6 > > beta 2(2.6.32.60). > > the vhost version which per-vhost kthread enable we used is rhel6 (2.6.32-71). > > > > Test result: > > with per-vhost kthread disable, the cpu rate of host os is 110%. > > with per-vhost kthread enable, the cpu rate of host os is 130%. > > Does it help if we schedule out the thread once we've passed > once over all vqs? Also, could you please check whether applying kvm: fast-path msi injection with irqfd makes any difference? That relieves the pressure on the scheduler by sending the interrupt directly from vhost without involving yet another thread.