From mboxrd@z Thu Jan 1 00:00:00 1970 From: Glauber Costa Subject: Re: migrate_set_downtime bug Date: Wed, 30 Sep 2009 01:48:32 -0300 Message-ID: <20090930044832.GA5149@mothafucka.localdomain> References: <90D306BE6EBC8D428A824FBBA7A3113DFDCDF175@ronja.maurer-it.com> <90D306BE6EBC8D428A824FBBA7A3113DFDCDF178@ronja.maurer-it.com> <90D306BE6EBC8D428A824FBBA7A3113DFDCDF179@ronja.maurer-it.com> <4AC22A4D.5060805@codemonkey.ws> <20090929162345.GX29735@mothafucka.localdomain> <90D306BE6EBC8D428A824FBBA7A3113DFDCDF17D@ronja.maurer-it.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Anthony Liguori , kvm To: Dietmar Maurer Return-path: Received: from mx1.redhat.com ([209.132.183.28]:28978 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751120AbZI3Esf (ORCPT ); Wed, 30 Sep 2009 00:48:35 -0400 Content-Disposition: inline In-Reply-To: <90D306BE6EBC8D428A824FBBA7A3113DFDCDF17D@ronja.maurer-it.com> Sender: kvm-owner@vger.kernel.org List-ID: On Tue, Sep 29, 2009 at 06:36:57PM +0200, Dietmar Maurer wrote: > > Also, if this is really the case (buffered), then the bandwidth capping > > part > > of migration is also wrong. > > > > Have you compared the reported bandwidth to your actual bandwith ? I > > suspect > > the source of the problem can be that we're currently ignoring the time > > we take > > to transfer the state of the devices, and maybe it is not negligible. > > > > I have a 1GB network (e1000 card), and get values like bwidth=0.98 - which is much too high. The main reason for not using the whole migration time is that it can lead to values that are not very helpful in situation where the network load changes too much. Since the problem you pinpointed do exist, I would suggest measuring the average load of the last, say, 10 iterations. How would that work for you?