From owner-freebsd-xen@FreeBSD.ORG Wed Jun 18 13:16:06 2014 Return-Path: Delivered-To: freebsd-xen@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id C06876F0 for ; Wed, 18 Jun 2014 13:16:06 +0000 (UTC) Received: from mail.tdx.com (mail.tdx.com [62.13.128.18]) by mx1.freebsd.org (Postfix) with ESMTP id 69CEA2196 for ; Wed, 18 Jun 2014 13:16:05 +0000 (UTC) Received: from Mail-PC.tdx.co.uk (storm.tdx.co.uk [62.13.130.251]) (authenticated bits=0) by mail.tdx.com (8.14.3/8.14.3/) with ESMTP id s5IDBclR044719 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Wed, 18 Jun 2014 14:11:39 +0100 (BST) Date: Wed, 18 Jun 2014 14:11:38 +0100 From: Karl Pielorz To: freebsd-xen@freebsd.org Subject: re. pr188261 - any way I can investigate further? Message-ID: <7B689F2C8C07F01AD552CA61@Mail-PC.tdx.co.uk> X-Mailer: Mulberry/4.0.8 (Win32) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline X-BeenThere: freebsd-xen@freebsd.org X-Mailman-Version: 2.1.18 Precedence: list List-Id: Discussion of the freebsd port to xen - implementation and usage List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 18 Jun 2014 13:16:06 -0000 Hi, I submitted a PR a while ago (pr188261) - or now, Bugzilla I've updated this recently - as I found doing 'ifconfig xn0 -txcsum' on a "client" will fix the issue, for just that client - but I'm still unable to fix the 'router' VM in such a way as all clients don't need a fix. I have a test system setup with all this now (and all of 9.2-S, 10-S, and 11-Current have the issue) - is anyone able to point me in the right direction of what I can do to investigate this further? (i.e. debug things, packet captures, etc. etc.) We could really do with getting this fixed - we use FreeBSD as routers on a few systems - as as they move to Xen we end up having to either setup 2 pools (and be very, very careful about what machines we put on each) in order to avoid this - or face running them in HVM mode for which the performance is very, very poor. -Karl