From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-15?Q?J=E9r=F4me_Petazzoni?= Subject: Re: RE: Maturity of Xen PV drivers? Date: Tue, 27 Jan 2009 19:02:47 +0100 Message-ID: <497F4C47.3040702@enix.org> References: <485d0c040901160939nd39607fn708a321e03d58c23@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: James Harper Cc: xen-devel@lists.xensource.com, Phuong Hoang List-Id: xen-devel@lists.xenproject.org >> Hi James, >> Do you know any company has used Xen PV drivers for Windows in their >> production? Or Is there any limitation for those drivers (list of know >> issues etc.) >> > I haven't had any issues in quite a while (12 months, various versions), > and I use them in production (the machines are well backed up of course. > In fact the only problems I have had under windows was when _not_ using > PV drivers - a Xen/Dom0 crash left one of my windows domains corrupt > because of the way Dom0 caches disk writes in the qemu drivers. > Same thing here - we have a Xen host (64 bits) running a couple of Windows 2003 VMs. Without the GPL PV drivers, heavy I/O caused almost-reproducible crashes (for instance, downloading a large file thru CIFS hung the Windows VM). With the GPL PV drivers, I/O is of course *a lot* faster and no crash has been seen yet. HTH,