WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-users

Re: [Xen-users] unstable network problem

To: xen-users@xxxxxxxxxxxxxxxxxxx
Subject: Re: [Xen-users] unstable network problem
From: Ernst Bachmann <e.bachmann@xxxxxxxx>
Date: Mon, 8 Aug 2005 15:59:08 +0200
Delivery-date: Mon, 08 Aug 2005 13:57:32 +0000
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <9e246b4d0508080634485e236c@xxxxxxxxxxxxxx>
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
References: <9e246b4d0508080634485e236c@xxxxxxxxxxxxxx>
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: KMail/1.8.1
On Monday 08 August 2005 15:34, Tim Durack wrote:
> I must be doing something wrong:
>
> Have set up a basic Xen system, Dom0 + one Xen0 guest. Configured for
> a routed network.
>
> Ping Dom0 -> guest works.
> Ping guest -> Dom0 works.
>
> nmap Dom0 -> guest reports port 22 open.
>
> Ssh Dom0 -> guest hangs.
> ssh guest -> Dom0 hangs. Same behaviour. Watching a packet capture
> shows traffic passing but with retransmits and poor performance.
>
> If I build a gre tunnel between Dom0 and guest, everything works fine,
> with the exception that I must generate some traffic from the guest
> first.
>
> I have no iptables rules configured, so it's not that. Looks like
> there is maybe some issue with tcp traffic between domains.
>
> Looks like a bug to me, but I'm posting to the user list first.

There was a long thread about this problem maybe one or two weeks ago...
I think the problem was that the virtual eth devices had packet queueing 
disabled (txqueuelen:0 on ifconfig), and had a 4k size max. ring buffer for 
transfering packets between domains.
Whenever that buffer would run full, packets are dropped...

/Ernst

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users