[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [Xen-users] Xen peth0 dropping


  • To: "xen-users" <xen-users@xxxxxxxxxxxxxxxxxxx>
  • From: "John Cianfarani" <jcianfarani@xxxxxxxxxx>
  • Date: Mon, 13 Mar 2006 10:57:39 -0500
  • Cc: aschiefer@xxxxxx
  • Delivery-date: Mon, 13 Mar 2006 15:59:43 +0000
  • Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Subject:MIME-Version:Content-Type:Content-Transfer-Encoding:Content-class:Date:X-MimeOLE:Message-ID:X-MS-Has-Attach:X-MS-TNEF-Correlator:Thread-Topic:thread-index:From:To:Cc; b=igaUSOLv9U6T4g9VlI6lcLDnBPnXjqMK80U2Ms77NFbZfgzZx1k5Q4EagAMP1SmSTlwLz2p2HgvKcFJ+FE5WFFMCcN8u1MP4TcpYOYpuJYG1axpEZlYMW6c52uEzRNtrk82TPs2mbuVgpiPGueaIK90fmKCxzzstL5tnSE9qz7A= ;
  • List-id: Xen user discussion <xen-users.lists.xensource.com>
  • Thread-index: AcZGgG+71g2jxSXoTDWDPCZR/mxWSgANKkBw
  • Thread-topic: [Xen-users] Xen peth0 dropping

I'm not doing any bonding so your issue could be related to bonding.
Are you doing load balancing with the bonding or just failover?

I've disabled the network-script for the moment as I was planning on
using a custom setup anyhow, 1 for management and 1 for trunking with
domU's bridged into vlans.

Since disabling this, the network has stayed up and I've pounded it with
several hours of traffic with iperf.

Still very annoying and I would like to get to the bottom of the issue.

Thanks
John

-----Original Message-----
From: Artur Schiefer [mailto:aschiefer@xxxxxx] 
Sent: Monday, March 13, 2006 4:26 AM
To: John Cianfarani
Cc: xen-users
Subject: Re: [Xen-users] Xen peth0 dropping

hello,

i have no suggestion, sorry, but i just want to say that we have a
similar problem (see "network becomes unreachable under load"), which
wasn't the case with xen-2-testing(2.0.8). we are using a
bonding/teaming setup where the bridging scripts use
'brigde=brbonding0'.



Am Sonntag, den 12.03.2006, 19:03 -0500 schrieb John Cianfarani:
> I've got a Dell Poweredge 850 setup to do some testing with xen and I
> notice peth0 just seems to die quite frequently.
> 
> I don't really have to be doing anything for it to happen, no domU's
> running no real traffic other than ssh connections.
> 
> After this happens bringing eth0/xenbr0  down and up doesn't help only
> ifconfig peth0 down and then up seems to restore connectivity.
> 
>  
> 
> If I do a tcpdump -i peth0 while it's down I see no traffic at all.
> 
>  
> 
> I setup tcpdump -i peth0 while it was working and eventually it stops
> with the error:
> 
>  
> 
> tcpdump: pcap_loop: recvfrom: Network is down
> 
>  
> 
> and in /var/log/messages I find
> 
>  
> 
> Mar 12 17:51:09 nlnsrv1 kernel: xenbr0: port 2(peth0) entering
> disabled state
> 
>  
> 
>  
> 
> Does anyone have any suggestions as to what this could be?
> 
> I'm testing with Xen3.0.1 on CentOS 4.2.
> 
>  
> 
> Thanks
> 
> John 
> 
> 
> _______________________________________________
> Xen-users mailing list
> Xen-users@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-users



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


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.