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@lists.xensource.com http://lists.xensource.com/xen-users
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@lists.xensource.com > http://lists.xensource.com/xen-users_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
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@vub.de] 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@lists.xensource.com > http://lists.xensource.com/xen-users_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users