I'd suggest running iperf with various settings to stress test the nic to find the breaking point.
If you are able to replicate this issue - take a kdump and let redhat dev analyze. I've had tons of issues with be2net drivers in past and opened several BZ, on RedHat 5.8 it seemed to be finally addressed. From: rhelv5-list-boun...@redhat.com [mailto:rhelv5-list-boun...@redhat.com] On Behalf Of Colin Coe Sent: Tuesday, May 15, 2012 11:18 PM To: Red Hat Enterprise Linux 5 (Tikanga) discussion mailing-list; Srija Subject: Re: [rhelv5-list] Facing issue with be2net Good luck with HP support. Is bonding at the server level the right way? What are you using as your interconnect module? I had much more success when I let the interconnect module (flex10) handle the redundancy. CC On May 16, 2012 12:40 AM, "Srija" <swap_proj...@yahoo.com<mailto:swap_proj...@yahoo.com>> wrote: Hello All, Our server is hp proliant 620C g7, we have rhel5.8 86_64 xen kernel,. We are using four ports , two ports are bonded with vlan tagging where we can build several guests on different vlan. We are having issue, with be2net driver. getting the errors as be2net 0000:04:00.1: Out of MCCQ wrbs be2net 0000:04:00.1: Out of MCCQ wrbs be2net 0000:04:00.1: Out of MCCQ wrbs If we move the guests on this host, the guests are getting non responsive after running few minutes, also the hosts too. We upgraded the firmware , it is now as follows: version: 4.0.100r firmware-version: 4.0.493.0 HP has changed the NIC card too, but the problem did not resolve. we are also with HP support In the mean time if someone can advice , it will be really helpful Thanks in advance _______________________________________________ rhelv5-list mailing list rhelv5-list@redhat.com<mailto:rhelv5-list@redhat.com> https://www.redhat.com/mailman/listinfo/rhelv5-list
_______________________________________________ rhelv5-list mailing list rhelv5-list@redhat.com https://www.redhat.com/mailman/listinfo/rhelv5-list