I suggest you look at the current offload settings on the NIC There have been quite a few bugs when bonding, vlans, bridges etc. are involved - sometimes you have to set the offload settings on the logical interface (like bond0.vlan_id) and not on the NIC. Even then, what I’ve seen is that if the interface goes down and up, those settings are _reset_ and you need to set them again, but YMMV as that depends on what the driver does (and in our case has been fixed in newer EL6 kernels). The behaviour was almost exactly as what you see and we use Intel 82599ES (very close to X540, not sure if the same driver). run: ethtool -K $dev tso off gso off gro off lro off on the f18 and see if it makes a difference. Jan
|
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com