[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] Xen & AoE problem = Ethernet padding
Hi there, This is not a "broadcast", but also, a kind of ping.I have an entry at http://bugzilla.xensource.com/bugzilla/ show_bug.cgi?id=1140 , and maybe some of you could be interested. It follows: ------------------------------------ Hi,I made some tests about ethernet padding ( an expected behavior from ethernet 10/100 on-wire, that needs at least 60 bytes of data to be able to CRC. NIC chipset has the job of fullfill the packet if it is smaller than this - also called "padding" ) and I notice a behavior that is not expected (at least for me). >>> Ethernet Padding Sender / Receiver Matrix <<< \RECEIVER | Dom0_vif |FullV_DomU_2|ParaV_DomU_2|SMP_ParaV_DomU_2 SENDER/ Dom0_vif#######| No (OK) | Yes (OK) | No (NOK) | No (NOK) FullV_DomU#####| No (NOK) | Yes (OK) | No (NOK) | No (NOK) ParaV_DomU####| No (NOK) | Yes (OK) | No (NOK) | No (NOK) SMP_ParaV_DomU| No (NOK) | Yes (OK) | No (NOK) | No (NOK)My setup is a Centos 5.1 (2.6.18-53.1.4.el5xen) / Xen (3.0.3 or 3.1, as I hear) in a bridge network configuration.The results shows that only FullVirtualization do padding, and only when receives a packet (not when send it).You could ask "why padding if you dont have a physical transport?". If you are playing with some L2 protocol (like AoE), this behavior do impact. A direct related problem: it's not possible to export AoE disks from Dom0 and other Paravirtualized guests (AoE blade server verifies if the packet has a minimal size - 60 bytes) to any local VM. I do not known if another layer2 protocols has the same problem, but I think that is a expected feature that a virtual NIC works as a physical one. Best Regards Marcelo Messa _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxxxxxxxx http://lists.xensource.com/xen-devel
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |