On Aug 19, 2011 12:54 AM, "Justin Pettit" <jpet...@nicira.com> wrote: > > On Aug 18, 2011, at 9:31 AM, Ben Pfaff wrote: > > Do we need to disable LRO on internal ports too (after we add them)? > > The current code doesn't appear to do that, and I don't know if LRO makes sense without hardware. I'll wait for Jesse's final word, of course.
LRO only makes sense in the context of hardware and only on receive. Since internal devices are software and the packets they receive are actually transmitted by the network stack, they can never produce LRO packets so this should be find. The main thing that I was wondering about in this patch is the implications for the backports in RHEL 5. I looked through some of their patches and it appears that they backported LRO (and drivers that enable it) but not the userspace interface (I could be wrong about this though). If that's the case then this will break on that platform because the userspace request to disable LRO would be ignored. In that situation, we'd probably need to make the kernel continue to disable LRO on the old kernels. This is still an improvement though because the userspace/kernel expectations are set properly and on those old kernels it would just seem like the NIC doesn't support LRO.
_______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev
