On Wed, Jun 8, 2011 at 10:51 AM, Ben Pfaff <b...@nicira.com> wrote: > I accidentally discovered that on "master" every IP fragment ends up > being sent to userspace. My test case is "netperf -H 192.168.0.2 -t > UDP_STREAM" (which generates 64 kB UDP packets), then observing that > the datapath "miss" counter goes up quickly while the "hit" counter > stays put, as well as noticing that the packet counter for the UDP > datapath flow stays stuck at 0.
Thanks, good catch. In flow_extract() we currently act as if there is no L4 header at all if the packet is a fragment, however, we should match against a set of zeroed fields instead of effectively wildcarding them. I write a patch for this in a little bit. _______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev