On Sun, Oct 14, 2012 at 06:41:25PM -0700, Pravin B Shelar wrote: > Following patch adds start offset for sw_flow-key, so that we can > skip tunneling information in key for non-tunnel flows. > > Signed-off-by: Pravin B Shelar <[email protected]> > CC: Kyle Mestery <[email protected]> > Cc: Simon Horman <[email protected]> > Cc: Jesse Gross <[email protected]>
Does this actually speed up the fast path? (Did you measure it?) In struct sw_flow_key, why put tun inside phy? Why not just move it to the beginning without nesting it? Why change tun from struct to (one-member) union? When a range is expressed as an offset and a length, I expect that the length is relative to the offset, not to the start of the buffer. The usage here is more like what I'd expect to be called a start and an end, not an offset and a length. In ovs_flow_tbl_lookup(), I think there's a (faint) possibility that the key and the hash are equal, but the bucket's key_offset differs from the searched-for key_offset, so I would check for a match in that also. The ovs_flow_metadata_from_nlattrs() change seems almost unrelated to the main goal of the patch. I guess it's OK though. Thanks, Ben. _______________________________________________ dev mailing list [email protected] http://openvswitch.org/mailman/listinfo/dev
