Paul Durrant wrote: > Garrett D'Amore wrote: >> >> Far far better, IMO, is to "fix" the main driver this case is for >> (cassini), which architecturally could easily be converted to GLDv3 >> and bundled into Nevada, and then spend effort to wrap up GLDv3 enough >> to publish it for 3rd parties. >> > > Completely agree. Adding complexity to GLDv3 to work around a > performance issue that exists for one driver seems completely backwards. > I agree with you to some extend. Unfortunately cassini (ce) is still a very popular legacy driver that is used on lots of Solaris system. Further, our GLDv3 driver APIs are not made public yet. Before that happens, we will have to make the legacy driver performs well enough.
Also, please note that the proposal we proposed here is not invasive to the current GLDv3 framework at all. Most of the fastpath enhancement is in softmac itself. We do introduced the new DL_NOTE_REPLUMB and DL_NOTE_REPLUMB_DONE message, but how IP handling those new messages are mostly existing code path, and it will be very easy to remove them if it proves there is no legacy driver requires this one day. Thanks - Cathy
