On Tue, Jun 10, 2014 at 9:52 AM, Jason Gunthorpe <[email protected]> wrote: > On Mon, Jun 09, 2014 at 05:08:09PM -0700, PJ Waskiewicz wrote: >> > > The patch set you refer to tried to _unify_ the port space and was >> > > rejected. The only other alternative is to pick ephemeral ports and >> > > maintain a mapping for RDMA services. >> > >> > I thought both approaches were tried in kernel and NAK'd by >> > netdev? This looks very similar to the 2010 patchset, except the >> > dummy socket allocation is living in userspace in this version. >> >> This was something I presented and discussed at NetConf 2011 with >> David and other netdev core folks: >> http://vger.kernel.org/netconf2011.html. The main issue David had >> with the original approach was the socket was being consumed by >> something else inside the kernel. It circumvented the TCP socket >> allocation/reservation code, which was frowned upon. > > If you have/can get agreement from netdev that this is acceptable then > I think it is OK from the RDMA side. It would be a good touch to CC > the netdev list with the cover letter describing this mechanism > properly, maybe referencing this discussion just so there are no > surprises.
Bob and/or Tatyana, did you want to re-send and make sure netdev is included? Even though I did the initial championing of the design, I'm no longer directly involved, and it would be better coming from you guys. > BTW, you can purge my [email protected] email from your address book, > that hasn't worked in over 10 years.. Yeah, that's my bad. I didn't have the original email from the thread, so I had to make "guesses" of some of the email addresses. Cheers, -PJ -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
