Hi Frank, The fact that the Windows and Linux stacks treat the rkey differently in the SW should not affect wire interop. In the Windows stack, any values that end up on the wire (like the RKEY in the RDMA header) are always expressed in network order. They're tokens anyhow and swapping them isn't optimal - you end up with the HCA driver swapping it when returning it to the user, just so the user can swap it to put it on the wire, so that the recipient can swap it back to host order, just to have the HCA driver swap it back to network order when performing the RDMA operation.
So on the Linux side, applications have to swap the rkey and treat it as a host-order value. On the Windows side they don't. Can you elaborate on what prevents clean RDMA interop between Linux and Windows? -Fab -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of frank zago Sent: Tuesday, February 05, 2008 7:00 PM To: [email protected] Subject: Re: [ofw] what's up with the OFA Windows project? Gilad Shainer wrote: > The way to decide on a new code is what fits best the Windows > environment and not what should be done to enable interoperability > between Windows and Linux. As I see it, this is the way to go. > Well, speaking of interoperability, I can confirm that it does matter for some people. It's not the 80's anymore. And there's at least one issue I know about (rkey byte swapping) that prevent clean rdma between linux and windows, which makes your statement unfortunately true. Frank. _______________________________________________ ofw mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ofw _______________________________________________ ofw mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ofw
