Hal Rosenstock wrote:
On Fri, 2005-05-06 at 10:49, Hefty, Sean wrote:

When the ACK is sent, I do not get a send failure. This is expected
based on what you said at the SA side. I think it (TID matching) would
only happen in the MAD layer automatically on the SA client side so you
would get a send failure if the ACK didn't come back in the other
direction.

Are you referring to RMPP direction switch?


No. I referring to the SA sending the SA GetTableResp as one RMPP send,
the SA client at the other end not ACKing, but the send that the SA
issued completing successfully rather than failing with some send status
indicating something like timeout.

Ah... I think I finally understand now. I'll see if I can reproduce this.


If so, that is not yet
implemented.
I.e. The code will not generate or process ACKs to ACKs, which are
required for
RMPP direction switch.  What the code does now is to match RMPP requests
with
RMPP responses, but in a manner similar to receiver initiated RMPP.


And what is the definition of request/response in terms of RMPP. I'm not
sure it is method based if non DATA packets are included.

I was referring only to DATA packets and whether the response bit was set or not.


- Sean
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to