Roland> By the way, reposting the receives is not the right thing
Roland> to do on error -- the QP will be in the error state, so
Roland> any new work requests will just complete with a flush
Roland> status. We need to reset the QP and start over to recover
Roland> from errors.
Hal> Is the same thing true for QP0/1 ? If so, this needs to be
Hal> done there as well. (There used to be a port restart there
Hal> but this was excised).
Yes, of course (QP0/1 act just like normal UD QPs as far as work
request processing/error semantics go).
- R.
_______________________________________________
openib-general mailing list
[EMAIL PROTECTED]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
