On Monday 04 August 2008 08:58, Sean Hefty wrote:
> This is debatable, but rdma_create_qp_ex() with create_flags = 0 (or 1
> -1 or whatever) should give the exact same functionality as calling
> rdma_create_qp().  The expanded call should subsume all functionality as
> the existing call.  I believe the verbs interface should be similar.
> 
> This is more about the behavior of the API, than the internal
> implementation.
> 
Won't it be confusing if the rdma_create_qp_ex() call with create_flags = 0
succeeds, while the same call with create_flags != 0 fails (in the case where
userlevel is running against an older kernel which does not have the
ib_uverbs_create_qp_ex() interface)?

I prefer to keep the ex interface separate -- there is no point in using the
qp_ex call if there is no intent to use the expanded feature.

- Jack

_______________________________________________
general mailing list
[email protected]
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general

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

Reply via email to