Michael S. Tsirkin wrote:
No. A socket is a 5 tuple (proto, local addr, local port, remote addr, remote port). unbind just says that you can reuse local addresses, so e.g. a new connection request will connect to a new socket.
I understand. But if both sides do this, then the local and remote ports become available for re-use, and a new connection between the systems could end up with the same tuple.
Maybe rename it unbind_local?
I'm fine with the name rdma_unbind(). I will likely change rdma_bind_addr() to just rdma_bind() at some point. I'm just trying to determine what the real limitations are to rdma_unbind(), or if there's some other solution that we're missing that may make more sense, such as having SDP control its own port space.
- 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
