The more I think about this, the more I conclude the rdma-cm is just broken. There's no way to determine an RDMA device from 127.0.0.1, so how can bind succeed?
Steve Wise wrote: > I just opened 1918. The latest ofed-1.5.1 rdma-cm is allowing binds to > 127.0.0.1. This is no-no for devices that don't support hw loopback... > > OpenMPI uses rdma_bind_addr() to figure out which ip addresses are valid > for which IB devices. This logic is now broken. Regardless of whether > OpenMPI should use another method for determining which IP address > belong to which interfaces, we should probably rethink whether we're > breaking rdma-cm semantics in a bad way on a point release. > > > Steve. > _______________________________________________ > ewg mailing list > ewg@lists.openfabrics.org > http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg > _______________________________________________ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg