On Fri, 2007-01-26 at 09:15 -0800, Caitlin Bestler wrote: > [EMAIL PROTECTED] wrote: > > https://bugs.openfabrics.org/show_bug.cgi?id=325 > > > > Summary: RDMA_CM and address translation broken on sles9sp3 > > Product: OpenFabrics Linux > > Version: 1.2 > > Platform: X86-64 > > OS/Version: SLES 9 > > Status: NEW > > Severity: critical > > Priority: P2 > > Component: RDMA CM > > AssignedTo: [EMAIL PROTECTED] > > ReportedBy: [EMAIL PROTECTED] > > > > > > rdma_translate_ip() and friends use > > ip_dev_find(local_ip_addr) to obtain a net_device pointer. > > Then the device type is used to determine if the rdma > > address is iwarp or infiniband. > > > > On sles9sp3, ip_dev_find(local_ip_addr) is returning the > > loopback device. This causes rmda_copy_addr() to fail. > > I suspect that this is the most obvious case of a more > general problem. Specifically there is a higher priority > route to the destinatiaon IP address that is not RDMA > capable. >
We're not doing a routing lookup here. We're just trying to find the local netdev that has a particular ip address bound to it. > Essentially the selected route needs to be considered > "down" for RDMA traffic, so the less preferred route > can be taken. > > The more specific problem could be addressed by making > the loopback device support OFA verbs, but since nobody > sells loopback devices there might not be a rush of > volunteers. > ip_dev_find() shouldn't really be using the routing table IMO. It is supposed to find the netdev device that has a given ip address bound to it. > The other issue is that there may always be remote IP > addresses that are reachable for non-RDMA traffic but > not for RDMA traffic. All it takes is two network interfaces > that connect to two networks that have no routes between > them where one of them is not RDMA capable. Machines that > have Ethernet ports dedicated to an administrative network > are one obvious example. > > Ultimately that step suggests that the test should not > be "if the rdma address is iwarp or infiniband" but "iwarp, > infiniband or not RDMA accessible". _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
