> P1-> addr_resolve() > select(cm_event_fd) > gets RDMA_CM_ADDR_RESOLVED > > rout_resolve() > gets RDMA_CM_ROUTE_RESOLVE > > connect(): > > P2: Gets Connect request > > P1: -> Dies
When process 1 dies after trying to establish a connection, this generates a connection reject. This notifies the remote side that the connection request has been aborted. The destruction of the cm_id on process 2 should remove all unreported events for that id. There was a kernel bug that could result in reporting events like you are seeing, but that was fixed a while ago. If you're running an older kernel, this could be the reason you see the unexpected event. - Sean -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
