rdma_cm - RDMA communication manager. "#include <rdma/rdma_cma.h>" Used to establish communication over RDMA transports. The RDMA CM is a communication manager used to setup reliable, connected and unreliable datagram data transfers. It provides an RDMA transport neutral interface for establishing connections. The API is based on sockets, but adapted for queue pair (QP) based semantics: communication must be over a specific RDMA device, and data transfers are message based.

The RDMA CM only provides the communication management (connection setup / teardown) portion of an RDMA API. It works in conjunction with the verbs API defined by the libibverbs library. The libibverbs library provides the interfaces needed to send and receive data.

This section provides a general overview of the basic operation for the active, or client, side of communication. A general connection flow would be: create channel to receive events allocate an rdma_cm_id, this is conceptually similar to a socket obtain a local RDMA device to reach the remote address wait for RDMA_CM_EVENT_ADDR_RESOLVED event ack event allocate a QP for the communication determine the route to the remote address wait for RDMA_CM_EVENT_ROUTE_RESOLVED event ack event connect to the remote server wait for RDMA_CM_EVENT_ESTABLISHED event ack event

Perform data transfers over connection

tear-down connection wait for RDMA_CM_EVENT_DISCONNECTED event ack event destroy the QP release the rdma_cm_id release the event channel

An almost identical process is used to setup unreliable datagram (UD) communication between nodes. No actual connection is formed between QPs however, so disconnection is not needed.

Although this example shows the client initiating the disconnect, either side of a connection may initiate the disconnect.

This section provides a general overview of the basic operation for the passive, or server, side of communication. A general connection flow would be: create channel to receive events allocate an rdma_cm_id, this is conceptually similar to a socket set the local port number to listen on begin listening for connection requests wait for RDMA_CM_EVENT_CONNECT_REQUEST event with a new rdma_cm_id allocate a QP for the communication on the new rdma_cm_id accept the connection request ack event wait for RDMA_CM_EVENT_ESTABLISHED event ack event

Perform data transfers over connection

wait for RDMA_CM_EVENT_DISCONNECTED event ack event tear-down connection destroy the QP release the connected rdma_cm_id release the listening rdma_cm_id release the event channel success error - see errno for more details

Librdmacm functions return 0 to indicate success, and a -1 return value to indicate failure. If a function operates asynchronously, a return value of 0 means that the operation was successfully started. The operation could still complete in error; users should check the status of the related event. If the return value is -1, then errno will contain additional information regarding the reason for the failure.

Prior versions of the library would return -errno and not set errno for some cases related to ENOMEM, ENODEV, ENODATA, EINVAL, and EADDRNOTAVAIL codes. Applications that want to check these codes and have compatability with prior library versions must manually set errno to the negative of the return code if it is < -1.

rdma_create_event_channel(3), rdma_get_cm_event(3), rdma_create_id(3), rdma_resolve_addr(3), rdma_bind_addr(3), rdma_create_qp(3), rdma_resolve_route(3), rdma_connect(3), rdma_listen(3), rdma_accept(3), rdma_reject(3), rdma_join_multicast(3), rdma_leave_multicast(3), rdma_notify(3), rdma_ack_cm_event(3), rdma_disconnect(3), rdma_destroy_qp(3), rdma_destroy_id(3), rdma_destroy_event_channel(3), rdma_get_devices(3), rdma_free_devices(3), rdma_get_peer_addr(3), rdma_get_local_addr(3), rdma_get_dst_port(3), rdma_get_src_port(3), rdma_set_option(3) ucmatose(1), udaddy(1), mckey(1), rping(1)