The Solaris 10 release includes the Remote Direct Memory Access (RDMA) protocol, which is a technology for memory-to-memory transfer of data over high-speed networks. Specifically, RDMA provides remote data transfer directly to and from memory without CPU intervention. RDMA also provides direct data placement, which eliminates data copies and, therefore, further eliminates CPU intervention. Thus, RDMA relieves not only the host CPU, but also reduces contention for the host memory and I/O buses. To provide this capability, RDMA combines the interconnect I/O technology of InfiniBand on SPARC platforms with the Solaris operating system. The following figure shows the relationship of RDMA to other protocols, such as UDP and TCP.
If the RDMA transport is not available on both the client and the server, the TCP transport is the initial fallback, followed by UDP if TCP is unavailable. Note, however, that if you use the proto=rdma mount option, NFS mounts are forced to use RDMA only.
RDMA for InfiniBand uses the IP addressing format and the IP lookup infrastructure to specify peers. However, because RDMA is a separate protocol stack, it does not fully implement all IP semantics. For example, RDMA does not use IP addressing to communicate with peers. Therefore, RDMA might bypass configurations for various security policies that are based on IP addresses. However, the NFS and RPC administrative policies, such as mount restrictions and secure RPC, are not bypassed.