5G means that, for the first time, last-mile latency will often be less than backbone latency. If your data center is a long way from lots of your customers, your quality of service will be poorer (i.e. noticeably slower) than competitors with physically closer data centers. The potential answer to this problem has been around for a while – edge and fog computing. These may finally come into their own as last-mile latency drops and the sheer volume of data from the IoT skyrockets.
Given the future 5G requirements in terms of latency, data volumes, and reliability, fiber optics are undoubtedly the most future-proof and ideally scalable medium for data transfer. From a technological perspective, it is clear that fiber optics and the new 5G mobile networks offer the best foundations for high transmission rates, minimum latency periods, and thus the greatest possible speed.
Enterprise customers will soon require the low latency networking that RDMA offers so that they can address a variety of different applications, such as Oracle and SAP, and also implement software-defined storage using Windows Storage Spaces Direct (S2D) or VMware vSAN. There are three protocols that can be used in RDMA deployment: RDMA over InfiniBand, RDMA over Converged Ethernet (RoCE), and RDMA over iWARP. Given that there are several possible routes to go down, how do you ensure you pick the right protocol for your specific tasks?