UPC has lead the work on the PRISTINE paper entitled “Scalable Topological Forwarding and Routing Policies in RINA-enabled Programmable Data Centres“, which has been accepted for publication at the Wiley Transactions on Emerging Telecommunications Technologies. Congrats to the UPC team!
Given the current expansion of cloud computing, the expected advent of the Internet of Things (IoT) and the demands of future 5G network infrastructures, significantly larger pools of computational and storage resources will soon be required. This emphasises the need for more scalable datacentres, capable of providing such an amount of resources in a cost-effective way. A quick look into today’s commercial data centres shows that they tend to rely on variations of well-defined leaf-spine/clos Data Centre Network (DCN) topologies, offering low latencies, ultra-high bisectional bandwidth and enhanced reliability against concurrent failures. However, DCNs are typically restricted by the use of the TCP/IP protocol suite, suffering limited routing scalability. In this work, we study the benefits that the TCP/IP replacement with the Recursive InterNetwork Architecture (RINA) can bring into commercial DCNs, focusing on forwarding and routing scalability. We quantitatively evaluate the benefits that RINA solutions can yield against those IP-based and also highlight how, by deploying RINA, topological solutions can improve even more the efficiency of the network. To this goal, we propose a rule-and-exception forwarding policy tailored to the characteristics of several DCN variants, enabling fast forwarding decisions with merely neighbours’ information. Upon failures, few exceptions are necessary, which computation can also profit from the known topology. Extensive numerical results show that the proposed policy’s requirements depends mainly on the number of neighbours and concurrent failures in the DCN rather than its size, reducing dramatically the amount of forwarding and routing information stored at DCN nodes.