Commodity servers have transformed the data centers of many of today’s leading Internet companies. Could low-end switches drive a similar shift in data center networking, currently the domain of expensive brand-name switches?
That’s the focus of a research paper by three computer scientists at the University of California, San Diego. In A Scalable, Commodity Data Center Network Architecture, researchers Mohammad Al-Fares, Alexander Loukissas and Amin Vahdat propose a new twist on data center network topology, building on a technique developed 50 years ago by Charles Clos known as “fat tree” architecture. The approach has been used to leverage commodity switches in the high-performance computing arena.
“We argue that appropriately architected and interconnected commodity switches may deliver more performance at less cost than available from today’s higher-end solutions,” the researchers write. Here’s a summary:
We show that by interconnecting commodity switches in a fat-tree architecture, we can achieve the full bisection bandwidth of clusters consisting of tens of thousands of nodes. Specifically, one instance of our architecture employs 48-port Ethernet switches capable of providing full bandwidth to up 27,648 hosts. By leveraging strictly commodity switches, we achieve lower cost than existing solutions while simultaneously delivering more bandwidth. Our solution requires no changes to end hosts, is fully TCP/IP compatible, and imposes only moderate modifications to the forwarding functions of the switches themselves. We also expect that our approach will be the only way to deliver full bandwidth for large clusters once 10 GigE switches become commodity at the edge, given the current lack of any higher-speed Ethernet alternatives (at any cost).
The fat-tree topology proposed by the researchers creates some cabling challenges, which they discuss in their paper. See Network World, Storage Mojo Science Daily, Supercomputing Online and Dr. Dobb’s for additional coverage.