IST Lunch Bunch
The combination of two inexorable trends---increasing parallelism and increasing big data analytics---means modern data centers urgently need efficient high-capacity networks interconnecting thousands of servers. But we have lacked a fundamental understanding of what network topologies achieve high throughput. This talk shows how surprisingly, today's carefully-structured designs such as fat-trees are far from optimal. Our Jellyfish architecture uses a random network to achieve substantially higher throughput than deployed designs using the same equipment, while allowing flexible incremental expansion. This leads to numerous important theoretical and practical questions in network design, such as optimality and the design of heterogeneous networks. Joint work with Ankit Singla, Chi-Yao Hong, Alexandra Kolla, and Lucian Popa.