Date: October 24, 2019
Time: 2:30-3:30pm ET
Abstract
Disaggregated racks comprise dense pools of compute, memory and storage blades, all interconnected through an internal network. However, their density poses a unique challenge for the rack’s network: it needs to connect an order of magnitude more resource nodes than today’s racks with- out exceeding the rack’s fixed power budget and without compromising on performance. We present Shoal, a power- efficient yet performant intra-rack network fabric built using fast circuit switches. Such switches consume less power as they have no buffers and no packet inspection mechanism, yet can be reconfigured in nanoseconds. Rack nodes transmit according to a static schedule such that there is no in-network contention without requiring a centralized controller. Shoal’s congestion control leverages the physical fabric to achieve fairness and both bounded worst-case network throughput and queuing. We use an FPGA-based prototype, testbed experiments, and simulations to illustrate Shoal’s mechanisms are practical, and can simultaneously achieve high density and high performance: 71% lower power and comparable or higher performance than today’s network designs.
Bio
Vishal Shrivastav is a PhD student in Computer Science at Cornell. He is advised by Hakim Weatherspoon. His research focusses on resolving challenges arising in high-speed datacenter networking by efficiently leveraging custom hardware for networking. Prior to Cornell, Vishal was an undergraduate student at Indian Institute of Technology, Kharagpur.