Towards highly available clos-based WAN routers

Abstract

The performance and availability of cloud and content providers often depends on the wide area networks (WANs) they use to interconnect their datacenters. WAN routers, which connect to each other using trunks (bundles of links), are sometimes built using an internal Clos topology connecting merchant-silicon switches. As such, these routers are susceptible to internal link and switch failures, resulting in reduced capacity and low availability. Based on the observation that today's WAN routers use relatively simple trunk wiring and routing techniques, we explore the design of novel wiring and more sophisticated routing techniques to increase failure resilience. Specifically, we describe techniques to 1) optimize trunk wiring to increase effective internal router capacity so as to be resilient to internal failures, 2) compute the effective capacity under different failure patterns, and 3) use these to compute compact routing tables under different failure patterns, since switches have limited routing table sizes. Our evaluations show that our approach can mask failures of up to 75% of switches in some cases without exceeding routing table limits, whereas competing techniques can sometimes lose half of a WAN router's capacity with a single failure.

Congestion Control for Cross-Datacenter Networks

“…large enterprises start to build and deploy their own customized networking hardware both on WAN [64,107] and DCN [41,105]. However, while the cutting-edge merchant…”

“…To scale the wide-area network cost-effectively and flexibly, large enterprises such as Google and Alibaba have been building and deploying their customized wide-area routers based on shallow-buffered commodity switching chips [41,64,105,107,8] ( §4.1.1).…”