DeTail: Reducing The Flow Completion Time Tail In Datacenter Networks

Abstract

Web applications have now become so sophisticated that rendering a typical page may require hundreds of intra-datacenter flows. At the same time, web sites must meet strict page creation deadlines of 200-300<i>ms</i> to satisfy user demands for interactivity. Long-tailed flow completion times make it challenging for web sites to meet these constraints. They are forced to choose between rendering a subset of the complex page, or delay its rendering, thus missing deadlines and sacrificing either quality or responsiveness. Either option leads to potential financial loss. In this paper, we present a new cross-layer network stack aimed at reducing the long tail of flow completion times. The approach exploits cross-layer information to reduce packet drops, prioritize latency-sensitive flows, and evenly distribute network load, effectively reducing the long tail of flow completion times. We evaluate our approach through NS-3 based simulation and Click-based implementation demonstrating our ability to consistently reduce the tail across a wide range of workloads. We often achieve reductions of over 50% in 99.9<i>^th</i> percentile flow completion times.