A Case for Data Centre Traffic Management on Software Programmable Ethernet Switches
Abstract
Virtualisation first and cloud computing later has led to a consolidation of workload in data centres that also comprises latency-sensitive application domains such as High Performance Computing and telecommunication. These types of applications require strict latency guarantees to maintain their Quality of Service. In virtualised environments with their churn, this demands for adaptability and flexibility to satisfy. At the same time, the mere scale of the infrastructures favours commodity (Ethernet) over specialised (Infiniband) hardware. For that purpose, this paper introduces a novel traffic management algorithm that combines Rate-limited Strict Priority and Deficit round-robin for latency-aware and fair scheduling respectively. In addition, we present an implementation of this algorithm on the bmv2 P4 software switch by evaluating it against standard priority-based and best-effort scheduling.
Cite
@article{arxiv.2002.07027,
title = {A Case for Data Centre Traffic Management on Software Programmable Ethernet Switches},
author = {Kamil Tokmakov and Mitalee Sarker and Jörg Domaschka and Stefan Wesner},
journal= {arXiv preprint arXiv:2002.07027},
year = {2020}
}
Comments
8th IEEE International Conference on Cloud Networking (IEEE CloudNet 2019)