Search for: All records

We describe the deployment of an Internet measurement experiment to three testbeds that offer Linux containers hosted at widely distributed vantage points: the well-established PlanetLab Central and PlanetLab Europe platforms, and the new EdgeNet platform. The experiment results were published in the proceedings of ACM IMC 2018. We compare the capabilities of each testbed and their effect on the ease of deployment of the experiment. Because the software for this experiment has several library dependencies and requires a recent compiler, it was easiest to deploy on EdgeNet, which is based on Docker and Kubernetes. This extended abstract is accompanied by a demonstration of the reproducible deployment of a measurement tool on EdgeNet. 

This paper describes EdgeNet, a lightweight cloud infrastructure for the edge. We aim to bring as much of the flexibility of open cloud computing as possible to a very lightweight, easily-deployed, software-only edge infrastructure. EdgeNet has been informed by the advances of cloud computing and the successes of such distributed systems as PlanetLab, GENI, G-Lab, SAVI, and V-Node: a large number of small points-of-presence, designed for the deployment of highly distributed experiments and applications. EdgeNet differs from its predecessors in two significant areas: first, it is a software-only infrastructure, where each worker node is designed to run part- or full-time on existing hardware at the local site; and, second, it uses modern, industry-standard software both as the node agent and the control framework. The first innovation permits rapid and unlimited scaling: whereas GENI and PlanetLab required the installation and maintenance of dedicated hardware at each site, EdgeNet requires only a software download, and a node can be added to the EdgeNet infrastructure in 15 minutes. The second offers performance, maintenance, and training benefits; rather than maintaining bespoke kernels and control frameworks, and developing training materials on using the latter, we are able to ride the wave of open-source and industry development, and the plethora of industry and community tutorial materials developed for industry standard control frameworks. The result is a global Kubernetes cluster, where pods of Docker containers form the service instances at each point of presence.