Workload and Failure Characterization on a Large-Scale Federated Testbed
Brent N. Chun, Amin M. Vahdat · 2003
Recently, a number of federated distributed computational and communication infrastructures have emerged, including the Grid, PlanetLab, and Content Distribution Networks. In these environments, mutually distrustful autonomous domains pool resources together for their mutual benefit, for instance to gain access to: unique computational resources, multiple vantage points on the network, or more computation than available locally. Key challenges for such federated infrastructures include resource allocation, scheduling, and constructing highly available services in the face of faulty end hosts and unpredictable network behavior. Developing such appropriate mechanisms and policies requires an understanding of the usage characteristics and operating environment of the target environment. In this paper, we present a detailed characterization of the actual use of the PlanetLab network testbed. PlanetLab consists of 240 nodes spread across 100 autonomous domains with over 500 active users. Using a variety of measurement tools, we present a three-month study on the network, CPU, memory and disk usage of individual PlanetLab nodes and sites. On the consumer side, we further characterize the consumption of individual users. Next, we present results on the availability and reliability of system nodes and the network interconnecting them. Finally, we discuss the implications of our measurements for emerging federated environments.