VF2x: Fast, efficient virtual network mapping for real testbed workloads

Abstract

Distributed network testbeds like GENI aim to support a potentially large number of experiments simultaneously on a complex, widely distributed physical network by mapping each requested network onto a share or "slice" of physical hosts, switches and links. A significant challenge is network mapping: how to allocate virtual nodes, switches and links from the physical infrastructure so as to accurately emulate the requested network configurations. In this paper we present the VF2x virtual network mapping system. Based on the VF2 subgraph isomorphism detection algorithm designed for matching large graphs, VF2x incorporates several novel algorithmic improvements. These and careful implementation make VF2x perform more than two orders of magnitude faster than the fastest previously published algorithm. In evaluating our algorithm, we generated an extensive test workload based on analysis of a 5-year trace of experiments submitted to the popular Emulab testbed, and using the current ProtoGENI topology. We use this test workload to evaluate the performance of VF2x, showing that it can allocate resources to virtual networks on a large testbed in a matter of seconds using commodity hardware. © 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering.