Abstract

Abstract To be agile and cost e ective, data centers should allow dynamic resource allocation across large server pools. In particular, the data center network should enable any server to be assigned to any service. To meet these goals, we present VL, a practical network architecture that scales to support huge data centers with uniform high capacity between servers, performance isolation between services, and Ethernet layer- semantics. VL uses () at addressing to allow service instances to be placed anywhere in the network, () Valiant Load Balancing to spread tra c uniformly across network paths, and () end-system based address resolution to scale to large server pools, without introducing complexity to the network control plane. VL's design is driven by detailed measurements of tra c and fault data from a large operational cloud service provider. VL's implementation leverages proven network technologies, already available at low cost in high-speed hardware implementations, to build a scalable and reliable network architecture. As a result, VL networks can be deployed today, and we have built a working prototype. We evaluate the merits of the VL design using measurement, analysis, and experiments. Our VL prototype shu es . TB of data among  servers in  seconds -sustaining a rate that is  of the maximum possible.