Network performance and scalability become major issues in cloud computing. The OpenFlow framework enabling flowlevel management makes routing more effective and simpler in datacenter networks (DCNs). A prior routing algorithm named DENDIST-FM shows a good result in improving throughput and avoiding congestion of DCNs. However, flow migration for cloud management often incurs extra overhead from modifying the flow tables in switches. Therefore, on the basis of DENDISTFM, we propose a novel address-partitioned wildcard routing (APWR) scheme, which leverages the symmetry of a Portland topology and applies wildcard matching to achieve low cost for flow-table modification. Simulation results demonstrate that on a Portland 8-16-16 datacenter network with 128 host machines, the proposed scheme achieves throughput as good as DENDISTFM does, but reduces 70% cost on flow-table modifications used by DENDIST-FM. As a result, our APWR scheme is proven a practical algorithm for improving network performance and reducing flow-migration cost, simultaneously.
|Number of pages||7|
|State||Published - 1 Jan 2014|
|Event||International Conference on Software Intelligence Technologies and Applications and International Conference on Frontiers of Internet of Things, 2014 - Hsinchu, Taiwan|
Duration: 4 Dec 2014 → 6 Dec 2014
|Conference||International Conference on Software Intelligence Technologies and Applications and International Conference on Frontiers of Internet of Things, 2014|
|Period||4/12/14 → 6/12/14|