@misc{14201, keywords = {InfiniBand, scalability, Cloud computing, HPC, Network Reconfiguration, Fat-Tree}, author = {Evangelos Tasoulas and Ernst Gran and Tor Skeie and Bj{\o}rn Johnsen}, editor = {Alessandro Pellegrini and Aris Gkoulalas-Divanis and Pierangelo Di Sanzo and Dimiter Avresky}, title = {Fast Hybrid Network Reconfiguration for Large-Scale Lossless Interconnection Networks}, abstract = {Reconfiguration of high performance lossless interconnection networks is a cumbersome and time-consuming task. For that reason reconfiguration in large networks are typically limited to situations where it is absolutely necessary, for instance when severe faults occur. On the contrary, due to the shared and dynamic nature of modern cloud infrastructures, performance-driven reconfigurations are necessary to ensure efficient utilization of resources. In this work we present a scheme that allows for fast reconfigurations by limiting the task to sub-parts of the network that can benefit from a local reconfiguration. Moreover, our method is able to use different routing algorithms for different sub-parts within the same subnet. We also present a Fat-Tree routing algorithm that reconfigures a network given a user-provided node ordering. Hardware experiments and large scale simulation results show that we are able to significantly reduce reconfiguration times from 50\% to as much as 98.7\% for very large topologies, while improving performance.}, year = {2016}, journal = {15th IEEE International Symposium on Network Computing and Applications (NCA 2016)}, pages = {101-108}, publisher = {IEEE}, }