Virtual Hybrid Elastic Clusters in the Cloud

A. Calatrava, G. Moltó, M. Caballer, and C. De Alfonso. Virtual Hybrid Elastic Clusters in the Cloud. In 8th Iberian Grid Infrastructure Conference (IberGrid 2014), pp. 103–114, 2014.

Download

[632.7kB pdf] 

Abstract

Clusters of PCs are one of the most widely used computing platforms in science and engineering, supporting different programming models. However, they suffer from lack of customizability, difficult extensibility and complex workload-balancing. To this end, this work introduces virtual hybrid elastic clusters that can simultaneously harness on-premise and public Cloud resources. They can be fully customized, dynamically and automatically enlarged and shrinked (in terms of the number of nodes) and they offer migration capabilities to outsource workload from one datacenter to another (or to a public Cloud) in different situations. This is exemplified with case studies that involve a parallel computationally intensive gyro kinetic plasma turbulence code running on such hybrid clusters with resources provisioned from an on-premise OpenNebula Cloud and the Amazon Web Services public Cloud.

BibTeX Entry

@inproceedings{Calatrava2014vhe,
   abstract = {Clusters of PCs are one of the most widely used computing platforms in science and engineering, supporting different programming models. However, they suffer from lack of customizability, difficult extensibility and complex workload-balancing. To this end, this work introduces virtual hybrid elastic clusters that can simultaneously harness on-premise and public Cloud resources. They can be fully customized, dynamically and automatically enlarged and shrinked (in terms of the number of nodes) and they offer migration capabilities to outsource workload from one datacenter to another (or to a public Cloud) in different situations. This is exemplified with case studies that involve a parallel computationally intensive gyro kinetic plasma turbulence code running on such hybrid clusters with resources provisioned from an on-premise OpenNebula Cloud and the Amazon Web Services public Cloud.},
   author = {A. Calatrava and G. Moltó and M. Caballer and C. De Alfonso},
   booktitle = {8th Iberian Grid Infrastructure Conference (IberGrid 2014)},
   pages = {103-114},
   title = {Virtual Hybrid Elastic Clusters in the Cloud},
   year = {2014}
}