Complementarity Between Virtualization and Single System Image Technologies ⋆ J´ erˆomeGallard 1 , Geoffroy Vall´ ee 2 , Adrien L` ebre 1 , Christine Morin 1 , Pascal Gallard 3 , and Stephen L. Scott 2 1 INRIA Rennes - Bretagne Atlantique, PARIS project-team, Rennes, France 2 Oak Ridge National Laboratory, Oak Ridge, USA 3 KERLABS, Rennes, France {jerome.gallard,adrien.lebre,christine.morin}@inria.fr {valleegr,scottsl}@ornl.gov pascal.gallard@kerlabs.com Abstract. Nowadays, the use of clusters in research centers or industries is undeniable. Since few years, the usage of virtual machines (VM) offers more advanced resource management capabilities, using features such as virtual machine live migration. Because of the latest contributions in the domain, some may argue that single system image (SSI) technologies are now deprecated, without considering some complementarities between VMs and SSI technologies are possible. After evaluating different configurations, we show that combining both approaches allows us to better address cluster challenges such as flexi- bility for the usage of available resources and simplicity of use. In other terms, the study shows that VMs add a level of management flexibility between the hardware and the application, whereas, SSIs give an ab- straction of the distributed resources. The simultaneous usage of both technologies could improve the overall platform resources utilization, the cluster productivity and the efficiency of the running applications. Key words: cluster, virtualization, SSI, resource management. 1 Introduction Clusters are today a standard computation platform for both research and pro- duction. Batch schedulers or single system image systems (SSI) are frequently used to manage clusters. In the first case, a head node is in charge of scheduling applications whereas in the second case, the SSI makes an abstraction of the cluster resources creating the illusion of an SMP machine. Several studies have focused on combining virtual machines (VMs) and batch schedulers in order ⋆ The INRIA team carries out this research work in the framework of the XtreemOS project partially funded by the European Commission under contract #FP6-033576. ORNL’s research sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory (ORNL), managed by UT-Battelle, LLC for the U. S. Department of Energy under Contract No. DE-AC05-00OR22725.