Modeling Energy Savings for Job Migration in Grid Environments

An open issue to exploit Grid resources is related to job migration, possibly due to resource failures (real or perceived ones) or to the violation of QoS, it may be required to migrate an entire job, or parts of it, to other resources and reschedule the job there. There are several research questions associated with the migration concept. The two most crucial ones are determination of metrics and conditions when to migrate, and the selection of the resource to migrate the job to. In this work, we propose to combine job migration with energy consumption indicators. The objective is to understand if it is possible to exploit the migration of jobs also to save energy. Thus the main question of this work is "Can job migration save energy?". In order to provide an answer, we define a simple model to evaluate the energy consumption related to Grid job migration. An adequate Grid infrastructure is assumed to actually enable job migration, and the proposed model will take into account the overhead arising from that infrastructure.

[1]  Ian Foster,et al.  The Grid: A New Infrastructure for 21st Century Science , 2002 .

[2]  Nicholas J. Wright,et al.  WRF nature run , 2007, Proceedings of the 2007 ACM/IEEE Conference on Supercomputing (SC '07).

[3]  Rajkumar Buyya,et al.  Exploiting Heterogeneity in Grid Computing for Energy-Efficient Resource Allocation , 2009 .

[4]  Isabelle Guérin Lassous,et al.  ECOFEN: An End-to-end energy Cost mOdel and simulator For Evaluating power consumption in large-scale Networks , 2011, 2011 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks.

[5]  Alexandru Iosup,et al.  How are Real Grids Used? The Analysis of Four Grid Traces and Its Implications , 2006, 2006 7th IEEE/ACM International Conference on Grid Computing.

[6]  Laurent Lefèvre,et al.  The GREEN-NET framework: Energy efficiency in large scale distributed systems , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[7]  Albert Y. Zomaya,et al.  Energy efficient utilization of resources in cloud computing systems , 2010, The Journal of Supercomputing.

[8]  San Murugesan,et al.  Harnessing Green IT: Principles and Practices , 2008, IT Professional.

[9]  Jianhui Li,et al.  A performance and energy optimization mechanism for cooperation-oriented multiple server clusters , 2012, Future Gener. Comput. Syst..

[10]  Francesco Palmieri,et al.  Towards a federated Metropolitan Area Grid environment: The SCoPE network-aware infrastructure , 2010, Future Gener. Comput. Syst..

[11]  Albert Y. Zomaya,et al.  Cooperative power-aware scheduling in grid computing environments , 2010, J. Parallel Distributed Comput..

[12]  Calton Pu,et al.  Mistral: Dynamically Managing Power, Performance, and Adaptation Cost in Cloud Infrastructures , 2010, 2010 IEEE 30th International Conference on Distributed Computing Systems.

[13]  N. Rasmussen.  Calculating Total Cooling Requirements for Data Centers , 2007 .

[14]  Helen D. Karatza,et al.  Performance and energy aware cluster-level scheduling of compute-intensive jobs with unknown service times , 2011, Simul. Model. Pract. Theory.