Towards a green cluster through dynamic remapping of virtual machines

Since power is one of the major limiting factors for a data center or for large cluster growth, the objective of this study is to minimize the power consumption of the cluster without violating the performance constraints of the applications. We propose a runtime virtual machine (VM) mapping framework in a cluster or data center to save energy. The new framework can make reconfiguration decisions on time with the consideration of a low influence on the performance. In the GreenMap framework, one probabilistic, heuristic algorithm is designed for the optimization problem: mapping VMs onto a set of physical machines (PMs) under the constraint of multi-dimensional resource consumptions. Experimental measurements show that the new method can reduce the power consumption by up to 69.2% over base, with few performance penalties. The effectiveness and performance insights are also analytically verified.

[1]  Reza Entezari-Maleki,et al.  Task scheduling modelling and reliability evaluation of grid services using coloured Petri nets , 2010, Future Gener. Comput. Syst..

[2]  Kirk W. Cameron,et al.  An Implementation of Page Allocation Shaping for Energy Efficiency , 2007, 2007 IEEE International Parallel and Distributed Processing Symposium.

[3]  Steven Skiena,et al.  The Algorithm Design Manual , 2020, Texts in Computer Science.

[4]  E. N. Elnozahy,et al.  Energy-Efficient Server Clusters , 2002, PACS.

[5]  Li Xiao,et al.  Adaptive and virtual reconfigurations for effective dynamic job scheduling in cluster systems , 2002, Proceedings 22nd International Conference on Distributed Computing Systems.

[6]  Karsten Schwan,et al.  Vpm tokens: virtual machine-aware power budgeting in datacenters , 2008, HPDC '08.

[7]  Dror G. Feitelson,et al.  Paired Gang Scheduling , 2003, IEEE Trans. Parallel Distributed Syst..

[8]  Renato J. O. Figueiredo,et al.  Experimental Study of Virtual Machine Migration in Support of Reservation of Cluster Resources , 2007, Proceedings of the 2nd International Workshop on Virtualization Technology in Distributed Computing (VTDC '07).

[9]  Eduardo Huedo,et al.  A decentralized model for scheduling independent tasks in Federated Grids , 2009, Future Gener. Comput. Syst..

[10]  Fatos Xhafa,et al.  Computational models and heuristic methods for Grid scheduling problems , 2010, Future Gener. Comput. Syst..

[11]  James L. Peterson,et al.  Design and validation of a performance and power simulator for PowerPC systems , 2003, IBM J. Res. Dev..

[12]  Christos Kozyrakis,et al.  Full-System Power Analysis and Modeling for Server Environments , 2006 .

[13]  Li Xiao,et al.  Dynamic load sharing with unknown memory demands in clusters , 2001, Proceedings 21st International Conference on Distributed Computing Systems.

[14]  Andrzej Kochut,et al.  Dynamic Placement of Virtual Machines for Managing SLA Violations , 2007, 2007 10th IFIP/IEEE International Symposium on Integrated Network Management.

[15]  Akshat Verma,et al.  pMapper: Power and Migration Cost Aware Application Placement in Virtualized Systems , 2008, Middleware.

[16]  Andrew Warfield,et al.  Live migration of virtual machines , 2005, NSDI.

[17]  Thomas A. Henzinger,et al.  FlexPRICE: Flexible Provisioning of Resources in a Cloud Environment , 2010, 2010 IEEE 3rd International Conference on Cloud Computing.

[18]  Liang Zhong,et al.  EnaCloud: An Energy-Saving Application Live Placement Approach for Cloud Computing Environments , 2009, 2009 IEEE International Conference on Cloud Computing.

[19]  Mark S. Squillante,et al.  Analysis of Job Arrival Patterns and Parallel Scheduling Performance , 1999, Perform. Evaluation.

[20]  Li Xiao,et al.  Improving distributed workload performance by sharing both CPU and memory resources , 2000, Proceedings 20th IEEE International Conference on Distributed Computing Systems.