• Aucun résultat trouvé

Virtual machines-based

Future of grids resources management

5.6 Future direction of resource scheduling

5.6.3 Virtual machines-based

An obvious evolution from grid to cloud computing is virtualization which enables the applications to be isolated from the physical hardware. For ex-ample, a physical machine can be used as a set of multiple logical virtual machines, while the tasks can be run on any virtual machines. So on the same physical machine, we can host multiple operating system environments

Future of grids resources management 139 separately and configure virtual machines to utilize different partitions of re-sources. Virtual machines-based technology gives challenges like the intel-ligent allocation of physical resources for managing competing resource de-mands of the users. Besides, the virtual machines and operating systems do not provide a programmer-visible way to ensure all the application threads to be run at the same time. Therefore, the future scheduling algorithm is expected to address how to assign virtual machines to meet the changing demand of resources by users as opposed to limited resources on a physical machine.

5.7 Concluding remarks

In this chapter, we provided a short overview of current computing paradigms, identifying each strength and weakness. Then, we evaluated the key components of the cloud system to give readers a better understanding about the dozens of different definitions of cloud computing. Services and resources in cloud system have then been discussed. According to the new requirements of cloud computing, layer-structured models are defined, which can address the limitation of the existing models. However, all these ideal models need further evaluation in our next step. In terms of the dynamic, secure and VM-based features, which will bring challenges and opportunities in clouds resource management domain, we discussed each of them in detail and aim to make a contribution on the resource scheduling topic in the future.

140 Fundamentals of Grid Computing

5.8 References

[Amazon Inc., 2008] Amazon Inc. (2008). Amazon simple storage service.

Available online athttp://aws.amazon.com/s3(accessed May 1, 2009).

[Amazon Inc., 2009] Amazon Inc. (2009). Amazon elastic compute cloud.

Available online at: http://aws.amazon.com/ec2 (accessed May 1, 2009).

[Armbrust et al., 2009] Armbrust, M., Fox, A., Griffith, R., Joseph, A., Katz, R., Konwinski, A., Lee, G., Patterson, D., Rabkin, A., and Stoica, I. (2009).

Above the clouds: A Berkeley view of cloud computing. Technical report, University of California, Berkeley.

[Broberg et al., 2008] Broberg, J., Venugopal, S., and Buyya, R. (2008).

Market-oriented grids and utility computing: The state-of-the-art and fu-ture directions. Journal of Grid Computing, 6:255–276.

[Buyya et al., 2000a] Buyya, R., Abramson, D., and Giddy, J. (2000a). An economy driven resource management architecture for global computational power grids. InProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA 2000), Las Vegas, NV, USA.

[Buyya et al., 2002] Buyya, R., Abramson, D., Giddy, J., and Stockinger, H. (2002). Economic models for resource management and scheduling in grid computing. Concurrency and computation: practice and experience, 14:1507–1542.

[Buyya et al., 2000b] Buyya, R., Giddy, J., and Abramson, D. (2000b). An evaluation of economy-based resource trading and scheduling on computa-tional power grids for parameter sweep applications. Kluwer Internacomputa-tional Series in Engineering and Computer Science.

[Buyya et al., 2001] Buyya, R., Stockinger, H., Giddy, J., and Abrams, D.

(2001). Economic models for management of resources in grid computing.

Technical report, Arxiv preprint cs/0106020.

[Calheiros et al., 2009] Calheiros, R., Ranjan, R., de Rose, C., Buyya, R., Trezentos, P., Yodaiken, V., Cabecinhas, F., and Lopes, N. (2009).

Cloudsim: a novel framework for modeling and simulation of cloud com-puting infrastructures and services. Technical report, Arxiv preprint arXiv:0903.2525.

[Chervenak et al., 2000] Chervenak, A., Foster, I., Kesselman, C., Salisbury, C., and Tuecke, S. (2000). The data grid: Towards an architecture for the distributed management and analysis of large scientific datasets. Journal of Network and Computer Applications, 23:187–200.

Future of grids resources management 141 [Church et al., 2008] Church, K., Hamilton, J., and Greenberg, A. (2008).

On delivering embarassingly distributed cloud services. ACM SIGCOMM Computer Communication Review.

[Eucalyptus, 2009] Eucalyptus (2009). Eucalyptus project. Available online at: http://open.eucalyptus.com/wiki/EucalyptusOverview (accessed May 1, 2009).

[Foster and Kesselman, 2004] Foster, I. and Kesselman, C. (2004). The grid:

blueprint for a new computing infrastructure. Morgan Kaufmann.

[Foster et al., 2002] Foster, I., Kesselman, C., Nick, J., and Tuecke, S. (2002).

The physiology of the grid: an open grid services architecture for distributed systems integration. InProceedings of the Open Grid Service Infrastructure WG, Global Grid Forum, USA.

[Foster et al., 2001] Foster, I., Kesselman, C., and Tuecke, S. (2001). The anatomy of the grid: enabling scalable virtual organizations. International Journal of High Performance Computing Applications, 15:200–222.

[Foster et al., 2008] Foster, I., Zhao, Y., Raicu, I., and Lu, S. (2008). Cloud computing and grid computing 360-degree compared. InGCE’08: Proceed-ings of the Grid Computing Environments Workshop, pages 1–10.

[Gens, 2008] Gens, F. (2008). Defining “cloud services” and “cloud comput-ing”. Available online at: http://blogs.idc.com/ie/?p=190 (accessed May 1, 2009).

[Google, 2008] Google (2008). Google app engine. Available online at: http:

//code.google.com/appengine/ (accessed May 1, 2009).

[HP, 2004] HP (2004). Hp utility data center. Available online at: http:

//www.hp.com/#Product (accessed May 1, 2009).

[IBM, 2007] IBM (2007). Ibm blue cloud project. Available online at: http://

www.ibm.com/developerworks/linux/library/l-cloud-computing/ (accessed May 1, 2009).

[Jin and Liu, 2004] Jin, X. and Liu, J. (2004).From individual based modeling to autonomy oriented computation. Lecture Notes in Computer Science.

[Liu et al., 2005] Liu, J., Jin, X., and Tsui, K. (2005). Autonomy oriented computing: from problem solving to complex systems modeling. Kluwer Academic Publishers.

[Magoul`es et al., 2008] Magoul`es, F., Nguyen, M., and Yu, L. (2008). Grid resource management: Towards virtual and services compliant grid com-puting. Chapman & Hall, CRC Press, Boca Raton, FL, USA.

142 Fundamentals of Grid Computing

[Microsoft Corp., 2008] Microsoft Corp. (2008). Microsoft software plus ser-vice. Available online at: http://www.microsoft.com/serviceproviders/

saas/default.mspx (accessed May 1, 2009).

[Paleologo, 2004] Paleologo, G. (2004). Price-at-risk: A methodology for pric-ing utility computpric-ing services. IBM Systems Journal, 43:20–31.

[Rappa, 2004] Rappa, M. (2004). The utility business model and the future of computing services. IBM Systems Journal, 43:32–42.

[Shiers, 2009] Shiers, J. (2009). Grid today, clouds on the horizon. Computer Physics Communications, 180:559–563.

[Wang et al., 2008] Wang, L., Laszewski, G. V., Kunze, M., and Tao, J.

(2008). Cloud computing: A perspective study. InProceedings of the 2008 Microsoft eScience Workshop.

[Weiss, 2007] Weiss, A. (2007). Computing in the clouds. ACM, 11(4):16–25.

[Yeo and Buyya, 2006] Yeo, C. and Buyya, R. (2006). A taxonomy of market-based resource management systems for utility-driven cluster computing.

Software: Practice and Experience, 36:1381–1419.

[Yeo et al., 2006] Yeo, C., de Assuncao, M., Yu, J., Sulistio, A., Venugopal, S., Placek, M., and Buyya, R. (2006). Utility computing and global grids.

Technical report, Arxiv preprint cs/0605056.

[Yu and Magoul`es, 2009] Yu, L. and Magoul`es, F. (2009). Service scheduling and rescheduling in an applications integration framework. Advances in Engineering Software, 40:941–946.

Chapter 6

Fault-tolerance and availability