International Journal of Distributed and Cloud Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Performance Evaluation of Private Clouds:OpenStack Vs Eucalyptus


Affiliations
1 Department of Computer Engineering, Aligarh Muslim University, Aligarh, Uttar Pradesh, India
     

   Subscribe/Renew Journal


With the rapid growth of cloud infrastructure in the organizations, more applications are dependent on the quality of services like network, disk, memory, processor. Due to this, many organizations drift towards choosing right cloud for deploying the application which caters to user’s needs. Currently, opensource cloud platforms (OpenStack, Eucalyptus, Cloudstack, Opennebula etc) are gaining a lot of popularity that establishes private cloud with low cost. But it is difficult for organizations to choose a platform suitable for hosting web application or running virtual machines for high availability. This paper focuses on choosing right cloud platform for network, disk, processor, and memory in running application specific to user’s need. The efficacy of our method is validated through a series of experiments which consists of benchmarking the performance of OpenStack and Eucalyptus opensource private clouds. The experimental result shows that Eucalyptus cloud performs better for Network, Memory and Processing operations while OpenStack cloud performs better for Disk I/O operations.

Keywords

Benchmarks, Cloud, Eucalyptus, OpenStack.
Subscription Login to verify subscription
User
Notifications
Font Size


  • O. Sefraoui, M. Aissaoui, and M. Eleuldg, “Comparison of multiple IaaS cloud platform solutions, recent researches in information science and applications,” Proceedings of the 7th WSEAS International Conference on Computer Engineering and Applications (CEA ‘13), pp. 212-217, 2013.

  • M. M. A. Al-Mukhtar, and A. A. A. Mardan, “Performance evaluation of private clouds eucalyptus vs cloudstack,” International Journal of Advanced Computer Science and Applications, vol.5, no.5, pp. 108-117, 2014.

  • A. Husain, M. H. Zaki, and S. Islam, “Pooling of Computing Resources in Private Cloud Deployment,” International Journal of Engineering Research in Computer Science and Engineering, vol. 4, no. 10, pp. 92-98, 2017.

  • A. S. Pilla, and L.S. Swasthimthi, “A study on open source cloud computing platforms,” EXCEL International Journal of Multidisciplinary Management Studies, vol. 2, no. 7, pp. 31-40, 2012.

  • N. Nagar, and U. Suman, “Architectural comparison and implementation of cloud tools and technologies,” International Journal of Future Computer and Communication, vol. 3, no. 3, pp. 153-160, June 2014.

  • B. Varghese, O. Akgun, L. Miguel, L. Thai, and A. Barker, “Cloud Benchmarking for performance,” IEEE 6th International Conference on Cloud Computing Technology and Science, pp. 1-14, 2014.

  • X. Wen, G. Gu, Q. Li, Y. Gao, and X. Zhang, “Comparison of opensource cloud management platforms openstack and open nebula,” 9th International Conference on Fuzzy Systems and Knowledge Discovery, pp. 29-31, May 2012.

  • A. Habbal, S. Hassan, B. M. Addokali, and N. Benamar, “Design and assessment of an experimental sdn-enabled private cloud using openstack,” Journal of Telecommunication, Electronic and Computer Engineering, vol. 9, no. 1-4, pp. 1-5, 2017.

  • A. Zerouali, and T, Mens, “An empirical comparison of the development history of cloudstack and eucalyptus,” In Proceedings of ICSDE 17, Rabat, Morocco, July 21-23, 2017,

  • A. Habbal, S. A. Abdullah, E. O. C. Mkpojiogu, S. Hassan, N. Benamar, “Assessing Experimental Private Cloud Using Web of System Performance Model,” International Journal of Grid and High-Performance Computing, vol. 9, no. 2, pp. 21-35, April-June 2017.

  • S. Mohapatra, S. Mohanty, A. Hota, and S. Pattanayak, “Performance evaluation of virtualization in a private cloud test bed,” International Journal of Computer Applications, vol. 162, no. 7, pp. 20-27, March 2017.

  • T. Brummet, P. Sheinidashtegol, D. Sarkar, M. Galloway, “Performance metrics of local cloud computing architectures,” IEEE 2nd International Conference on Cyber Security and Cloud Computing, pp. 3-5, November 2015.

  • D.Steinmetz, B. W. Perrault, R. Nordeen, J. Wilson, X. Wang, Cloud computing performance benchmarking and virtual machine launch time,” Proceedings of the 13th Annual Conference on Information Technology Education, pp. 89-90, October 2012.

  • M. Riasetiawan, A. Ashari, and S. W. Kumoro, “Resource isolation analysis on virtual server performance,” International Journal of Scientific Engineering and Research, vol.5, no. 1, pp. 1815-1819, 2014.

  • N. Kaur, and H. Singh, “A review on monitoring cloud performance using linpack benchmark on KVM in cloudstack platform,” International Journal of Advance Research in Science and Engineering, vol. 3, no. 7, pp. 29-38, July, 2014.

  • V. N. Van, L. M. Chi, N. Q. Long, G. N. Nguyen, and D. N. Le, “A performance analysis of openstack opensource solution for IAAS Cloud Computing,” Proceedings of the 2nd International Conference on Computer and Communication Technologies, vol. 2, pp. 141-150, 2015.

  • M. A. Khamis, M. Hataba, S. Samra, and A. El-Mahdy, “performance analysis of eucalyptus vs EC2 cloud for HPC scientific computing,” 2015.

  • Y. Tamura, and S. Yamada, “Performance evaluation and dependability analysis for opensource cloud computing,” International Transactions on System Science and Applications,” vol.8, pp. 1-11, December 2012.

  • C. El-Amrani, K. B. Filali, K. B. Ahmed, A. T. Diallo, S. Telolahy, and T. El-Ghazawi, “A Comparative Study of Cloud Computing Middleware,” Proceeding of the 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 690-693, 2012.

  • OpenStack. Available www.openstack.org (accessed on 20 January 2017)

  • OpenNebula Web page. Available www.opennebula.org (Accessed on 22 January 2017)

  • Eucalyptus Webpage. Available https://docs.eucalyptus.com/eucalyptus/3.4.3/install-guide/faststart.html (Accessed on 2 February 2017)

  • Iperf Web page. Available https://openmaniak.com/iperf.php (Available on 12 March 2017)

  • Bonnie++ Web page. Available https://www.jamescoyle.net/how-to/913-simple-bonnie-example (Accessed on 6 April 2017)

  • Stream Web page. Available https://www.cs.virginia.edu/stream (Accessed on 10 April 2017 )

  • Linpack Webpage. Available http://people.sc.fsu.edu/~jburkardt/c_src/linpack_bench/linpack_bench.c (Accessed on 1 May 2017)

  • Linpack Benchmark Report. Available http://www.netlib.org/utk/people/JackDongarra/faq-linpack.html ( Accessed on 5 May 2017)


Abstract Views: 253

PDF Views: 0




  • Performance Evaluation of Private Clouds:OpenStack Vs Eucalyptus

Abstract Views: 253  |  PDF Views: 0

Authors

A. Husain
Department of Computer Engineering, Aligarh Muslim University, Aligarh, Uttar Pradesh, India
M. H. Zaki
Department of Computer Engineering, Aligarh Muslim University, Aligarh, Uttar Pradesh, India
S. Islam
Department of Computer Engineering, Aligarh Muslim University, Aligarh, Uttar Pradesh, India

Abstract


With the rapid growth of cloud infrastructure in the organizations, more applications are dependent on the quality of services like network, disk, memory, processor. Due to this, many organizations drift towards choosing right cloud for deploying the application which caters to user’s needs. Currently, opensource cloud platforms (OpenStack, Eucalyptus, Cloudstack, Opennebula etc) are gaining a lot of popularity that establishes private cloud with low cost. But it is difficult for organizations to choose a platform suitable for hosting web application or running virtual machines for high availability. This paper focuses on choosing right cloud platform for network, disk, processor, and memory in running application specific to user’s need. The efficacy of our method is validated through a series of experiments which consists of benchmarking the performance of OpenStack and Eucalyptus opensource private clouds. The experimental result shows that Eucalyptus cloud performs better for Network, Memory and Processing operations while OpenStack cloud performs better for Disk I/O operations.

Keywords


Benchmarks, Cloud, Eucalyptus, OpenStack.

References