An Achievement of High Availability and Low Cost on Data Center Infrastructure
Keywords:Cloud, Data Center, High Availability (HA), Virtualization Clustering, Failover, Load Balance.
AbstractThis study is to provide a design of low-cost and high-availability data center infrastructure for small/medium-scale businesses. The basic concept is to establish an infrastructure consisting of primary and backup sides through the clustering technology. By default, the primary side is active and responsible for data switching while the backup side is standby for the failure of the primary side. The design achieves the features of 1) providing full-level high availability (HA) at network, server, application, and management levels, 2) controlling the routing among network-level clusters to solve the “PPPOE connection racing” and “winding path” problems, 3) monitoring and recovering the objects in each level with an economic and effective way, and 4) handling events resulting from changing of object states in an event center. Finally, the experiment results are exhibited with five testing scenarios for verification and elaboration of the effectiveness of the HA design. The system can recover the failed objects and solve the routing problems of PPPOE connection racing and winding path among HA clusters automatically.
(1) Cegielski, C. G., Bourrie, D. M. & Hazen, B. T., Evaluating Adoption of Emerging IT for Corporate IT Strategy: Developing a Model Using a Qualitative Method. Information Systems Management, 2013. 30 (3): p. 235–249.
(2) Duan, Q., Yan, Y. & Vasilakos, A. V., A Survey on Service-Oriented Network Virtualization toward Convergence of Networking and Cloud Computing. IEEE Transactions on Network and Service Management, 2012. 9 (4): p. 373–392.
(3) Araujo, J. A., Lazaro, J., Astarloa, A., Zuloaga, A. & Garcia, A., High Availability Automation Networks: PRP and HSR ring implementations. IEEE International Symposium on Industrial Electronics (ISIE) 2012: p. 1197–1202.
(4) Sharkh, M. A., Jammal, M., Shami, A., & Ouda, A., Resource Allocation in a Network-Based Cloud Computing Environment: Design Challenges. IEEE Communications Magazine, 2013. 51 (11): p. 46–52.
(5) Bitar, N., Gringeri, S. & Xia, T. J., Technologies and protocols for data center and cloud networking. IEEE Communications Magazine, 2013. 51 (9): p. 24–31.
(6) Liao, C. F., Chang, H. C. & Fu, L. C., Message-Efficient Service Management Schemes for MOM-Based UPnP Networks. IEEE Transactions on Services Computing, 2013. 6 (2): p. 214–226.
(7) Lin, C. C., Chin, H. H. & Deng, D. J., Dynamic Multiservice Load Balancing in Cloud-Based Multimedia System. IEEE Systems Journal, 2014. 8 (1): p. 225–234.
(8) LVS. http://www.linuxvirtualserver.org as of October 11, 2015.
(9) Vyatta. Vyatta Community Documentation. http://www.vyatta.org/ as of August 15, 2014.
(10) NMap. http://nmap.org/ as of October 11, 2015.
(11) Membrey, P., Plugge, E. & Hows, D., Practical Load Balancing: Ride the Performance Tiger, 2012. 1st Ed. Apress.
(12) Rusu, L. & Smeu, A., Managing the Reliable Design of an Enterprise IT Network Infrastructure. Information Systems Management, 2010. 27 (3): p. 238–246.
(13) Radhakrishnan, R., Mark, K., & Powell, B., IT Service Management for High Availability. IBM Systems Journal, 2008. 47 (4): p. 549–561.
(14) Mahmood, A. & Rashid, I., Comparison of load balancing algorithms for clustered web servers. International Conference on Information Technology and Multimedia (ICIM) 2011: p. 1–6.
(15) IT Today. Is High-Performance Computing For You? IBM Systems Magazine, Power Systems, January. 2013.
(16) Cisco. Cisco Data Center Infrastructure 2.5 Design Guide. Cisco Validated Design. 2013.
(17) HP. Designing Disaster Tolerant High Availability Clusters. Manufacturing Part Number: B7660-90006. HP Document. 2014.
(18) Ahmed, I., Auvenshine, J. J., & Blackburn, J., System for Autonomic Monitoring for Web High Availability. IBM Corp. US 7996529 B2; Patent.
August 9, 2011.
(19) Sim, K. M., Agent-based Approaches for Intelligent InterCloud Resource Allocation, IEEE Transactions on Cloud Computing, 2016: p. 1-14.