Adaptive Load Balancing Mechanism for Server Cluster
Server cluster provides high availability, scalability, and reliability by gathering server nodes into a group. Client requests need to be distributed to each server node fairly to maximize the performance of server cluster. In this paper, we propose an adaptive and efficient load balancing algorithm for the server cluster. The proposed algorithm computes the load of server nodes with the usages of computer resources and their weights. These weights are determined dynamically based on the statistics of the usages. The experimental result shows that the proposed algorithm can prevent the bottleneck of server cluster efficiently compared with existing algorithms. This guarantees its adaptability even though there are changes to the characteristic of service.
KeywordsLoad Balancer Server Node Load Information Client Request Request Rate
Unable to display preview. Download preview PDF.
- 1.Zhang, W.: Linux virtual server for scalable network services. In: Proceedings of the Ottawa Linux Symposium 2000 (July 2000)Google Scholar
- 2.The linux virtual server project - linux server cluster for load balancing, http://www.linuxvirtualserver.org/
- 3.Baik, H.-K., Kim, G.-H., Park, M.-S., Shin, Y.-H., Lee, S.-H.: Agent-based sophisticated and scalable scheduling method. In: Proc. 3rd International Network Conference (2002)Google Scholar
- 4.Jangho, L., Park, M.-S., Kang, K., Lee, S.: Assum:agent-based sophisticated scheduling mechanism by using memory utilization in web server cluster (2003)Google Scholar
- 6.Yoshikawa, C., Chun, B., Eastham, P., Vahdat, A., Anderson, T., Culler, D.: Using smart clients to build scalable services. In: Proceedings of the USENIX 1997 Annual Technical Conference. USENIX Association (1997)Google Scholar
- 7.Kwan, T.T., McCrath, R., Reed, D.A.: NCSA’s world wide web server: Design and performance. IEEE Computer 28(11), 68–74 (1995)Google Scholar