Content-based load balancing with multicast and TCP-handoff

Recently, cluster systems have been used by many web sites to increase service availability and balancing workload among multiple servers. There are two types of cluster architecture; centralized cluster and distributed cluster. Although centralized cluster is more effective at load balancing than distributed cluster, it contains two serious weaknesses; bottlenecking and single-point-of-failure. To achieve the strengths of both the centralized and distributed clusters, this paper proposes the use of distributed cluster using multicast technology. With the use of distributed cluster, problems of bottleneck and single-point-of-failure are effectively prevented. To gain the load balancing strength of centralized cluster, multicast technology is employed. Multicast load balancing occurs at layer-2 of the protocol stack. Hence, the overhead of request redirecting is significantly reduced. Additionally, TCP-handoff technology for content-based load balancing is applied to enhance system's availability and scalability.

[1]  Azer Bestavros,et al.  Distributed packet rewriting and its application to scalable server architectures , 1998, Proceedings Sixth International Conference on Network Protocols (Cat. No.98TB100256).

[2]  Heon Young Yeom,et al.  IP Multiplexing by Transparent Port-Address Translator , 1996, LISA.

[3]  Willy Zwaenepoel,et al.  Scalable Content-aware Request Distribution in Cluster-based Network Servers , 2000, USENIX ATC, General Track.

[4]  Yi-Min Wang,et al.  ONE-IP: Techniques for Hosting a Service on a Cluster of Machines , 1997, Comput. Networks.

[5]  George Tsirtsis,et al.  Network Address Translation - Protocol Translation (NAT-PT) , 2000, RFC.

[6]  Magnus Karlsson,et al.  Scalable Web server cluster design with workload-aware request distribution strategy WARD , 2001, Proceedings Third International Workshop on Advanced Issues of E-Commerce and Web-Based Information Systems. WECWIS 2001.

[7]  Guerney D. H. Hunt,et al.  Network Dispatcher: A Connection Router for Scalable Internet Services , 1998, Comput. Networks.

[8]  Philip S. Yu,et al.  Dynamic Load Balancing on Web-Server Systems , 1999, IEEE Internet Comput..

[9]  Daeyeon Park,et al.  Request rate adaptive dispatching architecture for scalable Internet server , 2000, Proceedings IEEE International Conference on Cluster Computing. CLUSTER 2000.

[10]  Azer Bestavros,et al.  Load balancing a cluster of web servers: using distributed packet rewriting , 2000, Conference Proceedings of the 2000 IEEE International Performance, Computing, and Communications Conference (Cat. No.00CH37086).

[11]  Daniel M. Dias,et al.  A scalable and highly available web server , 1996, COMPCON '96. Technologies for the Information Superhighway Digest of Papers.

[12]  David A. Maltz,et al.  TCP Splice for application layer proxy performance , 1999, J. High Speed Networks.

[13]  Erich M. Nahum,et al.  Enabling Content-Based Load Distribution for Scalable Services , 2002 .

[14]  W. Richard Stevens,et al.  TCP/IP Illustrated, Volume 2: The Implementation , 1995 .