Locality-aware request distribution in cluster-based network servers
Proceedings of the eighth international conference on Architectural support for programming languages and operating systems
A client-aware dispatching algorithm for web clusters providing multiple services
Proceedings of the 10th international conference on World Wide Web
Efficiency vs. portability in cluster-based network servers
PPoPP '01 Proceedings of the eighth ACM SIGPLAN symposium on Principles and practices of parallel programming
Scalable Web Server Cluster Design with Workload-Aware Request Distribution Strategy WARD
WECWIS '01 Proceedings of the Third International Workshop on Advanced Issues of E-Commerce and Web-Based Information Systems (WECWIS '01)
Efficient support for content-aware request distribution and persistent connection in Web clusters
Software—Practice & Experience
Journal of Systems and Software
New content-aware request distribution policies in web clusters providing multiple services
Proceedings of the 2009 ACM symposium on Applied Computing
Proceedings of the 20th international conference companion on World wide web
Hi-index | 0.00 |
The content-aware load balancing strategy uses the services or content requested for the scheduling of a request. This paper considers a special scenario where the application server and database server are deployed over a Distributed Computing Environment (DCE). The content aware algorithms developed till now are specially designed for the clusters computing, but this paper considers all possible DCE like cluster, grid and cloud computing. There are two types of users in a DCE, namely the service providers and consumers. Service providers provide the services to its consumers' requests. Generally the services providers offer the computing nodes for processing of the users requests. This paper proposes a new content aware load balancing policy called workload and client aware policy (WCAP). This method is a hybrid approach of client aware policy and workload aware request distribution policy discussed below. A parameter unique and special property (USP) is defined to specify the property of the service provider's computing nodes and the consumer's requests for data. This parameter specifies the unique and special property of the requests as well as computing nodes. Based on this parameter, the scheduler decides the node that is best suitable for the processing of the requests. This load balancing strategy is implemented in a decentralized manner with low overhead. Preliminary investigation proves that the proposed method is a promising content aware load balancing.