COLLOQUIUM Department of Computer Science and Engineering University of South Carolina Clustering, Resource Management, and Replication Support for Large-scale Internet Services Kai Shen Department of Computer Science University of California at Santa Barbara Date: March 8, 2002 (Friday) Time: 4:00-5:00PM Place: 300 Main B110 Abstract With the increasing demand of providing highly scalable, available and asy-to-manage services, the deployment of large-scale complex server clusters has been rapidly emerging in which service components are usually partitioned, replicated, and aggregated. In this talk, I will present my research in building a software infrastructure(Neptune) that provides clustering, resource management, and replication support for large-scale internet services. Neptune has been deployed at Internet search engines Teoma and Aks Jeeves in a commercial system serving 6-7 million search queries per day. Neptune's clustering architecture is based on the design principles of symmetry, decentralization, non-scaling overhead, and soft state to achieve high scalability, availability, and manageability. I will first talk about Neptune's overall clustering architecture, followed by a brief discussion on the load balancing support for fine-grain services. In the second part of the talk, I will present an integrated resource management framework combining resource utilization efficiency, consumer-perceived service response time, and service differentiation support. In the end, I will present my work on service replication. Replication of persistent service data is crucial to achieving high availability. My work focused on providing scalable replication support at the intended consistency level with high availability and failure recovery support. Kai Shen is currently a Ph.D. student in the Computer Science Department at the University of California at Santa Barbara. His research interests include parallel and distributed systems, scalable network services, Internet search, and high performance scientific computing. He worked for Microsoft and Internet search engine Teoma Technologies (acquired by Ask Jeeves).