InformationManagementSystems创新.PDFVIP

Dynamic Policy-Driven Quality of Service in Service-Oriented Information Management Systems Joseph P. Loyall,1 Matthew Gillen,1 Aaron Paulos,1 Larry Bunch,2 Marco Carvalho,2 James Edmondson,3 3 4 5 Douglas C. Schmidt, Andrew Martignoni III , and Asher Sinclair 1BBN Technologies, Cambridge, MA USA 2Institute for Human Machine Cognition, Pensacola, FL USA 3Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN USA 4The Boeing Company, St. Louis, MO USA 5Air Force Research Laboratory, Rome, NY USA ABSTRACT Service-oriented architecture (SOA) middleware has emerged as a powerful and popular distributed computing paradigm due to its high-level abstractions for composing systems and encapsulating plat- form-level details and complexities. Control of some details encapsulated by SOA middleware is ne- cessary, however, to provide managed quality-of-service (QoS) for SOA systems that require pre- dictable performance and behavior. This paper presents a policy-driven approach for managing QoS in SOA systems called QoS Enabled Dissemination (QED). QED includes services for (1) specifying and enforcing the QoS preferences of individual clients, (2) mediating and aggregating QoS man- agement on behalf of competing users, and (3) shaping information exchange to improve real-time performance. We describe QED’s QoS services and mechanisms in the context of managing QoS for a set of Publish-Subscribe-Query information management services. These services provide a repre- sentative case study in which CPU and network bottlenecks can occur, client QoS preferences can conflict, and system-level QoS requirements are based on higher level, aggregate end-to-end goals. We also discuss the design of several key QoS services and describe how QED’s policy-driven ap- proach b