MMNS 2001 Keynote/Invited Speakers

Keynote Speaker:

Managing the Grid David Hutchison Lancaster University, UK

Abstract: The 'Grid' is, by analogy with the electricity grid, intended to be a plug-in source of (distributed) computing services. Of course, applications will implicitly or explicitly use the communications services of the Grid, which will largely be based on Internet technology. A vital part of the Grid is the set of middleware services, including resource location and remote invocation of operations, that applications will frequently require. Initially the Grid will support e-Science applications including those from the slikely to become a common platform for supporting other sorts of application including Ubiquitous Computing and possibly e-Business. Given the key role of the Grid in underpinning applications that, for the most part, will require predictable and dependable Quality of Service, management of the underlying networks and the Grid services becomes a hot topic. This talk will present a personal perspective on the issues in Managing the Grid.

Speaker Bio: David Hutchison is Professor of Computing at Lancaster University and has worked in the areas of computer communications and distributed systems for more than 15 years. He has completed many UK and European funded research contracts and published over 120 papers as well as writing and editing books in these areas. The main theme of his current research is architecture, services and protocols for distributed multimedia systems, including QoS for the Internet (IPv6, IntServ, DiffServ etc.), and multimedia content description and extraction. He is involved in several UK and European collaborative projects, in which an integrating theme is Quality of Service for multimedia communications. He is a programme committee member for many international conferences and workshops, was Program Chair of the IEEE OpenArch 2000 Conference, and more recently Program Co

Chair of the International Workshop on Quality of Service held in 2001 (IWQoS 2001). As of mid 2001, he is a member of the UK Grid Technical Advisory Group, and chair of the Grid Network Team responsible for the communications infrastructure to be used by e

Science applications funded by the UK Research Councils.

Invited Speaker:

Managing Distributed Systems: Approaches to Problem Determination Gautam Kar IBM T. J. Watson Research center

Abstract: One of the most significant challenges in managing modern enterprise systems lies in the area of problem determination - detecting system problems, isolating their root causes, and identifying proper repair procedures. Problem determination is crucial for reducing the length of system outages and for quickly mitigating the effects of performance degradations, yet it is becoming an increasingly difficult task as systems grow in complexity. This is especially true as the number of system hardware and software components increases, since more components result in more places that the system manager must examine in order to identify the cause of an end-user-reported problem, and also more paths by which the effects of problems can propagate between components, masking the original root cause. A promising approach to managing this complexity, and thereby simplifying problem determination, lies in the study of dependencies between system hardware and software components. Some work has been reported in the literature describing the use of dependency models for the important root-cause analysis stage of problem determination, that is, for the process of determining which system component is ultimately responsible for the symptoms of a given problem. However, there has been little work on the requisite task of automatically obtaining accurate, detailed, up-to-date dependency models from a complex distributed system; most existing problem determination work assumes the pre-existence of a manually constructed dependency model, an optimistic assumption given the complexity and dynamics of many of today’s enterprise and Internet-service systems. While there has been some work on automatically extracting static, single-node dependencies, there does not appear to be an existing solution for automatically detecting dynamic runtime dependencies, especially those that cross system and domain boundaries. This talk will present an approach based on perturbation and fault injection for discovering such dependencies. Further, the talk will illustrate how dependency data can be used as an aid to root cause analysis while performing end to end problem determination in a distributed system.

Speaker Bio: Dr. Gautam Kar has over twenty years experience in the areas of computer & telecommunication networks with focus on distributed systems & network management. He has held senior management and technical strategist positions in network/distributed systems design and management, value added network services definition & delivery and software development in IBM USA , IBM Europe and the ITT Corporation. Gautam received a PhD in Computer and Information Science from the Ohio State University, Columbus, Ohio. After teaching at the University of South Carolina for three years as an Assistant Professor of Computer Science, he joined the ITT Advanced Technology Center as a Member of Technical Staff. He was at ITT for three years, where he worked on the design and implementation of database and call processing software for distributed telephone switches. In 1983, Gautam joined the IBM T.J. Watson Research Center and has been associated with it since. Currently, he is the Manager of the Intelligent Server Management group. His research interests include, management of distributed systems and modeling and designing web based services. During his eighteen year tenure at IBM, Gautam has worked in several divisions besides the Research Division. From 1989 to 1993, he was the Manager of the Distributed Applications research group at the IBM European Networking Center in Heidelberg, Germany. From 1994 to 1999, he was the Senior Manager of Network and Systems Management in the IBM Global Network Services division. Dr. Kar is active in the Distributed Systems research community. He has published in the top conferences in this field and has served as the Technical Program Chair for the Eleventh IFIP/IEEE International Workshop on Distributed Systems, December 2000. He is a co editor of Lecture Notes in Computer Science: Services Management in Intelligent Networks (No. 1960), Springer Verlag, 2000.

Invited Speaker:

Networks On-Demands Andrew T. Campbell Columbia University

Abstract: (not available yet)

Speaker Bio: Andrew T. Campbell is an Associate Professor in the Department of Electrical Engineering and member of the COMET Group and Columbia Networking Research Center (CNRC), Columbia University. His areas on interest encompass mobile computing and networking, open programmable networks, and quality of service research. Andrew received his Ph.D in Computer Science in 1996 and the NSF CAREER Award for his research in programmable mobile networking in 1999.