220 Int. J. High Performance Computing and Networking, Vol. 6, Nos. 3/4, 2010 Copyright © 2010 Inderscience Enterprises Ltd. Supporting time-critical clients in scalable pub-sub systems Sibabrata Ray Google Inc., 604 Arizona Blvd., Santa Monica, CA 90401, USA E-mail: siburay@gmail.com Mark H. Linderman Air Force Research Laboratory, 525 Brooks Road, Rome, NY 13441-4505, USA Fax: (315) 330-7009 E-mail: mark.linderman@rl.af.mil Danyang Zhang* Department of Mathematics and Computer Science, School of Arts and Sciences, York College, The City University of New York, 94-20 Guy R. Brewer Blvd., Jamaica, NY 11451, USA E-mail: dzhang@york.cuny.edu *Corresponding author Abstract: In a publish-subscribe environment like the Air Force Joint Battlespace Infosphere (JBI), information/data has to be efficiently and reliably transmitted between servers and clients. However, due to various reasons such as unexpected network traffic, hardware/software failure, etc., the overlay network of the system may require reconfiguration, leading to intolerable service interruption of information flow to time-critical applications. This paper proposes theoretical methods for providing temporary respite to the time-critical clients while the backbone network is under repair. Keywords: overlay network; Joint Battlespace Infosphere; JBI; alternate server list; recovery scheme; reliability. Reference to this paper should be made as follows: Ray, S., Linderman, M.H. and Zhang, D.Z. (2010) ‘Supporting time-critical clients in scalable pub-sub systems’, Int. J. High Performance Computing and Networking, Vol. 6, Nos. 3/4, pp.220–225. Biographical notes: R. Sibabrata is currently working for Google Inc. He received his PhD in Computer Science from the University of Nebraska. He has numerous publications in prestigious conferences and journals. His research interests include parallel and distributed systems, networking, sensor networks, network security, wireless and ad-hoc networking and distributed algorithms. M. Linderman is a Principal Researcher in Information Management Technologies at the Air Force Research Laboratory Information Directorate. He received his PhD in Electrical Engineering from Cornell University. He is active in the Technical Cooperation Program (TTCP) that fosters collaboration of research, development and experimentation among the USA, the UK, Australia and Canada. D. Zhang is currently an Assistant Professor of Computer Science at York College, CUNY. He is also a Doctoral Faculty at CUNY Graduate Center. He received his PhD in Computer Science from the University of Alabama. He has many publications in international journals and conferences. His research interests include multicasting, overlay network, sensor networks, distributed computing, pervasive computing and graph theory. 1 Introduction With the advent of internet, communication has become convenient and efficient. Many technologies have been built to exploit the variety of communications. The Joint Battlespace Infosphere (JBI) of US military is one such technology. Technically JBI is a publish-subscribe (pub-sub) environment, a common paradigm for supporting