Aug 31, 2006: Sustainable Scalability in Large-Scale Distributed Systems
Filed in: Colloquium
Dr. Fabian Bustamante, Northwestern University
An interesting model for building large-scale distributed systems is a cooperative one in which nodes are expected to contribute resources in exchange for using the supported services. We are experimenting with this approach in a number of domains and applications, including data-sharing services, overlay-based multicast systems and, most recently, vehicular ad-hoc networks.
While promising due to its potential for natural scalability and resilience, the cooperative approach is no silver bullet. There are a number of systems issues that need to be addressed in this context: from the effects of high population transiency, given the strong interdependencies among participant nodes; to resource management in very heterogeneous and highly dynamic environments, to monitoring, testing and debugging in this chaotic setting.
In this talk I will describe some of my group's efforts to ensure sustainable scalability in globally-distributed systems. I will then discuss the problem of sustainable scalability across systems and applications and introduce our newest project in which we are exploring techniques for inferring and exploiting network measurements performed by commercial content distribution networks (CDNs), such as Akamai, with the goal of locating and utilizing quality Internet paths without performing extensive path probing or monitoring.
Fabian Bustamante is currently an assistant professor in the Electrical Engineering and Computer Science Department at Northwestern University. Dr. Bustamante joined Northwestern in 2002, after receiving his Ph.D. from the College of Computing, Georgia Institute of Technology. He is the head of the AquaLab group at Northwestern, which researches systems issues in large-scale distributed computing over wired and ad-hoc networks. His research has been funded by various sources, including Sun Microsystems, Ford, Microsoft, the Murphy foundation and NSF. He frequently serves on government panels and has been part of the program committees of leading conferences including ICDCS, ICAC, WWW and IEEE P2P. He is also the founder and co-chair for the new Workshop on Hot-Topics in Autonomic Computing Systems. For a list of publications and more detailed information, please visit: http://www.aqualab.cs.northwestern.edu.
Abstract
An interesting model for building large-scale distributed systems is a cooperative one in which nodes are expected to contribute resources in exchange for using the supported services. We are experimenting with this approach in a number of domains and applications, including data-sharing services, overlay-based multicast systems and, most recently, vehicular ad-hoc networks.
While promising due to its potential for natural scalability and resilience, the cooperative approach is no silver bullet. There are a number of systems issues that need to be addressed in this context: from the effects of high population transiency, given the strong interdependencies among participant nodes; to resource management in very heterogeneous and highly dynamic environments, to monitoring, testing and debugging in this chaotic setting.
In this talk I will describe some of my group's efforts to ensure sustainable scalability in globally-distributed systems. I will then discuss the problem of sustainable scalability across systems and applications and introduce our newest project in which we are exploring techniques for inferring and exploiting network measurements performed by commercial content distribution networks (CDNs), such as Akamai, with the goal of locating and utilizing quality Internet paths without performing extensive path probing or monitoring.
Bio sketch:
Fabian Bustamante is currently an assistant professor in the Electrical Engineering and Computer Science Department at Northwestern University. Dr. Bustamante joined Northwestern in 2002, after receiving his Ph.D. from the College of Computing, Georgia Institute of Technology. He is the head of the AquaLab group at Northwestern, which researches systems issues in large-scale distributed computing over wired and ad-hoc networks. His research has been funded by various sources, including Sun Microsystems, Ford, Microsoft, the Murphy foundation and NSF. He frequently serves on government panels and has been part of the program committees of leading conferences including ICDCS, ICAC, WWW and IEEE P2P. He is also the founder and co-chair for the new Workshop on Hot-Topics in Autonomic Computing Systems. For a list of publications and more detailed information, please visit: http://www.aqualab.cs.northwestern.edu.