As networked systems grow and traffic patterns evolve, management applications are increasing in complexity and functionality. To address these demands, equipment vendors and administrators today depend on incremental solutions that increase the complexity of network elements and deployment costs for operators. Despite this increased complexity and cost, there is still a fundamental disconnect between the policy objectives of system administrators and today’s mechanisms.
I argue that much of this disconnect arises from the narrow device-centric view of current solutions. Such piecemeal solutions are inefficient: network elements duplicate tasks and some locations become overloaded. Worse still, administrators struggle to retrofit their high-level goals within device-centric configurations. I describe a clean-slate system-wide approach for resource management in large-scale networked systems based on three high-level principles: (1) systematic selection and placement of device-level primitives, (2) lightweight coordination mechanisms that enable different network elements to operate in synchrony, and (3) practical optimization models that capture operating constraints and policy objectives. In this talk, I will highlight the benefits of such a system-wide approach in the context of meeting fine-grained coverage requirements in traffic monitoring and implementing a redundancy elimination service to improve network performance. Further, these principles can be more broadly applied in other contexts such as intrusion detection and prevention, managing cloud services, and multi-hop wireless and sensor networks.
Vyas Sekar is a final year PhD student in the Computer Science Department at Carnegie Mellon University, co-advised by Michael Reiter and Hui Zhang. His research interests are in systems, networking, and security. Before CMU, he earned his bachelor’s degree from the Indian Institute of Technology Madras, where he was awarded the President of India Gold Medal.