Position:  PhD Student

Current Institution:  Princeton University

Abstract:  Programmable Network Monitoring and Control

Computer networks are crucial to online services. They transfer data between end users and data centers and between servers in data centers to process user requests. To ensure that these networks are efficient, secure, and highly available, it is essential to continuously (i) monitor them for congestion anomalies and failures and (ii) take control actions accordingly on network devices, i.e., network interface cards (NICs), at the end hosts and switches in the network. To that end, programmable network devices have emerged to provide operators with fine-grained control over how to process packets, what information to maintain across packets, and what control actions to take based on it. The programming interfaces of these devices, however, are quite low-level and only suitable for programming a single device, making them cumbersome to use in today’s large-scale and complex networks. Therefore, my research focuses on designing programming platforms that facilitate the use of programmable network devices for large-scale and real-time network monitoring and control both at the end hosts and inside the network. More specifically, I have designed (i) domain-specific languages that are expressive enough for high-level specification of a broad set of network monitoring and control tasks while being amenable to efficient implementation and (ii) compilers that use efficient intermediate data structures to automatically distribute and implement these specifications on programmable devices. So far, I have focused on programming platforms for end-to-end network transport network-wide stateful monitoring and control and path-based network monitoring. Moving forward, I plan to explore the design of a holistic monitoring and control platform using the rich but local and per-flow control actions on the NICs and the aggregate monitoring information observed by the switches to realize even more sophisticated network-wide policies.

Bio:
Mina Tahmaski is a fifth-year PhD student in the Computer Science Department at Princeton, working with Professor Jennifer Rexford. She is primarily interested in networked systems with a focus on software defined networking (SDN) and programmable data planes. Previously, she received a bachelor’s degree in computer engineering from Sharif University of Technology in Iran.