Progressive Network Deployment, Performance, and Control with Software-Defined Networking
Abstract
The in exible nature of traditional computer networks has led to tightly-integrated systems that are inherently difficult to manage and secure. New designs move low-level network control into software creating software-defined networks (SDN). Augmenting an existing network with these enhancements can be expensive and complex. This research investigates solutions to these problems. It is hypothesized that an add-on device, or \shim" could be used to make a traditional switch behave as an Open Flow SDN switch while maintaining reasonable performance. A design prototype is found to cause approximately 1.5 reduction in throughput for one flow and less than double increase in latency, showing that such a solution may be feasible. It is hypothesized that a new design built on event-loop and reactive programming may yield a controller that is higher-performing and easier to program. The library node-open flow is found to have performance approaching that of professional controllers, however it exhibits higher variability in response rate. The framework rxdn is found to exceed performance of two comparable controllers by at least 33 with statistical significance in latency mode with 16 simulated switches, but is slower than the library node-open flow or professional controllers (e.g., Lib uid, ONOS, and NOX). Collectively, this work enhances the tools available to researchers, enabling experimentation and development toward more sustainable and secure infrastructure.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 23, 2018
- Accession Number
- AD1055983
Entities
People
- Daniel J Casey
Organizations
- Air Force Institute of Technology