Application performance optimization using application-aware networking

Abstract

The traditional IP network has its inherent limitations that could cause application runs in a non-optimized manner. The common methods to improve applications' performance requires a great effort from both network administrators and application designers. In this work, we propose a Software- Defined Network (SDN) approach in an Application-Aware Network (AAN) platform. We first present an architecture for our approach and then show how this architecture can be applied to two real-world applications: Hadoop MapReduce (M/R) framework and MPEG-DASH. Our approach provides both underlying network functions and application-level forwarding logic for MapReduce and video streaming. Based on our experiments, we observed that our AAN platform for Hadoop MapReduce job optimization offers a significant improvement compared to a static, traditional IP network environment by reducing job run time by 16% to 300% for various MapReduce benchmark jobs. As for MPEG-DASH based video streaming, we can increase user perceived video bitrate by 100%.