Characterizing the Cloud's Outbound Network Latency: An Experimental and Modeling Study

Abstract

Cloud latency has critical influences on the success of cloud applications. Therefore, characterizing cloud network performance is crucial for analyzing and satisfying different latency requirements. By focusing on the cloud's outbound network latency, this case study on Google App Engine confirms the necessity of optimizing application deployment. More importantly, our modeling effort has established a divide-and-conquer framework to address the complexity in understanding and investigating the cloud latency.