The use of video streaming has been growing rapidly in the recent years and has beenutilized in various applications. Many of these applications are latency sensitive, butthe latency requirements varies largely from one application to another. The highquality videos captured by cameras are quite large in size, so they are encoded toreduce the video size to achieve a reasonable bandwidth when sent over a network.In this work, we characterize the latency components of edge video streaming withthe goal of identifying latency bottlenecks. In edge applications, the processing is performedat the edge of the network close to data generation, rather than in the cloud,to meet the latency requirements. This work specifically investigates the latenciesin the transmit and receive paths in the Linux networking stack, and the impact ofencoding parameters on the latency.
