Analysis of a real-world HTTP segment streaming case

Today, adaptive HTTP segment streaming is a popular way to deliver video content to users. The benefits of HTTP segment streaming include its scalability, high performance and easy deployment, especially the possibility to reuse the already deployed HTTP infrastructure. However, current research focuses merely on client side statistics like for example achieved video qualities and adaption algorithms. To quantify the properties of such streaming systems from a service provider point of view, we have analyzed both sender and receiver side logging data provided by a popular Norwegian streaming provider. For example, we observe that more than 90% of live streaming clients send their requests for the same video segment with an inter-arrival time of only 10 seconds. Moreover, the logs indicate that the server sends substantially less data than is actually reported to be received by the clients, and the origin server streams data to less clients than there really are. Based on these facts, we conclude that HTTP segment streaming really makes use of the HTTP cache infrastructure without the need to change anything in the parts of Internet that are not controlled by the streaming provider.