ABSTRACT:

A range of business peer-to-peer (P2P) systems for live streaming are introduced in recent years. The behavior of those well-liked systems has been extensively studied in several measurement papers. Due to the proprietary nature of those business systems, however, these studies must depend on a “black-box” approach, where packet traces are collected from a single or a restricted number of measurement points, to infer varied properties of traffic on the management and data planes. Although such studies are helpful to match different systems from the tip-user's perspective, it's difficult to intuitively perceive the observed properties without fully reverse-engineering the underlying systems. In this paper, we tend to describe the network design of Zattoo, one of the largest production live streaming suppliers in Europe at the time of writing, and present a massive-scale measurement study of Zattoo using information collected by the provider. To highlight, we found that even when the Zattoo system was heavily loaded with as high as twenty 000 concurrent users on a single overlay, the median channel be part of delay remained but two-5 s, which, for a majority of users, the streamed signal lags over-the-air broadcast signal by only three s.