Coolstreaming represented one of the earliest largescale live streaming trials in the Internet. In this paper, we discuss the fundamental components of the system. By leveraging the recent results obtained from live event broadcast, we develop some basis to demonstrate that a random partnership selection has the potentially to scale. Specific- cally, first, we examine the overlay topology. Second, using a combination of real traces and analysis, we present the highly skewed distribution of peer contribution; a small fraction of peers contribute most of the upload capacity. Third, we discuss the main limitations and the implications on the scalability.