Exploring the Design Space of Cooperative Streaming Multicast.

Video streaming over the Internet is rapidly rising in popularity, but the availability and quality of video content is currently limited by the high bandwidth costs and infrastructure needs of server-based solutions. Recently, however, cooperative end-system multicast (CEM) has emerged as a promising paradigm for content distribution in the Internet, because the bandwidth overhead of disseminating content is shared among the participants of the CEM overlay network. In this thesis, we identify the dimensions in the design space of CEMs, explore the design space, and seek to understand the inherent tradeoffs of different design choices. In the first part of the thesis, we study the control mechanisms for CEM overlay maintenance. We demonstrate that the control task of neighbor acquisition in CEMs can be factored out into a separate control overlay that provides a single primitive: a configurable anycast for peer selection. The separation of control from data overlay avoids the efficiency tradeoffs that afflict some of the current systems. The anycast primitive can be used to build and maintain different data overlay organizations like single-tree, multi-tree, mesh-based, and hybrids, by expressing appropriate policies. We built SAAR, a reusable, shared control overlay for CEMs, that efficiently implements this anycast primitive, and thereby, efficiently serves the control needs for CEMs. In the second part of the thesis, we focus on techniques for data dissemination. We built a common framework in which different CEM data delivery techniques can be faithfully compared. A systematic empirical comparison of CEM design choices demonstrates that there is no single approach that is best in all scenarios. In fact, our results suggest that every CEM protocol is inherently limited in certain aspects of its performance. We distill our observations into a novel model that explains the inherent tradeoffs of CEM design choices and provides bounds on the practical performance limits of any future CEM protocol. In particular, the model asserts that no CEM design can simultaneously achieve all three of low overhead, low lag, and high streaming quality.