Browsing by Author "Nandi, Animesh"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Exploring the design space of cooperative streaming multicast
    (2009) Nandi, Animesh; Druschel, Peter
    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.
  • Thumbnail Image
    Item
    LALA: Location aware load aware overlay anycast
    (2004) Nandi, Animesh; Druschel, Peter
    Anycast is a powerful paradigm for managing and locating resources in decentralized distributed systems. Ideally, an anycast system must be scalable, location-aware and load-aware. Location-awareness means that the anycast system should be able to locate a resource that is near the client in the network. Load-awareness means that it must be able to disperse load to avoid overloading group members in the case of high demand in a certain region of the network. Existing anycast systems are either location-aware or load-aware, but not both. We motivate LALA, a generic architecture for doing scalable, location-aware, load-aware anycast that realizes the following anycast functionality: Given a client request, our goal is to select the closest anycast server that has enough resources to satisfy the client's request. We show how LALA can be designed on some of the existing overlay anycast architectures and close with an evaluation that demonstrates its effectiveness.
  • Thumbnail Image
    Item
    Measurement-Based Analysis, Modeling, and Synthesis of the Internet Delay Space for Large Scale Simulation
    (2006-10-04) Zhang, Bo; Ng, T. S. Eugene; Nandi, Animesh; Riedi, Rudolf H.; Druschel, Peter; Wang, Guohui
    The characteristics of packet delays among edge networks in the Internet can have a significant impact on the performance and scalability of global-scale distributed systems. Designers rely on simulation to study design alternatives for such systems at scale, which requires an appropriate model of the Internet delay space. The model must preserve the geometry and density distribution of the delay space, which are known, for instance, to influence the effectiveness of selforganization algorithms used in overlay networks. In this paper, we characterize measured delays between Internet edge networks with respect to a set of relevant metrics. We show that existing Internet models differ dramatically from measured delays relative to these metrics. Then, based on measured data, we derive a model of the Internet delay space. The model preserves the relevant metrics, allows for a compact representation, and can be used to synthesize delay data for large-scale simulations. Moreover, specific metrics of the delay space can be adjusted in a principled manner, thus allowing systems designers to study the robustness of their designs to such variations.