Hash tables – which map “keys ” onto “values” – are an essential building block in modern software systems. We believe a similar functionality would be equally valuable to large distributed systems. In this paper, we introduce the concept of a Content-Addressable Network (CAN) as a distributed infrastructure that provides hash table-like functionality on Internet-like scales. The CAN is scalable, fault-tolerant and completely self-organizing, and we demonstrate its scalability, robustness and low-latency properties through simulation.

Most currently proposed solutions to application-level multicast organize the group members into an application-level mesh over which a DistanceVector routing protocol, or a similar algorithm, is used to construct source-rooted distribution trees. The use of a global routing protocol limits the scalability of these systems. Other proposed solutions that scale to larger numbers of receivers do so by restricting the multicast service model to be single-sourced. In this paper, we propose an application-level multicast scheme capable of scaling to large group sizes without restricting the service model to a single source. Our scheme builds on recent work on Content-Addressable Networks (CANs). Extending the CAN framework to support multicast comes at trivial additional cost and, because of the structured nature of CAN topologies, obviates the need for a multicast routing algorithm. Given the deployment of a distributed infrastructure such as a CAN, we believe our CAN-based multicast scheme offers the dual advantages of simplicity and scalability.

The recent success of multicast applications such as Internet teleconferencing illustrates the tremendous potential of applications built upon wide-area multicast communication services. A critical issue for such multicast applications and the higher layer protocols required to support them is the manner in which packet losses occur within the multicast network. In this paper we present and analyze packet loss data collected on multicast-capable hosts at 17 geographically distinct locations in Europe and the US and connected via the MBone. We experimentally and quantitatively examine the spatial and temporal correlation in packet loss among participants in a multicast session. Our results show that there is some spatial correlation in loss among the multicast sites. However, the shared loss in the backbone of the MBone is, for the most part, low. We find a fairly significant amount of of burst loss (consecutive losses) at most sites. In every dataset, at least one receiver experienced ...

The Application Level Framing (ALF) protocol architecture [2] encourages application control over mechanisms that traditionally fall within the "transport layer", e.g., loss detection and recovery. Traditional ARQ-based reliable protocols for unicast (e.g., TCP) as well as multicast (e.g., Horus [30], RMTP [15], etc.) number data units sequentially to detect losses. Unfortunately, these transport-level sequence numbers do not permit receivers to flexibly tailor their reliability semantics. Achieving receiver-driven reliability is cumbersome in the existing "layered" architecture of the network protocol stack where the receiving application has no knowledge of how application-level objects map onto transport level sequence numbers. In this paper, we propose a new data naming scheme that exposes the structure of application data to the transport layer, thereby enhancing the expressibility of an applications' reliability and ordering semantics. We apply this data naming scheme to a reliab...

By trading off temporal and spatial quality with available bandwidth, or manipulating the playout time of continuous media in response to variation in delay, audio and video flows can be made to adapt to fluctuating network conditions with minimal perceptual distortion. In this article the authors describe the implementation of an adaptive transport system that incorporates a QoS-oriented API and a range of QoS mechanisms that best assist multimedia applications in adapting to fluctuations in the delivered network QoS. The system, which is an instantiation of the transport and network layers of a QoS architecture, is implemented in a multi-ATM switch network environment with Linux-based PC end systems and continuous media file servers. A performance evaluation of the system configured to support a video-ondemand application scenario is presented and discussed. A novel aspect of the system is the implementation of a "QoS adaptation" algorithm which allows applications to del...

Distributed audio and video applications need to adapt to fluctuations in delivered quality of service (QoS). By trading off temporal and spatial quality to available bandwidth, or manipulating the playout time of continuous media in response to variation in delay, audio and video flows can be made to adapt to fluctuating QoS with minimal perceptual distortion. In this paper we extend our previous work on a Quality of Service Architecture (QoS-A) by populating the QoS management planes of our architecture with a framework for the control and management of multi-layer coded flows operating in heterogeneous multimedia networking environments. Two key techniques are proposed: i) an end-to-end rate shaping scheme which adapts the rate of MPEG-coded flows to the available network resources while minimising the distortion observed at the receiver; and ii) an Adaptive Network Service, which offers "hard" guarantees to the base layer of multi-layer coded flows, and "fairness" guarantees to the...

A Framework for Interactive Multicast Data Transport in the Internet by Suchitra Raman Doctor of Philosophy in Computer Science University of California at Berkeley Professor Steven R. McCanne, Chair The remarkable growth of the Internet as the a data transmission medium has in part been enabled by the simplicity and scalability of the core Internet Protocol (IP), which is used for addressing and routing unicast data packets through the network. The IP service model does not provide any packet delivery guarantees, but rather provides a "best-effort" contract, and leaves it to higher layers to provide enhanced services using this basic service. Today, the de facto transport protocol on the Internet is the Transmission Control Protocol (TCP) [109, 128]. TCP was designed primarily for applications such as telnet, a remote terminal application, and ftp, a file transfer application, which require data to be delivered reliably and in an ordered manner. While the TCP abstraction and pro...

An enduring trait of the Internet is its heterogeneity. Evidence of this heterogeneity includes the wide range of network transmission rates, varying across many orders of magnitude, and the vast differences in computing power, ranging from PDA's to supercomputers. These heterogeneities present significant barriers to the transmission of real-time multimedia data across groups. The barriers stem from the fact that in order to accommodate the entire gamut of group member characteristics, e.g., bandwidth availability or computing power, a source is required to transmit its data with properties matching the most constrained receiver. Instead, we would like to transmit media to multiple receivers at heterogeneous rates and properties tha...