Although IP Multicast is an effective network primitive for best-effort, large-scale, multi-point communication, many multicast applications such as shared whiteboards, multi-player games and software distribution require reliable data delivery. Building services like reliable sequenced delivery on top of IP Multicast has proven to be a hard problem. The enormous extent of network and end-system heterogeneity in multipoint communication exacerbates the design of scalable end-to-end reliable multicast protocols. In this paper, we propose a radical departure from the traditional end-to-end model for reliable multicast and instead propose a hybrid approach that leverages the successes of unicast reliability protocols such as TCP while retaining the efficiency of IP multicast for multi-point data delivery. Our approach splits a large heterogeneous reliable multicast session into a number of multicast data groups of co-located homogeneous participants. A collection of application-aware agents--Reliable Multicast proxies (RMXs)--organizes these data groups into a spanning tree using an overlay network of TCP connections. Sources transmit data to their local group, and the RNLX in that group forwards the data towards the rest of the data groups. RMXs use detailed knowledge of application semantics to adapt to the effects of heterogeneity in the environment. To demonstrate the efficacy of our architecture, we have built a prototype implementation that can be customized for different kinds of applications.

Abstract not found

This document describes a framework for the standardization of bulkdata reliable multicast transport. It builds upon the experience gained during the deployment of several classes of contemporary reliable multicast transport, and attempts to pull out the commonalities between these classes of protocols into a number of building blocks. To that end, this document recommends that certain components that are common to multiple protocol classes be standardized as "building blocks". The remaining parts of the protocols, consisting of highly protocol specific, tightly intertwined functions, shall be designated as "protocol cores". Thus, each protocol...

Frequently updated web objects reduce the benefit of caching, increase the problem of cache inconsistency, and aggravate the inefficiency of the conventional "repeated unicast " delivery model. In this paper, we investigate multicast invalidation and delivery of popular, frequently updated objects to web cache proxies. Our protocol, MMO, groups objects into volumes, each of which maps to one IP multicast group. We show that, by forming volumes of the appropriate size and/or object correlation, the benefit from reliable multicast outweighs the cost of delivering extraneous data as well as the overhead of multicast reliability. Moreover, tracedriven simulations show that the bandwidth saving over conventional approaches increases significantly as the audience size grows. We conclude that MMO provides efficient bandwidth utilization and service scalability, and makes strong web cache consistency for dynamic objects practical.

The design space for reliable multicast is rich, with many possible solutions having been devised. However, application requirements serve to constrain this design space to a relatively small solution space. This document provides an overview of the design space and the ways in which application constraints affect possible solutions.

Forward Error Correction (FEC) has been proposed as a technique for implementing efficient reliable multicast (RM). However, FEC incurs costs in encode/decode delay and implementation complexity. How much benefit is provided relative to these costs and how dependent is the benefit on the specific RM protocol? In this paper, we evaluate the benefits of FEC for RM, considering both proactive and reactive use with three RM recovery techniques: duplicate avoidance, limited scope multicast and subcast. Our simulationbased results indicate that FEC provides little benefit for an efficient RM protocol like OTERS and introduces extra delay for multi-point streaming data applications. 1

We examine the impact of the loss recovery mechanism on the performance of a reliable multicast protocol. Approaches for loss recovery in reliable multicast can be divided into two major classes: centralized (source-based) recovery and distributed recovery. For both classes we consider the state of the art: For centralized recovery, an integrated transport layer scheme using parity multicast for error recovery (hybrid ARQ type 2) as well as timer-based feedback suppression. For distributed recovery, a scheme with local data multicast retransmission and feedback processing in a local neighborhood. We also evaluate the benefits of combining the two approaches into distributed error recovery with local retransmissions using a type 2 hybrid ARQ scheme. The schemes are evaluated for up to 10 receivers under different loss scenarios with respect to network bandwidth usage and completion time of a reliable transfer. We show that using distributed error recovery with type 2 hybrid ARQ gives best performance in terms of bandwidth and latency. For networks, where local retransmission is not possible, we show that a centralized protocol based on type 2 hybrid ARQ comes close to the performance of a protocol with local retransmissions.

Developing scalable, reliable multicast protocols for lossy networks presents an array of challenges. In this work we focus on scheduling policies which determine what data the sender places into each sent packet. Our objective is to develop scalable policies which provably deliver a long intact prefix of the message to each receiver at each point in time during the transmission. To accurately represent conditions in existing networks, our theoretical model of the network allows bursty periods of packet loss which can vary widely and arbitrarily over time. Under this general model, we give a proof that there is an inherent performance gap between algorithms which use encoding schemes such as forward error correction (FEC) and those which do not. We then present simple, feedbackfree policies which employ FEC and have guaranteed worstcase performance. Our analytic results are complemented by trace-driven simulationswhich demonstrate the effectiveness of our approach in practice.

Data servers for multimedia applications like News-onDemand represent a severe bottleneck, because a potentially (very) high number of users concurrently retrieve data with high data rates. In the Intermediate Storage Node Concept (INSTANCE) project, we develop a new architecture for Media-on-Demand servers that maximizes the number of concurrent clients a single server can support. Traditional bottlenecks, like copy operations, multiple copies of the same data element in main memory, and checksum calculation in communication protocols are avoided by applying three orthogonal techniques: zero-copy-one-copy memory architecture, network level framing, and integrated error management. In this paper, we describe design, implementation, and evaluation of our integrated error management mechanism. Our results show that the reuse of parity information from a RAID system as forward error correction information in the transport protocol reduces the server workload and enables smooth playout at the client.

This paper presents a simple, generic source-based end-to-end multicast congestion control (GSC) algorithm for reliable multicast transport (RMT) protocols. The algorithm is completely implemented at the source and leverages the reverse control information ow in RMT protocols like PGM or RMTP [13,44]. Speci cally, itdoes not introduce any new control tra c or new elds in RMT protocol headers. It addresses the drop-to-zero problem [43] by introducing a robust, adaptive timelter based upon RTT estimates collected by observing NAK tra c. This solution allows it to scale for large multicast groups while being very adaptive to congestion situation changes in any part of the tree. The algorithm is friendly to TCP in terms of competition for bandwidth shares. The scheme has minimal control tra c requirements and weak RTT estimation requirements which allows a large deployment space including multi-sender multicast and combination with receiver-based schemes. Key words: reliable multicast, congestion control, transport protocol 1