The continuous growth in applications that require communications among a group of hosts or simultaneous dissemination of data to multiple sites on the Internet has led to considerable interest in multicast communication. These applications have different quality of service requirements such as deadlines to response time and tolerance to data loss. Internet multicast protocols provide a spectrum of services to cater for the needs of a wide array of multicast applications. The design alternatives of a multicast protocol for a particular application may lead to different performance characteristics, for example higher utilization of network bandwidth vs lower protocol processing requirements. Therefore a framework is required to various design choices available to design multicast protocols and evaluate the performance tradeoffs associated with these alternatives. Motivated by such a need and by the evolution of multicast applications over the Internet, this article presents a taxonomy of multicast protocols and a common framework to evaluate their performance.

This paper presents an analytic model of a reliable multicast session protocol for collaborative continuous-feed applications. The protocol supports N/spl times/N group multicast communications at the session layer and runs on the top of existing reliable transport protocols (e.g., TCP). The protocol is portable as a network-layer-independent library that is suitable for both LAN and WAN environments. It multiplexes messages from different group members into transport packets to reduce the transport overhead per message. It requires only two transport-level connections per node, irrespective of the multicast group size, to reduce the overhead of acknowledgements and retransmissions per node. We compare the throughput of this protocol with the throughput of general sender-initiated and receiver-initiated reliable multicast transport protocols.

Real-time transport protocols rely on IP to disseminate audio/video packets from a sender to one or more receivers. In IP over ATM broadband networks, studies have shown that the e(cid:11)ective bandwidth is reduced by at least 10% and that larger protocol payload sizes yield higher throughput. However, a dropped cell corrupts the IP packet it belongs to and reduces the rate successfully-received data, or goodput. This results in quality of service degradation to multimedia tra(cid:14)c, particularly for intra-frame encoded video ra(cid:14)c that is sensitive to a packet loss. A key observation for multimedia applications is that achieving maximum throughput versus reaching optimum goodput is determined by the end-to-end quality of service requirements. In this report, we derive analytic expressions for the maximum throughput and packet-loss probability which provides us with a better understanding of the goodput of real-time transport protocols. We also derive an analytic expression for optimum PDU that maximizes the goodput with respect to cell-loss probability and number of ATM switches. We show that optimum PDUs yield higher goodput than the default MTU for IP over ATM, particularly as the cell-loss probability and/or the number of ATM switches increase. For reliable multicast, We also derive analytic expressions to the expected total number of transmissions per packet and to the goodput of reliable multicast.

Article Free Access Share on A reliable multicast session protocol for collaborative continuous-feed applications Authors: Walid Mostafa The Ohio State University, Department of Computer & Information Science, Columbus, OH The Ohio State University, Department of Computer & Information Science, Columbus, OHView Profile , Mukesh Singhal The Ohio State University, Department of Computer & Information Science, Columbus, OH The Ohio State University, Department of Computer & Information Science, Columbus, OHView Profile Authors Info & Claims SAC '97: Proceedings of the 1997 ACM symposium on Applied computingApril 1997 Pages 35–39https://doi.org/10.1145/331697.331706Online:01 April 1997Publication History 0citation234DownloadsMetricsTotal Citations0Total Downloads234Last 12 Months1Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

Reliable multicast transport protocols support dissemination communication and their through-puts are either limited by the sender or by intermediate nodes that consolidate acknowledgements and retransmissions. RMSP is a portable reliable multicast protocol that supports collaborative communication at the session-layer level and provides higher throughput by maintaining two transport connections per node irrespective of the number of nodes. However, the throughput only of RMSP may degrade if one or more nodes or the centralized connection manager that monitors them fails. In this report, we propose a fully distributed fault-tolerant protocol, DFT-RMSP, that detects and isolates faulty nodes and reinstates the multicast collaborative communications. We derive analytic expressions for throughput degradation and analyze its sensitivity to node-failure rates, network delay, and multicast group size. We show that DFT-RMSP provides less down-time and achieves graceful throughput degradation under high failure rates compared with RMSP. simultaneous node failures.