The Case for End System Multicast

Authors:

• Yang-hua Chu
• Sanjay G. Rao
• Srinivasan Seshan
• Hui Zhang

Complete Citation

Yang-hua Chu, Sanjay G. Rao, Srinivasan Seshan, and Hui Zhang, IEEE Journal on Selected Areas in Communication (JSAC), Special Issue on Networking Support for Multicast, Vol. 20, No. 8, 2002.

Download the PDF

Abstract

The conventional wisdom has been that IP is the natural protocol layer for implementing multicast related functionality. However, more than a decade after its initial proposal, IP Multicast is still plagued with concerns pertaining to scalability, network management, deployment and support for higher layer functionality such as error, flow and congestion control. In this paper, we explore an alternative architecture that we term End System Multicast, where end systems implement all multicast related functionality including membership management and packet replication. This shifting of multicast support from routers to end systems has the potential to address most problems associated with IP Multicast. However, the key concern is the performance penalty associated with such a model. In particular, End System Multicast introduces duplicate packets on physical links and incurs larger end-to-end delays than IP Multicast. In this paper, we study these performance concerns in the context of the Narada protocol. In Narada, end systems selforganize into an overlay structure using a fully distributed protocol. Further, end systems attempt to optimize the efficiency of the overlay by adapting to network dynamics and by considering application level performance. We present details of Narada and evaluate it using both simulation and Internet experiments. Our results indicate that the performance penalties are low both from the application and the network perspectives. We believe the potential benefits of transferring multicast functionality from end systems to routers significantly outweigh the performance penalty incurred..

Annotations

This paper discusses a system of multicasting based on the end systems, or clients,of the stream, instead of the traditional router-based multicast. They point out that traditional router-based multicasting is stateful, and scales poorly, and has been slow in being deployed. They argue that multicast can be effectually implemented by the end hosts, and provide Narada, a protocol for doing so.

Narada builds a mesh of all known participants in a multicast session and then creates a tree overlay on this mesh. Members may join by contacting at least one active member of the group, presumably via out-of-band information sharing. As all nodes regularly update eachother on status, a joined member is quickly assimilated into the mesh and tree structure. Member leaving, either with foreknowledge and without warning, is handled similarly as refresh messages between nodes propagate information on the disruption.

ESM differs essentially from our work in TailSync? , in that it provides access to an ongoing session: all participants see the same thing at roughly the same time. However their approach to overlay mesh creation and tree forming share similarities to the application layer multicasting we will be implementing for TailSync? .

It should also be noted that ESM is a fully deployed and accessible technology: their website provides a client to download and advertises the ability to run or share in multicast streams immediately.

-- DavidMoore - 10 Oct 2007