Fault Tolerance in Application-Level Multicast Networks

Overlay multicast (Application-Level Multicast (ALM)) constructs a multicast delivery tree among end hosts. Unlike traditional IP multicast where the internal tree nodes are dedicated routers which are relatively stable and do not leave the multicast tree voluntarily, the non-leaf nodes in the overlay tree are free end hosts which can join/leave the overlay at will, or even crash without notification. So, the leaving node can leave suddenly and cannot give its descendants (and the Rendez-vous Point (RP)) the time to prepare the recovering (the reconnection) of the overlay tree, and so there is a need to trigger a rearrangement process in which each one of its descendants should rejoin the overlay tree. In this case, all of its downstream nodes are partitioned from the overlay tree and cannot get the multicast data any more. These dynamic characteristics cause the instability of the overlay tree, which can significantly impact the user. A key challenge in constructing an efficient and resilient ALM protocol is to provide fast data recovery when overlay node failures partition the data delivery paths. In this paper, we analyze the performance of the ALM tree recovery solutions using different metrics.

Cheating Impact on Overlay Tree Construction Algorithms in Application-Level Multicast Networks

Application-Level Multicast (ALM) has been proposed as an alternative solution to overcome the lack of deployment of the IP Multicast group communication model. It builds an overlay tree consisting of end-to-end unicast connections between end-hosts based on the collaboration of group members with each other. The efficiency of the constructed overlay tree depends entirely on the honesty and on the cooperation of all participating members. However such behaviour can not be guaranteed and some selfish and non-cooperative nodes may take profit from the honesty of other members in the overlay. Recently, many researchers have been investigating the impact of selfishness of nodes in the overlay multicast. Our contribution in this paper is to describe in detail the basic algorithms used to construct the overlay tree, and evaluate the impact of cheating nodes on the stability and on the performance of constructed overlay tree using these algorithms.

A New Fault Tolerance Protocol in Application-Level Multicast Networks

Application-Level Multicast Networks are easy to deployment, it does not require any change in the network layer, where data is sent to the network via the built-up coverage of the tree using a single-contact transmission of the final contract, who are the hosts are free can join / leave whenever they want it, or even to leave without telling any node so. Causing the separation of the children of the leaved node from the tree, and the request for rejoin, in other words, these nodes will be separated from the overlay tree and cannot get the data even rejoin. This causes the distortion of the constructed tree, and the loss of several packets which can significantly impact the user. One of the key challenges in building a multi-efficiently and effectively overlay multicast protocol is to provide a robust mechanism to overcome the sudden departure of a node from the overlay tree without a significant impact on the performance of the constructed tree. In this research, we propose a new protocol to solve problems presented previously.