Center placement algorithms for large multicast groups
نویسندگان
چکیده
An increasing number of distributed applications require a speci c form of multicast called dissemination, in which a single source reliably transfers data to multiple receivers. Reliability requires that data packets are acknowledged positively or negatively, which leads for large groups of receivers (100s or 1000s of participants) to the problem of feedback implosion. Among the approaches trying to avoid feedback implosion, the cluster approach is the most promising. It partitions the multicast delivery tree into clusters. Each cluster has a representative called center, which is used for acknowledgment accumulation and local retransmission. Up to now, clustering/center placement has been done administratively or based on network addresses. Needed are center placement algorithms, allowing the introduction of placement criteria based on the network topology and on delay. In this work, three center placement algorithms designed for static multicast groups are presented and simulation results are shown in order to asses their performance.
منابع مشابه
Algorithms and Trade-Offs in Multicast Service Overlay Design
Multicast Service Overlay Network (MSON) has been recently introduced to address some of the deployment and maintenance problems of IP multicast and application-level multicast. An MSON is essentially a backbone service overlay provisioned by an MSON provider and designed to “multiplex” multiple user overlays. It consists of service nodes or proxies deployed by the provider. The proxies are str...
متن کاملGenuine versus Non-Genuine Atomic Multicast Protocols
In this paper, we study atomic multicast, a fundamental abstraction for building fault-tolerant systems. We suppose a system composed of data centers, or groups, that host many processes connected through high-end local links; a few groups exist, interconnected through high-latency communication links. In this context, a recent paper has shown that no multicast protocol can deliver messages add...
متن کاملComputer Science at Kent Applying clustering algorithms to multicast group hierarchies
Multicasting offers group communication a considerable efficiency gain, particularly for large groups. As the size of the group increases, management and protocols become more complex and severe scaling problems can arise, for example in the routers at the network layer, for reliable file distribution at the transport layer and for large scale Peer-to-Peer file sharing or processing sharing sys...
متن کاملSubgroup-based Source Recovery or Local Recovery for Reliable Multicasting
A traditional approach to design scalable reliable multicast algorithms is using proxies to recover lost packets. The proxies store the packets from the source and retransmit them to the requesting end receivers. Proxy placement in a multicast tree is a well-researched problem. However, given that the proxies require significant storage and processing resources, it is not possible to place them...
متن کاملOn the scaling of feedback algorithms for very large multicast groups
Feedback from multicast group members is vital for many multicast protocols. In order to avoid feedback implosion in very large groups feedback algorithms with well behaved scaling-properties must be chosen. In this paper we analyse the performance of three typical feedback algorithms described in the literature. Apart from the basic trade-off between feedback latency and response duplicates we...
متن کامل