To efficiently support large-scale multicast applications with many thousand simultaneous members, it is essential that protocol mechanisms be available which support efficient exchange of control information between the members of a multicast group. Recently, we proposed the use of a control topology, which organizes multicast group members in a logical n-dimensional hypercube, and transmits all control information along the edges of the hypercube. In this paper, we present the design, verification, and implementation of a protocol, called HyperCast, which maintains members of a large multicast group in a logical hypercube. We use measurement experiments of an implementation of the protocol on a networked computer cluster to quantitatively assess the performance of the protocol for multicast group sizes up to 1024 members. * This work is supported in part by the National Science Foundation under grants ANI-9870336 and NCR9624106 (CAREER). # Corresponding Author: J. Lieb...

There exist several applications of sensor networks where reliability of data delivery can be critical. While the redundancy inherent in a sensor network might increase the degree of reliability, it by no means can provide any guaranteed reliability semantics. In this paper, we consider the problem of reliable sink-to-sensors data delivery. We first identify several fundamental challenges that need to be addressed, and are unique to a wireless sensor network environment. We then propose a scalable framework for reliable downstream data delivery that is specifically designed to both address and leverage the characteristics of a wireless sensor network, while achieving the reliability in an efficient manner. Through ns2 based simulations, we evaluate the proposed framework.

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.

Large-scale applications are characterized by a large number of dynamic and often interactive group members. The nature of these applications is such that participants are not interested in all the content transmitted. We examine two currently available techniques to scope delivery of content to interested receivers in IP multicast: filtering (data is filtered by middleware before passed to the application) and addressing (data is routed only to those receivers that express their interest). We propose a framework that models large-scale application behavior. We use this framework to evaluate the performance of these applications (and related protocols) when the network is capable of filtering or addressing. Our results show that the current Internet architecture does not efficiently support large-scale applications because it can not efficiently manage multiple multicast groups. We show that addressing is preferred to filtering given that groups are easy to create and manage. We highli...

Unpredictable network latency is the most challenging problem in multiplayer game networking design.  Latencies can be reduced by using a peer-to-peer rather than a client-server architecture.  However, peer-to-peer architectures raise a whole new set of issues, the most immediate being game state synchronization. The drawbacks of the peer-to-peer architecture are addressed in our game system.  The game system includes 1) a new mirrored-server architecture, 2) a trailing state synchronization protocol and 3) a many-to-many reliable multicast protocol.  As a proof-of-concept, we converted Quake, a client-server game, to our mirrored-server architecture.

The IP service model retains its simplicity and robustness by deferring reliability and congestion control to higher layers through end-to-end transport protocols. While the IP unicast service has proven successful, extending end-to-end adaptation to multicast has been a difficult problem. Unlike the unicast case, multicast protocols must support large and heterogeneous receiver sets. While proposed approaches to multicast transports attempt to localize problems and/or organize receivers into a hierarchy through a divide-and-conquer approach, this approach succeeds only if the resulting hierarchy is congruent with the underlying routing tree topology. This implies the need for some level of topological information at the end systems which the IP multicast service deliberately hides. In this paper, we explore the problem of inferring the required topological information using only observations made at the end hosts. To this end, we present a Group Formation Protocol (GFP) whereby receivers dynamically organize themselves into a multi-level hierarchy of multicast groups that corresponds to the underlying routing tree. GFP can serve as a core component across a wide range of multicast applications and protocols such as local recovery for reliable multicast, self organized transcoding, self organizing web caches, the optimal and dynamic placement of proxies, repeaters, designated receivers, recorders and so forth. Our simulations indicate that GFP structures receivers in accordance with the underlying topology for a range of workloads and network topologies.

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

Of the many distributed applications designed for the Internet, the successful ones are those that have paid careful attention to scale and robustness. These applications share several design principles. In this paper, we illustrate the application of these principles to common network monitoring tasks. Specifically, we describe and evaluate 1) a robust distributed topology discovery mechanism and 2) a mechanism for scalable fault isolation in multicast distribution trees. Our mechanisms reveal a different design methodology for network monitoring one that carefully trades off monitoring fidelity (where necessary) for more graceful degradation in the presence of different kinds of network dynamics.

Abstract—One approach to achieving scalability in reliable multicast is to use a hierarchy. A hierarchy can be established at the application level, or by using router-assist. With router-assist we have more fine-grain control over the placement of error-recovery functionality, therefore, a hierarchy produced by assistance from the routers is expected to have better performance. In this paper, we test this hypothesis by comparing two schemes, one that uses an application-level hierarchy (ALH) and another that uses router-assisted hierarchy (RAH). Contrary to our expectations, we find that the qualitative performance of ALH is comparable to RAH. We do not model the overhead of creating the hierarchy nor the cost of adding router-assist to the network. Therefore, our conclusions inform rather than close the debate of which approach is better. Index Terms—Reliable multicast, router-assist for reliable multicast. I.

Abstract—Scalable reliable multicast protocols have been a focus of recent research, tackling the problem of efficient reliable data delivery to an arbitrarily large number of receivers. Yet, the common applications of multicast, such as multi-point file delivery, or video streaming from a media server, typically only involve a moderate number of receivers, such as a thousand or fewer. Moreover, because of the limited deployment of these specialized multicast protocols, it is common for applications to instead use multiple TCP connections, one for each receiver, to implement multi-point delivery when feasible, causing a significant demand on the transmission server and the downstream links. In this paper, we describe a multicast extension to TCP, called the Single-source Multicast Optimization (SMO), that optimizes this case of multipoint delivery, providing the benefits of multicast together with the familiar features and API of TCP. Our results from experiments based on a Linux implementation and performed on a test-bed show that TCP-SMO requires just a modest extension to the TCP implementation and provides the scalable performance of multicast up to over a thousand receivers, thereby satisfying the common case requirements. In addition, used with TCP-RTM (Real-Time Mode), TCP-SMO also supports real-time multimedia multicast applications well.