We present a protocol for controlling a shared ATM multicast tree supporting many-to-many communication. The protocol supports one or several ATM VCCs of the many-to-many type. The number of VCCs is independent of the number of endpoints. The protocol guarantees that there is no interleaving on any VCC of the tree. The protocol also guarantees that the traffic contract associated with the VCCs is respected, thus making it possible to use ordinary VCCs of the CBR, VBR or UBR class. No re-sequencing server is required, and all cell forwarding is performed at the ATM layer. We describe the protocol both informally and formally.

This paper proposes a multipoint-to-multipoint multicast architecture for ATM networks. The necessity for such an architecture stems from the scalability requirements, both in terms of state to be maintained in the network and in terms of the group population dynamics, of a wide range of networking applications. We argue that approaches of using multicast servers or meshes of point-to-multipoint Virtual Circuits (VCs) may be inadequate solutions to this problem. We propose a true multipoint-to-multipoint architecture called SEAM, which uses a single VC for a multicast group consisting of multiple senders and receivers. We achieve this without changes to ATM's AAL5. SEAM relies on an additional switching feature we call cut-through forwarding, which enables the mapping of several incoming VCs into outgoing VCs. We believe that SEAM is both an important and necessary step in the evolution of ATM. It will enable applications relying on group multicast to benefit directly from ATM's qual...

The concept of a Service Specific Control Architecture (SSCA) in an ATM environment is presented. Here a Control Architecture denotes the out-of-band control and management mechanisms operational in a network or virtual network (or part thereof). An SSCA can use knowledge about the applications it serves to make better use of network resources and thus provide a more efficient service. Such a control architecture can be designed to provide only the subset of control functions required by the applications it serves, thereby greatly reducing its complexity. The switchlet mechanism, which allows more than one control architecture to be operational simultaneously within the same network, enables the use of service specific control architectures. Implementation work is presented to illustrate the use of switchlets and SSCAs. This includes both an environment which uses switchlets to dynamically create virtual networks, and an SSCA used to provide video and audio conferencing facilities in a...

Human collaboration applications and distributed systems are expected to benefit from a group multicast service, both in terms of performance and design simplicity. We argue that such a service must be scalable both in the number of potential senders and receivers. The success of ATM will in part depend on the availability of an efficient group multicast service. We provide a brief description of the requirements for a general multicast service, and then present SEAM, a proposal for scalable and efficient multicast in ATM. SEAM relies on an additional switching feature we call cut-through forwarding, which enables the mapping of several incoming Virtual Channels into one or several outgoing Virtual Channels. SEAM relies on a shared tree spanning all senders and receivers of the group...

While support for IP multicasting continues to spread enabling new applications, an increasing number of hosts connects to the worldwide Internet via low bandwidth Point-toPoint links, such as wireline or wireless telephone lines. In this paper we discuss existing proposals for local and wide area IP multicasting and their implications for Point-to-Point links, identify problems with their integration in this environment, and propose alternative special purpose mechanisms to solve these problems. The main problems are overhead due to IGMP leave latency and unnecessary continuous probing of potentially power constrained hosts. Our solution is an alternative to IGMP mechanisms based on join/leave messages for tracking group membership over PtP networks. After presenting the implementation requirements of our proposed and the existing mechanisms, we compare them with respect to performance, interoperability, robustness and implementation complexity, demonstrating that our join/leave protocol is uniformly superior.

. We explore the issues concerning the support of reliable concurrent multicast in ATM networks. We provide motivation for using tree-based schemes versus receiver-initiated schemes, and compare variations on the fundamental tree-based scheme, showing the properties needed for an efficient reliable concast protocol for ATM. A new tree structure, called a feedback tree, is introduced for use in packet deletion flow control. Feedback trees are shown to have a lower average path length, and therefore require less memory and have lower flow control latencies than traditional ack trees. We consider proposals for multipoint-to-multipoint routing and how these protocols effect the efficiency of the reliable concast protocols. 1.0 Introduction The responsibilities of a reliable concurrent multicast (concast) service consist of disseminating information from multiple sources to all members of a multicast group, such that (a) every packet from each source is delivered to each receiver within a ...

The Multicast Address Resolution Server protocol has been proposed as a mechanism for supporting IP multicast over ATM networks. Two basic techniques exist for the intra-subnet multicasting of IP packets over ATM networks. Both the approaches are based on the use of a Multicast Address Resolution Server (MARS). One approach makes use of a mesh of point-to-multipoint Virtual Circuits (VC Mesh) each of which is rooted at a multicast source, while the other uses a shared point-to-multipoint tree rooted at a Multicast Server (MCS). In this paper we describe the design and implementation of a MARS client and an MCS. We present a framework for comparing the VC Mesh and MCS approaches using experimental, simulation and analytical techniques. Finally we present three protocols for the usage of multiple MCSs per IP multicast group, a technique required for groups with large number of senders and group members. Keywords: IP Multicast, Multicast Server Architectures, Network Protocols, ...

This is a survey of the state of the art in delivering IP services over ATM networks, as it stands in the second quarter of 1997. It also includes a look at the alternatives to that set of technologies. The technology and the choices are changing "on the fly", and have evolved significantly during the course of this project. Moreover, the issues are not exclusively technical, but in many respects reflect the great schism in the data communications world: connection-oriented versus connectionless networks. We have tried to present the technical issues and solutions along with an unbiased overview of the more "philosophical" issues. We indicate how we think the technology and the installed base of equipment is going to develop over the next few years, in order to give a picture of the future of ATM in data networking. Contents 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2 Supported Services . . . . . . . . . . . . . . . . . . . . . . . . . 9 3 The Standar...

this document) [Zhang93]. Because ATM is one of the networking technologies which can actually provide the kind of QoS guarantees required, a mapping of RSVP onto ATM is being proposed [Berson96]. Unfortunately, this proposal follows earlier IP-over-ATM work in that the standard ATM control architecture is assumed. An approach in which RSVP is used as the control architecture on an ATM network would appear to be a better solution. 7.1.3 Other Control Architectures

This paper proposes a multipoint-to-multipoint multicast architecture for ATM networks. The necessity for such an architecture stems from the scalability requirements, both in terms of state to be maintained in the network and in terms of the group population dynamics, of a wide range of networking applications including distributed interactive simulation (DIS), distributed databases and games, web caches and efficient support of IP multicasting. Our proposal, SEAM, uses a single VC for a multicast group consisting of multiple senders and receivers. SEAM relies on an additional switching feature called cut-through forwarding, which enables the mapping of several incoming VCs into one or several outgoing VCs.