Rajendra Yavatkar

A reliable dissemination protocol for interactive collaborative applications

The widespread availability of networked multimedia workstations and PCs has caused a signi cant interest in the use of collaborative multimedia applications. Examples of such applications include distributed shared whiteboards, group editors, and distributed games or simulations. Such applications often involve many participants and typically require a speci c form of multicast communication called dissemination in which a single sender must reliably transmit data to multiple receivers in a timely fashion. This paper describes the design and implementation of a reliable multicast transport protocol called TMTP (Tree-based Multicast Transport Protocol). TMTP exploits the e cient beste ort delivery mechanism of IP multicast for packet routing and delivery. However, for the purpose of scalable ow and error control, it dynamically organizes the participants into a hierarchical control tree. The control tree hierarchy employs restricted nacks with suppression and an expanding ring search to distribute the functions of state management and error recovery among many members, thereby allowing scalability to large numbers of receivers. An Mbone-based implementation of TMTP spanning the United States and Europe has been tested and experimental results are presented.

MCP: a protocol for coordination and temporal synchronization in multimedia collaborative applications

The multiflow conversation protocol (MCP), which provides two communication abstractions is discussed. MCP provides a token-based mechanism for concurrency control among participants of a multipoint connection and includes a communication abstraction called a multiflow conversation. A conversation may consist of one or more connections, and MCP enforces temporal synchronization in the delivery of traffic over participant connections. Delivery of traffic in a conversation is also based on a notion of causality that takes into account the delay constraints associated with real-time traffic.<<ETX>>

A rate-based congestion avoidance and control scheme for packet switched networks

A congestion avoidance and control scheme that monitors the incoming traffic to each destination and provides rate-based feedback information to the sources of bursty traffic so that sources of traffic can adjust their packet rates to match the network capacity is described. The congestion avoidance mechanism at nodes on the periphery of the network controls incoming traffic so that it does not exceed the capacity of paths to different destinations. The congestion control mechanism at each node monitors the performance of adjacent links and generates rate control messages that warn the sources of traffic before congestion develops. Some existing schemes are reviewed, and the congestion avoidance and control scheme and its applicability to various transport protocols are discussed. Experiments show that the scheme is effective in preventing congestion inside the network and that it manages to restrict the traffic on any overloaded path to 80%-90% of its capacity.<<ETX>>

Communication support for distributed collaborative applications

The development of distributed, multimedia, collaborative applications requires the resolution of communication issues such as concurrency control and temporal and causal synchronization of traffic over related data streams. Existing transport and/or session-layer protocols do not include the desired support for multistream, multipoint communication. In this paper, we propose new communication abstractions and mechanisms that facilitate the implementation of the necessary coordination and concurrency control semantics in a collaborative application. We propose a protocol suite called themultiflow conversation protocol (MCP) for the realization of these abstractions and describe its prototype implementation in an internetwork of workstations. The paper also describes our experience with the prototype and results of a performance evaluation.

Optimistic strategies for large-scale dissemination of multimedia information

We are investigating alternative transport protocol strategies for realizing large scale dissemination services across a wide area network. Communication requirements of such applications are distinct from those based on conventional client-server interactions. Conventional ow and error control methods based on the retransmissions-with-timeout paradigm are not appropriate for such applications. Instead, we are interested in using optimistic ow and error control strategies that take into account application-speci c error tolerance and media rates of multimedia applications. This paper describes transport level policies that use a combination of redundant transmissions, rate-based ow control, and selective feedback from receivers. A simulation-based performance evaluation demonstrates that relatively simple techniques succeed well in meeting the QOS requirements of a multimedia multicast and in scaling to hundreds of recipients.

A CPU Scheduling Algorithm for Continuous Media Applications

We provide an overview of a CPU management algorithm called RAP (Rate-based Adjustable Priority Scheduling) that provides predictable service and dynamic QOS control in the presence of varying compute times, arrival and departure of processes, and CPU overloads. A significant feature of RAP includes an application-level QOS manager that implements policies for graceful adaptation in the face of CPU overload.

An object-oriented model for image information representation

Efficient management of non-alphanumeric data (such as images, videos, and graphs) is essential to a large number of applications. This paper discusses the issues in pictorial information modeling, examines the suitability of traditional data modeling approaches, and then proposes a new objectoriented data modeling approach, called Modeling ObjectOriented Data Semantics (MOODS). A key idea in MOODS is to integrate the image processing component of an image information management system with the data modeling technique. In addition, a user may provide additional assistance in defining semantics at various stages. We argue that the data modeling technique must capture the sequence of transformations and allow a variety of semantics to be associated with the same data to accommodate different application domains. Additional salient features of MOODS include a notion of abstract function classes and dynamic binding of functions to data.

Semantic data model for embedded image information

Historically, database systems have provided convenient methods for obtaining specific information from a large repository of data. All the information was readily available and the mapping between the data and its semantics was straightforward. However, the increasing availability of multimedia data sources introduces new data forms for which the mapping between data and its semantics is not clear. In particular non- alphanumeric data such as images, videos, graphs, charts, etc. contain large amounts of information that are difficult to quantify in a complete and concise fashion. Moreover, the semantic information contained in such data is often application specific. This paper addressed the problem of embedded semantic information. The basic idea is the integration of a data processing component into data modeling systems to allow additional (possibly application dependent) information to be extracted. This paper proposes a new object-oriented data modeling approach, shows how such a design can be applied to a pictorial information system, and describes a prototype system with an example application.

Clique: a toolkit for group communication using IP multicast

Widespread availability of IP multicast has renewed interest in structuring distributed applications around a group communication paradigm that exploits network-layer support for multicast applications. In the past, distributed systems that provided group communication supported a restricted group communication model. Such systems are either designed to provide reliable delivery with support for atomicity and causality or to provide simple unreliable, unordered multicast delivery. We believe that the group communication abstraction is useful to many application domains. However, the group communication requirements of an application vary widely from domain to domain. The paper describes a group communication toolkit called Clique that contains the basic building blocks required to provide a flexible group communication paradigm. Clique achieves support for a wide variety of applications by tailoring the underlying multicast mechanism to meet the applications group communications requirements with the least amount of unnecessary overhead.<<ETX>>

High-speed propagation of link status routing control information

A link status routing algorithm required each node to know the current status of all the links in the network. Nodes use a link status update protocol that helps in keeping the database at each node up-to-date. The authors describe a link status update protocol designed for a highspeed network. The protocol uses the best-effort model of packet delivery, but is fault-tolerant. It uses an algorithm for fast propagation of link status updates that is optimized for the expected case when no update packets are lost, and no link or node failures occur. The protocol uses a separate mechanism to detect and recover from errors caused by loss of updates and failure of nodes or links.<<ETX>>