Teruji Shiroshita

Performance evaluation of reliable multicast transport protocol for large-scale delivery

This paper analyzes the performance of a reliable multicast transport protocol and discusses experimental test results. The Reliable Multicast Transport Protocol has been proposed to support “reliable” information delivery from a server to thousands of receivers over unreliable networks via IP-multicast. The protocol provides high-performance for most receivers through the advantage of IP multicast while also supporting temporarily unavailable or performance impaired receivers. Its applicability to large scale delivery is examined using an experimental network and the backoff time algorithm which avoids ACK implosion. The two types of flow control with the protocol are also examined. Separate retransmission is used to offset the local performance decline limited to a small number of receivers. Monitor-based rate control is used to offset the global performance declines due to causes such as network congestion.

Reliable data distribution middleware for large-scale massive data replication

For massive data replication, Infocast, a communication middleware, is proposed. It distributes large data sets to thousands of receivers without any data loss. This paper examines the distributed processing feature of Infocast and also evaluates its performance. Reliability is achieved by an effective receiver-initiated recovery algorithm and servers complete supervision of all receiver states. Infocast provides reliable data distribution with high-performance to most receivers through the advantage of network-provided multicast while also supporting temporarily unavailable or performance impaired receivers by parallel state transitions. Implementation and performance test results including very large data distribution by VLDD scheme are examined through experiments. Scalability of receiver number and data size is discussed for various conditions.

A Proposal for Reliable Information Multicast Environment: its Implementation and Evaluation

This paper proposes RIME (a Reliable Information Multicast Environment) which supports reliable multicast information delivery, error-free and secure, between a single server and thousands of remote clients. Using RIME it is possible to simultaneously ‘multicast’ such multimedia contents as data, text, image, video and even software updates over networks such as LAN, TCP/IP networks, ATM, ISDN, PSTN or the Internet.

Flow/congestion control for bulk reliable multicast

This paper proposes Monitor-based flow control (MBFC) to realize flow/congestion control needed for one-to-many bulk reliable multicast (RM) protocols. Bulk RM on top of UP multicast requires flow/congestion control because 1) it needs to adjust to the effective bandwidth to minimize packet losses and retransmission, and 2) to share the link bandwidth with other legacy traffic such as TCP so that RM does not override them aggressively. MBFC is a generic mechanism to implement such flow/congestion control. Thus we think it is very important to provide an effective flow and congestion control mechanism that enable RM traffic to coexist with legacy TCP traffic in Internet. MBFC is based on rate flow control and involves a monitor mechanism to adjust its sending rate. In order to realize existence with TCP traffic it mimics TCPs flow/congestion control algorithm, that is, additive increase/multiplicative decrease. To investigate its effectiveness MBFC was implemented in our RM protocol, and a series of simulations were performed in which simultaneous bulk RM and TCP flow were poured. The simulation result showed that our rate control policy effectively achieved bandwidth sharing between bulk RM and bulk TCP transfer traffic. We also conclude that 1) setting the transmission rate to the worst receiver leads to an extremely unfair bandwidth sharing occupied by TCP flow, 2) If Rm only experiences a few loses it should not give up its bandwidth, otherwise TCP monopolizes it. 3) It is more effective for MBFC to introduce RED gateways to prevent RM from an aggressive TCP traffic.

Evaluation of Reliable Multicast Applications for Large-Scale Contents Delivery

Reliable Multicast has been applied to large-scale contents delivery systems for distributing digital contents to a large number of users without data loss. Reliable contents distribution is indispensable for software updates and management data sharing in actual delivery services. This paper evaluates the implementation and performance of RMTP; a reliable multicast protocol for bulk-data transfer, through the developments of contents delivery systems. Software configuration is also examined including operation functions such as delivery scheduling. Furthermore, applicability of reliable multicast to emerging broadband networks is also discussed based on the experimentation results. Through the deployment of the protocol and the software, performance estimation has played a key role for constructing the delivery systems as well as for designing the communication protocol.

A large-scale contents publishing architecture based on reliable multicast

Communication networks have matured to realize online digital contents publishing. This paper proposes a contents publishing architecture which makes a large-scale contents delivery available using recent networks. Multicast is a promising network technology to provide large-scale efficient delivery. However, the issues of reliable and restricted delivery using multicast need to be solved to realize a practical contents publishing. A reliable multicast tool is proposed for error free and confirmed delivery to thousands of users. A contents publishing procedure including service access control and delivery charge is also proposed for commercial publishing.

Applying performance evaluation to large-scale contents delivery system

Reliable multicast has been applied to large-scale contents delivery systems for distributing digital contents to a large number of users without data loss. Performance evaluation of reliable multicast is useful for delivery time estimation in active delivery systems as well as for designing communication protocols and systems. This paper shows the performance estimation scheme for RMTP; a reliable multicast protocol for bulk-data transfer and applies it to the scheduling function in megacast; a contents delivery system for large numbers of receiver. Some performance characteristics of RMTP are also examined.