TRUMP-a fast reliable transport protocol for distributed systems

Traditional transport protocols such as TCP and TP4 were not designed to be used in distributed systems; they also fail to support the high speeds and low error rates of current high speed networks such as FDDI. Various protocols, such as VMTP, RRDP, NET-BLT and XTP have suggested ways of supporting distributed systems and/or high speed networks. However, none of them have fully supported both distributed systems and high-speed networks. This paper outlines the structure of TRUMP, a transport protocol that meets most of the requirements for high speed networks and distributed systems, except for multicast, which is still being designed.

[1]  Andrew Birrell,et al.  Implementing remote procedure calls , 1984, TOCS.

[2]  Andrzej M. Goscinski,et al.  Distributed operating systems - the logical design , 1991 .

[3]  D.R. Cheriton,et al.  VMTP as the transport layer for high-performance distributed systems , 1989, IEEE Communications Magazine.

[4]  Alfred C. Weaver,et al.  The Xpress transfer protocol (XTP)—a tutorial , 1990, CCRV.

[5]  Lixia Zhang,et al.  NETBLT: a high throughput transport protocol , 1987, Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication.