VMTP: a transport protocol for the next generation of communication systems
SIGCOMM '86 Proceedings of the ACM SIGCOMM conference on Communications architectures & protocols
Internetworking with TCP/IP: principles, protocols, and architecture
Internetworking with TCP/IP: principles, protocols, and architecture
The VMP network adapter board (NAB): high-performance network communication for multiprocessors
SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
Computer networks
Translation of Formal Protocol Specifications to VLSI Designs
Proceedings of the IFIP WG6.1 Seventh International Conference on Protocol Specification, Testing and Verification VII
Data transport in a byte stream network
IEEE Journal on Selected Areas in Communications
Architectural considerations for a new generation of protocols
SIGCOMM '90 Proceedings of the ACM symposium on Communications architectures & protocols
A control-theoretic approach to flow control
SIGCOMM '91 Proceedings of the conference on Communications architecture & protocols
A bibliography on performance issues ATM networks
ACM SIGCOMM Computer Communication Review
Alternative software architectures for parallel protocol execution with synchronous IPC
IEEE/ACM Transactions on Networking (TON)
A control-theoretic approach to flow control
ACM SIGCOMM Computer Communication Review - Special twenty-fifth anniversary issue. Highlights from 25 years of the Computer Communication Review
Research: Signature-based method for run-time fault detection in communication protocols 1
Computer Communications
Hi-index | 0.01 |
We present a design and preliminary analysis of an end-to-end transport protocol that is capable of high throughput consistent with the evolving wideband physical networks based on fiber optic transmission lines and high capacity switches. Unlike the current transport protocols in which changes in control state information are exchanged between the two communicating entities only when some significant event occurs, our protocol exchanges relevant and full state information periodically, routinely and frequently. We show that this results in reducing the complexity of protocol processing by removing many of the procedures required to recover from the inadequacies of the network such as bit-errors, packet loss, out of sequence packets and makes it more amenable to parallel processing. Also, to increase channel utilization in the presence of high speed, long latency networks, and to support datagrams, we propose an efficient implementation of selective repeat method of error control used in our protocol. Thus, we utilize small extra bandwidth to simplify protocol processing; a trade-off that appears proper since electronic speeds for protocol processing are far slower than fiber transmission rates. Our preliminary estimates indicate that 20,000 packets/second can be handled in a completely software implementation on a 10 MIP microprocessor using 8% of its cycles.