A Parallel TCP/IP Protocol Implementation

نویسندگان

Paul Mackerras

David Sitsky

چکیده

With the ever-increasing network data rates available, the throughput achieved on a connection over a fast network using a transport protocol such as TCP/ IP can easily be limited by the speed of the processor used to implement the transport protocol, rather than the network data rate. Distributing TCP/IP protocol processing over several processors in a distributed-memory parallel computer, the Fujitsu AP1000, is shown to provide a useful improvement in throughput achieved on connections over an FDDI ring.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Minimal TCP/IP implementation with proxy support

Over the last years, interest for connecting small devices such as sensors to an existing network infrastructure such as the global Internet has steadily increased. Such devices often has very limited CPU and memory resources and may not be able to run an instance of the TCP/IP protocol suite. In this thesis, techniques for reducing the resource usage in a TCP/IP implementation is presented. A ...

متن کامل

A Method and Tool for Optimized Parallel Protocol Implementation

We are introducing and discussing a method for the optimized and parallel implementation of protocols as well as a tool OpParIm to apply the method automatically to the speciication of a protocol. We present a study case representing an IP/TCP/FTP protocol stack speciied in SDL. We show how Op-ParIm generates dependence graphs from the speciication and how it manipulates these graphs to allow f...

متن کامل

Implementation and Performance Evaluation of TCP Boston: A Fragmentation-Tolerant TCP Protocol for ATM Networks

In this paper, we overview the implementation of TCP Boston— a novel fragmentation-tolerant transport protocol, especially suited for ATM's 53-byte cell-oriented switching architecture. TCP Boston integrates a standard TCP/IP protocol, such as Reno or Vegas, with a powerful redundancy control mechanism based on AIDA—an adaptive version of Rabin's IDA dispersal and reconstruction algorithms. Our...

متن کامل

Benchmarking a Network of PCs Running Parallel Applications

We present a benchmarking study that compares the performance of a network of four PCs connected by 100 Mb/s Fast Ethernet running three different system software configurations: TCP/IP on Windows NT, TCP/IP on Linux and a light weight message passing protocol (U-Net Active messages) on Linux. For each configuration, we report results for communication micro-benchmarks and the NAS parallel benc...

متن کامل