New types of specialized network applications are being created that should be able to transmit large amounts of data across dedicated network links. TCP fails to be a suitable method of bulk data transfer in many of these applications, giving rise to new classes of protocols designed to circumvent TCP’s shortcomings. It is typical in these high-performance applications however, the system hardware is simply incapable of saturating the bandwidths supported by the network infrastructure. When the bottleneck for data transfer occurs in the system itself and not in the network, it is critical that the protocol scales gracefully to prevent buffer overflow and packet loss. It is therefore necessary to build a high-speed protocol adaptive to the performance of each system by including a dynamic performance-based flow control. In this post we are talking about such a protocol, Performance Adaptive User Data Protocol (henceforth PA-UDP). PA-UDP can be used for high speed data transfer which aims to dynamically and autonomously maximize performance under different systems A mathematical model and related algorithms are proposed to describe the theoretical basis behind effective buffer and CPU management. A novel delay-based rate-throttling model is also demonstrated to be very accurate under diverse system latencies. Based on these models, we implemented a prototype under Linux, and the experimental results demonstrate that PA-UDP outperforms other existing high-speed protocols on commodity hardware in terms of throughput, packet loss, and CPU utilization. PA-UDP is efficient not only for high-speed research networks, but also for reliable high-performance bulk data transfer over dedicated local area networks where congestion and fairness are typically not a concern.
High-bandwidth data transport is required for large-scale distributed scientific applications. The default implementations of Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) do not adequately meet these requirements. TCP enhancements and UDP-based transport with non-Additive Increase Multiplicative Decrease (AIMD) control. In the recent years, many changes to TCP have been introduced to improve its performance for high-speed networks. The Fast Active-Queue-Management Scalable TCP(FAST) is based on a modification of TCP Vegas. The Explicit Control Protocol(XCP) has a congestion control mechanism designed for networks with a high BDP and requires hardware support in routers.
The goal of our work is to present a protocol that can maximally utilize the bandwidth of these private links through a novel performance-based system flow control. On high-speed, high-latency, congestion-free networks, a protocol should strive to accomplish two goals: to maximize good put by minimizing synchronous, latency-bound communication and to maximize the data rate according to the receiver’s capacity. Latency-bound communication is one of the primary problems of TCP due to the positive acknowledgment congestion window mechanism. As previous solutions have shown, asynchronous communication is the key to achieving maximum good put. When UDP is used in tandem with TCP, UDP packets can be sent asynchronously, allowing the synchronous TCP component to do its job without limiting the overall bandwidth.
This can be developed as a project. For this you would need electronics laboratory equipments to calculate the data transfer rate in a given time interval.
This Paper was originally published by Ben Eckart.