Random early detection gateways for congestion avoidance
IEEE/ACM Transactions on Networking (TON)
Modeling TCP throughput: a simple model and its empirical validation
Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication
Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication
Fluid models and solutions for large-scale IP networks
SIGMETRICS '03 Proceedings of the 2003 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
On Individual and Aggregate TCP Performance
ICNP '99 Proceedings of the Seventh Annual International Conference on Network Protocols
Data transfers in the grid: workload analysis of globus GridFTP
DADC '08 Proceedings of the 2008 international workshop on Data-aware distributed computing
Hi-index | 0.00 |
In this paper, we quantitatively evaluate the performance of GridFTP operating with the existing TCP by using a mathematical analytic approach. GridFTP has the following mechanisms for solving the problems of the existing TCP. First, for accelerating the start-up in the TCP's slow start phase and achieving high throughput in the TCP's congestion avoidance phase, multiple TCP connections can be established in parallel. Second, according to the bandwidth-delay product of a network, the TCP socket buffer size can be adjusted betweenGridFTP server and client. However, in the literature, sufficient investigation has been performed neither on the optimal number of TCP connections, nor the optimal configuration of the TCP socket buffer size. Therefore, in this paper, by focusing on the number of TCP connections and the TCP socket buffer size, we quantitatively investigate the optimal parameter configuration of GridFTP, in particular, in terms of the number of TCP connections and the TCP socket buffer size.