Title :
MNEMONIC: A Network Environment for Automatic Optimization and Tuning of Data Movement over Advanced Networks
Author :
Patrick McClory;Ezra Kissel;Martin Swany;Michela Taufer
Author_Institution :
Dept. of Comput. & Inf. Sci., Univ. of Delaware, Newark, DE, USA
Abstract :
Computational science is considered the third pillar of science but while we continue to make significant strides in high-performance computing, the ability to transfer the vast amounts of data generated and consumed by scientists has fallen behind. This divergence has significantly constrained scientific progress. This paper describes MNEMONIC, an end-to-end cyber-infrastructure system designed to improve scientists´ productivity by automatically and transparently optimizing and tuning data movement over the network. MNEMONIC integrates advanced technologies, i.e., network interfaces, protocols, and measurement toolkits, to seamlessly manage high-performance data movement. We have integrated the Java implementation of GridFTP in MNEMONIC to provide a cross-platform data transfer capability. Preliminary results show that MNEMONIC+GridFTP outperforms the TCP+GridFTP implementation by over a factor of 10x, while remaining easy to install and operate.
Keywords :
"Protocols","Computer networks","Throughput","US Department of Energy","Productivity","Technology management","Java","Large Hadron Collider","Design optimization","Network interfaces"
Conference_Titel :
Computer Communications and Networks, 2009. ICCCN 2009. Proceedings of 18th Internatonal Conference on
DOI :
10.1109/ICCCN.2009.5235222