Abstract
The current trend in constructing high-performance computing systems is to connect a large number of machines via a fast interconnect or a large-scale network such as the Internet. This approach relies on the performance of the interconnect (or Internet) to enable fast, large-scale distributed computing. A detailed understanding of the communication traffic is required in order to optimize the operation of the entire system.
Network researchers traditionally monitor traffic in the network to gain the insight necessary to optimize network operations. Recent work suggests additional insight can be obtained by also monitoring traffic at the application level.
The Monitor for Application-Generated Network Traffic toolkit (MAGNeT) we describe here monitors application traffic patterns in production systems, thus enabling more highly optimized networks and interconnects for the next generation of high-performance computing systems.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Accelerated Strategic Computing Initiative. http://www.asci.doe.gov/index.htm.
Distributed Systems Department. http://grid.lbl.gov. ia3._ Grid Computing Info Centre. http://www.gridcomputing.com.
Grid Computing Info Centre.http://www.gridcomputing.com.
Netperf. http://www.netperf.org. ia5._ tcpdump. http://www.tcpdump.org.
tcpdump .http://www.tcpdump.org.
The Beowulf Project. http://www.beowulf.org.
The Internet Traffic Archive. http://ita.ee.lbl.gov/html/traces.html.
J. Bolliger and R. Gross. Bandwidth monitoring for network-aware applications. In Proceedings of the 10th Annual International Symposium on High Performance Distributed Computing, 2001.
CAIDA, CoralReef Software Suite. http://www.caida.org/tools/measurement/coralreef.
et al., B. W. T. The NetLogger methodology for high performance distributed systems performance analysis. In Proceedings of IEEE the High Performance Distributed Computing Conference (HPDC-7), 1998.
W. Feng, J. Hay, and M. Gardner. MAGNeT: Monitor for application-generated network traffic. In Proceedings of the 10th International Conference on Computer Communication and Networking (IC3N'01), 2001.
W. Feng and P. Tinnakornsrisuphap. The adverse impact of the TCP congestion-control mechanism in heterogeneous computing systems. In Proceedings of the International Conference on Parallel Processing, 2000a.
W. Feng and P. Tinnakornsrisuphap. The failure of TCP in high-performance computational grids. In Proceedings of SC 2000: High-Performance Networking and Computing Conference, 2000b.
M. Fisk and W. Feng. Dynamic right-sizing: TCP flow-control adaptation. In Proceedings of the 14th Annual ACM/IEEE SC2001 Conference, 2001.
J. Hay, W. Feng, and M. Gardner. Capturing network traffic with a MAGNeT. In Proceedings of the 5th Annual Linux Showcase and Conference (ALS'01), 2001.
A. Kato, J. Murai, and S. Katsuno. An Internet traffic data repository: The architecture and the design policy. In INET'99 Proceedings, 1999.
J. Semke, PSC TCP kernel monitor. Technical report CMU-PSC-TR-2000–0001, PSC/CMU, 2000.
P. Tinnakornsrisuphap, W. Feng, and I. Philp. On the burstiness of the TCP congestion-control mechanism in a distributed computing system. In Proceedings of the International Conference on Distributed Computing Systems, 2000.
E. Weigle and W. Feng. A case for TCPV egas in high-performance computational grids. In Proceedings of the 10th Annual International Symposium on High Performance Distributed Computing, 2001.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Feng, WC., Gardner, M.K. & Hay, J.R. The MAGNeT Toolkit: Design, Implementation and Evaluation. The Journal of Supercomputing 23, 67–79 (2002). https://doi.org/10.1023/A:1015737203428
Issue Date:
DOI: https://doi.org/10.1023/A:1015737203428