On the use of anonymized trace data for performance evaluation in IP routers

Authors:
Yusuke Toji;Shingo Ata;Ikuo Oka
Affiliations:
Graduate School of Engineering Osaka City University, Osaka, Japan;Graduate School of Engineering Osaka City University, Osaka, Japan;Graduate School of Engineering Osaka City University, Osaka, Japan
Venue:
APNOMS'07 Proceedings of the 10th Asia-Pacific conference on Network Operations and Management Symposium: managing next generation networks and services
Year:
2007

Citing 3
Cited 0

Performance modeling for fast IP lookups

Proceedings of the 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Fast address look-up for internet routers

BC '98 Proceedings of the IFIP TC6/WG6.2 Fourth International Conference on Broadband Communications: The future of telecommunications
Survey and taxonomy of IP address lookup algorithms

IEEE Network: The Magazine of Global Internetworking

Quantified Score

Hi-index	0.00

Visualization

Abstract

For IP routers, it is important for realistic performance evaluation of address lookup algorithms to consider both routing table and trace data obtained from target network. However, most of trace data available are published after anonymizing personal information. Thus, the published trace data cannot be applied directly to estimate performance of routers. In this paper, we propose a new method for predicting more realistic router performance by using anonymized trace data. For our motivation, we analyze correlations of address space usage between real trace data and routing table. Based on analytic results, we also propose a method which transforms IP addresses in trace data by using statistics of address space usage in routing table. Through trace-driven simulation we show that our method can predict the routers' performance closer to the actual one.