Correlating Internet Performance Changes and Route Changes to Assist in Trouble-Shooting from an End-User Perspective

With the growth of world wide data intensive scientific collaborations, there is a need to transfer large amounts of data to and from data repositories around the world. To effectively enable such transfers, high speed, predictable networks are needed. In turn, these require performance monitoring to ensure their quality. One tool/infrastructure that has been successfully used for the analysis and monitoring of critical paths is IEPM-BW [1]. Based on experience gained from the achievable throughput monitoring in IEPM-BW, we developed AbwE [2], a tool to enable quick (< 1 second), low impact (40 packets) measurements of available bandwidth. Using ABwE we have been able to quickly detect significant changes in available bandwidth on production links up to 1Gbps, and report this information to the appropriate Network Operations Centers (NOCs) for repair, as such changes are often associated with route changes. This paper discusses this set of tools and their effectiveness together with examples of their utilization.