Effective diagnosis of routing disruptions from end systems
Ying Zhang, Z. Morley Mao, Ming Zhang · 2008
Internet routing events are known to introduce severe disruption to applications. So far effective diagnosis of routing events has relied on proprietary ISP data feeds, resulting in limited ISP-centric views not easily acces-sible by customers or other ISPs. In this work, we pro-pose a novel approach to diagnosing signicant routing events associated with any large networks from the per-spective of end systems. Our approach is based on scal-able, collaborative probing launched from end systems and does not require proprietary data from ISPs. Us-ing a greedy scheme for event correlation and cause in-ference, we can diagnose both interdomain and intrado-main routing events. Unlike existing methods based on passive route monitoring, our approach can also mea-sure the impact of routing events on end-to-end network performance. We demonstrate the effectiveness of our approach by studying ve large ISPs over four months. We validate its accuracy by comparing with the exist-ing ISP-centric method and also with events reported on NANOG mailing lists. Our work is the rst to scalably and accurately diagnose routing events associated with large networks entirely from end systems. 1