Duration: 1:22:03

137 views

1

Of the major factors affecting end-to-end service availability, network component failure is perhaps the least well understood. How often do failures occur, how long do they last, what are their causes, and how do they impact customers? Traditionally, answering questions such as these has required dedicated (and often expensive) instrumentation broadly deployed across a network. We are exploring an alternative approach: opportunistically mining ΓÇ£low-qualityΓÇ¥ data sources that are already available in modern network environments. This talk will describe a methodology for recreating a succinct history of failure events in a wide-area IP network using a combination of structured data (router configurations and syslogs) and semi-structured data (email logs). We have used this technique to analyze over five years of failure events in a large regional network consisting of over 200 routers; to our knowledge, this is the largest study of its kind. Currently, we are conducting similar evaluations in a number of enterprise environments.