Large scale monitoring of home routers

This paper describes our experience with concurrent asynchronous monitoring of large populations of end-user broadband-access routers. Despite of the wealth of research in large-scale monitoring, which assumes that it is possible to inquiry individual nodes efficiently, end-user access routers usually have manual legacy interfaces, either HTTP- or telnet-oriented. They seldom offer a direct interface to other programs. Moreover, the uptime of end-user routers is unpredictable. For all these reasons, commercial large-scale monitoring tools such as SNMP collectors are useless. This research is motivated by the fact that some telecommunications operators do not let end-users buy their routers in the consumer electronics market. Instead, they rent the routers and maintain them under long-term contracts. By monitoring line signal-to-noise ratio, transmission and reception power, memory usage or uptime, the operators can predict many types of router failures. In any case, this information may feed their data warehouses for future use. In our field tests we monitored the routers of the Spanish ISP and VoIP operator Comunitel. With our approach, a full monitoring cycle of 22,300 such routers took less than five minutes.