STRID: Scalable Trigger-Based Route Incidence Diagnosis

Abstract

As the Internet steadily increases in importance, it is still based on a quite fragile routing design. From network operators perspective it is therefore crucial to detect end-to- end path performance due to routing outages early to either mitigate them directly or contact other entities to mitigate them. In this work we demonstrate the feasibility of a real-time tool for detecting degraded forwarding performance due to routing problems. Our tool passively monitors the traffic within the network and actively probes paths for which the TCP traffic characteristics indicate a possible routing problem. More importantly, our tool focuses on detecting routing events that actually affect network traffic, which from the network operators' perspective is most relevant. The experimental results based on large-scale measurement in the Internet indicate that our tool effectively detects a significant number of routing outages and forwarding loops.