Finding Similar Failures Using Callstack Similarity

We develop a machine-learned similarity metric for Windows failure reports using telemetry data gathered from clients describing the failures. The key feature is a tuned callstack edit distance with learned costs for seven fundamental edits based on callstack frames. We present results of a failure similarity classifier based on this and other features. We also describe how the model can be deployed to conduct a global search for similar failures across a failure database.

• Type: Conference
• Year: 2008
• Where: OSDI
• Authors: Kevin Bartz, Jack W. Stokes, John C. Platt, Ryan Kivett, David Grant, Silviu Calinoiu, Gretchen Loihle
• Keywords: Machine-learned Similarity Metric, Operating System, OSDI 2008, Tuned Callstack Edit, Windows Failure Reports