Finding similar failures using callstack similarity

Authors:
Kevin Bartz;Jack W. Stokes;John C. Platt;Ryan Kivett;David Grant;Silviu Calinoiu;Gretchen Loihle
Affiliations:
Department of Statistics, Harvard University;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Microsoft Corporation, Redmond, WA;Microsoft Corporation, Redmond, WA;Microsoft Corporation, Redmond, WA;Microsoft Corporation, Redmond, WA
Venue:
SysML'08 Proceedings of the Third conference on Tackling computer systems problems with machine learning techniques
Year:
2008

Citing 5
Cited 4

Algorithms on strings, trees, and sequences: computer science and computational biology

Algorithms on strings, trees, and sequences: computer science and computational biology
Learning String-Edit Distance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Computation of Normalized Edit Distance and Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence
Quickly Finding Known Software Problems via Automated Symptom Matching

ICAC '05 Proceedings of the Second International Conference on Automatic Computing
Automatically Identifying Known Software Problems

ICDEW '07 Proceedings of the 2007 IEEE 23rd International Conference on Data Engineering Workshop

Assisting failure diagnosis through filesystem instrumentation

Proceedings of the 2011 Conference of the Center for Advanced Studies on Collaborative Research
ReBucket: a method for clustering duplicate crash reports based on call stack similarity

Proceedings of the 34th International Conference on Software Engineering
Predicting recurring crash stacks

Proceedings of the 27th IEEE/ACM International Conference on Automated Software Engineering
DeltaPath: Precise and Scalable Calling Context Encoding

Proceedings of Annual IEEE/ACM International Symposium on Code Generation and Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.