The Community for Technology Leaders
RSS Icon
Subscribe
Miami, Florida
Dec. 6, 2009 to Dec. 9, 2009
ISBN: 978-0-7695-3895-2
pp: 588-597
ABSTRACT
We describe a novel application of using data mining and statistical learning methods to automatically monitor and detect abnormal execution traces from console logs in an online setting. Different from existing solutions, we use a two stage detection system. The first stage uses frequent pattern mining and distribution estimation techniques to capture the dominant patterns (both frequent sequences and time duration). The second stage use principal component analysis based anomaly detection technique to identify actual problems. Using real system data from a 203-node Hadoop [1] cluster, we show that we can not only achieve highly accurate and fast problem detection, but also help operators better understand execution patterns in their system.
INDEX TERMS
console logs, system management, monitoring, problem detection, logs, pattern mining
CITATION
Wei Xu, Ling Huang, Armando Fox, David Patterson, Michael Jordan, "Online System Problem Detection by Mining Patterns of Console Logs", ICDM, 2009, 2013 IEEE 13th International Conference on Data Mining, 2013 IEEE 13th International Conference on Data Mining 2009, pp. 588-597, doi:10.1109/ICDM.2009.19
25 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool