Mining association rules between sets of items in large databases
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Fault isolation and event correlation for integrated fault management
Proceedings of the fifth IFIP/IEEE international symposium on Integrated network management V : integrated management in a virtual world: integrated management in a virtual world
Mining N-most Interesting Itemsets
ISMIS '00 Proceedings of the 12th International Symposium on Foundations of Intelligent Systems
Pinpoint: Problem Determination in Large, Dynamic Internet Services
DSN '02 Proceedings of the 2002 International Conference on Dependable Systems and Networks
Performance debugging for distributed systems of black boxes
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
Active probing strategies for problem diagnosis in distributed systems
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Discovering actionable patterns in event data
IBM Systems Journal
Problem classification method to enhance the ITIL incident and problem
IM'09 Proceedings of the 11th IFIP/IEEE international conference on Symposium on Integrated Network Management
Performance analysis and problem determination in SOA environments
ICSOC'11 Proceedings of the 2011 international conference on Service-Oriented Computing
Hi-index | 0.00 |
Enterprise middleware systems typically consist of a large cluster of machines with stringent performance requirements. Hence, when a performance problem occurs in such environments, it is critical that the health monitoring software identifies the root cause with minimal delay. A technique commonly used for isolating root causes is rule definition, which involves specifying combinations of events that cause particular problems. However, such predefined rules (or problem signatures) tend to be inflexible, and crucially depend on domain experts for their definition. We present in this paper a method that automatically generates change point based problem signatures using administrator feedback, thereby removing the dependence on domain experts. The problem signatures generated by our method are flexible, in that they do not require exact matches for triggering, and adapt as more information becomes available. Unlike traditional data mining techniques, where one requires a large number of problem instances to extract meaningful patterns, our method requires few fault instances to learn problem signatures. We demonstrate the efficacy of our approach by learning problem signatures for five common problems that occur in enterprise systems and reliably recognizing these problems with a small number of learning instances.