Log filtering and interpretation for root cause analysis

Zawawy, H; Kontogiannis, K; Mylopoulos, J

dc.contributor.author	Zawawy, H	en
dc.contributor.author	Kontogiannis, K	en
dc.contributor.author	Mylopoulos, J	en
dc.date.accessioned	2014-03-01T02:46:52Z
dc.date.available	2014-03-01T02:46:52Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32898
dc.subject	Goal model	en
dc.subject	Latent semantic indexing	en
dc.subject	Log analysis	en
dc.subject	Performance	en
dc.subject	Root cause analysis	en
dc.subject.other	Goal models	en
dc.subject.other	Latent Semantic Indexing	en
dc.subject.other	Log analysis	en
dc.subject.other	Performance	en
dc.subject.other	Root cause analysis	en
dc.subject.other	Automation	en
dc.subject.other	Computer software maintenance	en
dc.subject.other	Indexing (of information)	en
dc.subject.other	Mathematical operators	en
dc.subject.other	Metadata	en
dc.subject.other	Problem solving	en
dc.subject.other	Query languages	en
dc.subject.other	Semantics	en
dc.subject.other	Trees (mathematics)	en
dc.title	Log filtering and interpretation for root cause analysis	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICSM.2010.5609556	en
heal.identifier.secondary	5609556	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICSM.2010.5609556	en
heal.publicationDate	2010	en
heal.abstract	Problem diagnosis in large software systems is a challenging and complex task. The sheer complexity and size of the logged data make it often difficult for human operators and administrators to perform problem diagnosis and root cause analysis. A challenge in this area is to provide the necessary means, tools, and techniques for the operators to focus their attention to specific parts of the logged data reducing thus the complexity of the diagnostic process. In this paper, we propose a framework for filtering logs according to specific analysis goals and diagnostic hypotheses set by the user or by an automated process. More specifically, the proposed framework uses annotated goal trees to model the constraints and the conditions by which the functionality of a particular system is being delivered. Next, a transformation process maps such constraints and conditions to a collection of queries that can be either applied to a relational database that stores the logged data or use Latent Semantic Indexing to identify the most relevant log entries for the given query. The results of such queries provide a subset of the logged data that is compliant with the goal tree and can be used by a diagnostic SAT-solver based algorithm. Experimental results show that the filtering process can reduce the time and complexity of the diagnosis when applied to multitier heterogeneous service oriented systems. © 2010 IEEE.	en
heal.journalName	IEEE International Conference on Software Maintenance, ICSM	en
dc.identifier.doi	10.1109/ICSM.2010.5609556	en