Measurement-based Performance Problem Detection and Diagnosis

van Hoorn, Andre (2015) Measurement-based Performance Problem Detection and Diagnosis [Invited talk] In: Invited talk at Gran Sasso Science Institute, April 21, 2015, L'Aquila, Italy.

[img]
Preview
Slideshow
20150421-GSSI-LAquila.pdf

Download (4Mb) | Preview

Abstract

Application performance monitoring (APM) is getting more and more common in practice. The APM data obtained from the monitored application systems – ranging from aggregated response time and resource utilization values to detailed event traces of individual transactions – includes valuable information for detecting and diagnosing performance problems even before they occur. However, particularly problem diagnosis is currently often performed manually with little guidance by APM tools. After a brief introduction into application performance problem detection and diagnosis, I will present what we have done in this area in the context of our open-source APM framework Kieker (http://kieker-monitoring.net/) and outline our plans for the recently started collaborative research project diagnoseIT on expert-guided automatic diagnosis of performance problems in enterprise applications.

Document Type: Conference or Workshop Item (Invited talk)
Keywords: Kieker, monitoring, performance problems detection and diagnosis, diagnoseIT
Research affiliation: Kiel University > Faculty of Engineering > Department of Computer Science > Software Engineering
Projects: Kieker
Date Deposited: 21 Apr 2015 22:11
Last Modified: 21 Apr 2015 22:13
URI: http://eprints.uni-kiel.de/id/eprint/28605

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...