Fa: A system for automating failure diagnosis

Conference Paper

Failures of Internet services and enterprise systems lead to user dissatisfaction and considerable loss of revenue. Since manual diagnosis is often laborious and slow, there is considerable interest in tools that can diagnose the cause of failures quickly and automatically from system-monitoring data. This paper identifies two key data-mining problems arising in a platform for automated diagnosis called Fa. Fa uses monitoring data to construct a database of failure signatures against which data from undiagnosed failures can be matched. Two novel challenges we address are to make signatures robust to the noisy monitoring data in production systems, and to generate reliable confidence estimates for matches. Fa uses a new technique called anomalybased clustering when the signature database has no highconfidence match for an undiagnosed failure. This technique clusters monitoring data based on how it differs from the failure data, and pinpoints attributes linked to the failure. We show the effectiveness of Fa through a comprehensive experimental evaluation based on failures from a production setting, a variety of failures injected in a testbed, and synthetic data. © 2009 IEEE.

Full Text

Duke Authors

Cited Authors

  • Duan, S; Babu, S; Munagala, K

Published Date

  • July 8, 2009

Published In

Start / End Page

  • 1012 - 1023

International Standard Serial Number (ISSN)

  • 1084-4627

International Standard Book Number 13 (ISBN-13)

  • 9780769535456

Digital Object Identifier (DOI)

  • 10.1109/ICDE.2009.115

Citation Source

  • Scopus