@inproceedings{7a1869234f904fc481275f0913f31675,
title = "Fault prediction in distributed systems gone wild",
abstract = "We consider the problem of predicting faults in deployed, large-scale distributed systems that are heterogeneous and federated. Motivated by the importance of ensuring reliability of the services these systems provide, we argue that the key step in making these systems reliable is the need to automatically predict faults. For example, doing so is vital for avoiding Internet-wide outages that occur due to programming errors or misconfigurations.",
keywords = "BGP, fault prediction, federated systems, heterogeneous systems, shadow snapshot, spatial and temporal awareness",
author = "Marco Canini and Dejan Novakovi{\'c} and Vojin Jovanovi{\'c} and Dejan Kosti{\'c}",
year = "2010",
doi = "10.1145/1859184.1859187",
language = "English (US)",
isbn = "9781450304061",
series = "Proceedings of the 4th ACM/SIGOPS Workshop on Large-Scale Distributed Systems and Middleware, LADIS 2010",
pages = "7--11",
booktitle = "Proceedings of the 4th ACM/SIGOPS Workshop on Large-Scale Distributed Systems and Middleware, LADIS 2010",
note = "4th ACM/SIGOPS Workshop on Large-Scale Distributed Systems and Middleware, LADIS 2010 ; Conference date: 28-07-2010 Through 29-07-2010",
}