Failure Analysis of Jobs in Compute Clouds: A Google Cluster Case Study
- 1 November 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 167-177
- https://doi.org/10.1109/issre.2014.34
Abstract
In this paper, we analyze a workload trace from the Google cloud cluster and characterize the observed failures. The goal of our work is to improve the understanding of failures in compute clouds. We present the statistical properties of job and task failures, and attempt to correlate them with key scheduling constraints, node operations, and attributes of users in the cloud. We also explore the potential for early failure prediction, and anomaly detection for the jobs. Based on our results, we speculate that there are many opportunities to enhance the reliability of the applications running in the cloud, such as pro-active maintenance of nodes or limiting job resubmissions. We further find that resource usage patterns of the jobs can be leveraged by failure prediction techniques. Finally, we find that the termination statuses of jobs and tasks can be clustered into six dominant categories based on the user profiles.Keywords
This publication has 24 references indexed in Scilit:
- An Empirical Failure-Analysis of a Large-Scale Cloud Computing EnvironmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Characterizing Cloud Applications on a Google Data CenterPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Adaptive Anomaly Identification by Exploring Metric Subspace in Cloud Computing InfrastructuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Workload characterization on a production Hadoop cluster: A case study on TaobaoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Characterization and Comparison of Cloud versus Grid WorkloadsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Characterizing Machines and Workloads on a Google ClusterPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Failure-aware resource provisioning for hybrid Cloud infrastructureJournal of Parallel and Distributed Computing, 2012
- The Elements of Statistical LearningPublished by Springer Science and Business Media LLC ,2009
- Energy aware scheduling for distributed real-time systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987