Critical event prediction for proactive management in large-scale computer clusters

By R. Sahoo, Adam J. Oliner, Irina Rish, Manish Gupta, J. Moreira, Sheng Ma, Ricardo Vilalta, Anand Sivasubramaniam. Knowledge Discovery and Data Mining, 2003

305 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A survey of online failure prediction methods (2010, methodology): “The eventset method has been applied for failure prediction in a 350-node cluster system, as described in [Sahoo et al. 2003] (Category 2.”
BlueGene/L Failure Analysis and Prediction Models (2006, background): “Consequently, several studies [6, 29, 28], including ours [20], have examined system logs either in an online or offline fashion, to identify causal events that lead to failures.”
Outlier Analysis (2013, methodology): “For example, methods for system monitoring of large computer clusters are discussed in [390].”
Proactive fault tolerance for HPC with Xen virtualization (2007, methodology): “, by using ACPI [2], and more generically, by critical-event prediction [28].”
What Supercomputers Say: A Study of Five System Logs (2007, background): “Failure prediction based on time interdependence of events has been the subject of much research [9, 11, 13, 19], and it has been shown that such prediction can be a potent resource for improving job scheduling [17], QoS [16], and checkpointing [14, 15].”
A Survey on Automated Log Analysis for Reliability Engineering (2020, methodology): “Sahoo et al. [157] first addressed this problem by collecting system logs representing the components’ health status.”
Failure Prediction in IBM BlueGene/L Event Logs (2007, background): “Despite these challenges, there have been several attempts [7, 5 , 6] to derive realistic failure prediction models.”