Finding Soon-to-Fail Disks in a Haystack

This paper presents a detector of soon-to-fail disks based on a combination of statistical models. During operation the detector takes as input a performance signal from each disk and sends and alarm when there is enough evidence (according to the models) that the disk is not healthy. The parameters of these models are automatically trained using signals from healthy and failed disks. In an evaluation on a population of 1190 production disks from a popular customer-facing internet service, the detector was able to predict 15 out of the 17 failed disks (88.2% detection) with 30 false alarms (2.56% false positive rate).