Abstract: A method for predicting software failure characteristics is discussed. The method includes accessing failure data and context data related to a failed software call into a software stack. The failure data indicates software call information. The context data indicates characteristics including functionality of the failed software call. The method includes accessing cluster data on previous software failures. The cluster data includes analyzed failure data and analyzed context data on software call traces. The analyzed failure data is provided by first and second failure tools. The cluster data for software calls is generated through respective instances of the software stack for each software call trace. The method also includes correlating the failed software call trace to a particular software call trace of the cluster data. The correlating is based at least on analysis of clusters indicated by the cluster data, the failure data, and the context data.

Abstract: A method for predicting software failure characteristics is discussed. The method includes accessing failure data and context data related to a failed software call into a software stack. The failure data indicates software call information. The context data indicates characteristics including functionality of the failed software call. The method includes accessing cluster data on previous software failures. The cluster data includes analyzed failure data and analyzed context data on software call traces. The analyzed failure data is provided by first and second failure tools. The cluster data for software calls is generated through respective instances of the software stack for each software call trace. The method also includes correlating the failed software call trace to a particular software call trace of the cluster data. The correlating is based at least on analysis of clusters indicated by the cluster data, the failure data, and the context data.