Correlation of failures that shift for different versions of an analysis engine

摘要

In some embodiments, a data set is selected based on one or more applications experiencing events. A first analysis of the data set is received that classifies the data set into a first set of failures using an analysis engine configured with first classification logic that performs the classifying. A portion of the data set is selected to re-run based on the first set of failures. A second analysis of the portion of the data set is received that classifies the portion of the data set into a second set of failures using the analysis engine that is configured with second classification logic. A correlation of one or more first failures that shift to one or more second failures is determined. An annotation describing the shift in the one or more first failures to the one or more second failures is then output.