Abstract: A method may comprise accessing first data sets associated with a first job of a workflow, each first data set associated with an execution of the first job, each first data set specifying a runtime of the first job and a first plurality of feature values of features associated with the runtime; executing a first plurality of feature weighting analyses utilizing the first data sets to rank the plurality of features with respect to their predictive value on a runtime of the first job; and generating, using at least one data processing apparatus, a predicted runtime of the first job based on a time series analysis of a plurality of runtimes of a plurality of second data sets, the second data sets selected from the first data sets based on the rank and one or more expected feature values associated with a future execution of the first job.

Abstract: A workflow to be executed may be identified, the workflow comprising a plurality of jobs linked via relationships. A graph of the jobs of the workflow may be generated based on the relationships. Runtimes for the jobs of the workflow are predicted, wherein for at least some of the predicted runtimes a predicted runtime for a job is based on an analysis of features of the job deemed to be predictive of a runtime for the job. A predicted runtime of a critical path through the workflow is generated based on the graph of the jobs and at least a subset of the predicted runtimes of the jobs of the workflow.

Abstract: A method may comprise accessing first data sets associated with a first job of a workflow, each first data set associated with an execution of the first job, each first data set specifying a runtime of the first job and a first plurality of feature values of features associated with the runtime; executing a first plurality of feature weighting analyses utilizing the first data sets to rank the plurality of features with respect to their predictive value on a runtime of the first job; and generating, using at least one data processing apparatus, a predicted runtime of the first job based on a time series analysis of a plurality of runtimes of a plurality of second data sets, the second data sets selected from the first data sets based on the rank and one or more expected feature values associated with a future execution of the first job.

Abstract: First data sets associated with a job of a workflow are accessed, each first data set specifying a runtime of a job and a first plurality of feature values of a plurality of features. Feature weighting analyses are executed utilizing the first data sets to rank the plurality of features with respect to their predictive value on whether or not execution of the job is to fail. During execution of the workflow, a runtime of the job of the workflow is monitored. During execution of the job, a likelihood of failure of the job is generated based at least in part on the monitored runtime of the job and a plurality of runtimes of second data sets, the second data sets selected from the first data sets based on the rank of the plurality of features and one or more expected feature values associated with the execution of the job.