Workload traces are widely used to profile and characterize workflow executions, and to build distributions of workflow execution behaviors, which are used to evaluate methods and techniques in simulation or in real conditions.
WfTraces provides the collection and curation of open access production workflow executions from various scientific applications shared in a common trace format. The WfCommons Python package provides a set of tools for analyzing traces, which can be used to develop workflow recipes for the WfGen.
In this page, we keep a list of open access workflow execution trace repositories that host traces compliant with The WfFormat for describing workflow executions. We are constantly seeking for additional workflow execution traces for refining or developing new workflow recipes for the WfCommons’s WfGen.
Workflow execution traces are organized into sub-folders within the repositories. Each sub-folder represents
a workflow application, which itself contains sub-folders for workflow executions in different computing
platforms. For each workflow application, a
README.md file provides detailed description of the
structure and pointers to relevant material.