Using GQM for Testing Design Patterns in Real-Time and Embedded Systems on a Software Production Line

This article describes a methodology named Causal Analysis and Resolution (CAR) based on Goals, Questions, and Metrics (GQM) principles. Indicators are defined based on metrics for a decision-making process. Its main contributions are the construction of an information process system model and a prototype, involving GQM approach, in a quantitative definition and qualitative metrics. The CAR methodology is a process area (PA) of the Capability Maturity Model Integrated (CMMi) for software development from Carnegie Mellon University. This PA was used to eliminate systematic error cases listed in a Technical Report (TR) generated by CAR. An information system model was created to allow the elimination of defects, errors, and failures in a design pattern named IO Manager, during the test phase, and before its publication in a components library. The prototype was created using Rational Rose RealTime (RRRT) with focus on verification tests. It provided a quality assessment to the IO Manager design pattern. The use of this methodology was based on GQM and CAR along with the information process system model. The developed prototype aimed to monitor errors on design pattern tests in real-time embedded system of a software production line.