An Empirical Evaluation of the Cost and Effectiveness of Structural Testing Criteria for Concurrent Programs

Abstract

Concurrent program testing is not a trivial task. Features like nondeterminism, communication and synchronization impose new challenges that must be considered during the testing activity. Some initiatives have proposed testing approaches for concurrent programs, in which different paradigms and programming languages are considered. However, in general, these contributions do not present a well-formed experimental study to validate their ideas. The problem is that the data used and generated during the validation is not always available, hampering the replication of studies in the context of other testing approaches. This paper presents an experimental study, taking into account the concepts of the Experimental Software En- gineering to evaluate the cost, effectiveness and strength of the structural testing criteria for message-passing programs. The evaluation was conducted considering a benchmark composed of eight MPI programs. A set of eight structural testing criteria defined for message-passing programs was evaluated with the ValiMPI testing tool, which provides the support required to apply the investigated testing criteria. The results indicate the complementary aspect of the criteria and the information about cost and effectiveness has contributed to the establishment of an incremental testing strategy to apply the criteria. All material generated during the experimental study is available for further comparisons.