Does PageRank apply to service ranking in microservice regression testing?

Regression testing is required in each development iteration of microservice systems. Test case prioritization, which improves the fault detection rate by optimizing the execution order of test cases, is one of the main techniques to optimize regression testing. Existing test case prioritization techniques mainly rely on artifacts such as codes and system models, which are limited to microservice systems with service autonomy, development method diversity, and large service scale. This paper proposes a test case prioritization approach based on service ranking referred to as TCP-SR. TCP-SR ranks the services based on API gateway logs. The weights of test cases are calculated with the result of service ranking, which could be used to order test cases with single-objective and multi-objective strategies. To evaluate the effectiveness of TCP-SR, the empirical study based on four microservice systems is presented. The results show that the fault detection rate of TCP-SR is almost twice as high as that of the random prioritization technique, and almost the same as the prioritization technique based on WS-BPEL but requires much less prioritization time cost.