Spectrum-Based Fault Localization via Enlarging Non-Fault Region to Improve Fault Absolute Ranking

Abstract

Spectrum-based fault localization (SFL) is a popular lightweight automatic software fault localization technique that uses coverage information of program execution to compute the likelihood of root cause of failure(s) for each program component and ranks them descending by their suspiciousness scores. However, some recent studies indicate an SFL technique to be useful only if the root cause(s) of failures is ranked at top k. Due to the nature of the SFL technique, it is impossible that the root fault(s) is always ranked at top k, which may interfere with the usefulness of SFL in practice. To solve this issue, an SFL technique via enlarging the non-fault region to further improve fault absolute ranking was proposed. The idea behind this is that we can intuitively improve fault absolute ranking for an SFL technique if some non-fault components ranked higher were excluded from the fault ranking list. In the approach, we enlarge the non-fault region iteratively to narrow down the suspicious region based on two scenarios, and then rank those components in the suspicious region using existing SFL techniques. The empirical results indicate that our approach significantly helps existing SFL techniques to further improve their usefulness.

Keywords

• Fault localization
• absolute ranking
• testing
• debugging