Analyzing Performance-Aware Code Changes in Software Development Process

Abstract

With the continuous expansion of software market and the updating of the maturity of the software development process, the performance requirements of software users have gradually become prominent. Performance issues are closely related to the source code. Thus, with the increasing complex of the software product, its performance changed during the evolution of the software product. Performance optimization related work has always been an important goal for developers who usually coding at a low-level. However, performance problems are well studied on architecture level. All too often, some developers are ignorant of the way their code modifications affect performance and simply to wait until performance drops to a point that is unacceptable to the business side. As software developers did a lot of daily work at code level, we think code level performance awareness can help developers in sight of the performance of the code that they are working with. To deal with this, we firstly build performance-aware code change model to identify the performance changes and its related code changes at the granularity of function between each two reversions of a program. Then, we analyzed the evolution history of the code performance and mined the frequent code change patterns that used to improve performance. We have build related tool to implement the proposed approach and applied it to 8 open source projects.