Practical Strategies to Improve Test Efficiency |
| |
作者单位: | Shanghai Development Center of Software Technology Shanghai Key Laboratory of Computer Software Evaluating and Testing,Shanghai Development Center of Software Technology,Shanghai Key Laboratory of Computer Software Evaluating and Testing,Shanghai Development Center of Software Technology,Shanghai Key Laboratory of Computer Software Evaluating and Testing,Shanghai 201114,China,Shanghai 201114,China,Shanghai 201114,China |
| |
基金项目: | 国家高技术研究发展计划(863计划);上海市科委资助项目 |
| |
摘 要: | This paper introduces strategies to detect software bugs in earlier life cycle stage in order to improve test efficiency. Static analysis tool is one of the effective methods to reveal software bugs during software development. Three popular static analysis tools are introduced, two of which, PolySpace and Splint, are compared with each other by analyzing a set of test cases generatedd by the authors. PolySpace can reveal 60% bugs with 100% R/W ratio (ratio of real bugs and total warnings), while Splint reveal 73.3% bugs with 44% R/W ratio. And they are good at finding different categories of bugs. Two strategies are concluded to improve test efficiency, under the guideline that static analysis tools should be used in finding different categories of bugs according to their features. The first one aims at finding bugs as many as possible, while the second concentrates to reduce the average time on bug revelation. Experimental data shows the first strategy can find 100% bugs with 60% R/W ratio, the second one find 80% bugs with 66.7% R/W ratio. Experiment results prove that these two strategies can improve the test efficiency in both fault coverage and testing time.
|
Practical Strategies to Improve Test Efficiency |
| |
Authors: | DING Zhigang WANG Hongcheng LING Lianghe |
| |
Abstract: | This paper introduces strategies to detect software bugs in earlier life cycle stage in order to improve test efficiency. Static analysis tool is one of the effective methods to reveal software bugs during software development. Three popular static analysis tools are introduced, two of which, PolySpace and Splint, are compared with each other by analyzing a set of test cases generatedd by the authors. PolySpace can reveal 60% bugs with 100% R/W ratio (ratio of real bugs and total warnings), while Splint reveal 73.3% bugs with 44% R/W ratio. And they are good at finding different categories of bugs. Two strategies are concluded to improve test efficiency, under the guideline that static analysis tools should be used in finding different categories of bugs according to their features. The first one aims at finding bugs as many as possible, while the second concentrates to reduce the average time on bug revelation. Experimental data shows the first strategy can find 100% bugs with 60% R/W ratio, the second one find 80% bugs with 66.7% R/W ratio. Experiment results prove that these two strategies can improve the test efficiency in both fault coverage and testing time. |
| |
Keywords: | static analysis PolySpace splint software bug |
本文献已被 CNKI 万方数据 等数据库收录! |