@article{rahman_farhana_parnin_williams_2020, title={Gang of Eight: A Defect Taxonomy for Infrastructure as Code Scripts}, ISSN={["0270-5257"]}, DOI={10.1145/3377811.3380409}, abstractNote={Defects in infrastructure as code (IaC) scripts can have serious consequences, for example, creating large-scale system outages. A taxonomy of IaC defects can be useful for understanding the nature of defects, and identifying activities needed to fix and prevent defects in IaC scripts. The goal of this paper is to help practitioners improve the quality of infrastructure as code (IaC) scripts by developing a defect taxonomy for IaC scripts through qualitative analysis. We develop a taxonomy of IaC defects by applying qualitative analysis on 1,448 defect-related commits collected from open source software (OSS) repositories of the Openstack organization. We conduct a survey with 66 practitioners to assess if they agree with the identified defect categories included in our taxonomy. We quantify the frequency of identified defect categories by analyzing 80,425 commits collected from 291 OSS repositories spanning across 2005 to 2019. Our defect taxonomy for IaC consists of eight categories, including a category specific to IaC called idempotency (i.e., defects that lead to incorrect system provisioning when the same IaC script is executed multiple times). We observe the surveyed 66 practitioners to agree most with idempotency. The most frequent defect category is configuration data i.e., providing erroneous configuration data in IaC scripts. Our taxonomy and the quantified frequency of the defect categories may help in advancing the science of IaC script quality.}, journal={2020 ACM/IEEE 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2020)}, author={Rahman, Akond and Farhana, Effat and Parnin, Chris and Williams, Laurie}, year={2020}, pages={752–764} }
 @article{rahman_farhana_williams_2020, title={The 'as code' activities: development anti-patterns for infrastructure as code}, volume={25}, ISSN={["1573-7616"]}, DOI={10.1007/s10664-020-09841-8}, abstractNote={The ‘as code’ suffix in infrastructure as code (IaC) refers to applying software engineering activities, such as version control, to maintain IaC scripts. Without the application of these activities, defects that can have serious consequences may be introduced in IaC scripts. A systematic investigation of the development anti-patterns for IaC scripts can guide practitioners in identifying activities to avoid defects in IaC scripts. Development anti-patterns are recurring development activities that relate with defective IaC scripts. The goal of this paper is to help practitioners improve the quality of infrastructure as code (IaC) scripts by identifying development activities that relate with defective IaC scripts. We identify development anti-patterns by adopting a mixed-methods approach, where we apply quantitative analysis with 2,138 open source IaC scripts and conduct a survey with 51 practitioners. We observe five development activities to be related with defective IaC scripts from our quantitative analysis. We identify five development anti-patterns namely, ‘boss is not around’, ‘many cooks spoil’, ‘minors are spoiler’, ‘silos’, and ‘unfocused contribution’. Our identified development anti-patterns suggest the importance of ‘as code’ activities in IaC because these activities are related to quality of IaC scripts.}, number={5}, journal={EMPIRICAL SOFTWARE ENGINEERING}, author={Rahman, Akond and Farhana, Effat and Williams, Laurie}, year={2020}, month={Sep}, pages={3430–3467} }
 @article{farhana_imtiaz_rahman_2019, title={Synthesizing Program Execution Time Discrepancies in Julia Used for Scientific Software}, ISSN={["1063-6773"]}, DOI={10.1109/ICSME.2019.00083}, abstractNote={Scientific software is defined as software that is used to analyze data to investigate unanswered research questions in the scientific community. Developers use programming languages such as Julia to build scientific software. When programming with Julia, developers experience program execution time discrepancy i.e. not obtaining desired program execution time, which hinders them to efficiently complete their tasks. The goal of this paper is to help developers in achieving desired program execution time for Julia by identifying the causes of why program execution time discrepancies happen with an empirical study of Stack Overflow posts. We conduct an empirical study with 263 Julia-related posts collected from Stack Overflow, and apply qualitative analysis on the collected 263 posts. We identify 9 categories of program execution time discrepancies for Julia, which include discrepancies related to data structures usage such as, arrays and dictionaries. We also identify 10 causes that explain why the program execution time discrepancies happen. For example, we identify program execution time discrepancy to happen when developers unnecessarily allocate memory by using array comprehension.}, journal={2019 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME 2019)}, author={Farhana, Effat and Imtiaz, Nasif and Rahman, Akond}, year={2019}, pages={496–500} }