Real-Time Reflexion Modelling in architecture reconciliation: A multi case study

Abstract

ContextReflexion Modelling is considered one of the more successful approaches to architecture reconciliation. Empirical studies strongly suggest that professional developers involved in real-life industrial projects find the information provided by variants of this approach useful and insightful, but the degree to which it resolves architecture conformance issues is still unclear. ObjectiveThis paper aims to assess the level of architecture conformance achieved by professional architects using Reflexion Modelling, and to determine how the approach could be extended to improve its suitability for this task. MethodAn in-vivo, multi-case-study protocol was adopted across five software systems, from four different financial services organizations. Think-aloud, video-tape and interview data from professional architects involved in Reflexion Modelling sessions were analysed qualitatively. ResultsThis study showed that (at least) four months after the Reflexion Modelling sessions less than 50% of the architectural violations identified were removed. The majority of participants who did remove violations favoured changes to the architectural model rather than to the code. Participants seemed to work off two specific architectural templates, and interactively explored their architectural model to focus in on the causes of violations, and to assess the ramifications of potential code changes. They expressed a desire for dependency analysis beyond static-source-code analysis and scalable visualizations. ConclusionThe findings support several interesting usage-in-practice traits, previously hinted at in the literature. These include 1) the iterative analysis of systems through Reflexion models, as a precursor to possible code change or as a focusing mechanism to identify the location of architecture conformance issues, 2) the extension of the approach with respect to dependency analysis of software systems and architectural modelling templates, 3) improved visualization support and 4) the insight that identification of architectural violations in itself does not lead to their removal in the majority of instances.

Architecture consistency: State of the practice, challenges and requirements

“…Studies suggest that they are effective but, by-in-large, these studies focus on identification of inconsistencies only (Lindvall et al 2002;Tesoriero et al 2004) or identification and removal of inconsistencies (Bang and Medvidovic 2015;Brunet et al 2012Brunet et al , 2015Buckley et al 2015;Rosik et al 2011). In order to assess if there was literature directly targeted at practitioners' needs in the AC area, we carried out a targeted literature review of the IEEE and ACM search engines with a query search logically equivalent to Bsoftware AND architecture AND (conformance OR consistency) AND (empirical OR practice OR study).…”

“…Other empirical studies where practitioners' feedback has been provided are (Ali et al 2012;Brunet et al 2015;Buckley et al 2015;Le Gear et al 2005). In these works, the objective was to understand how practitioners have used the current AC approaches and report on the effectiveness of these approaches in identifying inconsistencies (e.g., what kinds of architectural inconsistencies are identified or how do developers identify inconsistencies).…”

“…& Analysis beyond the source code to the entire system including entities like deployment descriptors and 3rd part components (Ali et al 2012;Buckley et al 2015). & Enriched mapping capabilities between the designed and implemented architecture, based on lexical mapping and drag-and-drop mapping of large grained software structures like classes and packages, to architectural components (Ali et al 2012;Buckley et al 2015;Le Gear et al 2005).…”

“…& Enriched mapping capabilities between the designed and implemented architecture, based on lexical mapping and drag-and-drop mapping of large grained software structures like classes and packages, to architectural components (Ali et al 2012;Buckley et al 2015;Le Gear et al 2005). & The ability to enrich the modelling of the architecture, to allow, for example, the definition of interfaces to localize inconsistencies .…”

“…& The ability to enrich the modelling of the architecture, to allow, for example, the definition of interfaces to localize inconsistencies . & Scalable visualization of the designed/implemented architecture, for industrial systems (Ali et al 2012;Buckley et al 2015;Koschke and Simon 2003). & The ability to rank the elements (e.g., classes, and methods) that cause the most architectural inconsistencies between architectural components (Ali et al 2012;Buckley et al 2015).…”