arXiv subjects

Thiago Emmanuel Pereira

Publications and source records attributed to Thiago Emmanuel Pereira.

5 recordsLinked to original sources

arXiv2025

A Defect Taxonomy for Infrastructure as Code: A Replication Study

Background: As Infrastructure as Code (IaC) becomes standard practice, ensuring the reliability of IaC scripts is essential. Defect taxonomies are valuable tools for this, offering a common language for issues and enabling systematic tracking. A significant prior study developed such a taxonomy, but based it exclusively on the declarative language Puppet. It remained unknown whether this taxonomy applies to programming language-based IaC (PL-IaC) tools like Pulumi, Terraform CDK, and AWS CDK. Aim: We replicated this foundational work to assess the generalizability of the taxonomy across a broader and more diverse landscape. Method: We performed qualitative analysis on 3,364 defect-related commits from 285 open-source PL-IaC repositories (PIPr dataset) to derive a PL-IaC-specific defect taxonomy. We then enhanced the ACID tool, originally developed for the prior study, to automatically classify and analyze defect distributions across an expanded dataset-447 open-source repositories and 94 proprietary projects from VTEX (e-commerce) and Nubank (financial). Results: Our research confirmed the same eight defect categories identified in the original study, with idempotency and security defects appearing infrequently but persistently across projects. Configuration Data defects maintain high frequency in both open-source and proprietary codebases. Conclusions: Our replication supports the generalizability of the original taxonomy, suggesting IaC development challenges surpass organizational boundaries. Configuration Data defects emerge as a persistent high-frequency problem, while idempotency and security defects remain important concerns despite lower frequency. These patterns appear consistent across open-source and proprietary projects, indicating they are fundamental to the IaC paradigm itself, transcending specific tools or project types.

cs.SE↗

arXiv2022

A case study of proactive auto-scaling for an ecommerce workload

Preliminary data obtained from a partnership between the Federal University of Campina Grande and an ecommerce company indicates that some applications have issues when dealing with variable demand. This happens because a delay in scaling resources leads to performance degradation and, in literature, is a matter usually treated by improving the auto-scaling. To better understand the current state-of-the-art on this subject, we re-evaluate an auto-scaling algorithm proposed in the literature, in the context of ecommerce, using a long-term real workload. Experimental results show that our proactive approach is able to achieve an accuracy of up to 94 percent and led the auto-scaling to a better performance than the reactive approach currently used by the ecommerce company.

cs.DC↗

arXiv2021

Validation of a simulation model for FaaS performance benchmarking using predictive validation

In the paper Controlling Garbage Collection and Request Admission to Improve Performance of FaaS Applications, we verified and evaluated the impact of memory management mechanics of programming languages in the context of Functions as a Service (FaaS) via simulation experiments. The results of this study pointed to an impact of up to 11.68% on the response time of requests when a garbage collector procedure was executed during the execution of a CPU-bound function. As future work, we listed a few threats to the validity of the results attained, and among them, we cited the validation of the simulation model used. The validation of the model is important because it validates the results generated in the simulation experiments, which ensures realistic results. In this work, we proposed and executed a validation to the simulation model used in the previous work. To do so, we run measurement experiments in a public FaaS platform and simulation experiments of the same scenarios using the same simulator of the previous paper. Then, we validate the simulator by comparing the results obtained in both experiments to ensure that the simulation result and the measurement one are equivalent.

cs.DC↗

arXiv2021

Performance Evaluation of Snapshot Methods to Warm the Serverless Cold Start

The serverless computing model strengthens the cloud computing tendency to abstract resource management. Serverless platforms are responsible for deploying and scaling the developer's applications. Serverless also incorporated the pay-as-you-go billing model, which only considers the time spent processing client requests. Such a decision created a natural incentive for improving the platform's efficient resource usage. This search for efficiency can lead to the cold start problem, which represents a delay to execute serverless applications. Among the solutions proposed to deal with the cold start, those based on the snapshot method stand out. Despite the rich exploration of the technique, there is a lack of research that evaluates the solution's trade-offs. In this direction, this work compares two solutions to mitigate the cold start: Prebaking and SEUSS. We analyzed the solution's performance with functions of different levels of complexity: NoOp, a function that renders Markdown to HTML, and a function that loads 41 MB of dependencies. Preliminary results indicated that Prebaking showed a 33% and 25% superior performance to startup the NoOp and Markdown functions, respectively. Further analysis also revealed that Prebaking's warmup mechanism reduced the Markdown first request processing time by 69%.

cs.DC↗

arXiv2019

Characterising Volunteers' Task Execution Patterns Across Projects on Multi-Project Citizen Science Platforms

Citizen science projects engage people in activities that are part of a scientific research effort. On multi-project citizen science platforms, scientists can create projects consisting of tasks. Volunteers, in turn, participate in executing the project's tasks. Such type of platforms seeks to connect volunteers and scientists' projects, adding value to both. However, little is known about volunteer's cross-project engagement patterns and the benefits of such patterns for scientists and volunteers. This work proposes a Goal, Question, and Metric (GQM) approach to analyse volunteers' cross-project task execution patterns and employs the Semiotic Inspection Method (SIM) to analyse the communicability of the platform's cross-project features. In doing so, it investigates what are the features of platforms to foster volunteers' cross-project engagement, to what extent multi-project platforms facilitate the attraction of volunteers to perform tasks in new projects, and to what extent multi-project participation increases engagement on the platforms. Results from analyses on real platforms show that volunteers tend to explore multiple projects, but they perform tasks regularly in just a few of them; few projects attract much attention from volunteers; volunteers recruited from other projects on the platform tend to get more engaged than those recruited outside the platform. System inspection shows that platforms still lack personalised and explainable recommendations of projects and tasks. The findings are translated into useful claims about how to design and manage multi-project platforms.

cs.HC↗