Analyzing DevOps Practices Through Merge Request Data: A Case Study in Networking Software Company

2025-03-18

AI Summary

This study investigates the evolution of collaboration patterns, productivity, and process efficiency in DevOps practices at a network software company, using a dataset of 267,000 merge requests (MRs). Employing quantitative analysis, temporal modeling, and cross-team comparison, we examine MR metadata—including branch type, reviewer experience, commit frequency—and temporal activity distributions. Our key contributions are: (1) empirical evidence that team collaboration resilience manifests as 70% of MR activity shifting to off-hours; (2) identification of stable branches’ consistently higher priority management during release cycles; and (3) demonstration that automated reviewers accelerate initial reviews, yet human reviewers remain critical for optimizing end-to-end latency. We further find that the pandemic prolonged review duration without reducing overall productivity, and that metrics gradually converged post-OpenShift migration. Based on these findings, we propose actionable, empirically grounded MR workflow optimization strategies.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Evaluation and Analysis
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Data transparency and provenance

Abstract

DevOps integrates collaboration, automation, and continuous improvement, enhancing agility, reducing time to market, and ensuring consistent software releases. A key component of this process is GitLab's Merge Request (MR) mechanism, which streamlines code submission and review. Studies have extensively analyzed MR data and similar mechanisms like GitHub pull requests and Gerrit Code Review, focusing on metrics such as review completion time and time to first comment. However, MR data also reflects broader aspects, including collaboration patterns, productivity, and process optimization. This study examines 26.7k MRs from four teams across 116 projects of a networking software company to analyze DevOps processes. We first assess the impact of external factors like COVID-19 and internal changes such as migration to OpenShift. Findings show increased effort and longer MR review times during the pandemic, with stable productivity and a lasting shift to out-of-hours work, reaching 70% of weekly activities. The transition to OpenShift was successful, with stabilized metrics over time. Additionally, we identify prioritization patterns in branch management, particularly in stable branches for new releases, underscoring the importance of workflow efficiency. In code review, while bots accelerate review initiation, human reviewers remain crucial in reducing review completion time. Other factors, such as commit count and reviewer experience, also influence review efficiency. This research provides actionable insights for practitioners, demonstrating how MR data can enhance productivity, effort analysis, and overall efficiency in DevOps.

Problem

• Analyzes DevOps practices using Merge Request data
• Examines impact of COVID-19 and OpenShift migration
• Identifies factors influencing code review efficiency

Innovation

• Analyzed 26.7k Merge Requests for DevOps insights
• Assessed COVID-19 impact on MR review times
• Identified workflow efficiency in branch management