Scholarlink

<p>Cloud-native applications leverages cloud environments for enhanced scalability, resilience, and agility. Using containerization technologies like Docker enables modular deployments. Despite their advantages, effectively evaluating the performance of these dynamic and distributed applications presents challenges. Cloud-native application performance is complex because diverse metrics–including response times, throughput, and resource utilization–are used across varied workloads. Organizations face hurdles in selecting appropriate evaluation tools, defining specific objectives, and gaining insights into microservices and orchestration. A more structured approach is essential to optimizing deployments and meeting performance expectations in cloud-native environments. This paper presents a systematic mapping study that examined 1158 initial papers and refined them to 32 primary studies. It meticulously analyzes key metrics, software tools, objectives, and contributions related to performance evaluation in cloud-native applications. Visual representations with bubble plots were used as cross-correlation analysis, revealing patterns and research gaps. This study provides insights that guide future research directions, advocating for methodological frameworks to enhance the assessment and optimization of cloud-native application performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Performance Evaluation of Cloud Native Applications: A Systematic Mapping Study

  • 期刊论文

  • 发表日期：

    2025年6月30日

查看全文
  • Francisco Airton Silva,
  • Fernando A. M. Trinta,
  • Michel S. Bonfim,
  • José Antonio F. de Macedo,
  • Paulo A. L. Rego,
  • Vinícius Lagrota

摘要

Cloud-native applications leverages cloud environments for enhanced scalability, resilience, and agility. Using containerization technologies like Docker enables modular deployments. Despite their advantages, effectively evaluating the performance of these dynamic and distributed applications presents challenges. Cloud-native application performance is complex because diverse metrics–including response times, throughput, and resource utilization–are used across varied workloads. Organizations face hurdles in selecting appropriate evaluation tools, defining specific objectives, and gaining insights into microservices and orchestration. A more structured approach is essential to optimizing deployments and meeting performance expectations in cloud-native environments. This paper presents a systematic mapping study that examined 1158 initial papers and refined them to 32 primary studies. It meticulously analyzes key metrics, software tools, objectives, and contributions related to performance evaluation in cloud-native applications. Visual representations with bubble plots were used as cross-correlation analysis, revealing patterns and research gaps. This study provides insights that guide future research directions, advocating for methodological frameworks to enhance the assessment and optimization of cloud-native application performance.