Performance testing is a critical component of the modern software development lifecycle. It ensures application stability under typical workloads and resilience during anomalous conditions. Due to its time-consuming nature, performance testing is often integrated into DevOps CI/CD pipelines to accelerate software delivery and reduce testing delays. While prior research has examined the integration of performance testing into CI/CD, the effect of the testing tools themselves on pipeline performance remains largely unexplored. In this study, we evaluate the impact of five widely-used open-source performance testing tools—Apache Jmeter, Grafana K6, Gatling, Locust, and Artillery—when integrated into a Jenkins-based CI/CD pipeline for a Spring Boot Java application. We designed and executed automated in-pipeline tests using three common load testing methodologies: representative load, maximum load, and spike load. During these tests, we measured both system-level metrics (CPU and RAM usage) and business-level metrics (response time). To assess the significance of observed differences, we applied two non-parametric statistical methods: the Kruskal-Wallis test and the Mann-Whitney U test with Bonferroni correction. Our analysis confirms that the differences in performance metrics across tools are statistically significant (p-values \(\le 0.05\) ). Among the tested tools, Grafana K6 consistently demonstrated the highest resource efficiency across all testing scenarios. This work contributes (i) a comparative analysis of performance testing tools in a CI/CD context, (ii) an automated pipeline framework for load testing with real-time monitoring, and (iii) practical recommendations for selecting the most appropriate tool based on efficiency and usability.