This course aims to explore the reproducibility of big data performance in modern cloud networks. The learning outcomes include understanding the impact of variability on cloud-based big data workloads, characterizing network variability, and providing guidelines to enhance the repeatability of experiments. The course teaches skills such as assessing performance in the cloud, measuring network variability, and running repeatable experiments. The teaching method involves presenting research findings and guidelines based on data gathered from commercial and private cloud networks. The intended audience for this course includes cloud practitioners, performance engineers, and researchers interested in big data workloads and cloud network performance.
Leave a Reply