Publication Date

Spring 2024

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Robert Chun

Second Advisor

Navrati Saxena

Third Advisor

Anuj Sharma

Keywords

Distributed Computing, Infrastructure Design, Kubernetes, MapReduce, Parallel Processing, Performance Optimization.

Abstract

The combination of MapReduce (MR) & Kubernetes (K8s) strengths is not explored, and this study leverages the synergy between the two frameworks to meet the growing demands of data-intensive applications. First, this report elaborates on the existing literature work to understand the pros and cons of using MR and K8s, in what use cases these frameworks come to use, and investigates the effectiveness of research studies that explore the combination. This study aims to research the efficacy of the fusion of MR and K8s, considering these factors - application use case, infrastructure design, resource allocation, load balancing, and hypertuning parameters that could accelerate the performance gains. Through comprehensive experimentation, this report provides insights as proof of concept serving as a starting point for architectural design development. It offers a concise understanding of what to expect when integrating MR and K8s, and how performance gains can be achieved.

Download

Available for download on Thursday, May 22, 2025

Share

COinS