Performance Evaluation of Stateful Serverless Computing using Stream Processing

Medhane, Abhishek Jaipal (2023) Performance Evaluation of Stateful Serverless Computing using Stream Processing. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration manual) Download (755kB) | Preview

Abstract

In the evolving landscape of cloud-native technologies, serverless Function as a Service (FaaS) platforms are gaining significant traction. In the field of real-time streaming, it is becoming important to process such big data as the use cases are increasing, ranging from IoT, smart devices, and e-commerce, hence a need for storage and query optimization techniques. In this research work, we delve into the advantages of stateless serverless computing that retains state across real-time streaming invocations. Our objective is to gauge its efficacy in executing complex stateful tasks. Through a comprehensive, measurement-driven analysis focused on real-time streaming, we assess various performance, latency, and throughput metrics. This research focuses on the construction and deployment of Kafka streams and the development of a stateful serverless function in Apache Flink. We aim to design modular stateful functions and migrate them to diverse databases on a unified platform, facilitating efficient storage and latency measurements via diverse deployment strategies, as opposed to local storage. Also, significant work has been done to propose a novel approach and compare the stateful operations using Flink’s Python Table APIs.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Heeney, Sean UNSPECIFIED
Uncontrolled Keywords:	serverless; FaaS; stateful; streaming; latency; Flink; Kakfa
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	09 Oct 2024 18:02
Last Modified:	09 Oct 2024 18:02
URI:	https://norma.ncirl.ie/id/eprint/7090

Actions (login required)

View Item