A comparison of Azure’s Function-as-a-Service and Infrastructure-as-a-Service solutions

Sammanfattning: Cloud computing is a growing industry. More and more companies are moving away from on-premise infrastructure. Instead, the choice is often to build their systems based on cloud services. This growth in the industry has brought with it new needs and consequently, new solutions. There have never existed as many different cloud providers and services offered by these providers. One of the newer paradigms in this industry is the serverless approach. The problem of this thesis is that there is a lack of research into how Azure's serverless Function-as-a-Service offering compare to their more traditional Infrastructure-as-a-Service one. Therefore, the purpose of this work is to compare the two with regards to their performance, cost, and required developer effort. The goal is to provide a comparison that can help software professionals in choosing an appropriate cloud solution for their application. Additionally, it aims to contribute to the increased knowledge of modern serverless solutions while providing a basis for future research. A qualitative method supported by measurements is used. The two cloud solutions are compared with regards to their performance, cost and developer effort. This is done by implementing and deploying equivalent Representational State Transfer applications with the two Azure offerings. The two implementations are stress-tested to measure their performance, and their incurred costs are compared. Additionally, the effort involved in developing the two solutions is compared by studying the amount of time required to deploy them, and the amount of code needed for them. The results show that the serverless Function-as-a-Service solution performed worse under the types of high loads used in the study. The incurred costs for the performed tests were higher for the serverless option, while the developer effort involved was lower. Additionally, further testing showed that the performance of the Function-as-a-Service solution was highly dependent on the concept of cold starts.