Serverless Computing: Behind the Scenes of Major Platforms

TL;DR

This paper investigates the architecture and performance of major serverless platforms, analyzing factors like cold starts, interference, and underlying infrastructure to understand their operational differences and challenges.

Contribution

It uncovers the hidden architecture of serverless functions and compares platform behaviors, providing insights into performance issues like cold starts and load interference.

Findings

Differences in cold start handling across platforms

Impact of load interference on function latency

Method to reveal underlying serverless architecture

Abstract

Serverless computing offers an event driven pay-as-you-go framework for application development. A key selling point is the concept of no back-end server management, allowing developers to focus on application functionality. This is achieved through severe abstraction of the underlying architecture the functions run on. We examine the underlying architecture and report on the performance of serverless functions and how they are effected by certain factors such as memory allocation and interference caused by load induced by other users on the platform. Specifically, we focus on the serverless offerings of the four largest platforms; AWS Lambda, Google Cloud Functions, Microsoft Azure Functions and IBM Cloud Functions}. In this paper, we observe and contrast between these platforms in their approach to the common issue of "cold starts", we devise a means to unveil the underlying architecture serverless functions execute on and we investigate the effects of interference from load on the platform over the time span of one month.