Implications of Programming Language Selection for Serverless Data Processing Pipelines

Streaming vs. Functions: A Cost Perspective on Cloud Event Processing

“…To quantify the effect of runtime choice, we implement our benchmark in Node.js and Go. Node.js is one of the most popular choices for cloud functions, while Go is the only programming language supported by Google Cloud Functions that is compiled directly to machine code and may thus have the smallest performance overhead [33].…”

The Serverless Application Analytics Framework

“…In this section we detail three serverless case studies enabled by SAAF: (1) an image processing pipeline, (2) a data processing pipeline with implementations in four different programming languages to contrast performance implications [23], and (3) random compute-bound workloads used to develop and refine serverless performance models using Linux time accounting principles [13].…”

“…In our paper: "Implications of Programming Language Selection for Serverless Data Processing Pipelines" [23], we developed four identical Transform-Load-Query pipelines in Java, Python, Go, and Node.js and compared the performance of each language on AWS Lambda. Using SAAF we profiled each language using Linux Time Accounting metrics.…”

Fusionize: Improving Serverless Application Performance through Feedback-Driven Function Fusion

“…FaaS is a popular paradigm for cloud software development and deployment in which developers write their source code in the form of small, stateless functions 3 and leave all operations aspects to the cloud provider. These functions are usually written in highlevel programming languages such as Node.js [10]. At runtime, the cloud provider routes incoming requests or events to an instance of the corresponding function -either to a newly created one thus incurring the socalled cold start latency [8,11] or reusing an existing one.…”