What is it about?
Description of a performance analysis of a patient status prediction function when running at different types of clusters. The analysis indicates how much time the function takes to execute in each cluster, depending on the load and characteristics of the cluster.
Featured Image
Photo by Stephen Dawson on Unsplash
Why is it important?
The analyzed delay is broken down to different parts, such as network latency, wait time in the system, initialization and execution time. Furthermore, reasons for this delay are explained based on the characteristics of each cluster. By knowing these aspects, the customer can select at any time the best location for execution, while the cluster provider can optimize the setup of their infrastructure.
Read the Original
This page is a summary of: Performance Experiences From Running An E-health Inference Process As FaaS Across Diverse Clusters, April 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3578245.3585023.
You can read the full text:
Resources
Contributors
The following have contributed to this page
