With the Cloud buzz all around us, whether deploying microservices or traditional applications, scaling applications, going serverless and more, there are challenges to be solved at all layers (Hardware, Container, Runtime, App Server, Application). And it is important to tune each layer to achieve improved performance with cost benefits
In this talk, we will walk you through:
- Challenges in tuning your application at different layers
- Understanding performance tunables for each layer and best practices to tune them
- Leveraging ML/Hyperparameter Optimizations (HPO) to achieve optimal application performance for a user defined Service Level Objective (such as High throughput/Low response time/Optimal resource usage, etc.)
- Performance and cost benefits observed from our experiments using HPO techniques
Objective of the presentation:
This presentation is intended to show case usage of Hyper parameter optimization to improve application performance during runtime.
Attendee pre-requisites - If none, enter "N/A":
N/A