Roshan Bhandari is a Masters student studying Computer Science at Clemson University in the USA.
Roshan's project involved creating utilities to estimate the money saved by running HPCC Systems in spot instances in different regions in the Azure cloud, as well as developing scripts to automate cluster formation in Azure Kubernetes Service (AKS). Another important task of this project involves developing strategies for job recovery after eviction and cleaning after an eviction notice. Since minimizing the cost of setting up cloud infrastructure is very important for all companies, this project provides some valuable insights to share with our users as they adopt HPCC Systems Cloud Native.
As well as the resources included here, read Roshan's intern blog journal which includes a more in depth look of his work.
Minimizing the cost of setting up cloud infrastructure is very important for all companies. Azure spot instances can provide great cost savings for cloud infrastructure setup. Azure Spot Instances are unused computing resources (virtual machines) azure has. Azure gives it for a lower price compared to normal virtual machines. It is found that Azure gives these instances at a rate that can be as low as 90% below the normal instance. The price can vary based on region and size. These spot instances do not have any service level agreement and Azure does not provide any high availability guarantee for these instances. Azure also takes the machines whenever they need it with or without notice.
In this project, we try to analyze different aspects related to the use of Azure Spot Instance with HPCC Systems.
In this Video Recording, Roshan provides a tour and explanation of his poster content.
Use Azure Spot Instance with HPCC Systems for Cost Optimization
Click on the poster for a larger image.