request bare metal kubernetes cluster for PEAKS project #259
Description
Please fill out the details below to file a request for access to the CNCF Community Infrastructure Lab. Please note that access is targeted to people working on specific open source projects; this is not designed just to get your feet wet. The most important answer is the URL of the project you'll be working with.
If you're looking to learn Kubernetes and related technologies, please try out Killercoda or Play With Kubernetes instead.
First and Last Name
Krishnasuri Narayanam
Company/Organization
IBM Research, India
Job Title
Senior Research Engineer
Project Title (i.e., a summary of what do you want to do, not what is the name of the open source project you're working with)
Evaluate the amount of savings in power consumption to execute a workload by using PEAKS kubernetes scheduler-plugin vs. the default kubernetes scheduler
Briefly describe the project (i.e., what are the details of what you're planning to do with these servers?)
We want to create a three node bare-metal k8s cluster. Then we want to run workload using the default k8s scheduler and measure the power consumption (using node utilization metrics collected from Metrics Server and energy consumption metrics collected using Kepler). Later we want to run the same workload using PEAKS k8s scheduler-plugin to schedule the workload pod on the cluster nodes and measure the power consumption. The amount of power consumption using PEAKS k8s scheduler-plugin should be less (leading to saving in power consumption). PEAKS plugin achieves this saving in power consumption as it tries to choose more power efficient nodes for pod placement at any time.
Is the code that you're going to run 100% open source? If so, what is the URL or URLs where it is located? What is your association with that project?
Yes, the code that we are going to run is 100% open source. URL: https://github.com/sustainable-computing-io/peaks/ and https://github.com/sustainable-computing-io/scheduler-plugins/tree/master/pkg/peaks
What kind of machines and how many do you expect to use (see: https://deploy.equinix.com/product/bare-metal/servers/)?
What operating system and networking are you planning to use?
Prefer RHEL 9 or CentOS stream 9 but open to other alternatives
Any other relevant details we should know about?
This issue is tracked in PEAKS: sustainable-computing-io/peaks#42