Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Metrics identification and collection #23

Open
knarayan opened this issue Nov 3, 2023 · 1 comment
Open

Metrics identification and collection #23

knarayan opened this issue Nov 3, 2023 · 1 comment
Labels
Power modeling Node utilization vs. power model training

Comments

@knarayan
Copy link
Collaborator

knarayan commented Nov 3, 2023 •
edited
Loading

Identify the specific metrics to be used for the node CPU utilization vs. power modeling, and find ways to collect those metrics.
@knarayan knarayan added the Power modeling Node utilization vs. power model training label Nov 3, 2023
@husky-parul
Copy link
Collaborator

husky-parul commented Nov 6, 2023 •
edited
Loading

Nov 6

Currently we are getting constant metric values from Kepler.

  • Use the latest Kepler image to see if utilization and power changes
  • Modify workloads

Metrics we are collecting right now

  1. Node:
    For CPU utilization node_cpu_seconds_total (from kube metrics)
    For Power kepler_node_package_joules_total (from kepler)

For Kepler we were seeing power metrics from only one node. Also we are only getting RAPL power. We do not see other power metrics from Kepler.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Power modeling Node utilization vs. power model training
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@knarayan @husky-parul