sustainable-computing-io
Inconsistent values for core and platform metrics at idle state
What happened?
I used kepler to measure energy/power of Kubernetes cluster deployed on VMs, hosted on an Intel server. Currently ithe server doesnot have iDRAC or ACPI support. I measured these metrices: kepler_container_joules_total kepler_container_core_joules_total kepler_container_platform_joules_total kepler_node_core_joules_total kepler_node_platform_joules_total So according to the definition, node platform metric is a reflection of source power, but in idle state it is lesser than core metrics like kepler_container_core_joules_total. May you better draw conclusion from the output snapshot attached: Specific to this example, how come kepler_container_platform_joules_total is 83W in idle state whereas kepler_container_core_joules_total is 147.
What did you expect to happen?
How is kepler_container_platform_joules_total is related to kepler_container_joules_total? Because in idle state they are not equal, although they are same in magnitude during loading.
How can we reproduce it (as minimally and precisely as possible)?
Simply deploy kepler on an VM (kunbernetes node) and observe the metrics at idle and load state
Anything else we need to know?
NA
Kepler image tag
Kubernetes version
$ kubectl version
# paste output here
Cloud provider or bare metal
OS version
# On Linux:
$ cat /etc/os-release
# paste output here
$ uname -a
# paste output here
# On Windows:
C:\> wmic os get Caption, Version, BuildNumber, OSArchitecture
# paste output here
Install tools
Kepler deployment config
For on kubernetes:
$ KEPLER_NAMESPACE=kepler
# provide kepler configmap
$ kubectl get configmap kepler-cfm -n ${KEPLER_NAMESPACE}
# paste output here
# provide kepler deployment description
$ kubectl describe deployment kepler-exporter -n ${KEPLER_NAMESPACE}
For standalone:
put your Kepler command argument here
Container runtime (CRI) and version (if applicable)
Related plugins (CNI, CSI, ...) and versions (if applicable)
@muzakkir6207 since the rewrite of kepler is close to being complete, all new bug fixes and feature requests will be addressed in the reboot branch. If it isn't too much to ask for, could you please test the same using the reboot release - https://github.com/sustainable-computing-io/kepler/releases/tag/v0.0.9-reboot (or higher)
