Kepler (Kubernetes-based Efficient Power Level Exporter) uses eBPF to probe performance counters and other system stats, use ML models to estimate workload energy consumption based on these stats, and exports them as Prometheus metrics
When Kepler using v0.7.12 and latest is deployed independently on a BM and stress is applied to the machine Kepler using latest reports inconsistent values where as Kepler using v0.7.12 always reports consistent values
Attaching screenshot for reference:
When Kepler v0.7.12 is deployed:
When Kepler using latest code base is deployed:
What did you expect to happen?
Kepler process shouldn't deviate much from the stable release
How can we reproduce it (as minimally and precisely as possible)?
Checkout v0.7.12 code base and latest code base separately
Deploy Kepler using dev compose manifests
Compare kepler_process_<pkg|core|dram|other>_joules_total between dev and latest. Note: Dev and latest will point to the same Kepler version
Anything else we need to know?
No response
Kepler image tag
v0.7.12, latest
Kubernetes version
```console
$ kubectl version
# paste output here
```
Cloud provider or bare metal
BM
OS version
```console
# 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:
```console
$ 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)
What happened?
When Kepler using v0.7.12 and latest is deployed independently on a BM and stress is applied to the machine Kepler using latest reports inconsistent values where as Kepler using v0.7.12 always reports consistent values
Attaching screenshot for reference: When Kepler v0.7.12 is deployed:
When Kepler using latest code base is deployed:
What did you expect to happen?
Kepler process shouldn't deviate much from the stable release
How can we reproduce it (as minimally and precisely as possible)?
kepler_process_<pkg|core|dram|other>_joules_totalbetween dev and latest. Note: Dev and latest will point to the same Kepler versionAnything else we need to know?
No response
Kepler image tag
Kubernetes version
Cloud provider or bare metal
OS version
Install tools
Kepler deployment config
Container runtime (CRI) and version (if applicable)
Related plugins (CNI, CSI, ...) and versions (if applicable)