sustainable-computing-io
update absolute power metrics when cannot determine idle/dynamic power
What happened?
Suppose a Node has ACPI, and from which power values are being read, so we have data for node platform power. But kepler somehow cannot access Rapl, so there is no component power. Which means we do not have resource usage to divide the node power read from ACPI into node platform idle and dynamic power.
which results in kepler_node_platform_joules_total for both idle and dynamic to be zero.
In this case can we raise metrics for absolute power? i.e. kepler_node_platform_joules_total {mode="absolute"}
What did you expect to happen?
raise metrics for absolute power? i.e. kepler_node_platform_joules_total {mode="absolute"}
How can we reproduce it (as minimally and precisely as possible)?
run kepler on a node with either ACPI or Redfish to read node power, and have no access to RAPL, check the kepler_node_platform_joules_total metric
The initial kepler logs should be similar to:
I0729 14:56:17.673625 8260 rapl_msr_util.go:129] failed to open path /dev/cpu/0/msr: no such file or directory
I0729 14:56:17.674109 8260 power.go:72] Unable to obtain power, use estimate method
I0729 14:56:17.673568 8260 config.go:156] EXPOSE_ESTIMATED_IDLE_POWER_METRICS: false. This only impacts when the power is estimated using pre-prained models. Estimated idle power is meaningful only when Kepler is running on bare-metal or with a single virtual machine (VM) on the node.
W0729 14:56:18.037859 8260 exporter.go:299] Failed to open perf event for CPU cycles: failed to open bpf perf event on cpu 0: no such file or directory
Anything else we need to know?
No response
Kepler image tag
Kubernetes version
$ kubectl version
# paste output here
Use baremetal machine
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:
