Metric kepler_container_bpf_net_tx_irq_total showing as zero

[emoek]

trafficstars

What happened?

The metric "kepler_container_bpf_net_tx_irq_total" only shows "zero" for all containers and pods.

What did you expect to happen?

I expected non-zero values similarly to the network transmit metric provided by cAdvisor as visible in the figure.

How can we reproduce it (as minimally and precisely as possible)?

I guess just install the below specified Helm version of Kepler and test it out.

Anything else we need to know?

The receive metrics net_rx_irq works as expected, or more precisely everything else works as expected.

Kepler image tag

Kubernetes version

$ kubectl version
# Server Version: v1.25.6

Cloud provider or bare metal

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

Helm Chart Version 0.5.5 - release-0.7.2

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)

[rootfs]

@emoek can you provide more info? what is the kepler image you are using, what is the OS platform, do you have access to the kepler container logs?

[emoek]

I only have limited access to the cluster as its a private cluster but I will try to get as many informations as I can get. In the image you can see the log output the last time I had access to them. It seems to be that the Kepler version is "c1cae95" and the kernel version "5.1" on an Debian/Ubuntu server.