Skip to content

[dcgm-exporter] Add option hostNetwork for dcgmExporter#1545

Closed
Alja9 wants to merge 4 commits intoNVIDIA:mainfrom
Alja9:hostnetwork
Closed

[dcgm-exporter] Add option hostNetwork for dcgmExporter#1545
Alja9 wants to merge 4 commits intoNVIDIA:mainfrom
Alja9:hostnetwork

Conversation

@Alja9
Copy link

@Alja9 Alja9 commented Jul 20, 2025

Is it possible to add the hostNetwork option to the dcgm-exporter via gpu-operator ?
because the dcgm-exporter itself already provides that option :
https://github.com/NVIDIA/dcgm-exporter/blob/8fd69339fe2138459d3618508c3ebb1f43b51f79/deployment/templates/daemonset.yaml#L49-L50

Why is this necessary? because the label on the dcgm-exporter metrics does not have a node label to display the node name, while the label provided by the dcgm-exporter that is possible to display the node name is only hostname (can use node name or pod name).

And I think this is useful for monitoring tools that require access to node-level network interfaces or need to expose ports directly on the node. And actually I want the dcgm-exporter to use the node IP as the pod IP instead of assigning its own IP or new IP (this helps to use node ip on value instance label).

And also it seems there is a request for this feature in the issue : #1086

Signed-off-by: aldi.j <aldi.jayadi222@gmail.com>
@copy-pr-bot
Copy link

copy-pr-bot bot commented Jul 20, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

Alja9 added 3 commits July 20, 2025 21:27
Signed-off-by: aldi.j <aldi.jayadi222@gmail.com>
Signed-off-by: aldi.j <aldi.jayadi222@gmail.com>
Signed-off-by: aldi.j <aldi.jayadi222@gmail.com>
@elezar elezar removed their request for review October 15, 2025 13:52
@github-actions
Copy link
Contributor

This PR is stale because it has been open 90 days with no activity. This PR will be closed in 30 days unless new comments are made or the stale label is removed. To skip these checks, apply the "lifecycle/frozen" label.

@github-actions github-actions bot added the lifecycle/stale Denotes an issue or PR has remained open with no activity and has become stale. label Feb 20, 2026
@rahulait rahulait removed the lifecycle/stale Denotes an issue or PR has remained open with no activity and has become stale. label Feb 23, 2026
@tariq1890
Copy link
Contributor

@Alja9 Thank you for creating this PR and we apologise for missing this earlier. It looks like this PR #1962 has already been merged with the same changes.

We appreciate you taking the time to contribute to gpu-operator!

@tariq1890 tariq1890 closed this Feb 27, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants