Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

VM deploy issue #458

Open
NeqTarine opened this issue Oct 28, 2024 · 2 comments
Open

VM deploy issue #458

NeqTarine opened this issue Oct 28, 2024 · 2 comments
Labels
bug Something isn't working

Comments

@NeqTarine
Copy link

Version TalosOS : 1.8.1
Version Cozystack : 17.1

Trying to deploy a VM (simple) from the dashboard, the VM blocks on a step that prevents the deployment. The deployment hangs when there's a Pod called “import prime” that doesn't seem to be able to import the ubuntu image.

All PV/PVC/Service are created.
Capture d’écran 2024-10-28 à 13 30 54

Capture d’écran 2024-10-28 à 13 31 06

Do you have idea ?

Thanks

@dosubot dosubot bot added the bug Something isn't working label Oct 28, 2024
Copy link

dosubot bot commented Oct 28, 2024

Hello, @NeqTarine! I'm here to help you with any bugs, questions, or contributions. Let's tackle this issue together!

The issue you're encountering with the "import prime" pod failing due to a "Permission denied" error on /dev/cdi-block-volume suggests that there might be a problem with the permissions or security context settings for the pod. Here are a few steps you can take to troubleshoot and potentially resolve the issue:

  1. Check Security Contexts: Ensure that the pod's security context allows access to the necessary devices. You might need to adjust the securityContext settings in your pod specification to allow access to /dev/cdi-block-volume.

  2. Verify Permissions: Double-check the permissions on /dev/cdi-block-volume to ensure that the user or service account running the pod has the necessary permissions to access this device.

  3. Pod Logs and Events: Review the logs of the "importer-prime" pod for any additional error messages that might provide more context. Also, check the events associated with the pod to see if there are any clues about why the container is failing to start.

  4. Back-off Restarting Issue: The "Back-off restarting failed container" message indicates that Kubernetes is trying to restart the container but is encountering repeated failures. This is often related to the initial permission issue, so resolving the permission error should help address this as well.

If these steps do not resolve the issue, you may need to delve deeper into the configuration of your Cozystack environment or consult additional documentation specific to the containerized data importer you're using.

To continue talking to Dosu, mention @dosu.

@kvaps
Copy link
Member

kvaps commented Oct 29, 2024

Hey @NeqTarine thank you fo report, do you have:

  files:
  - content: |
      [plugins]
        [plugins."io.containerd.grpc.v1.cri"]
          device_ownership_from_security_context = true
        [plugins."io.containerd.cri.v1.runtime"]
          device_ownership_from_security_context = true      
    path: /etc/cri/conf.d/20-customization.part
    op: create

In your Talos configuration?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants