Fix disabling NVIDIA driver install on Slurm cluster install#948
Merged
ajdecon merged 1 commit intoNVIDIA:masterfrom Jun 16, 2021
Merged
Fix disabling NVIDIA driver install on Slurm cluster install#948ajdecon merged 1 commit intoNVIDIA:masterfrom
ajdecon merged 1 commit intoNVIDIA:masterfrom
Conversation
The Slurm cluster playbook provides the var slurm_cluster_install_nvidia_driver to disable installs of the NVIDIA driver. However, the Slurm cluster playbook also sources the CUDA playbook, which installs the driver itself. And the CUDA playbook does not respect the flag in the Slurm cluster playbook. Aren't dependencies fun? This commit adds a flag to the CUDA playbook to allow disabling the driver install, and plumbs it through so the user can set the flag in the Slurm cluster playbook. To test, set slurm_cluster_install_nvidia_driver to false and set up a Slurm cluster, and the driver should not be installed.
dholt
approved these changes
Jun 16, 2021
Contributor
|
Just a thought, maybe we should remove the driver install from the CUDA playbook? Historically we've tried to make these playbooks work well standalone, but this could be an instance where it's not needed. |
Contributor
Author
I thought about doing that (and would technically prefer that!)... But I'm aware of users who just run the CUDA playbook directly to set up their GPU hosts, and that would break their workflow in an annoying way. Hence this, which is kinda a hack 😛 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The Slurm cluster playbook provides the var
slurm_cluster_install_nvidia_driverto disable installs of the NVIDIA driver. However, the Slurm cluster playbook also sources the CUDA playbook, which installs the driver itself. And the CUDA playbook does not respect the flag in the Slurm cluster playbook.Aren't dependencies fun?
This commit adds a flag to the CUDA playbook to allow disabling the driver install, and plumbs it through so the user can set the flag in the Slurm cluster playbook.
To test, set
slurm_cluster_install_nvidia_driverto false and set up a Slurm cluster, and the driver should not be installed.