Skip vfio-pci unbind when GPUs already bound in VFIO mode#146
Closed
karthikvetrivel wants to merge 1 commit intoNVIDIA:mainfrom
Closed
Skip vfio-pci unbind when GPUs already bound in VFIO mode#146karthikvetrivel wants to merge 1 commit intoNVIDIA:mainfrom
karthikvetrivel wants to merge 1 commit intoNVIDIA:mainfrom
Conversation
cdesiniotis
reviewed
Jan 29, 2026
Signed-off-by: Karthik Vetrivel <kvetrivel@nvidia.com>
karthikvetrivel
force-pushed
the
fix/skip-vfio-unbind-when-already-bound
branch
from
750db0f to
263b723
Compare
Member
Author
|
What do you think about this approach? Are there any scenarios where the workload config is |
5 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Relevant PR: NVIDIA/gpu-operator#2079
Description
Prevents unnecessary GPU unbind/rebind operations during rolling updates of the vfio-manager DaemonSet. Currently, k8s-driver-manager unconditionally unbinds all GPUs from vfio-pci on startup, even when the desired state is already vfio-pci. This disrupts active VM workloads using GPU passthrough (KubeVirt, Kata Containers).
Solution
Check for
GPU_WORKLOAD_CONFIGenvironment variable to determine if the pod is running in VFIO workload mode. When set tovm-passthrough, skip the vfio-pci unbind operation since GPUs should remain bound to vfio-pci.Behavior by DaemonSet Context
GPU_WORKLOAD_CONFIGvm-passthrough