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

introduced known issues section for pcidevices controller #675

Merged
merged 3 commits into from
Nov 27, 2024
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docs/advanced/addons/pcidevices.md
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,12 @@ Boot the VM up, and run `lspci` inside the VM, the attached PCI devices will sho

This is just like installing drivers in the host. The PCI passthrough feature will bind the host device to the `vfio-pci` driver, which gives VMs the ability to use their own drivers. [Here is a screenshot](https://tobilehman.com/posts/suse-harvester-pci/#toc) of NVIDIA drivers being installed in a VM. It includes a CUDA example that proves that the device drivers work.

## Known Issues
* [issue-6648](https://github.com/harvester/harvester/issues/6648): In a cluster with multiple instances of the same device, it is possible for a VM to be scheduled to an incorrect node.

The current implementation of the addon, publishes each device using a unique resource descriptor to the kubelet. If multiple `PCIDeviceClaims` of same device type exist within the cluster, the VM may be scheduled to an incorrect node as the unique resource descriptor will be same for all similar devices. To ensure device from the correct node is used, please use the `VM Scheduling` section and use `Run VM on specific node(s)`
![](/img/v1.4/vm/vm-scheduling.png)
ibrokethecloud marked this conversation as resolved.
Show resolved Hide resolved

## SRIOV Network Devices
_Available as of v1.2.0_

Expand Down
Binary file added static/img/v1.4/vm/vm-scheduling.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
6 changes: 6 additions & 0 deletions versioned_docs/version-v1.3/advanced/addons/pcidevices.md
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,12 @@ Boot the VM up, and run `lspci` inside the VM, the attached PCI devices will sho

This is just like installing drivers in the host. The PCI passthrough feature will bind the host device to the `vfio-pci` driver, which gives VMs the ability to use their own drivers. [Here is a screenshot](https://tobilehman.com/posts/suse-harvester-pci/#toc) of NVIDIA drivers being installed in a VM. It includes a CUDA example that proves that the device drivers work.

## Known Issues
* [issue-6648](https://github.com/harvester/harvester/issues/6648): In a cluster with multiple instances of the same device, it is possible for a VM to be scheduled to an incorrect node.

The current implementation of the addon, publishes each device using a unique resource descriptor to the kubelet. If multiple `PCIDeviceClaims` of same device type exist within the cluster, the VM may be scheduled to an incorrect node as the unique resource descriptor will be same for all similar devices. To ensure device from the correct node is used, please use the `VM Scheduling` section and use `Run VM on specific node(s)`
![](/img/v1.4/vm/vm-scheduling.png)

## SRIOV Network Devices
_Available as of v1.2.0_

Expand Down