Kubernetes includes experimental support for managing NVIDIA GPUs spread across nodes. The support for NVIDIA GPUs was added in v1.6 and has gone through multiple backwards incompatible iterations. This page describes how users can consume GPUs across different Kubernetes versions and the current limitations.
From 1.8 onwards, the recommended way to consume GPUs is to use device plugins.
To enable GPU support through device plugins before 1.10, the
feature gate has to be explicitly set to true across the system:
--feature-gates="DevicePlugins=true". This is no longer required starting
Then you have to install NVIDIA drivers on the nodes and run an NVIDIA GPU device plugin (see below).
When the above conditions are true, Kubernetes will expose
a schedulable resource.
You can consume these GPUs from your containers by requesting
nvidia.com/gpu just like you request
However, there are some limitations in how you specify the resource requirements
when using GPUs:
- GPUs are only supposed to be specified in the
limits section, which means:
* You can specify GPU
limits without specifying
Kubernetes will use the limit as the request value by default.
* You can specify GPU in both
requests but these two values
must be equal.
* You cannot specify GPU
requests without specifying
- Containers (and pods) do not share GPUs. There’s no overcommitting of GPUs.
- Each container can request one or more GPUs. It is not possible to request a
fraction of a GPU.
Here’s an example:
apiVersion: v1 kind: Pod metadata: name: cuda-vector-add spec: restartPolicy: OnFailure containers: - name: cuda-vector-add # https://github.com/kubernetes/kubernetes/blob/v1.7.11/test/images/nvidia-cuda/Dockerfile image: "k8s.gcr.io/cuda-vector-add:v0.1" resources: limits: nvidia.com/gpu: 1 # requesting 1 GPU
There are currently two device plugin implementations for NVIDIA GPUs:
The official NVIDIA GPU device plugin has the following requirements: - Kubernetes nodes have to be pre-installed with NVIDIA drivers. - Kubernetes nodes have to be pre-installed with nvidia-docker 2.0 - nvidia-container-runtime must be configured as the default runtime for docker instead of runc. - NVIDIA drivers ~= 361.93
To deploy the NVIDIA device plugin once your cluster is running and the above requirements are satisfied:
# For Kubernetes v1.8 kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v1.8/nvidia-device-plugin.yml # For Kubernetes v1.9 kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v1.9/nvidia-device-plugin.yml
Report issues with this device plugin to NVIDIA/k8s-device-plugin.
The NVIDIA GPU device plugin used by GKE/GCE doesn’t require using nvidia-docker and should work with any container runtime that is compatible with the Kubernetes Container Runtime Interface (CRI). It’s tested on Container-Optimized OS and has experimental code for Ubuntu from 1.9 onwards.
On your 1.9 cluster, you can use the following commands to install the NVIDIA drivers and device plugin:
# Install NVIDIA drivers on Container-Optimized OS: kubectl create -f https://raw.githubusercontent.com/GoogleCloudPlatform/container-engine-accelerators/k8s-1.9/daemonset.yaml # Install NVIDIA drivers on Ubuntu (experimental): kubectl create -f https://raw.githubusercontent.com/GoogleCloudPlatform/container-engine-accelerators/k8s-1.9/nvidia-driver-installer/ubuntu/daemonset.yaml # Install the device plugin: kubectl create -f https://raw.githubusercontent.com/kubernetes/kubernetes/release-1.9/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml
Report issues with this device plugin and installation method to GoogleCloudPlatform/container-engine-accelerators.
If different nodes in your cluster have different types of NVIDIA GPUs, then you can use Node Labels and Node Selectors to schedule pods to appropriate nodes.
# Label your nodes with the accelerator type they have. kubectl label nodes <node-with-k80> accelerator=nvidia-tesla-k80 kubectl label nodes <node-with-p100> accelerator=nvidia-tesla-p100
Specify the GPU type in the pod spec:
apiVersion: v1 kind: Pod metadata: name: cuda-vector-add spec: restartPolicy: OnFailure containers: - name: cuda-vector-add # https://github.com/kubernetes/kubernetes/blob/v1.7.11/test/images/nvidia-cuda/Dockerfile image: "k8s.gcr.io/cuda-vector-add:v0.1" resources: limits: nvidia.com/gpu: 1 nodeSelector: accelerator: nvidia-tesla-p100 # or nvidia-tesla-k80 etc.
This will ensure that the pod will be scheduled to a node that has the GPU type you specified.