Update examples v1

README.md

@@ -83,7 +83,7 @@ Now you can install the DRA driver's Helm chart into the Kubernetes cluster:
 Submit workload:
 
 ```console
-kubectl apply -f ./demo/specs/quickstart/gpu-test2.yaml
+kubectl apply -f ./demo/specs/quickstart/v1/gpu-test2.yaml
 ```
 
 If you're curious, have a look at [the `ResourceClaimTemplate`](https://github.com/jgehrcke/k8s-dra-driver-gpu/blob/526130fbaa3c8f5b1f6dcfd9ef01c9bdd5c229fe/demo/specs/quickstart/gpu-test2.yaml#L12) definition in this spec, and how the corresponding _single_ `ResourceClaim` is [being referenced](https://github.com/jgehrcke/k8s-dra-driver-gpu/blob/526130fbaa3c8f5b1f6dcfd9ef01c9bdd5c229fe/demo/specs/quickstart/gpu-test2.yaml#L46) by both containers.

demo/clusters/kind/scripts/common.sh

@@ -40,7 +40,7 @@ DRIVER_IMAGE_VERSION=$(from_versions_mk "VERSION")
 # From https://github.com/kubernetes/kubernetes/tags
 # See also https://hub.docker.com/r/kindest/node/tags
 : ${KIND_K8S_REPO:="https://github.com/kubernetes/kubernetes.git"}
-: ${KIND_K8S_TAG:="v1.32.0"}
+: ${KIND_K8S_TAG:="v1.34.0"}
 
 # The name of the kind cluster to create
 : ${KIND_CLUSTER_NAME:="${DRIVER_NAME}-cluster"}

demo/specs/quickstart/README.md

@@ -1,4 +1,6 @@
 #### Apply the half-balanced mig-parted config
+
+To enable MIG mode on your GPUs, you can use [nvidia-mig-parted](https://github.com/NVIDIA/mig-parted).
 ```console
 sudo -E nvidia-mig-parted apply -f mig-parted-config.yaml -c half-balanced
 ```
@@ -15,6 +17,7 @@ kubectl get pod -A
 
 #### Deploy the 4 example apps discussed in the slides
 ```console
+cd v1
 kubectl apply --filename=gpu-test{1,2,3,4}.yaml
 ```
 

demo/specs/quickstart/v1/gpu-test-mps.yaml

@@ -0,0 +1,64 @@
+# One pod, 2 containers share GPU using MPS
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gpu-test-mps
+---
+apiVersion: resource.k8s.io/v1
+kind: ResourceClaimTemplate
+metadata:
+  namespace: gpu-test-mps
+  name: shared-gpu
+spec:
+  spec:
+    devices:
+      requests:
+      - name: mps-gpu
+        exactly:
+          deviceClassName: gpu.nvidia.com
+      config:
+      - requests: ["mps-gpu"]
+        opaque:
+          driver: gpu.nvidia.com
+          parameters:
+            apiVersion: resource.nvidia.com/v1beta1
+            kind: GpuConfig
+            sharing:
+              strategy: MPS
+              mpsConfig:
+                defaultActiveThreadPercentage: 50
+                defaultPinnedDeviceMemoryLimit: 10Gi
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test-mps
+  name: test-pod
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: mps-ctr0
+    image: nvcr.io/nvidia/k8s/cuda-sample:nbody-cuda11.6.0-ubuntu18.04
+    command: ["bash", "-c"]
+    args: ["trap 'exit 0' TERM; /tmp/sample --benchmark --numbodies=4226000 & wait"]
+    resources:
+      claims:
+      - name: shared-gpu
+        request: mps-gpu
+  - name: mps-ctr1
+    image: nvcr.io/nvidia/k8s/cuda-sample:nbody-cuda11.6.0-ubuntu18.04
+    command: ["bash", "-c"]
+    args: ["trap 'exit 0' TERM; /tmp/sample --benchmark --numbodies=4226000 & wait"]
+    resources:
+      claims:
+      - name: shared-gpu
+        request: mps-gpu
+  resourceClaims:
+  - name: shared-gpu
+    resourceClaimTemplateName: shared-gpu
+  tolerations:
+  - key: "nvidia.com/gpu"
+    operator: "Exists"
+    effect: "NoSchedule"

demo/specs/quickstart/v1/gpu-test-vfiopci.yaml

@@ -0,0 +1,42 @@
+# One pod, one container asking for 1 distinct GPU
+
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gpu-test-vfio
+
+---
+apiVersion: resource.k8s.io/v1
+kind: ResourceClaimTemplate
+metadata:
+  namespace: gpu-test-vfio
+  name: single-gpu
+spec:
+  spec:
+    devices:
+      requests:
+      - name: gpu
+        exactly:
+          deviceClassName: vfio.gpu.nvidia.com
+
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test-vfiopci
+  name: pod1
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: ctr
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: gpu
+  resourceClaims:
+  - name: gpu
+    resourceClaimTemplateName: single-gpu

demo/specs/quickstart/v1/gpu-test1.yaml

@@ -0,0 +1,72 @@
+# Two pods, one container each
+# Each container asking for 1 distinct GPU
+
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gpu-test1
+
+---
+apiVersion: resource.k8s.io/v1
+kind: ResourceClaimTemplate
+metadata:
+  namespace: gpu-test1
+  name: single-gpu
+spec:
+  spec:
+    devices:
+      requests:
+      - name: gpu
+        exactly:
+          deviceClassName: gpu.nvidia.com
+
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test1
+  name: pod1
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: ctr
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["nvidia-smi -L; trap 'exit 0' TERM; sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: gpu
+  resourceClaims:
+  - name: gpu
+    resourceClaimTemplateName: single-gpu
+  tolerations:
+  - key: "nvidia.com/gpu"
+    operator: "Exists"
+    effect: "NoSchedule"
+
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test1
+  name: pod2
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: ctr
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["nvidia-smi -L; trap 'exit 0' TERM; sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: gpu
+  resourceClaims:
+  - name: gpu
+    resourceClaimTemplateName: single-gpu
+  tolerations:
+  - key: "nvidia.com/gpu"
+    operator: "Exists"
+    effect: "NoSchedule"

demo/specs/quickstart/v1/gpu-test2.yaml

@@ -0,0 +1,54 @@
+# One pod, two containers
+# Each asking for shared access to a single GPU
+
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gpu-test2
+
+---
+apiVersion: resource.k8s.io/v1
+kind: ResourceClaimTemplate
+metadata:
+  namespace: gpu-test2
+  name: single-gpu
+spec:
+  spec:
+    devices:
+      requests:
+      - name: gpu
+        exactly:
+          deviceClassName: gpu.nvidia.com
+
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test2
+  name: pod
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: ctr0
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["nvidia-smi -L; trap 'exit 0' TERM; sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: shared-gpu
+  - name: ctr1
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["nvidia-smi -L; trap 'exit 0' TERM; sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: shared-gpu
+  resourceClaims:
+  - name: shared-gpu
+    resourceClaimTemplateName: single-gpu
+  tolerations:
+  - key: "nvidia.com/gpu"
+    operator: "Exists"
+    effect: "NoSchedule"

demo/specs/quickstart/v1/gpu-test3.yaml

@@ -0,0 +1,71 @@
+# One shared, global claim providing access to a GPU
+# Two pods, each asking for access to the shared GPU
+
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gpu-test3
+
+---
+apiVersion: resource.k8s.io/v1
+kind: ResourceClaim
+metadata:
+  namespace: gpu-test3
+  name: single-gpu
+spec:
+  devices:
+    requests:
+    - name: gpu
+      exactly:
+        deviceClassName: gpu.nvidia.com
+
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test3
+  name: pod1
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: ctr
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["nvidia-smi -L; trap 'exit 0' TERM; sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: shared-gpu
+  resourceClaims:
+  - name: shared-gpu
+    resourceClaimName: single-gpu
+  tolerations:
+  - key: "nvidia.com/gpu"
+    operator: "Exists"
+    effect: "NoSchedule"
+
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  namespace: gpu-test3
+  name: pod2
+  labels:
+    app: pod
+spec:
+  containers:
+  - name: ctr
+    image: ubuntu:22.04
+    command: ["bash", "-c"]
+    args: ["nvidia-smi -L; trap 'exit 0' TERM; sleep 9999 & wait"]
+    resources:
+      claims:
+      - name: shared-gpu
+  resourceClaims:
+  - name: shared-gpu
+    resourceClaimName: single-gpu
+  tolerations:
+  - key: "nvidia.com/gpu"
+    operator: "Exists"
+    effect: "NoSchedule"