prod: add tolerations to clusterpolicy daemonset

The NVIDIA DaemonSets are unable to run their pods without specifying the tolerations given to the GPU nodes in the AcceleratorProfiles. See #647 and nerc-project/operations#913
OCP-on-NERC · Jan 31, 2025 · 0899001 · 0899001
1 parent 36c6506
commit 0899001
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 0 deletions.
diff --git a/nvidia-gpu-operator/overlays/nerc-ocp-prod/clusterpolicy/clusterpolicy_patch.yaml b/nvidia-gpu-operator/overlays/nerc-ocp-prod/clusterpolicy/clusterpolicy_patch.yaml
@@ -0,0 +1,15 @@
+apiVersion: nvidia.com/v1
+kind: ClusterPolicy
+metadata:
+  name: gpu-cluster-policy
+spec:
+  daemonsets:
+    tolerations:
+    - effect: NoSchedule
+      key: nvidia.com/gpu.product
+      operator: Equal
+      value: NVIDIA-A100-SXM4-40GB
+    - effect: NoSchedule
+      key: nvidia.com/gpu.product
+      operator: Equal
+      value: Tesla-V100-PCIE-32GB
diff --git a/nvidia-gpu-operator/overlays/nerc-ocp-prod/kustomization.yaml b/nvidia-gpu-operator/overlays/nerc-ocp-prod/kustomization.yaml
@@ -3,3 +3,5 @@ kind: Kustomization
 namespace: nvidia-gpu-operator
 resources:
   - ../../base
+patches:
+  - path: clusterpolicy/clusterpolicy_patch.yaml