update: setup gpu console plugin

components/operators/gpu-operator-certified/instance/base/console-plugin-nvidia-gpu/kustomization.yaml

@@ -0,0 +1,8 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - templates/configmap.yaml
+  - templates/consoleplugin.yaml
+  - templates/deployment.yaml
+  - templates/service.yaml

components/operators/gpu-operator-certified/instance/base/console-plugin-nvidia-gpu/templates/configmap.yaml

@@ -0,0 +1,28 @@
+---
+# Source: console-plugin-nvidia-gpu/templates/configmap.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: release-name-console-plugin-nvidia-gpu
+  labels:
+    helm.sh/chart: console-plugin-nvidia-gpu-0.2.3
+    app.kubernetes.io/name: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: release-name
+    app.kubernetes.io/version: "latest"
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/component: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: console-plugin-nvidia-gpu
+    app.kubernetes.io/part-of: console-plugin-nvidia-gpu
+data:
+  dcgm-metrics.csv: |
+    DCGM_FI_PROF_GR_ENGINE_ACTIVE, gauge, gpu utilization.
+    DCGM_FI_DEV_MEM_COPY_UTIL, gauge, mem utilization.
+    DCGM_FI_DEV_ENC_UTIL, gauge, enc utilization.
+    DCGM_FI_DEV_DEC_UTIL, gauge, dec utilization.
+    DCGM_FI_DEV_POWER_USAGE, gauge, power usage.
+    DCGM_FI_DEV_POWER_MGMT_LIMIT_MAX, gauge, power mgmt limit.
+    DCGM_FI_DEV_GPU_TEMP, gauge, gpu temp.
+    DCGM_FI_DEV_SM_CLOCK, gauge, sm clock.
+    DCGM_FI_DEV_MAX_SM_CLOCK, gauge, max sm clock.
+    DCGM_FI_DEV_MEM_CLOCK, gauge, mem clock.
+    DCGM_FI_DEV_MAX_MEM_CLOCK, gauge, max mem clock.

components/operators/gpu-operator-certified/instance/base/console-plugin-nvidia-gpu/templates/consoleplugin.yaml

@@ -0,0 +1,22 @@
+---
+# Source: console-plugin-nvidia-gpu/templates/consoleplugin.yaml
+apiVersion: console.openshift.io/v1alpha1
+kind: ConsolePlugin
+metadata:
+  name: release-name-console-plugin-nvidia-gpu
+  labels:
+    helm.sh/chart: console-plugin-nvidia-gpu-0.2.3
+    app.kubernetes.io/name: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: release-name
+    app.kubernetes.io/version: "latest"
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/component: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: console-plugin-nvidia-gpu
+    app.kubernetes.io/part-of: console-plugin-nvidia-gpu
+spec:
+  displayName: 'Console Plugin NVIDIA GPU Template'
+  service:
+    name: release-name-console-plugin-nvidia-gpu
+    namespace: sandbox
+    port: 9443
+    basePath: '/'

components/operators/gpu-operator-certified/instance/base/console-plugin-nvidia-gpu/templates/deployment.yaml

@@ -0,0 +1,61 @@
+---
+# Source: console-plugin-nvidia-gpu/templates/deployment.yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: release-name-console-plugin-nvidia-gpu
+  labels:
+    helm.sh/chart: console-plugin-nvidia-gpu-0.2.3
+    app.kubernetes.io/name: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: release-name
+    app.kubernetes.io/version: "latest"
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/component: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: console-plugin-nvidia-gpu
+    app.kubernetes.io/part-of: console-plugin-nvidia-gpu
+    app.openshift.io/runtime-namespace: console-plugin-nvidia-gpu
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: console-plugin-nvidia-gpu
+      app.kubernetes.io/instance: release-name
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: console-plugin-nvidia-gpu
+        app.kubernetes.io/instance: release-name
+    spec:
+      securityContext:
+        runAsNonRoot: true
+      containers:
+      - name: console-plugin-nvidia-gpu
+        image: "quay.io/edge-infrastructure/console-plugin-nvidia-gpu:latest"
+        imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+        ports:
+        - containerPort: 9443
+          protocol: TCP
+        volumeMounts:
+        - name: plugin-serving-cert
+          readOnly: true
+          mountPath: /var/serving-cert
+        resources:
+            {}
+      volumes:
+      - name: plugin-serving-cert
+        secret:
+          secretName: plugin-serving-cert
+          defaultMode: 420
+      - name: nginx-conf
+        configMap:
+          name: nginx-conf
+          defaultMode: 420
+      restartPolicy: Always
+      dnsPolicy: ClusterFirst
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 25%
+      maxSurge: 25%

components/operators/gpu-operator-certified/instance/base/console-plugin-nvidia-gpu/templates/service.yaml

@@ -0,0 +1,28 @@
+---
+# Source: console-plugin-nvidia-gpu/templates/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: release-name-console-plugin-nvidia-gpu
+  labels:
+    helm.sh/chart: console-plugin-nvidia-gpu-0.2.3
+    app.kubernetes.io/name: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: release-name
+    app.kubernetes.io/version: "latest"
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/component: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: console-plugin-nvidia-gpu
+    app.kubernetes.io/part-of: console-plugin-nvidia-gpu
+  annotations:
+    service.alpha.openshift.io/serving-cert-secret-name: plugin-serving-cert
+spec:
+  ports:
+  - name: 9443-tcp
+    protocol: TCP
+    port: 9443
+    targetPort: 9443
+  selector:
+    app.kubernetes.io/name: console-plugin-nvidia-gpu
+    app.kubernetes.io/instance: release-name
+  type: ClusterIP
+  sessionAffinity: None

components/operators/gpu-operator-certified/instance/base/console-plugin-nvidia-gpu/templates/tests/test-plugin-service.yaml

@@ -0,0 +1,20 @@
+---
+# Source: console-plugin-nvidia-gpu/templates/tests/test-plugin-service.yaml
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "release-name-service-test"
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: release-name-service-test
+      image: quay.io/cilium/alpine-curl:v1.4.0
+      imagePullPolicy: "Always"
+      args:
+        - -XGET
+        - --silent
+        - --fail
+        - --insecure
+        - https://release-name-console-plugin-nvidia-gpu.sandbox.svc:9443/plugin-manifest.json
+  restartPolicy: Never

components/operators/gpu-operator-certified/instance/base/kustomization.yaml

@@ -7,4 +7,5 @@ commonLabels:
 resources:
   - cluster-policy.yaml
   - device-plugin-config.yaml
+  - setup-console-plugin-job.yaml
   - setup-dashboard-job.yaml

components/operators/gpu-operator-certified/instance/base/setup-console-plugin-job.yaml

@@ -0,0 +1,118 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: nvidia-gpu-console-setup
+rules:
+- apiGroups:
+  - ''
+  resources:
+  - configmaps
+  verbs:
+  - '*'
+- apiGroups:
+  - operator.openshift.io
+  resources:
+  - consoles
+  resourceNames:
+  - cluster
+  verbs:
+  - '*'
+- apiGroups:
+  - console.openshift.io
+  resources:
+  - consoleplugins
+  resourceNames:
+  - release-name-console-plugin-nvidia-gpu
+  verbs:
+  - '*'
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: nvidia-gpu-console-setup
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: nvidia-gpu-console-setup
+subjects:
+  - kind: ServiceAccount
+    name: nvidia-gpu-console-setup
+    namespace: nvidia-gpu-operator
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: nvidia-gpu-console-setup
+  namespace: openshift-config-managed
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: nvidia-gpu-console-setup
+subjects:
+  - kind: ServiceAccount
+    name: nvidia-gpu-console-setup
+    namespace: nvidia-gpu-operator
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: nvidia-gpu-console-setup
+  namespace: nvidia-gpu-operator
+---
+apiVersion: batch/v1
+kind: Job
+metadata:
+  annotations:
+    argocd.argoproj.io/hook: Sync
+    # argocd.argoproj.io/hook-delete-policy: HookSucceeded
+  generateName: nvidia-gpu-console-setup-
+  name: nvidia-gpu-console-setup
+  namespace: nvidia-gpu-operator
+spec:
+  template:
+    spec:
+      containers:
+        - name: nvidia-gpu-console-setup
+          image: image-registry.openshift-image-registry.svc:5000/openshift/cli:latest
+          env:
+            - name: NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+          command:
+            - /bin/bash
+            - -c
+            - |
+              #!/usr/bin/env bash
+              set -x
+
+              cd /tmp
+
+              nvidia_setup_console_plugin(){
+                if which helm; then
+                  helm repo add rh-ecosystem-edge https://rh-ecosystem-edge.github.io/console-plugin-nvidia-gpu || true
+                  helm repo update > /dev/null 2>&1
+                  helm upgrade --install -n nvidia-gpu-operator console-plugin-nvidia-gpu rh-ecosystem-edge/console-plugin-nvidia-gpu > /dev/null 2>&1
+                else
+                  return
+                fi
+
+                if oc get consoles.operator.openshift.io cluster --output=jsonpath="{.spec.plugins}" >/dev/null; then
+                  oc patch consoles.operator.openshift.io cluster --patch '{ "spec": { "plugins": ["console-plugin-nvidia-gpu"] } }' --type=merge
+                else
+                  oc get consoles.operator.openshift.io cluster --output=jsonpath="{.spec.plugins}" | grep -q console-plugin-nvidia-gpu || \
+                    oc patch consoles.operator.openshift.io cluster --patch '[{"op": "add", "path": "/spec/plugins/-", "value": "console-plugin-nvidia-gpu" }]' --type=json
+                fi
+
+                oc patch clusterpolicies.nvidia.com gpu-cluster-policy --patch '{ "spec": { "dcgmExporter": { "config": { "name": "console-plugin-nvidia-gpu" } } } }' --type=merge
+                oc -n nvidia-gpu-operator get deploy -l app.kubernetes.io/name=console-plugin-nvidia-gpu
+              }
+
+              nvidia_setup_console_plugin
+
+
+      restartPolicy: Never
+      terminationGracePeriodSeconds: 30
+      serviceAccount: nvidia-gpu-console-setup
+      serviceAccountName: nvidia-gpu-console-setup

scripts/library/nvidia.sh

@@ -9,10 +9,21 @@ nvidia_setup_dashboard_monitor(){
   rm dcgm-exporter-dashboard.json
 }
 
-nvidia_setup_dashboard_admin(){
+nvidia_setup_console_plugin_dump_helm(){
+  which helm || return 1
   helm repo add rh-ecosystem-edge https://rh-ecosystem-edge.github.io/console-plugin-nvidia-gpu || true
   helm repo update > /dev/null 2>&1
-  helm upgrade --install -n nvidia-gpu-operator console-plugin-nvidia-gpu rh-ecosystem-edge/console-plugin-nvidia-gpu > /dev/null 2>&1
+  helm template --output-dir components/operators/gpu-operator-certified/instance/base rh-ecosystem-edge/console-plugin-nvidia-gpu
+}
+
+nvidia_setup_console_plugin(){
+  if which helm; then
+    helm repo add rh-ecosystem-edge https://rh-ecosystem-edge.github.io/console-plugin-nvidia-gpu || true
+    helm repo update > /dev/null 2>&1
+    helm upgrade --install -n nvidia-gpu-operator console-plugin-nvidia-gpu rh-ecosystem-edge/console-plugin-nvidia-gpu > /dev/null 2>&1
+  else
+    return
+  fi
 
   if oc get consoles.operator.openshift.io cluster --output=jsonpath="{.spec.plugins}" >/dev/null; then
     oc patch consoles.operator.openshift.io cluster --patch '{ "spec": { "plugins": ["console-plugin-nvidia-gpu"] } }' --type=merge