feat: Add AWS Neuron device plugin, remove ecr-login-renew

charts/kubezero-addons/Chart.yaml

@@ -2,14 +2,13 @@ apiVersion: v2
 name: kubezero-addons
 description: KubeZero umbrella chart for various optional cluster addons
 type: application
-version: 0.5.0
+version: 0.5.1
 appVersion: v1.22.8
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
   - kubezero
   - fuse-device-plugin
-  - k8s-ecr-login-renew
   - aws-node-termination-handler
   - external-dns
 maintainers:

charts/kubezero-addons/README.md

@@ -25,19 +25,9 @@ Kubernetes: `>= 1.20.0`
    
 # device-plugins   
    
-# k8s-ecr-login-renew   
+## AWS Neuron
+Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/) - [Inf1 instances](https://aws.amazon.com/ec2/instance-types/inf1/)
    
-## IAM setup   
- - Create IAM user for ECR read-only access and attach the following managed policy: `AmazonEC2ContainerRegistryReadOnly`   
- - create AWS credentials for the IAM users   
-   
-## Kubernetes secret   
-Create secret with the IAM user credential for ecr-renew to use, using the credentials from the previous step:   
-`kubectl create secret -n kube-system generic ecr-renew-cred --from-literal=AWS_REGION=<AWS_REGION> --from-literal=AWS_ACCESS_KEY_ID=<AWS_SECRET_ID> --from-literal=AWS_SECRET_ACCESS_KEY=<AWS_SECRET_KEY>`   
-   
-## Resources   
-- https://github.com/nabsul/k8s-ecr-login-renew
-
 ## Values
 
 | Key | Type | Default | Description |
@@ -65,6 +55,7 @@ Create secret with the IAM user credential for ecr-renew to use, using the crede
 | aws-node-termination-handler.taintNode | bool | `true` |  |
 | aws-node-termination-handler.tolerations[0].effect | string | `"NoSchedule"` |  |
 | aws-node-termination-handler.tolerations[0].key | string | `"node-role.kubernetes.io/master"` |  |
+| awsNeuron.enabled | bool | `false` |  |
 | clusterBackup.enabled | bool | `false` |  |
 | clusterBackup.extraEnv | list | `[]` |  |
 | clusterBackup.image.name | string | `"public.ecr.aws/zero-downtime/kubezero-admin"` |  |
@@ -96,4 +87,3 @@ Create secret with the IAM user credential for ecr-renew to use, using the crede
 | forseti.image.name | string | `"public.ecr.aws/zero-downtime/forseti"` |  |
 | forseti.image.tag | string | `"v0.1.2"` |  |
 | fuseDevicePlugin.enabled | bool | `false` |  |
-| k8sEcrLoginRenew.enabled | bool | `false` |  |

charts/kubezero-addons/README.md.gotmpl

@@ -17,17 +17,7 @@
     
 # device-plugins    
     
-# k8s-ecr-login-renew    
+## AWS Neuron 
+Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/) - [Inf1 instances](https://aws.amazon.com/ec2/instance-types/inf1/)
     
-## IAM setup    
- - Create IAM user for ECR read-only access and attach the following managed policy: `AmazonEC2ContainerRegistryReadOnly`    
- - create AWS credentials for the IAM users    
-    
-## Kubernetes secret    
-Create secret with the IAM user credential for ecr-renew to use, using the credentials from the previous step:    
-`kubectl create secret -n kube-system generic ecr-renew-cred --from-literal=AWS_REGION=<AWS_REGION> --from-literal=AWS_ACCESS_KEY_ID=<AWS_SECRET_ID> --from-literal=AWS_SECRET_ACCESS_KEY=<AWS_SECRET_KEY>`    
-    
-## Resources    
-- https://github.com/nabsul/k8s-ecr-login-renew
-
 {{ template "chart.valuesSection" . }}

charts/kubezero-addons/templates/device-plugins/aws-neuron-ds.yaml

@@ -0,0 +1,79 @@
+{{- if .Values.awsNeuron.enabled }}
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: neuron-device-plugin
+  namespace: kube-system
+spec:
+  selector:
+    matchLabels:
+      name:  neuron-device-plugin-ds
+  updateStrategy:
+    type: RollingUpdate
+  template:
+    metadata:
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ""
+      labels:
+        name: neuron-device-plugin-ds
+    spec:
+      serviceAccount: neuron-device-plugin
+      tolerations:
+      - key: CriticalAddonsOnly
+        operator: Exists
+      - key: aws.amazon.com/neuron
+        operator: Exists
+        effect: NoSchedule
+      # Mark this pod as a critical add-on; when enabled, the critical add-on
+      # scheduler reserves resources for critical add-on pods so that they can
+      # be rescheduled after a failure.
+      # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
+      priorityClassName: "system-node-critical"
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                  - key: "beta.kubernetes.io/instance-type"
+                    operator: In
+                    values:
+                      - inf1.xlarge
+                      - inf1.2xlarge
+                      - inf1.6xlarge
+                      - inf1.4xlarge
+              - matchExpressions:
+                  - key: "node.kubernetes.io/instance-type"
+                    operator: In
+                    values:
+                      - inf1.xlarge
+                      - inf1.2xlarge
+                      - inf1.6xlarge
+                      - inf1.24xlarge
+      containers:
+      - image: "{{ .Values.awsNeuron.image.name }}:{{ .Values.awsNeuron.image.tag }}"
+        imagePullPolicy: IfNotPresent
+        name: neuron-device-plugin
+        env:
+        - name: KUBECONFIG
+          value: /etc/kubernetes/kubelet.conf
+        - name: NODE_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: spec.nodeName
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop: ["ALL"]
+        volumeMounts:
+          - name: device-plugin
+            mountPath: /var/lib/kubelet/device-plugins
+          - name: infa-map
+            mountPath: /run
+      volumes:
+        - name: device-plugin
+          hostPath:
+            path: /var/lib/kubelet/device-plugins
+        - name: infa-map
+          hostPath:
+            path: /run
+{{- end }}

charts/kubezero-addons/templates/device-plugins/aws-neuron-rbac.yaml

@@ -0,0 +1,59 @@
+{{- if .Values.awsNeuron.enabled }}
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: neuron-device-plugin
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - nodes
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - events
+  verbs:
+  - create
+  - patch
+- apiGroups:
+  - ""
+  resources:
+  - pods
+  verbs:
+  - update
+  - patch
+  - get
+  - list
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - nodes/status
+  verbs:
+  - patch
+  - update
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: neuron-device-plugin
+  namespace: kube-system
+---
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: neuron-device-plugin
+  namespace: kube-system
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: neuron-device-plugin
+subjects:
+- kind: ServiceAccount
+  name: neuron-device-plugin
+  namespace: kube-system
+{{- end }}

charts/kubezero-addons/templates/k8s-ecr-login-renew/cronjob.yaml

@@ -1,42 +0,0 @@
-{{- if .Values.k8sEcrLoginRenew.enabled }}
-apiVersion: batch/v1beta1
-kind: CronJob
-metadata:
-  namespace: kube-system
-  name: ecr-renew
-  labels:
-    app: ecr-renew
-spec:
-  schedule: "0 */6 * * *"
-  successfulJobsHistoryLimit: 3
-  failedJobsHistoryLimit: 5
-  jobTemplate:
-    spec:
-      template:
-        spec:
-          restartPolicy: OnFailure
-          serviceAccountName: ecr-renew
-          containers:
-            - name: ecr-renew
-              image: nabsul/k8s-ecr-login-renew:v1.4
-              env:
-                - name: DOCKER_SECRET_NAME
-                  value: ecr-login
-                - name: TARGET_NAMESPACE
-                  value: "*"
-                - name: AWS_REGION
-                  valueFrom:
-                    secretKeyRef:
-                      name: ecr-renew-cred
-                      key: AWS_REGION
-                - name: AWS_ACCESS_KEY_ID
-                  valueFrom:
-                    secretKeyRef:
-                      name: ecr-renew-cred
-                      key: AWS_ACCESS_KEY_ID
-                - name: AWS_SECRET_ACCESS_KEY
-                  valueFrom:
-                    secretKeyRef:
-                      name: ecr-renew-cred
-                      key: AWS_SECRET_ACCESS_KEY
-{{- end }}

charts/kubezero-addons/templates/k8s-ecr-login-renew/service-account.yml

@@ -1,35 +0,0 @@
-{{- if .Values.k8sEcrLoginRenew.enabled }}
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  namespace: kube-system
-  name: ecr-renew
----
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: ecr-renew
-rules:
-  - apiGroups: [""]
-    resources: ["secrets"]
-    verbs: ["create", "update", "get", "delete"]
-  - apiGroups: [""]
-    resources: ["namespaces"]
-    verbs: ["get", "list"]
----
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  namespace: kube-system
-  name: ecr-renew
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: ecr-renew
-subjects:
-  - kind: ServiceAccount
-    name: ecr-renew
-    namespace: kube-system
-{{- end }}

charts/kubezero-addons/values.yaml

@@ -70,9 +70,13 @@ aws-node-termination-handler:
 fuseDevicePlugin:
   enabled: false
 
-k8sEcrLoginRenew:
+awsNeuron:
   enabled: false
 
+  image:
+    name: public.ecr.aws/neuron/neuron-device-plugin
+    tag: 1.9.0.0
+
 external-dns:
   enabled: false