chore(deps): update kubezero-argo-dependencies

charts/kubezero-addons/Chart.yaml

@@ -33,11 +33,6 @@ dependencies:
     # https://github.com/NVIDIA/k8s-device-plugin
     repository: https://nvidia.github.io/k8s-device-plugin
     condition: nvidia-device-plugin.enabled
-  - name: neuron-helm-chart
-    version: 1.1.1
-    # https://github.com/aws-neuron/neuron-helm-charts/tree/main/charts/neuron-helm-chart
-    repository: oci://public.ecr.aws/neuron #/neuron-helm-chart
-    condition: neuron-helm-chart.enabled
   - name: sealed-secrets
     version: 2.16.2
     repository: https://bitnami-labs.github.io/sealed-secrets

charts/kubezero-addons/README.md

@@ -25,7 +25,6 @@ Kubernetes: `>= 1.26.0`
 | https://nvidia.github.io/k8s-device-plugin | nvidia-device-plugin | 0.17.0 |
 | https://twin.github.io/helm-charts | aws-eks-asg-rolling-update-handler | 1.5.0 |
 | oci://public.ecr.aws/aws-ec2/helm | aws-node-termination-handler | 0.24.1 |
-| oci://public.ecr.aws/neuron | neuron-helm-chart | 1.1.1 |
 
 # MetalLB   
    
@@ -101,11 +100,13 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | aws-node-termination-handler.tolerations[0].effect | string | `"NoSchedule"` |  |
 | aws-node-termination-handler.tolerations[0].key | string | `"node-role.kubernetes.io/control-plane"` |  |
 | aws-node-termination-handler.useProviderId | bool | `true` |  |
+| awsNeuron.enabled | bool | `false` |  |
+| awsNeuron.image.name | string | `"public.ecr.aws/neuron/neuron-device-plugin"` |  |
+| awsNeuron.image.tag | string | `"2.22.4.0"` |  |
 | cluster-autoscaler.autoDiscovery.clusterName | string | `""` |  |
 | cluster-autoscaler.awsRegion | string | `"us-west-2"` |  |
 | cluster-autoscaler.enabled | bool | `false` |  |
 | cluster-autoscaler.extraArgs.balance-similar-node-groups | bool | `true` |  |
-| cluster-autoscaler.extraArgs.ignore-daemonsets-utilization | bool | `true` |  |
 | cluster-autoscaler.extraArgs.ignore-taint | string | `"node.cilium.io/agent-not-ready"` |  |
 | cluster-autoscaler.extraArgs.scan-interval | string | `"30s"` |  |
 | cluster-autoscaler.extraArgs.skip-nodes-with-local-storage | bool | `false` |  |
@@ -140,24 +141,22 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | fuseDevicePlugin.enabled | bool | `false` |  |
 | fuseDevicePlugin.image.name | string | `"public.ecr.aws/zero-downtime/fuse-device-plugin"` |  |
 | fuseDevicePlugin.image.tag | string | `"v1.2.0"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[0].key | string | `"CriticalAddonsOnly"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[0].operator | string | `"Exists"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[1].effect | string | `"NoSchedule"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[1].key | string | `"aws.amazon.com/neuron"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[1].operator | string | `"Exists"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[2].effect | string | `"NoSchedule"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[2].key | string | `"kubezero-workergroup"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[2].operator | string | `"Exists"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[0].mountPath | string | `"/var/lib/kubelet/device-plugins"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[0].name | string | `"device-plugin"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[1].mountPath | string | `"/run"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[1].name | string | `"infa-map"` |  |
-| neuron-helm-chart.devicePlugin.volumes[0].hostPath.path | string | `"/var/lib/kubelet/device-plugins"` |  |
-| neuron-helm-chart.devicePlugin.volumes[0].name | string | `"device-plugin"` |  |
-| neuron-helm-chart.devicePlugin.volumes[1].hostPath.path | string | `"/run"` |  |
-| neuron-helm-chart.devicePlugin.volumes[1].name | string | `"infa-map"` |  |
-| neuron-helm-chart.enabled | bool | `false` |  |
-| neuron-helm-chart.npd.enabled | bool | `false` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].key | string | `"node.kubernetes.io/instance-type"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].operator | string | `"In"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[0] | string | `"g5.xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[10] | string | `"g4dn.4xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[11] | string | `"g4dn.8xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[12] | string | `"g4dn.12xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[13] | string | `"g4dn.16xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[1] | string | `"g5.2xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[2] | string | `"g5.4xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[3] | string | `"g5.8xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[4] | string | `"g5.12xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[5] | string | `"g5.16xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[6] | string | `"g5.24xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[7] | string | `"g5.48xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[8] | string | `"g4dn.xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[9] | string | `"g4dn.2xlarge"` |  |
 | nvidia-device-plugin.cdi.nvidiaHookPath | string | `"/usr/bin"` |  |
 | nvidia-device-plugin.deviceDiscoveryStrategy | string | `"nvml"` |  |
 | nvidia-device-plugin.enabled | bool | `false` |  |
@@ -168,23 +167,6 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | nvidia-device-plugin.tolerations[1].effect | string | `"NoSchedule"` |  |
 | nvidia-device-plugin.tolerations[1].key | string | `"kubezero-workergroup"` |  |
 | nvidia-device-plugin.tolerations[1].operator | string | `"Exists"` |  |
-| py-kube-downscaler.enabled | bool | `false` |  |
-| py-kube-downscaler.excludedNamespaces[0] | string | `"kube-system"` |  |
-| py-kube-downscaler.excludedNamespaces[1] | string | `"operators"` |  |
-| py-kube-downscaler.excludedNamespaces[2] | string | `"monitoring"` |  |
-| py-kube-downscaler.excludedNamespaces[3] | string | `"logging"` |  |
-| py-kube-downscaler.excludedNamespaces[4] | string | `"telemetry"` |  |
-| py-kube-downscaler.excludedNamespaces[5] | string | `"istio-system"` |  |
-| py-kube-downscaler.excludedNamespaces[6] | string | `"istio-ingress"` |  |
-| py-kube-downscaler.excludedNamespaces[7] | string | `"cert-manager"` |  |
-| py-kube-downscaler.excludedNamespaces[8] | string | `"argocd"` |  |
-| py-kube-downscaler.nodeSelector."node-role.kubernetes.io/control-plane" | string | `""` |  |
-| py-kube-downscaler.resources.limits.cpu | string | `nil` |  |
-| py-kube-downscaler.resources.limits.memory | string | `"256Mi"` |  |
-| py-kube-downscaler.resources.requests.cpu | string | `"20m"` |  |
-| py-kube-downscaler.resources.requests.memory | string | `"48Mi"` |  |
-| py-kube-downscaler.tolerations[0].effect | string | `"NoSchedule"` |  |
-| py-kube-downscaler.tolerations[0].key | string | `"node-role.kubernetes.io/control-plane"` |  |
 | sealed-secrets.enabled | bool | `false` |  |
 | sealed-secrets.fullnameOverride | string | `"sealed-secrets-controller"` |  |
 | sealed-secrets.keyrenewperiod | string | `"0"` |  |

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

@@ -0,0 +1,80 @@
+{{- 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:
+      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
+      - key: kubezero-workergroup
+        effect: NoSchedule
+        operator: Exists
+      # 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: "node.kubernetes.io/instance-type"
+                    operator: In
+                    values:
+                      - inf1.xlarge
+                      - inf1.2xlarge
+                      - inf1.6xlarge
+                      - inf1.24xlarge
+                      - inf2.xlarge
+                      - inf2.4xlarge
+                      - inf2.8xlarge
+                      - inf2.24xlarge
+                      - inf2.48xlarge
+                      - trn1.2xlarge
+                      - trn1.32xlarge
+                      - trn1n.32xlarge
+      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/values.yaml

@@ -155,35 +155,12 @@ fuseDevicePlugin:
     name: public.ecr.aws/zero-downtime/fuse-device-plugin
     tag: v1.2.0
 
-neuron-helm-chart:
+awsNeuron:
   enabled: false
 
-  npd:
-    enabled: false
-
-  devicePlugin:
-    tolerations:
-      - key: CriticalAddonsOnly
-        operator: Exists
-      - key: aws.amazon.com/neuron
-        operator: Exists
-        effect: NoSchedule
-      - key: kubezero-workergroup
-        effect: NoSchedule
-        operator: Exists
-
-    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
+  image:
+    name: public.ecr.aws/neuron/neuron-device-plugin
+    tag: 2.22.4.0
 
 nvidia-device-plugin:
   enabled: false
@@ -201,6 +178,29 @@ nvidia-device-plugin:
     effect: NoSchedule
     operator: Exists
 
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+          - matchExpressions:
+              - key: "node.kubernetes.io/instance-type"
+                operator: In
+                values:
+                  - g5.xlarge
+                  - g5.2xlarge
+                  - g5.4xlarge
+                  - g5.8xlarge
+                  - g5.12xlarge
+                  - g5.16xlarge
+                  - g5.24xlarge
+                  - g5.48xlarge
+                  - g4dn.xlarge
+                  - g4dn.2xlarge
+                  - g4dn.4xlarge
+                  - g4dn.8xlarge
+                  - g4dn.12xlarge
+                  - g4dn.16xlarge
+
 cluster-autoscaler:
   enabled: false
 

charts/kubezero-argo/Chart.yaml

@@ -1,7 +1,7 @@
 apiVersion: v2
 description: KubeZero Argo - Events, Workflow, CD
 name: kubezero-argo
-version: 0.2.7
+version: 0.2.8
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
@@ -18,11 +18,11 @@ dependencies:
     version: ">= 0.1.6"
     repository: https://cdn.zero-downtime.net/charts/
   - name: argo-events
-    version: 2.4.9
+    version: 2.4.13
     repository: https://argoproj.github.io/argo-helm
     condition: argo-events.enabled
   - name: argo-cd
-    version: 7.7.7
+    version: 7.7.17
     repository: https://argoproj.github.io/argo-helm
     condition: argo-cd.enabled
   - name: argocd-apps
@@ -30,7 +30,7 @@ dependencies:
     repository: https://argoproj.github.io/argo-helm
     condition: argo-cd.enabled
   - name: argocd-image-updater
-    version: 0.11.2
+    version: 0.12.0
     repository: https://argoproj.github.io/argo-helm
     condition: argocd-image-updater.enabled
 kubeVersion: ">= 1.26.0-0"