update azure deployments

azure/Makefile

@@ -38,11 +38,14 @@ create-deployments:
 	helm template --namespace=kube-system -f deployments/azure-autoscaler.yaml cluster-autoscaler-azure \
 		autoscaler/cluster-autoscaler > deployments/azure-autoscaler-result.yaml
 
+	helm template --namespace=kube-system -f deployments/azuredisk-csi-driver.yaml azuredisk-csi-driver \
+		azuredisk-csi-driver/azuredisk-csi-driver > deployments/azuredisk-csi-driver-result.yaml
+
 create-network: ## Create networks
 	cd prepare && terraform init && terraform apply -auto-approve
 
 create-controlplane-bootstrap:
-	talosctl --talosconfig _cfgs/talosconfig config endpoint ${CPFIRST}
+	talosctl --talosconfig _cfgs/talosconfig config endpoint ${ENDPOINT}
 	talosctl --talosconfig _cfgs/talosconfig --nodes ${CPFIRST} bootstrap
 
 create-controlplane: ## Bootstrap controlplane

azure/README.md

@@ -37,7 +37,6 @@ kubectl -n kube-system create secret generic azure-csi --from-file=azure.json=_c
 * [Azure CSI](https://github.com/kubernetes-sigs/azuredisk-csi-driver)
 * [Azure Node AutoScaler](https://github.com/kubernetes/autoscaler/blob/master/cluster-autoscaler/cloudprovider/azure/README.md)
 * [cilium](https://github.com/cilium/cilium) 1.12.5
-* [kubelet-serving-cert-approver](https://github.com/alex1989hu/kubelet-serving-cert-approver)
 * [metrics-server](https://github.com/kubernetes-sigs/metrics-server) 0.5.0
 * [rancher.io/local-path](https://github.com/rancher/local-path-provisioner) 0.0.19
 * [ingress-nginx](https://kubernetes.github.io/ingress-nginx/) 4.4.2

azure/deployments/azure-autoscaler-result.yaml

@@ -7,7 +7,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
   namespace: kube-system
 spec:
@@ -26,7 +26,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
   namespace: kube-system
 automountServiceAccountToken: true
@@ -39,7 +39,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
 rules:
   - apiGroups:
@@ -180,7 +180,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
 roleRef:
   apiGroup: rbac.authorization.k8s.io
@@ -199,7 +199,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
   namespace: kube-system
 rules:
@@ -228,7 +228,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
   namespace: kube-system
 roleRef:
@@ -248,7 +248,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
   namespace: kube-system
 spec:
@@ -272,7 +272,7 @@ metadata:
     app.kubernetes.io/instance: "cluster-autoscaler-azure"
     app.kubernetes.io/name: "azure-cluster-autoscaler"
     app.kubernetes.io/managed-by: "Helm"
-    helm.sh/chart: "cluster-autoscaler-9.24.0"
+    helm.sh/chart: "cluster-autoscaler-9.29.1"
   name: cluster-autoscaler-azure
   namespace: kube-system
 spec:
@@ -291,7 +291,7 @@ spec:
       dnsPolicy: "ClusterFirst"
       containers:
         - name: azure-cluster-autoscaler
-          image: "registry.k8s.io/autoscaling/cluster-autoscaler:v1.26.1"
+          image: "registry.k8s.io/autoscaling/cluster-autoscaler:v1.27.2"
           imagePullPolicy: "IfNotPresent"
           command:
             - ./cluster-autoscaler
@@ -334,4 +334,4 @@ spec:
       volumes:
         - name: cloud-config
           secret:
-            secretName: azure-cluster-autoscaler
+            secretName: azure-managed-identity

azure/deployments/azure-autoscaler.yaml

@@ -4,7 +4,7 @@
 
 fullnameOverride: cluster-autoscaler-azure
 image:
-  tag: v1.26.1
+  tag: v1.27.2
 
 cloudProvider: azure
 cloudConfigPath: /etc/azure/azure.json
@@ -21,7 +21,8 @@ extraArgs:
 
 extraVolumeSecrets:
   cloud-config:
-    name: azure-cluster-autoscaler
+    name: azure-managed-identity
+    # name: azure-cloud-controller-manager
     mountPath: /etc/azure
 
 priorityClassName: system-cluster-critical

azure/deployments/azure-cloud-controller-manager.yaml

@@ -201,4 +201,4 @@ spec:
       volumes:
         - name: cloud-config
           secret:
-            secretName: azure-cloud-controller-manager
+            secretName: azure-managed-identity

azure/deployments/azure-cloud-node-manager.yaml

@@ -1,92 +0,0 @@
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  labels:
-    k8s-app: azure-cloud-node-manager
-  name: azure-cloud-node-manager
-  namespace: kube-system
----
-kind: ClusterRole
-apiVersion: rbac.authorization.k8s.io/v1
-metadata:
-  name: cloud-node-manager
-  labels:
-    k8s-app: cloud-node-manager
-rules:
-- apiGroups: [""]
-  resources: ["nodes"]
-  verbs: ["watch","list","get","update", "patch"]
-- apiGroups: [""]
-  resources: ["nodes/status"]
-  verbs: ["patch"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: cloud-node-manager
-  labels:
-    k8s-app: cloud-node-manager
-    kubernetes.io/cluster-service: "true"
-    addonmanager.kubernetes.io/mode: Reconcile
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: cloud-node-manager
-subjects:
-- kind: ServiceAccount
-  name: azure-cloud-node-manager
-  namespace: kube-system
----
-apiVersion: apps/v1
-kind: DaemonSet
-metadata:
-  name: azure-cloud-node-manager
-  namespace: kube-system
-  labels:
-    component: azure-cloud-node-manager
-    kubernetes.io/cluster-service: "true"
-    addonmanager.kubernetes.io/mode: Reconcile
-spec:
-  selector:
-    matchLabels:
-      k8s-app: azure-cloud-node-manager
-  template:
-    metadata:
-      labels:
-        k8s-app: azure-cloud-node-manager
-      annotations:
-        cluster-autoscaler.kubernetes.io/daemonset-pod: "true"
-    spec:
-      priorityClassName: system-node-critical
-      serviceAccountName: azure-cloud-node-manager
-      hostNetwork: true   # required to fetch correct hostname
-      nodeSelector:
-        node-role.kubernetes.io/control-plane: ""
-        node.cloudprovider.kubernetes.io/platform: azure
-      tolerations:
-        - key: "node.cloudprovider.kubernetes.io/uninitialized"
-          value: "true"
-          effect: "NoSchedule"
-        - key: "node-role.kubernetes.io/control-plane"
-          effect: NoSchedule
-      containers:
-      - name: cloud-node-manager
-        image: mcr.microsoft.com/oss/kubernetes/azure-cloud-node-manager:v1.26.0
-        imagePullPolicy: IfNotPresent
-        command:
-        - cloud-node-manager
-        - --node-name=$(NODE_NAME)
-        - --wait-routes=false
-        - --v=4
-        env:
-        - name: NODE_NAME
-          valueFrom:
-            fieldRef:
-              fieldPath: spec.nodeName
-        resources:
-          requests:
-            cpu: 50m
-            memory: 32Mi
-          limits:
-            cpu: 100m
-            memory: 64Mi

azure/deployments/azure-cluster-autoscaler.yaml

@@ -173,4 +173,4 @@ spec:
       volumes:
         - name: cloud-config
           secret:
-            secretName: azure-cloud-controller-manager
+            secretName: azure-managed-identity

azure/deployments/azuredisk-csi-driver-result.yaml

@@ -0,0 +1,697 @@
+---
+# Source: azuredisk-csi-driver/templates/serviceaccount-csi-azuredisk-controller.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: csi-azuredisk-controller-sa
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+---
+# Source: azuredisk-csi-driver/templates/serviceaccount-csi-azuredisk-node.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: csi-azuredisk-node-sa
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-external-provisioner-role
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+rules:
+  - apiGroups: [""]
+    resources: ["persistentvolumes"]
+    verbs: ["get", "list", "watch", "create", "delete"]
+  - apiGroups: [""]
+    resources: ["persistentvolumeclaims"]
+    verbs: ["get", "list", "watch", "update"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["storageclasses"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["events"]
+    verbs: ["get", "list", "watch", "create", "update", "patch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["csinodes"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["snapshot.storage.k8s.io"]
+    resources: ["volumesnapshots"]
+    verbs: ["get", "list"]
+  - apiGroups: ["snapshot.storage.k8s.io"]
+    resources: ["volumesnapshotcontents"]
+    verbs: ["get", "list"]
+  - apiGroups: ["coordination.k8s.io"]
+    resources: ["leases"]
+    verbs: ["get", "watch", "list", "delete", "update", "create", "patch"]
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-external-attacher-role
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+rules:
+  - apiGroups: [""]
+    resources: ["persistentvolumes"]
+    verbs: ["get", "list", "watch", "update"]
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["csi.storage.k8s.io"]
+    resources: ["csinodeinfos"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["volumeattachments"]
+    verbs: ["get", "list", "watch", "update", "patch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["volumeattachments/status"]
+    verbs: ["get", "list", "watch", "update", "patch"]
+  - apiGroups: ["coordination.k8s.io"]
+    resources: ["leases"]
+    verbs: ["get", "watch", "list", "delete", "update", "create", "patch"]
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-external-snapshotter-role
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+rules:
+  - apiGroups: [""]
+    resources: ["events"]
+    verbs: ["list", "watch", "create", "update", "patch"]
+  - apiGroups: [""]
+    resources: ["secrets"]
+    verbs: ["get", "list"]
+  - apiGroups: ["snapshot.storage.k8s.io"]
+    resources: ["volumesnapshotclasses"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["snapshot.storage.k8s.io"]
+    resources: ["volumesnapshotcontents"]
+    verbs: ["create", "get", "list", "watch", "update", "delete", "patch"]
+  - apiGroups: ["snapshot.storage.k8s.io"]
+    resources: ["volumesnapshotcontents/status"]
+    verbs: ["update", "patch"]
+  - apiGroups: ["coordination.k8s.io"]
+    resources: ["leases"]
+    verbs: ["get", "watch", "list", "delete", "update", "create", "patch"]
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-external-resizer-role
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+rules:
+  - apiGroups: [""]
+    resources: ["persistentvolumes"]
+    verbs: ["get", "list", "watch", "update", "patch"]
+  - apiGroups: [""]
+    resources: ["persistentvolumeclaims"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["persistentvolumeclaims/status"]
+    verbs: ["update", "patch"]
+  - apiGroups: [""]
+    resources: ["events"]
+    verbs: ["list", "watch", "create", "update", "patch"]
+  - apiGroups: ["coordination.k8s.io"]
+    resources: ["leases"]
+    verbs: ["get", "watch", "list", "delete", "update", "create", "patch"]
+  - apiGroups: [""]
+    resources: ["pods"]
+    verbs: ["get", "list", "watch"]
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: csi-azuredisk-controller-secret-role
+rules:
+  - apiGroups: [""]
+    resources: ["secrets"]
+    verbs: ["get"]
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-node.yaml
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: csi-azuredisk-node-role
+rules:
+  - apiGroups: [""]
+    resources: ["secrets"]
+    verbs: ["get"]
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["get"]
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-csi-provisioner-binding
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+subjects:
+  - kind: ServiceAccount
+    name: csi-azuredisk-controller-sa
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: azuredisk-external-provisioner-role
+  apiGroup: rbac.authorization.k8s.io
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-csi-attacher-binding
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+subjects:
+  - kind: ServiceAccount
+    name: csi-azuredisk-controller-sa
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: azuredisk-external-attacher-role
+  apiGroup: rbac.authorization.k8s.io
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-csi-snapshotter-binding
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+subjects:
+  - kind: ServiceAccount
+    name: csi-azuredisk-controller-sa
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: azuredisk-external-snapshotter-role
+  apiGroup: rbac.authorization.k8s.io
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: azuredisk-csi-resizer-role
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+subjects:
+  - kind: ServiceAccount
+    name: csi-azuredisk-controller-sa
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: azuredisk-external-resizer-role
+  apiGroup: rbac.authorization.k8s.io
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-controller.yaml
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: csi-azuredisk-controller-secret-binding
+subjects:
+  - kind: ServiceAccount
+    name: csi-azuredisk-controller-sa
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: csi-azuredisk-controller-secret-role
+  apiGroup: rbac.authorization.k8s.io
+---
+# Source: azuredisk-csi-driver/templates/rbac-csi-azuredisk-node.yaml
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: csi-azuredisk-node-secret-binding
+subjects:
+  - kind: ServiceAccount
+    name: csi-azuredisk-node-sa
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: csi-azuredisk-node-role
+  apiGroup: rbac.authorization.k8s.io
+---
+# Source: azuredisk-csi-driver/templates/csi-azuredisk-node.yaml
+kind: DaemonSet
+apiVersion: apps/v1
+metadata:
+  name: csi-azuredisk-node
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+spec:
+  updateStrategy:
+    rollingUpdate:
+      maxUnavailable: 1
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      app: csi-azuredisk-node
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/instance: "azuredisk-csi-driver"
+        app.kubernetes.io/managed-by: "Helm"
+        app.kubernetes.io/name: "azuredisk-csi-driver"
+        app.kubernetes.io/version: "v1.28.0"
+        helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+        app: csi-azuredisk-node
+    spec:
+      hostNetwork: true
+      dnsPolicy: Default
+      serviceAccountName: csi-azuredisk-node-sa
+      nodeSelector:
+        kubernetes.io/os: linux
+        node.cloudprovider.kubernetes.io/platform: azure
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+            - matchExpressions:
+              - key: type
+                operator: NotIn
+                values:
+                - virtual-kubelet
+      priorityClassName: system-node-critical
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
+      tolerations:
+        - operator: Exists
+      containers:
+        - name: liveness-probe
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+          image: "mcr.microsoft.com/oss/kubernetes-csi/livenessprobe:v2.10.0"
+          args:
+            - --csi-address=/csi/csi.sock
+            - --probe-timeout=3s
+            - --health-port=29603
+            - --v=2
+          resources:
+            limits:
+              memory: 100Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: node-driver-registrar
+          image: "mcr.microsoft.com/oss/kubernetes-csi/csi-node-driver-registrar:v2.8.0"
+          args:
+            - --csi-address=$(ADDRESS)
+            - --kubelet-registration-path=$(DRIVER_REG_SOCK_PATH)
+            - --v=2
+          livenessProbe:
+            exec:
+              command:
+                - /csi-node-driver-registrar
+                - --kubelet-registration-path=$(DRIVER_REG_SOCK_PATH)
+                - --mode=kubelet-registration-probe
+            initialDelaySeconds: 30
+            timeoutSeconds: 15
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+            - name: DRIVER_REG_SOCK_PATH
+              value: /var/lib/kubelet/plugins/disk.csi.azure.com/csi.sock
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+            - name: registration-dir
+              mountPath: /registration
+          resources:
+            limits:
+              memory: 100Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: azuredisk
+          image: "mcr.microsoft.com/oss/kubernetes-csi/azuredisk-csi:v1.28.0"
+          args:
+            - "--v=5"
+            - "--endpoint=$(CSI_ENDPOINT)"
+            - "--nodeid=$(KUBE_NODE_NAME)"
+            - "--enable-perf-optimization=true"
+            - "--drivername=disk.csi.azure.com"
+            - "--volume-attach-limit=-1"
+            # - "--cloud-config-secret-name=azure-cloud-provider"
+            # - "--cloud-config-secret-namespace=kube-system"
+            - "--custom-user-agent="
+            - "--user-agent-suffix=OSS-helm"
+            - "--allow-empty-cloud-config=true"
+            - "--support-zone=true"
+            - "--get-node-info-from-labels=false"
+            - "--get-nodeid-from-imds=false"
+          ports:
+            - containerPort: 29603
+              name: healthz
+              protocol: TCP
+          livenessProbe:
+            failureThreshold: 5
+            httpGet:
+              path: /healthz
+              port: healthz
+            initialDelaySeconds: 30
+            timeoutSeconds: 10
+            periodSeconds: 30
+          env:
+            - name: AZURE_CREDENTIAL_FILE
+              value: /etc/azure/azure.json
+            - name: CSI_ENDPOINT
+              value: unix:///csi/csi.sock
+            - name: KUBE_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  apiVersion: v1
+                  fieldPath: spec.nodeName
+          imagePullPolicy: IfNotPresent
+          securityContext:
+            privileged: true
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+            - mountPath: /var/lib/kubelet/
+              mountPropagation: Bidirectional
+              name: mountpoint-dir
+            - name: cloud-config
+              mountPath: /etc/azure
+              readOnly: true
+            - mountPath: /dev
+              name: device-dir
+            - mountPath: /sys/bus/scsi/devices
+              name: sys-devices-dir
+            - mountPath: /sys/class/
+              name: sys-class
+          resources:
+            limits:
+              memory: 200Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+      volumes:
+        - hostPath:
+            path: /var/lib/kubelet/plugins/disk.csi.azure.com
+            type: DirectoryOrCreate
+          name: socket-dir
+        - hostPath:
+            path: /var/lib/kubelet/
+            type: DirectoryOrCreate
+          name: mountpoint-dir
+        - hostPath:
+            path: /var/lib/kubelet/plugins_registry/
+            type: DirectoryOrCreate
+          name: registration-dir
+        - name: cloud-config
+          secret:
+            secretName: azure-managed-identity
+        - hostPath:
+            path: /dev
+            type: Directory
+          name: device-dir
+        - hostPath:
+            path: /sys/bus/scsi/devices
+            type: Directory
+          name: sys-devices-dir
+        - hostPath:
+            path: /sys/class/
+            type: Directory
+          name: sys-class
+---
+# Source: azuredisk-csi-driver/templates/csi-azuredisk-controller.yaml
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  name: csi-azuredisk-controller
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/instance: "azuredisk-csi-driver"
+    app.kubernetes.io/managed-by: "Helm"
+    app.kubernetes.io/name: "azuredisk-csi-driver"
+    app.kubernetes.io/version: "v1.28.0"
+    helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: csi-azuredisk-controller
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/instance: "azuredisk-csi-driver"
+        app.kubernetes.io/managed-by: "Helm"
+        app.kubernetes.io/name: "azuredisk-csi-driver"
+        app.kubernetes.io/version: "v1.28.0"
+        helm.sh/chart: "azuredisk-csi-driver-v1.28.0"
+        app: csi-azuredisk-controller
+    spec:
+      hostNetwork: true
+      serviceAccountName: csi-azuredisk-controller-sa
+      nodeSelector:
+        kubernetes.io/os: linux
+        node-role.kubernetes.io/control-plane: ""
+        node.cloudprovider.kubernetes.io/platform: azure
+      priorityClassName: system-cluster-critical
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
+      tolerations:
+        - effect: NoSchedule
+          key: node-role.kubernetes.io/control-plane
+      containers:
+        - name: csi-provisioner
+          image: "mcr.microsoft.com/oss/kubernetes-csi/csi-provisioner:v3.5.0"
+          args:
+            - "--feature-gates=Topology=true"
+            - "--csi-address=$(ADDRESS)"
+            - "--v=2"
+            - "--timeout=30s"
+            - "--leader-election"
+            - "--leader-election-namespace=kube-system"
+            - "--worker-threads=100"
+            - "--extra-create-metadata=true"
+            - "--strict-topology=true"
+            - "--kube-api-qps=50"
+            - "--kube-api-burst=100"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+          resources:
+            limits:
+              memory: 500Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: csi-attacher
+          image: "mcr.microsoft.com/oss/kubernetes-csi/csi-attacher:v4.3.0"
+          args:
+            - "-v=2"
+            - "-csi-address=$(ADDRESS)"
+            - "-timeout=1200s"
+            - "-leader-election"
+            - "--leader-election-namespace=kube-system"
+            - "-worker-threads=1000"
+            - "-kube-api-qps=200"
+            - "-kube-api-burst=400"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          volumeMounts:
+          - mountPath: /csi
+            name: socket-dir
+          resources:
+            limits:
+              memory: 500Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: csi-snapshotter
+          image: "mcr.microsoft.com/oss/kubernetes-csi/csi-snapshotter:v6.2.2"
+          args:
+            - "-csi-address=$(ADDRESS)"
+            - "-leader-election"
+            - "--leader-election-namespace=kube-system"
+            - "-v=2"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+          resources:
+            limits:
+              memory: 200Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: csi-resizer
+          image: "mcr.microsoft.com/oss/kubernetes-csi/csi-resizer:v1.8.0"
+          args:
+            - "-csi-address=$(ADDRESS)"
+            - "-v=2"
+            - "-leader-election"
+            - "--leader-election-namespace=kube-system"
+            - '-handle-volume-inuse-error=false'
+            - '-feature-gates=RecoverVolumeExpansionFailure=true'
+            - "-timeout=240s"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+          resources:
+            limits:
+              memory: 500Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: liveness-probe
+          image: "mcr.microsoft.com/oss/kubernetes-csi/livenessprobe:v2.10.0"
+          args:
+            - --csi-address=/csi/csi.sock
+            - --probe-timeout=3s
+            - --health-port=29602
+            - --v=2
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+          resources:
+            limits:
+              memory: 100Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+        - name: azuredisk
+          image: "mcr.microsoft.com/oss/kubernetes-csi/azuredisk-csi:v1.28.0"
+          args:
+            - "--v=5"
+            - "--endpoint=$(CSI_ENDPOINT)"
+            - "--metrics-address=0.0.0.0:29604"
+            - "--disable-avset-nodes=false"
+            - "--vm-type=vmss"
+            - "--drivername=disk.csi.azure.com"
+            # - "--cloud-config-secret-name=azure-managed-identity"
+            # - "--cloud-config-secret-namespace=kube-system"
+            - "--custom-user-agent="
+            - "--user-agent-suffix=OSS-helm"
+            - "--allow-empty-cloud-config=true"
+            - "--vmss-cache-ttl-seconds=-1"
+            - "--enable-traffic-manager=false"
+            - "--traffic-manager-port=7788"
+          ports:
+            - containerPort: 29602
+              name: healthz
+              protocol: TCP
+            - containerPort: 29604
+              name: metrics
+              protocol: TCP
+          livenessProbe:
+            failureThreshold: 5
+            httpGet:
+              path: /healthz
+              port: healthz
+            initialDelaySeconds: 30
+            timeoutSeconds: 10
+            periodSeconds: 30
+          env:
+            - name: AZURE_CREDENTIAL_FILE
+              value: /etc/azure/azure.json
+            - name: CSI_ENDPOINT
+              value: unix:///csi/csi.sock
+          imagePullPolicy: IfNotPresent
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+            - name: cloud-config
+              mountPath: /etc/azure
+              readOnly: true
+          resources:
+            limits:
+              memory: 500Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+      volumes:
+        - name: socket-dir
+          emptyDir: {}
+        - name: cloud-config
+          secret:
+            secretName: azure-managed-identity
+---
+# Source: azuredisk-csi-driver/templates/csi-azuredisk-driver.yaml
+apiVersion: storage.k8s.io/v1
+kind: CSIDriver
+metadata:
+  name: disk.csi.azure.com
+  annotations:
+    csiDriver: "v1.28.0"
+    snapshot: "v6.2.2"
+spec:
+  attachRequired: true
+  podInfoOnMount: false
+  fsGroupPolicy: File

azure/deployments/azuredisk-csi-driver.yaml

@@ -0,0 +1,25 @@
+
+controller:
+  cloudConfigSecretName: azure-managed-identity
+  cloudConfigSecretNamespace: kube-system
+
+  replicas: 1
+  vmType: vmss
+  allowEmptyCloudConfig: true
+
+  nodeSelector:
+    node-role.kubernetes.io/control-plane: ""
+    node.cloudprovider.kubernetes.io/platform: azure
+
+  tolerations:
+    - key: node-role.kubernetes.io/control-plane
+      effect: NoSchedule
+
+linux:
+  enabled: true
+
+  nodeSelector:
+    node.cloudprovider.kubernetes.io/platform: azure
+
+windows:
+  enabled: false

azure/deployments/azuredisk-storage.yaml

@@ -1,8 +1,6 @@
 apiVersion: storage.k8s.io/v1
 kind: StorageClass
 metadata:
-  annotations:
-    storageclass.kubernetes.io/is-default-class: "false"
   name: csi-azure-hdd-xfs
 provisioner: kubernetes.io/azure-disk
 parameters:
@@ -14,17 +12,10 @@ parameters:
 reclaimPolicy: Delete
 volumeBindingMode: WaitForFirstConsumer
 allowVolumeExpansion: true
-# allowedTopologies:
-# - matchLabelExpressions:
-#   - key: topology.disk.csi.azure.com/zone
-#     values:
-#     - azure
 ---
 apiVersion: storage.k8s.io/v1
 kind: StorageClass
 metadata:
-  annotations:
-    storageclass.kubernetes.io/is-default-class: "false"
   name: csi-azure-ssd-xfs
 provisioner: kubernetes.io/azure-disk
 parameters:
@@ -36,28 +27,37 @@ parameters:
 reclaimPolicy: Delete
 volumeBindingMode: WaitForFirstConsumer
 allowVolumeExpansion: true
-# allowedTopologies:
-# - matchLabelExpressions:
-#   - key: topology.disk.csi.azure.com/zone
-#     values:
-#     - azure
 ---
 apiVersion: storage.k8s.io/v1
 kind: StorageClass
 metadata:
-  annotations:
-    storageclass.kubernetes.io/is-default-class: "false"
   name: csi-azure-premium-xfs
 provisioner: kubernetes.io/azure-disk
 parameters:
   kind: Managed
   cachingMode: ReadOnly
   fsType: xfs
-  skuName: Premium_LRS # available values: Standard_LRS, Premium_LRS, StandardSSD_LRS and UltraSSD_LRS
+  skuName: Premium_LRS
   zoned: "true"
 reclaimPolicy: Delete
 volumeBindingMode: WaitForFirstConsumer
 allowVolumeExpansion: true
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: csi-azure-premium-2-xfs
+provisioner: kubernetes.io/azure-disk
+parameters:
+  fsType: xfs
+  kind: Managed
+  cachingMode: None
+  skuName: PremiumV2_LRS
+  perfProfile: Basic
+  # enableBursting: true
+reclaimPolicy: Delete
+volumeBindingMode: WaitForFirstConsumer
+allowVolumeExpansion: true
 # allowedTopologies:
 # - matchLabelExpressions:
 #   - key: topology.disk.csi.azure.com/zone

azure/deployments/test-as.yaml

@@ -22,6 +22,7 @@ spec:
         run: overprovisioning
     spec:
       nodeSelector:
+        node.cloudprovider.kubernetes.io/platform: azure
         project.io/node-pool: web
       affinity:
         podAntiAffinity:

azure/deployments/test-pv.yaml

@@ -16,12 +16,12 @@ spec:
     spec:
       nodeSelector:
         node.cloudprovider.kubernetes.io/platform: azure
+        # project.io/node-pool: worker
       tolerations:
         - effect: NoSchedule
           key: node-role.kubernetes.io/control-plane
       securityContext:
-        runAsNonRoot: true
+        runAsUser: 0
-        runAsUser: 1000
         seccompProfile:
           type: RuntimeDefault
       containers:
@@ -31,11 +31,6 @@ spec:
           volumeMounts:
             - name: persistent-storage
               mountPath: /mnt/azuredisk
-          securityContext:
-            allowPrivilegeEscalation: false
-            capabilities:
-              drop:
-              - ALL
   updateStrategy:
     type: RollingUpdate
   selector:
@@ -49,4 +44,5 @@ spec:
         resources:
           requests:
             storage: 10Gi
-        storageClassName: csi-azure-ssd-xfs
+        # storageClassName: csi-azure-ssd-xfs
+        storageClassName: csi-azure-premium-2-xfs

azure/init/policy.tf

@@ -72,7 +72,6 @@ resource "azurerm_role_definition" "csi" {
   }
 }
 
-
 resource "azurerm_role_definition" "scaler" {
   name              = "kubernetes-node-autoscaler"
   description       = "This is a kubernetes role for node autoscaler system, created via Terraform"

azure/instances-controlplane.tf

@@ -6,7 +6,7 @@ resource "azurerm_availability_set" "controlplane" {
   resource_group_name = local.resource_group
 
   platform_update_domain_count = 1
-  platform_fault_domain_count  = 2
+  platform_fault_domain_count  = 3
 
   tags = merge(var.tags, { type = "infra" })
 }
@@ -22,7 +22,7 @@ locals {
         region : region
         availability_set : azurerm_availability_set.controlplane[region].id
 
-        image : data.azurerm_shared_image_version.talos[startswith(lookup(try(var.controlplane[region], {}), "type", ""), "Standard_D2p") ? "Arm64" : "x64"].id
+        image : data.azurerm_shared_image_version.talos[length(regexall("^Standard_[DE][\\d+]p", lookup(try(var.controlplane[region], {}), "db_type", ""))) > 0 ? "Arm64" : "x64"].id
         type : lookup(try(var.controlplane[region], {}), "type", "Standard_B2ms")
 
         ip : 11 + inx
@@ -35,6 +35,12 @@ locals {
 
   lbv4s = [for ip in flatten([for c in local.network_controlplane : c.controlplane_lb]) : ip if length(split(".", ip)) > 1]
   lbv6s = [for ip in flatten([for c in local.network_controlplane : c.controlplane_lb]) : ip if length(split(":", ip)) > 1]
+  cpv4s = flatten([for cp in azurerm_network_interface.controlplane :
+    [for ip in cp.ip_configuration : ip.private_ip_address if ip.private_ip_address_version == "IPv4"]
+  ])
+  cpv6s = flatten([for cp in azurerm_network_interface.controlplane :
+    [for ip in cp.ip_configuration : ip.private_ip_address if ip.private_ip_address_version == "IPv6"]
+  ])
 }
 
 resource "azurerm_public_ip" "controlplane_v4" {
@@ -120,7 +126,7 @@ resource "local_file" "controlplane" {
         azurerm_public_ip.controlplane_v4[each.key].ip_address,
       ])
       ipAliases   = compact(each.value.network.controlplane_lb)
-      nodeSubnets = [cidrsubnet(each.value.network.cidr[0], 1, 0), "!${each.value.network.controlplane_lb[0]}"]
+      nodeSubnets = [cidrsubnet(each.value.network.cidr[0], 1, 0)]
 
       ccm = templatefile("${path.module}/deployments/azure.json.tpl", {
         subscriptionId = local.subscription_id
@@ -187,10 +193,18 @@ resource "azurerm_linux_virtual_machine" "controlplane" {
 }
 
 resource "azurerm_role_assignment" "controlplane" {
-  for_each             = local.controlplanes
+  for_each = { for k in flatten([
+    for cp in azurerm_linux_virtual_machine.controlplane : [
+      for role in var.controlplane_role_definition : {
+        name : "role-${cp.name}-${role}"
+        role : role
+        principal : cp.identity[0].principal_id
+      }
+    ]
+  ]) : k.name => k }
   scope                = "/subscriptions/${local.subscription_id}"
-  role_definition_name = var.controlplane_role_definition
+  role_definition_name = each.value.role
-  principal_id         = azurerm_linux_virtual_machine.controlplane[each.key].identity[0].principal_id
+  principal_id         = each.value.principal
 }
 
 locals {
@@ -203,18 +217,18 @@ resource "azurerm_private_dns_a_record" "controlplane" {
   resource_group_name = local.resource_group
   zone_name           = each.key
   ttl                 = 300
-  records             = local.lbv4s
+  records             = length(local.lbv4s) > 0 ? local.lbv4s : local.cpv4s
 
   tags = merge(var.tags, { type = "infra" })
 }
 
 resource "azurerm_private_dns_aaaa_record" "controlplane" {
-  for_each            = toset(values({ for zone, name in local.network : zone => name.dns if name.dns != "" && length(local.lbv6s) > 0 }))
+  for_each            = toset(values({ for zone, name in local.network : zone => name.dns if name.dns != "" && length(local.cpv6s) > 0 }))
   name                = split(".", var.kubernetes["apiDomain"])[0]
   resource_group_name = local.resource_group
   zone_name           = each.key
   ttl                 = 300
-  records             = local.lbv6s
+  records             = length(local.lbv6s) > 0 ? local.lbv6s : local.cpv6s
 
   tags = merge(var.tags, { type = "infra" })
 }

azure/instances-db.tf

@@ -7,14 +7,18 @@ resource "azurerm_linux_virtual_machine_scale_set" "db" {
   for_each = { for idx, name in local.regions : name => idx }
   location = each.key
 
-  instances                   = lookup(try(var.instances[each.key], {}), "db_count", 0)
+  instances                    = lookup(try(var.instances[each.key], {}), "db_count", 0)
-  name                        = "db-${lower(each.key)}"
+  name                         = "db-${lower(each.key)}"
-  computer_name_prefix        = "db-${lower(each.key)}-"
+  computer_name_prefix         = "db-${lower(each.key)}-"
-  resource_group_name         = local.resource_group
+  resource_group_name          = local.resource_group
-  sku                         = lookup(try(var.instances[each.key], {}), "db_type", "Standard_B2s")
+  sku                          = lookup(try(var.instances[each.key], {}), "db_type", "Standard_B2s")
-  provision_vm_agent          = false
+  provision_vm_agent           = false
-  overprovision               = false
+  overprovision                = false
-  platform_fault_domain_count = 2
+  platform_fault_domain_count  = 5
+  proximity_placement_group_id = azurerm_proximity_placement_group.common[each.key].id
+
+  # zone_balance = true
+  # zones        = ["0", "1", "2"]
 
   network_interface {
     name                      = "db-${lower(each.key)}"
@@ -44,7 +48,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "db" {
 
   custom_data = base64encode(templatefile("${path.module}/templates/worker.yaml.tpl",
     merge(var.kubernetes, {
-      lbv4        = local.network_controlplane[each.key].controlplane_lb[0]
+      lbv4        = try(local.network_controlplane[each.key].controlplane_lb[0], "")
       labels      = local.db_labels
       nodeSubnets = [local.network_public[each.key].cidr[0]]
     })
@@ -62,7 +66,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "db" {
     disk_size_gb         = 50
   }
 
-  source_image_id = data.azurerm_shared_image_version.talos[startswith(lookup(try(var.instances[each.key], {}), "db_type", ""), "Standard_D2p") ? "Arm64" : "x64"].id
+  source_image_id = data.azurerm_shared_image_version.talos[length(regexall("^Standard_[DE][\\d+]p", lookup(try(var.instances[each.key], {}), "db_type", ""))) > 0 ? "Arm64" : "x64"].id
   #   source_image_reference {
   #     publisher = "talos"
   #     offer     = "Talos"

azure/instances-web.tf

@@ -14,9 +14,12 @@ resource "azurerm_linux_virtual_machine_scale_set" "web" {
   sku                          = lookup(try(var.instances[each.key], {}), "web_type", "Standard_B2s")
   provision_vm_agent           = false
   overprovision                = false
-  platform_fault_domain_count  = 2
+  platform_fault_domain_count  = 5
   proximity_placement_group_id = azurerm_proximity_placement_group.common[each.key].id
 
+  # zone_balance = false
+  # zones        = ["1"]
+
   #   health_probe_id = local.network_public[each.key].sku != "Basic" ? azurerm_lb_probe.web[each.key].id : null
   #   automatic_instance_repair {
   #     enabled      = local.network_public[each.key].sku != "Basic"
@@ -51,7 +54,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "web" {
 
   custom_data = base64encode(templatefile("${path.module}/templates/worker.yaml.tpl",
     merge(var.kubernetes, {
-      lbv4        = local.network_controlplane[each.key].controlplane_lb[0]
+      lbv4        = try(local.network_controlplane[each.key].controlplane_lb[0], "")
       labels      = local.web_labels
       nodeSubnets = [local.network_public[each.key].cidr[0]]
     })
@@ -69,7 +72,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "web" {
     disk_size_gb         = 50
   }
 
-  source_image_id = data.azurerm_shared_image_version.talos[startswith(lookup(try(var.instances[each.key], {}), "worker_type", ""), "Standard_D2p") ? "Arm64" : "x64"].id
+  source_image_id = data.azurerm_shared_image_version.talos[length(regexall("^Standard_[DE][\\d+]p", lookup(try(var.instances[each.key], {}), "web_type", ""))) > 0 ? "Arm64" : "x64"].id
   #   source_image_reference {
   #     publisher = "talos"
   #     offer     = "Talos"

azure/instances-werker.tf

@@ -14,9 +14,29 @@ resource "azurerm_linux_virtual_machine_scale_set" "worker" {
   sku                          = lookup(try(var.instances[each.key], {}), "worker_type", "Standard_B2s")
   provision_vm_agent           = false
   overprovision                = false
-  platform_fault_domain_count  = 2
+  platform_fault_domain_count  = 5
   proximity_placement_group_id = azurerm_proximity_placement_group.common[each.key].id
 
+  # zone_balance = false
+  # zones        = ["1"]
+
+  # extension_operations_enabled = true
+  # extension {
+  #   name                       = "KubeletHealth"
+  #   publisher                  = "Microsoft.ManagedServices"
+  #   type                       = "ApplicationHealthLinux"
+  #   type_handler_version       = "1.0"
+  #   auto_upgrade_minor_version = false
+
+  #   settings = jsonencode({
+  #     protocol : "http"
+  #     port : "10248"
+  #     requestPath : "/healthz"
+  #     intervalInSeconds : 60
+  #     numberOfProbes : 3
+  #   })
+  # }
+
   network_interface {
     name                      = "worker-${lower(each.key)}"
     primary                   = true
@@ -46,7 +66,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "worker" {
 
   custom_data = base64encode(templatefile("${path.module}/templates/worker.yaml.tpl",
     merge(var.kubernetes, {
-      lbv4        = local.network_controlplane[each.key].controlplane_lb[0]
+      lbv4        = try(local.network_controlplane[each.key].controlplane_lb[0], "")
       labels      = local.worker_labels
       nodeSubnets = [local.network_private[each.key].cidr[0]]
     })
@@ -72,7 +92,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "worker" {
     }
   }
 
-  source_image_id = data.azurerm_shared_image_version.talos[startswith(lookup(try(var.instances[each.key], {}), "worker_type", ""), "Standard_D2p") ? "Arm64" : "x64"].id
+  source_image_id = data.azurerm_shared_image_version.talos[length(regexall("^Standard_[DE][\\d+]p", lookup(try(var.instances[each.key], {}), "worker_type", ""))) > 0 ? "Arm64" : "x64"].id
   #   source_image_reference {
   #     publisher = "talos"
   #     offer     = "Talos"

azure/prepare/network-gw.tf

@@ -79,8 +79,8 @@ resource "azurerm_linux_virtual_machine" "router" {
 
   source_image_reference {
     publisher = "Debian"
-    offer     = "debian-11"
+    offer     = "debian-12"
-    sku       = "11-gen2"
+    sku       = "12-gen2"
     version   = "latest"
   }
 

azure/prepare/network-lb.tf

@@ -1,6 +1,6 @@
 
 resource "azurerm_lb" "controlplane" {
-  for_each            = { for idx, name in var.regions : name => idx }
+  for_each            = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) }
   location            = each.key
   name                = "controlplane-${each.key}"
   resource_group_name = var.resource_group
@@ -22,7 +22,7 @@ resource "azurerm_lb" "controlplane" {
 }
 
 resource "azurerm_lb_probe" "controlplane" {
-  for_each            = { for idx, name in var.regions : name => idx }
+  for_each            = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) }
   name                = "controlplane-tcp-probe"
   loadbalancer_id     = azurerm_lb.controlplane[each.key].id
   interval_in_seconds = 30
@@ -31,19 +31,19 @@ resource "azurerm_lb_probe" "controlplane" {
 }
 
 resource "azurerm_lb_backend_address_pool" "controlplane_v4" {
-  for_each        = { for idx, name in var.regions : name => idx }
+  for_each        = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) }
   loadbalancer_id = azurerm_lb.controlplane[each.key].id
   name            = "controlplane-pool-v4"
 }
 
 resource "azurerm_lb_backend_address_pool" "controlplane_v6" {
-  for_each        = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_sku, "Basic") != "Basic" }
+  for_each        = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) && try(var.capabilities[name].network_lb_sku, "Basic") != "Basic" }
   loadbalancer_id = azurerm_lb.controlplane[each.key].id
   name            = "controlplane-pool-v6"
 }
 
 resource "azurerm_lb_rule" "kubernetes_v4" {
-  for_each                       = { for idx, name in var.regions : name => idx }
+  for_each                       = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) }
   name                           = "controlplane-v4"
   loadbalancer_id                = azurerm_lb.controlplane[each.key].id
   frontend_ip_configuration_name = "controlplane-lb-v4"
@@ -57,7 +57,7 @@ resource "azurerm_lb_rule" "kubernetes_v4" {
 }
 
 resource "azurerm_lb_rule" "kubernetes_v6" {
-  for_each                       = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_sku, "Basic") != "Basic" }
+  for_each                       = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) && try(var.capabilities[name].network_lb_sku, "Basic") != "Basic" }
   name                           = "controlplane-v6"
   loadbalancer_id                = azurerm_lb.controlplane[each.key].id
   frontend_ip_configuration_name = "controlplane-lb-v6"
@@ -71,7 +71,7 @@ resource "azurerm_lb_rule" "kubernetes_v6" {
 }
 
 resource "azurerm_lb_rule" "talos" {
-  for_each                       = { for idx, name in var.regions : name => idx }
+  for_each                       = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) }
   name                           = "controlplane-talos-v4"
   loadbalancer_id                = azurerm_lb.controlplane[each.key].id
   frontend_ip_configuration_name = "controlplane-lb-v4"
@@ -85,7 +85,7 @@ resource "azurerm_lb_rule" "talos" {
 }
 
 resource "azurerm_lb_rule" "talos_v6" {
-  for_each                       = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_sku, "Basic") != "Basic" }
+  for_each                       = { for idx, name in var.regions : name => idx if try(var.capabilities[name].network_lb_enable, false) && try(var.capabilities[name].network_lb_sku, "Basic") != "Basic" }
   name                           = "controlplane-talos-v6"
   loadbalancer_id                = azurerm_lb.controlplane[each.key].id
   frontend_ip_configuration_name = "controlplane-lb-v6"

azure/prepare/network.tf

@@ -79,6 +79,8 @@ resource "azurerm_virtual_network_peering" "peering" {
   allow_virtual_network_access = true
   allow_forwarded_traffic      = true
   allow_gateway_transit        = false
+
+  depends_on = [azurerm_virtual_network.main]
 }
 
 resource "azurerm_route_table" "main" {

azure/prepare/outputs.tf

@@ -16,50 +16,50 @@ output "resource_group" {
 
 output "network" {
   description = "The network"
-  value = { for zone, net in azurerm_virtual_network.main : zone => {
+  value = { for region, net in azurerm_virtual_network.main : region => {
     name    = net.name
-    nat     = try(azurerm_public_ip.nat[zone].ip_address, "")
+    nat     = try(azurerm_public_ip.nat[region].ip_address, "")
     dns     = try(azurerm_private_dns_zone.main[0].name, "")
-    peering = try(azurerm_linux_virtual_machine.router[zone].private_ip_addresses, [])
+    peering = try(azurerm_linux_virtual_machine.router[region].private_ip_addresses, [])
   } }
 }
 
 output "network_controlplane" {
   description = "The controlplane network"
-  value = { for zone, subnet in azurerm_subnet.controlplane : zone => {
+  value = { for region, subnet in azurerm_subnet.controlplane : region => {
     network_id           = subnet.id
     cidr                 = subnet.address_prefixes
-    sku                  = azurerm_lb.controlplane[zone].sku
+    sku                  = try(var.capabilities[region].network_lb_sku, "Basic")
-    controlplane_pool_v4 = try(azurerm_lb_backend_address_pool.controlplane_v4[zone].id, "")
+    controlplane_pool_v4 = try(var.capabilities[region].network_lb_enable, false) ? try(azurerm_lb_backend_address_pool.controlplane_v4[region].id, "") : ""
-    controlplane_pool_v6 = try(azurerm_lb_backend_address_pool.controlplane_v6[zone].id, "")
+    controlplane_pool_v6 = try(var.capabilities[region].network_lb_enable, false) ? try(azurerm_lb_backend_address_pool.controlplane_v6[region].id, "") : ""
-    controlplane_lb      = azurerm_lb.controlplane[zone].private_ip_addresses
+    controlplane_lb      = try(var.capabilities[region].network_lb_enable, false) ? azurerm_lb.controlplane[region].private_ip_addresses : []
   } }
 }
 
 output "network_public" {
   description = "The public network"
-  value = { for zone, subnet in azurerm_subnet.public : zone => {
+  value = { for region, subnet in azurerm_subnet.public : region => {
     network_id = subnet.id
     cidr       = subnet.address_prefixes
-    sku        = var.capabilities[zone].network_gw_sku
+    sku        = var.capabilities[region].network_gw_sku
   } }
 }
 
 output "network_private" {
   description = "The private network"
-  value = { for zone, subnet in azurerm_subnet.private : zone => {
+  value = { for region, subnet in azurerm_subnet.private : region => {
     network_id = subnet.id
     cidr       = subnet.address_prefixes
-    nat        = try(azurerm_public_ip.nat[zone].ip_address, "")
+    nat        = try(azurerm_public_ip.nat[region].ip_address, "")
-    sku        = try(azurerm_public_ip.nat[zone].ip_address, "") == "" ? "Standard" : var.capabilities[zone].network_gw_sku
+    sku        = try(azurerm_public_ip.nat[region].ip_address, "") == "" ? "Standard" : var.capabilities[region].network_gw_sku
   } }
 }
 
 output "secgroups" {
   description = "List of secgroups"
-  value = { for zone, subnet in azurerm_subnet.private : zone => {
+  value = { for region, subnet in azurerm_subnet.private : region => {
-    common       = azurerm_network_security_group.common[zone].id
+    common       = azurerm_network_security_group.common[region].id
-    controlplane = azurerm_network_security_group.controlplane[zone].id
+    controlplane = azurerm_network_security_group.controlplane[region].id
-    web          = azurerm_network_security_group.web[zone].id
+    web          = azurerm_network_security_group.web[region].id
   } }
 }

azure/prepare/variables.tf

@@ -72,6 +72,7 @@ variable "capabilities" {
     },
     "uksouth" = {
       network_nat_enable = false,
+      network_lb_enable  = false
       network_lb_sku     = "Basic", # Standard
       network_gw_enable  = false,
       network_gw_type    = "Standard_B1s",
@@ -79,6 +80,7 @@ variable "capabilities" {
     },
     "ukwest" = {
       network_nat_enable = false,
+      network_lb_enable  = false
       network_lb_sku     = "Basic",
       network_gw_enable  = false,
       network_gw_type    = "Standard_B1s",

azure/templates/controlplane.yaml.tpl

@@ -19,8 +19,10 @@ machine:
         routes:
           - network: ::/0
             gateway: fe80::1234:5678:9abc
+%{if length(ipAliases) > 0 }
       - interface: lo
         addresses: ${format("%#v",ipAliases)}
+%{endif}
       - interface: dummy0
         addresses:
           - 169.254.2.53/32
@@ -85,13 +87,13 @@ cluster:
       election-timeout: "5000"
       heartbeat-interval: "1000"
   inlineManifests:
-    - name: azure-cloud-controller-config
+    - name: azure-managed-identity
       contents: |-
         apiVersion: v1
         kind: Secret
         type: Opaque
         metadata:
-          name: azure-cloud-controller-manager
+          name: azure-managed-identity
           namespace: kube-system
         data:
           azure.json: ${base64encode(ccm)}
@@ -100,9 +102,8 @@ cluster:
     manifests:
       - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/_deployments/vars/talos-cloud-controller-manager-result.yaml
       - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/azure/deployments/azure-cloud-controller-manager.yaml
-      - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/azure/deployments/azure-csi-node.yaml
+      - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/azure/deployments/azuredisk-csi-driver-result.yaml
-      - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/azure/deployments/azure-csi.yaml
+      - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/azure/deployments/azuredisk-storage.yaml
-      - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/azure/deployments/azure-storage.yaml
       - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/_deployments/vars/metrics-server-result.yaml
       - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/_deployments/vars/local-path-storage-ns.yaml
       - https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/_deployments/vars/local-path-storage-result.yaml

azure/templates/worker.yaml.tpl

@@ -28,10 +28,15 @@ machine:
       - interface: dummy0
         addresses:
           - 169.254.2.53/32
+%{if lbv4 != "" }
     extraHostEntries:
       - ip: ${lbv4}
         aliases:
           - ${apiDomain}
+%{endif}
+  time:
+    servers:
+      - time.cloudflare.com
   install:
     wipe: false
   sysctls:

azure/variables.tf

@@ -1,6 +1,6 @@
 
 variable "controlplane_role_definition" {
-  default = "kubernetes-ccm"
+  default = ["kubernetes-ccm", "kubernetes-csi", "kubernetes-node-autoscaler"]
 }
 
 variable "gallery_name" {