oracle-quickstart · streamnsight · Mar 11, 2023 · Mar 10, 2023 · Mar 10, 2023 · Mar 10, 2023
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,4 @@
+.terraform
+.terraform.lock.hcl
+terraform.tfstate
+terraform.tfstate.backup
diff --git a/cluster_autoscaler.yaml b/cluster_autoscaler.yaml
@@ -0,0 +1,182 @@
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    k8s-addon: cluster-autoscaler.addons.k8s.io
+    k8s-app: cluster-autoscaler
+  name: cluster-autoscaler
+  namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: cluster-autoscaler
+  labels:
+    k8s-addon: cluster-autoscaler.addons.k8s.io
+    k8s-app: cluster-autoscaler
+rules:
+  - apiGroups: [""]
+    resources: ["events", "endpoints"]
+    verbs: ["create", "patch"]
+  - apiGroups: [""]
+    resources: ["pods/eviction"]
+    verbs: ["create"]
+  - apiGroups: [""]
+    resources: ["pods/status"]
+    verbs: ["update"]
+  - apiGroups: [""]
+    resources: ["endpoints"]
+    resourceNames: ["cluster-autoscaler"]
+    verbs: ["get", "update"]
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["watch", "list", "get", "patch", "update"]
+  - apiGroups: [""]
+    resources:
+      - "pods"
+      - "services"
+      - "replicationcontrollers"
+      - "persistentvolumeclaims"
+      - "persistentvolumes"
+      - "namespaces"
+    verbs: ["watch", "list", "get"]
+  - apiGroups: ["extensions"]
+    resources: ["replicasets", "daemonsets"]
+    verbs: ["watch", "list", "get"]
+  - apiGroups: ["policy"]
+    resources: ["poddisruptionbudgets"]
+    verbs: ["watch", "list"]
+  - apiGroups: ["apps"]
+    resources: ["statefulsets", "replicasets", "daemonsets"]
+    verbs: ["watch", "list", "get"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["storageclasses", "csinodes", "csistoragecapacities", "csidrivers"]
+    verbs: ["watch", "list", "get"]
+  - apiGroups: ["batch", "extensions"]
+    resources: ["jobs"]
+    verbs: ["get", "list", "watch", "patch"]
+  - apiGroups: ["coordination.k8s.io"]
+    resources: ["leases"]
+    verbs: ["create"]
+  - apiGroups: ["coordination.k8s.io"]
+    resourceNames: ["cluster-autoscaler"]
+    resources: ["leases"]
+    verbs: ["get", "update"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: cluster-autoscaler
+  namespace: kube-system
+  labels:
+    k8s-addon: cluster-autoscaler.addons.k8s.io
+    k8s-app: cluster-autoscaler
+rules:
+  - apiGroups: [""]
+    resources: ["configmaps"]
+    verbs: ["create","list","watch"]
+  - apiGroups: [""]
+    resources: ["configmaps"]
+    resourceNames: ["cluster-autoscaler-status", "cluster-autoscaler-priority-expander"]
+    verbs: ["delete", "get", "update", "watch"]
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: cluster-autoscaler
+  labels:
+    k8s-addon: cluster-autoscaler.addons.k8s.io
+    k8s-app: cluster-autoscaler
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: cluster-autoscaler
+subjects:
+  - kind: ServiceAccount
+    name: cluster-autoscaler
+    namespace: kube-system
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: cluster-autoscaler
+  namespace: kube-system
+  labels:
+    k8s-addon: cluster-autoscaler.addons.k8s.io
+    k8s-app: cluster-autoscaler
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: cluster-autoscaler
+subjects:
+  - kind: ServiceAccount
+    name: cluster-autoscaler
+    namespace: kube-system
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: cluster-autoscaler
+  namespace: kube-system
+  labels:
+    app: cluster-autoscaler
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: cluster-autoscaler
+  template:
+    metadata:
+      labels:
+        app: cluster-autoscaler
+      annotations:
+        prometheus.io/scrape: 'true'
+        prometheus.io/port: '8085'
+    spec:
+      serviceAccountName: cluster-autoscaler
+      containers:
+        - image: ${image}
+          name: cluster-autoscaler
+          resources:
+            limits:
+              cpu: 100m
+              memory: 300Mi
+            requests:
+              cpu: 100m
+              memory: 300Mi
+          command:
+            - ./cluster-autoscaler
+            - --v=4
+            - --stderrthreshold=info
+            - --cloud-provider=oci-oke
+            - --max-node-provision-time=25m
+            ${node_pools_settings}
+            - --scale-down-delay-after-add=10m
+            - --scale-down-unneeded-time=10m
+            - --unremovable-node-recheck-timeout=5m
+            - --balance-similar-node-groups
+            - --balancing-ignore-label=displayName
+            - --balancing-ignore-label=hostname
+            - --balancing-ignore-label=internal_addr
+            - --balancing-ignore-label=oci.oraclecloud.com/fault-domain
+          imagePullPolicy: "Always"
+          env:
+          - name: OKE_USE_INSTANCE_PRINCIPAL
+            value: "true"
+          - name: OCI_SDK_APPEND_USER_AGENT
+            value: "oci-oke-cluster-autoscaler"
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: coredns-pdb
+  namespace: kube-system
+spec:
+  maxUnavailable: 1
+  selector:
+    matchLabels:
+      k8s-app: kube-dns
diff --git a/datasources.tf b/datasources.tf
@@ -43,36 +43,6 @@ data "oci_identity_availability_domains" "ADs" {
   compartment_id = var.tenancy_ocid
 }
 
-# data "oci_containerengine_cluster_kube_config" "KubeConfig" {
-#   cluster_id    = oci_containerengine_cluster.oci_oke_cluster.id
-#   token_version = var.cluster_kube_config_token_version
-# }
-
-
-# locals {
-#   gpu = {
-#     sources = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.sources : s if length(regexall(".*Gen2-GPU.*", s.source_name)) > 0]
-#     shapes = {
-#       BM = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.shapes : s if length(regexall("BM[.]GPU.*", s)) > 0]
-#       VM = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.shapes : s if length(regexall("VM[.]GPU.*", s)) > 0]
-#     }
-#   }
-#   arm = {
-#     sources = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.sources : s if length(regexall(".*aarch64.*", s.source_name)) > 0]
-#     shapes = {
-#       BM = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.shapes : s if length(regexall("BM[.]Standard[.]A1.*", s)) > 0]
-#       VM = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.shapes : s if length(regexall("VM[.]Standard[.]A1.*", s)) > 0]
-#     }
-#   }
-#   x86 = {
-#     sources = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.sources : s if length(regexall(".*(aarch64|Gen2-GPU).*", s.source_name)) == 0]
-#     shapes = {
-#       BM = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.shapes : s if length(regexall(".*(GPU|A1).*", s)) == 0 && length(regexall("BM.*", s)) > 0]
-#       VM = [for s in data.oci_containerengine_node_pool_option.oci_oke_node_pool_option.shapes : s if length(regexall(".*(GPU|A1).*", s)) == 0 && length(regexall("VM.*", s)) > 0]
-#     }
-#   }
-# }
-
 data "oci_limits_limit_definitions" "limit_def" {
   compartment_id = var.tenancy_ocid
   service_name   = "compute"
@@ -104,22 +74,6 @@ data "oci_core_shapes" "valid_shapes" {
   availability_domain = data.oci_identity_availability_domains.ADs.availability_domains[count.index].name
 }
 
-# output valid_shapes {
-#   value = data.oci_core_shapes.valid_shapes.*.shapes
-# }
-
-# output "shape_ad_availability" {
-#   value = local.shape_ad_availability
-# }
-
-# output "limits" {
-#   value = local.availability_map
-# }
-
-# output "limits_definitions" {
-#   value = local.limits_definitions
-# }
-
 resource "random_string" "deploy_id" {
   length      = 4
   special     = false

diff --git a/helm_cert_manager.tf b/helm_cert_manager.tf
@@ -8,24 +8,75 @@ locals {
   enable_cert_manager = var.enable_flink ? true : var.enable_cert_manager
 }
 
-resource "helm_release" "cert_manager" {
-  count            = local.enable_cert_manager ? 1 : 0
-  name             = "cert-manager"
-  repository       = "https://charts.jetstack.io"
-  chart            = "cert-manager"
-  version          = "1.8.2"
-  namespace        = "cert-manager"
-  create_namespace = true
-  wait             = true # wait to allow the webhook be properly configured
-
-  set {
-    name  = "installCRDs"
-    value = true
+# resource "helm_release" "cert_manager" {
+#   count            = local.enable_cert_manager ? 1 : 0
+#   name             = "cert-manager"
+#   repository       = "https://charts.jetstack.io"
+#   chart            = "cert-manager"
+#   version          = "1.8.2"
+#   namespace        = "cert-manager"
+#   create_namespace = true
+#   wait             = true # wait to allow the webhook be properly configured
+
+#   set {
+#     name  = "installCRDs"
+#     value = true
+#   }
+
+#   set {
+#     name  = "webhook.timeoutSeconds"
+#     value = "30"
+#   }
+#   depends_on = [oci_containerengine_cluster.oci_oke_cluster]
+# }
+
+
+resource "null_resource" "cert_manager" {
+  count = local.enable_cert_manager ? 1 : 0
+
+  provisioner "local-exec" {
+    command = "mkdir -p ~/.kube/ && oci ce cluster create-kubeconfig --cluster-id $CLUSTER_ID --file ~/.kube/config --region us-sanjose-1 --token-version 2.0.0  --kube-endpoint $ENDPOINT_TYPE"
+
+    environment = {
+      CLUSTER_ID    = oci_containerengine_cluster.oci_oke_cluster.id
+      ENDPOINT_TYPE = var.is_endpoint_public ? "PUBLIC_ENDPOINT" : "PRIVATE_ENDPOINT"
+    }
+  }
+
+  provisioner "local-exec" {
+    command = "helm repo add cert-manager https://charts.jetstack.io"
+  }
+
+
+  provisioner "local-exec" {
+    command = "kubectl create ns cert-manager"
+  }
+
+  provisioner "local-exec" {
+    command = "helm install cert-manager cert-manager/cert-manager -n cert-manager --version 1.8.2 --set installCRDs=true --set webhook.timeoutSeconds=30 --wait"
+  }
+
+  provisioner "local-exec" {
+    when       = destroy
+    command    = "helm uninstall cert-manager -n cert-manager"
+    on_failure = continue
   }
 
-  set {
-    name  = "webhook.timeoutSeconds"
-    value = "30"
+  provisioner "local-exec" {
+    when       = destroy
+    command    = "helm repo remove cert-manager"
+    on_failure = continue
   }
-  depends_on = [oci_containerengine_cluster.oci_oke_cluster]
-}
+
+  provisioner "local-exec" {
+    when       = destroy
+    command    = "kubectl delete ns cert-manager"
+    on_failure = continue
+  }
+
+  depends_on = [
+    oci_containerengine_cluster.oci_oke_cluster,
+    oci_containerengine_node_pool.oci_oke_node_pool
+  ]
+
+}