create tidb cluster on ack with cr (#2012)

* create tidb cluster on ack with cr

* update variable name

* update variable name

* update default replicas

deploy/aliyun/main.tf

@@ -71,17 +71,17 @@ module "tidb-cluster" {
     helm = helm.default
   }
 
-  cluster_name = "my-cluster"
+  cluster_name = var.tidb_cluster_name
   ack          = module.tidb-operator
 
-  tidb_version               = var.tidb_version
-  tidb_cluster_chart_version = var.tidb_cluster_chart_version
-  pd_instance_type           = var.pd_instance_type
-  pd_count                   = var.pd_count
-  tikv_instance_type         = var.tikv_instance_type
-  tikv_count                 = var.tikv_count
-  tidb_instance_type         = var.tidb_instance_type
-  tidb_count                 = var.tidb_count
-  monitor_instance_type      = var.monitor_instance_type
-  override_values            = file("my-cluster.yaml")
+  tidb_version                = var.tidb_version
+  tidb_cluster_chart_version  = var.tidb_cluster_chart_version
+  pd_instance_type            = var.pd_instance_type
+  pd_count                    = var.pd_count
+  tikv_instance_type          = var.tikv_instance_type
+  tikv_count                  = var.tikv_count
+  tidb_instance_type          = var.tidb_instance_type
+  tidb_count                  = var.tidb_count
+  monitor_instance_type       = var.monitor_instance_type
+  create_tidb_cluster_release = var.create_tidb_cluster_release
 }

deploy/aliyun/manifests/db-monitor.yaml.example

@@ -0,0 +1,86 @@
+apiVersion: pingcap.com/v1alpha1
+kind: TidbMonitor
+metadata:
+  name: TIDB_CLUSTER_NAME
+spec:
+  alertmanagerURL: ""
+  annotations: {}
+  clusters:
+  - name: TIDB_CLUSTER_NAME
+  grafana:
+    baseImage: grafana/grafana
+    envs:
+      # Configure Grafana using environment variables except GF_PATHS_DATA, GF_SECURITY_ADMIN_USER and GF_SECURITY_ADMIN_PASSWORD
+      # Ref https://grafana.com/docs/installation/configuration/#using-environment-variables
+      GF_AUTH_ANONYMOUS_ENABLED: "true"
+      GF_AUTH_ANONYMOUS_ORG_NAME: "Main Org."
+      GF_AUTH_ANONYMOUS_ORG_ROLE: "Viewer"
+      # if grafana is running behind a reverse proxy with subpath http://foo.bar/grafana
+      # GF_SERVER_DOMAIN: foo.bar
+      # GF_SERVER_ROOT_URL: "%(protocol)s://%(domain)s/grafana/"
+    imagePullPolicy: IfNotPresent
+    logLevel: info
+    password: admin
+    resources: {}
+    #  limits:
+    #    cpu: 8000m
+    #    memory: 8Gi
+    #  requests:
+    #    cpu: 4000m
+    #    memory: 4Gi
+    service:
+      portName: http-grafana
+      type: LoadBalancer
+      annotations:
+        service.beta.kubernetes.io/alicloud-loadbalancer-address-type: internet
+    username: admin
+    version: 6.0.1
+  imagePullPolicy: IfNotPresent
+  initializer:
+    baseImage: pingcap/tidb-monitor-initializer
+    imagePullPolicy: IfNotPresent
+    resources: {}
+    #  limits:
+    #    cpu: 50m
+    #    memory: 64Mi
+    #  requests:
+    #    cpu: 50m
+    #    memory: 64Mi
+    version: v3.0.12
+  kubePrometheusURL: ""
+  nodeSelector: {}
+  persistent: true
+  prometheus:
+    baseImage: prom/prometheus
+    imagePullPolicy: IfNotPresent
+    logLevel: info
+    reserveDays: 12
+    resources: {}
+    #  limits:
+    #    cpu: 8000m
+    #    memory: 8Gi
+    #  requests:
+    #    cpu: 4000m
+    #    memory: 4Gi
+    service:
+      portName: http-prometheus
+      type: NodePort
+    version: v2.11.1
+  reloader:
+    baseImage: pingcap/tidb-monitor-reloader
+    imagePullPolicy: IfNotPresent
+    resources: {}
+    #  limits:
+    #    cpu: 50m
+    #    memory: 64Mi
+    #  requests:
+    #    cpu: 50m
+    #    memory: 64Mi
+    service:
+      portName: tcp-reloader
+      type: NodePort
+    version: v1.0.1
+  storage: 100Gi
+  storageClassName: alicloud-disk-available
+  tolerations: []
+

deploy/aliyun/manifests/db.yaml.example

@@ -0,0 +1,110 @@
+apiVersion: pingcap.com/v1alpha1
+kind: TidbCluster
+metadata:
+  name: TIDB_CLUSTER_NAME
+spec:
+  configUpdateStrategy: RollingUpdate
+  enableTLSCluster: false
+  helper:
+    image: busybox:1.31.1
+  hostNetwork: false
+  imagePullPolicy: IfNotPresent
+  pd:
+    affinity: {}
+    baseImage: pingcap/pd
+    config:
+      log:
+        level: info
+    nodeSelector:
+      dedicated: TIDB_CLUSTER_NAME-pd
+    podSecurityContext: {}
+    replicas: 3
+    requests:
+      cpu: "1"
+      memory: 400Mi
+      storage: 20Gi
+    storageClassName: alicloud-disk
+    tolerations:
+    - effect: NoSchedule
+      key: dedicated
+      operator: Equal
+      value: TIDB_CLUSTER_NAME-pd
+  pvReclaimPolicy: Retain
+  schedulerName: tidb-scheduler
+  tidb:
+    affinity: {}
+    annotations:
+      tidb.pingcap.com/sysctl-init: "true"
+    baseImage: pingcap/tidb
+    config:
+      log:
+        level: info
+      performance:
+        max-procs: 0
+        tcp-keep-alive: true
+    enableTLSClient: false
+    maxFailoverCount: 3
+    nodeSelector:
+      dedicated: TIDB_CLUSTER_NAME-tidb
+    podSecurityContext:
+      sysctls:
+      - name: net.ipv4.tcp_keepalive_time
+        value: "300"
+      - name: net.ipv4.tcp_keepalive_intvl
+        value: "75"
+      - name: net.core.somaxconn
+        value: "32768"
+    replicas: 2
+    requests:
+      cpu: "1"
+      memory: 400Mi
+    separateSlowLog: true
+    service:
+      annotations:
+        service.beta.kubernetes.io/alicloud-loadbalancer-address-type: intranet
+        service.beta.kubernetes.io/alicloud-loadbalancer-slb-network-type: vpc
+      exposeStatus: true
+      externalTrafficPolicy: Local
+      type: LoadBalancer
+    slowLogTailer:
+      limits:
+        cpu: 100m
+        memory: 50Mi
+      requests:
+        cpu: 20m
+        memory: 5Mi
+    tolerations:
+    - effect: NoSchedule
+      key: dedicated
+      operator: Equal
+      value: TIDB_CLUSTER_NAME-tidb
+  tikv:
+    affinity: {}
+    annotations:
+      tidb.pingcap.com/sysctl-init: "true"
+    baseImage: pingcap/tikv
+    config:
+      log-level: info
+    hostNetwork: false
+    maxFailoverCount: 3
+    nodeSelector:
+      dedicated: TIDB_CLUSTER_NAME-tikv
+    podSecurityContext:
+      sysctls:
+      - name: net.core.somaxconn
+        value: "32768"
+    privileged: false
+    replicas: 3
+    requests:
+      cpu: "1"
+      memory: 2Gi
+      storage: 100Gi
+    storageClassName: local-volume
+    tolerations:
+    - effect: NoSchedule
+      key: dedicated
+      operator: Equal
+      value: TIDB_CLUSTER_NAME-tikv
+  timezone: UTC
+  version: v3.0.12
+

deploy/aliyun/variables.tf

@@ -10,7 +10,7 @@ variable "bastion_cpu_core_count" {
 
 variable "operator_version" {
   type    = string
-  default = "v1.0.6"
+  default = "v1.1.0"
 }
 
 variable "operator_helm_values" {
@@ -112,3 +112,13 @@ variable "vpc_cidr" {
   description = "VPC cidr_block, options: [192.168.0.0.0/16, 172.16.0.0/16, 10.0.0.0/8], cannot collidate with kubernetes service cidr and pod cidr. Cannot change once the vpc created."
   default     = "192.168.0.0/16"
 }
+
+variable "create_tidb_cluster_release" {
+  description = "whether creating tidb-cluster helm release"
+  default     = false
+}
+
+variable "tidb_cluster_name" {
+  description = "The TiDB cluster name"
+  default     = "my-cluster"
+}

deploy/modules/aliyun/tidb-cluster/main.tf

@@ -12,4 +12,5 @@ module "tidb-cluster" {
   base_values                = file("${path.module}/values/default.yaml")
   kubeconfig_filename        = var.ack.kubeconfig_filename
   service_ingress_key        = "ip"
+  create                     = var.create_tidb_cluster_release
 }

deploy/modules/aliyun/tidb-cluster/variables.tf

@@ -65,3 +65,8 @@ variable "local_exec_interpreter" {
   type        = list(string)
   default     = ["/bin/sh", "-c"]
 }
+
+variable "create_tidb_cluster_release" {
+  description = "whether creating tidb-cluster helm release"
+  default     = false
+}

deploy/modules/aliyun/tidb-operator/operator.tf

@@ -25,10 +25,11 @@ resource "null_resource" "setup-env" {
     # it manually and the resource namespace & name are hard-coded by convention
     command = <<EOS
 kubectl apply -f https://raw.githubusercontent.com/pingcap/tidb-operator/${var.operator_version}/manifests/crd.yaml
+kubectl apply -f https://raw.githubusercontent.com/pingcap/tidb-operator/${var.operator_version}/manifests/tiller-rbac.yaml
 kubectl apply -f ${path.module}/manifest/alicloud-disk-storageclass.yaml
 echo '${data.template_file.local-volume-provisioner.rendered}' | kubectl apply -f -
 kubectl patch -n kube-system daemonset flexvolume --type='json' -p='[{"op":"replace", "path": "/spec/template/spec/tolerations", "value":[{"operator": "Exists"}]}]'
-helm init
+helm init --upgrade --tiller-image registry.cn-hangzhou.aliyuncs.com/google_containers/tiller:$(helm version --client --short | grep -Eo 'v[0-9]\.[0-9]+\.[0-9]+') --service-account tiller
 until helm ls; do
   echo "Wait tiller ready"
 done