chore(server): split gcloud sql proxy into a separate deployment (#5101)

After merge this pull request, need to change the `DATABASE_URL` in environment secrets (stable/beta) from `127.0.0.1` to `affine-cloud-sql-proxy`

.github/actions/deploy/deploy.mjs

@@ -28,6 +28,7 @@ const {
   REDIS_PASSWORD,
   STRIPE_API_KEY,
   STRIPE_WEBHOOK_KEY,
+  STATIC_IP_NAME,
 } = process.env;
 
 // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
@@ -35,17 +36,13 @@ const buildType = BUILD_TYPE || 'canary';
 
 const isProduction = buildType === 'stable';
 const isBeta = buildType === 'beta';
+const isInternal = buildType === 'internal';
 
 const createHelmCommand = ({ isDryRun }) => {
   const flag = isDryRun ? '--dry-run' : '--atomic';
   const imageTag = `${buildType}-${GIT_SHORT_HASH}`;
-  const staticIpName = isProduction
-    ? 'affine-cluster-production'
-    : isBeta
-      ? 'affine-cluster-beta'
-      : 'affine-cluster-dev';
   const redisAndPostgres =
-    isProduction || isBeta
+    isProduction || isBeta || isInternal
       ? [
           `--set-string global.database.url=${DATABASE_URL}`,
           `--set-string global.database.user=${DATABASE_USERNAME}`,
@@ -59,26 +56,32 @@ const createHelmCommand = ({ isDryRun }) => {
         ]
       : [];
   const serviceAnnotations =
-    isProduction || isBeta
+    isProduction || isBeta || isInternal
       ? [
           `--set-json   web.service.annotations=\"{ \\"cloud.google.com/neg\\": \\"{\\\\\\"ingress\\\\\\": true}\\" }\"`,
-          `--set-json   graphql.serviceAccount.annotations=\"{ \\"iam.gke.io/gcp-service-account\\": \\"${CLOUD_SQL_IAM_ACCOUNT}\\" }\"`,
           `--set-json   graphql.service.annotations=\"{ \\"cloud.google.com/neg\\": \\"{\\\\\\"ingress\\\\\\": true}\\" }\"`,
-          `--set-json   sync.serviceAccount.annotations=\"{ \\"iam.gke.io/gcp-service-account\\": \\"${CLOUD_SQL_IAM_ACCOUNT}\\" }\"`,
           `--set-json   sync.service.annotations=\"{ \\"cloud.google.com/neg\\": \\"{\\\\\\"ingress\\\\\\": true}\\" }\"`,
+          `--set-json   cloud-sql-proxy.serviceAccount.annotations=\"{ \\"iam.gke.io/gcp-service-account\\": \\"${CLOUD_SQL_IAM_ACCOUNT}\\" }\"`,
+          `--set-json   cloud-sql-proxy.nodeSelector=\"{ \\"iam.gke.io/gke-metadata-server-enabled\\": \\"true\\" }\"`,
         ]
       : [];
   const webReplicaCount = isProduction ? 3 : isBeta ? 2 : 2;
   const graphqlReplicaCount = isProduction ? 10 : isBeta ? 5 : 2;
   const syncReplicaCount = isProduction ? 10 : isBeta ? 5 : 2;
-  const namespace = isProduction ? 'production' : isBeta ? 'beta' : 'dev';
+  const namespace = isProduction
+    ? 'production'
+    : isBeta
+      ? 'beta'
+      : isInternal
+        ? 'internal'
+        : 'dev';
   // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
   const host = DEPLOY_HOST || CANARY_DEPLOY_HOST;
   const deployCommand = [
     `helm upgrade --install affine .github/helm/affine`,
     `--namespace  ${namespace}`,
     `--set        global.ingress.enabled=true`,
-    `--set-json   global.ingress.annotations=\"{ \\"kubernetes.io/ingress.class\\": \\"gce\\", \\"kubernetes.io/ingress.allow-http\\": \\"true\\", \\"kubernetes.io/ingress.global-static-ip-name\\": \\"${staticIpName}\\" }\"`,
+    `--set-json   global.ingress.annotations=\"{ \\"kubernetes.io/ingress.class\\": \\"gce\\", \\"kubernetes.io/ingress.allow-http\\": \\"true\\", \\"kubernetes.io/ingress.global-static-ip-name\\": \\"${STATIC_IP_NAME}\\" }\"`,
     `--set-string global.ingress.host="${host}"`,
     `--set-string global.version="${APP_VERSION}"`,
     ...redisAndPostgres,

.github/helm/affine/charts/gcloud-sql-proxy/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

.github/helm/affine/charts/gcloud-sql-proxy/Chart.yaml

@@ -0,0 +1,6 @@
+apiVersion: v2
+name: cloud-sql-proxy
+description: Google Cloud SQL Proxy
+type: application
+version: 0.0.0
+appVersion: "2.8.1"

.github/helm/affine/charts/gcloud-sql-proxy/templates/NOTES.txt

@@ -0,0 +1,18 @@
+{{- if .Values.global.database.gcloud.enabled -}}
+1. Get the application URL by running these commands:
+{{- if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "gcloud-sql-proxy.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "gcloud-sql-proxy.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "gcloud-sql-proxy.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "gcloud-sql-proxy.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}
+{{- end }}

.github/helm/affine/charts/gcloud-sql-proxy/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "gcloud-sql-proxy.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "gcloud-sql-proxy.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "gcloud-sql-proxy.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "gcloud-sql-proxy.labels" -}}
+helm.sh/chart: {{ include "gcloud-sql-proxy.chart" . }}
+{{ include "gcloud-sql-proxy.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "gcloud-sql-proxy.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "gcloud-sql-proxy.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "gcloud-sql-proxy.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "gcloud-sql-proxy.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

.github/helm/affine/charts/gcloud-sql-proxy/templates/deployment.yaml

@@ -0,0 +1,132 @@
+{{- if .Values.global.database.gcloud.enabled -}}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "gcloud-sql-proxy.fullname" . }}
+  labels:
+    {{- include "gcloud-sql-proxy.labels" . | nindent 4 }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "gcloud-sql-proxy.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "gcloud-sql-proxy.labels" . | nindent 8 }}
+	{{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "gcloud-sql-proxy.serviceAccountName" . }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Chart.Name }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          terminationMessagePath: /dev/termination-log
+          terminationMessagePolicy: File
+          image: "{{ .Values.image.repository }}:{{ .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          args:
+            - "--address"
+            - "0.0.0.0"
+            - "--structured-logs"
+            - "--auto-iam-authn"
+            - "{{ .Values.global.database.gcloud.connectionName }}"
+          env:
+            # Enable HTTP healthchecks on port 9801. This enables /liveness,
+            # /readiness and /startup health check endpoints. Allow connections
+            # listen for connections on any interface (0.0.0.0) so that the
+            # k8s management components can reach these endpoints.
+            - name: CSQL_PROXY_HEALTH_CHECK
+              value: "true"
+            - name: CSQL_PROXY_HTTP_PORT
+              value: "9801"
+            - name: CSQL_PROXY_HTTP_ADDRESS
+              value: 0.0.0.0
+          ports:
+            - name: cloud-sql-proxy
+              containerPort: {{ .Values.global.database.gcloud.proxyPort }}
+              protocol: TCP
+            - containerPort: 9801
+              protocol: TCP
+          # The /startup probe returns OK when the proxy is ready to receive
+          # connections from the application. In this example, k8s will check
+          # once a second for 60 seconds.
+          startupProbe:
+            failureThreshold: 60
+            httpGet:
+              path: /startup
+              port: 9801
+              scheme: HTTP
+            periodSeconds: 1
+            successThreshold: 1
+            timeoutSeconds: 10
+          # The /liveness probe returns OK as soon as the proxy application has
+          # begun its startup process and continues to return OK until the
+          # process stops.
+          livenessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /liveness
+              port: 9801
+              scheme: HTTP
+            # The probe will be checked every 10 seconds.
+            periodSeconds: 10
+            # Number of times the probe is allowed to fail before the transition
+            # from healthy to failure state.
+            #
+            # If periodSeconds = 60, 5 tries will result in five minutes of
+            # checks. The proxy starts to refresh a certificate five minutes
+            # before its expiration. If those five minutes lapse without a
+            # successful refresh, the liveness probe will fail and the pod will be
+            # restarted.
+            successThreshold: 1
+            # The probe will fail if it does not respond in 10 seconds
+            timeoutSeconds: 10
+          readinessProbe:
+            # The /readiness probe returns OK when the proxy can establish
+            # a new connections to its databases.
+            httpGet:
+              path: /readiness
+              port: 9801
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            timeoutSeconds: 10
+            # Number of times the probe must report success to transition from failure to healthy state.
+            # Defaults to 1 for readiness probe.
+            successThreshold: 1
+            failureThreshold: 6
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+          {{- with .Values.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+      {{- with .Values.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+{{- end }}

.github/helm/affine/charts/gcloud-sql-proxy/templates/service.yaml

@@ -0,0 +1,17 @@
+{{- if .Values.global.database.gcloud.enabled -}}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "gcloud-sql-proxy.fullname" . }}
+  labels:
+    {{- include "gcloud-sql-proxy.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.global.database.port }}
+      targetPort: cloud-sql-proxy
+      protocol: TCP
+      name: cloud-sql-proxy
+  selector:
+    {{- include "gcloud-sql-proxy.selectorLabels" . | nindent 4 }}
+{{- end }}

.github/helm/affine/charts/gcloud-sql-proxy/templates/serviceaccount.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.global.database.gcloud.enabled -}}
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "gcloud-sql-proxy.serviceAccountName" . }}
+  labels:
+    {{- include "gcloud-sql-proxy.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
+{{- end }}
+{{- end }}

.github/helm/affine/charts/gcloud-sql-proxy/templates/tests/test-connection.yaml

@@ -0,0 +1,17 @@
+{{- if .Values.global.database.gcloud.enabled -}}
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "gcloud-sql-proxy.fullname" . }}-test-connection"
+  labels:
+    {{- include "gcloud-sql-proxy.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args: ['{{ include "gcloud-sql-proxy.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never
+{{- end }}

.github/helm/affine/charts/gcloud-sql-proxy/values.yaml

@@ -0,0 +1,40 @@
+replicaCount: 3
+
+image:
+  # the tag is defined as chart appVersion.
+  repository: gcr.io/cloud-sql-connectors/cloud-sql-proxy
+  pullPolicy: IfNotPresent
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+serviceAccount:
+  create: true
+  automount: true
+  annotations: {}
+  name: ""
+
+podAnnotations: {}
+podLabels: {}
+
+podSecurityContext:
+  fsGroup: 2000
+
+securityContext:
+  runAsNonRoot: true
+
+service:
+  type: ClusterIP
+  port: 5432
+
+resources:
+  limits:
+    memory: "4Gi"
+    cpu: "2"
+
+volumes: []
+volumeMounts: []
+nodeSelector: {}
+tolerations: []
+affinity: {}

.github/helm/affine/charts/graphql/Chart.yaml

@@ -4,3 +4,8 @@ description: AFFiNE GraphQL server
 type: application
 version: 0.0.0
 appVersion: "0.10.3-canary.2"
+dependencies:
+  - name: gcloud-sql-proxy
+    version: 0.0.0
+    repository: "file://../gcloud-sql-proxy"
+    condition: .global.database.gcloud.enabled

.github/helm/affine/charts/graphql/templates/deployment.yaml

@@ -189,20 +189,6 @@ spec:
             initialDelaySeconds: {{ .Values.probe.initialDelaySeconds }}
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
-        {{ if .Values.global.database.gcloud.enabled }}
-        - name: cloud-sql-proxy
-          image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.6.0
-          args:
-            - "--structured-logs"
-            - "--auto-iam-authn"
-            - "{{ .Values.global.database.gcloud.connectionName }}"
-          securityContext:
-            runAsNonRoot: true
-          resources:
-            requests:
-              memory: "2Gi"
-              cpu: "1"
-        {{ end }}
       {{- with .Values.nodeSelector }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}

.github/helm/affine/charts/sync/Chart.yaml

@@ -1,6 +1,11 @@
 apiVersion: v2
 name: sync
-description: A Helm chart for Kubernetes
+description: AFFiNE Sync Server
 type: application
 version: 0.0.0
 appVersion: "0.10.3-canary.2"
+dependencies:
+  - name: gcloud-sql-proxy
+    version: 0.0.0
+    repository: "file://../gcloud-sql-proxy"
+    condition: .global.database.gcloud.enabled

.github/helm/affine/charts/sync/templates/deployment.yaml

@@ -82,20 +82,6 @@ spec:
             initialDelaySeconds: {{ .Values.probe.initialDelaySeconds }}
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
-        {{ if .Values.global.database.gcloud.enabled }}
-        - name: cloud-sql-proxy
-          image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.6.0
-          args:
-            - "--structured-logs"
-            - "--auto-iam-authn"
-            - "{{ .Values.global.database.gcloud.connectionName }}"
-          securityContext:
-            runAsNonRoot: true
-          resources:
-            requests:
-              memory: "2Gi"
-              cpu:    "1"
-        {{ end }}
       {{- with .Values.nodeSelector }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}

.github/helm/affine/values.yaml

@@ -16,6 +16,8 @@ global:
       cloudSqlInternal: ''
       connectionName: ''
       serviceAccount: ''
+      cloudProxyReplicas: 3
+      proxyPort: '5432'
   redis:
     enabled: true
     host: 'redis-master'

.github/workflows/deploy.yml

@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
     inputs:
       flavor:
-        description: 'Build type (canary, beta, or stable)'
+        description: 'Build type (canary, beta, or stable or internal)'
         type: string
         default: canary
 
@@ -249,3 +249,4 @@ jobs:
           CLOUD_SQL_IAM_ACCOUNT: ${{ secrets.CLOUD_SQL_IAM_ACCOUNT }}
           STRIPE_API_KEY: ${{ secrets.STRIPE_API_KEY }}
           STRIPE_WEBHOOK_KEY: ${{ secrets.STRIPE_WEBHOOK_KEY }}
+          STATIC_IP_NAME: ${{ secrets.STATIC_IP_NAME }}

.github/workflows/workers.yml

@@ -11,7 +11,7 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     name: Deploy
-    environment: production
+    environment: stable
     steps:
       - uses: actions/checkout@v4
       - name: Publish