by default add flink historyserver to deployment

helm-charts/flink-historyserver/.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/

helm-charts/flink-historyserver/Chart.yaml

@@ -0,0 +1,24 @@
+apiVersion: v2
+name: flink-historyserver
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.2
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "0.1.2"

helm-charts/flink-historyserver/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "flink-historyserver.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 "flink-historyserver.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 "flink-historyserver.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "flink-historyserver.labels" -}}
+helm.sh/chart: {{ include "flink-historyserver.chart" . }}
+{{ include "flink-historyserver.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "flink-historyserver.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "flink-historyserver.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "flink-historyserver.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "flink-historyserver.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

helm-charts/flink-historyserver/templates/configmap.yaml

@@ -0,0 +1,9 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: historyserver-config
+data:
+  flink-conf.yaml: |
+    {{- .Values.flinkConfigMap | nindent 4 }}
+  log4j-console.properties: |
+    {{- .Values.log4jConfigMap | nindent 4 }}

helm-charts/flink-historyserver/templates/efs.yaml

@@ -0,0 +1,37 @@
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: {{ .Release.Name }}-efs-flink-history
+parameters:
+  provisioningMode: efs-ap
+  fileSystemId: "{{- .Values.efsFileSystemId }}"
+provisioner: "efs.csi.aws.com"
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: flink-historyserver-efs-pv
+spec:
+  capacity:
+    storage: "1Mi"
+  volumeMode: "Filesystem"
+  accessModes:
+    - "ReadWriteMany"
+  # 'persistentVolumeReclaimPolicy' means EFS volumes must be manually cleaned up when testing is done
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: {{ .Release.Name }}-efs-flink-history
+  csi:
+    driver: "efs.csi.aws.com"
+    volumeHandle: "{{- .Values.efsFileSystemId }}"
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: flink-historyserver-efs-pvc
+spec:
+  accessModes:
+    - ReadWriteMany
+  storageClassName: {{ .Release.Name }}-efs-flink-history
+  resources:
+    requests:
+      storage: 1Mi

helm-charts/flink-historyserver/templates/historyserver.yaml

@@ -0,0 +1,121 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  generation: 1
+  labels:
+    app: historyserver
+  name: historyserver
+  namespace: default
+spec:
+  progressDeadlineSeconds: 150
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      app: historyserver
+  strategy:
+    rollingUpdate:
+      maxSurge: 25%
+      maxUnavailable: 25%
+    type: RollingUpdate
+  template:
+    metadata:
+      creationTimestamp: null
+      labels:
+        app: historyserver
+    spec:
+      containers:
+      - args:
+        - history-server
+        command:
+        - /docker-entrypoint.sh
+        env:
+        - name: _POD_IP_ADDRESS
+          valueFrom:
+            fieldRef:
+              apiVersion: v1
+              fieldPath: status.podIP
+        image: flink:{{- .Values.flinkVersion }}
+        imagePullPolicy: IfNotPresent
+        name: flink-main-container
+        ports:
+        - containerPort: 8082
+          name: history
+          protocol: TCP
+        resources:
+          limits:
+            cpu: 300m
+            memory: 1536Mi
+          requests:
+            cpu: 300m
+            memory: 1536Mi
+        startupProbe:
+          failureThreshold: 2147483647
+          httpGet:
+            path: /config
+            port: history
+            scheme: HTTP
+          periodSeconds: 1
+          successThreshold: 1
+          timeoutSeconds: 1
+        volumeMounts:
+        - mountPath: /opt/history/jobs
+          name: efs-flink-history
+        - mountPath: /opt/flink/conf
+          name: flink-config-volume
+      dnsPolicy: ClusterFirst
+      initContainers:
+      - command:
+        - sh
+        - -c
+        - chown 9999:9999 /opt/history/jobs && ls -lhd /opt/history/jobs
+        image: busybox:1.36.1
+        imagePullPolicy: IfNotPresent
+        name: efs-mount-ownership-fix
+        resources: {}
+        volumeMounts:
+        - mountPath: /opt/history/jobs
+          name: efs-flink-history
+      restartPolicy: Always
+      schedulerName: default-scheduler
+      securityContext:
+        fsGroup: 9999
+      serviceAccount: flink
+      serviceAccountName: flink
+      terminationGracePeriodSeconds: 30
+      volumes:
+      - name: efs-flink-history
+        persistentVolumeClaim:
+          claimName: flink-historyserver-efs-pvc
+      - configMap:
+          defaultMode: 420
+          items:
+          - key: log4j-console.properties
+            path: log4j-console.properties
+          - key: flink-conf.yaml
+            path: flink-conf.yaml
+          name: historyserver-config
+        name: flink-config-volume
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: historyserver
+  name: historyserver-rest
+  namespace: default
+spec:
+  ipFamilies:
+  - IPv4
+  ipFamilyPolicy: SingleStack
+  ports:
+  - name: history
+    port: 8082
+    protocol: TCP
+    targetPort: 8082
+  selector:
+    app: historyserver
+  sessionAffinity: None
+  type: ClusterIP
+status:
+  loadBalancer: {}

helm-charts/flink-historyserver/values.schema.json

@@ -0,0 +1,19 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "type": "object",
+  "required": ["efsFileSystemId", "log4jConfigMap", "flinkConfigMap"],
+  "properties": {
+    "efsFileSystemId": {
+      "type": "string",
+      "minLength": 1
+    },
+    "log4jConfigMap": {
+      "type": "string",
+      "minLength": 1
+    },
+    "flinkConfigMap": {
+      "type": "string",
+      "minLength": 1
+    }
+  }
+}

helm-charts/flink-historyserver/values.yaml

@@ -0,0 +1,4 @@
+efsFileSystemId: ""
+flinkConfigMap: ""
+log4jConfigMap: ""
+flinkVersion: "1.16"

terraform/aws/.gitignore

@@ -0,0 +1 @@
+*.yaml

terraform/aws/addons.tf

@@ -36,4 +36,28 @@ resource "aws_eks_addon" "ebs_provisioner" {
   depends_on = [
     aws_iam_role_policy_attachment.ebs_provisioner
   ]
+}
+
+# EFS CSI Driver for HistoryServer
+resource "aws_iam_role" "efs_provisioner" {
+  name               = "${var.cluster_name}-eks-efs-provisioner"
+  assume_role_policy = data.aws_iam_policy_document.assume_role_with_oidc.json
+}
+
+resource "aws_iam_role_policy_attachment" "efs_provisioner" {
+  policy_arn = "arn:aws:iam::aws:policy/service-role/AmazonEFSCSIDriverPolicy"
+  role       = aws_iam_role.efs_provisioner.name
+}
+
+resource "aws_eks_addon" "efs_provisioner" {
+  cluster_name                = aws_eks_cluster.cluster.name
+  addon_name                  = "aws-efs-csi-driver"
+  # Fetch the most recent version for your current version of k8s
+  # AWS_PROFILE=<your-profile> eksctl utils describe-addon-versions --kubernetes-version 1.27 -v0 | jq '.Addons[] | select(.AddonName == "aws-efs-csi-driver") | .AddonVersions[0]'
+  addon_version               = "v1.7.0-eksbuild.1"
+  resolve_conflicts_on_create = "OVERWRITE"
+  service_account_role_arn  = aws_iam_role.efs_provisioner.arn
+  depends_on = [
+    aws_iam_role_policy_attachment.efs_provisioner
+  ]
 }

terraform/aws/cluster.tf

@@ -53,7 +53,7 @@ resource "aws_iam_openid_connect_provider" "cluster_oidc" {
 module "cluster_autoscaler_irsa" {
   source = "terraform-aws-modules/iam/aws//modules/iam-role-for-service-accounts-eks"
 
-  role_name = "cluster_autoscaler"
+  role_name = "${var.cluster_name}_cluster_autoscaler"
 
   attach_cluster_autoscaler_policy = true
   cluster_autoscaler_cluster_ids = [

terraform/aws/efs.tf

@@ -0,0 +1,10 @@
+resource "aws_efs_file_system" "job_history" {
+  creation_token = "pforge-flink-job-history"
+}
+
+resource "aws_efs_mount_target" "job_history" {
+  for_each         = toset(data.aws_subnets.default.ids)
+  file_system_id   = aws_efs_file_system.job_history.id
+  subnet_id        = each.value
+  security_groups  = [aws_eks_cluster.cluster.vpc_config[0].cluster_security_group_id]
+}

terraform/aws/flink_operator_config.tpl

@@ -0,0 +1,7 @@
+kubernetes.operator.metrics.reporter.prom.factory.class: org.apache.flink.metrics.prometheus.PrometheusReporterFactory
+kubernetes.operator.metrics.reporter.prom.factory.port: 9999
+kubernetes.jobmanager.annotations:
+  prometheus.io/scrape: true
+  prometheus.io/port: 9999
+jobmanager.archive.fs.dir: /opt/history/jobs
+historyserver.archive.fs.dir: /opt/history/jobs