FROM myharbor.com/bigdata/centos:7.9.2009

RUN rm -f /etc/localtime && ln -sv /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && echo "Asia/Shanghai" > /etc/timezone
RUN export LANG=zh_CN.UTF-8

### install tools
RUN yum install -y vim tar wget curl less telnet net-tools lsof

RUN groupadd --system --gid=9999 admin && useradd --system -m /home/admin --uid=9999 --gid=admin admin

RUN mkdir -p /opt/apache

ADD apache-livy-0.8.0-incubating-SNAPSHOT-bin.zip /opt/apache/
ENV LIVY_HOME=/opt/apache/apache-livy
RUN ln -s /opt/apache/apache-livy-0.8.0-incubating-SNAPSHOT-bin $LIVY_HOME

ADD hadoop-3.3.2.tar.gz /opt/apache/
ENV HADOOP_HOME=/opt/apache/hadoop
RUN ln -s /opt/apache/hadoop-3.3.2 $HADOOP_HOME
ENV HADOOP_CONFIG_DIR=${HADOOP_HOME}/etc/hadoop

ADD spark-3.3.0-bin-hadoop3.tar.gz /opt/apache/
ENV SPARK_HOME=/opt/apache/spark
RUN ln -s /opt/apache/spark-3.3.0-bin-hadoop3 $SPARK_HOME

ENV PATH=${LIVY_HOME}/bin:${HADOOP_HOME}/bin:${SPARK_HOME}/bin:$PATH

RUN chown -R admin:admin /opt/apache

WORKDIR $LIVY_HOME

ENTRYPOINT ${LIVY_HOME}/bin/livy-server start;tail -f ${LIVY_HOME}/logs/livy-root-server.out

docker build -t myharbor.com/bigdata/livy:0.8.0 . --no-cache

### 參數解釋
# -t：指定鏡像名稱
# . ：當前目錄Dockerfile
# -f：指定Dockerfile路徑
#  --no-cache：不緩存

# 推送到harbor
docker push myharbor.com/bigdata/livy:0.8.0

helm create livy

replicaCount: 1

image:
  repository: myharbor.com/bigdata/livy
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: "0.8.0"

securityContext:
  runAsUser: 9999
  runAsGroup: 9999
  privileged: true

service:
  type: NodePort
  port: 8998
  nodePort: 31998

apiVersion: v1
kind: ConfigMap
metadata:
  name: {{ include "livy.fullname" . }}
  labels:
    {{- include "livy.labels" . | nindent 4 }}
data:
  livy.conf: |-
    livy.spark.master = yarn
    livy.spark.deploy-mode = client
    livy.environment = production
    livy.impersonation.enabled = true
    livy.server.csrf_protection.enabled = false
    livy.server.port = {{ .Values.service.port }}
    livy.server.session.timeout = 3600000
    livy.server.recovery.mode = recovery
    livy.server.recovery.state-store = filesystem
    livy.server.recovery.state-store.url = /tmp/livy
    livy.repl.enable-hive-context = true
  livy-env.sh: |-
    export JAVA_HOME=/opt/apache/jdk1.8.0_212
    export HADOOP_HOME=/opt/apache/hadoop
    export HADOOP_CONF_DIR=/opt/apache/hadoop/etc/hadoop
    export SPARK_HOME=/opt/apache/spark
    export SPARK_CONF_DIR=/opt/apache/spark/conf
    export LIVY_LOG_DIR=/opt/apache/livy/logs
    export LIVY_PID_DIR=/opt/apache/livy/pid-dir
    export LIVY_SERVER_JAVA_OPTS="-Xmx512m"
  spark-blacklist.conf: |-
    spark.master
    spark.submit.deployMode

    # Disallow overriding the location of Spark cached jars.
    spark.yarn.jar
    spark.yarn.jars
    spark.yarn.archive

    # Don't allow users to override the RSC timeout.
    livy.rsc.server.idle-timeout

apiVersion: apps/v1
kind: Deployment
metadata:
  name: {{ include "livy.fullname" . }}
  labels:
    {{- include "livy.labels" . | nindent 4 }}
spec:
  {{- if not .Values.autoscaling.enabled }}
  replicas: {{ .Values.replicaCount }}
  {{- end }}
  selector:
    matchLabels:
      {{- include "livy.selectorLabels" . | nindent 6 }}
  template:
    metadata:
      {{- with .Values.podAnnotations }}
      annotations:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      labels:
        {{- include "livy.selectorLabels" . | nindent 8 }}
    spec:
      {{- with .Values.imagePullSecrets }}
      imagePullSecrets:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      serviceAccountName: {{ include "livy.serviceAccountName" . }}
      securityContext:
        {{- toYaml .Values.podSecurityContext | nindent 8 }}
      containers:
        - name: {{ .Chart.Name }}
          securityContext:
            {{- toYaml .Values.securityContext | nindent 12 }}
          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
          imagePullPolicy: {{ .Values.image.pullPolicy }}
          ports:
            - name: http
              containerPort: 8998
              protocol: TCP
          livenessProbe:
            httpGet:
              path: /
              port: http
          readinessProbe:
            httpGet:
              path: /
              port: http
          resources:
            {{- toYaml .Values.resources | nindent 12 }}
          {{- with .Values.securityContext }}
          securityContext:
            runAsUser: {{ .runAsUser }}
            runAsGroup: {{ .runAsGroup }}
            privileged: {{ .privileged }}
          {{- end }}
          volumeMounts:
            - name: {{ .Release.Name }}-livy-conf
              mountPath: /opt/apache/livy/conf/livy.conf
              subPath: livy.conf
            - name: {{ .Release.Name }}-livy-env
              mountPath: /opt/apache/livy/conf/livy-env.sh
              subPath: livy-env.sh
            - name: {{ .Release.Name }}-spark-blacklist-conf
              mountPath: /opt/apache/livy/conf/spark-blacklist.conf
              subPath: spark-blacklist.conf
      {{- with .Values.nodeSelector }}
      nodeSelector:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      {{- with .Values.affinity }}
      affinity:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      {{- with .Values.tolerations }}
      tolerations:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      volumes:
        - name: {{ .Release.Name }}-livy-conf
          configMap:
            name: {{ include "livy.fullname" . }}
        - name: {{ .Release.Name }}-livy-env
          configMap:
            name: {{ include "livy.fullname" . }}
        - name: {{ .Release.Name }}-spark-blacklist-conf
          configMap:
            name: {{ include "livy.fullname" . }}

helm install livy ./livy -n livy --create-namespace

NOTES:
1. Get the application URL by running these commands:
  export NODE_PORT=$(kubectl get --namespace livy -o jsonpath="{.spec.ports[0].nodePort}" services livy)
  export NODE_IP=$(kubectl get nodes --namespace livy -o jsonpath="{.items[0].status.addresses[0].address}")
  echo http://$NODE_IP:$NODE_PORT

kubectl get pods,svc -n livy -owide

curl -s -XPOST -d '{"file":"hdfs://myhdfs/tmp/spark-examples_2.12-3.3.0.jar","className":"org.apache.spark.examples.SparkPi","name":"SparkPi-test"}'  -H "Content-Type: application/json"  http://local-168-182-110:31998/batches|python -m json.tool