教你在k8s上部署HADOOP-3.2.2(HDFS)的方法

环境+版本

k8s: v1.21.1

hadoop: 3.2.2

dockerfile

FROM openjdk:8-jdk # 如果要通过ssh连接容器内部,添加自己的公钥(非必须) ARG SSH_PUB=ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQC3nTRJ/aVb67l1xMaN36jmIbabU7Hiv/xpZ8bwLVvNO3Bj7kUzYTp7DIbPcHQg4d6EsPC6j91E8zW6CrV2fo2Ai8tDO/rCq9Se/64F3+8oEIiI6E/OfUZfXD1mPbG7M/kcA3VeQP6wxNPhWBbKRisqgUc6VTKhl+hK6LwRTZgeShxSNcey+HZst52wJxjQkNG+7CAEY5bbmBzAlHCSl4Z0RftYTHR3q8LcEg7YLNZasUogX68kBgRrb+jw1pRMNo7o7RI9xliDAGX+E4C3vVZL0IsccKgr90222axsADoEjC9O+Q6uwKjahemOVaau+9sHIwkelcOcCzW5SuAwkezv 805899926@qq.com RUN apt-get update; RUN apt-get install -y openssh-server net-tools vim git; RUN sed -i -r s/^s*UseDNSs+w+/#/; s/^s*PasswordAuthentications+w+/#/; s/^s*ClientAliveIntervals+w+/#/ /etc/ssh/sshd_config; RUN echo UseDNS no nPermitRootLogin yes nPasswordAuthentication yes nClientAliveInterval 30 >> /etc/ssh/sshd_config; RUN cat /etc/ssh/sshd_config RUN su root bash -c cd;mkdir .ssh;chmod 700 .ssh;echo ${SSH_PUB} > .ssh/authorized_keys;chmod 644 .ssh/authorized_keys RUN su root bash -c cd;ssh-keygen -t rsa -f ~/.ssh/id_rsa; cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys # hadoop ENV HADOOP_TGZ_URL=https://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common/hadoop-3.2.2/hadoop-3.2.2.tar.gz ENV HADOOP_HOME=/opt/hadoop ENV PATH=$HADOOP_HOME/bin:$PATH RUN set -ex; mkdir -p $HADOOP_HOME; wget -nv -O $HADOOP_HOME/src.tgz $HADOOP_TGZ_URL; tar -xf $HADOOP_HOME/src.tgz –strip-components=1 -C $HADOOP_HOME; rm $HADOOP_HOME/src.tgz; chown -R root:root $HADOOP_HOME; RUN mkdir -p $HADOOP_HOME/hdfs/name/ && mkdir -p $HADOOP_HOME/hdfs/data/ # clean trash file or dir RUN rm -rf $HADOOP_HOME/share/doc/; COPY docker-entrypoint.sh / EXPOSE 22 9870 9000 ENTRYPOINT [“/docker-entrypoint.sh”]

docker-entrypoint.sh

#!/bin/bash set -e service ssh start hdfs_dir=$HADOOP_HOME/hdfs/ if [ $HADOOP_NODE_TYPE = “datanode” ]; then echo -e “33[32m start datanode 33[0m” $HADOOP_HOME/bin/hdfs datanode -regular fi if [ $HADOOP_NODE_TYPE = “namenode” ]; then if [ -z $(ls -A ${hdfs_dir}) ]; then echo -e “33[32m start hdfs namenode format 33[0m” $HADOOP_HOME/bin/hdfs namenode -format fi echo -e “33[32m start hdfs namenode 33[0m” $HADOOP_HOME/bin/hdfs namenode

pod template

apiVersion: v1 kind: ConfigMap metadata: name: hadoop namespace: big-data labels: app: hadoop data: hadoop-env.sh: | export HDFS_DATANODE_USER=root export HDFS_NAMENODE_USER=root export HDFS_SECONDARYNAMENODE_USER=root export JAVA_HOME=/usr/local/openjdk-8 export HADOOP_OS_TYPE=${HADOOP_OS_TYPE:-$(uname -s)} export HADOOP_OPTS=”-Djava.library.path=${HADOOP_HOME}/lib/native” core-site.xml: | <?xml version=”1.0″ encoding=”UTF-8″?> <?xml-stylesheet type=”text/xsl” href=”configuration.xsl” rel=”external nofollow” rel=”external nofollow” ?> <configuration> <property> <name>fs.defaultFS</name> <value>hdfs://hadoop-master:9000</value> </property> <property> <name>dfs.namenode.rpc-bind-host</name> <value>0.0.0.0</value> </property> </configuration> hdfs-site.xml: | <?xml version=”1.0″ encoding=”UTF-8″?> <?xml-stylesheet type=”text/xsl” href=”configuration.xsl” rel=”external nofollow” rel=”external nofollow” ?> <configuration> <property> <name>dfs.namenode.name.dir</name> <value>file:///opt/hadoop/hdfs/name</value> </property> <property> <name>dfs.datanode.data.dir</name> <value>file:///opt/hadoop/hdfs/data</value> </property> <property> <name>dfs.namenode.datanode.registration.ip-hostname-check</name> <value>false</value> </property> <property> <name>dfs.replication</name> <value>1</value> </property> </configuration> — # namenode svc apiVersion: v1 kind: Service metadata: name: hadoop-master namespace: big-data spec: selector: app: hadoop-namenode type: NodePort ports: – name: rpc port: 9000 targetPort: 9000 – name: http port: 9870 targetPort: 9870 nodePort: 9870 # namenode pod — apiVersion: apps/v1 kind: Deployment metadata: name: hadoop-namenode namespace: big-data spec: strategy: type: Recreate selector: matchLabels: app: hadoop-namenode template: metadata: labels: app: hadoop-namenode spec: volumes: – name: hadoop-env configMap: name: hadoop items: – key: hadoop-env.sh path: hadoop-env.sh – name: core-site configMap: name: hadoop items: – key: core-site.xml path: core-site.xml – name: hdfs-site configMap: name: hadoop items: – key: hdfs-site.xml path: hdfs-site.xml – name: hadoop-data persistentVolumeClaim: claimName: data-hadoop-namenode containers: – name: hadoop image: registry:5000/hadoop imagePullPolicy: Always ports: – containerPort: 22 – containerPort: 9000 – containerPort: 9870 volumeMounts: – name: hadoop-env mountPath: /opt/hadoop/etc/hadoop/hadoop-env.sh subPath: hadoop-env.sh – name: core-site mountPath: /opt/hadoop/etc/hadoop/core-site.xml subPath: core-site.xml – name: hdfs-site mountPath: /opt/hadoop/etc/hadoop/hdfs-site.xml subPath: hdfs-site.xml – name: hadoop-data mountPath: /opt/hadoop/hdfs/ subPath: hdfs – name: hadoop-data mountPath: /opt/hadoop/logs/ subPath: logs env: – name: HADOOP_NODE_TYPE value: namenode — apiVersion: v1 kind: PersistentVolumeClaim metadata: name: data-hadoop-namenode namespace: big-data spec: accessModes: – ReadWriteMany resources: requests: storage: 256Gi storageClassName: “managed-nfs-storage” # datanode pod — apiVersion: apps/v1 kind: StatefulSet metadata: name: hadoop-datanode namespace: big-data spec: replicas: 2 selector: matchLabels: app: hadoop-datanode serviceName: hadoop-datanode template: metadata: labels: app: hadoop-datanode spec: volumes: – name: hadoop-env configMap: name: hadoop items: – key: hadoop-env.sh path: hadoop-env.sh – name: core-site configMap: name: hadoop items: – key: core-site.xml path: core-site.xml – name: hdfs-site configMap: name: hadoop items: – key: hdfs-site.xml path: hdfs-site.xml containers: – name: hadoop image: registry:5000/hadoop imagePullPolicy: Always ports: – containerPort: 22 – containerPort: 9000 – containerPort: 9870 volumeMounts: – name: hadoop-env mountPath: /opt/hadoop/etc/hadoop/hadoop-env.sh subPath: hadoop-env.sh – name: core-site mountPath: /opt/hadoop/etc/hadoop/core-site.xml subPath: core-site.xml – name: hdfs-site mountPath: /opt/hadoop/etc/hadoop/hdfs-site.xml subPath: hdfs-site.xml – name: data mountPath: /opt/hadoop/hdfs/ subPath: hdfs – name: data mountPath: /opt/hadoop/logs/ subPath: logs env: – name: HADOOP_NODE_TYPE value: datanode volumeClaimTemplates: – metadata: name: data namespace: big-data spec: accessModes: – ReadWriteMany resources: requests: storage: 256Gi storageClassName: “managed-nfs-storage”