共计 7810 个字符，预计需要花费 20 分钟才能阅读完成。
单机基于 Docker 搭建 Hadoop2.7.1 Spark1.7 高可用集群
获取 Ubuntu 镜像
sudo docker pull ubuntu
分别下载 spark1.7 hadoop2.7.1 scala1.1 zookeeper3.4.6 jdk1.8 解压后放置本地文件夹用于挂载到容器中
并在文件夹下创建文件
authorized_keys
hosts
本例目录使用 /home/docker/config
启动容器
sudo docker run –name installspark -v /home/docker/config/:/config -it ubuntu:14.04
安装
启动后在容器内 /config 文件夹下能够看到放置的安装文件
安装 jdk,scala :
vim ~/.bashrc
追加:
/usr/sbin/sshd
cat /config/hosts > /etc/hosts
cat /config/authorized_keys > /root/.ssh/authorized_keys
export Java_HOME=/usr/lib/jvm/java-8-sun
export PATH=${JAVA_HOME}/bin:$PATH
export HADOOP_HOME=/opt/hadoop
export PATH=${HADOOP_HOME}/bin:$PATH
export SCALA_HOME=/opt/scala
export PATH=${SCALA_HOME}/bin:$PATH
export SPARK_HOME=/opt/spark
export PATH=${SPARK_HOME}/bin:$PATH
拷贝 spark/hadoop/zookeeper 到 /opt 下
安装 hadoop:
创建文件夹:/opt/hadoop/namenode /opt/hadoop/datanode /opt/hadoop/tmp /opt/hadoop/journal
root@nn1:/opt/hadoop/etc/hadoop# vim hadoop-env.sh
修改:
export JAVA_HOME=/usr/lib/jvm/java-8-sun
root@nn1:/opt/hadoop/etc/hadoop# vim core-site.xml
添加:
<property>
<name>fs.defaultFS</name>
<value>hdfs://ns1</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/hadoop/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>dnzk1:2181,dnzk2:2181,dnzk3:2181</value>
</property>
root@nn1:/opt/hadoop/etc/hadoop#vim hdfs-site.xml
添加:
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/opt/hadoop/datanode</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/opt/hadoop/namenode</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>ns1</value>
</property>
<property>
<name>dfs.ha.namenodes.ns1</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns1.nn1</name>
<value>nn1:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.ns1.nn1</name>
<value>nn1:50070</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns1.nn2</name>
<value>nn2:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.ns1.nn2</name>
<value>nn2:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://dnzk1:8485;dnzk2:8485;dnzk3:8485/ns1</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/opt/hadoop/journal</value>
</property>
<property>
<name>dfs.journalnode.http-address</name>
<value>0.0.0.0:8480</value>
</property>
<property>
<name>dfs.journalnode.rpc-address</name>
<value>0.0.0.0:8485</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.ns1</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
<property>
<name>dfs.permissions</name>
<value>false</value>
</property>
<name>yarn.resourcemanager.store.class</name> <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value> </property> <property> <name>yarn.resourcemanager.zk-address</name> <value>dnzk1:2181,dnzk2:2181,dnzk3:2181</value> </property> <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property>
root@nn1:/opt/hadoop# vim /opt/hadoop/etc/hadoop/slaves
添加:
dnzk1
dnzk2
dnzk3
安装 spark
root@nn1:/opt/spark/conf# vim spark-env.sh
添加:
export SPARK_MASTER_IP=nn1
export SPARK_WORKER_MEMORY=256m
export JAVA_HOME=/usr/lib/jvm/java-8-sun
export SCALA_HOME=/opt/scala
export SPARK_HOME=/opt/spark
export HADOOP_CONF_DIR=/opt/hadoop/etc/hadoop
export SPARK_LIBRARY_PATH=$$SPARK_HOME/lib
export SCALA_LIBRARY_PATH=$SPARK_LIBRARY_PATH
export SPARK_WORKER_CORES=1
export SPARK_WORKER_INSTANCES=1
export SPARK_MASTER_PORT=7077
root@nn1:/opt/spark/conf# vim slaves
添加:
安装 zookeeper
创建文件夹 /opt/zookeeper/tmp
创建文件 /opt/zookeeper/tmp/myid
echo 1 > /opt/zookeeper/tmp/myid
root@nn1:/opt/zookeeper/conf# vim zoo.cfg
修改
dataDir=/opt/zookeeper/tmp
server.1=dnzk1:2888:3888
server.2=dnzk2:2888:3888
server.3=dnzk3:2888:3888
生成密钥
ssh-keygen -t dsa
追加 id_dsa.pub 到宿主机的 /home/docker/config/authorized_keys 文件
root@nn1:/opt/hadoop# cat ~/.ssh/id_dsa.pub
执行
sudo docker commit -m “namenode1” installspark ubuntu:ns1
修改本地宿主机 /home/docker/config/hosts 文件
添加
172.17.0.11 nn1
172.17.0.12 nn2
172.17.0.13 rm1
172.17.0.14 rm2
172.17.0.15 dnzk1
172.17.0.16 dnzk2
172.17.0.17 dnzk3
启动 docker
sudo docker run –name dnzk1 -h dnzk1 –net=none -p 2185:2181 -p 50075:50070 -p 9005:9000 -p 8485:8485 -p 7075:7077 -p 2885:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
sudo docker run –name dnzk2 -h dnzk2 –net=none -p 2186:2181 -p 50076:50070 -p 9006:9000 -p 8486:8485 -p 7076:7077 -p 2886:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
sudo docker run –name dnzk3 -h dnzk3 –net=none -p 2186:2181 -p 50076:50070 -p 9006:9000 -p 8486:8485 -p 7076:7077 -p 2887:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
sudo docker run –name nn1 -h nn1 –net=none -p 2181:2181 -p 50071:50070 -p 9001:9000 -p 8481:8485 -p 7071:7077 -p 2881:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
sudo docker run –name nn2 -h nn2 –net=none -p 2182:2181 -p 50072:50070 -p 9002:9000 -p 8482:8485 -p 7072:7077 -p 2882:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
sudo docker run –name rm1 -h rm1 –net=none -p 2183:2181 -p 50073:50070 -p 9003:9000 -p 8483:8485 -p 7073:7077 -p 2883:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
sudo docker run –name rm2 -h rm2 –net=none -p 2184:2181 -p 50074:50070 -p 9004:9000 -p 8484:8485 -p 7074:7077 -p 2884:2888 -v /home/docker/config/:/config -it spark1_7-hadoop2_7_1-scala1_1:basic
dnzk2(执行 echo 2 > /opt/zookeeper/tmp/myid),dnzk2(执行 echo 3 > /opt/zookeeper/tmp/myid)
配置网络
sudo pipework docker0 -i eth0 nn1 172.17.0.11/16
sudo pipework docker0 -i eth0 nn2 172.17.0.12/16
sudo pipework docker0 -i eth0 rm1 172.17.0.13/16
sudo pipework docker0 -i eth0 rm2 172.17.0.14/16
sudo pipework docker0 -i eth0 dnzk1 172.17.0.15/16
sudo pipework docker0 -i eth0 dnzk2 172.17.0.16/16
sudo pipework docker0 -i eth0 dnzk3 172.17.0.17/16
启动 hadoop 集群
在 dnzk1/dnzk2/dnzk3 上启动 zookeeper 和 hadoop journal
/opt/zookeeper/bin/zkServer.sh start
/opt/hadoop/sbin/hadoop-daemon.sh start journalnode
在 nn1 上格式化 zookeeper 启动和 format hadoop
/opt/hadoop/bin/hdfs namenode -format
/opt/hadoop/bin/hdfs namenode -format
scp -r /opt/hadoop/namenode/ nn2:/opt/hadoop/
或
/opt/hadoop/bin/hdfs namenode -bootstrapStandby
/opt/hadoop/bin/hdfs zkfc -formatZK
/opt/hadoop/sbin/start-dfs.sh
在 rm1 上启动 yarn
/opt/hadoop/sbin/start-yarn.sh
在 rm2 上启动
/opt/hadoop/sbin/yarn-daemon.sh start resourcemanager
启动 spark
/opt/spark/sbin/start-all.sh
查看:
http://172.17.0.11:50070 (active)
http://172.17.0.12:50070(standby)
启动后集群服务情况
nn1 172.17.0.11 jdk、hadoop NameNode、DFSZKFailoverController(zkfc)
nn2 172.17.0.12 jdk、hadoop NameNode、DFSZKFailoverController(zkfc)
rm1 172.17.0.13 jdk、hadoop ResourceManager
rm2 172.17.0.14 jdk、hadoop ResourceManager
dnzk1 172.17.0.15 jdk、hadoop、zookeeper DataNode、NodeManager、JournalNode、QuorumPeerMain
dnzk2 172.17.0.16 jdk、hadoop、zookeeper DataNode、NodeManager、JournalNode、QuorumPeerMain
dnzk3 172.17.0.17 jdk、hadoop、zookeeper DataNode、NodeManager、JournalNode、QuorumPeerMain
下面关于 Hadoop 的文章您也可能喜欢，不妨看看：
Ubuntu14.04 下 Hadoop2.4.1 单机 / 伪分布式安装配置教程 http://www.linuxidc.com/Linux/2015-02/113487.htm
CentOS 安装和配置 Hadoop2.2.0 http://www.linuxidc.com/Linux/2014-01/94685.htm
Ubuntu 13.04 上搭建 Hadoop 环境 http://www.linuxidc.com/Linux/2013-06/86106.htm
Ubuntu 12.10 +Hadoop 1.2.1 版本集群配置 http://www.linuxidc.com/Linux/2013-09/90600.htm
Ubuntu 上搭建 Hadoop 环境（单机模式 + 伪分布模式）http://www.linuxidc.com/Linux/2013-01/77681.htm
Ubuntu 下 Hadoop 环境的配置 http://www.linuxidc.com/Linux/2012-11/74539.htm
单机版搭建 Hadoop 环境图文教程详解 http://www.linuxidc.com/Linux/2012-02/53927.htm
更多 Hadoop 相关信息见Hadoop 专题页面 http://www.linuxidc.com/topicnews.aspx?tid=13
本文永久更新链接地址：http://www.linuxidc.com/Linux/2016-01/127699.htm
