Docker安装Hadoop分布式集群

一、准备环境

docker search hadoop
docker pull sequenceiq/hadoop-docker
docker images

二、Hadoop集群搭建

1. 运行hadoop102容器

docker run --name hadoop102 -d -h hadoop102 -p 9870:9870 -p 19888:19888 -v /opt/data/hadoop:/opt/data/hadoop sequenceiq/hadoop-docker

docker exec -it hadoop102 bash  #进入该容器
ssh-keygen -t rsa  #生成密钥，一直回车，有一个根据提示输入y
cd /root/.ssh/ && cat id_rsa.pub > authorized_keys #复制公钥到authorized_keys中
cat authorized_keys #复制到其他文档中保存

2. 运行hadoop103容器

docker run --name hadoop103 -d -h hadoop103 -p 8088:8088 sequenceiq/hadoop-docker

docker exec -it hadoop103 bash  #进入该容器
ssh-keygen -t rsa  #生成密钥
cd /root/.ssh/ && cat id_rsa.pub > authorized_keys #复制公钥到authorized_keys中
cat authorized_keys #复制到其他文档中保存

3. 运行hadoop104容器

docker run --name hadoop104 -d -h hadoop104 sequenceiq/hadoop-docker

docker exec -it hadoop104 bash  #进入该容器
ssh-keygen -t rsa  #生成密钥
cd /root/.ssh/ && cat id_rsa.pub > authorized_keys #复制公钥到authorized_keys中
cat authorized_keys #复制到其他文档中保存

4.将三个密钥全部复制到authorized_keys文件

vi authorized_keys #将hadoop102 hadoop103 hadoop104复制到这一个文件中,在hadoop102 hadoop103 hadoop104中都保存起来

cat > authorized_keys << EOF
ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAx01kz5PaWIU/oV7AuBZkiwQ52EVO61GDgRCsNUQd7GgdFKpCENCbDIRP9IvAumN0rdxloxQd2WMaEWTycHfeu8tsECihb4iIywDSx1XiQHrik+CUBPggCWdzJknZQgNSmMGRd4129r1bJO8lra100QoK/YpSYQY7Odapd1dg3dhrcEf2D59a/gvX8yHnYkBAuFNAm/HXijTNHq5TezoIOo63WT9BCWTQ4DLBmLdIZsOrZzHkNJCFpRgHTbEGX+h0vzqXhGXlkA9IMdrwFuAc5lTuazK9wwXgjmAq9M38Zh3ithr/LYB2VaHyUCXzNB44e1fGQ8+O946XerO8IO8r9w== root@hadoop102
ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAyctJZBLE1pktU8jv2983inSZazyV0v49Dpzt6+z9K3E5JlBuNvM806mMzLhvta+eXnu7Th70fE20vUNukrjRCpZUv/zxzuKKadSLr76xQEsjP/ZnmUVsJfJU4Q/ThRR32TiDRDdnCf0nM/pi/eXePrbgZLxMNd2+r0o65++th6mDMV8Y/lGAxGBYIAsI3xJwEx+6/Ok9h5AlvtEezKWkI6JhpEjpTwncVEdk16vR8WJ51JsnYwszSenRmyOFmcT+O7qU0phpy/FvwlDzDen54nrssqj1vB+yhlkCdlfLN5PQ5nJIPE0sAwTxaFOLqEbLf1mLrtO9iTx+UwboGCxoRQ== root@hadoop103
ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAz7cQxzbxJoFMWVchuFdcCDY3nD8jb4lRZPTH+5+J4iFP1vEIADj18rMlfQy/d+c+v3XrFfNVvlrawKFVals5LcfVd97eEEX1g2KRxsM07aqPibVYGwturFpiu3pFKwI9j2hYwa4uWVM+5VCR49sgAxHce4jmlf/ZpLz5FxxqVYyRvQ3GoN8KsqDH7CwDyqnbgnrgJw7RE0d7nVOdfgXif1VXPPjPTzRUxMJKtyP1Ja+Sym/sxRJwOuEGEqNCg6WHYZ4OFArtWKMliDv3hRCUvJK9LlWu9+aeCHGrA6qJApaQ/vAOdzsSBj1IGzgDttYO4uxNkQavwazw/DHtRA9swQ== root@hadoop104
EOF

5. 配置地址映射

cat >> /etc/hosts << EOF
172.17.0.2    hadoop102 #ip是容器的IP
172.17.0.3    hadoop103 #ip是容器的IP
172.17.0.4    hadoop104 #ip是容器的IP
EOF

6.检查ssh是否成功

#在hadoop102 hadoop103 hadoop104都测试
ssh hadoop102
ssh hadoop103
ssh hadoop104

三、配置Hadoop

hadoop目录安装在：/usr/local/hadoop-2.7.0/etc/hadoop

1. core-site.xml

#在hadoop102容器中执行
cd /usr/local/hadoop-2.7.0/etc/hadoop
cat  > core-site.xml << EOF
<configuration>
   <property> 
      <name>fs.defaultFS</name> 
      <value>hdfs://hadoop102:8020</value> 
   </property> 
    <property>
    <name>hadoop.tmp.dir</name>
    <value>/opt/data/hadoop</value>
    </property>
   <property> 
      <name>hadoop.http.staticuser.user</name> 
      <value>root</value> 
   </property>
</configuration>
EOF

2. hdfs-site.xml

#在hadoop102容器中执行
cd /usr/local/hadoop-2.7.0/etc/hadoop
cat > hdfs-site.xml << EOF
<configuration>
    <property>
        <name>dfs.namenode.http-address</name> 
        <value>hadoop102:9870</value> 
    </property> 
</configuration>
EOF

3. yarn-site.xml

#在hadoop102容器中执行 注意：还有其他需要编辑
cd /usr/local/hadoop-2.7.0/etc/hadoop
vi yarn-site.xml
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>hadoop103</value> 
    </property>

4. mapred-site.xml

cd /usr/local/hadoop-2.7.0/etc/hadoop
cat > mapred-site.xml << EOF
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>
EOF

5. 分发文件

cd /usr/local/hadoop-2.7.0/etc/hadoop
scp /usr/local/hadoop-2.7.0/etc/hadoop/core-site.xml hadoop103:/usr/local/hadoop-2.7.0/etc/hadoop
scp /usr/local/hadoop-2.7.0/etc/hadoop/hdfs-site.xml hadoop103:/usr/local/hadoop-2.7.0/etc/hadoop
scp /usr/local/hadoop-2.7.0/etc/hadoop/yarn-site.xml hadoop103:/usr/local/hadoop-2.7.0/etc/hadoop

scp /usr/local/hadoop-2.7.0/etc/hadoop/core-site.xml hadoop104:/usr/local/hadoop-2.7.0/etc/hadoop
scp /usr/local/hadoop-2.7.0/etc/hadoop/hdfs-site.xml hadoop104:/usr/local/hadoop-2.7.0/etc/hadoop
scp /usr/local/hadoop-2.7.0/etc/hadoop/yarn-site.xml hadoop104:/usr/local/hadoop-2.7.0/etc/hadoop

四、启动集群

1. 配置slaves文件

cd /usr/local/hadoop-2.7.0/etc/hadoop
cat > slaves << EOF
hadoop102
hadoop103
hadoop104
EOF

2. 发送到其他节点

scp /usr/local/hadoop-2.7.0/etc/hadoop/slaves hadoop103:/usr/local/hadoop-2.7.0/etc/hadoop
scp /usr/local/hadoop-2.7.0/etc/hadoop/slaves hadoop104:/usr/local/hadoop-2.7.0/etc/hadoop

3. 格式化文件系统

cd /usr/local/hadoop-2.7.0/bin
./hadoop namenode -format

4. 在hadoop102启动hdfs

cd /usr/local/hadoop-2.7.0/sbin
./start-all.sh

5. 在hadoop103启动yarn

cd /usr/local/hadoop-2.7.0/sbin
./start-yarn.sh

6.访问验证

#关闭防火墙
systemctl stop firewalld
systemctl disable firewalld

#关闭selinux
sed -i 's/enforcing/disabled/' /etc/selinux/config # 永久
setenforce 0 # 临时

sysctl net.ipv4.ip_forward  #启用IP_FORWARD
systemctl restart docker
docker start hadoop102  hadoop103  hadoop104

访问Hadoop102:9870，查看是否能够看到hdfs界面

访问hadoop103:8088，查看能够看到yarn界面

五 案例

1. 执行一些hdfs命令

cat >> /root/.bashrc << EOF
export HADOOP_HOME=/usr/local/hadoop
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
EOF

source /root/.bashrc

hadoop fs -ls /
hadoop fs -mkdir /hadoop
hadoop fs -ls /

2. 上传文件到hdfs上

hadoop fs -put word.txt /hadoop
hadoop fs -ls /hadoop

3. 执行wordcount案例

cd /usr/local/hadoop
./bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.0.jar wordcount /hadoop/word.txt /output

在yarn上可以看到执行情况

五、关闭集群

#hadoop102上
stop-dfs.sh

#hadoop103上：
stop-yarn.sh