centos7安装hadoop2.7.6和jdk1.8的集群安装方法

centos7安装hadoop2.7.6和jdk1.8的集群安装方法

hadoop2.7.6版本最多只能配置两台namenode

规划二台namenode (master,slave1)
规划五台zookeeper node(master,slave1,slave2,datanode1,datanode2)
规划6台datanode(master,slave1,slave3,datanode1,datanode2,datanode3)
vi /etc/hosts

127.0.0.1  core  localhost.localdomain localhost
192.168.145.200  master
192.168.145.201  slave1
192.168.145.202  slave2
192.168.145.211  datanode1
192.168.145.212  datanode2
192.168.145.213  datanode3

bashrc 配置文件

[hadoop3@master ~]$ cat ~/.bashrc
# .bashrc

# Source global definitions
if [ -f /etc/bashrc ]; then
    . /etc/bashrc
fi

# Uncomment the following line if you don't like systemctl's auto-paging feature:
# export SYSTEMD_PAGER=



# User specific aliases and functions

# add to path for /home/hadoop3/app/jdk   and   /home/hadoop3/tools
JAVA_HOME=/home/hadoop3/app/jdk
HADOOP_HOME=/home/hadoop3/app/hadoop
ZOOKEEPER_HOME=/home/hadoop3/app/zookeeper
CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
PATH=$JAVA_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/bin:$ZOOKEEPER_HOME/bin:/home/hadoop3/tools:$PATH
export JAVA_HOME CLASSPATH  HADOOP_HOME ZOOKEEPER_HOME PATH

core-site.xml

<configuration>
    <property>
      <name>fs.defaultFS</name>
      <value>hdfs://mycluster</value>
    </property>
    <property>
      <name>hadoop.tmp.dir</name>
      <value>/home/hadoop3/data/tmp</value>
    </property>
    <property>
       <name>ha.zookeeper.quorum</name>
       <value>master:2181,slave1:2181,slave2:2181,datanode1:2181,datanode2:2181</value>
    </property>
</configuration>

hdfs-site.xml

<configuration>
    <property>
      <name>dfs.nameservices</name>
      <value>mycluster</value>
    </property>
    <property>
      <name>dfs.permissions.enabled</name>
      <value>false</value>
    </property>
    <property>
      <name>dfs.ha.namenodes.mycluster</name>
      <value>nn1,nn2</value>
    </property>
    <property>
      <name>dfs.namenode.rpc-address.mycluster.nn1</name>
      <value>master:8020</value>
    </property>
    <property>
      <name>dfs.namenode.rpc-address.mycluster.nn2</name>
      <value>slave1:8020</value>
    </property> 
    <property>
      <name>dfs.namenode.http-address.mycluster.nn1</name>
      <value>master:50070</value>
    </property>
    <property>
      <name>dfs.namenode.http-address.mycluster.nn2</name>
      <value>slave1:50070</value>
    </property>     
    <property>
      <name>dfs.namenode.shared.edits.dir</name>
      <value>qjournal://master:8485;slave1:8485/mycluster</value>
    </property>
    <property>
      <name>dfs.journalnode.edits.dir</name>
      <value>/home/hadoop3/data/journaldata/jn</value>
    </property>
    <property>
      <name>dfs.client.failover.proxy.provider.mycluster</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>/home/hadoop3/.ssh/id_rsa</value>
    </property>
    <property>
      <name>dfs.ha.fencing.ssh.connect-timeout</name>
      <value>10000</value>
    </property>
    <property>
      <name>dfs.namenode.handler.count</name>
      <value>100</value>
    </property>
    <property>
       <name>dfs.ha.automatic-failover.enabled</name>
       <value>true</value>
     </property>
    <property>
         <name>dfs.webhdfs.enabled</name>
         <value>true</value>
    </property>  
</configuration>

slaves 文件内容：

master
slave1
slave2
datanode1
datanode2
datanode3

配置hadoop-env.sh,mapred-env.sh、yarn-env.sh

export JAVA_HOME=/home/hadoop3/app/jdk
export HADOOP_HOME=/home/hadoop3/app/hadoop

vi /home/hadoop3/app/zookeeper/conf/zoo.cfg

# The number of milliseconds of each tick
tickTime=2000
# The number of ticks that the initial 
# synchronization phase can take
initLimit=10
# The number of ticks that can pass between 
# sending a request and getting an acknowledgement
syncLimit=5
# the directory where the snapshot is stored.
# do not use /tmp for storage, /tmp here is just 
# example sakes.
dataDir=/home/hadoop3/data/zookeeper/zkdata
dataLogDir=/home/hadoop3/data/zookeeper/zkdatalog
# the port at which the clients will connect
clientPort=2181
# the maximum number of client connections.
# increase this if you need to handle more clients
#maxClientCnxns=60
#
# Be sure to read the maintenance section of the 
# administrator guide before turning on autopurge.
#
# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#
# The number of snapshots to retain in dataDir
#autopurge.snapRetainCount=3
# Purge task interval in hours
# Set to "0" to disable auto purge feature
#autopurge.purgeInterval=1
server.1=master:2888:3888
server.2=slave1:2888:3888
server.3=slave2:2888:3888
server.4=datanode1:2888:3888
server.5=datanode2:2888:3888

注意：重新格式化hdfs时如果hadoop的集群datanode数据目录不为空，要删除原来的数据文件和数据目录

如目录下：/home/hadoop3/data/tmp

其他配置方法参见：centos7安装hadoop3.03和jdk1.8的高可用集群模式
https://blog.csdn.net/hsg77/article/details/80945493