学习大数据：Hadoop的集群配置

################ 修改目录权限 ####################
[root@vwmaster hadoop]# chown -R root:root hadoop260/

################ JDK ####################
[root@vwmaster hadoop260]# vi etc/hadoop/hadoop-env.sh
export JAVA_HOME=/opt/bigdata/java/jdk180

################ hadoop fs 文件系统 ####################
集群配置时将 IP 改为 主机名
[root@vwmaster hadoop260]# vi etc/hadoop/core-site.xml

<configuration>
  <property>
    <name>fs.defaultFS</name>
    <value>hdfs://vwmaster:9000</value>
  </property>
  <property>
    <name>hadoop.tmp.dir</name>
    <value>/opt/bigdata/hadoop/hadoop260</value>
  </property>
  <property>
    <name>hadoop.proxyuser.root.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.root.groups</name>
    <value>*</value>
  </property>
</configuration>

################ hadoop replicas 备份 ####################
dfs.replication 备份数量改为2
dfs.hosts 添加节点白名单
[root@vwmaster hadoop]# pwd
/opt/bigdata/hadoop

[root@vwmaster hadoop]# mkdir hdfs
[root@vwmaster hadoop]# ls
hadoop260 hdfs

[root@vwmaster hadoop]# cd hdfs/
[root@vwmaster hdfs]# mkdir namenode datanode
[root@vwmaster hdfs]# ls
datanode namenode

[root@vwmaster hadoop260]# vi etc/hadoop/hdfs-site.xml

<configuration>
  <property>
    <name>dfs.replication</name>
    <value>1</value>
  </property>
  <property>
    <name>dfs.permissions</name>
    <value>false</value>
  </property>
  <!--
      <property>
        <name>dfs.hosts</name>
        <value>/opt/bigdata/hadoop/hadoop260/etc/hadoop/slaves</value>
      </property>
      <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>vwmaster:50090</value>
      </property>
      <property>
        <name>dfs.namenode.dir</name>
        <value>/opt/bigdata/hadoop/hdfs/namenode</value>
      </property>
      <property>
        <name>dfs.datanode.dir</name>
        <value>/opt/bigdata/hadoop/hdfs/datanode</value>
      </property>
  -->
</configuration>

################ hadoop mapreduce 计算框架 ####################
mapreduce.jobhistory.address 添加jobhistory访问端口
mapreduce.jobhistory.webapp.address 添加jobhistory web访问端口
[root@vwmaster hadoop260]# cp etc/hadoop/mapred-site.xml.template etc/hadoop/mapred-site.xml
[root@vwmaster hadoop260]# vi etc/hadoop/mapred-site.xml

<configuration>
  <property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
  </property>
  <!--
      <property>
        <name>mapreduce.jobhistory.address</name>
        <value>vwmaster:10020</value>
      </property>
      <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>vwmaster:19888</value>
      </property>
  -->
</configuration>

################ hadoop yarn 管理调度 ####################
yarn.log-aggregation.retain-seconds 添加yarn日志保留时间为7天（单位秒）
yarn.nodemanager.aux-services.mapreduce.shuffle.class 添加指定shuffle计算具体类型
yarn.resourcemanager.hostname 添加yarn主机名
[root@vwmaster hadoop260]# vi etc/hadoop/yarn-site.xml

<configuration>
  <property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
  </property>
  <property>
    <name>yarn.resourcemanager.hostname</name>
    <value>vwmaster</value>
  </property>
  <!--
      <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
      </property>
      <property>
        <name>yarn.log-aggregation.retain-seconds</name>
        <value>604800</value>
      </property>
      <property>
        <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
        <value>org.apache.hadoop.mapred.ShuffleHandler</value>
      </property>
  -->
</configuration>

################ hadoop slaves 主机名 ####################

注意：hadoop 3.0 以上版本 slaves 更名为 workers

添加所有节点主机名 vwmaster:yarn.resourcemanager
添加所有节点主机名 vwjob:mapreduce.jobhistory
添加所有节点主机名 vwslave01/02:datanode
[root@vwmaster hadoop260]# vi etc/hadoop/slaves

vwslave01
vwslave02
vwslave03

################ hadoop 环境变量 ####################
[root@vwmaster hadoop260]# vi /etc/profile

export JAVA_HOME=/opt/bigdata/java/jdk180
export TOMCAT_HOME=/opt/bigdata/java/tomcat85
export NODE_HOME=/opt/bigdata/elk/node891

export HADOOP_HOME=/opt/bigdata/hadoop/hadoop260
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_OPTS="-Djava.library.path=$HADOOP_HOME/lib"

export PATH=$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$NODE_HOME/bin:$JAVA_HOME/bin:$TOMCAT_HOME/bin:$PATH
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar

[root@vwmaster hadoop260]# source /etc/profile

################ hadoop 格式化 HDFS ####################
[root@vwmaster hadoop260]# cd bin
[root@vwmaster bin]# hdfs namenode -format
##见到以下信息说明格式化成功
/****
SHUTDOWN_MSG: Shutting down NameNode at vwmaster/20.0.0.100
****/
##如果格式化失败：需要去检查之前各项配置

################ hadoop-native库 ####################
[root@vwmaster bin]# cd /opt/install/hadoop
[root@vwmaster hadoop]# tar -xf hadoop-native-64-2.6.0.tar -C /opt/bigdata/hadoop/hadoop260/lib/native/

################ 启动 hadoop ####################
[root@vwmaster hadoop]# cd /opt/bigdata/hadoop/hadoop260/bin
[root@vwmaster bin]# start-dfs.sh
[root@vwmaster bin]# start-yarn.sh
[root@vwmaster bin]# stop-all.sh

################ 启动或关闭 hadoop 需要输入密码的解决方法 ####################
[root@vwmaster bin]# cd ~
[root@vwmaster ~]# cd .ssh/
[root@vwmaster .ssh]# ls
authorized_keys id_rsa id_rsa.pub known_hosts
[root@vwmaster .ssh]# cat id_rsa.pub >> authorized_keys
[root@vwmaster .ssh]# ssh localhost

################ 启动 jobhistory ####################
[root@vwmaster bin]# cd ../sbin/
[root@vwmaster sbin]# jps
[root@vwmaster sbin]# ./mr-jobhistory-daemon.sh start historyserver

################ 查看 hadoop 服务状态 ####################
[root@vwmaster sbin]# jps
6800 NodeManager
7329 Jps
6387 DataNode
6548 SecondaryNameNode
6264 NameNode
6697 ResourceManager
7259 JobHistoryServer

http://20.0.0.100: 50070 8088 19888

#------------------------- 操作 hdfs -----------------------------------#
查看hdfs目录
如果存在警告 20/08/15 08:24:13 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes
解决方法：在log4j.properties中添加：log4j.logger.org.apache.hadoop.util.NativeCodeLoader=ERROR

cd ~/kb08/data

hdfs dfs -ls /
hdfs dfs -du [-s] /kb08/data 统计文件夹信息
hdfs dfs -mkdir /kb08
hdfs dfs -mkdir -p /kb08/data 创建多级目录
hdfs dfs -rmdir /kb08/data 删除目录

hdfs dfs -put ~/kb08/hadoop/story.csv /kb08/data 上传文件
hdfs dfs -get /kb08/data/story.csv ~ 下载文件
hdfs dfs -getmerge /kb08/data/* ~/merge.txt 合并下载
hdfs dfs -rm /kb08/data/story.csv
hdfs dfs -cat /kb08/data/story.csv

touch append.txt
vi append.txt
hello guys, I am so hornored to see you agin
let us enjoy this moment

hdfs dfs -appendToFile append.txt /kb08/data/story.csv 追加文件内容
hdfs dfs -chmod 777 /kb08/data/story.csv
hdfs dfs -chown henry:root /kb08/hadoop/story.csv
hdfs dfs -cp /kb08/hadoop/story.csv /kbcom/data
hdfs dfs -mv /kb08/hadoop/story.csv /kbcom/data

hdfs dfs -setrep 3 /kb08/data/story.csv 设置文件备份数量（不能超过节点数量）
hdfs dfsadmin -safemode get 查看安全模式
hdfs dfsadmin -safemode enter 进入安全模式
hdfs dfsadmin -safemode enter 离开安全模式

#--------------------- java 操作hadoop ----------------------#
#依赖
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<hadoop.version>2.6.0-cdh5.14.2</hadoop.version>
</properties>

<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<!-- hadoop-common -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- hadoop-hdfs -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- hadoop-client -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- log4j -->
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>1.2.17</version>
</dependency>
</dependencies>

#--------------- 因为maven没提供hadoop仓库，所以手动添加 --------------------------#
<repositories>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>;
</repository>
</repositories>

来源：oschina

链接：https://my.oschina.net/u/4345075/blog/4524450