Hadoop 版本： apache hadoop 2.9.1
JDK 版本： Oracle JDK1.8
集群规划
master（1）： NN， RM， DN， NM， JHS
slave1（2）： DN， NM
slave2（3）： DN， NM
jdk-8u172-linux-x64.tar.gz
hadoop-2.9.1.tar.gz
一 环境初始化
[root@hadoop1 opt]# cat /etc/redhat-release CentOS release 6.10 (Final) # service iptables stop # chkconfig iptables off # sed -i 's/=enforcing/=disabled/' /etc/selinux/config # cat >> /etc/profile << EOF export HISTTIMEFORMAT='%F %T ' EOF # sed -i '$a vm.swappiness = 0' /etc/sysctl.conf echo never > /sys/kernel/mm/redhat_transparent_hugepage/defrag echo never > /sys/kernel/mm/redhat_transparent_hugepage/enabled # sed -i '$a echo never > /sys/kernel/mm/redhat_transparent_hugepage/defrag' /etc/rc.local # sed -i '$a echo never > /sys/kernel/mm/redhat_transparent_hugepage/enabled' /etc/rc.local # vim /etc/ntp.conf ##注释掉所有的 server 开头内容 # Use public servers from the pool.ntp.org project. # Please consider joining the pool (http://www.pool.ntp.org/join.html). #server 0.centos.pool.ntp.org iburst #server 1.centos.pool.ntp.org iburst #server 2.centos.pool.ntp.org iburst #server 3.centos.pool.ntp.org iburst server cn.pool.ntp.org # service ntpd start # chkconfig ntpd on # rpm -qa | grep java-1 java-1.5.0-gcj-1.5.0.0-29.1.el6.x86_64 java-1.6.0-openjdk-1.6.0.41-1.13.13.1.el6_8.x86_64 java-1.7.0-openjdk-1.7.0.181-2.6.14.10.el6.x86_64 # rpm -e --nodeps ` rpm -qa | grep java-1` # tar -zxvf jdk-8u191-linux-x64.tar.gz # ln -s jdk1.8.0_191 jdk # alternatives --install /usr/bin/java java /opt/jdk/bin/java 100 # alternatives --install /usr/bin/javac javac /opt/jdk/bin/javac 100 # cat >> /etc/profile << EOF export JAVA_HOME=/opt/jdk export PATH=$PATH:$JAVA_HOME/bin EOF [root@hadoop1 opt]# source /etc/profile [root@hadoop1 opt]# java -version java version "1.8.0_191" Java(TM) SE Runtime Environment (build 1.8.0_191-b12) Java HotSpot(TM) 64-Bit Server VM (build 25.191-b12, mixed mode) [root@hadoop1 opt]# javac -version javac 1.8.0_191 # cat >> /etc/hosts << EOF 1 hadoop1 2 hadoop2 3 hadoop3 EOF [root@hadoop1 opt]# id hadoop id: hadoop: No such user [root@hadoop1 opt]# useradd hadoop [root@hadoop1 opt]# vim /etc/sudoers hadoop ALL=NOPASSWD:ALL
三个节点都要执行
[hadoop@hadoop1 opt]$ ./test_hadoop_env.sh ######### 1. iptables: ##################### current iptables status: iptables: Only usable by root. [WARNING] chkconfig status： iptables 0:off 1:off 2:off 3:off 4:off 5:off 6:off ######### 2. Selinux: ###################### current selinux status: Disabled config of selinux: SELINUX=disabled ######### 3. THP: ########################## defrag status:always madvise [never] enabled status:always madvise [never] ######### 4. Swappiness => 0 : ################### current swapness setting: 0 ######### 5.ntp: ################### remote refid st t when poll reach delay offset jitter ============================================================================== ** * 3 u 178 256 377 253.202 8.052 2.663 ######### 6. JDK: ################### current java version: javac 1.8.0_191 ######### 7. hosts: ################### 127.0.0.1 localhost localhost.localdomain localhost4 localhost4.localdomain4 ::1 localhost localhost.localdomain localhost6 localhost6.localdomain6 1 hadoop1 2 hadoop2 3 hadoop3
安装
[root@hadoop1 opt]# tar -zxvf hadoop-2.9.1.tar.gz [root@hadoop1 opt]# ln -s hadoop-2.9.1 hadoop [root@hadoop1 opt]# vim ~/.bash_profile export HADOOP_HOME=/opt/hadoop export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin [root@hadoop1 opt]# vim /opt/hadoop/etc/hadoop/hadoop-env.sh export JAVA_HOME=/opt/jdk [root@hadoop1 opt]# source ~/.bash_profile [root@hadoop1 opt]# hadoop version Hadoop 2.9.1 Subversion https://github.com/apache/hadoop.git -r e30710aea4e6e55e69372929106cf119af06fd0e Compiled by root on 2018-04-16T09:33Z Compiled with protoc 2.5.0 From source with checksum 7d6d2b655115c6cc336d662cc2b919bd This command was run using /opt/hadoop-2.9.1/share/hadoop/common/hadoop-common-2.9.1.jar [root@hadoop1 opt]# vim /opt/hadoop/etc/hadoop/yarn-env.sh # export JAVA_HOME=/home/y/libexec/jdk1.6.0/ export JAVA_HOME=/opt/jdk [root@hadoop1 opt]# vim /opt/hadoop/etc/hadoop/core-site.xml <configuration> <property> <name>fs.defaultFS</name> <value>hdfs://hadoop1:9000</value> </property> <property> <name>hadoop.tmp.dir</name> <value>/opt/hadoopdata/tmp</value> </property> </configuration> [root@hadoop1 opt]# mkdir -p /opt/hadoopdata/tmp [root@hadoop1 opt]# vim /opt/hadoop/etc/hadoop/hdfs-site.xml <configuration> <property> <name>dfs.namenode.secondary.http-address</name> <value>hadoop2:9001</value> </property> <property> <name>dfs.namenode.name.dir</name> <value>/opt/hadoopdata/hdfs/name</value> </property> <property> <name>dfs.datanode.data.dir</name> <value>/opt/hadoopdata/hdfs/data</value> </property> <property> <name>dfs.namenode.checkpoint.dir</name> <value>/opt/hadoopdata/hdfs/snn</value> </property> <property> <name>dfs.namenode.checkpoint.period</name> <value>3600</value> </property> <property> <name>dfs.replication</name> <value>2</value> </property> <property> <name>dfs.webhdfs.enabled</name> <value>true</value> </property> </configuration> mkdir -p /opt/hadoopdata/hdfs/name mkdir -p /opt/hadoopdata/hdfs/data mkdir -p /opt/hadoopdata/hdfs/snn [root@hadoop1 opt]# vim /opt/hadoop/etc/hadoop/yarn-site.xml <configuration> <!-- Site specific YARN configuration properties --> <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> <property> <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name> <value>org.apache.hadoop.mapred.ShuffleHandler</value> </property> <property> <name>yarn.resourcemanager.address</name> <value>hadoop1:8032</value> </property> <property> <name>yarn.resourcemanager.scheduler.address</name> <value>hadoop1:8030</value> </property> <property> <name>yarn.resourcemanager.resource-tracker.address</name> <value>hadoop1:8031</value> </property> <property> <name>yarn.resourcemanager.admin.address</name> <value>hadoop1:8033</value> </property> <property> <name>yarn.resourcemanager.webapp.address</name> <value>hadoop1:8088</value> </property> </configuration> [root@hadoop1 opt]# cd /opt/hadoop/etc/hadoop/ [root@hadoop1 hadoop]# cp mapred-site.xml.template mapred-site.xml [root@hadoop1 hadoop]# vim mapred-site.xml <configuration> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> <property> <name>mapreduce.jobhistory.address</name> <value>hadoop1:10020</value> </property> <property> <name>mapreduce.jobhistory.webapp.address</name> <value>hadoop1:19888</value> </property> </configuration> [root@hadoop1 hadoop]# vim slaves hadoop1 hadoop2 hadoop3 [root@hadoop2 ~]# useradd -g hadoop hadoop [root@hadoop3 ~]# useradd -g hadoop hadoop [root@hadoop1 ~]# passwd hadoop ##hadoop [root@hadoop1 hadoop]# chown -R hadoop:hadoop /opt/hadoop [hadoop@hadoop1 ~]# ssh-keygen [hadoop@hadoop2 ~]# ssh-keygen [hadoop@hadoop3 ~]# ssh-keygen [hadoop@hadoop1 ~]# ssh-copy-id hadoop1 [hadoop@hadoop2 ~]# ssh-copy-id hadoop1 [hadoop@hadoop3 ~]# ssh-copy-id hadoop1 [hadoop@hadoop1 ~]$ scp ~/.ssh/authorized_keys hadoop2:~/.ssh/ [hadoop@hadoop1 ~]$ scp ~/.ssh/authorized_keys hadoop3:~/.ssh/[hadoop@hadoop1 ~]$ ssh hadoop2 [hadoop@hadoop2 ~]$ ssh hadoop3 [hadoop@hadoop3 ~]$ ssh hadoop1 [hadoop@hadoop1 ~]$ ssh hadoop3 Last login: Fri May 31 15:58:20 2019 from hadoop2 [hadoop@hadoop3 ~]$ ssh hadoop2 Last login: Fri May 31 15:58:12 2019 from hadoop1 [hadoop@hadoop2 ~]$ ssh hadoop1 Last login: Fri May 31 15:58:29 2019 from hadoop3
--启动并测试 Hadoop
sudo chown -R hadoop:hadoop /opt/hadoop/ [hadoop@hadoop1 bin]$ vim ~/.bash_profile [hadoop@hadoop1 bin]$ source ~/.bash_profile [hadoop@hadoop1 bin]$ hdfs namenode -format hare/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-2.9.1.jar:/contrib/capacity-scheduler/*.jar STARTUP_MSG: build = https://github.com/apache/hadoop.git -r e30710aea4e6e55e69372929106cf119af06fd0e; compiled by 'root' on 2018-04-16T09:33Z STARTUP_MSG: java = 1.8.0_191 9/05/31 16:04:24 WARN namenode.NameNode: Encountered exception during format: java.io.IOException: Cannot create directory /opt/hadoopdata/hdfs/name/current at org.apache.hadoop.hdfs.server.common.Storage$StorageDirectory.clearDirectory(Storage.java:361) at org.apache.hadoop.hdfs.server.namenode.NNStorage.format(NNStorage.java:571) at org.apache.hadoop.hdfs.server.namenode.NNStorage.format(NNStorage.java:592) at org.apache.hadoop.hdfs.server.namenode.FSImage.format(FSImage.java:172) at org.apache.hadoop.hdfs.server.namenode.NameNode.format(NameNode.java:1172) at org.apache.hadoop.hdfs.server.namenode.NameNode.createNameNode(NameNode.java:1614) at org.apache.hadoop.hdfs.server.namenode.NameNode.main(NameNode.java:1741) 19/05/31 16:04:24 ERROR namenode.NameNode: Failed to start namenode. java.io.IOException: Cannot create directory /opt/hadoopdata/hdfs/name/current at org.apache.hadoop.hdfs.server.common.Storage$StorageDirectory.clearDirectory(Storage.java:361) at org.apache.hadoop.hdfs.server.namenode.NNStorage.format(NNStorage.java:571) at org.apache.hadoop.hdfs.server.namenode.NNStorage.format(NNStorage.java:592) at org.apache.hadoop.hdfs.server.namenode.FSImage.format(FSImage.java:172) at org.apache.hadoop.hdfs.server.namenode.NameNode.format(NameNode.java:1172) at org.apache.hadoop.hdfs.server.namenode.NameNode.createNameNode(NameNode.java:1614) at org.apache.hadoop.hdfs.server.namenode.NameNode.main(NameNode.java:1741) 19/05/31 16:04:24 INFO util.ExitUtil: Exiting with status 1: java.io.IOException: Cannot create directory /opt/hadoopdata/hdfs/name/current 19/05/31 16:04:24 INFO namenode.NameNode: SHUTDOWN_MSG: /************************************************************ SHUTDOWN_MSG: Shutting down NameNode at hadoop1/1 [hadoop@hadoop1 opt]$ sudo chown -R hadoop:hadoop /opt/hadoopdata/ [hadoop@hadoop1 opt]$ hdfs namenode -format 19/05/31 16:10:20 INFO namenode.FSImage: Allocated new BlockPoolId: BP-339605524-192.168.19.69-1559290220937 19/05/31 16:10:20 INFO common.Storage: Storage directory /opt/hadoopdata/hdfs/name has been successfully formatted. --启动并测试 HDFS [hadoop@hadoop1 bin]$ start-dfs.sh 19/05/31 16:12:08 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Starting namenodes on [hadoop1] hadoop1: starting namenode, logging to /opt/hadoop-2.9.1/logs/hadoop-hadoop-namenode-hadoop1.out hadoop2: starting datanode, logging to /opt/hadoop-2.9.1/logs/hadoop-hadoop-datanode-hadoop2.out hadoop3: starting datanode, logging to /opt/hadoop-2.9.1/logs/hadoop-hadoop-datanode-hadoop3.out hadoop1: starting datanode, logging to /opt/hadoop-2.9.1/logs/hadoop-hadoop-datanode-hadoop1.out Starting secondary namenodes [hadoop2] hadoop2: starting secondarynamenode, logging to /opt/hadoop-2.9.1/logs/hadoop-hadoop-secondarynamenode-hadoop2.out 19/05/31 16:12:26 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable --http://1:50070/ 是否正常
检查进程是否启动
[hadoop@hadoop1 opt]$ jps 3347 DataNode 3242 NameNode 3647 Jps [hadoop@hadoop2 hadoop]$ jps 2880 DataNode 3057 Jps 2990 SecondaryNameNode [hadoop@hadoop3 ~]$ jps 2929 DataNode 3022 Jps 上传文件并查看 hdfs [hadoop@hadoop1 opt]$ hdfs dfs -mkdir -p /user/hadoop 19/05/31 16:20:01 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable [hadoop@hadoop1 opt]$ hdfs dfs -put /etc/hosts . 19/05/31 16:20:26 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable [hadoop@hadoop1 opt]$ hdfs dfs -ls . 19/05/31 16:20:35 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Found 1 items -rw-r--r-- 2 hadoop supergroup 224 2019-05-31 16:20 hosts
启动 YARN 并查看 Web UI
[hadoop@hadoop1 opt]$ start-yarn.sh starting yarn daemons starting resourcemanager, logging to /opt/hadoop-2.9.1/logs/yarn-hadoop-resourcemanager-hadoop1.out hadoop3: starting nodemanager, logging to /opt/hadoop-2.9.1/logs/yarn-hadoop-nodemanager-hadoop3.out hadoop2: starting nodemanager, logging to /opt/hadoop-2.9.1/logs/yarn-hadoop-nodemanager-hadoop2.out hadoop1: starting nodemanager, logging to /opt/hadoop-2.9.1/logs/yarn-hadoop-nodemanager-hadoop1.out
启动 history-server 并查看 Web UI
[hadoop@hadoop1 opt]$ mr-jobhistory-daemon.sh start historyserver starting historyserver, logging to /opt/hadoop-2.9.1/logs/mapred-hadoop-historyserver-hadoop1.out
运行 MR 作业
[hadoop@hadoop1 opt]$ hadoop jar /opt/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.9.1.jar wordcount hosts result
[hadoop@hadoop1 opt]$ hdfs dfs -ls result 19/05/31 16:29:07 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Found 2 items -rw-r--r-- 2 hadoop supergroup 0 2019-05-31 16:28 result/_SUCCESS -rw-r--r-- 2 hadoop supergroup 210 2019-05-31 16:28 result/part-r-00000 [hadoop@hadoop1 opt]$ hdfs dfs -cat result/part-r-00000 19/05/31 16:29:35 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 127.0.0.1 1 1 1 2 1 3 1 ::1 1 hadoop1 1 hadoop2 1 hadoop3 1 localhost 2 localhost.localdomain 2 localhost4 1 localhost4.localdomain4 1 localhost6 1 localhost6.localdomain6 1
通过 hdfs 的 Web UI 查看：
通过 ResourceManager 的 Web UI 查看
通过 JobHistoryServer 的 Web UI 查看
简单测试完成。