大数据学习环境搭建(CentOS6.9+Hadoop2.7.3+Hive1.2.1+Hbase1.3.1+Spark2.1.1)


 

 

node1

192.168.1.11

node2

192.168.1.12

node3

192.168.1.13

备注

NameNode

Hadoop

Y

Y


高可用

DateNode

 Y

Y

Y


ResourceManager

 Y

Y


高可用
NodeManager

Y

Y

Y


JournalNodes 

Y

Y

Y

奇数个,至少3个节点
ZKFC(DFSZKFailoverController

Y

Y

 

namenode的地方就有ZKFC

QuorumPeerMain

Zookeeper

Y

Y

Y


MySQL

HIVE

 Y

 

 

Hive元数据库

MetastoreRunJar

 Y

 



HIVERunJar

Y

 

 


HMasterHBaseYY
高可用
HRegionServerYYY

Spark(Master)

Spark

Y

 Y

 

高可用

Spark(Worker)

 Y

Y

Y




以前搭建过一套,带Federation,至少需4台机器,过于复杂,笔记本也吃不消。现为了学习Spark2.0版本,决定去掉Federation,简化学习环境,不过还是完全分布式

所有软件包:
apache-ant-1.9.9-bin.tar.gz
apache-hive-1.2.1-bin.tar.gz
apache-maven-3.3.9-bin.tar.gz
apache-tomcat-6.0.44.tar.gz
CentOS-6.9-x86_64-minimal.iso
findbugs-3.0.1.tar.gz
hadoop-2.7.3-src.tar.gz
hadoop-2.7.3.tar.gz
hadoop-2.7.3(自已编译的centOS6.9版本).tar.gz
hbase-1.3.1-bin(自己编译).tar.gz
hbase-1.3.1-src.tar.gz
jdk-8u121-linux-x64.tar.gz
mysql-connector-java-5.6-bin.jar
protobuf-2.5.0.tar.gz
scala-2.11.11.tgz
snappy-1.1.3.tar.gz
spark-2.1.1-bin-hadoop2.7.tgz

关闭防火墙

[root@node1 ~]# service iptables stop 
[root@node1 ~]# chkconfig iptables off

zookeeper

[root@node1 ~]# tar -zxvf /root/zookeeper-3.4.9.tar.gz -C /root
[root@node1 ~]# cp /root/zookeeper-3.4.9/conf/zoo_sample.cfg /root/zookeeper-3.4.9/conf/zoo.cfg
[root@node1 ~]# vi /root/zookeeper-3.4.9/conf/zoo.cfg

[root@node1 ~]# vi /root/zookeeper-3.4.9/bin/zkEnv.sh 
[root@node1 ~]# mkdir /root/zookeeper-3.4.9/logs
[root@node1 ~]# vi /root/zookeeper-3.4.9/conf/log4j.properties 
  
[root@node1 ~]# mkdir /root/zookeeper-3.4.9/zkData
[root@node1 ~]# scp -r /root/zookeeper-3.4.9 node2:/root
[root@node1 ~]# scp -r /root/zookeeper-3.4.9 node3:/root

[root@node1 ~]# touch /root/zookeeper-3.4.9/zkData/myid
[root@node1 ~]# echo 1 > /root/zookeeper-3.4.9/zkData/myid
[root@node2 ~]# touch /root/zookeeper-3.4.9/zkData/myid
[root@node2 ~]# echo 2 > /root/zookeeper-3.4.9/zkData/myid
[root@node3 ~]# touch /root/zookeeper-3.4.9/zkData/myid
[root@node3 ~]# echo 3 > /root/zookeeper-3.4.9/zkData/myid

环境变量

[root@node1 ~]# vi /etc/profile
export JAVA_HOME=/root/jdk1.8.0_121
export SCALA_HOME=/root/scala-2.11.11
export HADOOP_HOME=/root/hadoop-2.7.3
export HIVE_HOME=/root/apache-hive-1.2.1-bin
export HBASE_HOME=/root/hbase-1.3.1
export SPARK_HOME=/root/spark-2.1.1-bin-hadoop2.7
export PATH=.:$PATH:$JAVA_HOME/bin:$SCALA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:/root:$HIVE_HOME/bin:$HBASE_HOME/bin:$SPARK_HOME
export CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
[root@node1 ~]# source /etc/profile
[root@node1 ~]# scp /etc/profile node2:/etc
[root@node2 ~]# source /etc/profile
[root@node1~]# scp /etc/profile node3:/etc
[root@node3 ~]# source /etc/profile

Hadoop

[root@node1 ~]# tar -zxvf /root/hadoop-2.7.3.tar.gz -C /root
[root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/hadoop-env.sh
  
[root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/hdfs-site.xml
<property>
   <name>dfs.replication</name>
   <value>2</value>
</property>
<property>
   <name>dfs.blocksize</name>
   <value>64m</value>
</property>
<property>
   <name>dfs.permissions.enabled</name>
<value>false</value>
</property>
<property>
  <name>dfs.nameservices</name>
  <value>mycluster</value>
</property>
<property>
  <name>dfs.ha.namenodes.mycluster</name>
  <value>nn1,nn2</value>
</property>
<property>
  <name>dfs.namenode.rpc-address.mycluster.nn1</name>
  <value>node1:8020</value>
</property>
<property>
  <name>dfs.namenode.rpc-address.mycluster.nn2</name>
  <value>node2:8020</value>
</property>
<property>
  <name>dfs.namenode.http-address.mycluster.nn1</name>
  <value>node1:50070</value>
</property>
<property>
  <name>dfs.namenode.http-address.mycluster.nn2</name>
  <value>node2:50070</value>
</property>
<property>
  <name>dfs.namenode.shared.edits.dir</name>
  <value>qjournal://node1:8485;node2:8485;node3:8485/mycluster</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/root/hadoop-2.7.3/tmp/journal</value>
</property>
<property>
   <name>dfs.ha.automatic-failover.enabled.mycluster</name>
   <value>true</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</value>
</property>
<property>
  <name>dfs.ha.fencing.ssh.private-key-files</name>
  <value>/root/.ssh/id_rsa</value>
</property>
[root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/core-site.xml
<property>
<name>fs.defaultFS</name>
<value>hdfs://mycluster</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/root/hadoop-2.7.3/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>node1:2181,node2:2181,node3:2181</value>
</property>

[root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/slaves
node1
node2
node3
[root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/yarn-env.sh
 [root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/mapred-site.xml
<configuration>
<property> 
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>node1:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>node1:19888</value>
</property>
<property>
<name>mapreduce.jobhistory.max-age-ms</name>
<value>6048000000</value>
</property>
</configuration>
[root@node1 ~]# vi /root/hadoop-2.7.3/etc/hadoop/yarn-site.xml
<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.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yarn-cluster</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>node1</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>node2</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>node1:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>node2:8088</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>node1:2181,node2:2181,node3:2181</value>
</property>
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>   
<value>true</value>
</property>
<property>
<name>yarn.log.server.url</name>
<value>http://node1:19888/jobhistory/logs</value>
</property>

[root@node1 ~]# mkdir -p /root/hadoop-2.7.3/tmp/journal
[root@node2 ~]# mkdir -p /root/hadoop-2.7.3/tmp/journal
[root@node3 ~]# mkdir -p /root/hadoop-2.7.3/tmp/journal

将编译的本地包中的native库替换/root/hadoop-2.7.3/lib/native

[root@node1 ~]# scp -r /root/hadoop-2.7.3/ node2:/root 
[root@node1 ~]# scp -r /root/hadoop-2.7.3/ node3:/root 

查看自己的Hadoop是32位还是64位
[root@node1 native]# file libhadoop.so.1.0.0 
libhadoop.so.1.0.0: ELF 64-bit LSB shared object, x86-64, version 1 (SYSV), dynamically linked, not stripped
[root@node1 native]# pwd
/root/hadoop-2.7.3/lib/native

启动ZK

[root@node1 ~]#/root/zookeeper-3.4.9/bin/zkServer.sh start
[root@node2 ~]#/root/zookeeper-3.4.9/bin/zkServer.sh start
[root@node3 ~]#/root/zookeeper-3.4.9/bin/zkServer.sh start

格式化zkfc

[root@node1 ~]# /root/hadoop-2.7.3/bin/hdfs zkfc -formatZK   
[root@node1 ~]# /root/zookeeper-3.4.9/bin/zkCli.sh

启动journalnode

[root@node1 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start journalnode
[root@node2 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start journalnode
[root@node3 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start journalnode

Namenode格式化和启动

[root@node1 ~]# /root/hadoop-2.7.3/bin/hdfs namenode -format
[root@node1 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start namenode 
[root@node2 ~]# /root/hadoop-2.7.3/bin/hdfs namenode -bootstrapStandby
[root@node2 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start namenode

启动zkfc

[root@node1 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start zkfc
[root@node2 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start zkfc

启动datanode

[root@node1 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start datanode
[root@node2 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start datanode
[root@node3 ~]# /root/hadoop-2.7.3/sbin/hadoop-daemon.sh start datanode

启动yarn

[root@node1 ~]# /root/hadoop-2.7.3/sbin/yarn-daemon.sh start resourcemanager
[root@node2 ~]# /root/hadoop-2.7.3/sbin/yarn-daemon.sh start resourcemanager

[root@node1 ~]# /root/hadoop-2.7.3/sbin/yarn-daemon.sh start nodemanager
[root@node2 ~]# /root/hadoop-2.7.3/sbin/yarn-daemon.sh start nodemanager
[root@node3 ~]# /root/hadoop-2.7.3/sbin/yarn-daemon.sh start nodemanager

[root@node1 ~]# hdfs dfs -chmod -R 777 /

安装MySQL

[root@node1 ~]# yum remove -y mysql-libs

[root@node1 ~]# yum install mysql-server
[root@node1 ~]# service mysqld start
[root@node1 ~]# chkconfig mysqld on
[root@node1 ~]# mysqladmin -u root password 'AAAaaa111'
[root@node1 ~]# mysqladmin -u root -h node1 password 'AAAaaa111'

[root@node1 ~]# mysql -h localhost -u root -p

Enter password: AAAaaa111

mysql> GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' IDENTIFIED BY 'AAAaaa111' WITH GRANT OPTION;
mysql> flush privileges;


[root@node1 ~]# vi /etc/my.cnf
[client]
default-character-set=utf8
[mysql]
default-character-set=utf8
[mysqld]
character-set-server=utf8
lower_case_table_names = 1

[root@node1 ~]# service mysqld restart

HIVE安装


由于官方提供的spark-2.1.1-bin-hadoop2.7.tgz包中集成的Hive是1.2.1,所以Hive版本选择1.2.1

[root@node1 ~]# tar -xvf apache-hive-1.2.1-bin.tar.gz

将mysql-connector-java-5.6-bin.jar 驱动放在 /root/hive-1.2.1/lib/ 目录下面

[root@node1 ~]# cp /root/apache-hive-1.2.1-bin/conf/hive-env.sh.template /root/apache-hive-1.2.1-bin/conf/hive-env.sh
[root@node1 ~]# vi /root/apache-hive-1.2.1-bin/conf/hive-env.sh
         export HADOOP_HOME=/root/hadoop-2.7.3
[root@node1 ~]# cp /root/apache-hive-1.2.1-bin/conf/hive-log4j.properties.template /root/apache-hive-1.2.1-bin/conf/hive-log4j.properties
[root@node1 ~]# vi /root/apache-hive-1.2.1-bin/conf/hive-site.xml
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>thrift://node1:9083</value>
</property> 

<property>
<name>hive.metastore.warehouse.dir</name>
<value>/user/hive/warehouse</value>
</property>

<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://node1:3306/hive?createDatabaseIfNotExist=true&amp;characterEncoding=UTF-8</value>
</property>

<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.jdbc.Driver</value>
</property>

<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
</property>

<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>AAAaaa111</value>
</property>
</configuration>

[root@node1 ~]# vi /etc/init.d/hive-metastore 
        /root/apache-hive-1.2.1-bin/bin/hive --service metastore >/dev/null 2>&1 &
[root@node1 ~]# chmod 777 /etc/init.d/hive-metastore 
[root@node1 ~]# ln -s /etc/init.d/hive-metastore /etc/rc.d/rc3.d/S65hive-metastore
[root@node1 ~]# hive
[root@node1 ~]# mysql -h localhost -u root -p
mysql> alter database hive character set latin1;

Hbase编译安装


官方提供的是基础Hadoop2.5.1编译的,所以要进行编译:
 
将pom.xml文件中依赖的hadoop版本修改:
<hadoop-two.version>2.5.1</hadoop-two.version>
修改为
<hadoop-two.version>2.7.3</hadoop-two.version>

 <compileSource>1.7</compileSource>
修改为
 <compileSource>1.8</compileSource>

例如如下命令打包:
mvn clean package -DskipTests -Prelease assembly:single

/root/hbase-1.3.1/hbase-assembly/target/hbase-1.3.1-bin.tar.gz
下面基于此安装包进行Hbase的安装:

[root@node1 ~]# cp /root/hadoop-2.7.3/etc/hadoop/hdfs-site.xml /root/hadoop-2.7.3/etc/hadoop/core-site.xml /root/hbase-1.3.1/conf/

[root@node1 ~]# vi /root/hbase-1.3.1/conf/hbase-env.sh 
export JAVA_HOME=/root/jdk1.8.0_121
export HBASE_MANAGES_ZK=false

[root@node1 ~]# vi /root/hbase-1.3.1/conf/hbase-site.xml
<property>
        <name>hbase.rootdir</name>
        <value>hdfs://mycluster:8020/hbase</value>
</property>
<property>
        <name>hbase.cluster.distributed</name>
        <value>true</value>
</property>
<property>
        <name>hbase.zookeeper.quorum</name>
        <value>node1:2181,node2:2181,node3:2181</value>
</property>
<property>
    <name>hbase.master.port</name>
    <value>60000</value>
</property>
<property>
    <name>hbase.master.info.port</name>
    <value>60010</value>
</property>
<property>
    <name>hbase.tmp.dir</name>
    <value>/root/hbase-1.3.1/tmp</value>
</property>
<property>
    <name>hbase.regionserver.port</name>
    <value>60020</value>
</property>
<property>
    <name>hbase.regionserver.info.port</name>
    <value>60030</value>
</property>
[root@node1 ~]# vi /root/hbase-1.3.1/conf/regionservers 
node1
node2
node3
[root@node1 ~]# mkdir -p /root/hbase-1.3.1/tmp

[root@node1 ~]# vi /root/hbase-1.3.1/conf/hbase-env.sh 
# Configure PermSize. Only needed in JDK7. You can safely remove it for JDK8+
#export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
#export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
将etc/profile,及hbase复制到其他两个节点上

[root@node1 ~]# start-hbase.sh
#back-master需要手动起
[root@node2 ~]# hbase-daemon.sh start master

[root@node1 ~]# hbase shell

spark


[root@node1 ~]# cp /root/spark-2.1.1-bin-hadoop2.7/conf/spark-env.sh.template /root/spark-2.1.1-bin-hadoop2.7/conf/spark-env.sh
[root@node1 ~]# vi /root/spark-2.1.1-bin-hadoop2.7/conf/spark-env.sh
export SCALA_HOME=/root/scala-2.11.11
export JAVA_HOME=/root/jdk1.8.0_121
export HADOOP_HOME=/root/hadoop-2.7.3
export HADOOP_CONF_DIR=/root/hadoop-2.7.3/etc/hadoop
export SPARK_DAEMON_JAVA_OPTS="-Dspark.deploy.recoveryMode=ZOOKEEPER -Dspark.deploy.zookeeper.url=node1:2181,node2:2181,node3:2181 -Dspark.deploy.zookeeper.dir=/spark"
[root@node1 ~]# cp /root/spark-2.1.1-bin-hadoop2.7/conf/slaves.template /root/spark-2.1.1-bin-hadoop2.7/conf/slaves
[root@node1 ~]# vi /root/spark-2.1.1-bin-hadoop2.7/conf/slaves
node1
node2
node3
[root@node1 ~]# scp -r /root/spark-2.1.1-bin-hadoop2.7 node2:/root
[root@node1 ~]# scp -r /root/spark-2.1.1-bin-hadoop2.7 node3:/root

[root@node1 ~]# /root/spark-2.1.1-bin-hadoop2.7/sbin/start-all.sh

./start.sh

/root/zookeeper-3.4.9/bin/zkServer.sh start
ssh root@node2 'export BASH_ENV=/etc/profile;/root/zookeeper-3.4.9/bin/zkServer.sh start'
ssh root@node3 'export BASH_ENV=/etc/profile;/root/zookeeper-3.4.9/bin/zkServer.sh start'

/root/hadoop-2.7.3/sbin/start-dfs.sh
/root/hadoop-2.7.3/sbin/start-yarn.sh
#如果Yarn做HA,则打开
#ssh root@node2 'export BASH_ENV=/etc/profile;/root/hadoop-2.7.3/sbin/yarn-daemon.sh start resourcemanager'

/root/hadoop-2.7.3/sbin/hadoop-daemon.sh start zkfc
ssh root@node2 'export BASH_ENV=/etc/profile;/root/hadoop-2.7.3/sbin/hadoop-daemon.sh start zkfc'
ssh root@node3 'export BASH_ENV=/etc/profile;/root/hadoop-2.7.3/sbin/hadoop-daemon.sh start zkfc'

/root/hadoop-2.7.3/bin/hdfs haadmin -ns mycluster -failover nn2 nn1
echo 'Y' | ssh root@node1 'export BASH_ENV=/etc/profile;/root/hadoop-2.7.3/bin/yarn rmadmin -transitionToActive --forcemanual rm1'

/root/hbase-1.3.1/bin/start-hbase.sh
#如果HBase做HA,则打开
#ssh root@node2 'export BASH_ENV=/etc/profile;/root/hbase-1.3.1/bin/hbase-daemon.sh start master'

/root/spark-2.1.1-bin-hadoop2.7/sbin/start-all.sh
#如果Spark做HA,则打开
#ssh root@node2 'export BASH_ENV=/etc/profile;/root/spark-2.1.1-bin-hadoop2.7/sbin/start-master.sh'

/root/hadoop-2.7.3/sbin/mr-jobhistory-daemon.sh start historyserver

echo '--------------node1---------------'
jps | grep -v Jps | sort  -k 2 -t ' '
echo '--------------node2---------------'
ssh root@node2 "export PATH=/usr/bin:$PATH;jps | grep -v Jps | sort  -k 2 -t ' '"
echo '--------------node3---------------'
ssh root@node3 "export PATH=/usr/bin:$PATH;jps | grep -v Jps | sort  -k 2 -t ' '"

./stop.sh 

/root/spark-2.1.1-bin-hadoop2.7/sbin/stop-all.sh

/root/hbase-1.3.1/bin/stop-hbase.sh

#如果Yarn开HA,则去掉注释
#ssh root@node2 'export BASH_ENV=/etc/profile;/root/hadoop-2.7.3/sbin/yarn-daemon.sh stop resourcemanager'
/root/hadoop-2.7.3/sbin/stop-yarn.sh
/root/hadoop-2.7.3/sbin/stop-dfs.sh

/root/hadoop-2.7.3/sbin/hadoop-daemon.sh stop zkfc
ssh root@node2 'export BASH_ENV=/etc/profile;/root/hadoop-2.7.3/sbin/hadoop-daemon.sh stop zkfc'

/root/zookeeper-3.4.9/bin/zkServer.sh stop
ssh root@node2 'export BASH_ENV=/etc/profile;/root/zookeeper-3.4.9/bin/zkServer.sh stop'
ssh root@node3 'export BASH_ENV=/etc/profile;/root/zookeeper-3.4.9/bin/zkServer.sh stop'

/root/hadoop-2.7.3/sbin/mr-jobhistory-daemon.sh stop historyserver

./shutdown.sh 

ssh root@node2 "export PATH=/usr/bin:$PATH;shutdown -h now"
ssh root@node3 "export PATH=/usr/bin:$PATH;shutdown -h now"
shutdown -h now

./reboot.sh 

ssh root@node2 "export PATH=/usr/bin:$PATH;reboot"
ssh root@node3 "export PATH=/usr/bin:$PATH;reboot"
reboot




















posted @ 2017-06-28 13:04  江正军  阅读(...)  评论(... 编辑 收藏