大数据平台搭建-hadoop/hbase集群的搭建

时间:2022-12-16 08:10:10

版本要求

java

版本:1.8.*(1.8.0_60)

下载地址:http://www.oracle.com/technetwork/java/javase/downloads/jdk8-downloads-2133151.html

zookeeper

版本:3.4.*(zookeeper-3.4.8)

下载地址:http://mirrors.hust.edu.cn/apache/zookeeper/zookeeper-3.4.8/

hadoop

版本:2.7.*(hadoop-2.7.3)

下载地址:http://apache.fayea.com/hadoop/common/hadoop-2.7.3/

hbase

版本:1.2.*(hbase-1.2.4)

下载地址:http://archive.apache.org/dist/hbase/1.2.4/

hadoop安装

前置条件

免密登录

见链接http://www.cnblogs.com/molyeo/p/7007917.html

java安装

见链接http://www.cnblogs.com/molyeo/p/7007917.html

zookeeper安装

见链接http://www.cnblogs.com/molyeo/p/7048867.html

下载地址

http://apache.fayea.com/hadoop/common/hadoop-2.7.3/

解压安装

cd ~
tar -zxvf hadoop-2.7.3.tar.gz
mv  hadoop-2.7.3  hadoop  

配置环境变量

vi ~/.bash_profile
export JAVA_HOME=/wls/oracle/jdk
export SCALA_HOME=/wls/oracle/scala
export ZOOKEEPER_HOME=/wls/oracle/zookeeper
export HADOOP_HOME=/wls/oracle/hadoop
export HBASE_HOME=/wls/oracle/hbase
export SPARK_HOME=/wls/oracle/spark   

export PATH=$PATH:$HOME/bin:$JAVA_HOME/bin:$SCALA_HOME/bin:$SPARK_HOME/bin:$ZOOKEEPER_HOME/bin:$HADOOP_HOME/bin:$HBASE_HOME/bin
export CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar   

export PATH CLASSPATH JAVA_HOME  SCALA_HOME  ZOOKEEPER_HOME HADOOP_HOME SPARK_HOME   

hadoop配置更改

hadoop相关的配置都在$HADOOP_HOME/etc/hadoop目录下,hadoop集群搭建主要涉及如下配置文件的变更

hadoop-env.sh

hadoop-env.sh文件只需要改动JAVA_HOME为具体的路径即可

 export JAVA_HOME=/wls/oracle/jdk

core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://SZB-L0045546:9000</value>
    </property>
        <property>
        <name>hadoop.tmp.dir</name>
        <value>/wls/oracle/bigdata/hadoop/tmp</value>
    </property>

    <property>
        <name>ha.zookeeper.quorum</name>
        <value>SZB-L0045546:2181,SZB-L0045551:2181,SZB-L0045552:2181</value>
    </property>
</configuration>

hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>dfs.nameservices</name>
        <value>cluster</value>
    </property>
    <property>
        <name>dfs.ha.namenodes.cluster</name>
        <value>SZB-L0045546,SZB-L0045551</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.cluster.SZB-L0045546</name>
        <value>SZB-L0045546:9000</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.cluster.SZB-L0045546</name>
        <value>SZB-L0045546:50070</value>
    </property> 

    <property>
        <name>dfs.namenode.rpc-address.cluster.SZB-L0045551</name>
        <value>SZB-L0045551:9000</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.cluster.SZB-L0045551</name>
        <value>SZB-L0045551:50070</value>
    </property>
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://SZB-L0045552:8485;SZB-L0047815:8485;SZB-L0047816:8485/cluster</value>
    </property>
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/wls/oracle/bigdata/hadoop/journal</value>
    </property>
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>dfs.client.failover.proxy.provider.nsl</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>
</configuration>

slaves

SZB-L0045552
SZB-L0047815
SZB-L0047816

mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>

yarn-site.xml

<?xml version="1.0"?>
<configuration>
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>SZB-L0045546</value>
    </property>
        <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
</configuration>

运行命令

启动journalnode

启动journalnode

cd  /wls/oracle/hadoop/sbin
/wls/oracle/hadoop/sbin/hadoop-daemons.sh start journalnode

格式化hadoop

cd /wls/oracle/hadoop/bin
hadoop namenode -format

格式化zookeeper

cd /wls/oracle/hadoop/bin
hdfs zkfc -formatZK

cd /wls/oracle/hadoop/sbin
/wls/oracle/hadoop/sbin/start-dfs.sh

cd /wls/oracle/hadoop/sbin
/wls/oracle/hadoop/sbin/start-yarn.sh

hadoop集群停止

cd /wls/oracle/hadoop/sbin
/wls/oracle/hadoop/sbin/stop-yarn.sh

cd /wls/oracle/hadoop/sbin
/wls/oracle/hadoop/sbin/stop-dfs.sh

其他命令

/wls/oracle/hadoop/sbin/hadoop-daemon.sh start namenode
/wls/oracle/hadoop/sbin/hadoop-daemon.sh stop namenode
/wls/oracle/hadoop/bin/hdfs namenode -bootstrapStandby
/wls/oracle/hadoop/sbin/hadoop-daemon.sh start namenode
/wls/oracle/hadoop/sbin/hadoop-daemon.sh start datanode
/wls/oracle/hadoop/sbin/hadoop-daemon.sh --script hdfs start datanode

界面查看

hadoop
http://SZB-L0045546:50070

yarn
http://SZB-L0045546:8088/cluster

hdfs文件系统

hdfs dfs -ls hdfs://

mapreduce测试

hadoop jar /wls/oracle/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.3.jar pi 2 5

重复启停异常后,可以尝试删除

rm -f /wls/oracle/bigdata/hadoop/tmp/dfs/data/current/VERSION

hbase安装

解压安装

tar -zxvf hbase-1.2.4-bin.tar.gz
mv hbase-1.2.4-bin hbase

环境变量

vi ~/.bash_profile
export JAVA_HOME=/wls/oracle/jdk
export SCALA_HOME=/wls/oracle/scala
export ZOOKEEPER_HOME=/wls/oracle/zookeeper
export HADOOP_HOME=/wls/oracle/hadoop
export HBASE_HOME=/wls/oracle/hbase
export SPARK_HOME=/wls/oracle/spark   

export PATH=$PATH:$HOME/bin:$JAVA_HOME/bin:$SCALA_HOME/bin:$SPARK_HOME/bin:$ZOOKEEPER_HOME/bin:$HADOOP_HOME/bin:$HBASE_HOME/bin
export CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar   

export PATH CLASSPATH JAVA_HOME  SCALA_HOME  ZOOKEEPER_HOME HADOOP_HOME SPARK_HOME 

配置

hbase需要修改的配置主要包含如下文件

hbase-env.sh
hbase-site.xml
regionservers

hbase-env.sh

hbase-env.sh文件增加JAVA_HOME的配置即可

export JAVA_HOME=/wls/oracle/jdk

hbase-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>hbase.master</name>
        <value>10.20.112.59:60000</value>
    </property>
    <property>
        <name>hbase.master.maxclockskew</name>
        <value>180000</value>
    </property>
    <property>
        <name>hbase.rootdir</name>
        <value>hdfs://SZB-L0045546:9000/user/oracle/hbase</value>
    </property>
    <property>
        <name>hbase.cluster.distributed</name>
        <value>true</value>
    </property>
    <property>
        <name>hbase.zookeeper.quorum</name>
        <value>SZB-L0045546,SZB-L0045551,SZB-L0045552</value>
    </property>
    <property>
        <name>hbase.zookeeper.property.dataDir</name>
        <value>/hbase</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
</configuration>

regionservers

SZB-L0045546
SZB-L0045551
SZB-L0045552
SZB-L0047815
SZB-L0047816

运维命令

启动集群
/wls/oracle/hbase/bin/start_hbase.sh
停止集群
/wls/oracle/hbase/bin/stop_hbase.sh