hadoop安装

安装jdk

rpm -ivh /opt/downloads/jdk-8u201-linux-x64.rpm

vim /etc/profile 最下方加入

export JAVA_HOME=/usr/java/jdk1.8.0_201-amd64
export JAVA_BIN=/usr/java/jdk1.8.0_201-amd64/bin
export PATH=$PATH:$JAVA_HOME/bin
export CLASSPATH=:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar

source /etc/profile

vim /etc/bashrc 最下方加入

export JAVA_HOME=/usr/java/jdk1.8.0_201-amd64
export JAVA_BIN=/usr/java/jdk1.8.0_201-amd64/bin
export PATH=$PATH:$JAVA_HOME/bin
export CLASSPATH=:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar

source /etc/bashrc

下载hadoop
wget -P /opt/downloads http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-3.2.0/hadoop-3.2.0.tar.gz
tar zxvf /opt/downloads/hadoop-3.2.0.tar.gz -C /opt
mv /opt/hadoop-3.2.0/ /opt/hadoop

cp /opt/hadoop/etc/hadoop/*.xml input
/opt/hadoop/bin/hadoop jar /opt/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.2.0.jar grep input output 'dfs[a-z.]+'

创建文件夹
mkdir /opt/hadoop/tmp
mkdir /opt/hadoop/var
mkdir /opt/hadoop/dfs
mkdir /opt/hadoop/dfs/name
mkdir /opt/hadoop/dfs/data
mkdir /opt/hadoop/fs/checkpoint -p
mkdir /opt/hadoop/fs/checkpoint/edits
mkdir /opt/hadoop/jobhistory/done -p
mkdir /opt/hadoop/jobhistory/done_intermediate -p

查看java_home路径
echo $JAVA_HOME

修改配置

文件系统

vim /opt/hadoop/etc/hadoop/core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
        <property>
                <name>hadoop.tmp.dir</name>
                <value>../tmp</value>
                <description>namenode上本地的hadoop临时文件夹</description>
        </property>
        <property>
                <name>io.file.buffer.size</name>
                <value>262144</value>
                <description>Size of read/write buffer used in SequenceFiles.256k</description>
        </property>
        <property>
                <name>io.native.lib.available</name>
                <value>true</value>
        </property>
        <property>
                <name>fs.defaultFS</name>
                <value>hdfs://0.0.0.0:9000</value>
                <description>HDFS的URI，文件系统://namenode标识:端口号</description>
        </property>
</configuration>

name 节点用 fs.defaultFS，不建议使用 fs.default.name。

hadoop.tmp.dir 是hadoop文件系统依赖的基础配置，很多路径都依赖它。如果下面hdfs-site.xml中不配置 namenode 和 datanode 的存放位置，默认就放在如下路径中。

副本

vim /opt/hadoop/etc/hadoop/hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
        <description>副本个数，配置默认是3,应小于datanode机器数量</description>
    </property>
    <property>
        <name>dfs.namenode.http-address</name>
        <value>0.0.0.0:9870</value>
    </property>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>../dfs/name</value>
        <description>Path on the local filesystem where the NameNode stores the namespace and transactions logs persistently.</description>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>../dfs/data</value>
        <description>Comma separated list of paths on the localfilesystem of a DataNode where it should store its blocks.</description>
    </property>
    <property>
        <name>dfs.permissions</name>
        <value>false</value>
        <description>need not permissions</description>
    </property>
    <property>
        <name>dfs.webhdfs.enabled</name> 
        <value>true</value> 
    </property>
    <property>
        <name>dfs.block.size</name> 
        <value>134217728</value> 
        <description>HDFS blocksize of 128MB for large file-systems.used for on-line</description> 
        </property>
    <property>
        <name>fs.checkpoint.dir</name>
        <value>../checkpoint</value>
    </property>
    <property>
        <name>fs.checkpoint.edits.dir</name>
        <value>../checkpoint</value>
    </property>
</configuration>

资源调度框架

vim /opt/hadoop/etc/hadoop/mapred-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
        <description>设置MapReduce的运行平台为yarn。local表示本地运行，classic表示经典mapreduce框架，yarn表示新的框架。</description>
    </property>
    <property>
        <name>mapred.job.tracker</name>
        <value>0.0.0.0:9001</value>
    </property>
    <property>
        <name>mapred.local.dir</name>
        <value>../var</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>0.0.0.0:10020</value>
        <description>MapReduce JobHistory Server IPC host:port</description>
    </property>
    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>0.0.0.0:19888</value>
        <description>MapReduce JobHistory Server Web UI host:port</description>
    </property>
    <property>
        <name>mapreduce.jobhistory.done-dir</name>
        <value>../jobhistory/done</value>
        <description>MapReduce作业运行完之后放在哪</description>
    </property>
    <property>
        <name>mapreduce.jobhistory.intermediate-done-dir</name>
        <value>../jobhistory/done_intermediate</value>
        <description>MapReduce正在运行中的作业放在哪</description>
    </property>
    <property>
        <name>yarn.app.mapreduce.am.resource.mb</name>
    <value>512</value>
    </property>
    <property>
        <name>mapreduce.map.memory.mb</name>
        <value>512</value>
    </property>
    <property>
        <name>mapreduce.map.java.opts</name>
        <value>-Xmx512M</value>
    </property>
    <property>
        <name>mapreduce.reduce.memory.mb</name>
        <value>512</value>
    </property>
    <property>
        <name>mapreduce.reduce.java.opts</name>
        <value>-Xmx512M</value>
    </property>
    <property>
        <name>mapred.child.java.opts</name>
        <value>-Xmx512M</value>
    </property>
</configuration>

vim /opt/hadoop/etc/hadoop/yarn-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
        <description>NodeManager上运行的附属服务</description>
    </property>
    <property>
        <name>yarn.nodemanager.auxservices.mapreduce.shuffle.class</name>
        <value>org.apache.hadoop.mapred.ShuffleHandler</value>
    </property>
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>
        <value>0.0.0.0:8031</value>
    </property>
    <property>
        <name>yarn.resourcemanager.address</name>
        <value>0.0.0.0:8032</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>
        <value>0.0.0.0:8030</value>
    </property>
    <property>
        <name>yarn.resourcemanager.admin.address</name>
        <value>0.0.0.0:8033</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address</name>
        <value>0.0.0.0:48088</value>
    </property>
    <property>  
        <name>yarn.log-aggregation-enable</name>  
        <value>true</value>  
    </property>
    <property>
        <name>yarn.nodemanager.env-whitelist</name>
        <value> JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_HOME,PATH,LANG,TZ</value>
        <description>容器可能会覆盖的环境变量，而不是使用NodeManager的默认值</description>
    </property>
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</value>
        <description>关闭内存检测，虚拟机需要，虚拟环境不设置为false会报错</description>
    </property>
</configuration>

我机器上influxdb占用了8088端口，这里换成18088

vim /opt/hadoop/sbin/start-dfs.sh
头部加上

HDFS_DATANODE_USER=root
HDFS_DATANODE_SECURE_USER=hdfs
HDFS_NAMENODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root

vim /opt/hadoop/sbin/stop-dfs.sh
头部加上

HDFS_DATANODE_USER=root
HDFS_DATANODE_SECURE_USER=hdfs
HDFS_NAMENODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root

vim /opt/hadoop/sbin/start-yarn.sh
头部加上

YARN_RESOURCEMANAGER_USER=root
HDFS_DATANODE_SECURE_USER=yarn
YARN_NODEMANAGER_USER=root

vim /opt/hadoop/sbin/stop-yarn.sh
头部加上

YARN_RESOURCEMANAGER_USER=root
HDFS_DATANODE_SECURE_USER=yarn
YARN_NODEMANAGER_USER=root

vim /opt/hadoop/etc/hadoop/hadoop-env.sh

export JAVA_HOME=/usr/java/jdk1.8.0_201-amd64
export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export HADOOP_PID_DIR=/var/run

修改jdk路径，不能有空格

pid_dir影响 NameNode DataNode SecondaryNameNode 的进程pid存储

vim /opt/hadoop/etc/hadoop/mapred-env.sh

export JAVA_HOME=/usr/java/jdk1.8.0_201-amd64
export HADOOP_MAPRED_PID_DIR=/var/run

pid_dir影响 JobHistoryServer 的进程pid存储

vim /opt/hadoop/etc/hadoop/yarn-env.sh

export JAVA_HOME=/usr/java/jdk1.8.0_201-amd64
export HADOOP_PID_DIR=/var/run

pid_dir影响 NodeManager ResourceManager 的进程pid存储

检查ssh免密登录
ssh localhost

配置ssh免密登录
[root@localhost ~]# ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
[root@localhost ~]# cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
[root@localhost ~]# chmod 0600 ~/.ssh/authorized_keys

再次检查
ssh localhost

//查看版本
/opt/hadoop/bin/hadoop version

格式化 namenode
/opt/hadoop/bin/hdfs namenode -format
成功会看到 “successfully formatted” 和 “Exitting with status 0”，若为 “Exitting with status 1” 则是出错。

启动

/opt/hadoop/sbin/start-dfs.sh
/opt/hadoop/sbin/stop-dfs.sh

/opt/hadoop/sbin/start-all.sh
查看服务 jps

验证
/opt/hadoop/bin/hadoop fs -ls /

curl -X Get http://localhost:9870
curl -X Get http://localhost:18088

posted @ 2019-06-20 09:32 wintersoft 阅读(300) 评论(0) 编辑收藏举报

会员力量，点亮园子希望

刷新页面返回顶部

geek power

code change the world

hadoop安装

公告