Hadoop集群搭建（3）

Hadoop安装

与zookeeper大体一致

1. 上传并解压

1. 上传压缩包到/export/software目录

2. cd /export/software

3. tar xzvf hadoop-3.1.1.tar.gz -C ../servers

#####2. 修改配置文件

配置文件的位置在 hadoop/etc/hadoop

######core-site.xml

<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://bigdata1:8020</value>
    </property>
    <!-- 临时文件存储目录 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/export/servers/hadoop-3.1.1/datas/tmp</value>
    </property>
    <!--  缓冲区大小，实际工作中根据服务器性能动态调整 -->
    <property>
        <name>io.file.buffer.size</name>
        <value>8192</value>
    </property>
    <!--  开启hdfs的垃圾桶机制，删除掉的数据可以从垃圾桶中回收，单位分钟 -->
    <property>
        <name>fs.trash.interval</name>
        <value>10080</value>
    </property>
</configuration>

######hadoop-env.sh

export JAVA_HOME=/export/servers/jdk1.8.0_141

######hdfs-site.xml

<configuration>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/namenode/namenodedatas</value>
    </property>
    <property>
        <name>dfs.blocksize</name>
        <value>134217728</value>
    </property>
    <property>
        <name>dfs.namenode.handler.count</name>
        <value>10</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/datanode/datanodeDatas</value>
    </property>
    <property>
        <name>dfs.namenode.http-address</name>
        <value>bigdata1:50070</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>3</value>
    </property>
    <property>
        <name>dfs.permissions.enabled</name>
        <value>false</value>
    </property>
    <property>
        <name>dfs.namenode.checkpoint.edits.dir</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/dfs/nn/snn/edits</value>
    </property>
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>bigdata1.hadoop.com:50090</value>
    </property>
    <property>
        <name>dfs.namenode.edits.dir</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/dfs/nn/edits</value>
    </property>
    <property>
        <name>dfs.namenode.checkpoint.dir</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/dfs/snn/name</value>
    </property>
</configuration>

######mapred-site.xml

<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <property>
        <name>mapreduce.map.memory.mb</name>
        <value>1024</value>
    </property>
    <property>
        <name>mapreduce.map.java.opts</name>
        <value>-Xmx512M</value>
    </property>
    <property>
        <name>mapreduce.reduce.memory.mb</name>
        <value>1024</value>
    </property>
    <property>
        <name>mapreduce.reduce.java.opts</name>
        <value>-Xmx512M</value>
    </property>
    <property>
        <name>mapreduce.task.io.sort.mb</name>
        <value>256</value>
    </property>
    <property>
        <name>mapreduce.task.io.sort.factor</name>
        <value>100</value>
    </property>
    <property>
        <name>mapreduce.reduce.shuffle.parallelcopies</name>
        <value>25</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>bigdata1.hadoop.com:10020</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>bigdata1.hadoop.com:19888</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.intermediate-done-dir</name>
        <value>/export/servers/hadoop-3.1.1/datas/jobhsitory/intermediateDoneDatas</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.done-dir</name>
        <value>/export/servers/hadoop-3.1.1/datas/jobhsitory/DoneDatas</value>
    </property>
    <property>
      <name>yarn.app.mapreduce.am.env</name>
      <value>HADOOP_MAPRED_HOME=/export/servers/hadoop-3.1.1</value>
    </property>
    <property>
      <name>mapreduce.map.env</name>
      <value>HADOOP_MAPRED_HOME=/export/servers/hadoop-3.1.1/</value>
    </property>
    <property>
      <name>mapreduce.reduce.env</name>
      <value>HADOOP_MAPRED_HOME=/export/servers/hadoop-3.1.1</value>
    </property>
</configuration>

######yarn-site.xml

<configuration>
    <property>
        <name>dfs.namenode.handler.count</name>
        <value>100</value>
    </property>
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.address</name>
        <value>bigdata1:8032</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>
        <value>bigdata1:8030</value>
    </property>
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>
        <value>bigdata1:8031</value>
    </property>
    <property>
        <name>yarn.resourcemanager.admin.address</name>
        <value>bigdata1:8033</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address</name>
        <value>bigdata1:8088</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>bigdata1</value>
    </property>
    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>
        <value>1024</value>
    </property>
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>2048</value>
    </property>
    <property>
        <name>yarn.nodemanager.vmem-pmem-ratio</name>
        <value>2.1</value>
    </property>
    <!-- 设置不检查虚拟内存的值，不然内存不够会报错 -->
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</value>
    </property>
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>1024</value>
    </property>
    <property>
        <name>yarn.nodemanager.resource.detect-hardware-capabilities</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.nodemanager.local-dirs</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/nodemanager/nodemanagerDatas</value>
    </property>
    <property>
        <name>yarn.nodemanager.log-dirs</name>
        <value>file:///export/servers/hadoop-3.1.1/datas/nodemanager/nodemanagerLogs</value>
    </property>
    <property>
        <name>yarn.nodemanager.log.retain-seconds</name>
        <value>10800</value>
    </property>
    <property>
        <name>yarn.nodemanager.remote-app-log-dir</name>
        <value>/export/servers/hadoop-3.1.1/datas/remoteAppLog/remoteAppLogs</value>
    </property>
<property>
<name>yarn.nodemanager.remote-app-log-dir-suffix</name>
<value>logs</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>18144000</value>
</property>
<property>
<name>yarn.log-aggregation.retain-check-interval-seconds</name>
<value>86400</value>
</property>
<!-- yarn上面运行一个任务，最少需要1.5G内存，虚拟机没有这么大的内存就调小这个值，不然会报错 -->
<property>
        <name>yarn.app.mapreduce.am.resource.mb</name>
        <value>1024</value>
</property>
</configuration>

######worker

bigdata1
bigdata2
bigdata3

3. 创建数据和临时文件夹

mkdir -p /export/servers/hadoop-3.1.1/datas/tmp
mkdir -p /export/servers/hadoop-3.1.1/datas/dfs/nn/snn/edits
mkdir -p /export/servers/hadoop-3.1.1/datas/namenode/namenodedatas
mkdir -p /export/servers/hadoop-3.1.1/datas/datanode/datanodeDatas
mkdir -p /export/servers/hadoop-3.1.1/datas/dfs/nn/edits
mkdir -p /export/servers/hadoop-3.1.1/datas/dfs/snn/name
mkdir -p /export/servers/hadoop-3.1.1/datas/jobhsitory/intermediateDoneDatas
mkdir -p /export/servers/hadoop-3.1.1/datas/jobhsitory/DoneDatas
mkdir -p /export/servers/hadoop-3.1.1/datas/nodemanager/nodemanagerDatas
mkdir -p /export/servers/hadoop-3.1.1/datas/nodemanager/nodemanagerLogs
mkdir -p /export/servers/hadoop-3.1.1/datas/remoteAppLog/remoteAppLogs

4. 分发安装包到其它机器

cd /export/servers
scp -r hadoop-3.1.1/ bigdata2:$PWD
scp -r hadoop-3.1.1/ bigdata3:$PWD

5. 在每个节点配置环境变量

vi /etc/profile

export HADOOP_HOME=/export/servers/hadoop-3.1.1/
export PATH=:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH

6. 格式化HDFS

• 为什么要格式化HDFS

  • HDFS需要一个格式化的过程来创建存放元数据(image, editlog)的目录

bin/hdfs namenode -format

7. 启动集群

# 会登录进所有的worker启动相关进行, 也可以手动进行, 但是没必要
/export/servers/hadoop-3.1.1/sbin/start-dfs.sh
/export/servers/hadoop-3.1.1/sbin/start-yarn.sh
mapred --daemon start historyserver