Hadoop部署配置
阿新 • • 發佈:2021-01-20
上傳並解壓壓縮包
Hadoop配置
配置的檔案目錄是hadoop安裝目錄下的etc/bin/hadoop
core-site.xml
<configuration> <!-- 臨時檔案儲存目錄 --> <property> <name>hadoop.tmp.dir</name> <value>自己指定</value> </property> <!-- namenode指定,指定檔案系統型別:分散式檔案系統 --> <property> <name>fs.default.name</name> <value>hdfs://192.168.2.135:9000</value> </property> <!-- 緩衝區大小 --> <property> <name>io.file.buffer.size</name> <value>4096</value> </property> <!-- 開啟hdfs垃圾桶機制,單位分鐘 --> <property> <name>fs.trash.interval</name> <value>10080</value> </property> </configuration>
hdfs-site.xml
<configuration> <!-- 指定 Hadoop 輔助名稱節點主機配置--> <property> <name>dfs.namenode.secondary.http-address</name> <value>node01:50090</value> </property> <!-- 指定namenode訪問位置--> <property> <name>dfs.namenode.http-address</name> <value>node01:50070</value> </property> <!-- 配置 HDFS 的備份檔案數量, 預設數量是3 --> <property> <name>dfs.replication</name> <value>3</value> </property> <!-- 指定datanode資料的存放位置--> <property> <name>dfs.datanode.data.dir</name> <value>file:///export/servers/hadoop-2.7.5/hadoopDatas/datanodeDatas, file:///export/servers/hadoop-2.7.5/hadoopDatas/datanodeDatas2</value> </property> <!-- 指定namenode元資料存放位置,元資料是資料的目錄--> <property> <name>dfs.namenode.name.dir</name> <value>file:///export/servers/hadoop-2.7.5/hadoopDatas/namenodeDatas, file:///export/servers/hadoop-2.7.5/hadoopDatas/namenodeDatas2</value> </property> <property> <name>dfs.namenode.edits.dir</name> <value>file:///export/servers/hadoop-2.7.5/hadoopDatas/nn/edits</value> </property> <property> <name>dfs.namenode.checkpoint.dir</name> <value>file:///export/servers/hadoop-2.7.5/hadoopDatas/snn/name</value> </property> <property> <name>dfs.namenode.checkpoint.edits.dir</name> <value>file:///export/servers/hadoop-2.7.5/hadoopDatas/dfs/snn/edits</value> </property> <property> <name>dfs.permissions</name> <value>false</value> </property> <property> <name>dfs.blocksize</name> <value>34217728</value> </property> </configuration>
hadoop-env.sh(jdk配置)
export JAVA_HOME=/export/servers/jdk1.8.0_271/
mapred-site.xml
<configuration> <!-- 開啟MapReduce小任務模式 --> <property> <name>mapreduce.job.ubertask.enable</name> <value>true</value> </property> <!-- 設定歷史任務主機和埠 --> <property> <name>mapreduce.jobhistory.address</name> <value>node01:10020</value> </property> <!-- 設定網頁訪問歷史任務的主機和埠 --> <property> <name>mapreduce.jobhistory.webapp.address</name> <value>node01:19888</value> </property> </configuration>
yarn-site.xml
<configuration>
<!-- Site specific YARN configuration properties -->
<!-- 指定yarn執行的主節點 -->
<property>
<name>yarn.resourcemanager.hostname</name>
<value>node01</value>
</property>
<!-- 指定yarn執行的主機 -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<!-- 開啟日誌聚合功能 -->
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<!-- 聚合日誌儲存時間 -->
<property>
<name>yarn.resourcemanager.retain-seconds</name>
<value>604800</value>
</property>
<!-- 設定yarn叢集的記憶體分配方案 -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>20480</value>
</property>
<property>
<name>yarn.scheduler.minimunm-allocation-mb</name>
<value>2048</value>
</property>
<property>
<name>yarn.nodemanager.vmem-pmem-ratio</name>
<value>2.1</value>
</property>
</configuration>
mapred-env.sh
export JAVA_HOME=/export/servers/jdk1.8.0_271/
slaves
#從節點配置
node01
node02
node03
配置hadoop環境變數
#hadoop環境變數
export HADOOP_HOME=/export/servers/hadoop-2.7.5
export PATH=:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH