这里给大家安排一下Hadoop集群四大配置文件,如何做到优化最高,一起来看看楼主的总结:
1.core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- 指定NameNode的地址 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop102:8020</value>
</property>
<!-- 指定hadoop数据的存储目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/module/hadoop-3.1.3/data</value>
</property>
<!-- 配置HDFS网页登录使用的静态用户为atguigu -->
<property>
<name>hadoop.http.staticuser.user</name>
<value>atguigu</value>
</property>
<!-- 配置该atguigu(superUser)允许通过代理访问的主机节点 -->
<property>
<name>hadoop.proxyuser.atguigu.hosts</name>
<value>*</value>
</property>
<!-- 配置该atguigu(superUser)允许通过代理用户所属组 -->
<property>
<name>hadoop.proxyuser.atguigu.groups</name>
<value>*</value>
</property>
<!-- 配置该atguigu(superUser)允许通过代理的用户-->
<property>
<name>hadoop.proxyuser.atguigu.groups</name>
<value>*</value>
</property>
<!-- 增加配置支持LZO压缩 -->
<property>
<name>io.compression.codecs</name>
<value>
org.apache.hadoop.io.compress.GzipCodec,
org.apache.hadoop.io.compress.DefaultCodec,
org.apache.hadoop.io.compress.BZip2Codec,
org.apache.hadoop.io.compress.SnappyCodec,
com.hadoop.compression.lzo.LzoCodec,
com.hadoop.compression.lzo.LzopCodec
</value>
</property>
<property>
<name>io.compression.codec.lzo.class</name>
<value>com.hadoop.compression.lzo.LzoCodec</value>
</property>
</configuration>
2.hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- nn web端访问地址-->
<property>
<name>dfs.namenode.http-address</name>
<value>hadoop102:9870</value>
</property>
<!-- 2nn web端访问地址-->
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop104:9868</value>
</property>
</configuration>
3.yarn-site.xml
<?xml version="1.0"?>
<configuration>
<!-- Site specific YARN configuration properties -->
<!-- 指定MR走shuffle -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<!-- 指定ResourceManager的地址-->
<property>
<name>yarn.resourcemanager.hostname</name>
<value>hadoop103</value>
</property>
<!-- 环境变量的继承 -->
<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_MAPRED_HOME</value>
</property>
<!-- yarn容器允许分配的最大最小内存 -->
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>512</value>
</property>
<property>
<name>yarn.scheduler.maximum-allocation-mb</name>
<value>4096</value>
</property>
<!-- yarn容器允许管理的物理内存大小 -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>4096</value>
</property>
<!-- 关闭yarn对物理内存和虚拟内存的限制检查 -->
<property>
<name>yarn.nodemanager.pmem-check-enabled</name>
<value>false</value>
</property>
<property>
<name>yarn.nodemanager.vmem-check-enabled</name>
<value>false</value>
</property>
<!-- 开启日志聚集功能 -->
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<!-- 设置日志聚集服务器地址 -->
<property>
<name>yarn.log.server.url</name>
<value>http://hadoop102:19888/jobhistory/logs</value>
</property>
<!-- 设置日志保留时间为7天 -->
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>
</configuration>
4.mapred-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- 指定MapReduce程序运行在Yarn上 -->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<!-- 历史服务器端地址 -->
<property>
<name>mapreduce.jobhistory.address</name>
<value>hadoop102:10020</value>
</property>
<!-- 历史服务器web端地址 -->
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>hadoop102:19888</value>
</property>
</configuration>
如有更多需求,可以去官网hadoop.apache.org查看默认配置文件,在进行相应的修改!!!