编辑hadoop配置文档
# hadoop-env.sh
# The java implementation to use.
export JAVA_HOME=/usr/java/jdk1.8
# hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>192.168.88.143:50090</value>
</property>
</configuration>
# core-site.xml (核心文档)
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://192.168.88.142:8020</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/data/hadoop</value>
</property>
<!-- 设置hdfs web ui的用户身份 -->
<property>
<name>hadoop.http.staticuser.user</name>
<value>root</value>
</property>
<!-- 整合hive -->
<property>
<name>hadoop.proxyuser.root.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.root.groups</name>
<value>*</value>
</property>
</configuration>
# yarn-site.xml
<?xml version="1.0"?>
<configuration>
<!-- Site specific YARN configuration properties -->
<!-- 指定YARN的主角色(ResourceManager)的地址 -->
<property>
<name>yarn.resourcemanager.hostname</name>
<value>master</value>
</property>
<!-- NodeManager上运行的附属服务。需配置成mapreduce_shuffle,才可运行MapReduce程序默认值:"" -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<!-- 是否将对容器实施物理内存限制 -->
<property>
<name>yarn.nodemanager.pmem-check-enabled</name>
<value>false</value>
</property>
<!-- 是否将对容器实施虚拟内存限制。 -->
<property>
<name>yarn.nodemanager.vmem-check-enabled</name>
<value>false</value>
</property>
<!-- 开启日志聚集 -->
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<!-- 设置yarn历史服务器地址 -->
<property>
<name>yarn.log.server.url</name>
<value>http://master:19888/jobhistory/logs</value>
</property>
<!-- 保存的时间7天 -->
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>
</configuration>
# 最后编辑slaves
master
slave1
slave2
编辑hive配置文档
# hive-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- jdbc 连接的 URL -->
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://192.168.88.142:3306/hive_db?useSSL=false</value>
</property>
<!-- jdbc 连接的 Driver-->
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.jdbc.Driver</value>
</property>
<!-- jdbc 连接的 username-->
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
</property>
<!-- jdbc 连接的 password -->
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>123</value>
</property>
<!-- Hive 元数据存储版本的验证 -->
<property>
<name>hive.metastore.schema.verification</name>
<value>false</value>
</property>
<!--元数据存储授权-->
<property>
<name>hive.metastore.event.db.notification.api.auth</name>
<value>false</value>
</property>
<!--Hive 默认在 HDFS 的工作目录 -->
<property>
<name>hive.metastore.warehouse.dir</name>
<value>/usr/hive/warehouse</value>
</property>
</configuration>
hive配置完成后记得初始化
# 初始化hive的元数据库
schematool -initSchema -dbType mysql -verbose