大数据集群搭建之Linux安装Hive2.3.2

cd /usr/local/hadoop
tar zxpf apache-hive-2.3.2-bin.tar.gz

ln -s /usr/local/hadoop/apache-hive-2.3.2-bin /usr/local/hadoop/hive

vim /etc/profile

export HIVE_HOME=/usr/local/hadoop/hive
export PATH=$PATH:$HIVE_HOME/bin

source /etc/profile

cd $HIVE_HOME/conf
touch hive-env.sh hive-site.xml
chmod +x hive-env.sh

export HADOOP_HEAPSIZE=4096
export JAVA_HOME=/usr/java/jdk1.8
export HADOOP_HOME=/usr/local/hadoop/hadoop
export HIVE_HOME=/usr/local/hadoop/hive
export HIVE_CONF_DIR=/usr/local/hadoop/hive/conf
export HBASE_HOME=/usr/local/hadoop/hbase
export SPARK_HOME=/usr/local/hadoop/spark
export ZOO_HOME=/usr/local/hadoop/zookeeper

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>

  <!-- Hive数据库在HDFS上的数据存储路径 -->
  <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/user/hive/warehouse</value>
    <description>location of default database for the warehouse</description>
  </property>

  <!-- Hive临时文件，用于存储每个查询的临时/中间数据集，通常在完成查询后由配置单元客户端清除 -->
  <property>
    <name>hive.exec.local.scratchdir</name>
    <value>/usr/local/hadoop/hive/tmp</value>
    <description>Local scratch space for Hive jobs</description>
  </property>
 
  <!-- Hive添加资源时的临时目录 -->
  <property>
    <name>hive.downloaded.resources.dir</name>
    <value>/usr/local/hadoop/hive/tmp/resources</value>
    <description>Temporary local directory for added resources in the remote file system.</description>
  </property>
 
  <!-- Hive运行时结构化日志文件的位置 -->
  <property>
    <name>hive.querylog.location</name>
    <value>/user/hadoop/hive/logs</value>
    <description>Location of Hive run time structured log file</description>
  </property>
 
  <!-- 用于验证metastore和hivejar包是否一致问题，默认为true。false：hive升级版本不一致只会警告 -->
  <property>
    <name>hive.metastore.schema.verification</name>
    <value>false</value>
	<description>
      Enforce metastore schema version consistency.
      True: Verify that version information stored in is compatible with one from Hive jars.  Also disable automatic
            schema migration attempt. Users are required to manually migrate schema after Hive upgrade which ensures
            proper metastore schema migration. (Default)
      False: Warn if the version information stored in metastore doesn't match with one from in Hive jars.
    </description>
  </property>

  <!-- 使用MySQL作为hive的元数据Metastore数据库 -->
  <property>
    <name>hive.metastore.db.type</name>
    <value>mysql</value>
    <description>
      Expects one of [derby, oracle, mysql, mssql, postgres].
      Type of database used by the metastore. Information schema &amp; JDBCStorageHandler depend on it.
    </description>
  </property>
 
  <!-- 使用MySQL作为hive的元数据Metastore数据库 -->
  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://hadoop001:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false</value>
  </property>
 
  <!-- MySQL JDBC驱动程序类 -->
  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
	<description>Driver class name for a JDBC metastore</description>
  </property>
 
  <!-- 连接到MySQL服务器的用户名 -->
  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>hive</value>
	<description>Username to use against metastore database</description>
  </property>
 
  <!-- 连接MySQL服务器的密码 -->
  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>hive</value>
	<description>Comma separated list of configuration options which should not be read by normal user like passwords</description>
  </property>

  <!-- 初始化Hive数据库自动创建schema -->
  <property>
    <name>datanucleus.schema.autoCreateAll</name>
    <value>true</value>
  <description>Auto creates necessary schema on a startup if one doesn't exist. Set this to false, after creating it once.To enable auto create also set hive.metastore.schema.verification=false. Auto creation is not recommended for production use cases, run schematool command instead.</description>
 </property>
 
  <!-- Hive server2 thrift 主机 -->
  <property>
    <name>hive.server2.thrift.bind.host</name>
    <value>hadoop001</value>
    <description>Bind host on which to run the HiveServer2 Thrift service.</description>
  </property>
 
  <!-- Hive server2 thrift 端口 -->
  <property>
    <name>hive.server2.thrift.port</name>
    <value>10000</value>
	<description>Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'binary'.</description>
  </property>
 
  <!-- Thrift Metastore服务器的主机和端口 默认 <value/> -->
  <property>
    <name>hive.metastore.uris</name>
    <!-- <value>thrift://hadoop001:9083</value> -->
	<description>Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore.</description>
  </property>
 
  <!-- 如果启用了日志功能，则存储操作日志的顶级目录 -->
  <property>
    <name>hive.server2.logging.operation.log.location</name>
    <value>/usr/local/hadoop/hive/tmp/operation_logs</value>
    <description>Top level directory where operation logs are stored if logging functionality is enabled</description>
  </property>

  <!-- HiveServer2 webUI 监听主机 -->
  <property>
    <name>hive.server2.webui.host</name>
    <value>hadoop001</value>
    <!-- <value>0.0.0.0</value> -->
    <description>The host address the HiveServer2 WebUI will listen on</description>
  </property>
  
  <!-- HiveServer2 webUI 监听端口 -->
  <property>
    <name>hive.server2.webui.port</name>
    <value>10002</value>
    <description>The port the HiveServer2 WebUI will listen on. This can beset to 0 or a negative integer to disable the web UI</description>
  </property>

  <!-- HiveServer2 webUI 最大线程数 -->
  <property>
    <name>hive.server2.webui.max.threads</name>
    <value>50</value>
    <description>The max HiveServer2 WebUI threads</description>
  </property>

  <!-- HiveServer2 webUI SSL验证 -->
  <property>
    <name>hive.server2.webui.use.ssl</name>
    <value>false</value>
    <description>Set this to true for using SSL encryption for HiveServer2 WebUI.</description>
  </property>

  <!-- HiveServer2 账户 -->
  <property>
    <name>hive.server2.thrift.client.user</name>
    <value>root</value>
    <description>Username to use against thrift client</description>
  </property>

  <!-- HiveServer2 密码 -->
  <property>
    <name>hive.server2.thrift.client.password</name>
    <value>root</value>
    <description>Password to use against thrift client</description>
  </property>

 </configuration> 

cd $HIVE_HOME/lib

wget https://repo1.maven.org/maven2/mysql/mysql-connector-java/5.1.47/mysql-connector-java-5.1.47.jar

wget https://repo1.maven.org/maven2/mysql/mysql-connector-java/8.0.16/mysql-connector-java-8.0.16.jar

-- 创建hive用户，密码为hive
CREATE USER 'hive'@'%' IDENTIFIED BY 'hive';
-- 赋予hive用户全部权限
GRANT ALL PRIVILEGES ON *.* TO 'hive'@'%' IDENTIFIED BY 'hive' WITH GRANT OPTION;
-- 刷新权限
FLUSH PRIVILEGES;

zkServer.sh start

hdfs --daemon start zkfc

start-all.sh

hadoop fs -mkdir       /tmp
hadoop fs -mkdir       /user/hive/warehouse
hadoop fs -chmod g+w   /tmp
hadoop fs -chmod g+w   /user/hive/warehouse

schematool -dbType mysql -initSchema

hive

SHOW DATABASES;
CREATE DATABASE db01;
USE db01;
set hive.cli.print.current.db=true;
CREATE TABLE pokes (foo INT, bar STRING);
CREATE TABLE invites (foo INT, bar STRING) PARTITIONED BY (ds STRING);
SHOW TABLES;
SHOW TABLES '.*s';
DESCRIBE invites;

nohup hiveserver2 > /dev/null 2>&1 &

tail -n 300 /tmp/root/hive.log

beeline

!connect jdbc:hive2://hadoop001:10000

SHOW DATABASES;
SHOW TABLES;
SELECT * FROM sqoop_user;
!quit

import java.sql.SQLException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;
import java.sql.DriverManager;
 
public class TestHiveQuery {
  private static final String driverName = "org.apache.hive.jdbc.HiveDriver";
 
  public static void main(String[] args) throws SQLException {
    try {
      Class.forName(driverName);
    } catch (ClassNotFoundException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
      System.exit(1);
    }
    Connection con = DriverManager.getConnection("jdbc:hive2://node3:10000/default", "hive", "hive");
    Statement stmt = con.createStatement();
    String tableName = "default.emp";
    
 
    // select * query
    String sql = "select * from " + tableName;
    System.out.println("Running: " + sql);
    ResultSet res = stmt.executeQuery(sql);
    while (res.next()) {
      System.out.println(String.valueOf(res.getInt(1)) + "\t" + res.getString(2));
    }
  }
}