spark-sql on hive配置 thriftserver

版本

spark-2.1.3-bin-hadoop2.7

hive-site.xml

<configuration>
        <property>
                <name>javax.jdo.option.ConnectionURL</name>
                <value>jdbc:mysql://bigdata02:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false</value>
        </property>
        <property>
                <name>javax.jdo.option.ConnectionDriverName</name>
                <value>com.mysql.jdbc.Driver</value>
        </property>
        <property>
                <name>javax.jdo.option.ConnectionUserName</name>
                <value>root</value>
        </property>
        <property>
                <name>javax.jdo.option.ConnectionPassword</name>
                <value>123456</value>
        </property>


        <property>
                <name>hive.insert.into.multilevel.dirs</name>
                <value>true</value>
                <description>允许生成多级目录</description>
        </property>

        <property>
                <name>hive.exec.stagingdir</name>
                <value>/home/tools/spark/spark-2.1.3-bin-hadoop2.7/hive_tmp</value>
                <description>临时文件暂放目录</description>
        </property>

        <property>
                <name>hive.metastore.warehouse.dir</name>
                <value>hdfs://bigdata02:9000/user/hive/warehouse</value>
        </property>
        <property>
                <name>fs.defaultFS</name>
                <value>hdfs://bigdata02:9000</value>
        </property>

        <property>
                <name>hive.server2.thrift.bind.host</name>
                <value>bigdata01</value>
                <description>ip配置</description>
        </property>

        <property>
                <name>hive.server2.thrift.port</name>
                <value>10001</value>
                <description>端口配置</description>
        </property>
</configuration>

spark-defaults.conf

spark.yarn.jars hdfs://mini:9000/home/hadoop/spark_jars/*
spark.sql.adaptive.enabled true

spark-env.sh

export JAVA_HOME=/usr/local/jdk/jdk1.8.0_251
export HADOOP_HOME=/home/tools/hadoop/hadoop-2.7.3
export HADOOP_CONF_DIR=/home/tools/hadoop/hadoop-2.7.3/etc/hadoop
export YARN_CONF_DIR=/home/tools/hadoop/hadoop-2.7.3/etc/hadoop
export SPARK_HOME=/home/tools/spark/spark-2.1.3-bin-hadoop2.7

//将hadoop的配置文件放在spark_home/conf 目录下

将spark目录下的lib包上传到配置文件指定的目录 hdfs://bigdata01:9000/home/hadoop/spark_jars/*

启动

./spark-sql \
--master yarn-client \   #使用yarn集群启动
--num-executors 3 \      #配置执行者数量
--executor-memory 3G \   #配置每一个执行者的内存
--executor-cores 3       #配置每一个执行者的cpu核心数

使用thriftserver服务启动

spark_home/sbin/start-thriftserver.sh \
--master yarn \
--num-executors 3 \
--executor-memory 3G \
--executor-cores 3

连接sparksql

 spark_home/bin/beeline -u jdbc:hive2://bigdata01:10001/

创建表并导入数据

create table data_table(id int,group1 string,group2 string,value1 int,value2 int,value3 int,date string) row format delimited fields terminated by ',' stored as textfile

load data inpath 'hdfs://bigdata01:9000/tempdata/sparksql' into table data_table

进行数据查询