hive on spark亲自编译，详细教程

news2024/11/27 1:31:18

hive on spark 进行编译操作

软件

hive 2.3.6

spark 2.0.0版本

hadoop-2.7.6版本

操作流程：

hadoop-2.7.6

1、安装hadoop不说了。简单。

spark-2.0.0

2、下载spark-2.0.0的源码. https://archive.apache.org/dist/spark/spark-2.1.0/ 这个下载spark各个版本。

3、编译spark源码

[root@master local]# tar -zxvf spark-2.0.0.tgz
[root@master local]# vim ./spark-2.0.0/dev/make-distribution.sh
# 在该文件中找到以下内容删除
VERSION=$("$MVN" help:evaluate -Dexpression=project.version $@ 2>/dev/null | grep -v "INFO" | tail -n 1)
SCALA_VERSION=$("$MVN" help:evaluate -Dexpression=scala.binary.version $@ 2>/dev/null\
    | grep -v "INFO"\
    | tail -n 1)
SPARK_HADOOP_VERSION=$("$MVN" help:evaluate -Dexpression=hadoop.version $@ 2>/dev/null\
    | grep -v "INFO"\
    | tail -n 1)
SPARK_HIVE=$("$MVN" help:evaluate -Dexpression=project.activeProfiles -pl sql/hive $@ 2>/dev/null\
    | grep -v "INFO"\
    | fgrep --count "<id>hive</id>";\
    # Reset exit status to 0, otherwise the script stops here if the last grep finds nothing\
    # because we use "set -o pipefail"
echo -n)
#删除完成后修改为
VERSION=2.0.0  
SCALA_VERSION=2.11
SPARK_HADOOP_VERSION=2.7.7

执行编译操作:

编译spark
./dev/make-distribution.sh --name "hadoop2-without-hive" --tgz "-Pyarn,hadoop-provided,hadoop-2.7,parquet-provided"

在这里插入图片描述

当前目录下面会多一个tgz的安装包。需要把这个文件拷贝的机器的安装目录下面，解压配置安装。

[root@master local]# cd ./spark/conf/
[root@master conf]# cp spark-env.sh.template spark-env.sh
[root@master conf]# vim spark-env.sh
#将以下配置添加到spark-env.sh文件中
export JAVA_HOME=/usr/java/jdk1.8.0_144
export SCALA_HOME=/usr/local/scala
export HADOOP_HOME=/usr/local/hadoop
export HADOOP_CONF_DIR=/usr/local/hadoop/etc/hadoop
export HADOOP_YARN_CONF_DIR=/usr/local/hadoop/etc/hadoop
export SPARK_HOME=/usr/local/spark
export SPARK_WORKER_MEMORY=512m
export SPARK_EXECUTOR_MEMORY=512m
export SPARK_DRIVER_MEMORY=512m
export SPARK_DIST_CLASSPATH=$(/usr/local/hadoop/bin/hadoop classpath)

安装hive

[root@master local]# tar -zxvf apache-hive-2.3.7-bin.tar.gz
[root@master local]# mv apache-hive-2.3.7-bin hive
[root@master local]# vim /usr/local/hive/conf/hive-site.xml
#在文件中添加以下配置
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
  <property>
     <!-- 查询数据时 显示出列的名字 -->
     <name>hive.cli.print.header</name>
     <value>true</value>
  </property>
  <property>
     <!-- 在命令行中显示当前所使用的数据库 -->
     <name>hive.cli.print.current.db</name>
     <value>true</value>
  </property>
  <property>
     <!-- 默认数据仓库存储的位置，该位置为HDFS上的路径 -->
     <name>hive.metastore.warehouse.dir</name>
     <value>/user/hive/warehouse</value>
  </property>
  <!-- 5.x -->
  <property>
     <name>javax.jdo.option.ConnectionURL</name>
     <value>jdbc:mysql://localhost:3306/hive_metastore?createDatabaseIfNotExist=true</value>
  </property>
  <!-- 5.x -->
  <property>
     <name>javax.jdo.option.ConnectionDriverName</name>
     <value>com.mysql.jdbc.Driver</value>
  </property>
  <property>
   <!-- MySQL密码 -->
     <name>javax.jdo.option.ConnectionUserName</name>
     <value>root</value>
  </property>
  <property>
   <!-- 设置mysql密码 -->
     <name>javax.jdo.option.ConnectionPassword</name>
     <value>123456</value>
  </property>
 <property>
  <!-- 设置引擎为Spark-->
    <name>hive.execution.engine</name>
    <value>spark</value>
  </property>
  <property>
    <name>hive.enable.spark.execution.engine</name>
    <value>true</value>
  </property>
  <property>
    <name>spark.home</name>
    <value>/usr/local/spark</value>
  </property>
  <property>
    <name>spark.master</name>
    <value>yarn</value>
  </property>
  <property>
    <name>spark.eventLog.enabled</name>
    <value>true</value>
  </property>
  <property>
   <!-- Hive的日志存储目录，HDFS -->
    <name>spark.eventLog.dir</name>
    <value>hdfs://master:9000/spark-hive-jobhistory</value>
  </property>
  <property>
    <name>spark.executor.memory</name>
    <value>512m</value>
  </property>
  <property>
    <name>spark.driver.memory</name>
    <value>512m</value>
  </property>
  <property>
    <name>spark.serializer</name>
    <value>org.apache.spark.serializer.KryoSerializer</value>
  </property>
  <property>
   <!-- HDFS中jar包的存储路径 -->
    <name>spark.yarn.jars</name>
    <value>hdfs://master:9000/spark-jars/*</value>
  </property>
  <property>
    <name>hive.spark.client.server.connect.timeout</name>
    <value>300000</value>
</configuration>