一 部署Spark客户端

1.1 部署spark3客户端

tar -zxvf spark-3.3.1-bin-3.0.0-cdh6.3.2.tgz -C /opt/cloudera/parcels/CDH/lib
cd /opt/cloudera/parcels/CDH/lib
mv spark-3.3.1-bin-3.0.0-cdh6.3.2/ spark3

将 CDH 集群的 spark-env.sh 复制到 /opt/cloudera/parcels/CDH/lib/spark3/conf 下:

cp /etc/spark/conf/spark-env.sh  /opt/cloudera/parcels/CDH/lib/spark3/conf
chmod +x /opt/cloudera/parcels/CDH/lib/spark3/conf/spark-env.sh#修改 spark-env.sh
vim /opt/cloudera/parcels/CDH/lib/spark3/conf/spark-env.shexport SPARK_HOME=/opt/cloudera/parcels/CDH/lib/spark3
HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-/etc/hadoop/conf}

将 gateway 节点的 hive-site.xml 复制到 spark3/conf 目录下，不需要做变动:

cp /etc/hive/conf/hive-site.xml /opt/cloudera/parcels/CDH/lib/spark3/conf/

1.2 部署Spark2客户端

tar -zxvf spark-2.4.0-bin-hadoop2.7.tgz -C /opt/cloudera/parcels/CDH/lib
cd /opt/cloudera/parcels/CDH/lib
mv spark-2.4.0-bin-hadoop2.7/ spark2

将 CDH 集群的 spark-env.sh 复制到 /opt/cloudera/parcels/CDH/lib/spark2/conf 下:

cp /etc/spark/conf/spark-env.sh  /opt/cloudera/parcels/CDH/lib/spark2/conf
chmod +x /opt/cloudera/parcels/CDH/lib/spark2/conf/spark-env.sh#修改 spark-env.sh
vim /opt/cloudera/parcels/CDH/lib/spark2/conf/spark-env.shexport SPARK_HOME=/opt/cloudera/parcels/CDH/lib/spark2
HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-/etc/hadoop/conf}

将 gateway 节点的 hive-site.xml 复制到 spark2/conf 目录下，不需要做变动:

cp /etc/hive/conf/hive-site.xml /opt/cloudera/parcels/CDH/lib/spark2/conf/

二 创建spark-sql

2.1 spark3

vim /opt/cloudera/parcels/CDH/bin/spark3-sql#!/bin/bash 
export HADOOP_CONF_DIR=/etc/hadoop/conf
export YARN_CONF_DIR=/etc/hadoop/conf
SOURCE="${BASH_SOURCE[0]}"  
BIN_DIR="$( dirname "$SOURCE" )"  
while [ -h "$SOURCE" ]  
do  SOURCE="$(readlink "$SOURCE")"  [[ $SOURCE != /* ]] && SOURCE="$BIN_DIR/$SOURCE"  BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"  
done  
BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"  
LIB_DIR=$BIN_DIR/../lib  
export HADOOP_HOME=$LIB_DIR/hadoop  # Autodetect JAVA_HOME if not defined  
. $LIB_DIR/bigtop-utils/bigtop-detect-javahome  exec $LIB_DIR/spark3/bin/spark-submit --class org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver "$@"

配置 spark-sql 快捷方式

chmod +x /opt/cloudera/parcels/CDH/bin/spark3-sql
alternatives --install /usr/bin/spark-sql spark-sql /opt/cloudera/parcels/CDH/bin/spark3-sql 1

2.2 spark2

vim /opt/cloudera/parcels/CDH/bin/spark2-sql#!/bin/bash 
export HADOOP_CONF_DIR=/etc/hadoop/conf
export YARN_CONF_DIR=/etc/hadoop/conf
SOURCE="${BASH_SOURCE[0]}"  
BIN_DIR="$( dirname "$SOURCE" )"  
while [ -h "$SOURCE" ]  
do  SOURCE="$(readlink "$SOURCE")"  [[ $SOURCE != /* ]] && SOURCE="$BIN_DIR/$SOURCE"  BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"  
done  
BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"  
LIB_DIR=$BIN_DIR/../lib  
export HADOOP_HOME=$LIB_DIR/hadoop  # Autodetect JAVA_HOME if not defined  
. $LIB_DIR/bigtop-utils/bigtop-detect-javahome  exec $LIB_DIR/spark2/bin/spark-submit --class org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver "$@"

配置 spark-sql 快捷方式

chmod +x /opt/cloudera/parcels/CDH/bin/spark2-sql
alternatives --install /usr/bin/spark-sql spark-sql /opt/cloudera/parcels/CDH/bin/spark2-sql 2

三 配置conf

3.1 spark3

cd /opt/cloudera/parcels/CDH/lib/spark3/conf
## 开启日志
mv log4j2.properties.template log4j2.properties
## spark-defaults.conf 配置
cp /opt/cloudera/parcels/CDH/lib/spark/conf/spark-defaults.conf ./# 修改 spark-defaults.conf
vim /opt/cloudera/parcels/CDH/lib/spark3/conf/spark-defaults.conf
删除 spark.extraListeners、spark.sql.queryExecutionListeners、spark.yarn.jars
添加 spark.yarn.jars=hdfs:///spark/3versionJars/*hadoop fs -mkdir -p /spark/3versionJars
cd /opt/cloudera/parcels/CDH/lib/spark3/jars
hadoop fs -put *.jar /spark/3versionJars

3.2 spark2

cd /opt/cloudera/parcels/CDH/lib/spark2/conf
## 开启日志
mv log4j2.properties.template log4j2.properties
## spark-defaults.conf 配置
cp /opt/cloudera/parcels/CDH/lib/spark/conf/spark-defaults.conf ./# 修改 spark-defaults.conf
vim /opt/cloudera/parcels/CDH/lib/spark3/conf/spark-defaults.conf
删除 spark.extraListeners、spark.sql.queryExecutionListeners、spark.yarn.jars
添加 spark.yarn.jars=hdfs:///spark/2versionJars/*hadoop fs -mkdir -p /spark/2versionJars
cd /opt/cloudera/parcels/CDH/lib/spark2/jars
hadoop fs -put *.jar /spark/2versionJars

四 创建spark-submit

4.1 spark3

vim /opt/cloudera/parcels/CDH/bin/spark3-submit#!/usr/bin/env bash
export HADOOP_CONF_DIR=/etc/hadoop/conf
export YARN_CONF_DIR=/etc/hadoop/conf
SOURCE="${BASH_SOURCE[0]}"
BIN_DIR="$( dirname "$SOURCE" )"
while [ -h "$SOURCE" ]
doSOURCE="$(readlink "$SOURCE")"[[ $SOURCE != /* ]] && SOURCE="$BIN_DIR/$SOURCE"BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
done
BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
LIB_DIR=/opt/cloudera/parcels/CDH/lib
export HADOOP_HOME=$LIB_DIR/hadoop# Autodetect JAVA_HOME if not defined
. $LIB_DIR/bigtop-utils/bigtop-detect-javahome# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0exec $LIB_DIR/spark3/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

配置 spark3-submit 快捷方式:

chmod +755 /opt/cloudera/parcels/CDH/bin/spark3-submit
alternatives --install /usr/bin/spark-submit spark-submit /opt/cloudera/parcels/CDH/bin/spark3-submit 1

4.2 spark2

vim /opt/cloudera/parcels/CDH/bin/spark2-submit#!/usr/bin/env bash
export HADOOP_CONF_DIR=/etc/hadoop/conf
export YARN_CONF_DIR=/etc/hadoop/conf
SOURCE="${BASH_SOURCE[0]}"
BIN_DIR="$( dirname "$SOURCE" )"
while [ -h "$SOURCE" ]
doSOURCE="$(readlink "$SOURCE")"[[ $SOURCE != /* ]] && SOURCE="$BIN_DIR/$SOURCE"BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
done
BIN_DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
LIB_DIR=/opt/cloudera/parcels/CDH/lib
export HADOOP_HOME=$LIB_DIR/hadoop# Autodetect JAVA_HOME if not defined
. $LIB_DIR/bigtop-utils/bigtop-detect-javahome# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0exec $LIB_DIR/spark2/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

配置 spark2-submit 快捷方式:

chmod +755 /opt/cloudera/parcels/CDH/bin/spark2-submit
alternatives --install /usr/bin/spark-submit spark-submit /opt/cloudera/parcels/CDH/bin/spark2-submit 1

---