数据湖仓一体(五)安装spark

上传安装包到/opt/software目录并解压

[bigdata@node106 software]$ tar -zxvf spark-3.3.1-bin-hadoop3.tgz -C /opt/services/ 

重命名文件

[bigdata@node106 services]$ mv spark-3.3.1-bin-hadoop3 spark-3.3.1 

 配置环境变量

[bigdata@node106 ~]$ sudo vim /etc/profile.d/bigdata_env.sh

export SPARK_HOME=/opt/services/spark-3.3.1
export $PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$ZK_HOME/bin:$KAFKA_HOME/bin:$SEA_HOME/bin:$HIVE_HOME/bin:$SPARK_HOME/bin

分发环境变量

[bigdata@node106 bin]$ sudo ./bin/xsync /etc/profile.d/bigdata_env.sh 

刷新环境变量，5台机器上执行

[bigdata@node106 ~]$ source /etc/profile

配置spark-env.sh

HADOOP_CONF_DIR=/opt/services/hadoop-3.3.5/etc/hadoop
YARN_CONF_DIR=/opt/services/hadoop-3.3.5/etc/hadoop
export SPARK_DIST_CLASSPATH=$(hadoop classpath)
export SPARK_HISTORY_OPTS=" 
-Dspark.history.ui.port=18080  
-Dspark.history.fs.logDirectory=hdfs://mycluster:8020/spark-history  
-Dspark.history.retainedApplications=30"

配置spark-defaults.conf

spark.master                       yarn
spark.eventLog.enabled             true
spark.eventLog.dir                 hdfs://mycluster:8020/spark-history
spark.serializer                   org.apache.spark.serializer.KryoSerializer
spark.yarn.archive               hdfs://mycluster:8020/spark-archive/spark-archive.zip
spark.sql.warehouse.dir       hdfs://mycluster:8020/user/hudi/warehouse
spark.serializer                    org.apache.spark.serializer.KryoSerializer
spark.sql.extensions            org.apache.spark.sql.hudi.HoodieSparkSessionExtension
spark.sql.catalog.spark_catalog              org.apache.spark.sql.hudi.catalog.HoodieCatalog
spark.kryo.registrator                              org.apache.spark.HoodieSparkKryoRegistrar
spark.hadoop.yarn.timeline-service.enabled    false
spark.executor.cores     4
spark.executor.memory 3g
spark.executor.memoryOverhead 1g
spark.driver.memory     2g
spark.driver.memoryOverhead 1g
#启动动态分配
spark.dynamicAllocation.enabled    true
#启用Spark shuffle服务
spark.shuffle.service.enabled    true
#Executor个数初始值
spark.dynamicAllocation.initialExecutors    2
#Executor个数最小值
spark.dynamicAllocation.minExecutors    2
#Executor个数最大值
spark.dynamicAllocation.maxExecutors    4
#Executor空闲时长，若某Executor空闲时间超过此值，则会被关闭
spark.dynamicAllocation.executorIdleTimeout    60s
#积压任务等待时长，若有Task等待时间超过此值，则申请启动新的Executor
spark.dynamicAllocation.schedulerBacklogTimeout    1s
spark.yarn.queue hive 
spark.yarn.historyServer.address=node106:18080
spark.history.ui.port=18080
spark.history.fs.logDirectory=hdfs://mycluster:8020/spark-history

创建日志文件

[bigdata@node106 conf]$ hdfs dfs -mkdir /spark-history

创建运行依赖的文件夹

[bigdata@node106 conf]$ hdfs dfs -mkdir /spark-archive

上传mysql驱动包，hudi依赖的包

[bigdata@node106 software]$ cp mysql-connector-java-8.0.18.jar /opt/services/spark-3.3.1/jars/ 
[bigdata@node106 software]$ cp hudi-spark3.3-bundle_2.12-0.14.1.jar /opt/services/spark-3.3.1/jars/ 

压缩jar包并上传到hdfs

[bigdata@node106 jars]$ zip spark-archive.zip ./* 

[bigdata@node106 jars]$ hdfs dfs -put ./spark-archive.zip /spark-archive

上传spark-3.3.1-yarn-shuffle.jar

[bigdata@node106 conf]$ cp $SPARK_HOME/yarn/spark-3.3.1-yarn-shuffle.jar  /opt/services/hadoop-3.3.5/share/hadoop/yarn/lib/

配置日志文件

[bigdata@node106 conf]$ cp log4j2.properties.template log4j2.properties

上传hive-site.xml到conf目录下，配置hudi存储目录和spark的server2服务

<property>
		<name>hive.metastore.warehouse.dir</name>
		<value>/user/hudi/warehouse</value>
	</property>
	<property>
			<name>hive.server2.thrift.port</name>
			<value>10001</value>
	</property>
	<property>
			<name>hive.server2.thrift.bind.host</name>
			<value>node106</value>
	</property>

编写spark.sh脚本

[bigdata@node106 bin]$ vim spark.sh 

#!/bin/bash

if [ $# -lt 1 ]
then
    echo "No Args Input...[start,stop]"
    exit ;
fi
case $1 in
"start")
        echo ==================== 启动history服务 =========================
        ssh node106 "$SPARK_HOME/sbin/start-history-server.sh"
        echo ==================== 启动server2服务 ====================
        ssh node106 "$SPARK_HOME/sbin/start-thriftserver.sh --master yarn"
;;
"stop")
        echo ==================== 关闭history服务 =========================
        ssh node106 "$SPARK_HOME/sbin/stop-history-server.sh"
        echo ==================== 关闭server2服务 ====================
        ssh node106 "$SPARK_HOME/sbin/stop-thriftserver.sh --master yarn"
;;
*)
    echo "Input Args Error...[start,stop]"
;;
esac

授权

[bigdata@node106 bin]$ chmod +x spark.sh

分发到其他机器

[bigdata@node106 bin]$ xsync  spark.sh 

copy到其他机器

[bigdata@node107 bin]$ scp -r bigdata@node106:/opt/services/spark-3.3.1/ /opt/services/spark-3.3.1/   
[bigdata@node108 bin]$ scp -r bigdata@node106:/opt/services/spark-3.3.1/ /opt/services/spark-3.3.1/

启动spark

[bigdata@node106 bin]$ spark.sh start