配置spark

Yarn 模式

tar -zxvf spark-3.0.0-bin-hadoop3.2.tgz -C /opt/module
cd /opt/module 
mv spark-3.0.0-bin-hadoop3.2 spark-yarn

修改 hadoop 配置文件/opt/module/hadoop/etc/hadoop/yarn-site.xml, 并分发

<!--是否启动一个线程检查每个任务正使用的物理内存量，如果任务超出分配值，则直接将其杀掉，默认
是 true -->
    <property>
        <name>yarn.nodemanager.pmem-check-enabled</name>
        <value>false</value>
    </property>
    <!--是否启动一个线程检查每个任务正使用的虚拟内存量，如果任务超出分配值，则直接将其杀掉，默认
是 true -->
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</value>
    </property>

cd /opt/module/
xsync hadoop-3.1.3

修改 conf/spark-env.sh，添加 JAVA_HOME 和 YARN_CONF_DIR 配置

export JAVA_HOME=/opt/module/jdk1.8.0_212
YARN_CONF_DIR=/opt/module/hadoop-3.1.3/etc/hadoop

bin/spark-submit \
--class org.apache.spark.examples.SparkPi \
--master yarn \
--deploy-mode cluster \
./examples/jars/spark-examples_2.12-3.0.0.jar \
10

http://hadoop103:8088/cluster

配置历史服务器
mv spark-defaults.conf.template spark-defaults.conf
修改 spark-default.conf 文件，配置日志存储路径

spark.eventLog.enabled true
spark.eventLog.dir hdfs://hadoop102:8020/directory

[root@linux1 hadoop]# sbin/start-dfs.sh
[root@linux1 hadoop]# hadoop fs -mkdir /directory
修改 spark-env.sh 文件, 添加日志配置

export SPARK_HISTORY_OPTS="
-Dspark.history.ui.port=18080 
-Dspark.history.fs.logDirectory=hdfs://hadoop102:8020/directory 
-Dspark.history.retainedApplications=30"

修改 spark-defaults.conf

spark.yarn.historyServer.address=hadoop102:18080
spark.history.ui.port=18080

启动历史服务

sbin/start-history-server.sh 

重新提交应用

bin/spark-submit \
--class org.apache.spark.examples.SparkPi \
--master yarn \
--deploy-mode client \
./examples/jars/spark-examples_2.12-3.0.0.jar \
10

http://hadoop103:8088/cluster

Standalone 模式

tar -zxvf spark-3.0.0-bin-hadoop3.2.tgz -C /opt/module
cd /opt/module 
mv spark-3.0.0-bin-hadoop3.2 spark-standalone

mv slaves.template slaves

linux1
linux2
linux3

mv spark-env.sh.template spark-env.sh

export JAVA_HOME=/opt/module/jdk1.8.0_212
SPARK_MASTER_HOST=hadoop102
SPARK_MASTER_PORT=7077

xsync spark-standalone

sbin/start-all.sh

配置历史服务

mv spark-defaults.conf.template spark-defaults.conf

//修改 spark-default.conf 文件，配置日志存储路径
spark.eventLog.enabled true
spark.eventLog.dir hdfs://hadoop102:8020/directory

sbin/start-dfs.sh
hadoop fs -mkdir /directory

//修改 spark-env.sh 文件, 添加日志配置
export SPARK_HISTORY_OPTS="
-Dspark.history.ui.port=18080 
-Dspark.history.fs.logDirectory=hdfs://hadoop102:8020/directory 
-Dspark.history.retainedApplications=30"

xsync conf

sbin/start-all.sh
sbin/start-history-server.sh

配置高可用
？先配置zookeeper

sbin/stop-all.sh

Local 模式

上传安装包

sudo mv spark-3.0.0-bin-hadoop3.2.tgz /opt/software/
tar -zxvf spark-3.0.0-bin-hadoop3.2.tgz -C /opt/module
cd /opt/module 
mv spark-3.0.0-bin-hadoop3.2 spark-local