虚拟机中Spark运行在Yarn上

初始化Centos7
vi /etc/sysconfig/network-scripts/ifcfg-ens33

DEVICE=ens33
TYPE=Ethernet
ONBOOT=yes
NM_CONTROLLED=yes
BOOTPROTO=static
IPADDR=192.168.3.131
GATEWAY=192.168.3.2
NETMASK=255.255.255.0
DNS1=192.168.3.2


hostnamectl set-hostname node-03


配置环境变量
export JAVA_HOME=/root/apps/jdk1.8.0_202
export HADOOP_HOME=/root/apps/hadoop-2.8.1
export HADOOP_CONF_DIR=/root/apps/hadoop-2.8.1/etc/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin


往Spark集群中提交任务
/root/apps/spark-2.2.3-bin-hadoop2.7/bin/spark-submit --master spark://node-01:7077 --class org.apache.spark.examples.SparkPi /root/apps/spark-2.2.3-bin-hadoop2.7/examples/jars/spark-examples_2.11-2.2.3.jar 100




HDFS的配置

cat /root/apps/hadoop-2.8.1/etc/hadoop/core-site.xml
<property>
    <name>fs.defaultFS</name>
    <value>hdfs://node-01:9000</value>
</property>



cat /root/apps/hadoop-2.8.1/etc/hadoop/hdfs-site.xml


<property>
    <name>dfs.namenode.name.dir</name>
    <value>/root/dfs/name</value>
</property>

<property>
    <name>dfs.datanode.data.dir</name>
    <value>/root/dfs/data</value>
</property>

<property>
    <name>dfs.blocksize</name>
    <value>64m</value>
</property>

<property>
    <name>dfs.replication</name>
    <value>2</value>
</property>


初始化nameNode
hadoop namenode -format

启动HDFS
/root/apps/hadoop-2.8.1/sbin/start-yarn.sh;

测试HDFS
hadoop fs -mkdir  -p /wordcount/input;
hadoop fs -copyFromLocal /home/bduser/data/testData/testWc.txt  /wordcount/input/testWc1.txt;
hadoop fs -rm -p /wordcount




Yarn的配置
/root/apps/hadoop-2.8.1/etc/hadoop/yarn-site.xml

<property>
    <name>yarn.resourcemanager.hostname</name>
    <value>node-01</value>
</property>
<property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>
<property>
    <name>yarn.nodemanager.resource.memory-mb</name>
    <value>2048</value>
</property>
<property>
    <name>yarn.nodemanager.resource.cpu-vcores</name>
    <value>2</value>
</property>


hadoop namenode -format


启动Yarn
/root/apps/hadoop-2.8.1/sbin/start-yarn.sh;

测试Yarn
http://node-01:8088/cluster

虚拟机中执行Pi求值得Demo
/root/apps/spark-2.2.3-bin-hadoop2.7/bin/spark-submit --master yarn --deploy-mode cluster --class org.apache.spark.examples.SparkPi --driver-memory 1024m --executor-memory 1024m --total-executor-cores 2 --queue default /root/apps/spark-2.2.3-bin-hadoop2.7/examples/jars/spark-examples_2.11-2.2.3.jar 100