Spark Streaming實時流處理筆記(7)—— 環境搭建
阿新 • • 發佈:2018-12-06
1 配置Hadoop
hadoop-env.sh
export JAVA_HOME=/usr/apps/jdk1.8.0_181-amd64
core-site.xml
<configuration> <property> <name>fs.defaultFS</name> <value>hdfs://node1:8020</value> </property> <property> <name>hadoop.tmp.dir</name> <value>/home/hadoop/appsData/hdpData/tmp</value> </property> </configuration>
hdfs-site.xml
<configuration> <property> <name>dfs.replication</name> <name>1</name> </property> <property> <name>dfs.namenode.name.dir</name> <value>/home/hadoop/appsData/hdpData/namedir</value> </property> <property> <name>dfs.datanode.data.dir</name> <value>/home/hadoop/appsData/hdpData/datadir</value> </property> <property> <name>dfs.permissions</name> <value>false</value> </property> </configuration>
slaves
node1
1.1 格式化 namenode
hdfs namenode -format
1.2 啟動 hdfs
[[email protected] hadoop]$ start-dfs.sh
18/12/06 10:37:57 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Starting namenodes on [node1]
node1: starting namenode, logging to /home/hadoop/apps/hadoop-2.6.0-cdh5.7.0/logs/hadoop-hadoop-namenode-node1.out
node1: starting datanode, logging to /home/hadoop/apps/hadoop-2.6.0-cdh5.7.0/logs/hadoop-hadoop-datanode-node1.out
Starting secondary namenodes [0.0.0.0]
0.0.0.0: starting secondarynamenode, logging to /home/hadoop/apps/hadoop-2.6.0-cdh5.7.0/logs/hadoop-hadoop-secondarynamenode-node1.out
18/12/06 10:38:13 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
[ [email protected] hadoop]$ jps
1777 DataNode
1953 SecondaryNameNode
2071 Jps
1647 NameNode
[[email protected] hadoop]$
http://node1:50070
2 配置 YARN
mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
yarn-site.xml
<configuration>
<!-- Site specific YARN configuration properties -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.resourcemanager.hostname</name>
<value>node1</value>
</property>
</configuration>
2.1 啟動 YARN
[[email protected] ~]$ start-yarn.sh
starting yarn daemons
starting resourcemanager, logging to /home/hadoop/apps/hadoop-2.6.0-cdh5.7.0/logs/yarn-hadoop-resourcemanager-node1.out
node1: starting nodemanager, logging to /home/hadoop/apps/hadoop-2.6.0-cdh5.7.0/logs/yarn-hadoop-nodemanager-node1.out
[[email protected] ~]$ jps
2144 ResourceManager
1777 DataNode
1953 SecondaryNameNode
2567 Jps
2251 NodeManager
1647 NameNode
[[email protected] ~]$
http://node1:8088
3 配置 Hbase
http://archive-primary.cloudera.com/cdh5/cdh/5/
新增到環境變數
export HBASE_HOME=/home/hadoop/apps/hbase-1.2.0-cdh5.7.0
export PATH=$PATH:$HBASE_HOME/bin
3.1 Hbase 配置檔案
/home/hadoop/apps/hbase-1.2.0-cdh5.7.0/conf
hbase-env.sh
export JAVA_HOME=/usr/apps/jdk1.8.0_181-amd64
export HBASE_MANAGES_ZK=false
hbase-site.xml
<property>
<name>hbase.rootdir</name>
<value>hdfs://node1:8020/hbase</value>
</property>
<property>
<name>hbase.cluster.distributed</name>
<value>true</value>
</property>
<property>
<name>hbase.zookeeper.quorum</name>
<value>node1:2181</value>
</property>
regionservers
node1
3.2 啟動 hbase
- 先啟動 zookeeper
[[email protected] ~]$ zkServer.sh start
JMX enabled by default
Using config: /home/hadoop/apps/zookeeper-3.4.5-cdh5.7.0/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
[[email protected] ~]$ jps
2144 ResourceManager
2768 Jps
1777 DataNode
1953 SecondaryNameNode
2744 QuorumPeerMain
2251 NodeManager
1647 NameNode
[[email protected] ~]$
[[email protected] ~]$ start-hbase.sh
starting master, logging to /home/hadoop/apps/hbase-1.2.0-cdh5.7.0/logs/hbase-hadoop-master-node1.out
Java HotSpot(TM) 64-Bit Server VM warning: ignoring option PermSize=128m; support was removed in 8.0
Java HotSpot(TM) 64-Bit Server VM warning: ignoring option MaxPermSize=128m; support was removed in 8.0
node1: starting regionserver, logging to /home/hadoop/apps/hbase/bin/../logs/hbase-hadoop-regionserver-node1.out
node1: Java HotSpot(TM) 64-Bit Server VM warning: ignoring option PermSize=128m; support was removed in 8.0
node1: Java HotSpot(TM) 64-Bit Server VM warning: ignoring option MaxPermSize=128m; support was removed in 8.0
http://node1:60010
hbase shell
4 IDEA +MAVEN 環境搭建
參考 Kafka部分
POM
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.myspark.com</groupId>
<artifactId>sparktrain</artifactId>
<version>1.0</version>
<inceptionYear>2008</inceptionYear>
<properties>
<scala.version>2.11.12</scala.version>
<kafka.version>0.9.0.0</kafka.version>
<spark.version>2.2.0</spark.version>
<hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
<hbase.version>1.2.0-cdh5.7.0</hbase.version>
</properties>
<repositories>
<repository>
<id>scala-tools.org</id>
<name>Scala-Tools Maven2 Repository</name>
<url>http://scala-tools.org/repo-releases</url>
</repository>
<!--新增庫-->
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
</repository>
</repositories>
<pluginRepositories>
<pluginRepository>
<id>scala-tools.org</id>
<name>Scala-Tools Maven2 Repository</name>
<url>http://scala-tools.org/repo-releases</url>
</pluginRepository>
</pluginRepositories>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.11</artifactId>
<version>${kafka.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>${hbase.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>${hbase.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
<args>
<arg>-target:jvm-1.5</arg>
</args>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<configuration>
<downloadSources>true</downloadSources>
<buildcommands>
<buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
</buildcommands>
<additionalProjectnatures>
<projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
</additionalProjectnatures>
<classpathContainers>
<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
<classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
</classpathContainers>
</configuration>
</plugin>
</plugins>
</build>
<reporting>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
</configuration>
</plugin>
</plugins>
</reporting>
</project>