大数据集群配置信息

1. 大数据集群各组件版本

组件	版本
Hadoop	2.6.0
Spark	2.1.0
Hive	1.2.1
Scala	2.11.8
Java	1.8.0_144
CDH	5.13.0

2. Yarn的队列与资源

队列	webui(访问需先申请windows 远程桌面)	资源
zz	http://172.18.x.xx:8088	zz_aa、zz_bb等一系列以zz为前缀的账号均共享zz池，2560vcore,10240G内存

3. Spark提交任务命令示例[ deploy-mode 可选:client/cluster ]

spark-submit \
--conf "spark.executorEnv.JAVA_HOME=/usr/jdk1.8.0_144" \
--conf "spark.yarn.appMasterEnv.JAVA_HOME=/usr/jdk1.8.0_144" \
--conf spark.kryoserializer.buffer.max=512m \
--conf spark.kryoserializer.buffer=256m \
--class com.xxx.spark.WordCount \
--master yarn \
--deploy-mode client \
--driver-memory 4g \
--executor-memory 1g \
--executor-cores 1 \
--num-executors 40 \
--queue zz \
spark-mllib-1.0-jar-with-dependencies.jar

或

nohup spark-submit  \
    --name KafkaSink2MongoForHeartBeat \
    --class im.youni.contact.streaming.KafkaSink2MongoForHeartBeat \
    --master yarn \
    --deploy-mode client \
    --driver-memory 6g \
    --executor-memory 3g \
    --executor-cores 3 \
    --num-executors 4 \
    --queue root.zz  \
    # --keytab /home/zx_realtime/zx_realtime.keytab \
    # --principal zx_realtime@CENTER.DATAPLAT \
    baseprofile-real-1.0-jar-with-dependencies.jar  \
    false KafkaSink2MongoForHeartBeat  172.18.2.102:18080,172.18.2.133:18080,172.18.16.175:18080 heartbeat userprofile_heartbeat_g1 \
>/dev/null 2>&1 &

4. Maven依赖

<properties>
    <maven.compiler.source>1.8</maven.compiler.source>
    <maven.compiler.target>1.8</maven.compiler.target>
    <scala.version>2.11.8</scala.version>
    <hadoop.version>2.6.0</hadoop.version>
    <spark.version>2.1.0</spark.version>
    <hive.version>1.2.1</hive.version>
</properties>
 
<dependencies>
    <dependency>
        <groupId>org.scala-lang</groupId>
        <artifactId>scala-library</artifactId>
        <version>${scala.version}</version>
        <!--<scope>provided</scope>-->
    </dependency>
 
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.11</artifactId>
        <version>${spark.version}</version>
    </dependency>
 
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.11</artifactId>
        <version>${spark.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-hive_2.11</artifactId>
        <version>${spark.version}</version>
    </dependency>
 
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
 
    <dependency>
        <groupId>org.apache.hive</groupId>
        <artifactId>hive-jdbc</artifactId>
        <version>${hive.version}</version>
    </dependency>
 
</dependencies>
 
<build>
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    <plugins>
        <plugin>
            <groupId>net.alchim31.maven</groupId>
            <artifactId>scala-maven-plugin</artifactId>
            <version>3.2.2</version>
            <executions>
                <execution>
                    <goals>
                        <goal>compile</goal>
                        <goal>testCompile</goal>
                    </goals>
                    <configuration>
                        <args>
                            <arg>-dependencyfile</arg>
                            <arg>${project.build.directory}/.scala_dependencies</arg>
                        </args>
                    </configuration>
                </execution>
            </executions>
        </plugin>
        <!-- 编译插件 -->
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <version>3.6.0</version>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
                <encoding>UTF-8</encoding>
            </configuration>
        </plugin>
        <!-- scala编译插件 -->
        <plugin>
            <groupId>net.alchim31.maven</groupId>
            <artifactId>scala-maven-plugin</artifactId>
            <version>3.1.6</version>
            <configuration>
                <scalaCompatVersion>2.11</scalaCompatVersion>
                <scalaVersion>2.11.12</scalaVersion>
                <encoding>UTF-8</encoding>
            </configuration>
            <executions>
                <execution>
                    <id>compile-scala</id>
                    <phase>compile</phase>
                    <goals>
                        <goal>add-source</goal>
                        <goal>compile</goal>
                    </goals>
                </execution>
                <execution>
                    <id>test-compile-scala</id>
                    <phase>test-compile</phase>
                    <goals>
                        <goal>add-source</goal>
                        <goal>testCompile</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
        <!-- 打jar包插件(会包含所有依赖) -->
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-assembly-plugin</artifactId>
            <version>2.6</version>
            <configuration>
                <descriptorRefs>
                    <descriptorRef>jar-with-dependencies</descriptorRef>
                </descriptorRefs>
                <archive>
                    <manifest>
                        <!-- 可以设置jar包的入口类(可选) -->
                        <!--<mainClass></mainClass>-->
                    </manifest>
                </archive>
                <includeSite>
 
                </includeSite>
 
            </configuration>
            <executions>
                <execution>
                    <id>make-assembly</id>
                    <phase>package</phase>
                    <goals>
                        <goal>single</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
    </plugins>
</build>