spark编译

安装jdk1.8

vi pom.xml

CDH版本编译添加：

pom.xml

<repositories>

  <repository>

    <id>central</id>

    <!-- This should be at top, it makes maven try the central repo first and then others and hence faster dep resolution -->

    <name>Maven Repository</name>

    <url>http://maven.aliyun.com/nexus/content/groups/public/</url>

    <releases>

      <enabled>true</enabled>

    </releases>

    <snapshots>

      <enabled>false</enabled>

    </snapshots>

  </repository>

  <repository>

    <id>cloudera</id>

    <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>

  </repository>

</repositories>

<pluginRepositories>

  <pluginRepository>

    <id>central</id>

    <url>http://maven.aliyun.com/nexus/content/groups/public/</url>

    <releases>

      <enabled>true</enabled>

    </releases>

    <snapshots>

      <enabled>false</enabled>

    </snapshots>

  </pluginRepository>

</pluginRepositories>

<dependencies>

./dev/make-distribution.sh (自定义版本)

VERSION=2.3.1

#VERSION=$("$MVN" help:evaluate -Dexpression=project.version $@ 2>/dev/null | grep -v "INFO" | tail -n 1)

#SCALA_VERSION=$("$MVN" help:evaluate -Dexpression=scala.binary.version $@ 2>/dev/null\

 #   | grep -v "INFO"\

  #  | tail -n 1)

SCALA_VERSION=2.11

SPARK_HADOOP_VERSION=2.6.0

#SPARK_HADOOP_VERSION=$("$MVN" help:evaluate -Dexpression=hadoop.version $@ 2>/dev/null\

#    | grep -v "INFO"\

#    | tail -n 1)

SPARK_HIVE=1

#SPARK_HIVE=$("$MVN" help:evaluate -Dexpression=project.activeProfiles -pl sql/hive $@ 2>/dev/null\

 #   | grep -v "INFO"\

#    | fgrep --count "<id>hive</id>";\

    # Reset exit status to 0, otherwise the script stops here if the last grep finds nothing\

    # because we use "set -o pipefail"

 #   echo -n)

执行编译命令：

./dev/make-distribution.sh --name 2.6.0-cdh5.10.0 --tgz  -Pyarn -Phadoop-2.6  -Dhadoop.version=2.6.0-cdh5.10.0 -Phive -Phive-thriftserver -DskipTests