spark源码编译

[root@MySQL ~]# wget https://archive.apache.org/dist/spark/spark-2.4.0/spark-2.4.0.tgz

[root@MySQL ~]# tar zxvf spark-2.4.0.tgz 

[root@MySQL ~]# cd spark-2.4.0

[root@MySQL ~]# cd spark-2.4.0/dev

VERSION=2.4.0

SCALA_VERSION=2.12.8

SPARK_HADOOP_VERSION=2.6.0-cdh5.14.0

SPARK_HIVE=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)

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

<hadoop.version>2.6.0-cdh5.14.0</hadoop.version>

<flume.version>1.6.0-cdh5.14.0</flume.version>

<zookeeper.version>3.4.5-cdh5.14.0</zookeeper.version>

<repository>

<id>cloudera</id>

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

</repository>

<repository>

<id>aliyun</id>

<name>aliyun</name>

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

<layout>default</layout>

<releases>

<enabled>true</enabled>

<updatePolicy>never</updatePolicy>

</releases>

<snapshots>

<enabled>true</enabled>

<updatePolicy>never</updatePolicy>

</snapshots>

</repository>

添加pluginRepository

<pluginRepository>

<id>cloudera</id>

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

</pluginRepository>

[root@MySQL ~]# cd spark-2.4.0/

[root@MySQL ~]# export MAVEN_OPTS="-Xmx4g -XX:ReservedCodeCacheSize=1024m"

[root@MySQL ~]# ./dev/make-distribution.sh --name 2.6.0-cdh5.14.0 --tgz  -Pyarn -Phadoop-2.6 -Phive -Phive-thriftserver -Dhadoop.version=2.6.0-cdh5.14.0 -DskipTests