2cf83c4783
## What changes were proposed in this pull request? Add a new `spark-hadoop-cloud` module and maven profile to pull in object store support from `hadoop-openstack`, `hadoop-aws` and `hadoop-azure` (Hadoop 2.7+) JARs, along with their dependencies, fixing up the dependencies so that everything works, in particular Jackson. It restores `s3n://` access to S3, adds its `s3a://` replacement, OpenStack `swift://` and azure `wasb://`. There's a documentation page, `cloud_integration.md`, which covers the basic details of using Spark with object stores, referring the reader to the supplier's own documentation, with specific warnings on security and the possible mismatch between a store's behavior and that of a filesystem. In particular, users are advised be very cautious when trying to use an object store as the destination of data, and to consult the documentation of the storage supplier and the connector. (this is the successor to #12004; I can't re-open it) ## How was this patch tested? Downstream tests exist in [https://github.com/steveloughran/spark-cloud-examples/tree/master/cloud-examples](https://github.com/steveloughran/spark-cloud-examples/tree/master/cloud-examples) Those verify that the dependencies are sufficient to allow downstream applications to work with s3a, azure wasb and swift storage connectors, and perform basic IO & dataframe operations thereon. All seems well. Manually clean build & verify that assembly contains the relevant aws-* hadoop-* artifacts on Hadoop 2.6; azure on a hadoop-2.7 profile. SBT build: `build/sbt -Phadoop-cloud -Phadoop-2.7 package` maven build `mvn install -Phadoop-cloud -Phadoop-2.7` This PR *does not* update `dev/deps/spark-deps-hadoop-2.7` or `dev/deps/spark-deps-hadoop-2.6`, because unless the hadoop-cloud profile is enabled, no extra JARs show up in the dependency list. The dependency check in Jenkins isn't setting the property, so the new JARs aren't visible. Author: Steve Loughran <stevel@apache.org> Author: Steve Loughran <stevel@hortonworks.com> Closes #17834 from steveloughran/cloud/SPARK-7481-current.
245 lines
8 KiB
XML
245 lines
8 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!--
|
|
~ Licensed to the Apache Software Foundation (ASF) under one or more
|
|
~ contributor license agreements. See the NOTICE file distributed with
|
|
~ this work for additional information regarding copyright ownership.
|
|
~ The ASF licenses this file to You under the Apache License, Version 2.0
|
|
~ (the "License"); you may not use this file except in compliance with
|
|
~ the License. You may obtain a copy of the License at
|
|
~
|
|
~ http://www.apache.org/licenses/LICENSE-2.0
|
|
~
|
|
~ Unless required by applicable law or agreed to in writing, software
|
|
~ distributed under the License is distributed on an "AS IS" BASIS,
|
|
~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
~ See the License for the specific language governing permissions and
|
|
~ limitations under the License.
|
|
-->
|
|
|
|
<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/xsd/maven-4.0.0.xsd">
|
|
<modelVersion>4.0.0</modelVersion>
|
|
<parent>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-parent_2.11</artifactId>
|
|
<version>2.3.0-SNAPSHOT</version>
|
|
<relativePath>../pom.xml</relativePath>
|
|
</parent>
|
|
|
|
<artifactId>spark-assembly_2.11</artifactId>
|
|
<name>Spark Project Assembly</name>
|
|
<url>http://spark.apache.org/</url>
|
|
<packaging>pom</packaging>
|
|
|
|
<properties>
|
|
<sbt.project.name>assembly</sbt.project.name>
|
|
<build.testJarPhase>none</build.testJarPhase>
|
|
<build.copyDependenciesPhase>package</build.copyDependenciesPhase>
|
|
</properties>
|
|
|
|
<dependencies>
|
|
<!-- Prevent our dummy JAR from being included in Spark distributions or uploaded to YARN -->
|
|
<dependency>
|
|
<groupId>org.spark-project.spark</groupId>
|
|
<artifactId>unused</artifactId>
|
|
<version>1.0.0</version>
|
|
<scope>provided</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-core_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-mllib_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-streaming_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-graphx_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-sql_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-repl_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
|
|
<!--
|
|
Because we don't shade dependencies anymore, we need to restore Guava to compile scope so
|
|
that the libraries Spark depend on have it available. We'll package the version that Spark
|
|
uses (14.0.1) which is not the same as Hadoop dependencies, but works.
|
|
-->
|
|
<dependency>
|
|
<groupId>com.google.guava</groupId>
|
|
<artifactId>guava</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
</dependencies>
|
|
|
|
<build>
|
|
<plugins>
|
|
<plugin>
|
|
<groupId>org.apache.maven.plugins</groupId>
|
|
<artifactId>maven-deploy-plugin</artifactId>
|
|
<configuration>
|
|
<skip>true</skip>
|
|
</configuration>
|
|
</plugin>
|
|
<plugin>
|
|
<groupId>org.apache.maven.plugins</groupId>
|
|
<artifactId>maven-install-plugin</artifactId>
|
|
<configuration>
|
|
<skip>true</skip>
|
|
</configuration>
|
|
</plugin>
|
|
<!-- zip pyspark archives to run python application on yarn mode -->
|
|
<plugin>
|
|
<groupId>org.apache.maven.plugins</groupId>
|
|
<artifactId>maven-antrun-plugin</artifactId>
|
|
<executions>
|
|
<execution>
|
|
<phase>package</phase>
|
|
<goals>
|
|
<goal>run</goal>
|
|
</goals>
|
|
</execution>
|
|
</executions>
|
|
<configuration>
|
|
<target>
|
|
<delete dir="${basedir}/../python/lib/pyspark.zip"/>
|
|
<zip destfile="${basedir}/../python/lib/pyspark.zip">
|
|
<fileset dir="${basedir}/../python/" includes="pyspark/**/*"/>
|
|
</zip>
|
|
</target>
|
|
</configuration>
|
|
</plugin>
|
|
</plugins>
|
|
</build>
|
|
|
|
<profiles>
|
|
<profile>
|
|
<id>yarn</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-yarn_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
<profile>
|
|
<id>mesos</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-mesos_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
<profile>
|
|
<id>hive</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-hive_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
<profile>
|
|
<id>hive-thriftserver</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
<profile>
|
|
<id>spark-ganglia-lgpl</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-ganglia-lgpl_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
<profile>
|
|
<id>bigtop-dist</id>
|
|
<!-- This profile uses the assembly plugin to create a special "dist" package for BigTop
|
|
that contains Spark but not the Hadoop JARs it depends on. -->
|
|
<build>
|
|
<plugins>
|
|
<plugin>
|
|
<groupId>org.apache.maven.plugins</groupId>
|
|
<artifactId>maven-assembly-plugin</artifactId>
|
|
<version>3.0.0</version>
|
|
<executions>
|
|
<execution>
|
|
<id>dist</id>
|
|
<phase>package</phase>
|
|
<goals>
|
|
<goal>single</goal>
|
|
</goals>
|
|
<configuration>
|
|
<descriptors>
|
|
<descriptor>src/main/assembly/assembly.xml</descriptor>
|
|
</descriptors>
|
|
</configuration>
|
|
</execution>
|
|
</executions>
|
|
</plugin>
|
|
</plugins>
|
|
</build>
|
|
</profile>
|
|
|
|
<!-- Profiles that disable inclusion of certain dependencies. -->
|
|
<profile>
|
|
<id>hadoop-provided</id>
|
|
<properties>
|
|
<hadoop.deps.scope>provided</hadoop.deps.scope>
|
|
</properties>
|
|
</profile>
|
|
<profile>
|
|
<id>hive-provided</id>
|
|
<properties>
|
|
<hive.deps.scope>provided</hive.deps.scope>
|
|
</properties>
|
|
</profile>
|
|
<profile>
|
|
<id>parquet-provided</id>
|
|
<properties>
|
|
<parquet.deps.scope>provided</parquet.deps.scope>
|
|
</properties>
|
|
</profile>
|
|
|
|
<!--
|
|
Pull in spark-hadoop-cloud and its associated JARs,
|
|
-->
|
|
<profile>
|
|
<id>hadoop-cloud</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-hadoop-cloud_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
</profiles>
|
|
</project>
|