ce7ba2e98e
## What changes were proposed in this pull request? 1. Adds a `hadoop-3.1` profile build depending on the hadoop-3.1 artifacts. 1. In the hadoop-cloud module, adds an explicit hadoop-3.1 profile which switches from explicitly pulling in cloud connectors (hadoop-openstack, hadoop-aws, hadoop-azure) to depending on the hadoop-cloudstorage POM artifact, which pulls these in, has pre-excluded things like hadoop-common, and stays up to date with new connectors (hadoop-azuredatalake, hadoop-allyun). Goal: it becomes the Hadoop projects homework of keeping this clean, and the spark project doesn't need to handle new hadoop releases adding more dependencies. 1. the hadoop-cloud/hadoop-3.1 profile also declares support for jetty-ajax and jetty-util to ensure that these jars get into the distribution jar directory when needed by unshaded libraries. 1. Increases the curator and zookeeper versions to match those in hadoop-3, fixing spark core to build in sbt with the hadoop-3 dependencies. ## How was this patch tested? * Everything this has been built and tested against both ASF Hadoop branch-3.1 and hadoop trunk. * spark-shell was used to create connectors to all the stores and verify that file IO could take place. The spark hive-1.2.1 JAR has problems here, as it's version check logic fails for Hadoop versions > 2. This can be avoided with either of * The hadoop JARs built to declare their version as Hadoop 2.11 `mvn install -DskipTests -DskipShade -Ddeclared.hadoop.version=2.11` . This is safe for local test runs, not for deployment (HDFS is very strict about cross-version deployment). * A modified version of spark hive whose version check switch statement is happy with hadoop 3. I've done both, with maven and SBT. Three issues surfaced 1. A spark-core test failure —fixed in SPARK-23787. 1. SBT only: Zookeeper not being found in spark-core. Somehow curator 2.12.0 triggers some slightly different dependency resolution logic from previous versions, and Ivy was missing zookeeper.jar entirely. This patch adds the explicit declaration for all spark profiles, setting the ZK version = 3.4.9 for hadoop-3.1 1. Marking jetty-utils as provided in spark was stopping hadoop-azure from being able to instantiate the azure wasb:// client; it was using jetty-util-ajax, which could then not find a class in jetty-util. Author: Steve Loughran <stevel@hortonworks.com> Closes #20923 from steveloughran/cloud/SPARK-23807-hadoop-31.
269 lines
8.8 KiB
XML
269 lines
8.8 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>2.4.0-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>kubernetes</id>
|
|
<dependencies>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-kubernetes_${scala.binary.version}</artifactId>
|
|
<version>${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>3.1.0</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>orc-provided</id>
|
|
<properties>
|
|
<orc.deps.scope>provided</orc.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>
|
|
<!--
|
|
Redeclare this dependency to force it into the distribution.
|
|
-->
|
|
<dependency>
|
|
<groupId>org.eclipse.jetty</groupId>
|
|
<artifactId>jetty-util</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
</profiles>
|
|
</project>
|