9c0af746e5
## What changes were proposed in this pull request? This PR upgrade `hadoop-3` to `3.2.0` to workaround [HADOOP-16086](https://issues.apache.org/jira/browse/HADOOP-16086). Otherwise some test case will throw IllegalArgumentException: ```java 02:44:34.707 ERROR org.apache.hadoop.hive.ql.exec.Task: Job Submission failed with exception 'java.io.IOException(Cannot initialize Cluster. Please check your configuration for mapreduce.framework.name and the correspond server addresses.)' java.io.IOException: Cannot initialize Cluster. Please check your configuration for mapreduce.framework.name and the correspond server addresses. at org.apache.hadoop.mapreduce.Cluster.initialize(Cluster.java:116) at org.apache.hadoop.mapreduce.Cluster.<init>(Cluster.java:109) at org.apache.hadoop.mapreduce.Cluster.<init>(Cluster.java:102) at org.apache.hadoop.mapred.JobClient.init(JobClient.java:475) at org.apache.hadoop.mapred.JobClient.<init>(JobClient.java:454) at org.apache.hadoop.hive.ql.exec.mr.ExecDriver.execute(ExecDriver.java:369) at org.apache.hadoop.hive.ql.exec.mr.MapRedTask.execute(MapRedTask.java:151) at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:199) at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:100) at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:2183) at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1839) at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1526) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1237) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1227) at org.apache.spark.sql.hive.client.HiveClientImpl.$anonfun$runHive$1(HiveClientImpl.scala:730) at org.apache.spark.sql.hive.client.HiveClientImpl.$anonfun$withHiveState$1(HiveClientImpl.scala:283) at org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:221) at org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:220) at org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:266) at org.apache.spark.sql.hive.client.HiveClientImpl.runHive(HiveClientImpl.scala:719) at org.apache.spark.sql.hive.client.HiveClientImpl.runSqlHive(HiveClientImpl.scala:709) at org.apache.spark.sql.hive.StatisticsSuite.createNonPartitionedTable(StatisticsSuite.scala:719) at org.apache.spark.sql.hive.StatisticsSuite.$anonfun$testAlterTableProperties$2(StatisticsSuite.scala:822) ``` ## How was this patch tested? manual tests Closes #24106 from wangyum/SPARK-27175. Authored-by: Yuming Wang <yumwang@ebay.com> Signed-off-by: Sean Owen <sean.owen@databricks.com>
256 lines
9.1 KiB
XML
256 lines
9.1 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_2.12</artifactId>
|
|
<version>3.0.0-SNAPSHOT</version>
|
|
<relativePath>../pom.xml</relativePath>
|
|
</parent>
|
|
|
|
<artifactId>spark-hadoop-cloud_2.12</artifactId>
|
|
<packaging>jar</packaging>
|
|
<name>Spark Project Cloud Integration through Hadoop Libraries</name>
|
|
<description>
|
|
Contains support for cloud infrastructures, specifically the Hadoop JARs and
|
|
transitive dependencies needed to interact with the infrastructures,
|
|
making everything consistent with Spark's other dependencies.
|
|
</description>
|
|
<properties>
|
|
<sbt.project.name>hadoop-cloud</sbt.project.name>
|
|
</properties>
|
|
|
|
<build>
|
|
<outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
|
|
<testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory>
|
|
</build>
|
|
|
|
<dependencies>
|
|
<!--used during compilation but not exported as transitive dependencies-->
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-sql_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
<scope>provided</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.spark</groupId>
|
|
<artifactId>spark-core_${scala.binary.version}</artifactId>
|
|
<version>${project.version}</version>
|
|
<type>test-jar</type>
|
|
<scope>test</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-client</artifactId>
|
|
<version>${hadoop.version}</version>
|
|
<scope>provided</scope>
|
|
</dependency>
|
|
<!--
|
|
the AWS module pulls in jackson; its transitive dependencies can create
|
|
intra-jackson-module version problems.
|
|
-->
|
|
<dependency>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-aws</artifactId>
|
|
<version>${hadoop.version}</version>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
<exclusions>
|
|
<exclusion>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-common</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>commons-logging</groupId>
|
|
<artifactId>commons-logging</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>org.codehaus.jackson</groupId>
|
|
<artifactId>jackson-mapper-asl</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>org.codehaus.jackson</groupId>
|
|
<artifactId>jackson-core-asl</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-core</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-databind</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-annotations</artifactId>
|
|
</exclusion>
|
|
</exclusions>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-openstack</artifactId>
|
|
<version>${hadoop.version}</version>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
<exclusions>
|
|
<exclusion>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-common</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>commons-logging</groupId>
|
|
<artifactId>commons-logging</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>junit</groupId>
|
|
<artifactId>junit</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>org.mockito</groupId>
|
|
<artifactId>mockito-all</artifactId>
|
|
</exclusion>
|
|
</exclusions>
|
|
</dependency>
|
|
|
|
<!--
|
|
Add joda time to ensure that anything downstream which doesn't pull in spark-hive
|
|
gets the correct joda time artifact, so doesn't have auth failures on later Java 8 JVMs
|
|
-->
|
|
<dependency>
|
|
<groupId>joda-time</groupId>
|
|
<artifactId>joda-time</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
<!-- explicitly declare the jackson artifacts desired -->
|
|
<dependency>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-databind</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-annotations</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>com.fasterxml.jackson.dataformat</groupId>
|
|
<artifactId>jackson-dataformat-cbor</artifactId>
|
|
<version>${fasterxml.jackson.version}</version>
|
|
</dependency>
|
|
<!--Explicit declaration to force in Spark version into transitive dependencies -->
|
|
<dependency>
|
|
<groupId>org.apache.httpcomponents</groupId>
|
|
<artifactId>httpclient</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
<!--Explicit declaration to force in Spark version into transitive dependencies -->
|
|
<dependency>
|
|
<groupId>org.apache.httpcomponents</groupId>
|
|
<artifactId>httpcore</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-azure</artifactId>
|
|
<version>${hadoop.version}</version>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
<exclusions>
|
|
<exclusion>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-common</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>org.codehaus.jackson</groupId>
|
|
<artifactId>jackson-mapper-asl</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-core</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.google.guava</groupId>
|
|
<artifactId>guava</artifactId>
|
|
</exclusion>
|
|
</exclusions>
|
|
</dependency>
|
|
</dependencies>
|
|
|
|
<profiles>
|
|
|
|
<!--
|
|
Hadoop 3 simplifies the classpath, and adds a new committer base class which
|
|
enables store-specific committers.
|
|
-->
|
|
<profile>
|
|
<id>hadoop-3.2</id>
|
|
<dependencies>
|
|
<!--
|
|
There's now a hadoop-cloud-storage which transitively pulls in the store JARs,
|
|
but it still needs some selective exclusion across versions, especially 3.0.x.
|
|
-->
|
|
<dependency>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-cloud-storage</artifactId>
|
|
<version>${hadoop.version}</version>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
<exclusions>
|
|
<exclusion>
|
|
<groupId>org.apache.hadoop</groupId>
|
|
<artifactId>hadoop-common</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>org.codehaus.jackson</groupId>
|
|
<artifactId>jackson-mapper-asl</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.fasterxml.jackson.core</groupId>
|
|
<artifactId>jackson-core</artifactId>
|
|
</exclusion>
|
|
<exclusion>
|
|
<groupId>com.google.guava</groupId>
|
|
<artifactId>guava</artifactId>
|
|
</exclusion>
|
|
</exclusions>
|
|
</dependency>
|
|
<!--
|
|
The jetty declarations are made
|
|
(a) to keep that jetty-util-ajax version in sync with the rest of Spark.
|
|
(b) to minimise the effects which Spark's jetty shading has on the
|
|
availability of the jetty JARs on for hadoop-azure, which depends
|
|
on them.
|
|
-->
|
|
<dependency>
|
|
<groupId>org.eclipse.jetty</groupId>
|
|
<artifactId>jetty-util</artifactId>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.eclipse.jetty</groupId>
|
|
<artifactId>jetty-util-ajax</artifactId>
|
|
<version>${jetty.version}</version>
|
|
<scope>${hadoop.deps.scope}</scope>
|
|
</dependency>
|
|
</dependencies>
|
|
</profile>
|
|
|
|
</profiles>
|
|
|
|
</project>
|