Merge -r 1182150:1182151 from trunk to branch. FIXES: HADOOP-7642

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-0.23@1190616 13f79535-47bb-0310-9956-ffa450edef68

hadoop-assemblies/src/main/resources/assemblies/hadoop-mapreduce-dist.xml

@@ -0,0 +1,101 @@
+<assembly xmlns="http://maven.apache.org/plugins/maven-assembly-plugin/assembly/1.1.0"
+  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xsi:schemaLocation="http://maven.apache.org/plugins/maven-assembly-plugin/assembly/1.1.0 http://maven.apache.org/xsd/assembly-1.1.0.xsd">
+  <id>hadoop-mapreduce-dist</id>
+  <formats>
+    <format>tar.gz</format>
+  </formats>
+  <includeBaseDirectory>true</includeBaseDirectory>
+  <!-- TODO: this layout is wrong. We need module specific bin files in module specific dirs -->
+  <fileSets>
+    <fileSet>
+      <directory>hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/target/classes/bin</directory>
+      <outputDirectory>bin</outputDirectory>
+      <includes>
+        <include>container-executor</include>
+      </includes>
+      <fileMode>0755</fileMode>
+    </fileSet>
+    <fileSet>
+      <directory>hadoop-yarn/bin</directory>
+      <outputDirectory>bin</outputDirectory>
+      <includes>
+        <include>*</include>
+      </includes>
+      <fileMode>0755</fileMode>
+    </fileSet>
+    <fileSet>
+      <directory>bin</directory>
+      <outputDirectory>bin</outputDirectory>
+      <includes>
+        <include>*</include>
+      </includes>
+      <fileMode>0755</fileMode>
+    </fileSet>
+    <fileSet>
+      <directory>hadoop-yarn/conf</directory>
+      <outputDirectory>conf</outputDirectory>
+      <includes>
+        <include>**/*</include>
+      </includes>
+    </fileSet>
+    <fileSet>
+      <outputDirectory>sources</outputDirectory>
+      <excludes>
+        <exclude>**/*.jar</exclude>
+        <exclude>**/target/**</exclude>
+        <!-- scripts to include later for setting fileMode -->
+        <exclude>**/bin/*</exclude>
+        <exclude>**/scripts/*</exclude>
+        <!-- images that we don't need (and cause problems for our tools) -->
+        <exclude>**/dt-*/images/**</exclude>
+        <!-- until the code that does this is fixed -->
+        <exclude>**/file:/**</exclude>
+        <exclude>**/SecurityAuth.audit*</exclude>
+      </excludes>
+      <includes>
+        <include>assembly/**</include>
+        <include>pom.xml</include>
+        <include>build*.xml</include>
+        <include>ivy.xml</include>
+        <include>ivy/**</include>
+        <include>INSTALL</include>
+        <include>LICENSE.txt</include>
+        <include>mr-client/**</include>
+        <include>hadoop-yarn/**</include>
+        <include>src/**</include>
+      </includes>
+    </fileSet>
+    <fileSet>
+      <outputDirectory>sources</outputDirectory>
+      <includes>
+        <include>**/bin/*</include>
+        <include>**/scripts/*</include>
+      </includes>
+      <fileMode>0755</fileMode>
+    </fileSet>
+  </fileSets>
+  <moduleSets>
+    <moduleSet>
+      <excludes>
+        <exclude>org.apache.hadoop:hadoop-yarn-server-tests</exclude>
+      </excludes>
+      <binaries>
+        <outputDirectory>modules</outputDirectory>
+        <includeDependencies>false</includeDependencies>
+        <unpack>false</unpack>
+      </binaries>
+    </moduleSet>
+  </moduleSets>
+  <dependencySets>
+    <dependencySet>
+      <useProjectArtifact>false</useProjectArtifact>
+      <outputDirectory>/lib</outputDirectory>
+      <!-- Exclude hadoop artifacts. They will be found via HADOOP* env -->
+      <excludes>
+        <exclude>org.apache.hadoop:hadoop-common</exclude>
+        <exclude>org.apache.hadoop:hadoop-hdfs</exclude>
+      </excludes>
+    </dependencySet>
+  </dependencySets>
+</assembly>

hadoop-common-project/hadoop-common/CHANGES.txt

@@ -956,6 +956,9 @@ Release 0.22.0 - Unreleased
 
     HADOOP-7624. Set things up for a top level hadoop-tools module. (tucu)
 
+    HADOOP-7642. create hadoop-dist module where TAR stitching would happen.
+    (Thomas White via tucu)
+
   OPTIMIZATIONS
 
     HADOOP-6884. Add LOG.isDebugEnabled() guard for each LOG.debug(..).

hadoop-dist/pom.xml

@@ -0,0 +1,144 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+  Licensed 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. See accompanying LICENSE file.
+-->
+<project>
+  <modelVersion>4.0.0</modelVersion>
+  <parent>
+    <groupId>org.apache.hadoop</groupId>
+    <artifactId>hadoop-project</artifactId>
+    <version>0.23.0-SNAPSHOT</version>
+    <relativePath>../hadoop-project</relativePath>
+  </parent>
+  <groupId>org.apache.hadoop</groupId>
+  <artifactId>hadoop-dist</artifactId>
+  <version>0.23.0-SNAPSHOT</version>
+  <description>Apache Hadoop Distribution</description>
+  <name>Apache Hadoop Distribution</name>
+  <packaging>jar</packaging>
+
+  <!-- Using dependencies to ensure this module is the last one -->
+  <dependencies>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-hdfs</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-mapreduce-client-app</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-yarn-api</artifactId>
+      <scope>provided</scope>
+    </dependency>
+  </dependencies>
+
+  <build>
+    <plugins>
+      <plugin>
+        <artifactId>maven-deploy-plugin</artifactId>
+        <configuration>
+          <skip>true</skip>
+        </configuration>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.rat</groupId>
+        <artifactId>apache-rat-plugin</artifactId>
+        <configuration>
+          <includes>
+            <include>pom.xml</include>
+          </includes>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
+
+  <profiles>
+    <profile>
+      <id>dist</id>
+      <activation>
+        <activeByDefault>false</activeByDefault>
+      </activation>
+      <build>
+        <plugins>
+          <plugin>
+            <groupId>org.apache.maven.plugins</groupId>
+            <artifactId>maven-antrun-plugin</artifactId>
+            <executions>
+              <execution>
+                <id>dist</id>
+                <phase>package</phase>
+                <goals>
+                  <goal>run</goal>
+                </goals>
+                <configuration>
+                  <target if="tar">
+                    <echo file="${project.build.directory}/dist-tar-stitching.sh">
+                      run() {
+                        echo "\$ ${@}"
+                        "${@}"
+                        if [ $? != 0 ]; then
+                          echo
+                          echo "Failed!"
+                          echo
+                          exit $?
+                        fi
+                      }
+
+                      ROOT=`cd ${basedir}/..;pwd`
+                      echo
+                      echo "Current directory `pwd`"
+                      echo
+                      run rm -rf hadoop-${project.version}
+                      run mkdir hadoop-${project.version}
+                      run cd hadoop-${project.version}
+                      run tar xzf $ROOT/hadoop-common-project/hadoop-common/target/hadoop-common-${project.version}.tar.gz --strip-components 1
+                      run tar xzf $ROOT/hadoop-hdfs-project/hadoop-hdfs/target/hadoop-hdfs-${project.version}.tar.gz --strip-components 1
+                      run tar xzf $ROOT/hadoop-mapreduce-project/target/hadoop-mapreduce-${project.version}.tar.gz --strip-components 1
+                      COMMON_LIB=share/hadoop/common/lib
+                      MODULES=../../../../modules
+                      run ln -s $MODULES/hadoop-mapreduce-client-app-${project.version}.jar $COMMON_LIB
+                      run ln -s $MODULES/hadoop-yarn-api-${project.version}.jar $COMMON_LIB
+                      run ln -s $MODULES/hadoop-mapreduce-client-common-${project.version}.jar $COMMON_LIB
+                      run ln -s $MODULES/hadoop-yarn-common-${project.version}.jar $COMMON_LIB
+                      run ln -s $MODULES/hadoop-mapreduce-client-core-${project.version}.jar $COMMON_LIB
+                      run ln -s $MODULES/hadoop-yarn-server-common-${project.version}.jar $COMMON_LIB
+                      run ln -s $MODULES/hadoop-mapreduce-client-jobclient-${project.version}.jar $COMMON_LIB
+                      run cd -
+                      run tar czf hadoop-${project.version}.tar.gz hadoop-${project.version}
+                      echo
+                      echo "Hadoop dist tar available at: ${project.build.directory}/hadoop-${project.version}.tar.gz"
+                      echo
+                    </echo>
+                    <exec executable="sh" dir="${project.build.directory}" failonerror="true">
+                      <arg line="./dist-tar-stitching.sh"/>
+                    </exec>
+                  </target>
+                </configuration>
+              </execution>
+            </executions>
+          </plugin>
+        </plugins>
+      </build>
+    </profile>
+  </profiles>
+
+</project>

hadoop-mapreduce-project/INSTALL

@@ -2,49 +2,31 @@ To compile  Hadoop Mapreduce next following, do the following:
 
 Step 1) Install dependencies for yarn
 
-See http://svn.apache.org/repos/asf/hadoop/common/trunk/hadoop-mapreduce/hadoop-yarn/README
+See http://svn.apache.org/repos/asf/hadoop/common/trunk/hadoop-mapreduce-porject/hadoop-yarn/README
 Make sure protbuf library is in your library path or set: export LD_LIBRARY_PATH=/usr/local/lib
 
 Step 2) Checkout
 
 svn checkout http://svn.apache.org/repos/asf/hadoop/common/trunk
 
-Step 3) Build common
+Step 3) Build
 
-Go to common directory - choose your regular common build command
-Example: mvn clean install package -Pbintar -DskipTests
+Go to common directory - choose your regular common build command. For example:
 
-Step 4) Build HDFS 
-
-Go to hdfs directory
-ant veryclean mvn-install -Dresolvers=internal 
-
-Step 5) Build yarn and mapreduce
-
-Go to mapreduce directory
 export MAVEN_OPTS=-Xmx512m
+mvn clean package -Pdist -Dtar -DskipTests -Pnative
 
-mvn clean install assembly:assembly -DskipTests
-
-Copy in build.properties if appropriate - make sure eclipse.home not set
-ant veryclean tar -Dresolvers=internal 
+You can omit -Pnative it you don't want to build native packages.
 
-You will see a tarball in
-ls target/hadoop-mapreduce-0.23.0-SNAPSHOT-all.tar.gz  
+Step 4) Untar the tarball from hadoop-dist/target/ into a clean and different
+directory, say YARN_HOME.
 
-Step 6) Untar the tarball in a clean and different directory.
-say YARN_HOME. 
-
-Make sure you aren't picking up avro-1.3.2.jar, remove:
-  $HADOOP_COMMON_HOME/share/hadoop/common/lib/avro-1.3.2.jar
-  $YARN_HOME/lib/avro-1.3.2.jar
-
-Step 7)
-Install hdfs/common and start hdfs
+Step 5)
+Start hdfs
 
 To run Hadoop Mapreduce next applications: 
 
-Step 8) export the following variables to where you have things installed:
+Step 6) export the following variables to where you have things installed:
 You probably want to export these in hadoop-env.sh and yarn-env.sh also.
 
 export HADOOP_MAPRED_HOME=<mapred loc>
@@ -54,7 +36,7 @@ export YARN_HOME=directory where you untarred yarn
 export HADOOP_CONF_DIR=<conf loc>
 export YARN_CONF_DIR=$HADOOP_CONF_DIR
 
-Step 9) Setup config: for running mapreduce applications, which now are in user land, you need to setup nodemanager with the following configuration in your yarn-site.xml before you start the nodemanager.
+Step 7) Setup config: for running mapreduce applications, which now are in user land, you need to setup nodemanager with the following configuration in your yarn-site.xml before you start the nodemanager.
     <property>
       <name>yarn.nodemanager.aux-services</name>
       <value>mapreduce.shuffle</value>
@@ -65,31 +47,21 @@ Step 9) Setup config: for running mapreduce applications, which now are in user
       <value>org.apache.hadoop.mapred.ShuffleHandler</value>
     </property>
 
-Step 10) Modify mapred-site.xml to use yarn framework
+Step 8) Modify mapred-site.xml to use yarn framework
     <property>    
       <name> mapreduce.framework.name</name>
       <value>yarn</value>  
     </property>
 
-Step 11) Create the following symlinks in $HADOOP_COMMON_HOME/share/hadoop/common/lib
-
-ln -s $YARN_HOME/modules/hadoop-mapreduce-client-app-0.23.0-SNAPSHOT.jar .	
-ln -s $YARN_HOME/modules/hadoop-yarn-api-0.23.0-SNAPSHOT.jar .
-ln -s $YARN_HOME/modules/hadoop-mapreduce-client-common-0.23.0-SNAPSHOT.jar .	
-ln -s $YARN_HOME/modules/hadoop-yarn-common-0.23.0-SNAPSHOT.jar .
-ln -s $YARN_HOME/modules/hadoop-mapreduce-client-core-0.23.0-SNAPSHOT.jar .	
-ln -s $YARN_HOME/modules/hadoop-yarn-server-common-0.23.0-SNAPSHOT.jar .
-ln -s $YARN_HOME/modules/hadoop-mapreduce-client-jobclient-0.23.0-SNAPSHOT.jar .
-
-Step 12) cd $YARN_HOME
+Step 9) cd $YARN_HOME
 
-Step 13) bin/yarn-daemon.sh start resourcemanager
+Step 10) bin/yarn-daemon.sh start resourcemanager
 
-Step 14) bin/yarn-daemon.sh start nodemanager
+Step 11) bin/yarn-daemon.sh start nodemanager
 
-Step 15) bin/yarn-daemon.sh start historyserver
+Step 12) bin/yarn-daemon.sh start historyserver
 
-Step 16) You are all set, an example on how to run a mapreduce job is:
+Step 13) You are all set, an example on how to run a mapreduce job is:
 cd $HADOOP_MAPRED_HOME
 ant examples -Dresolvers=internal 
 $HADOOP_COMMON_HOME/bin/hadoop jar $HADOOP_MAPRED_HOME/build/hadoop-mapreduce-examples-0.23.0-SNAPSHOT.jar randomwriter -Dmapreduce.job.user.name=$USER -Dmapreduce.clientfactory.class.name=org.apache.hadoop.mapred.YarnClientFactory -Dmapreduce.randomwriter.bytespermap=10000 -Ddfs.blocksize=536870912 -Ddfs.block.size=536870912 -libjars $YARN_HOME/modules/hadoop-mapreduce-client-jobclient-0.23.0-SNAPSHOT.jar output 

hadoop-mapreduce-project/assembly/all.xml

@@ -1,101 +0,0 @@
-<assembly xmlns="http://maven.apache.org/plugins/maven-assembly-plugin/assembly/1.1.0"
-  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-  xsi:schemaLocation="http://maven.apache.org/plugins/maven-assembly-plugin/assembly/1.1.0 http://maven.apache.org/xsd/assembly-1.1.0.xsd">
-  <id>all</id>
-  <formats>
-    <format>tar.gz</format>
-  </formats>
-  <includeBaseDirectory>true</includeBaseDirectory>
-  <!-- TODO: this layout is wrong. We need module specific bin files in module specific dirs -->
-  <fileSets>
-    <fileSet>
-      <directory>hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/c/container-executor</directory>
-      <outputDirectory>bin</outputDirectory>
-      <includes>
-        <include>container-executor</include>
-      </includes>
-      <fileMode>0755</fileMode>
-    </fileSet>
-    <fileSet>
-      <directory>hadoop-yarn/bin</directory>
-      <outputDirectory>bin</outputDirectory>
-      <includes>
-        <include>*</include>
-      </includes>
-      <fileMode>0755</fileMode>
-    </fileSet>
-    <fileSet>
-      <directory>bin</directory>
-      <outputDirectory>bin</outputDirectory>
-      <includes>
-        <include>*</include>
-      </includes>
-      <fileMode>0755</fileMode>
-    </fileSet>
-    <fileSet>
-      <directory>hadoop-yarn/conf</directory>
-      <outputDirectory>conf</outputDirectory>
-      <includes>
-        <include>**/*</include>
-      </includes>
-    </fileSet>
-    <fileSet>
-      <outputDirectory>sources</outputDirectory>
-      <excludes>
-        <exclude>**/*.jar</exclude>
-        <exclude>**/target/**</exclude>
-        <!-- scripts to include later for setting fileMode -->
-        <exclude>**/bin/*</exclude>
-        <exclude>**/scripts/*</exclude>
-        <!-- images that we don't need (and cause problems for our tools) -->
-        <exclude>**/dt-*/images/**</exclude>
-        <!-- until the code that does this is fixed -->
-        <exclude>**/file:/**</exclude>
-        <exclude>**/SecurityAuth.audit*</exclude>
-      </excludes>
-      <includes>
-        <include>assembly/**</include>
-        <include>pom.xml</include>
-        <include>build*.xml</include>
-        <include>ivy.xml</include>
-        <include>ivy/**</include>
-        <include>INSTALL</include>
-        <include>LICENSE.txt</include>
-        <include>mr-client/**</include>
-        <include>hadoop-yarn/**</include>
-        <include>src/**</include>
-      </includes>
-    </fileSet>
-    <fileSet>
-      <outputDirectory>sources</outputDirectory>
-      <includes>
-        <include>**/bin/*</include>
-        <include>**/scripts/*</include>
-      </includes>
-      <fileMode>0755</fileMode>
-    </fileSet>
-  </fileSets>
-  <moduleSets>
-    <moduleSet>
-      <excludes>
-        <exclude>org.apache.hadoop:hadoop-yarn-server-tests</exclude>
-      </excludes>
-      <binaries>
-        <outputDirectory>modules</outputDirectory>
-        <includeDependencies>false</includeDependencies>
-        <unpack>false</unpack>
-      </binaries>
-    </moduleSet>
-  </moduleSets>
-  <dependencySets>
-    <dependencySet>
-      <useProjectArtifact>false</useProjectArtifact>
-      <outputDirectory>/lib</outputDirectory>
-      <!-- Exclude hadoop artifacts. They will be found via HADOOP* env -->
-      <excludes>
-        <exclude>org.apache.hadoop:hadoop-common</exclude>
-        <exclude>org.apache.hadoop:hadoop-hdfs</exclude>
-      </excludes>
-    </dependencySet>
-  </dependencySets>
-</assembly>

hadoop-mapreduce-project/hadoop-yarn/pom.xml

@@ -25,6 +25,7 @@
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <test.logs>true</test.logs>
     <test.timeout>600000</test.timeout>
+    <hadoop.assemblies.version>${project.version}</hadoop.assemblies.version>
     <hadoop-common.version>0.23.0-SNAPSHOT</hadoop-common.version>
     <hadoop-hdfs.version>0.23.0-SNAPSHOT</hadoop-hdfs.version>
     <yarn.version>0.23.0-SNAPSHOT</yarn.version>
@@ -329,13 +330,33 @@
     </pluginManagement>
     <plugins>
       <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-assembly-plugin</artifactId>
+        <dependencies>
+          <dependency>
+            <groupId>org.apache.hadoop</groupId>
+            <artifactId>hadoop-assemblies</artifactId>
+            <version>${hadoop.assemblies.version}</version>
+          </dependency>
+        </dependencies>
         <configuration>
           <tarLongFileMode>gnu</tarLongFileMode>
-          <descriptors>
-            <descriptor>assembly/all.xml</descriptor>
-          </descriptors>
+          <appendAssemblyId>false</appendAssemblyId>
+          <attach>false</attach>
+          <finalName>${project.artifactId}-${project.version}</finalName>
+          <descriptorRefs>
+            <descriptorRef>hadoop-mapreduce-dist</descriptorRef>
+          </descriptorRefs>
         </configuration>
+        <executions>
+          <execution>
+            <id>tar</id>
+            <phase>package</phase>
+            <goals>
+              <goal>single</goal>
+            </goals>
+          </execution>
+        </executions>
       </plugin>
       <plugin>
         <artifactId>maven-antrun-plugin</artifactId>

hadoop-mapreduce-project/pom.xml

@@ -26,6 +26,7 @@
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <test.logs>true</test.logs>
     <test.timeout>600000</test.timeout>
+    <hadoop.assemblies.version>${project.version}</hadoop.assemblies.version>
     <hadoop-common.version>0.23.0-SNAPSHOT</hadoop-common.version>
     <hadoop-hdfs.version>0.23.0-SNAPSHOT</hadoop-hdfs.version>
     <hadoop-mapreduce.version>0.23.0-SNAPSHOT</hadoop-mapreduce.version>
@@ -325,13 +326,33 @@
         </executions>
       </plugin>
       <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-assembly-plugin</artifactId>
+        <dependencies>
+          <dependency>
+            <groupId>org.apache.hadoop</groupId>
+            <artifactId>hadoop-assemblies</artifactId>
+            <version>${hadoop.assemblies.version}</version>
+          </dependency>
+        </dependencies>
         <configuration>
           <tarLongFileMode>gnu</tarLongFileMode>
-          <descriptors>
-            <descriptor>assembly/all.xml</descriptor>
-          </descriptors>
+          <appendAssemblyId>false</appendAssemblyId>
+          <attach>false</attach>
+          <finalName>${project.artifactId}-${project.version}</finalName>
+          <descriptorRefs>
+            <descriptorRef>hadoop-mapreduce-dist</descriptorRef>
+          </descriptorRefs>
         </configuration>
+        <executions>
+          <execution>
+            <id>tar</id>
+            <phase>package</phase>
+            <goals>
+              <goal>single</goal>
+            </goals>
+          </execution>
+        </executions>
       </plugin>
       <plugin>
         <groupId>com.atlassian.maven.plugins</groupId>

hadoop-project/pom.xml

@@ -111,6 +111,21 @@
         <artifactId>hadoop-auth</artifactId>
         <version>${project.version}</version>
       </dependency>
+      <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-hdfs</artifactId>
+        <version>${project.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-mapreduce-client-app</artifactId>
+        <version>${project.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-yarn-api</artifactId>
+        <version>${project.version}</version>
+      </dependency>
 
       <dependency>
         <groupId>com.google.guava</groupId>

pom.xml

@@ -41,6 +41,7 @@
     <module>hadoop-hdfs-project</module>
     <module>hadoop-mapreduce-project</module>
     <module>hadoop-tools</module>
+    <module>hadoop-dist</module>
   </modules>
 
   <build>