MAPREDUCE-3505. yarn APPLICATION_CLASSPATH needs to be overridable. (ahmed via tucu)

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1235391 13f79535-47bb-0310-9956-ffa450edef68

hadoop-mapreduce-project/CHANGES.txt

@@ -540,6 +540,9 @@ Release 0.23.1 - Unreleased
 
     MAPREDUCE-3681. Fixed computation of queue's usedCapacity. (acmurthy) 
 
+    MAPREDUCE-3505. yarn APPLICATION_CLASSPATH needs to be overridable. 
+    (ahmed via tucu)
+
 Release 0.23.0 - 2011-11-01 
 
   INCOMPATIBLE CHANGES

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java

@@ -522,13 +522,13 @@ public abstract class TaskAttemptImpl implements
    * a parent CLC and use it for all the containers, so this should go away
    * once the mr-generated-classpath stuff is gone.
    */
-  private static String getInitialClasspath() throws IOException {
+  private static String getInitialClasspath(Configuration conf) throws IOException {
     synchronized (classpathLock) {
       if (initialClasspathFlag.get()) {
         return initialClasspath;
       }
       Map<String, String> env = new HashMap<String, String>();
-      MRApps.setClasspath(env);
+      MRApps.setClasspath(env, conf);
       initialClasspath = env.get(Environment.CLASSPATH.name());
       initialClasspathFlag.set(true);
       return initialClasspath;
@@ -631,7 +631,7 @@ public abstract class TaskAttemptImpl implements
       Apps.addToEnvironment(
           environment,  
           Environment.CLASSPATH.name(), 
-          getInitialClasspath());
+          getInitialClasspath(conf));
     } catch (IOException e) {
       throw new YarnException(e);
     }

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/pom.xml

@@ -38,6 +38,10 @@
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-mapreduce-client-core</artifactId>
     </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-yarn-server-common</artifactId>
+    </dependency>
   </dependencies>
 
   <build>

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/src/main/java/org/apache/hadoop/mapreduce/v2/util/MRApps.java

@@ -54,6 +54,7 @@ import org.apache.hadoop.yarn.api.records.ApplicationId;
 import org.apache.hadoop.yarn.api.records.LocalResource;
 import org.apache.hadoop.yarn.api.records.LocalResourceType;
 import org.apache.hadoop.yarn.api.records.LocalResourceVisibility;
+import org.apache.hadoop.yarn.conf.YarnConfiguration;
 import org.apache.hadoop.yarn.factory.providers.RecordFactoryProvider;
 import org.apache.hadoop.yarn.util.Apps;
 import org.apache.hadoop.yarn.util.BuilderUtils;
@@ -171,7 +172,7 @@ public class MRApps extends Apps {
   }
 
   private static void setMRFrameworkClasspath(
-      Map<String, String> environment) throws IOException {
+      Map<String, String> environment, Configuration conf) throws IOException {
     InputStream classpathFileStream = null;
     BufferedReader reader = null;
     try {
@@ -208,8 +209,10 @@ public class MRApps extends Apps {
       }
 
       // Add standard Hadoop classes
-      for (String c : ApplicationConstants.APPLICATION_CLASSPATH) {
+      for (String c : conf.get(YarnConfiguration.YARN_APPLICATION_CLASSPATH)
-        Apps.addToEnvironment(environment, Environment.CLASSPATH.name(), c);
+          .split(",")) {
+        Apps.addToEnvironment(environment, Environment.CLASSPATH.name(), c
+            .trim());
       }
     } finally {
       if (classpathFileStream != null) {
@@ -222,8 +225,8 @@ public class MRApps extends Apps {
     // TODO: Remove duplicates.
   }
   
-  public static void setClasspath(Map<String, String> environment) 
+  public static void setClasspath(Map<String, String> environment,
-      throws IOException {
+      Configuration conf) throws IOException {
     Apps.addToEnvironment(
         environment, 
         Environment.CLASSPATH.name(), 
@@ -232,7 +235,7 @@ public class MRApps extends Apps {
         environment, 
         Environment.CLASSPATH.name(),
         Environment.PWD.$() + Path.SEPARATOR + "*");
-    MRApps.setMRFrameworkClasspath(environment);
+    MRApps.setMRFrameworkClasspath(environment, conf);
   }
   
   private static final String STAGING_CONSTANT = ".staging";

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/src/test/java/org/apache/hadoop/mapreduce/v2/util/TestMRApps.java

@@ -18,7 +18,12 @@
 
 package org.apache.hadoop.mapreduce.v2.util;
 
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
+
 import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.mapreduce.Job;
 import org.apache.hadoop.mapreduce.JobID;
 import org.apache.hadoop.mapreduce.MRJobConfig;
 import org.apache.hadoop.mapreduce.v2.api.records.JobId;
@@ -121,4 +126,17 @@ public class TestMRApps {
         "/my/path/to/staging/dummy-user/.staging/job_dummy-job_12345/job.xml", jobFile);
   }
 
+  @Test public void testSetClasspath() throws IOException {
+    Job job = Job.getInstance();
+    Map<String, String> environment = new HashMap<String, String>();
+    MRApps.setClasspath(environment, job.getConfiguration());
+    assertEquals("job.jar:$PWD/*:$HADOOP_CONF_DIR:" +
+        "$HADOOP_COMMON_HOME/share/hadoop/common/*:" +
+        "$HADOOP_COMMON_HOME/share/hadoop/common/lib/*:" +
+        "$HADOOP_HDFS_HOME/share/hadoop/hdfs/*:" +
+        "$HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*:" +
+        "$YARN_HOME/share/hadoop/mapreduce/*:" +
+        "$YARN_HOME/share/hadoop/mapreduce/lib/*",
+        environment.get("CLASSPATH"));
+  }
 }

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java

@@ -406,7 +406,7 @@ public class YARNRunner implements ClientProtocol {
     // Setup the CLASSPATH in environment
     // i.e. add { job jar, CWD, Hadoop jars} to classpath.
     Map<String, String> environment = new HashMap<String, String>();
-    MRApps.setClasspath(environment);
+    MRApps.setClasspath(environment, conf);
 
     // Parse distributed cache
     MRApps.setupDistributedCache(jobConf, localResources);

hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-api/src/main/java/org/apache/hadoop/yarn/api/ApplicationConstants.java

@@ -84,21 +84,7 @@ public interface ApplicationConstants {
   public static final String STDERR = "stderr";
 
   public static final String STDOUT = "stdout";
-  
+
-  /**
-   * Classpath for typical applications.
-   */
-  public static final String[] APPLICATION_CLASSPATH =
-      new String[] {
-        "$HADOOP_CONF_DIR",
-        "$HADOOP_COMMON_HOME/share/hadoop/common/*",
-        "$HADOOP_COMMON_HOME/share/hadoop/common/lib/*",
-        "$HADOOP_HDFS_HOME/share/hadoop/hdfs/*",
-        "$HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*",
-        "$YARN_HOME/share/hadoop/mapreduce/*",
-        "$YARN_HOME/share/hadoop/mapreduce/lib/*"
-      };
-  
   /**
    * Environment for Applications.
    * 

hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-common/src/main/java/org/apache/hadoop/yarn/conf/YarnConfiguration.java

@@ -508,6 +508,10 @@ public class YarnConfiguration extends Configuration {
   public static final long DEFAULT_NM_PROCESS_KILL_WAIT_MS =
       2000;
 
+  /** Standard Hadoop classes */
+  public static final String YARN_APPLICATION_CLASSPATH = YARN_PREFIX
+      + "application.classpath";
+
   public YarnConfiguration() {
     super();
   }

hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-common/src/main/resources/yarn-default.xml

@@ -482,4 +482,18 @@
      <name>yarn.web-proxy.address</name>
      <value/>
   </property>
+
+  <property>
+    <description>Classpath for typical applications.</description>
+     <name>yarn.application.classpath</name>
+     <value>
+        $HADOOP_CONF_DIR,
+        $HADOOP_COMMON_HOME/share/hadoop/common/*,
+        $HADOOP_COMMON_HOME/share/hadoop/common/lib/*,
+        $HADOOP_HDFS_HOME/share/hadoop/hdfs/*,
+        $HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*,
+        $YARN_HOME/share/hadoop/mapreduce/*,
+        $YARN_HOME/share/hadoop/mapreduce/lib/*
+     </value>
+  </property>
 </configuration>