MAPREDUCE-3696. MR job via oozie does not work on hadoop 23. (John George via mahadev) - Merging r1239310 from trunk.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-0.23@1239312 13f79535-47bb-0310-9956-ffa450edef68

hadoop-common-project/hadoop-common/src/main/bin/hadoop-config.sh

@@ -20,6 +20,16 @@
 # Resolve links ($0 may be a softlink) and convert a relative path
 # to an absolute path.  NB: The -P option requires bash built-ins
 # or POSIX:2001 compliant cd and pwd.
+
+#   HADOOP_CLASSPATH Extra Java CLASSPATH entries.
+#
+#   HADOOP_USER_CLASSPATH_FIRST      When defined, the HADOOP_CLASSPATH is 
+#                                    added in the beginning of the global
+#                                    classpath. Can be defined, for example,
+#                                    by doing 
+#                                    export HADOOP_USER_CLASSPATH_FIRST=true
+#
+
 this="${BASH_SOURCE-$0}"
 common_bin=$(cd -P -- "$(dirname -- "$this")" && pwd -P)
 script="$(basename -- "$this")"
@@ -153,6 +163,10 @@ fi
 # CLASSPATH initially contains $HADOOP_CONF_DIR
 CLASSPATH="${HADOOP_CONF_DIR}"
 
+if [ "$HADOOP_USER_CLASSPATH_FIRST" != "" ] && [ "$HADOOP_CLASSPATH" != "" ] ; then
+  CLASSPATH=${CLASSPATH}:${HADOOP_CLASSPATH}
+fi
+
 # so that filenames w/ spaces are handled correctly in loops below
 IFS=
 
@@ -174,7 +188,7 @@ fi
 CLASSPATH=${CLASSPATH}:$HADOOP_COMMON_HOME/$HADOOP_COMMON_DIR'/*'
 
 # add user-specified CLASSPATH last
-if [ "$HADOOP_CLASSPATH" != "" ]; then
+if [ "$HADOOP_USER_CLASSPATH_FIRST" = "" ] && [ "$HADOOP_CLASSPATH" != "" ]; then
   CLASSPATH=${CLASSPATH}:${HADOOP_CLASSPATH}
 fi
 

hadoop-mapreduce-project/CHANGES.txt

@@ -597,6 +597,9 @@ Release 0.23.1 - Unreleased
     MAPREDUCE-3499. New MiniMR does not setup proxyuser configuration 
     correctly, thus tests using doAs do not work. (johnvijoe via tucu)
 
+    MAPREDUCE-3696. MR job via oozie does not work on hadoop 23.
+    (John George via mahadev)
+
 Release 0.23.0 - 2011-11-01 
 
   INCOMPATIBLE CHANGES

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

@@ -227,15 +227,23 @@ public class MRApps extends Apps {
   
   public static void setClasspath(Map<String, String> environment,
       Configuration conf) throws IOException {
+    boolean userClassesTakesPrecedence = 
+      conf.getBoolean(MRJobConfig.MAPREDUCE_JOB_USER_CLASSPATH_FIRST, false);
+
+    if (!userClassesTakesPrecedence) {
+      MRApps.setMRFrameworkClasspath(environment, conf);
+    }
     Apps.addToEnvironment(
-        environment, 
-        Environment.CLASSPATH.name(), 
+        environment,
+        Environment.CLASSPATH.name(),
         MRJobConfig.JOB_JAR);
     Apps.addToEnvironment(
-        environment, 
+        environment,
         Environment.CLASSPATH.name(),
         Environment.PWD.$() + Path.SEPARATOR + "*");
-    MRApps.setMRFrameworkClasspath(environment, conf);
+    if (userClassesTakesPrecedence) {
+      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

@@ -130,13 +130,43 @@ public class TestMRApps {
     Job job = Job.getInstance();
     Map<String, String> environment = new HashMap<String, String>();
     MRApps.setClasspath(environment, job.getConfiguration());
-    assertEquals("job.jar:$PWD/*:$HADOOP_CONF_DIR:" +
+    assertEquals("$HADOOP_CONF_DIR:" +
         "$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/*:" +
-        "$YARN_HOME/share/hadoop/mapreduce/lib/*",
+        "$YARN_HOME/share/hadoop/mapreduce/lib/*:" +
+        "job.jar:$PWD/*",
         environment.get("CLASSPATH"));
   }
+
+ @Test public void testSetClasspathWithUserPrecendence() {
+    Configuration conf = new Configuration();
+    conf.setBoolean(MRJobConfig.MAPREDUCE_JOB_USER_CLASSPATH_FIRST, true);
+    Map<String, String> env = new HashMap<String, String>();
+    try {
+      MRApps.setClasspath(env, conf);
+    } catch (Exception e) {
+      fail("Got exception while setting classpath");
+    }
+    String env_str = env.get("CLASSPATH");
+    assertSame("MAPREDUCE_JOB_USER_CLASSPATH_FIRST set, but not taking effect!",
+      env_str.indexOf("job.jar"), 0);
+  }
+
+  @Test public void testSetClasspathWithNoUserPrecendence() {
+    Configuration conf = new Configuration();
+    conf.setBoolean(MRJobConfig.MAPREDUCE_JOB_USER_CLASSPATH_FIRST, false);
+    Map<String, String> env = new HashMap<String, String>();
+    try {
+      MRApps.setClasspath(env, conf);
+    } catch (Exception e) {
+      fail("Got exception while setting classpath");
+    }
+    String env_str = env.get("CLASSPATH");
+    assertNotSame("MAPREDUCE_JOB_USER_CLASSPATH_FIRST false, but taking effect!",
+      env_str.indexOf("job.jar"), 0);
+  }
+
 }

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java

@@ -118,6 +118,8 @@ public interface MRJobConfig {
 
   public static final String USER_LOG_RETAIN_HOURS = "mapreduce.job.userlog.retain.hours";
 
+  public static final String MAPREDUCE_JOB_USER_CLASSPATH_FIRST = "mapreduce.job.user.classpath.first";
+
   public static final String IO_SORT_FACTOR = "mapreduce.task.io.sort.factor";
 
   public static final String IO_SORT_MB = "mapreduce.task.io.sort.mb";

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

@@ -408,7 +408,7 @@ public class YARNRunner implements ClientProtocol {
         + mergedCommand);
 
     // Setup the CLASSPATH in environment
-    // i.e. add { job jar, CWD, Hadoop jars} to classpath.
+    // i.e. add { Hadoop jars, job jar, CWD } to classpath.
     Map<String, String> environment = new HashMap<String, String>();
     MRApps.setClasspath(environment, conf);