MAPREDUCE-4649. Ensure MapReduce JobHistory Daemon doens't assume HADOOP_YARN_HOME and HADOOP_MAPRED_HOME are the same. Contributed by Vinod K V.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1390224 13f79535-47bb-0310-9956-ffa450edef68

hadoop-mapreduce-project/CHANGES.txt

@@ -339,6 +339,10 @@ Release 2.0.2-alpha - 2012-09-07
     MAPREDUCE-4380. Empty Userlogs directory is getting created under logs
     directory (Devaraj K via bobby)
 
+    MAPREDUCE-4649. Ensure MapReduce JobHistory Daemon doens't assume
+    HADOOP_YARN_HOME and HADOOP_MAPRED_HOME are the same. (vinodkv via
+    acmurthy)
+
 Release 2.0.0-alpha - 05-23-2012
 
   INCOMPATIBLE CHANGES

hadoop-mapreduce-project/INSTALL

@@ -19,7 +19,7 @@ mvn clean package -Pdist -Dtar -DskipTests -Pnative
 You can omit -Pnative it you don't want to build native packages.
 
 Step 4) Untar the tarball from hadoop-dist/target/ into a clean and different
-directory, say YARN_HOME.
+directory, say HADOOP_YARN_HOME.
 
 Step 5)
 Start hdfs
@@ -32,7 +32,7 @@ You probably want to export these in hadoop-env.sh and yarn-env.sh also.
 export HADOOP_MAPRED_HOME=<mapred loc>
 export HADOOP_COMMON_HOME=<common loc>
 export HADOOP_HDFS_HOME=<hdfs loc>
-export YARN_HOME=directory where you untarred yarn
+export HADOOP_YARN_HOME=directory where you untarred yarn
 export HADOOP_CONF_DIR=<conf loc>
 export YARN_CONF_DIR=$HADOOP_CONF_DIR
 
@@ -53,7 +53,7 @@ Step 8) Modify mapred-site.xml to use yarn framework
       <value>yarn</value>  
     </property>
 
-Step 9) cd $YARN_HOME
+Step 9) cd $HADOOP_YARN_HOME
 
 Step 10) sbin/yarn-daemon.sh start resourcemanager
 
@@ -64,7 +64,7 @@ Step 12) sbin/mr-jobhistory-daemon.sh start historyserver
 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 $HADOOP_MAPRED_HOME/build/hadoop-mapreduce-examples-*.jar randomwriter -Dmapreduce.job.user.name=$USER -Dmapreduce.randomwriter.bytespermap=10000 -Ddfs.blocksize=536870912 -Ddfs.block.size=536870912 -libjars $YARN_HOME/modules/hadoop-mapreduce-client-jobclient-*.jar output 
+$HADOOP_COMMON_HOME/bin/hadoop jar $HADOOP_MAPRED_HOME/build/hadoop-mapreduce-examples-*.jar randomwriter -Dmapreduce.job.user.name=$USER -Dmapreduce.randomwriter.bytespermap=10000 -Ddfs.blocksize=536870912 -Ddfs.block.size=536870912 -libjars $HADOOP_YARN_HOME/modules/hadoop-mapreduce-client-jobclient-*.jar output 
 
 The output on the command line should be almost similar to what you see in the JT/TT setup (Hadoop 0.20/0.21)
 

hadoop-mapreduce-project/bin/mapred

@@ -115,6 +115,11 @@ for f in $HADOOP_MAPRED_HOME/${MAPRED_DIR}/*.jar; do
   CLASSPATH=${CLASSPATH}:$f;
 done
 
+# Need YARN jars also
+for f in $HADOOP_YARN_HOME/${YARN_DIR}/*.jar; do
+  CLASSPATH=${CLASSPATH}:$f;
+done
+
 # add libs to CLASSPATH
 for f in $HADOOP_MAPRED_HOME/${MAPRED_LIB_JARS_DIR}/*.jar; do
   CLASSPATH=${CLASSPATH}:$f;

hadoop-mapreduce-project/bin/mapred-config.sh

@@ -38,3 +38,14 @@ else
   echo "Hadoop common not found."
   exit
 fi
+
+# some more specific variables
+export HADOOP_MAPRED_LOG_DIR=${HADOOP_MAPRED_LOG_DIR:-${HADOOP_MAPRED_HOME}/logs}
+export HADOOP_MAPRED_LOGFILE=${HADOOP_MAPRED_LOGFILE:-hadoop.log}
+
+HADOOP_MAPRED_ROOT_LOGGER=${HADOOP_MAPRED_ROOT_LOGGER:-INFO,console}
+HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_MAPRED_LOG_DIR"
+HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_MAPRED_LOGFILE"
+export HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_MAPRED_ROOT_LOGGER}"
+
+

hadoop-mapreduce-project/bin/mr-jobhistory-daemon.sh

@@ -16,22 +16,16 @@
 # limitations under the License.
 
 
-# Runs a yarn command as a daemon.
 #
 # Environment Variables
 #
-#   HADOOP_LOGFILE Hadoop log file.
-#   HADOOP_ROOT_LOGGER Hadoop root logger.
 #   HADOOP_JHS_LOGGER  Hadoop JobSummary logger.
-#   YARN_CONF_DIR  Alternate conf dir. Default is ${YARN_HOME}/conf.
-#   YARN_LOG_DIR   Where log files are stored.  PWD by default.
-#   YARN_MASTER    host:path where hadoop code should be rsync'd from
-#   YARN_PID_DIR   The pid files are stored. /tmp by default.
-#   YARN_IDENT_STRING   A string representing this instance of hadoop. $USER by default
-#   YARN_NICENESS The scheduling priority for daemons. Defaults to 0.
+#   HADOOP_CONF_DIR  Alternate conf dir. Default is ${HADOOP_MAPRED_HOME}/conf.
+#   HADOOP_MAPRED_PID_DIR   The pid files are stored. /tmp by default.
+#   HADOOP_MAPRED_NICENESS The scheduling priority for daemons. Defaults to 0.
 ##
 
-usage="Usage: mr-jobhistory-daemon.sh [--config <conf-dir>] [--hosts hostlistfile] (start|stop) <mapred-command> "
+usage="Usage: mr-jobhistory-daemon.sh [--config <conf-dir>] (start|stop) <mapred-command> "
 
 # if no args specified, show usage
 if [ $# -le 1 ]; then
@@ -42,10 +36,6 @@ fi
 bin=`dirname "${BASH_SOURCE-$0}"`
 bin=`cd "$bin"; pwd`
 
-DEFAULT_LIBEXEC_DIR="$bin"/../libexec
-HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
-. $HADOOP_LIBEXEC_DIR/yarn-config.sh
-
 # get arguments
 startStop=$1
 shift
@@ -69,43 +59,47 @@ hadoop_rotate_log ()
   fi
 }
 
-if [ -f "${YARN_CONF_DIR}/yarn-env.sh" ]; then
-  . "${YARN_CONF_DIR}/yarn-env.sh"
+if [ "$HADOOP_MAPRED_IDENT_STRING" = "" ]; then
+  export HADOOP_MAPRED_IDENT_STRING="$USER"
 fi
 
-if [ "$YARN_IDENT_STRING" = "" ]; then
-  export YARN_IDENT_STRING="$USER"
-fi
+export HADOOP_MAPRED_HOME=${HADOOP_MAPRED_HOME:-${HADOOP_PREFIX}}
+export HADOOP_MAPRED_LOGFILE=mapred-$HADOOP_MAPRED_IDENT_STRING-$command-$HOSTNAME.log
+export HADOOP_MAPRED_ROOT_LOGGER=${HADOOP_MAPRED_ROOT_LOGGER:-INFO,RFA}
+export HADOOP_JHS_LOGGER=${HADOOP_JHS_LOGGER:-INFO,JSA}
+
+DEFAULT_LIBEXEC_DIR="$bin"/../libexec
+HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
+. $HADOOP_LIBEXEC_DIR/mapred-config.sh
 
-# get log directory
-if [ "$YARN_LOG_DIR" = "" ]; then
-  export YARN_LOG_DIR="$YARN_HOME/logs"
+if [ -f "${HADOOP_CONF_DIR}/mapred-env.sh" ]; then
+  . "${HADOOP_CONF_DIR}/mapred-env.sh"
 fi
-mkdir -p "$YARN_LOG_DIR"
-chown $YARN_IDENT_STRING $YARN_LOG_DIR
 
-if [ "$YARN_PID_DIR" = "" ]; then
-  YARN_PID_DIR=/tmp
+mkdir -p "$HADOOP_MAPRED_LOG_DIR"
+chown $HADOOP_MAPRED_IDENT_STRING $HADOOP_MAPRED_LOG_DIR
+
+if [ "$HADOOP_MAPRED_PID_DIR" = "" ]; then
+  HADOOP_MAPRED_PID_DIR=/tmp
 fi
 
-# some variables
-export HADOOP_LOGFILE=yarn-$YARN_IDENT_STRING-$command-$HOSTNAME.log
-export HADOOP_ROOT_LOGGER=${HADOOP_ROOT_LOGGER:-INFO,RFA}
-export HADOOP_JHS_LOGGER=${HADOOP_JHS_LOGGER:-INFO,JSA}
-log=$YARN_LOG_DIR/yarn-$YARN_IDENT_STRING-$command-$HOSTNAME.out
-pid=$YARN_PID_DIR/yarn-$YARN_IDENT_STRING-$command.pid
-YARN_STOP_TIMEOUT=${YARN_STOP_TIMEOUT:-5}
+HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.id.str=$HADOOP_MAPRED_IDENT_STRING"
+
+log=$HADOOP_MAPRED_LOG_DIR/mapred-$HADOOP_MAPRED_IDENT_STRING-$command-$HOSTNAME.out
+pid=$HADOOP_MAPRED_PID_DIR/mapred-$HADOOP_MAPRED_IDENT_STRING-$command.pid
+
+HADOOP_MAPRED_STOP_TIMEOUT=${HADOOP_MAPRED_STOP_TIMEOUT:-5}
 
 # Set default scheduling priority
-if [ "$YARN_NICENESS" = "" ]; then
-  export YARN_NICENESS=0
+if [ "$HADOOP_MAPRED_NICENESS" = "" ]; then
+  export HADOOP_MAPRED_NICENESS=0
 fi
 
 case $startStop in
 
   (start)
 
-    mkdir -p "$YARN_PID_DIR"
+    mkdir -p "$HADOOP_MAPRED_PID_DIR"
 
     if [ -f $pid ]; then
       if kill -0 `cat $pid` > /dev/null 2>&1; then
@@ -114,15 +108,10 @@ case $startStop in
       fi
     fi
 
-    if [ "$YARN_MASTER" != "" ]; then
-      echo rsync from $YARN_MASTER
-      rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $YARN_MASTER/ "$YARN_HOME"
-    fi
-
     hadoop_rotate_log $log
     echo starting $command, logging to $log
-    cd "$YARN_HOME"
-    nohup nice -n $YARN_NICENESS "$YARN_HOME"/bin/mapred --config $YARN_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &
+    cd "$HADOOP_MAPRED_HOME"
+    nohup nice -n $HADOOP_MAPRED_NICENESS "$HADOOP_MAPRED_HOME"/bin/mapred --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &
     echo $! > $pid
     sleep 1; head "$log"
     ;;
@@ -134,9 +123,9 @@ case $startStop in
       if kill -0 $TARGET_PID > /dev/null 2>&1; then
         echo stopping $command
         kill $TARGET_PID
-        sleep $YARN_STOP_TIMEOUT
+        sleep $HADOOP_MAPRED_STOP_TIMEOUT
         if kill -0 $TARGET_PID > /dev/null 2>&1; then
-          echo "$command did not stop gracefully after $YARN_STOP_TIMEOUT seconds: killing with kill -9"
+          echo "$command did not stop gracefully after $HADOOP_MAPRED_STOP_TIMEOUT seconds: killing with kill -9"
           kill -9 $TARGET_PID
         fi
       else

hadoop-mapreduce-project/conf/mapred-env.sh

@@ -0,0 +1,27 @@
+# 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.
+
+# export JAVA_HOME=/home/y/libexec/jdk1.6.0/
+
+export HADOOP_JOB_HISTORYSERVER_HEAPSIZE=1000
+
+export HADOOP_MAPRED_ROOT_LOGGER=INFO,RFA
+
+#export HADOOP_JOB_HISTORYSERVER_OPTS=
+#export HADOOP_MAPRED_LOG_DIR="" # Where log files are stored.  $HADOOP_MAPRED_HOME/logs by default.
+#export HADOOP_JHS_LOGGER=INFO,RFA # Hadoop JobSummary logger.
+#export HADOOP_MAPRED_PID_DIR= # The pid files are stored. /tmp by default.
+#export HADOOP_MAPRED_IDENT_STRING= #A string representing this instance of hadoop. $USER by default
+#export HADOOP_MAPRED_NICENESS= #The scheduling priority for daemons. Defaults to 0.

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/resources/job_1329348432655_0001_conf.xml

@@ -102,7 +102,7 @@
 <property><!--Loaded from job.xml--><name>dfs.permissions.enabled</name><value>true</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.tasktracker.taskcontroller</name><value>org.apache.hadoop.mapred.DefaultTaskController</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.reduce.shuffle.parallelcopies</name><value>5</value></property>
-<property><!--Loaded from job.xml--><name>yarn.nodemanager.env-whitelist</name><value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,YARN_HOME</value></property>
+<property><!--Loaded from job.xml--><name>yarn.nodemanager.env-whitelist</name><value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,HADOOP_YARN_HOME</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.jobtracker.heartbeats.in.second</name><value>100</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.job.maxtaskfailures.per.tracker</name><value>4</value></property>
 <property><!--Loaded from job.xml--><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
@@ -317,8 +317,8 @@
         $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/*
+        $HADOOP_YARN_HOME/share/hadoop/mapreduce/*,
+        $HADOOP_YARN_HOME/share/hadoop/mapreduce/lib/*
      </value></property>
 <property><!--Loaded from job.xml--><name>yarn.nodemanager.log-aggregation.compression-type</name><value>gz</value></property>
 <property><!--Loaded from job.xml--><name>dfs.image.compress</name><value>false</value></property>