hadoop/bin/hadoop

#!/bin/bash
# 
# The Hadoop command script
#
# Environment Variables
#
#   JAVA_HOME        The java implementation to use.  Overrides JAVA_HOME.
#
#   HADOOP_HEAPSIZE  The maximum amount of heap to use, in MB. 
#                    Default is 1000.
#
#   HADOOP_OPTS      Extra Java runtime options.
#
#   HADOOP_CONF_DIR  Alternate conf dir. Default is ${HADOOP_HOME}/conf.
#
#   HADOOP_ROOT_LOGGER The root appender. Default is INFO,console
#

# resolve links - $0 may be a softlink
THIS="$0"
while [ -h "$THIS" ]; do
  ls=`ls -ld "$THIS"`
  link=`expr "$ls" : '.*-> \(.*\)$'`
  if expr "$link" : '.*/.*' > /dev/null; then
    THIS="$link"
  else
    THIS=`dirname "$THIS"`/"$link"
  fi
done

# if no args specified, show usage
if [ $# = 0 ]; then
  echo "Usage: hadoop COMMAND"
  echo "where COMMAND is one of:"
  echo "  namenode -format  format the DFS filesystem"
  echo "  namenode          run the DFS namenode"
  echo "  datanode          run a DFS datanode"
  echo "  dfs               run a DFS admin client"
  echo "  fsck              run a DFS filesystem checking utility"
  echo "  jobtracker        run the MapReduce job Tracker node" 
  echo "  tasktracker       run a MapReduce task Tracker node" 
  echo "  job               manipulate MapReduce jobs" 
  echo "  jar <jar>         run a jar file"
  echo "  distcp <srcurl> <desturl> copy file or directories recursively"
  echo " or"
  echo "  CLASSNAME         run the class named CLASSNAME"
  echo "Most commands print help when invoked w/o parameters."
  exit 1
fi

# get arguments
COMMAND=$1
shift

# some directories
THIS_DIR=`dirname "$THIS"`
export HADOOP_HOME=`cd "$THIS_DIR/.." ; pwd`

# Allow alternate conf dir location.
HADOOP_CONF_DIR="${HADOOP_CONF_DIR:-$HADOOP_HOME/conf}"

if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
  source "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi

# some Java parameters
if [ "$JAVA_HOME" != "" ]; then
  #echo "run java in $JAVA_HOME"
  JAVA_HOME=$JAVA_HOME
fi
  
if [ "$JAVA_HOME" = "" ]; then
  echo "Error: JAVA_HOME is not set."
  exit 1
fi

JAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m 

# check envvars which might override default args
if [ "$HADOOP_HEAPSIZE" != "" ]; then
  #echo "run with heapsize $HADOOP_HEAPSIZE"
  JAVA_HEAP_MAX="-Xmx""$HADOOP_HEAPSIZE""m"
  #echo $JAVA_HEAP_MAX
fi

# CLASSPATH initially contains $HADOOP_CONF_DIR
CLASSPATH="${HADOOP_CONF_DIR}"
CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar

# for developers, add Hadoop classes to CLASSPATH
if [ -d "$HADOOP_HOME/build/classes" ]; then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/classes
fi
if [ -d "$HADOOP_HOME/build/webapps" ]; then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build
fi
if [ -d "$HADOOP_HOME/build/test/classes" ]; then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/test/classes
fi

# so that filenames w/ spaces are handled correctly in loops below
IFS=

# for releases, add hadoop jars & webapps to CLASSPATH
if [ -d "$HADOOP_HOME/webapps" ]; then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME
fi
for f in $HADOOP_HOME/hadoop-*.jar; do
  CLASSPATH=${CLASSPATH}:$f;
done

# add libs to CLASSPATH
for f in $HADOOP_HOME/lib/*.jar; do
  CLASSPATH=${CLASSPATH}:$f;
done

for f in $HADOOP_HOME/lib/jetty-ext/*.jar; do
  CLASSPATH=${CLASSPATH}:$f;
done

# restore ordinary behaviour
unset IFS

# default log directory & file
if [ "$HADOOP_LOG_DIR" = "" ]; then
  HADOOP_LOG_DIR="$HADOOP_HOME/logs"
fi
if [ "$HADOOP_LOGFILE" = "" ]; then
  HADOOP_LOGFILE='hadoop.log'
fi

# figure out which class to run
if [ "$COMMAND" = "namenode" ] ; then
  CLASS='org.apache.hadoop.dfs.NameNode'
elif [ "$COMMAND" = "datanode" ] ; then
  CLASS='org.apache.hadoop.dfs.DataNode'
elif [ "$COMMAND" = "dfs" ] ; then
  CLASS=org.apache.hadoop.dfs.DFSShell
elif [ "$COMMAND" = "fsck" ] ; then
  CLASS=org.apache.hadoop.dfs.DFSck
elif [ "$COMMAND" = "jobtracker" ] ; then
  CLASS=org.apache.hadoop.mapred.JobTracker
elif [ "$COMMAND" = "tasktracker" ] ; then
  CLASS=org.apache.hadoop.mapred.TaskTracker
elif [ "$COMMAND" = "job" ] ; then
  CLASS=org.apache.hadoop.mapred.JobClient
elif [ "$COMMAND" = "jar" ] ; then
  CLASS=org.apache.hadoop.util.RunJar
elif [ "$COMMAND" = "distcp" ] ; then
  CLASS=org.apache.hadoop.util.CopyFiles
else
  CLASS=$COMMAND
fi

# cygwin path translation
if expr `uname` : 'CYGWIN*' > /dev/null; then
  CLASSPATH=`cygpath -p -w "$CLASSPATH"`
  HADOOP_HOME=`cygpath -d "$HADOOP_HOME"`
  HADOOP_LOG_DIR=`cygpath -d "$HADOOP_LOG_DIR"`
fi

HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_LOG_DIR"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_LOGFILE"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.home.dir=$HADOOP_HOME"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.id.str=$HADOOP_IDENT_STRING"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_ROOT_LOGGER:-INFO,console}"

# run it
exec "$JAVA" $JAVA_HEAP_MAX $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"