hadoop源码剖析--$HADOOP_HOME/bin/hadoop脚本文件分析

时间:2022-05-20 08:35:47

1. $HADOOP_HOME/bin/ hadoop 

 

#!/usr/bin/env bash# 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.# The Hadoop command script## Environment Variables##   JAVA_HOME        The java implementation to use.  Overrides JAVA_HOME.##   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##   HADOOP_HEAPSIZE  The maximum amount of heap to use, in MB. #                    Default is 1000.##   HADOOP_OPTS      Extra Java runtime options.#   #   HADOOP_NAMENODE_OPTS       These options are added to HADOOP_OPTS  #   HADOOP_CLIENT_OPTS         when the respective command is run.#   HADOOP_{COMMAND}_OPTS etc  HADOOP_JT_OPTS applies to JobTracker #                              for e.g.  HADOOP_CLIENT_OPTS applies to #                              more than one command (fs, dfs, fsck, #                              dfsadmin etc)  ##   HADOOP_CONF_DIR  Alternate conf dir. Default is ${HADOOP_HOME}/conf.##   HADOOP_ROOT_LOGGER The root appender. Default is INFO,console#

bin=`dirname "$0"`//(1)获取$HADOOP_HOME/hadoop/bin所在目录
bin=`cd "$bin"; pwd`//(2)进入到$HADOOP_HOME/bin/hadoop/bin目录if[-e "$bin"/../libexec/hadoop-config.sh ];then//(3)执行hadoop-config.sh进行,进行配置设置."$bin"/../libexec/hadoop-config.sh
else."$bin"/hadoop-config.sh
fi

cygwin=falsecase"`uname`"in
CYGWIN*) cygwin=true;;esac# if no args specified, show usageif[ $# = 0 ]; then
  echo "Usage: hadoop [--config confdir] COMMAND"
  echo "where COMMAND is one of:"
  echo "  namenode -format     format the DFS filesystem"
  echo "  secondarynamenode    run the DFS secondary namenode"
  echo "  namenode             run the DFS namenode"
  echo "  datanode             run a DFS datanode"
  echo "  dfsadmin             run a DFS admin client"
  echo "  mradmin              run a Map-Reduce admin client"
  echo "  fsck                 run a DFS filesystem checking utility"
  echo "  fs                   run a generic filesystem user client"
  echo "  balancer             run a cluster balancing utility"
  echo "  fetchdt              fetch a delegation token from the NameNode"
  echo "  jobtracker           run the MapReduce job Tracker node" 
  echo "  pipes                run a Pipes job"
  echo "  tasktracker          run a MapReduce task Tracker node" 
  echo "  historyserver        run job history servers as a standalone daemon"
  echo "  job                  manipulate MapReduce jobs"
  echo "  queue                get information regarding JobQueues" 
  echo "  version              print the version"
  echo "  jar <jar>            run a jar file"
  echo "  distcp <srcurl> <desturl> copy file or directories recursively"
  echo "  archive -archiveName NAME -p <parent path> <src>* <dest> create a hadoop archive"
  echo "  classpath            prints the class path needed to get the"
  echo "                       Hadoop jar and the required libraries"
  echo "  daemonlog            get/set the log level for each daemon"
  echo " or"
  echo "  CLASSNAME            run the class named CLASSNAME"
  echo "Most commands print help when invoked w/o parameters."exit1fi# get arguments
COMMAND=$1
shift

# Determine if we're starting a secure datanode, and if so, redefine appropriate variablesif["$COMMAND"=="datanode"]&&["$EUID"-eq 0]&&[-n "$HADOOP_SECURE_DN_USER"];then
  HADOOP_PID_DIR=$HADOOP_SECURE_DN_PID_DIR
  HADOOP_LOG_DIR=$HADOOP_SECURE_DN_LOG_DIR
  HADOOP_IDENT_STRING=$HADOOP_SECURE_DN_USER
  starting_secure_dn="true"fi# some Java parametersif["$JAVA_HOME"!=""];then#echo "run java in $JAVA_HOME"
  JAVA_HOME=$JAVA_HOME
fiif["$JAVA_HOME"=""];then
  echo "Error: JAVA_HOME is not set."exit1fi

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_MAXfi# CLASSPATH initially contains $HADOOP_CONF_DIR		//(3)设置CLASSPATH
CLASSPATH="${HADOOP_CONF_DIR}"if["$HADOOP_USER_CLASSPATH_FIRST"!=""]&&["$HADOOP_CLASSPATH"!=""];then
  CLASSPATH=${CLASSPATH}:${HADOOP_CLASSPATH}fi
CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar

# for developers, add Hadoop classes to CLASSPATHif[-d "$HADOOP_HOME/build/classes"];then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/classes
fiif[-d "$HADOOP_HOME/build/webapps"];then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build
fiif[-d "$HADOOP_HOME/build/test/classes"];then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/test/classes
fiif[-d "$HADOOP_HOME/build/tools"];then
  CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/tools
fi# so that filenames w/ spaces are handled correctly in loops below
IFS=# for releases, add core hadoop jar & webapps to CLASSPATHif[-e $HADOOP_PREFIX/share/hadoop/hadoop-core-*];then# binary layoutif[-d "$HADOOP_PREFIX/share/hadoop/webapps"];then
    CLASSPATH=${CLASSPATH}:$HADOOP_PREFIX/share/hadoop
  fifor f in $HADOOP_PREFIX/share/hadoop/hadoop-core-*.jar;do
    CLASSPATH=${CLASSPATH}:$f;done# add libs to CLASSPATHfor f in $HADOOP_PREFIX/share/hadoop/lib/*.jar; do
    CLASSPATH=${CLASSPATH}:$f;
  done

  for f in $HADOOP_PREFIX/share/hadoop/lib/jsp-2.1/*.jar; do
    CLASSPATH=${CLASSPATH}:$f;
  done

  for f in $HADOOP_PREFIX/share/hadoop/hadoop-tools-*.jar; do
    TOOL_PATH=${TOOL_PATH}:$f;
  done
else
  # tarball layout
  if [ -d "$HADOOP_HOME/webapps" ]; then
    CLASSPATH=${CLASSPATH}:$HADOOP_HOME
  fi
  for f in $HADOOP_HOME/hadoop-core-*.jar; do
    CLASSPATH=${CLASSPATH}:$f;
  done

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

  if [ -d "$HADOOP_HOME/build/ivy/lib/Hadoop/common" ]; then
    for f in $HADOOP_HOME/build/ivy/lib/Hadoop/common/*.jar; do
      CLASSPATH=${CLASSPATH}:$f;
    done
  fi

  for f in $HADOOP_HOME/lib/jsp-2.1/*.jar; do
    CLASSPATH=${CLASSPATH}:$f;
  done

  for f in $HADOOP_HOME/hadoop-tools-*.jar; do
    TOOL_PATH=${TOOL_PATH}:$f;
  done
  for f in $HADOOP_HOME/build/hadoop-tools-*.jar; do
    TOOL_PATH=${TOOL_PATH}:$f;
  done
fi

# add user-specified CLASSPATH last
if [ "$HADOOP_USER_CLASSPATH_FIRST" = "" ] && [ "$HADOOP_CLASSPATH" != "" ]; then
  CLASSPATH=${CLASSPATH}:${HADOOP_CLASSPATH}
fi

# 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

# default policy file for service-level authorization
if [ "$HADOOP_POLICYFILE" = "" ]; then
  HADOOP_POLICYFILE="hadoop-policy.xml"
fi

# restore ordinary behaviour
unset IFS

# figure out which class to run		//(4)根据不同命令确定CLASS
if [ "$COMMAND" = "classpath" ] ; then
  if $cygwin; then
    CLASSPATH=`cygpath -p -w "$CLASSPATH"`
  fi
  echo $CLASSPATH
  exit
elif [ "$COMMAND" = "namenode" ] ; then
  CLASS='org.apache.hadoop.hdfs.server.namenode.NameNode'
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_NAMENODE_OPTS"
elif [ "$COMMAND" = "secondarynamenode" ] ; then
  CLASS='org.apache.hadoop.hdfs.server.namenode.SecondaryNameNode'
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_SECONDARYNAMENODE_OPTS"
elif [ "$COMMAND" = "datanode" ] ; then
  CLASS='org.apache.hadoop.hdfs.server.datanode.DataNode'
  if [ "$starting_secure_dn" = "true" ]; then
    HADOOP_OPTS="$HADOOP_OPTS -jvm server $HADOOP_DATANODE_OPTS"
  else
    HADOOP_OPTS="$HADOOP_OPTS -server $HADOOP_DATANODE_OPTS"
  fi
elif [ "$COMMAND" = "fs" ] ; then
  CLASS=org.apache.hadoop.fs.FsShell
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "dfs" ] ; then
  CLASS=org.apache.hadoop.fs.FsShell
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "dfsadmin" ] ; then
  CLASS=org.apache.hadoop.hdfs.tools.DFSAdmin
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "mradmin" ] ; then
  CLASS=org.apache.hadoop.mapred.tools.MRAdmin
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "fsck" ] ; then
  CLASS=org.apache.hadoop.hdfs.tools.DFSck
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "balancer" ] ; then
  CLASS=org.apache.hadoop.hdfs.server.balancer.Balancer
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_BALANCER_OPTS"
elif [ "$COMMAND" = "fetchdt" ] ; then
  CLASS=org.apache.hadoop.hdfs.tools.DelegationTokenFetcher
elif [ "$COMMAND" = "jobtracker" ] ; then
  CLASS=org.apache.hadoop.mapred.JobTracker
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_JOBTRACKER_OPTS"
elif [ "$COMMAND" = "historyserver" ] ; then
  CLASS=org.apache.hadoop.mapred.JobHistoryServer
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_JOB_HISTORYSERVER_OPTS"
elif [ "$COMMAND" = "tasktracker" ] ; then
  CLASS=org.apache.hadoop.mapred.TaskTracker
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_TASKTRACKER_OPTS"
elif [ "$COMMAND" = "job" ] ; then
  CLASS=org.apache.hadoop.mapred.JobClient
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "queue" ] ; then
  CLASS=org.apache.hadoop.mapred.JobQueueClient
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "pipes" ] ; then
  CLASS=org.apache.hadoop.mapred.pipes.Submitter
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "version" ] ; then
  CLASS=org.apache.hadoop.util.VersionInfo
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "jar" ] ; then
  CLASS=org.apache.hadoop.util.RunJar
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "distcp" ] ; then
  CLASS=org.apache.hadoop.tools.DistCp
  CLASSPATH=${CLASSPATH}:${TOOL_PATH}
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "daemonlog" ] ; then
  CLASS=org.apache.hadoop.log.LogLevel
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "archive" ] ; then
  CLASS=org.apache.hadoop.tools.HadoopArchives
  CLASSPATH=${CLASSPATH}:${TOOL_PATH}
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "sampler" ] ; then
  CLASS=org.apache.hadoop.mapred.lib.InputSampler
  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
else
  CLASS=$COMMAND
fi

# cygwin path translation
if $cygwin; then
  CLASSPATH=`cygpath -p -w "$CLASSPATH"`
  HADOOP_HOME=`cygpath -w "$HADOOP_HOME"`
  HADOOP_LOG_DIR=`cygpath -w "$HADOOP_LOG_DIR"`
  TOOL_PATH=`cygpath -p -w "$TOOL_PATH"`
fi

#Determine the JAVA_PLATFORM		//(5)获取系统平台
JAVA_PLATFORM=`CLASSPATH=${CLASSPATH} ${JAVA} -Xmx32m ${HADOOP_JAVA_PLATFORM_OPTS} org.apache.hadoop.util.PlatformName | sed -e "s/ /_/g"`
  
if [ "$JAVA_PLATFORM" = "Linux-amd64-64" ]; then
  JSVC_ARCH="amd64"
else
  JSVC_ARCH="i386"
fi

# setup 'java.library.path' for native-hadoop code if necessary
JAVA_LIBRARY_PATH=''
if [ -d "${HADOOP_HOME}/build/native" -o -d "${HADOOP_HOME}/lib/native" -o -e "${HADOOP_PREFIX}/lib/libhadoop.a" ]; then

  if [ -d "$HADOOP_HOME/build/native" ]; then
    JAVA_LIBRARY_PATH=${HADOOP_HOME}/build/native/${JAVA_PLATFORM}/lib
  fi
  
  if [ -d "${HADOOP_HOME}/lib/native" ]; then
    if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
      JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}:${HADOOP_HOME}/lib/native/${JAVA_PLATFORM}
    else
      JAVA_LIBRARY_PATH=${HADOOP_HOME}/lib/native/${JAVA_PLATFORM}
    fi
  fi

  if [ -e "${HADOOP_PREFIX}/lib/libhadoop.a" ]; then
    JAVA_LIBRARY_PATH=${HADOOP_PREFIX}/lib
  fi
fi

# cygwin path translation
if $cygwin; then
  JAVA_LIBRARY_PATH=`cygpath -p "$JAVA_LIBRARY_PATH"`
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}"

#turn security logger on the namenode and jobtracker only
if [ $COMMAND = "namenode" ] || [ $COMMAND = "jobtracker" ]; then
  HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,DRFAS}"
else
  HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,NullAppender}"
fi

if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
  HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"		//(6)设定使用hadoop本地库
fi  
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.policy.file=$HADOOP_POLICYFILE"

# Check to see if we should start a secure datanode
if [ "$starting_secure_dn" = "true" ]; then
  if [ "$HADOOP_PID_DIR" = "" ]; then
    HADOOP_SECURE_DN_PID="/tmp/hadoop_secure_dn.pid"
  else
    HADOOP_SECURE_DN_PID="$HADOOP_PID_DIR/hadoop_secure_dn.pid"
  fi

  exec "$HADOOP_HOME/libexec/jsvc.${JSVC_ARCH}" -Dproc_$COMMAND -outfile "$HADOOP_LOG_DIR/jsvc.out" \
                                                -errfile "$HADOOP_LOG_DIR/jsvc.err" \
                                                -pidfile "$HADOOP_SECURE_DN_PID" \
                                                -nodetach \
                                                -user "$HADOOP_SECURE_DN_USER" \
                                                -cp "$CLASSPATH" \
                                                $JAVA_HEAP_MAX $HADOOP_OPTS \
                                                org.apache.hadoop.hdfs.server.datanode.SecureDataNodeStarter "$@"
else
  # run it
  exec "$JAVA" -Dproc_$COMMAND $JAVA_HEAP_MAX $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"		//运行具体的java class
  
fi

2. $HADOOP_HOME/bin/ hadoop-config.sh

 

 

# 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.# included in all the hadoop scripts with source command# should not be executable directly# also should not be passed any arguments, since we need original $*# resolve links - $0 may be a softlinkthis="${BASH_SOURCE-$0}"
common_bin=$(cd -P --"$(dirname -- "$this")"&& pwd -P)
script="$(basename -- "$this")"this="$common_bin/$script"# convert relative path to absolute path
config_bin=`dirname "$this"`
script=`basename "$this"`
config_bin=`cd "$config_bin"; pwd`this="$config_bin/$script"# the root of the Hadoop installationexport HADOOP_PREFIX=`dirname "$this"`/..#check to see if the conf dir is given as an optional argumentif[ $# -gt 1 ]thenif["--config"="$1"]then
	      shift
	      confdir=$1
	      shift
	      HADOOP_CONF_DIR=$confdir
    fifi# Allow alternate conf dir location.if[-e "${HADOOP_PREFIX}/conf/hadoop-env.sh"];then
  DEFAULT_CONF_DIR="conf"else
  DEFAULT_CONF_DIR="etc/hadoop"fi
HADOOP_CONF_DIR="${HADOOP_CONF_DIR:-$HADOOP_PREFIX/$DEFAULT_CONF_DIR}"#check to see it is specified whether to use the slaves or the# masters fileif[ $# -gt 1 ]thenif["--hosts"="$1"]then
        shift
        slavesfile=$1
        shift
        export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$slavesfile"fifiif[-f "${HADOOP_CONF_DIR}/hadoop-env.sh"];then."${HADOOP_CONF_DIR}/hadoop-env.sh"//(2)执行hadoop-env.sh,进行配置设置fiif["$HADOOP_HOME_WARN_SUPPRESS"=""]&&["$HADOOP_HOME"!=""];then
  echo "Warning: \$HADOOP_HOME is deprecated."1>&2
  echo 1>&2fi# Newer versions of glibc use an arena memory allocator that causes virtual# memory usage to explode. This interacts badly with the many threads that# we use in Hadoop. Tune the variable down to prevent vmem explosion.export MALLOC_ARENA_MAX=${MALLOC_ARENA_MAX:-4}export HADOOP_HOME=${HADOOP_PREFIX}export HADOOP_HOME_WARN_SUPPRESS=1

3. $HADOOP_HOME/conf/hadoop-env.sh

 


总结,hadoop命令在运行时一次分别执行hadoop-config.sh 和 hadoop-env.sh来设置配置和参数。最后将设置的配置和参数交给java类来运行,根据不同的参数定位不同的执行类和行为。