1       批量启动与停止

1.1  Start-all.sh

# Start all hadoop daemons.  Run this on master node.

bin=`dirname "$0"`

bin=`cd "$bin"; pwd`

#变量配置命令

. "$bin"/hadoop-config.sh

#Dfs服务器启动

# start dfs daemons

"$bin"/start-dfs.sh --config $HADOOP_CONF_DIR

MR服务器启动

# start mapred daemons

"$bin"/start-mapred.sh --config $HADOOP_CONF_DIR

1.2  Stop-all.sh

"$bin"/stop-mapred.sh --config $HADOOP_CONF_DIR

"$bin"/stop-dfs.sh --config $HADOOP_CONF_DIR

2       hdfs的启动与停止

2.1  start-dfs.sh

# start dfs daemons

# start namenode after datanodes, to minimize time namenode is up w/o data

# note: datanodes will log connection errors until namenode starts

"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR start namenode $nameStartOpt

"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR start datanode $dataStartOpt

"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR --hosts masters start secondarynamenode

2.2  Stop-dfs.sh

"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR stop namenode

"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR stop datanode

"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR --hosts masters stop secondarynamenode

3       MapReduce的启动与停止

3.1  start-mapred.sh

# start mapred daemons

# start jobtracker first to minimize connection errors at startup

"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR start jobtracker

"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR start tasktracker

3.2  Stop-mapred.sh

"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR stop jobtracker

"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR stop tasktracker

4       Balancer的启动与停止

4.1  start-balancer.sh

"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR start balancer $@

4.2  Stop-balancer.sh

"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR stop balancer

5       hadoop-daemon.sh主机系统脚本

5.1  start

nohup nice -n $HADOOP_NICENESS "$HADOOP_HOME"/bin/hadoop --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &

5.2  stop

echo stopping $command

        kill `cat $pid`

6       hadoop-daemons.sh从机系统脚本

Run a Hadoop command on all slave hosts.

exec "$bin/slaves.sh" --config $HADOOP_CONF_DIR cd "$HADOOP_HOME" \; "$bin/hadoop-daemon.sh" --config $HADOOP_CONF_DIR "$@"

7       hadoop应用程序调用脚本

基于java调用相应的类

7.1  6个服务器类

7.1.1       namenode服务器

# figure out which class to run

if [ "$COMMAND" = "namenode" ] ; then

  CLASS='org.apache.hadoop.hdfs.server.namenode.NameNode'

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_NAMENODE_OPTS"

7.1.2       SecondaryNameNode服务器

elif [ "$COMMAND" = "secondarynamenode" ] ; then

  CLASS='org.apache.hadoop.hdfs.server.namenode.SecondaryNameNode'

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_SECONDARYNAMENODE_OPTS"

7.1.3       DataNode服务器

elif [ "$COMMAND" = "datanode" ] ; then

  CLASS='org.apache.hadoop.hdfs.server.datanode.DataNode'

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_DATANODE_OPTS"

7.1.4       JOBSTACKET服务器

elif [ "$COMMAND" = "jobtracker" ] ; then

  CLASS=org.apache.hadoop.mapred.JobTracker

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_JOBTRACKER_OPTS"

7.1.5       TaskTracker服务器

elif [ "$COMMAND" = "tasktracker" ] ; then

  CLASS=org.apache.hadoop.mapred.TaskTracker

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_TASKTRACKER_OPTS"

7.1.6       Balancer负载均衡服务器

elif [ "$COMMAND" = "balancer" ] ; then

  CLASS=org.apache.hadoop.hdfs.server.balancer.Balancer

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_BALANCER_OPTS"

7.2  基它客户端命令

7.2.1       Fs-fsshell

elif [ "$COMMAND" = "fs" ] ; then

  CLASS=org.apache.hadoop.fs.FsShell

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

7.2.2       Dfs-fsshell

elif [ "$COMMAND" = "dfs" ] ; then

  CLASS=org.apache.hadoop.fs.FsShell

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

7.2.3       Dfsadmin-DFSADmin

elif [ "$COMMAND" = "dfsadmin" ] ; then

  CLASS=org.apache.hadoop.hdfs.tools.DFSAdmin

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

7.2.4       Fsck-DFSck

elif [ "$COMMAND" = "fsck" ] ; then

  CLASS=org.apache.hadoop.hdfs.tools.DFSck

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

7.2.5       Job-JobClient

elif [ "$COMMAND" = "job" ] ; then

  CLASS=org.apache.hadoop.mapred.JobClient

7.2.6       Queue- JobQueueClient

elif [ "$COMMAND" = "queue" ] ; then

  CLASS=org.apache.hadoop.mapred.JobQueueClient

7.2.7       Pipes- Submitter

elif [ "$COMMAND" = "pipes" ] ; then

  CLASS=org.apache.hadoop.mapred.pipes.Submitter

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

7.2.8       Version- VersionInfo

elif [ "$COMMAND" = "version" ] ; then

  CLASS=org.apache.hadoop.util.VersionInfo

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

7.2.9       Jar- JobShell

elif [ "$COMMAND" = "jar" ] ; then

  CLASS=org.apache.hadoop.mapred.JobShell

7.2.10 Distcp- DistCp

elif [ "$COMMAND" = "distcp" ] ; then

  CLASS=org.apache.hadoop.tools.DistCp

  CLASSPATH=${CLASSPATH}:${TOOL_PATH}

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

 

7.2.11 Daemonlog-LogLevel

elif [ "$COMMAND" = "daemonlog" ] ; then

  CLASS=org.apache.hadoop.log.LogLevel

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

 

7.2.12 Archive- HadoopArchives

elif [ "$COMMAND" = "archive" ] ; then

  CLASS=org.apache.hadoop.tools.HadoopArchives

  CLASSPATH=${CLASSPATH}:${TOOL_PATH}

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"


 

7.2.13 Sampler- InputSampler

elif [ "$COMMAND" = "sampler" ] ; then

  CLASS=org.apache.hadoop.mapred.lib.InputSampler

  HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"

else

  CLASS=$COMMAND

fi

8       hadoop-config.sh

# the root of the Hadoop installation

export HADOOP_HOME=`dirname "$this"`/..

# Allow alternate conf dir location.

HADOOP_CONF_DIR="${HADOOP_CONF_DIR:-$HADOOP_HOME/conf}"

export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$slavesfile"