大数据之shell脚本配置伪分布式Hadoop

shell脚本配置伪分布式Hadoop

一 hadoop安装

install_hadoop.sh

## !/bin/bash

## 安装jdk
./install_java.sh
##安装前的路径
INSTALL_PROFIX=/opt/apps
## 环境变量
ETC_PROFILE=/etc/profile
## hadoop安装路径
HADOOP_DIR=${INSTALL_PROFIX}/hadoop-2.8.1
## 安装包的前缀路径
HADOOP_PROFIX=/opt/software
## hadoop的安装包路径
HADOOP_TAR=${HADOOP_PROFIX}/hadoop-2.8.1.tar.gz

## 判断安装路径是否存在，如果存在说明此软件已经安装过了
if [ -e "${HADOOP_DIR}" ];then
        echo "warning:${HADOOP_DIR} is exists"
        exit 0
fi

## 判断安装包是否存在，如果不存在，就不用安装了
if [ ! -e "${HADOOP_TAR}" ];then
        echo "warving:${HADOOP_TAR} is not exists"
        exit -1
fi

tar -zxvf ${HADOOP_TAR} -C ${INSTALL_PROFIX}

cat << EOF >> ${ETC_PROFILE}
export HADOOP_HOME=${HADOOP_DIR}
export PATH=\$PATH:\${HADOOP_HOME}/bin:\${HADOOP_HOME}/sbin
EOF

## 修改hadoop-env.sh配置文件
./hadoop-env.sh

## 修改core-site.xml配置文件
./core-site.sh

## 修改hdfs-site.xml配置文件
./hdfs-site.sh

## 免密操作
ssh-keygen
ssh-copy-id 192.168.130.130

## 格式化namenode
source /etc/profile
hdfs namenode -format

## 关闭防火墙
systemctl stop firewalld

二 jdk安装

install_java.sh

## !/bin/bash

## 安装前缀路径
INSTALL_PREFIX=/opt/apps
## 配置环境变量
ETC_PROFILE=/etc/profile
## jdk安装路径
JAVA_DIR=${INSTALL_PREFIX}/jdk1.8.0_261
## 安装包的路径
TAR_PROFIX=/opt/software
## JDK的路径
JAVA_TAR=${TAR_PROFIX}/jdk-8u261-linux-x64.tar.gz

## 判断安装路径是否存在，如果存在说明我们已经安装过此应用
if [ -e "${JAVA_DIR}" ];then
	echo "warning:${JAVA_DIR} is exists"
	exit 0
fi

## 判断安装包是否存在，如果不存在，就不用安装
if [ ! -e "${JAVA_TAR}" ];then
	echo "warning:${JAVA_TAR} is not exists"
	exit -1
fi

tar -zxvf ${JAVA_TAR} -C ${INSTALL_PREFIX}

cat << EOF >> ${ETC_PROFILE}
 export JAVA_HOME=${JAVA_DIR}
 export PATH=\$PATH:\${JAVA_HOME}/bin
 export CLASS_PATH=./\${JAVA_HOME}/lib
EOF

三 修改Hadoop配置文件

hadoop-env.sh

## 更新配置文件
 source /etc/profile

## 更改Hadoop配置文件

echo '# 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.

# Set Hadoop-specific environment variables here.

# The only required environment variable is JAVA_HOME.  All others are
# optional.  When running a distributed configuration it is best to
# set JAVA_HOME in this file, so that it is correctly defined on
# remote nodes.

# The java implementation to use.
export JAVA_HOME=/opt/apps/jdk1.8.0_261

# The jsvc implementation to use. Jsvc is required to run secure datanodes
# that bind to privileged ports to provide authentication of data transfer
# protocol.  Jsvc is not required if SASL is configured for authentication of
# data transfer protocol using non-privileged ports.
#export JSVC_HOME=${JSVC_HOME}

export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop"}

# Extra Java CLASSPATH elements.  Automatically insert capacity-scheduler.
    export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$f
  else
done

# The maximum amount of heap to use, in MB. Default is 1000.
#export HADOOP_HEAPSIZE=
#export HADOOP_NAMENODE_INIT_HEAPSIZE=""

# Kerberos security.
# export HADOOP_JAAS_DEBUG=true

# Extra Java runtime options.  Empty by default.
# For Kerberos debugging, an extended option set logs more invormation
# export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true -Dsun.security.krb5.debug=true -Dsun.security.spnego.debug"
export HADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"

# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_DATANODE_OPTS="-Dhadoop.security.logger=ERROR,RFAS $HADOOP_DATANODE_OPTS"


export HADOOP_NFS3_OPTS="$HADOOP_NFS3_OPTS"
export HADOOP_PORTMAP_OPTS="-Xmx512m $HADOOP_PORTMAP_OPTS"

# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
export HADOOP_CLIENT_OPTS="$HADOOP_CLIENT_OPTS"
# set heap args when HADOOP_HEAPSIZE is empty
if [ "$HADOOP_HEAPSIZE" = "" ]; then
  export HADOOP_CLIENT_OPTS="-Xmx512m $HADOOP_CLIENT_OPTS"
fi
#HADOOP_JAVA_PLATFORM_OPTS="-XX:-UsePerfData $HADOOP_JAVA_PLATFORM_OPTS"

# On secure datanodes, user to run the datanode as after dropping privileges.
# This **MUST** be uncommented to enable secure HDFS if using privileged ports
# to provide authentication of data transfer protocol.  This **MUST NOT** be
# defined if SASL is configured for authentication of data transfer protocol
# using non-privileged ports.
export HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER}

# Where log files are stored.  $HADOOP_HOME/logs by default.
#export HADOOP_LOG_DIR=${HADOOP_LOG_DIR}/$USER

# Where log files are stored in the secure data environment.
#export HADOOP_SECURE_DN_LOG_DIR=${HADOOP_LOG_DIR}/${HADOOP_HDFS_USER}

###
# HDFS Mover specific parameters
###
# Specify the JVM options to be used when starting the HDFS Mover.
# These options will be appended to the options specified as HADOOP_OPTS
# and therefore may override any similar flags set in HADOOP_OPTS
#
# export HADOOP_MOVER_OPTS=""

###
# Advanced Users Only!
###

# The directory where pid files are stored. /tmp by default.
# NOTE: this should be set to a directory that can only be written to by
#       the user that will run the hadoop daemons.  Otherwise there is the
#       potential for a symlink attack.
export HADOOP_PID_DIR=${HADOOP_PID_DIR}
export HADOOP_SECURE_DN_PID_DIR=${HADOOP_PID_DIR}

# A string representing this instance of hadoop. $USER by default.
export HADOOP_IDENT_STRING=$USER ' > ${HADOOP_HOME}/etc/hadoop/hadoop-env.sh

core-site.sh

## 更新配置文件
 source /etc/profile

## 更改Hadoop配置文件

echo '







        
        
                fs.defaultFS
                hdfs://192.168.130.130:9000
        

        
        
                hadoop.tmp.dir
                /opt/apps/hadoop-2.8.1/hdpdata
        
 ' > ${HADOOP_HOME}/etc/hadoop/core-site.xml 

hdfs-site.sh

## 更新配置文件
 source /etc/profile

## 更改Hadoop配置文件

echo '






        
                dfs.replication
                1
        
 ' > ${HADOOP_HOME}/etc/hadoop/hdfs-site.xml

四 帮助文档

启动命令：sh install_hadoop.sh
启动内容：
1.调用install_jdk.sh，安装jdk和配置环境
2.安装hadoop和配置hadoop环境
3.调用hadoop-env.sh，修改jdk的路径
4.调用core-site.sh和hdfs-site.sh修改hadoop文件中的core-site.xml和hdfs-site.xml
完成操作：启动sh install_hadoop.sh成功后
通过start-dfs.sh启动
通过http://192.168.130.130:50070查看webGUI 

参考资源：