Hadoop集群安装部署

1.介绍

（1）架构模型

（2）使用工具

VMWARE
cenos7
Xshell
Xftp
jdk-8u91-linux-x64.rpm
hadoop-2.7.3.tar.gz

2.安装步骤

（1）部署master

创建一台虚拟机
修改ip

这里请参考：VMWARE虚拟机中CentOs7网络连接
Xftp传输jdk、hadhoop安装包

把两个安装包拉取到/usr/local路径下
安装jdk

rpm -ivh jdk-8u91-linux-x64.rpm
安装hadhoop

tar zxvf hadoop-2.7.3.tar.gz

配置环境变量

配置/hadoop/etc/hadoop/hadoop-env.sh的JAVA_HOME

# 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=/usr/java/default
# 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.
for f in $HADOOP_HOME/contrib/capacity-scheduler/*.jar; do
  if [ "$HADOOP_CLASSPATH" ]; then
    export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$f
  else
    export HADOOP_CLASSPATH=$f
  fi
done
# The maximum amount of heap to use, in MB. Default is 1000.
#export HADOOP_HEAPSIZE=
#export HADOOP_NAMENODE_INIT_HEAPSIZE=""
# Extra Java runtime options.  Empty by default.
export HADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"
# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_NAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_NAMENODE_OPTS"
export HADOOP_DATANODE_OPTS="-Dhadoop.security.logger=ERROR,RFAS $HADOOP_DATANODE_OPTS"
export HADOOP_SECONDARYNAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_SECONDARYNAMENODE_OPTS"
export HADOOP_NFS3_OPTS="$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="-Xmx512m $HADOOP_CLIENT_OPTS"
#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

配置hadoop的全局变量

修改/etc/profile

vi /etc/profile

# /etc/profile
# System wide environment and startup programs, for login setup
# Functions and aliases go in /etc/bashrc
# It's NOT a good idea to change this file unless you know what you
# are doing. It's much better to create a custom.sh shell script in
# /etc/profile.d/ to make custom changes to your environment, as this
# will prevent the need for merging in future updates.
pathmunge () {
    case ":${PATH}:" in
        *:"$1":*)
            ;;
        *)
            if [ "$2" = "after" ] ; then
                PATH=$PATH:$1
            else
                PATH=$1:$PATH
            fi
    esac
}
if [ -x /usr/bin/id ]; then
    if [ -z "$EUID" ]; then
        # ksh workaround
        EUID=`/usr/bin/id -u`
        UID=`/usr/bin/id -ru`
    fi
    USER="`/usr/bin/id -un`"
    LOGNAME=$USER
    MAIL="/var/spool/mail/$USER"
fi
# Path manipulation
if [ "$EUID" = "0" ]; then
    pathmunge /usr/sbin
    pathmunge /usr/local/sbin
else
    pathmunge /usr/local/sbin after
    pathmunge /usr/sbin after
fi
HOSTNAME=`/usr/bin/hostname 2>/dev/null`
HISTSIZE=1000
if [ "$HISTCONTROL" = "ignorespace" ] ; then
    export HISTCONTROL=ignoreboth
else
    export HISTCONTROL=ignoredups
fi
export PATH USER LOGNAME MAIL HOSTNAME HISTSIZE HISTCONTROL
# By default, we want umask to get set. This sets it for login shell
# Current threshold for system reserved uid/gids is 200
# You could check uidgid reservation validity in
# /usr/share/doc/setup-*/uidgid file
if [ $UID -gt 199 ] && [ "`/usr/bin/id -gn`" = "`/usr/bin/id -un`" ]; then
    umask 002
else
    umask 022
fi
for i in /etc/profile.d/*.sh /etc/profile.d/sh.local ; do
    if [ -r "$i" ]; then
        if [ "${-#*i}" != "$-" ]; then 
            . "$i"
        else
            . "$i" >/dev/null
        fi
    fi
done
unset i
unset -f pathmunge
export PATH=$PATH:/usr/local/hadoop/bin:/usr/local/hadoop/sbin

生效/etc/profile

source /etc/profile

（2）部署slave

克隆三个主机slave1、slave2、slave3
修改ip

（3）统一配置

利用Xshell提供的工具多窗口命令行，会使我们的操作更简单。

测试网络

ping 192.168.40.100

ping 192.168.40.101

ping 192.168.40.102

ping 192.168.40.103
关闭防火墙

systemctl stop filewalld ------关闭防火墙

systemctl disable filewalld ------失效防火墙，下次重启也属于关闭状态
修改host

vi /etc/hosts

192.168.40.100 master

192.168.40.101 slave1

192.168.40.102 slave2

192.168.40.103 slave3

配置core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed 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. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
        <name>fs.defaultFS</name>
        <value>hdfs://master:9090</value>
</property>
</configuration>

（4）启动master

切换到master主机：

格式化namenode

hdfs namenode -format
启动namenode

hadoop-daemon.sh start namenode
查看namenode是否启动成功

jps

如果有NameNode进程则启动成功。

（5）启动slave

切换到slave1,slave2,slave3主机：

启动datanode

hadoop-daemon.sh start datanode
查看datanode是否启动成功

jps

如果有DataNode进程则启动成功。

（6）查看NameNode里的DataNode

hadoop dfsadmin -report

结果：

[root@bogon hadoop]# hadoop dfsadmin -report
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
Configured Capacity: 19925041152 (18.56 GB)
Present Capacity: 13599780864 (12.67 GB)
DFS Remaining: 13599756288 (12.67 GB)
DFS Used: 24576 (24 KB)
DFS Used%: 0.00%
Under replicated blocks: 0
Blocks with corrupt replicas: 0
Missing blocks: 0
Missing blocks (with replication factor 1): 0
-------------------------------------------------
Live datanodes (3):
Name: 192.168.40.103:50010 (slave3)
Hostname: localhost
Decommission Status : Normal
Configured Capacity: 6641680384 (6.19 GB)
DFS Used: 8192 (8 KB)
Non DFS Used: 2108416000 (1.96 GB)
DFS Remaining: 4533256192 (4.22 GB)
DFS Used%: 0.00%
DFS Remaining%: 68.25%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Tue Oct 16 18:34:12 CST 2018
Name: 192.168.40.101:50010 (slave1)
Hostname: localhost
Decommission Status : Normal
Configured Capacity: 6641680384 (6.19 GB)
DFS Used: 8192 (8 KB)
Non DFS Used: 2108420096 (1.96 GB)
DFS Remaining: 4533252096 (4.22 GB)
DFS Used%: 0.00%
DFS Remaining%: 68.25%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Tue Oct 16 18:34:12 CST 2018
Name: 192.168.40.102:50010 (slave2)
Hostname: localhost
Decommission Status : Normal
Configured Capacity: 6641680384 (6.19 GB)
DFS Used: 8192 (8 KB)
Non DFS Used: 2108424192 (1.96 GB)
DFS Remaining: 4533248000 (4.22 GB)
DFS Used%: 0.00%
DFS Remaining%: 68.25%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Tue Oct 16 18:34:12 CST 2018