任务:配置6台或者多台机器 基本环境
0.1修改主机名
vim /etc/sysconfig/network
hostname= itcastX
0.2映射关系
vim /etc/hosts
-
192.168.8.101 itcast01 192.168.8.102 itcast02 192.168.8.103 itcast03 192.168.8.104 itcast04 192.168.8.105 itcast05 192.168.8.106 itcast06
0.3关闭防火墙
关闭防火墙 service iptables stop
关闭防火墙开机启动 chkconfig iptables off
0.4配置jdk
mkdir /usr/java
tar -zxvf jdk-7u65-linux-i586.tar.gz -C /usr/java/
vim /etc/profile
-
export JAVA_HOME=/usr/java/jdk1.7.0_65 export HADOOP_HOME=/itcast/hadoop-2.2.0 export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
source /etc/profile
配置ssh免密码登录(所有主机)
itcast01操作:
-
ssh-keygen -t rsa ssh-coyp-id itcast01 ssh-coyp-id itcast02 ssh-coyp-id itcast03 ssh-coyp-id itcast04 ssh-coyp-id itcast05 ssh-coyp-id itcast06
itcast02操作:
-
ssh-keygen -t rsa ssh-coyp-id -i itcast01
itcast03操作:
-
ssh-keygen -t rsa ssh-coyp-id itcast04 ssh-coyp-id itcast05 ssh-coyp-id itcast06
集群规划:
主机名 IP 安装的软件 运行的进程
itcast01 192.168.8.101 jdk,hadoop NameNode,DFSZKFailoverController
itcast02 192.168.8.102 jdk,hadoop NameNode,DFSZKFailoverController
itcast03 192.168.8.103 jdk,hadoop ResourceManager
itcast04 192.168.8.104 jdk,hadoop,zookeeper DataNode,NodeManager,JournalNode,QuorumPeerMain
itcast05 192.168.8.105 jdk,hadoop,zookeeper DataNode,NodeManager,JournalNode,QuorumPeerMain
itcast06 192.168.8.106 jdk,hadoop,zookeeper DataNode,NodeManager,JournalNode,QuorumPeerMain
一、安装配置zooekeeper集群: itcast04、itcast05、itcast06
1.1上传解压 (itcast04操作)
mkdir /itcast
tar -zxvf zookeeper-3.4.5.tar.gz -C /itcast/
1.2修改配置
cd /itcast/zookeeper-3.4.5/conf/
cp zoo_sample.cfg zoo.cfg
vim zoo.cfg
修改:dataDir=/itcast/zookeeper-3.4.5/tmp
添加:
-
server.4=itcast04:2888:3888 server.5=itcast05:2888:3888 server.6=itcast06:2888:3888
1.3创建一个tmp文件夹
mkdir /itcast/zookeeper-3.4.5/tmp
1.4创建一个空文件
touch /itcast/zookeeper-3.4.5/tmp/myid
vim myid 4
1.5复制zookeeper到itcast05、itcast06
scp -r /itcast/zookeeper-3.4.5/ itcast05:/
scp -r /itcast/zookeeper-3.4.5/ itcast06:/
1.6修改 itcast05、itcast06中的 myid
itcast05操作: vim myid 5
itcast06操作: vim myid 6
二、安装配置hadoop集群:全部机器
2.1解压
mkdir /itcast
tar -zxvf hadoop-2.2.0.tar.gz -C /itcast/
2.2配置环境变量
vim /etc/profile
-
export JAVA_HOME=/usr/java/jdk1.7.0_65 export HADOOP_HOME=/itcast/hadoop-2.2.0 export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin
source /etc/profile
2.3配置6个文件
1 hadoo-env.sh
-
export JAVA_HOME=/usr/java/jdk1.7.0_65
2 core-site.xml
-
<configuration> <!-- 指定hdfs的nameservice为ns1 --> <property> <name>fs.defaultFS</name> <value>hdfs://ns1</value> </property> <!-- 指定hadoop临时目录 --> <property> <name>hadoop.tmp.dir</name> <value>/itcast/hadoop-2.2.0/tmp</value> </property> <!-- 指定zookeeper地址 --> <property> <name>ha.zookeeper.quorum</name> <value>itcast04:2181,itcast05:2181,itcast06:2181</value> </property> </configuration>
3 hdfs-site.xml
-
<configuration> <!--指定hdfs的nameservice为ns1,需要和core-site.xml中的保持一致 --> <property> <name>dfs.nameservices</name> <value>ns1</value> </property> <!-- ns1下面有两个NameNode,分别是nn1,nn2 --> <property> <name>dfs.ha.namenodes.ns1</name> <value>nn1,nn2</value> </property> <!-- nn1的RPC通信地址 --> <property> <name>dfs.namenode.rpc-address.ns1.nn1</name> <value>itcast01:9000</value> </property> <!-- nn1的http通信地址 --> <property> <name>dfs.namenode.http-address.ns1.nn1</name> <value>itcast01:50070</value> </property> <!-- nn2的RPC通信地址 --> <property> <name>dfs.namenode.rpc-address.ns1.nn2</name> <value>itcast02:9000</value> </property> <!-- nn2的http通信地址 --> <property> <name>dfs.namenode.http-address.ns1.nn2</name> <value>itcast02:50070</value> </property> <!-- 指定NameNode的元数据在JournalNode上的存放位置 --> <property> <name>dfs.namenode.shared.edits.dir</name> <value>qjournal://itcast04:8485;itcast05:8485;itcast06:8485/ns1</value> </property> <!-- 指定JournalNode在本地磁盘存放数据的位置 --> <property> <name>dfs.journalnode.edits.dir</name> <value>/itcast/hadoop-2.2.0/journal</value> </property> <!-- 开启NameNode失败自动切换 --> <property> <name>dfs.ha.automatic-failover.enabled</name> <value>true</value> </property> <!-- 配置失败自动切换实现方式 --> <property> <name>dfs.client.failover.proxy.provider.ns1</name> <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value> </property> <!-- 配置隔离机制方法,多个机制用换行分割,即每个机制暂用一行--> <property> <name>dfs.ha.fencing.methods</name> <value> sshfence shell(/bin/true) </value> </property> <!-- 使用sshfence隔离机制时需要ssh免登陆 --> <property> <name>dfs.ha.fencing.ssh.private-key-files</name> <value>/root/.ssh/id_rsa</value> </property> <!-- 配置sshfence隔离机制超时时间 --> <property> <name>dfs.ha.fencing.ssh.connect-timeout</name> <value>30000</value> </property> </configuration>
4 mapred-site.xml
-
<configuration> <!-- 指定mr框架为yarn方式 --> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> </configuration>
5 yarn-site.xml
-
<configuration> <!-- 指定resourcemanager地址 --> <property> <name>yarn.resourcemanager.hostname</name> <value>itcast03</value> </property> <!-- 指定nodemanager启动时加载server的方式为shuffle server --> <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> </configuration>
6 slaves
-
itcast04 itcast05 itcast06
2.4将配置好的hadoop拷贝到其他节点
-
scp -r /itcast/ itcast02:/ scp -r /itcast/ itcast03:/ scp -r /itcast/hadoop-2.2.0/ root@itcast04:/itcast/ scp -r /itcast/hadoop-2.2.0/ root@itcast05:/itcast/ scp -r /itcast/hadoop-2.2.0/ root@itcast06:/itcast/
三、启动 严格按照下面的步骤
初次启动
3.1 启动zookeeper集群(itcast04、itcast05、itcast06启动zk)
cd /itcast/zookeeper-3.4.5/bin/
./zkServer.sh start
#查看状态:一个leader,两个follower
./zkServer.sh status
3.2 启动journalnode (itcast01操作)
cd /itcast/hadoop-2.2.0
./hadoop-daemons.sh start journalnode3.3格式化HDFS (itcast01操作)
hdfs namenode -format
复制tmp到itcast02:
scp -r tmp/ itcast02:/itcast/hadoop-2.2.0/3.4格式化ZK (itcast01操作)
hdfs zkfc -formatZK3.5启动HDFS (itcast01操作)
sbin/start-dfs.sh3.6启动YARN(itcast03操作)
sbin/start-yarn.sh
日常启动
3.1启动zookeeper集群 (itcast04、itcast05、itcast06操作)
cd /itcast/zookeeper-3.4.5/bin/
./zkServer.sh start
./zkServer.sh status #3.2启动journalnode (itcast01操作)
cd /itcast/hadoop-2.2.0/sbin
./hadoop-daemons.sh start journalnode3.3启动HDFS (itcast01操作)
sbin/start-dfs.sh3.4启动YARN (itcast03操作)
sbin/start-yarn.sh
四、验证
4.1浏览器验证
http://192.168.8.101:50070
NameNode 'itcast01:9000' (active)
http://192.168.8.102:50070
NameNode 'itcast02:9000' (standby)4.2HDFS验证
1 hdfs上传一个文件
hadoop fs -put /etc/profile /profile
hadoop fs -ls /
2 然后kill掉active的NameNode
kill -9 <pid of NN>
3 通过浏览器访问:http://192.168.8.101:50070
NameNode 'itcast02:9000' (active)
4 执行命令:
hadoop fs -ls /
刚才上传的文件依然存在
5.手动启动挂掉的NameNode
itcast01操作: ./hadoop-daemon.sh start namenode
6.通过浏览器访问:http://192.168.8.101:50070
NameNode 'itcast01:9000' (standby)