1、hadoop集群搭建 OK
hadoop安装、配置、伪分布式集群搭建
2、zookeeper OK(时区同步 OK)
zookeeper安装配置完成、时间同步设置完成
3、core-site.xml
设置namenode集群的名称
zookeeper 2181地址
name | value | 备注 |
---|---|---|
fs.defaultFS | hdfs://ns | 默认节点为namenode集群 |
hadoop.tmp.dir | /opt/hadoop/tmp | hdfs的临时文件的目录 |
ha.zookeeper.quorum | hadoop01:2181,hadoop02:2181,hadoop03:2181 | 故障转移需要的zookeeper集群 |
hadoop.proxyuser.root.hosts | * | 其他机器的root用户可访问 |
hadoop.proxyuser.root.groups | * | 其他root组下的用户都可以访问 |
4、hdfs-site.xml
nameservices集群下面的各个nameservice服务对应的映射
rpc-address的地址9000
http-address的地址50070
journalnode的共享地址(各个datanode)
qjournal://datanode:8485;列表/集群名
出错处理,切换方式及隔离机制的设置,超时设置
5、yarn-site.xml
允许ha
resourcemanager集群配置
rm-ids:rm1,rm2
rm1:nm1 及端口配置8088
rm2:nm2 及端口配置8088
zookeeper配置
6、保证3台机器一致
7、确保集群处于关闭状态
8、删除tmp文件夹,选择主节点重新format(可能需要提前启动journalnode)
9、把主节点新生成的tmp文件夹,复制到备用节点
10、zookeeper要启动
11、启动整个集群
12、在备用节点上启动备用resource manager
13、主节点格式化zkfc
hdfs zkfc -formatZK
14、主备节点启动zkfc
hadoop-daemon.sh start zkfc
15、datanode节点
在完全分布式模式的基础上修改配置文件:
1.core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://ns</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/hadoop/tmp</value>
</property>
<!--指定zookeeper地址-->
<property>
<name>ha.zookeeper.quorum</name>
<value>hadoop01:2181,hadoop02:2181,hadoop03:2181</value>
</property>
<property>
<name>hadoop.proxyuser.root.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.root.groups</name>
<value>*</value>
</property>
<property>
<name>hadoop.native.lib</name>
<value>false</value>
<description>Should native hadoop libraries, if present, be used.
</description>
</property>
</configuration>
可能有所不同的地方标注:
2.hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!--节点数,ha中可不配置 -->
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<!--指定名称服务,与core-stie.xml中的一致 -->
<property>
<name>dfs.nameservices</name>
<value>ns</value>
</property>
<!--指定名称服务下的namenode节点 -->
<property>
<name>dfs.ha.namenodes.ns</name>
<value>hadoop01,hadoop02</value>
</property>
<!--rpc地址,9000端口-->
<property>
<name>dfs.namenode.rpc-address.ns.hadoop01</name>
<value>hadoop01:9000</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns.hadoop02</name>
<value>hadoop02:9000</value>
</property>
<!--http地址,50070端口,即页面地址-->
<property>
<name>dfs.namenode.http-address.ns.hadoop01</name>
<value>hadoop01:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.ns.hadoop02</name>
<value>hadoop02:50070</value>
</property>
<!--指定namenode在jornalnode(datanode)上存放数据端口8485-->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hadoop01:8485;hadoop02:8485;hadoop03:8485/ns</value>
</property>
<!--开启namenode失败自动切换-->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/opt/hadoop/tmp/dfs/jn</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- 配置namenode自动切换方式 -->
<property>
<name>dfs.client.failover.proxy.provider.ns</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!--设置隔离机制,多个机制换行-->
<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>
<!--超时设置-->
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<!-- 当使用HA配置集群,则不需要secondarynamenode
<prooerty>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop02:50090</value>
</property>
-->
</configuration>
可能有所不同的地方标注:
3.mapred-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>hadoop01:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>hadoop01:19888</value>
</property>
</configuration>
4.yarn-site.xml
<?xml version="1.0"?>
<configuration>
<!--HA配置-->
<!--开启HA-->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<!--指定rm集群id-->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>cluster_id</value>
</property>
<!--rm集群的名称服务-->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!--指定rm映射关系-->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hadoop01</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hadoop02</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>hadoop01:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>hadoop02:8088</value>
</property>
<!--配置zookeeper集群-->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>hadoop01:2181,hadoop02:2181,hadoop03:2181</value>
</property>
<!-- Site specific YARN configuration properties -->
<!--指定YARN的ResourceManager的地址,值为主机名
<property>
<name>yarn.resourcemanager.hostname</name>
<value>hadoop01</value>
</property>-->
<!-- reducer获取数据方式 -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<!-- 日志聚集功能使用 -->
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<!-- 日志保留时间设置7天 -->
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>
</configuration>
5.slaves
hadoop01
hadoop02
hadoop03
6.删除tmp文件夹,选择主节点重新format(可能需要提前启动journalnode)
(1) 启动journalnode命令,每台机器都需要启动:
hadoop-daemon.sh start journalnode
(2) 选择主节点格式化:
hadoop namenode -format
7.把主节点新生成的tmp文件夹,复制到备用节点
scp -r /opt/hadoop/tmp hadoop02:/opt/hadoop
8.启动zookeeper
(1) 启动:
zkServer.sh start
(2) 查看状态是否启动成功:
zkServer.sh status
9.在主节点上启动集群
start-all.sh
10.启动zkfc
(1) 在主节点上格式化zkfc
hdfs zkfc -formatZK
(2) 在每个节点启动zkfc
hadoop-daemon.sh start zkfc
11.启动jobhistory,只要启动一个,最好在非主节点上
mr-jobhistory-daemon.sh start historyserver
相关命令:
start-all.sh :启动hdfs和yarn
start-dfs.sh :启动hdfs
start-yarn.sh:启动yarn
stop-all.sh:关闭hdfs和yarn
stop-dfs.sh:关闭hdfs
stop-yarn.sh:关闭yarn
mr-jobhistory-daemon.sh start historyserver :启动历史服务
mr-jobhistory-daemon.sh stop historyserver:关闭历史服务
hadoop-daemon.sh start journalnode 启动journalnode
hdfs zkfc -formatZK 格式化zkfc
hadoop-daemon.sh start zkfc 启动zkfc
zkServer.sh start 启动zookeeper
ntpstat 查看时间同步状态
两个互信用到的命令:
ssh-copy-id -i .ssh/id_rsa.pub -p22 root@hadoop03
scp /etc/hosts root@hadoop03:/etc/hosts