2021年大数据环境搭建（二）：分布式环境搭建

mkdir -p /opt/software

mkdir -p /opt/server

cd /opt/software

tar -zxvf hadoop-2.7.5.tar.gz -C /opt/server/

cd /opt/server/hadoop-2.7.5/etc/hadoop

<configuration>

<!-- 指定NameNode的HA高可用的zk地址  -->

 <property>

   <name>ha.zookeeper.quorum</name>

   <value>node1:2181,node2:2181,node3:2181</value>

 </property>

 <!-- 指定HDFS访问的域名地址  -->

 <property>

   <name>fs.defaultFS</name>

   <value>hdfs://ns</value>

 </property>

 <!-- 临时文件存储目录  -->

<property>

  <name>hadoop.tmp.dir</name>

  <value>/opt/server/hadoop-2.7.5/data/tmp</value>

</property>

 <!-- 开启hdfs垃圾箱机制，指定垃圾箱中的文件七天之后就彻底删掉

单位为分钟

 -->

<property>

 <name>fs.trash.interval</name>

 <value>10080</value>

</property>

</configuration>

<configuration>

<!-- 指定NameNode的HA高可用的zk地址  -->

 <property>

   <name>ha.zookeeper.quorum</name>

   <value>node1:2181,node2:2181,node3:2181</value>

 </property>

 <!-- 指定HDFS访问的域名地址  -->

 <property>

   <name>fs.defaultFS</name>

   <value>hdfs://ns</value>

 </property>

 <!-- 临时文件存储目录  -->

<property>

  <name>hadoop.tmp.dir</name>

  <value>/opt/server/hadoop-2.7.5/data/tmp</value>

</property>

 <!-- 开启hdfs垃圾箱机制，指定垃圾箱中的文件七天之后就彻底删掉

单位为分钟

 -->

<property>

 <name>fs.trash.interval</name>

 <value>10080</value>

</property>

</configuration>

<configuration>

<!-- Site specific YARN configuration properties -->

<!-- 是否启用日志聚合.应用程序完成后,日志汇总收集每个容器的日志,这些日志移动到文件系统,例如HDFS. -->

<!-- 用户可以通过配置"yarn.nodemanager.remote-app-log-dir"、"yarn.nodemanager.remote-app-log-dir-suffix"来确定日志移动到的位置 -->

<!-- 用户可以通过应用程序时间服务器访问日志 -->



<!-- 启用日志聚合功能，应用程序完成后，收集各个节点的日志到一起便于查看 -->

<property>

<name>yarn.log-aggregation-enable</name>

<value>true</value>

</property>

 



<!--开启resource manager HA,默认为false--> 

<property>

        <name>yarn.resourcemanager.ha.enabled</name>

        <value>true</value>

</property>

<!-- 集群的Id，使用该值确保RM不会做为其它集群的active -->

<property>

        <name>yarn.resourcemanager.cluster-id</name>

        <value>mycluster</value>

</property>

<!--配置resource manager  命名-->

<property>

        <name>yarn.resourcemanager.ha.rm-ids</name>

        <value>rm1,rm2</value>

</property>

<!-- 配置第一台机器的resourceManager -->

<property>

        <name>yarn.resourcemanager.hostname.rm1</name>

        <value>node2</value>

</property>

<!-- 配置第二台机器的resourceManager -->

<property>

        <name>yarn.resourcemanager.hostname.rm2</name>

        <value>node3</value>

</property>



<!-- 配置第一台机器的resourceManager通信地址 -->

<property>

        <name>yarn.resourcemanager.address.rm1</name>

        <value>node2:8032</value>

</property>

<property>

        <name>yarn.resourcemanager.scheduler.address.rm1</name>

        <value>node2:8030</value>

</property>

<property>

        <name>yarn.resourcemanager.resource-tracker.address.rm1</name>

        <value>node2:8031</value>

</property>

<property>

        <name>yarn.resourcemanager.admin.address.rm1</name>

        <value>node2:8033</value>

</property>

<property>

        <name>yarn.resourcemanager.webapp.address.rm1</name>

        <value>node2:8088</value>

</property>



<!-- 配置第二台机器的resourceManager通信地址 -->

<property>

        <name>yarn.resourcemanager.address.rm2</name>

        <value>node3:8032</value>

</property>

<property>

        <name>yarn.resourcemanager.scheduler.address.rm2</name>

        <value>node3:8030</value>

</property>

<property>

        <name>yarn.resourcemanager.resource-tracker.address.rm2</name>

        <value>node3:8031</value>

</property>

<property>

        <name>yarn.resourcemanager.admin.address.rm2</name>

        <value>node3:8033</value>

</property>

<property>

        <name>yarn.resourcemanager.webapp.address.rm2</name>

        <value>node3:8088</value>

</property>





<!--开启resourcemanager自动恢复功能-->

<property>

        <name>yarn.resourcemanager.recovery.enabled</name>

        <value>true</value>

</property>

<!--在node2上配置rm1,在node3上配置rm2,注意：一般都喜欢把配置好的文件远程复制到其它机器上，但这个在YARN的另一个机器上一定要修改，其他机器上不配置此项-->

<property>       

<name>yarn.resourcemanager.ha.id</name>

<value>rm1</value>

       <description>If we want to launch more than one RM in single node, we need this configuration</description>

</property>

   

   <!--用于持久存储的类。尝试开启-->

<property>

        <name>yarn.resourcemanager.store.class</name>

        <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>

</property>

<property>

        <name>yarn.resourcemanager.zk-address</name>

        <value>node2:2181,node3:2181,node1:2181</value>

        <description>For multiple zk services, separate them with comma</description>

</property>

<!--开启resourcemanager故障自动切换，指定机器--> 

<property>

        <name>yarn.resourcemanager.ha.automatic-failover.enabled</name>

        <value>true</value>

        <description>Enable automatic failover; By default, it is enabled only when HA is enabled.</description>

</property>

<property>

        <name>yarn.client.failover-proxy-provider</name>

        <value>org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider</value>

</property>

<!-- 允许分配给一个任务最大的CPU核数，默认是8 -->

<property>

        <name>yarn.nodemanager.resource.cpu-vcores</name>

        <value>2</value>

</property>

<!-- 每个节点可用内存,单位MB -->

<property>

        <name>yarn.nodemanager.resource.memory-mb</name>

        <value>2048</value>

</property>

<!-- 单个任务可申请最少内存，默认1024MB -->

<property>

        <name>yarn.scheduler.minimum-allocation-mb</name>

        <value>1024</value>

</property>

<!-- 单个任务可申请最大内存，默认8192MB -->

<property>

        <name>yarn.scheduler.maximum-allocation-mb</name>

        <value>2048</value>

</property>

<!--多长时间聚合删除一次日志 此处-->

<property>

        <name>yarn.log-aggregation.retain-seconds</name>

        <value>2592000</value><!--30 day-->

</property>

<!--时间在几秒钟内保留用户日志。只适用于如果日志聚合是禁用的-->

<property>

        <name>yarn.nodemanager.log.retain-seconds</name>

        <value>604800</value><!--7 day-->

</property>

<!--指定文件压缩类型用于压缩汇总日志-->

<property>

        <name>yarn.nodemanager.log-aggregation.compression-type</name>

        <value>gz</value>

</property>

<!-- nodemanager本地文件存储目录-->

<property>

        <name>yarn.nodemanager.local-dirs</name>

        <value>/opt/server/hadoop-2.7.5/yarn/local</value>

</property>

<!-- resourceManager  保存最大的任务完成个数 -->

<property>

        <name>yarn.resourcemanager.max-completed-applications</name>

        <value>1000</value>

</property>

<!-- 逗号隔开的服务列表，列表名称应该只包含a-zA-Z0-9_,不能以数字开始-->

<property>

        <name>yarn.nodemanager.aux-services</name>

        <value>mapreduce_shuffle</value>

</property>



<!--rm失联后重新链接的时间--> 

<property>

        <name>yarn.resourcemanager.connect.retry-interval.ms</name>

        <value>2000</value>

</property>

</configuration>

<configuration>

<!--指定运行mapreduce的环境是yarn -->

<property>

        <name>mapreduce.framework.name</name>

        <value>yarn</value>

</property>

<!-- MapReduce JobHistory Server IPC host:port -->

<property>

        <name>mapreduce.jobhistory.address</name>

        <value>node3:10020</value>

</property>

<!-- MapReduce JobHistory Server Web UI host:port -->

<property>

        <name>mapreduce.jobhistory.webapp.address</name>

        <value>node0:19888</value>

</property>

<!-- The directory where MapReduce stores control files.默认 ${hadoop.tmp.dir}/mapred/system -->

<property>

        <name>mapreduce.jobtracker.system.dir</name>

        <value>/opt/server/hadoop-2.7.5/data/system/jobtracker</value>

</property>

<!-- The amount of memory to request from the scheduler for each map task. 默认 1024-->

<property>

        <name>mapreduce.map.memory.mb</name>

        <value>1024</value>

</property>

<!-- <property>

                <name>mapreduce.map.java.opts</name>

                <value>-Xmx1024m</value>

        </property> -->

<!-- The amount of memory to request from the scheduler for each reduce task. 默认 1024-->

<property>

        <name>mapreduce.reduce.memory.mb</name>

        <value>1024</value>

</property>

<!-- <property>

               <name>mapreduce.reduce.java.opts</name>

               <value>-Xmx2048m</value>

        </property> -->

<!-- 用于存储文件的缓存内存的总数量，以兆字节为单位。默认情况下，分配给每个合并流1MB，给个合并流应该寻求最小化。默认值100-->

<property>

        <name>mapreduce.task.io.sort.mb</name>

        <value>100</value>

</property>

 

<!-- <property>

        <name>mapreduce.jobtracker.handler.count</name>

        <value>25</value>

        </property>-->

<!-- 整理文件时用于合并的流的数量。这决定了打开的文件句柄的数量。默认值10-->

<property>

        <name>mapreduce.task.io.sort.factor</name>

        <value>10</value>

</property>

<!-- 默认的并行传输量由reduce在copy(shuffle)阶段。默认值5-->

<property>

        <name>mapreduce.reduce.shuffle.parallelcopies</name>

        <value>15</value>

</property>

<property>

        <name>yarn.app.mapreduce.am.command-opts</name>

        <value>-Xmx1024m</value>

</property>

<!-- MR AppMaster所需的内存总量。默认值1536-->

<property>

        <name>yarn.app.mapreduce.am.resource.mb</name>

        <value>1536</value>

</property>

<!-- MapReduce存储中间数据文件的本地目录。目录不存在则被忽略。默认值${hadoop.tmp.dir}/mapred/local-->

<property>

        <name>mapreduce.cluster.local.dir</name>

        <value>/opt/server/hadoop-2.7.5/data/system/local</value>

</property>

</configuration>

node1

node2

node3

export JAVA_HOME=/export/server/jdk1.8.0_241

cd /opt/server

scp -r hadoop-2.7.5/ node2:$PWD

scp -r hadoop-2.7.5/ node3:$PWD

mkdir -p /opt/server/hadoop-2.7.5/data/dfs/nn/name

mkdir -p /opt/server/hadoop-2.7.5/data/dfs/nn/edits

mkdir -p /opt/server/hadoop-2.7.5/data/dfs/nn/name

mkdir -p /opt/server/hadoop-2.7.5/data/dfs/nn/edits

vim yarn-site.xml

<property>       

<name>yarn.resourcemanager.ha.id</name>

<value>rm2</value>

   <description>If we want to launch more than one RM in single node, we need this configuration</description>

</property>

cd   /opt/server/hadoop-2.7.5

bin/hdfs zkfc -formatZK

sbin/hadoop-daemons.sh start journalnode

bin/hdfs namenode -format

bin/hdfs namenode -initializeSharedEdits -force

sbin/start-dfs.sh

cd   /opt/server/hadoop-2.7.5

bin/hdfs namenode -bootstrapStandby

sbin/hadoop-daemon.sh start namenode

cd   /opt/server/hadoop-2.7.5

sbin/start-yarn.sh

cd   /export/servers/hadoop-2.7.5

sbin/start-yarn.sh

cd   /opt/server/hadoop-2.7.5

bin/yarn rmadmin -getServiceState rm1

cd   /opt/server/hadoop-2.7.5

bin/yarn rmadmin -getServiceState rm2

cd /opt/server/hadoop-2.7.5

sbin/mr-jobhistory-daemon.sh start historyserver