准备工作
1.搭建虚拟机集群
请参考
centos7虚拟机集群搭建
2.安装zookeeper集群
请参考
zookeeper集群搭建
3.下载或编译hadoop3.2.2安装包
请参考
hadoop3.2.2源码包编译
安装阶段
1.创建安装目录并解压安装包
在node1服务器上执行
#解压文件
tar -zxvf hadoop-3.2.2.tar.gz -C /home/
2.修改配置文件
2.1 修改 core-site.xml
cd /home/hadoop-3.2.2/etc/hadoop
vi /core-site.xml
<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>/home/hadoop-3.2.2/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>
2.2 修改hdfs-site.xml
cd /home/hadoop-3.2.2/etc/hadoop
vi /hdfs-site.xml
<configuration>
<!-- 指定命名空间 -->
<property>
<name>dfs.nameservices</name>
<value>ns</value>
</property>
<!-- 指定该命名空间下的两个机器作为我们的NameNode -->
<property>
<name>dfs.ha.namenodes.ns</name>
<value>nn1,nn2</value>
</property>
<!-- 配置第一台服务器的namenode通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns.nn1</name>
<value>node1:8020</value>
</property>
<!-- 配置第二台服务器的namenode通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns.nn2</name>
<value>node2:8020</value>
</property>
<!-- 所有从节点之间相互通信端口地址 -->
<property>
<name>dfs.namenode.servicerpc-address.ns.nn1</name>
<value>node1:8022</value>
</property>
<!-- 所有从节点之间相互通信端口地址 -->
<property>
<name>dfs.namenode.servicerpc-address.ns.nn2</name>
<value>node2:8022</value>
</property>
<!-- 第一台服务器namenode的web访问地址 -->
<property>
<name>dfs.namenode.http-address.ns.nn1</name>
<value>node1:50070</value>
</property>
<!-- 第二台服务器namenode的web访问地址 -->
<property>
<name>dfs.namenode.http-address.ns.nn2</name>
<value>node2:50070</value>
</property>
<!-- journalNode的访问地址,注意这个地址一定要配置 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://node1:8485;node2:8485;node3:8485/ns1</value>
</property>
<!-- 指定故障自动恢复使用的哪个java类 -->
<property>
<name>dfs.client.failover.proxy.provider.ns</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 故障转移使用的哪种通信机制 -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<!-- 指定通信使用的公钥 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<!-- journalNode数据存放地址 -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/home/hadoop-3.2.2/data/dfs/jn</value>
</property>
<!-- 启用自动故障恢复功能 -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- namenode产生的文件存放路径 -->
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///home/hadoop-3.2.2/data/dfs/nn/name</value>
</property>
<!-- edits产生的文件存放路径 -->
<property>
<name>dfs.namenode.edits.dir</name>
<value>file:home/hadoop-3.2.2/data/dfs/nn/edits</value>
</property>
<!-- dataNode文件存放路径 -->
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///home/hadoop-3.2.2/data/dfs/dn</value>
</property>
<!-- 关闭hdfs的文件权限 -->
<property>
<name>dfs.permissions</name>
<value>false</value>
</property>
<!-- 指定block文件块的大小 -->
<property>
<name>dfs.blocksize</name>
<value>134217728</value>
</property>
</configuration>
2.3.修改修改yarn-site.xml
cd /home/hadoop-3.2.2/etc/hadoop
vi /yarn-site.xml
<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>node3</value>
</property>
<!-- 配置第二台机器的resourceManager -->
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>node2</value>
</property>
<!-- 配置第一台机器的resourceManager通信地址 -->
<property>
<name>yarn.resourcemanager.address.rm1</name>
<value>node3:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>node3:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm1</name>
<value>node3:8031</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address.rm1</name>
<value>node3:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>node3:8088</value>
</property>
<!-- 配置第二台机器的resourceManager通信地址 -->
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>node2:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>node2:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm2</name>
<value>node2:8031</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address.rm2</name>
<value>node2:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>node2:8088</value>
</property>
<!--开启resourcemanager自动恢复功能-->
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<!--在node1上配置rm1,在node2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>rm2</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>4</value>
</property>
<!-- 每个节点可用内存,单位MB -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>1536</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>1536</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>1536</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>/home/hadoop-3.2.2/data/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>
2.4.修改workers文件
(老版本叫slave文件)
cd /home/hadoop-3.2.2/etc/hadoop
vi workers
加入要工作的服务器列表
node1
node2
node3
2.5.修改hadoop-env.sh
cd /home/hadoop-3.2.2/etc/hadoop
vi hadoop-env.sh
添加本机jdk配置
export JAVA_HOME=/usr/local/jdk1.8.0_271
集群部署阶段
1.同步hadoop到其他节点
cd /home
scp -r hadoop-3.2.2/ node2:$PWD
2.三台机器同时创建目录
mkdir -p /home/hadoop-3.2.2/data/dfs/nn/name
mkdir -p /home/hadoop-3.2.2/data/dfs/nn/edits
mkdir -p /home/hadoop-3.2.2/data/dfs/nn/name
mkdir -p /home/hadoop-3.2.2/data/dfs/nn/edits
3.更改node2的rm2
cd /home/hadoop-3.2.2/etc/hadoop
vi yarn-site.xml
rm1修改rm2
<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>
启动阶段
1.启动hdfs
cd /home/hadoop-3.2.2
bin/hdfs zkfc -formatZK
2.启动 journalnode
sbin/hadoop-daemons.sh start journalnode
#格式化 namenode
bin/hdfs namenode -format
bin/hdfs namenode -initializeSharedEdits -force
#启动hdfs
sbin/start-dfs.sh
启动成功
jps查看进程 可以看到服务已经启动
node1
node2
node3
时间原因今天先到这里。
2.启动 yarn过程
node3节点启动yarn
cd /home/hadoop-3.2.2/etc/hadoop
sbin/start-yarn.sh
node2节点启动yarn
cd /home/hadoop-3.2.2/etc/hadoop
sbin/start-yarn.sh
3.查看resourceManager状态
node3上执行
cd /home/hadoop-3.2.2/etc/hadoop
bin/yarn rmadmin -getServiceState rm1
node2上执行
cd /home/hadoop-3.2.2/etc/hadoop
bin/yarn rmadmin -getServiceState rm1
4.启动jobHistory
node3机器执行以下命令启动jobHistory
cd /home/hadoop-3.2.2/etc/hadoop
sbin/mr-jobhistory-daemon.sh start historyserver
5.hdfs状态查看
主节点hdfs
http://192.168.60.11:50070/dfshealth.html#tab-datanode
备用节点hdfs
http://192.168.60.12:50070/dfshealth.html#tab-datanode
三个节点已经建立成功了。
6.yarn集群的查看
http://192.168.60.13:8088/cluster
7.历史任务的查看
http://192.168.60.13:19888/jobhistory/app
DEMO测试
跑一个pI程序
进入目录 /home/hadoop-3.2.2/share/hadoop/mapreduce
hadoop jar hadoop-mapreduce-examples-3.2.2.jar pi 5 5
内存不足错误排查
org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.yarn.exceptions.InvalidResourceRequestException): Invalid resource request! Cannot allocate containers as requested resource is greater than maximum allowed allocation. Requested resource type=[memory-mb], Requested resource=<memory:1536, vCores:1>, maximum allowed allocation=<memory:512, vCores:4>, please note that maximum allowed allocation is calculated by scheduler based on maximum resource of registered NodeManagers, which might be less than configured maximum allocation=<memory:512, vCores:4>
内存调整到1536
<!-- 每个节点可用内存,单位MB -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>1536</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>1536</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>1536</value>
</property>
错误排查:
Error: Could not find or load main class org.apache.hadoop.mapreduce.v2.app.MRAppMaster
Please check whether your etc/hadoop/mapred-site.xml contains the below configuration:
<property>
<name>yarn.app.mapreduce.am.env</name>
<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>
</property>
<property>
<name>mapreduce.map.env</name>
<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>
</property>
<property>
<name>mapreduce.reduce.env</name>
<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>
</property>
[2021-08-26 02:13:48.447]Container exited with a non-zero exit code 1. Error file: prelaunch.err.
Last 4096 bytes of prelaunch.err :
Last 4096 bytes of stderr :
Error: Could not find or load main class org.apache.hadoop.mapreduce.v2.app.MRAppMaster
Please check whether your etc/hadoop/mapred-site.xml contains the below configuration:
<property>
<name>yarn.app.mapreduce.am.env</name>
<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>
</property>
<property>
<name>mapreduce.map.env</name>
<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>
</property>
<property>
<name>mapreduce.reduce.env</name>
<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>
</property>
For more detailed output, check the application tracking page: http://node3:8088/cluster/app/application_1629943989622_0001 Then click on links to logs of each attempt.
. Failing the application.
2021-08-26 02:13:49,416 INFO mapreduce.Job: Counters: 0
Job job_1629943989622_0001 failed!
解决方案:根据提示,在所有master和slave的mapred-site.xml中添加如下内容:
<property>
<name>yarn.app.mapreduce.am.env</name>
<value>HADOOP_MAPRED_HOME=${HADOOP_HOME}</value>
</property>
<property>
<name>mapreduce.map.env</name>
<value>HADOOP_MAPRED_HOME=${HADOOP_HOME}</value>
</property>
<property>
<name>mapreduce.reduce.env</name>
<value>HADOOP_MAPRED_HOME=${HADOOP_HOME}</value>
</property>
程序执行成功!
File System Counters
FILE: Number of bytes read=116
FILE: Number of bytes written=1441455
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=1260
HDFS: Number of bytes written=215
HDFS: Number of read operations=25
HDFS: Number of large read operations=0
HDFS: Number of write operations=3
HDFS: Number of bytes read erasure-coded=0
Job Counters
Launched map tasks=5
Launched reduce tasks=1
Data-local map tasks=5
Total time spent by all maps in occupied slots (ms)=25558
Total time spent by all reduces in occupied slots (ms)=4745
Total time spent by all map tasks (ms)=25558
Total time spent by all reduce tasks (ms)=4745
Total vcore-milliseconds taken by all map tasks=25558
Total vcore-milliseconds taken by all reduce tasks=4745
Total megabyte-milliseconds taken by all map tasks=39257088
Total megabyte-milliseconds taken by all reduce tasks=7288320
Map-Reduce Framework
Map input records=5
Map output records=10
Map output bytes=90
Map output materialized bytes=140
Input split bytes=670
Combine input records=0
Combine output records=0
Reduce input groups=2
Reduce shuffle bytes=140
Reduce input records=10
Reduce output records=0
Spilled Records=20
Shuffled Maps =5
Failed Shuffles=0
Merged Map outputs=5
GC time elapsed (ms)=500
CPU time spent (ms)=4730
Physical memory (bytes) snapshot=1582936064
Virtual memory (bytes) snapshot=16672661504
Total committed heap usage (bytes)=1177026560
Peak Map Physical memory (bytes)=295788544
Peak Map Virtual memory (bytes)=2778599424
Peak Reduce Physical memory (bytes)=185905152
Peak Reduce Virtual memory (bytes)=2801176576
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=590
File Output Format Counters
Bytes Written=97
Job Finished in 32.885 seconds
Estimated value of Pi is 3.68000000000000000000