0
0

Hadoop 3.1.1 HDFS 集群部署

Hadoop 3.1.1 HDFS 集群部署

依赖服务

系统优化

  • 每个节点都需进行如下优化
# 按需求更改主机名hostname hadoop1

# 关闭 SELinux# 将 SELINUX 值更改为 disabledvi /etc/selinux/config
SELINUX=disabled

# 需要重启后才可生效# 查看 SELinux 状态
getenforce

# 关闭防火墙
systemctl stop firewalld && systemctl disable firewalld && systemctl status firewalld

# 安装 Chrony 服务
yum install chrony -y# 配置 Chrony 服务# 注释默认的 NTP 服务地址# 配置所需的 NTP 服务地址vi /etc/chonry.conf
server hadoop1 iburst

# 重启 Chrony 服务并配置开机自启
systemctl enable chronyd --now# 查看 Chrony 服务状态
chronyc sources -v210 Number of sources =1
.-- Source mode  '^'= server, '='= peer, '#'=local clock.
/ .- Source state '*'= current synced, '+'= combined , '-'= not combined,
| /   '?'= unreachable, 'x'=time may be in error, '~'=time too variable.
||                                                 .- xxxx [ yyyy ] +/- zzzz
||      Reachability register (octal) -.           |  xxxx = adjusted offset,
||      Log2(Polling interval) --.      ||  yyyy = measured offset,
||\||  zzzz = estimated error.
||||       
MS Name/IP address         Stratum Poll Reach LastRx Last sample
====================================================================================================================
^* hadoop1                        4637712    -28us[  -45us] +/-   75ms

# 配置免密登录# 所有节点生成 id_rsa.pub
ssh-keygen -t rsa

# 将每个节点的 id_rsa.pub 信息，分别放入所有节点的 authorized_keys 文件内cat id_rsa.pub >> hadoop1:/root/.ssh/authorized_keys
cat id_rsa.pub >> hadoop2:/root/.ssh/authorized_keys
cat id_rsa.pub >> hadoop3:/root/.ssh/authorized_keys

# 最终效果cat /root/.ssh/authorized_keys
# redis-nodes
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDwuKw9LdfDO3Ln+ViNtQEqZtH/RvoFymKkexBXRUK/2XcczKHPv967KHH71L/5vPOQPUXZLZg3TPERlRTIW9MvCh0LmceGAiQHrxczx56RnYh8nESknd2jbHBToGwqgoB8xsB2IQuhze0CqvRs7A0nrbyBvnUpg/DvePTOSSgii4z9kishBCbrCPamQm20drXVDK3gQ9Q+/YJLKa3+mxzI67xfk/jby0A0DD9XKL7fflRgMK0GXEtYsJ04tKc5Bo+w6Zc8gHyryFrKD4wpeoPakqmrdzaTVYI1x5WvrAPrQplxAP8iNfBqRJSHvlDBXVeXgSxz2I4HBshsStkKp root@redis1
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDkspWeTwWoWyr6biMnefOYT4kh+7gPAboHAWe7p67IR9pfu+Rkk/vxLFDbi7X6Td9AhIXEZH6fY5BhihBzhRO/VtjE24QqnXdOLDHV1i0rSEYh6GOAbnVl/93lKidQF/2wvnQET31m1iwls3ul6aWw8/pOcxWy6kB+6MRiOExhu+0erE3jBFLcl+e0IJLKp/nLjCof/qWh3hLGVyhgMn/WmGhf7OyUbedXFqAwwS83/M60jSL1nB1lnIOoHrNSdnrN/GJVXmmwJjJAG4g4hbAg2zNind2rz6p4mq5k7iBbDUFghFwKKYsGeV0Onm7SKErFlHCJNFSOgfVNpaUYJ root@redis2
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQC+DGKAYw3tbdmv2GDsz3HEOdoKk8JVCEvDFczap2g3DoaqwEBkRag2l9IQ3RZL/WtpKe0f2vZzcm5t3d7e6YhyfEXRn1fjOmynTcykB13xAVrlRfJ6Sayur0OiPzWBktpNj8qaTKjwH+lyHGBwa5duqKiVEglEH2mX5grcOa/mH2Mo+IWsCYeCldKjfdBy2drlAim1fYvJwvtg0uDe8sfDUdDonG4phNOVaWB2u79SxKlGnGewGNuOrifIzkbc0mH9kNgrlw/xdSIqaFA738Yn/4n/kSe3BgceJ0wBowLzorgW2ogyGOdQp6MzBRlg/hxn4EDLJisrC9mSCMOOl root@redis3

# hadoop-nodes
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQCvWawSJqu4/Adnu6TjvV8rVDAqTU2CGNaSBOTDjcytHHOaY8UiwUMKvXUJugBmRkyhtWhQPHrVSmOH6+qMnHk5XQcWBmce8qCQqDoz49WwyZH95ciY/ynKR9dzAJwXN5fvJEoKxBhSJLk27SDsgRUX05IAjTN5Wx05GCNC36CRGHr6bwsC5iK+nv1ZllkRPyqoICJcvVVoJFDe+svNwLJS8bEpTUS/3C6w1RdfEgGVK0/NLnmANz6VIu5LAZqOpwFcB8Zed3wgnoHUfDCSXLEUQbcgRxDvba7lcvOqbiNh4Tr6WctSHw0UD9PSK6AXdS0jAAyjZ1J5kbWaI+vmZ root@hadoop1
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQCwCqgQWDgw7sSqNer1oONzsFhoCWBmLqdWOQCcC7RYhD6kiVzdAEP7qZwWKRwoe/E++xP0+slgxsIsXGVoObGrlT3n+g/2xsgTCaBT/6sGV7k28UOozh76GlyfJjzavbwWE9Q2yR2mkb3/ILGE6CUNCkqqLuYEDTG4DxNupGhsGSYChAcjclzYFrMxDARiOJ8cahDjVlmGzFWxNhzJ36pFC1Rdyeu4CrtZ8tkuqQagGZqB63bVmvTiOM2fY8Wp8TNv0Zz2XmFmv7IUhpDXlPZdFCviwLYLLoJ9LTG32rO/jY0U78LFdDpsYdebthztNakKMZEhCqVIR+k1VMPtp root@hadoop2
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDHmj5qT64jSc3LCR2EBKB+12C1XxhFlc44X8zdf3mL8gbepG+ndMgBV4eombLg7QjZshCsjhk9d8esofAlrPk5tX/nWWHg3p5jYTh5/6V+iU7VDpWmMVN/87dsjBbmM9P6jTNiwqk4rdSXDKXkmrVygGHnEj95eP35Nq1JKg+GS7RjWWB0+loGQ4eYKO1nj2nYNOlNBi28CKh1uMWf42bDtcfKP3Z4gEOtPBD5rVPiU2Tq6jgtAs/VvaYGv5FHO4MB0lBE1ik8zp/4trfGU5hie/1PzCRAIvsqPEBSzeUs9nhHODj6vZYwgQupK9Qv5jEbQgh6pCGEfFZlfsC03 root@hadoop3

# 配置 OracleJDK# 下载 Oracle JDK 并存放至指定路径内# 配置 /etc/profile 文件cat> /etc/profile <<EOF

# Oracle JDK 1.8.0_333
export JAVA_HOME=/data/service/jdk/jdk1.8.0_333
export CLASSPATH=$:CLASSPATH:$JAVA_HOME/lib/
export PATH=$PATH:$JAVA_HOME/bin
EOF# 刷新配置source /etc/profile

# 查看 JDK 状态java-versionjava version "1.8.0_333"
Java(TM) SE Runtime Environment (build 1.8.0_333-b02)
Java HotSpot(TM)64-Bit Server VM (build 25.333-b02, mixed mode)# 配置 HOSTS 文件cat> /etc/hosts <<EOF
# redis-nodes
10.10.10.21 redis1
10.10.10.22 redis2
10.10.10.23 redis3

# hadoop-nodes
10.10.10.131 hadoop1
10.10.10.132 hadoop2
10.10.10.133 hadoop3
EOF# 关闭 swap
swapoff -a# 注销 swap 分区挂载vi /etc/fstab

# 配置 vm.swapinessecho"vm.swappiness = 0">> /etc/sysctl.conf

# 刷新配置sysctl-p# 配置 transparent_hugepage# 临时生效echo never > /sys/kernel/mm/transparent_hugepage/enabled &&echo never > /sys/kernel/mm/transparent_hugepage/defrag

# 永久生效echo"echo never > /sys/kernel/mm/transparent_hugepage/enabled">> /etc/rc.local &&echo"echo never > /sys/kernel/mm/transparent_hugepage/defrag">> /etc/rc.local

# 配置 最大连接数# CentOS6 的文件名为 90-nproc.conf# CentOS7 的文件名为 20-nproc.confvi /etc/security/limits.d/20-nproc.conf
* - nofile 655350
* - nproc 655350

查看 ZooKeeper 集群状态

$ZK_HOME/bin/zkCli.sh -server hadoop1:2181,hadoop2:2181,hadoop3:2181
[zk: hadoop1:2181,hadoop2:2181,hadoop3:2181(CONNECTED)0]ls /
[admin, brokers, cluster, config, consumers, controller, controller_epoch, hadoop-ha, hbase, isr_change_notification, latest_producer_id_block, log_dir_event_notification, rmstore, spark, yarn-leader-election, zookeeper]

创建路径

  • 每个节点都需创建如下路径
mkdir-p /data/service/hadoop/{hadoop_logs,hadoop_pid,hadoop_tmp,hdfs_nn1,hdfs_nn2,hdfs_dn1,hdfs_dn2,hdfs_dn3}

配置 /etc/profile

  • 每个节点都需配置如下环境变量
  • 以便于后续启停及使用 HDFS 相关脚本和命令
# Hadoop 3.1.1exportHADOOP_HOME=/data/service/hadoop/hadoop-3.1.1
exportPATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/lib

配置 $HADOOP_HOME/etc/hadoop/hadoop-env.sh

exportJAVA_HOME="/data/service/jdk/jdk1.8.0_333"exportHADOOP_HOME="/data/service/hadoop/hadoop-3.1.1"exportHADOOP_CONF_DIR="/data/service/hadoop/hadoop-3.1.1/etc/hadoop"exportHADOOP_LOG_DIR="/data/service/hadoop/hadoop_logs"exportHADOOP_PID_DIR="/data/service/hadoop/hadoop_pid"exportHDFS_NAMENODE_OPTS="-Xms1024m -Xmx1024m -XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=80 -XX:+CMSParallelRemarkEnabled"exportHDFS_DATANODE_OPTS="-Xms512m -Xmx512m -XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=80 -XX:+CMSParallelRemarkEnabled"exportHDFS_ZKFC_OPTS="-Xms512m -Xmx512m -XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=80 -XX:+CMSParallelRemarkEnabled"exportHDFS_JOURNALNODE_OPTS="-Xms512m -Xmx512m -XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=80 -XX:+CMSParallelRemarkEnabled"exportHDFS_NAMENODE_USER=root
exportHDFS_DATANODE_USER=root
exportHDFS_ZKFC_USER=root
exportHDFS_JOURNALNODE_USER=root

配置 $HADOOP_HOME/etc/hadoop/core-site.xml

<configuration><property><name>fs.defaultFS</name><value>hdfs://hdfscluster</value><description>指定默认 HDFS 名称</description></property><property><name>hadoop.tmp.dir</name><value>/data/service/hadoop/hadoop_tmp</value><description>指定 HDFS 临时文件存放路径</description></property><property><name>hadoop.http.staticuser.user</name><value>root</value><description>指定 HDFS Web UI 操作 HDFS 的用户</description></property><property><name>ha.zookeeper.quorum</name><value>hadoop1:2181,hadoop2:2181,hadoop3:2181</value><description>指定 ZooKeeper 地址</description></property><property><name>fs.trash.interval</name><value>1440</value><description>指定垃圾桶内数据保留时间。默认为 0，即关闭。单位为分钟</description></property></configuration>

创建 DataNode 黑名单文件

touch$HADOOP_HOME/etc/hadoop/hdfs-exclude.txt

配置 $HADOOP_HOME/etc/hadoop/hdfs-site.xml

<configuration><property><name>dfs.namenode.name.dir</name><value>
      /data/service/hadoop/hdfs_nn1
      /data/service/hadoop/hdfs_nn2
    </value><description>指定 NameNode 元数据存放路径</description></property><property><name>dfs.hosts.exclude</name><value>/data/service/hadoop/hadoop-3.1.1/etc/hadoop/hdfs-exclude.txt</value><description>DataNode 黑名单文件路径</description></property><property><name>dfs.datanode.du.reserved</name><value>1024</value><description>指定每块磁盘的保留空间。单位为字节。默认为 0</description></property><property><name>dfs.data.dir</name><value>
      /data/service/hadoop/hdfs_dn1
      /data/service/hadoop/hdfs_dn2
      /data/service/hadoop/hdfs_dn3
    </value><description>指定 DataNode 数据存放路径</description></property><property><name>dfs.datanode.failed.volumes.tolerated</name><value>1</value><description>指定 DataNode 最多能够故障多少块磁盘</description></property><property><name>dfs.replication</name><value>2</value><description>指定数据副本数。默认值为 3</description></property><property><name>dfs.nameservices</name><value>hdfscluster</value><description>指定 HDFS 名字，需与 core-site.xml 中一致。后续配置也与此相同</description></property><property><name>dfs.namenode.acls.enabled</name><value>true</value><description>开启 ACL 权限管理功能</description></property><property><name>dfs.disk.balancer.enabled</name><value>true</value><description>开启磁盘负载均衡功能</description></property><!-- NN HA功能 --><property><name>dfs.ha.namenodes.hdfscluster</name><value>nn1,nn2,nn3</value><description>指定 NameNode ID</description></property><property><name>dfs.namenode.rpc-address.hdfscluster.nn1</name><value>hadoop1:8020</value><description>指定 nn1 的 RPC 地址</description></property><property><name>dfs.namenode.rpc-address.hdfscluster.nn2</name><value>hadoop2:8020</value><description>指定 nn2 的 RPC 地址</description></property><property><name>dfs.namenode.rpc-address.hdfscluster.nn3</name><value>hadoop3:8020</value><description>指定 nn3 的 RPC 地址</description></property><property><name>dfs.namenode.http-address.hdfscluster.nn1</name><value>hadoop1:9870</value><description>指定 nn1 的访问地址</description></property><property><name>dfs.namenode.http-address.hdfscluster.nn2</name><value>hadoop2:9870</value><description>指定 nn2 的访问地址</description></property><property><name>dfs.namenode.http-address.hdfscluster.nn3</name><value>hadoop3:9870</value><description>指定 nn3 的访问地址</description></property><property><name>dfs.namenode.shared.edits.dir</name><value>qjournal://redis1:8485;redis2:8485;redis3:8485/hdfscluster</value><description>指定 JournalNode 同步 NameNode 元数据的存放路径</description></property><property><name>dfs.client.failover.proxy.provider.hdfscluster</name><value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value><description>指定高可用方案，失败后自动切换的方式</description></property><property><name>dfs.ha.fencing.methods</name><value>shell(/bin/true)</value><description>指定 ssh 方案</description></property><property><name>dfs.ha.fencing.ssh.private-key-files</name><value>/root/.ssh/id_rsa</value><description>指定 ssh key 路径</description></property><property><name>dfs.journalnode.edits.dir</name><value>/data/service/hadoop/hdfs_jn</value><description>指定 JournalNode 数据存放路径</description></property><property><name>dfs.ha.automatic-failover.enabled</name><value>true</value><description>开启自动故障转移。但开启后，手动故障转移将失效</description></property><!-- 参数优化 --><property><name>dfs.namenode.handler.count</name><value>21</value><description>NameNode 的服务器线程的数量。计算公式：20 * log2(集群节点数)</description></property><property><name>dfs.namenode.handler.count</name><value>21</value><description>NameNode 用于服务调用的服务器线程数量。计算公式：20 * log2(集群节点数)</description></property><property><name>dfs.datanode.handler.count</name><value>21</value><description>DataNode 服务器线程数。计算公式：python -c 'import math ; print int(math.log(N) * 20)'</description></property><property><name>dfs.datanode.max.transfer.threads</name><value>8192</value><description>指定在 DataNode 内外传输数据使用的最大线程数。默认值为4096</description></property></configuration>

配置 $HADOOP_HOME/etc/hadoop/workers

hadoop1
hadoop2
hadoop3

分发配置

  • 将 /data/service/hadoop 分发至所有节点

初始化 HDFS

1. 初始化之前需提前启动所有的 JN

hdfs --daemon start journalnode

2. 初始化 HDFS 命名空间，只需在 NN-Master 节点进行初始化

hdfs namenode -format hadoop1

3. 创建并初始化 ZK 路径

hdfs zkfc -formatZK

启动 HDFS

1. NameNode-Master

hdfs --daemon start namenode

2. NameNode-Backup

hdfs namenode -bootstrapStandby

3. NameNode-Master

$HADOOP_HOME/sbin/start-dfs.sh

验证 HDFS 状态

  • HDFS Web UI：10.10.10.131:9870
  • HDFS Web UI：10.10.10.132:9870
  • HDFS Web UI：10.10.10.133:9870
  • 命令行查看
hdfs haadmin -getServiceState nn1
Active

hdfs haadmin -getServiceState nn2
Standby

hdfs haadmin -getServiceState nn3
Standby

hdfs dfsadmin -report
Configured Capacity: 454060661760(422.88 GB)
Present Capacity: 422851436544(393.81 GB)
DFS Remaining: 422851325952(393.81 GB)
DFS Used: 110592(108 KB)
DFS Used%: 0.00%
Replicated Blocks:
  Under replicated blocks: 0
  Blocks with corrupt replicas: 0
  Missing blocks: 0
  Missing blocks (with replication factor 1): 0
  Pending deletion blocks: 0
Erasure Coded Block Groups: 
  Low redundancy block groups: 0
  Block groups with corrupt internal blocks: 0
  Missing block groups: 0
  Pending deletion blocks: 0

-------------------------------------------------
Live datanodes (3):
Name: 10.10.10.131:9866 (hadoop1)
Hostname: hadoop1
Decommission Status : Normal
Configured Capacity: 151353553920(140.96 GB)
DFS Used: 36864(36 KB)
Non DFS Used: 10601001984(9.87 GB)
DFS Remaining: 140752515072(131.09 GB)
DFS Used%: 0.00%
DFS Remaining%: 93.00%
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: Wed Nov 1614:05:29 CST 2022
Last Block Report: Wed Nov 1610:26:13 CST 2022
Num of Blocks: 0

Name: 10.10.10.132:9866 (hadoop2)
Hostname: hadoop2
Decommission Status : Normal
Configured Capacity: 151353553920(140.96 GB)
DFS Used: 36864(36 KB)
Non DFS Used: 10296947712(9.59 GB)
DFS Remaining: 141056569344(131.37 GB)
DFS Used%: 0.00%
DFS Remaining%: 93.20%
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: Wed Nov 1614:05:29 CST 2022
Last Block Report: Wed Nov 1613:02:34 CST 2022
Num of Blocks: 0

Name: 10.10.10.133:9866 (hadoop3)
Hostname: hadoop3
Decommission Status : Normal
Configured Capacity: 151353553920(140.96 GB)
DFS Used: 36864(36 KB)
Non DFS Used: 10311275520(9.60 GB)
DFS Remaining: 141042241536(131.36 GB)
DFS Used%: 0.00%
DFS Remaining%: 93.19%
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: Wed Nov 1614:05:29 CST 2022
Last Block Report: Wed Nov 1610:53:26 CST 2022
Num of Blocks: 0

常用操作

# 获取指定参数的配置
hdfs getconf -confKey<config key># 创建测试文件echo1> test.log

# 创建测试目录
hdfs dfs -mkdir hdfs://hdfscluster/test/

# 上传文件
hdfs dfs -put hdfs://hdfscluster/test/test.log ./

# 下载文件
hdfs dfs -get hdfs://hdfscluster/test/test.log ./

# 删除文件
hdfs dfs -rm hdfs://hdfscluster/test/test.log

# 删除文件并跳过垃圾回收
hdfs dfs -rm –skipTrash hdfs://hdfscluster/test/test.log
标签： hadoop hdfs 大数据
本文转载自: https://blog.csdn.net/weixin_42598916/article/details/135726131
版权归原作者 JP.Hu 所有， 如有侵权，请联系我们删除。
登录后发布评论

“Hadoop 3.1.1 HDFS 集群部署”的评论:

还没有评论
关于作者
...
overfit同步小助手
文章同步
相关阅读

【网络】深入理解 HTTPS：确保数据传输安全的核心协议

【K8S问题系列 | 8】K8S集群资源突然爆满导致 Pod 状态变为 Pending 详细解决方案

[Linux]——常见指令（下）及权限

在VsCode中实现ESP-NOW通信

极客的最爱：Vim 编辑器深度解析

SpringBoot在线教育系统：性能优化策略

hadoop期末复习重点知识点总结集锦

文章导航