1、如果你使用root用户进行安装。 vi /etc/profile 即可 系统变量
2、如果你使用普通用户进行安装。 vi ~/.bashrc 用户变量
export HADOOP_HOME=/export/servers/hadoop-2.8.5
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:
同步配置文件
[root@jiang01 servers]# vi /etc/profile
[root@jiang01 servers]#
[root@jiang01 servers]# xrsync.sh /etc/profile
=========== jiang02 : /etc/profile ===========
命令执行成功
=========== jiang03 : /etc/profile ===========
命令执行成功
[root@jiang01 servers]#
刷新配置各个机器配置：
source /etc/profile
修改下面各个配置文件：
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<configuration>
<!-- 指定hdfs的nameservice为ns1 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://myha01/</value>
</property>
<!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/export/servers/hadoop-2.8.5/hadoopDatas/tempDatas</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>jiang01:2181,jiang02:2181,jiang03:2181</value>
</property>
</configuration>
core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<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>myha01</value>
</property>
<!-- ns1下面有两个NameNode，分别是nn1，nn2 -->
<property>
<name>dfs.ha.namenodes.myha01</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.myha01.nn1</name>
<value>jiang01:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.myha01.nn1</name>
<value>jiang01:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.myha01.nn2</name>
<value>jiang02:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.myha01.nn2</name>
<value>jiang02:50070</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://jiang01:8485;jiang02:8485;jiang03:8485/myha01</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>/opt/hadoop-2.8.5/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.myha01</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 配置隔离机制 -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<!-- 使用隔离机制时需要ssh免登陆 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_dsa</value>
</property>
</configuration>
hdfs-site.xml
<?xml version="1.0"?>
<!--
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. See accompanying LICENSE file.
-->
<configuration>
<!-- Site specific YARN configuration properties -->
<!-- 开启RM高可靠 -->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<!-- 指定RM的cluster id -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yrc</value>
</property>
<!-- 指定RM的名字 -->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!-- 分别指定RM的地址 -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>jiang02</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>jiang03</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>jiang01:2181,jiang02:2181,jiang03:2181</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>
yarn-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<configuration>
<!-- 指定mr框架为yarn方式 -->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
mapred-site.xml
[root@jiang01 servers]# hadoop version Hadoop 2.8.5 Subversion https://git-wip-us.apache.org/repos/asf/hadoop.git -r 0b8464d75227fcee2c6e7f2410377b3d53d3d5f8 Compiled by jdu on 2018-09-10T03:32Z Compiled with protoc 2.5.0 From source with checksum 9942ca5c745417c14e318835f420733 This command was run using /export/servers/hadoop-2.8.5/share/hadoop/common/hadoop-common-2.8.5.jar [root@jiang01 servers]#查看hadoop版本
启动zk
[root@jiang01 servers]# [root@jiang01 servers]# xcall.sh jps -l ============= jiang01 : jps -l ============ 10262 org.apache.zookeeper.server.quorum.QuorumPeerMain 10571 sun.tools.jps.Jps 命令执行成功 ============= jiang02 : jps -l ============ 10162 sun.tools.jps.Jps 9991 org.apache.zookeeper.server.quorum.QuorumPeerMain 命令执行成功 ============= jiang03 : jps -l ============ 2275 org.apache.zookeeper.server.quorum.QuorumPeerMain 2436 sun.tools.jps.Jps 命令执行成功 [root@jiang01 servers]# xcall.sh zkServer.sh status ============= jiang01 : zkServer.sh status ============ ZooKeeper JMX enabled by default Using config: /export/servers/zookeeper-3.4.14/bin/../conf/zoo.cfg Mode: follower 命令执行成功 ============= jiang02 : zkServer.sh status ============ ZooKeeper JMX enabled by default Using config: /export/servers/zookeeper-3.4.14/bin/../conf/zoo.cfg Mode: leader 命令执行成功 ============= jiang03 : zkServer.sh status ============ ZooKeeper JMX enabled by default Using config: /export/servers/zookeeper-3.4.14/bin/../conf/zoo.cfg Mode: follower 命令执行成功 [root@jiang01 servers]#启动zk
在你配置的各个journalnode节点启动该进程
[root@jiang01 servers]# [root@jiang01 servers]# xcall.sh hadoop-daemon.sh start journalnode ============= jiang01 : hadoop-daemon.sh start journalnode ============ starting journalnode, logging to /export/servers/hadoop-2.8.5/logs/hadoop-root-journalnode-jiang01.out 命令执行成功 ============= jiang02 : hadoop-daemon.sh start journalnode ============ starting journalnode, logging to /export/servers/hadoop-2.8.5/logs/hadoop-root-journalnode-jiang02.out 命令执行成功 ============= jiang03 : hadoop-daemon.sh start journalnode ============ starting journalnode, logging to /export/servers/hadoop-2.8.5/logs/hadoop-root-journalnode-jiang03.out 命令执行成功 [root@jiang01 servers]#启动journalnode
先选取一个namenode（jiang01）节点进行格式化
[root@jiang01 servers]# hadoop namenode -formatView Code
格式化zkfc，只能在nameonde节点进行
主节点上面启动 dfs文件系统：
[root@jiang01 dfs]# start-dfs.sh
jiang002启动yarm
[root@jiang02 mapreduce]# start-yarn.sh starting yarn daemons starting resourcemanager, logging to /export/servers/hadoop-2.8.5/logs/yarn-root-resourcemanager-jiang02.out jiang03: starting nodemanager, logging to /export/servers/hadoop-2.8.5/logs/yarn-root-nodemanager-jiang03.out jiang01: starting nodemanager, logging to /export/servers/hadoop-2.8.5/logs/yarn-root-nodemanager-jiang01.out jiang02: starting nodemanager, logging to /export/servers/hadoop-2.8.5/logs/yarn-root-nodemanager-jiang02.out [root@jiang02 mapreduce]#View Code
jiang03启动：resourcemanager
[root@jiang03 hadoopDatas]# yarn-daemon.sh start resourcemanager starting resourcemanager, logging to /export/servers/hadoop-2.8.5/logs/yarn-root-resourcemanager-jiang03.outView Code
hadoop wordcount程序启动：
1 cd /export/servers/hadoop-2.8.5/share/hadoop/mapreduce/
2 生成数据文件：
touch word.txt echo "hello world" >> word.txt echo "hello hadoop" >> word.txt echo "hello hive" >> word.txt
3 创建hadoop 文件目录
hdfs dfs -mkdir -p /work/data/input
4 向hadoop上传数据文件
hdfs dfs -put ./word.txt /work/data/input
5 计算例子
hadoop jar hadoop-mapreduce-examples-2.8.5.jar wordcount /work/data/input /work/data/output
6 查看结果：
[root@jiang01 mapreduce]# hadoop jar hadoop-mapreduce-examples-2.8.5.jar wordcount /work/data/input /work/data/output
19/10/09 11:44:48 INFO input.FileInputFormat: Total input files to process : 1
19/10/09 11:44:48 INFO mapreduce.JobSubmitter: number of splits:1
19/10/09 11:44:48 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1570635804389_0001
19/10/09 11:44:48 INFO impl.YarnClientImpl: Submitted application application_1570635804389_0001
19/10/09 11:44:48 INFO mapreduce.Job: The url to track the job: http://jiang02:8088/proxy/application_1570635804389_0001/
19/10/09 11:44:48 INFO mapreduce.Job: Running job: job_1570635804389_0001
19/10/09 11:45:00 INFO mapreduce.Job: Job job_1570635804389_0001 running in uber mode : false
19/10/09 11:45:00 INFO mapreduce.Job: map 0% reduce 0%
19/10/09 11:45:11 INFO mapreduce.Job: map 100% reduce 0%
19/10/09 11:45:20 INFO mapreduce.Job: map 100% reduce 100%
19/10/09 11:45:20 INFO mapreduce.Job: Job job_1570635804389_0001 completed successfully
19/10/09 11:45:21 INFO mapreduce.Job: Counters: 49
File System Counters
FILE: Number of bytes read=54
FILE: Number of bytes written=321397
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=139
HDFS: Number of bytes written=32
HDFS: Number of read operations=6
HDFS: Number of large read operations=0
HDFS: Number of write operations=2
Job Counters
Launched map tasks=1
Launched reduce tasks=1
Data-local map tasks=1
Total time spent by all maps in occupied slots (ms)=8790
Total time spent by all reduces in occupied slots (ms)=6229
Total time spent by all map tasks (ms)=8790
Total time spent by all reduce tasks (ms)=6229
Total vcore-milliseconds taken by all map tasks=8790
Total vcore-milliseconds taken by all reduce tasks=6229
Total megabyte-milliseconds taken by all map tasks=9000960
Total megabyte-milliseconds taken by all reduce tasks=6378496
Map-Reduce Framework
Map input records=3
Map output records=6
Map output bytes=60
Map output materialized bytes=54
Input split bytes=103
Combine input records=6
Combine output records=4
Reduce input groups=4
Reduce shuffle bytes=54
Reduce input records=4
Reduce output records=4
Spilled Records=8
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=199
CPU time spent (ms)=1320
Physical memory (bytes) snapshot=325742592
Virtual memory (bytes) snapshot=4161085440
Total committed heap usage (bytes)=198316032
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=36
File Output Format Counters
Bytes Written=32
View Code