3.Hadoop完全分布式搭建
1.完全分布式搭建
-
配置
#cd /soft/hadoop/etc/ #mv hadoop local #cp -r local full #ln -s full hadoop #cd hadoop -
修改core-site.xml配置文件
#vim core-site.xml [core-site.xml配置如下] <?xml version="1.0"?> <configuration> <property> <name>fs.defaultFS</name> <value>hdfs://hadoop-1</value> </property> </configuration> -
修改hdfs-site.xml配置文件
#vim hdfs-site.xml [hdfs-site.xml配置如下] <?xml version="1.0"?> <configuration> <property> <name>dfs.replication</name> <value>3</value> </property> <property> <name>dfs.namenode.secondary.http-address</name> <value>hadoop-2:50090</value> </description> </property> </configuration> -
修改mapred-site.xml配置文件
#cp mapred-site.xml.template mapred-site.xml #vim mapred-site.xml [mapred-site.xml配置如下] <?xml version="1.0"?> <configuration> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> </configuration> -
修改yarn-site.xml配置文件
#vim yarn-site.xml [yarn-site.xml配置如下] <?xml version="1.0"?> <configuration> <property> <name>yarn.resourcemanager.hostname</name> <value>hadoop-1</value> </property> <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> </configuration> -
修改slaves配置文件
#vim slaves [salves] hadoop-2 hadoop-3 hadoop-4 hadoop-5 -
同步到其他节点
#scp -r /soft/hadoop/etc/full hadoop-2:/soft/hadoop/etc/ #scp -r /soft/hadoop/etc/full hadoop-3:/soft/hadoop/etc/ #scp -r /soft/hadoop/etc/full hadoop-4:/soft/hadoop/etc/ #scp -r /soft/hadoop/etc/full hadoop-5:/soft/hadoop/etc/ #ssh hadoop-2 ln -s /soft/hadoop/etc/full /soft/hadoop/etc/hadoop #ssh hadoop-3 ln -s /soft/hadoop/etc/full /soft/hadoop/etc/hadoop #ssh hadoop-4 ln -s /soft/hadoop/etc/full /soft/hadoop/etc/hadoop #ssh hadoop-5 ln -s /soft/hadoop/etc/full /soft/hadoop/etc/hadoop -
格式化hdfs分布式文件系统
#hadoop namenode -format -
启动服务
[root@hadoop-1 hadoop]# start-all.sh This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh Starting namenodes on [hadoop-1] hadoop-1: starting namenode, logging to /soft/hadoop-2.7.3/logs/hadoop-root-namenode-hadoop-1.out hadoop-2: starting datanode, logging to /soft/hadoop-2.7.3/logs/hadoop-root-datanode-hadoop-2.out hadoop-3: starting datanode, logging to /soft/hadoop-2.7.3/logs/hadoop-root-datanode-hadoop-3.out hadoop-4: starting datanode, logging to /soft/hadoop-2.7.3/logs/hadoop-root-datanode-hadoop-4.out hadoop-5: starting datanode, logging to /soft/hadoop-2.7.3/logs/hadoop-root-datanode-hadoop-5.out Starting secondary namenodes [hadoop-2] hadoop-2: starting secondarynamenode, logging to /soft/hadoop-2.7.3/logs/hadoop-root-secondarynamenode-hadoop-2.out starting yarn daemons starting resourcemanager, logging to /soft/hadoop-2.7.3/logs/yarn-root-resourcemanager-hadoop-1.out hadoop-3: starting nodemanager, logging to /soft/hadoop-2.7.3/logs/yarn-root-nodemanager-hadoop-3.out hadoop-4: starting nodemanager, logging to /soft/hadoop-2.7.3/logs/yarn-root-nodemanager-hadoop-4.out hadoop-2: starting nodemanager, logging to /soft/hadoop-2.7.3/logs/yarn-root-nodemanager-hadoop-2.out hadoop-5: starting nodemanager, logging to /soft/hadoop-2.7.3/logs/yarn-root-nodemanager-hadoop-5.out -
查看服务运行状态
[root@hadoop-1 hadoop]# jps 16358 ResourceManager 12807 NodeManager 16011 NameNode 16204 SecondaryNameNode 16623 Jps hadoop-5 | SUCCESS | rc=0 >> 16993 NodeManager 16884 DataNode 17205 Jps hadoop-1 | SUCCESS | rc=0 >> 28520 ResourceManager 28235 NameNode 29003 Jps hadoop-2 | SUCCESS | rc=0 >> 17780 Jps 17349 DataNode 17529 NodeManager 17453 SecondaryNameNode hadoop-4 | SUCCESS | rc=0 >> 17105 Jps 16875 NodeManager 16766 DataNode hadoop-3 | SUCCESS | rc=0 >> 16769 DataNode 17121 Jps 16878 NodeManager -
登陆WEB查看
2. 完全分布式单词统计
-
通过hadoop自带的demo运行单词统计
#mkdir /input #cd /input/ #echo "hello world" > file1.txt #echo "hello world" > file2.txt #echo "hello world" > file3.txt #echo "hello hadoop" > file4.txt #echo "hello hadoop" > file5.txt #echo "hello mapreduce" > file6.txt #echo "hello mapreduce" > file7.txt #hadoop dfs -mkdir /input #hdfs dfs -ls / #hadoop fs -ls / #hadoop fs -put /input/* /input #hadoop fs -ls /input -
开始统计
[root@hadoop-1 ~]# hadoop jar /soft/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.3.jar wordcount /input/ /output 17/05/14 23:01:07 INFO client.RMProxy: Connecting to ResourceManager at hadoop-1/10.31.133.19:8032 17/05/14 23:01:09 INFO input.FileInputFormat: Total input paths to process : 7 17/05/14 23:01:10 INFO mapreduce.JobSubmitter: number of splits:7 17/05/14 23:01:10 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1494773207391_0001 17/05/14 23:01:10 INFO impl.YarnClientImpl: Submitted application application_1494773207391_0001 17/05/14 23:01:11 INFO mapreduce.Job: The url to track the job: http://hadoop-1:8088/proxy/application_1494773207391_0001/ 17/05/14 23:01:11 INFO mapreduce.Job: Running job: job_1494773207391_0001 17/05/14 23:01:23 INFO mapreduce.Job: Job job_1494773207391_0001 running in uber mode : false 17/05/14 23:01:23 INFO mapreduce.Job: map 0% reduce 0% 17/05/14 23:01:56 INFO mapreduce.Job: map 43% reduce 0% 17/05/14 23:01:57 INFO mapreduce.Job: map 100% reduce 0% 17/05/14 23:02:04 INFO mapreduce.Job: map 100% reduce 100% 17/05/14 23:02:05 INFO mapreduce.Job: Job job_1494773207391_0001 completed successfully 17/05/14 23:02:05 INFO mapreduce.Job: Counters: 50 File System Counters FILE: Number of bytes read=184 FILE: Number of bytes written=949365 FILE: Number of read operations=0 FILE: Number of large read operations=0 FILE: Number of write operations=0 HDFS: Number of bytes read=801 HDFS: Number of bytes written=37 HDFS: Number of read operations=24 HDFS: Number of large read operations=0 HDFS: Number of write operations=2 Job Counters Killed map tasks=1 Launched map tasks=7 Launched reduce tasks=1 Data-local map tasks=7 Total time spent by all maps in occupied slots (ms)=216289 Total time spent by all reduces in occupied slots (ms)=4827 Total time spent by all map tasks (ms)=216289 Total time spent by all reduce tasks (ms)=4827 Total vcore-milliseconds taken by all map tasks=216289 Total vcore-milliseconds taken by all reduce tasks=4827 Total megabyte-milliseconds taken by all map tasks=221479936 Total megabyte-milliseconds taken by all reduce tasks=4942848 Map-Reduce Framework Map input records=7 Map output records=14 Map output bytes=150 Map output materialized bytes=220 Input split bytes=707 Combine input records=14 Combine output records=14 Reduce input groups=4 Reduce shuffle bytes=220 Reduce input records=14 Reduce output records=4 Spilled Records=28 Shuffled Maps =7 Failed Shuffles=0 Merged Map outputs=7 GC time elapsed (ms)=3616 CPU time spent (ms)=3970 Physical memory (bytes) snapshot=1528823808 Virtual memory (bytes) snapshot=16635846656 Total committed heap usage (bytes)=977825792 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=94 File Output Format Counters Bytes Written=37 -
查看
[root@hadoop-1 ~]# hadoop fs -ls /out/put Found 2 items -rw-r--r-- 3 root supergroup 0 2017-05-14 23:02 /out/put/_SUCCESS -rw-r--r-- 3 root supergroup 37 2017-05-14 23:02 /out/put/part-r-00000 [root@hadoop-1 ~]# hadoop fs -cat /out/put/part-r-00000 hadoop 2 hello 7 mapreduce 2 world 3 [root@hadoop-1 ~]#