Hadoop集群运行

#master上操作
su - hadoop
cd /usr/local/src/hadoop/
./bin/hdfs namenode -format
hadoop-daemon.sh start namenode
hadoop-daemon.sh start secondarynamenode
jps
#看到NameNode和SecondayNameNode

#slave1上操作
su - hadoop
hadoop-daemon.sh start datanode
jps

#slave2上操作
su - hadoop
hadoop-daemon.sh start datanode
jps
#看到DataNode

#master上操作
su - hadoop
hdfs dfsadmin -report
ssh-keygen -t rsa
ssh-copy-id slave1
ssh-copy-id slave2
ssh-copy-id master
stop-dfs.sh
start-dfs.sh
start-yarn.sh
jps
#master上看到ResourceManager,slave上看到NodeManager
hdfs dfs -mkdir /input
hdfs dfs -ls /
mkdir ~/input
vi ~/input/data.txt
Hello World
Hello Hadoop
Hello Huasan
hdfs dfs -put ~/input/data.txt /input
hdfs dfs -cat /input/data.txt
hadoop jar /usr/local/src/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.1.jar wordcount /input/data.txt /output
#执行完看到map为100%，reduce为100%，还要看到successfully