1. #!/bin/bash
2.  
3. # Install deps
4. sudo apt install -y default-jdk
5. sudo apt update -y && sudo apt install -y default-jre openssh-client pdsh wget tar
6.  
7. # Define java
8. JAVA_VER=$(sudo update-alternatives --config java | grep 'java-11' | awk '{print $2}')
9. echo "java configuration file in $JAVA_VER"
10.  
11. # SSH Generate Key
12. sudo adduser hdoop
13. ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
14. cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
15. chmod 600 ~/.ssh/authorized_keys
16. chmod 700 ~/.ssh
17.  
18. # Installing Hadoop
19. wget https://downloads.apache.org/hadoop/common/hadoop-3.3.6/hadoop-3.3.6.tar.gz
20. tar -xvf hadoop-3.3.6.tar.gz
21. sudo mv hadoop-3.3.6 /usr/local/hadoop
22. sudo chown -R hdoop:hdoop /usr/local/hadoop
23. echo 'export JAVA_HOME=$(readlink -f /usr/bin/java | sed "s:bin/java::")' | sudo tee -a /usr/local/hadoop/etc/hadoop/hadoop-env.sh
24. echo "export HADOOP_HOME=/usr/local/hadoop" >> ~/.bashrc
25. echo "export PATH=\$PATH:\$HADOOP_HOME/bin:\$HADOOP_HOME/sbin" >> ~/.bashrc
26. source ~/.bashrc
27.  
28.  
29. # Modifying hadopp default configuration
30. # cd /usr/local/hadoop/etc/hadoop
31.  echo "<configuration>
32.     <property>
33.         <name>fs.defaultFS</name>
34.         <value>hdfs://localhost:9000</value>
35.     </property>
36. </configuration>" > core-site.xml
37.  
38. echo "<configuration>
39.     <property>
40.         <name>dfs.replication</name>
41.         <value>1</value>
42.     </property>
43. </configuration>" > hdfs-site.xml
44.  
45. # Format HDFS
46. /usr/local/hadoop/bin/hdfs namenode -format
47.  
48. # Start HDFS & Yarn Service
49. /usr/local/hadoop/sbin/start-dfs.sh
50. /usr/local/hadoop/sbin/start-yarn.sh
51.  
52. # Verify Installation
53. jps
54.  
55.  
56.  
57.