Initial commit

This commit is contained in:
2024-01-28 22:13:32 +05:30
commit 127fe5de01
6 changed files with 119 additions and 0 deletions

62
Dockerfile Normal file
View File

@@ -0,0 +1,62 @@
# Use the official Ubuntu base image
FROM ubuntu:latest
# Set environment variables for Hadoop
ENV HADOOP_HOME /usr/local/hadoop
ENV PATH $HADOOP_HOME/bin:$PATH
ENV HDFS_NAMENODE_USER=root
ENV HDFS_DATANODE_USER=root
ENV HDFS_SECONDARYNAMENODE_USER=root
ENV YARN_NODEMANAGER_USER=root
ENV YARN_RESOURCEMANAGER_USER=root
# Install necessary dependencies
RUN apt-get update && \
apt-get install -y ssh && \
apt-get install -y openjdk-8-jdk && \
apt-get install -y neovim && \
rm -rf /var/lib/apt/lists/*
# Download and extract Hadoop
RUN mkdir -p $HADOOP_HOME
RUN wget -O hadoop.tar.gz https://downloads.apache.org/hadoop/common/stable/hadoop-3.3.6.tar.gz
RUN tar -xzvf hadoop.tar.gz -C $HADOOP_HOME --strip-components=1
# Configure SSH
RUN ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa && \
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys && \
chmod 0600 ~/.ssh/authorized_keys
RUN wget -O /usr/local/hadoop/lib/javax.activation-api-1.2.0.jar https://jcenter.bintray.com/javax/activation/javax.activation-api/1.2.0/javax.activation-api-1.2.0.jar
RUN mkdir -p /home/hadoop/hdfs/{namenode,datanode}
RUN chown -R $USER:$USER /home/hadoop/hdfs
# Hadoop configuration
COPY core-site.xml $HADOOP_HOME/etc/hadoop/core-site.xml
COPY hdfs-site.xml $HADOOP_HOME/etc/hadoop/hdfs-site.xml
COPY mapred-site.xml $HADOOP_HOME/etc/hadoop/mapred-site.xml
COPY yarn-site.xml $HADOOP_HOME/etc/hadoop/yarn-site.xml
RUN echo "export HADOOP_HOME=/usr/local/hadoop" >> ~/.bashrc
RUN echo "export HADOOP_INSTALL=\$HADOOP_HOME" >> ~/.bashrc
RUN echo "export HADOOP_MAPRED_HOME=\$HADOOP_HOME" >> ~/.bashrc
RUN echo "export HADOOP_COMMON_HOME=\$HADOOP_HOME" >> ~/.bashrc
RUN echo "export HADOOP_HDFS_HOME=\$HADOOP_HOME" >> ~/.bashrc
RUN echo "export YARN_HOME=\$HADOOP_HOME" >> ~/.bashrc
RUN echo "export HADOOP_COMMON_LIB_NATIVE_DIR=\$HADOOP_HOME/lib/native" >> ~/.bashrc
RUN echo "export PATH=\$PATH:\$HADOOP_HOME/sbin:\$HADOOP_HOME/bin" >> ~/.bashrc
RUN echo "export HADOOP_OPTS=\"-Djava.library.path=\$HADOOP_HOME/lib/native\"" >> ~/.bashrc
RUN echo "HDFS_NAMENODE_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
RUN echo "HDFS_DATANODE_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
RUN echo "HDFS_SECONDARYNAMENODE_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
RUN echo "YARN_NODEMANAGER_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
RUN echo "YARN_RESOURCEMANAGER_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
RUN echo "export HADOOP_CLASSPATH+=\" \$HADOOP_HOME/lib/*.jar\"" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
# Expose necessary ports
EXPOSE 9870 8088 9000

9
core-site.xml Normal file
View File

@@ -0,0 +1,9 @@
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>fs.default.name</name>
<value>hdfs://0.0.0.0:9000</value>
<description>The default file system URI</description>
</property>
</configuration>

18
hdfs-site.xml Normal file
View File

@@ -0,0 +1,18 @@
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
<property>
<name>dfs.name.dir</name>
<value>file:///home/hadoop/hdfs/namenode</value>
</property>
<property>
<name>dfs.data.dir</name>
<value>file:///home/hadoop/hdfs/datanode</value>
</property>
</configuration>

22
mapred-site.xml Normal file
View File

@@ -0,0 +1,22 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>yarn.app.mapreduce.am.env</name>
<value>HADOOP_MAPRED_HOME=$HADOOP_HOME</value>
</property>
<property>
<name>mapreduce.map.env</name>
<value>HADOOP_MAPRED_HOME=$HADOOP_HOME</value>
</property>
<property>
<name>mapreduce.reduce.env</name>
<value>HADOOP_MAPRED_HOME=$HADOOP_HOME</value>
</property>
</configuration>

0
slaves Normal file
View File

8
yarn-site.xml Normal file
View File

@@ -0,0 +1,8 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>