Squash layers and add prompt customization

This commit is contained in:
2024-02-06 14:38:09 +05:30
parent b99f8e007c
commit 4ed3d66905
4 changed files with 144 additions and 85 deletions

View File

@@ -16,9 +16,9 @@ RUN apt-get update && \
apt-get install -y ssh openjdk-8-jdk neovim junit python-is-python3 nano curl python3-pip apt-get install -y ssh openjdk-8-jdk neovim junit python-is-python3 nano curl python3-pip
# Download and extract Hadoop # Download and extract Hadoop
RUN mkdir -p $HADOOP_HOME RUN mkdir -p $HADOOP_HOME && \
RUN wget -O hadoop.tar.gz https://downloads.apache.org/hadoop/common/stable/hadoop-3.3.6.tar.gz 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 tar -xzvf hadoop.tar.gz -C $HADOOP_HOME --strip-components=1
# Configure SSH # Configure SSH
RUN ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa && \ RUN ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa && \
@@ -27,8 +27,8 @@ RUN ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa && \
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 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 mkdir -p /home/hadoop/hdfs/{namenode,datanode} && \
RUN chown -R $USER:$USER /home/hadoop/hdfs chown -R $USER:$USER /home/hadoop/hdfs
# Hadoop configuration # Hadoop configuration
COPY core-site.xml $HADOOP_HOME/etc/hadoop/core-site.xml COPY core-site.xml $HADOOP_HOME/etc/hadoop/core-site.xml
@@ -55,100 +55,109 @@ RUN echo "HDFS_NAMENODE_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \ echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \
echo "export HADOOP_CLASSPATH+=\" \$HADOOP_HOME/lib/*.jar\"" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh echo "export HADOOP_CLASSPATH+=\" \$HADOOP_HOME/lib/*.jar\"" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
# Copy init and restart scripts
COPY restart $HADOOP_HOME/bin/restart
COPY init $HADOOP_HOME/bin/init
RUN chmod +x $HADOOP_HOME/bin/restart
RUN chmod +x $HADOOP_HOME/bin/init
# Install pig # Install pig
RUN wget -O pig.tar.gz https://downloads.apache.org/pig/pig-0.17.0/pig-0.17.0.tar.gz RUN wget -O pig.tar.gz https://downloads.apache.org/pig/pig-0.17.0/pig-0.17.0.tar.gz && \
RUN tar -xzvf pig.tar.gz tar -xzvf pig.tar.gz && \
RUN mv pig-0.17.0 /pig mv pig-0.17.0 /pig && \
RUN echo "export PIG_HOME=/pig" >> ~/.bashrc && \ echo "export PIG_HOME=/pig" >> ~/.bashrc && \
echo "export PATH=\$PATH:/pig/bin" >> ~/.bashrc && \ echo "export PATH=\$PATH:/pig/bin" >> ~/.bashrc && \
echo "export PIG_CLASSPATH=\$HADOOP_HOME/etc/hadoop" >> ~/.bashrc echo "export PIG_CLASSPATH=\$HADOOP_HOME/etc/hadoop" >> ~/.bashrc
# Install hbase # Install hbase
RUN wget http://apache.mirror.gtcomm.net/hbase/stable/hbase-2.5.7-bin.tar.gz RUN wget http://apache.mirror.gtcomm.net/hbase/stable/hbase-2.5.7-bin.tar.gz && \
RUN tar -xzvf hbase-2.5.7-bin.tar.gz tar -xzvf hbase-2.5.7-bin.tar.gz && \
RUN mv hbase-2.5.7 /usr/local/hbase mv hbase-2.5.7 /usr/local/hbase && \
RUN echo "export HBASE_HOME=/usr/local/hbase" >> ~/.bashrc && \ echo "export HBASE_HOME=/usr/local/hbase" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$HBASE_HOME/bin" >> ~/.bashrc echo "export PATH=\$PATH:\$HBASE_HOME/bin" >> ~/.bashrc && \
RUN echo "export HBASE_DISABLE_HADOOP_CLASSPATH_LOOKUP=\"true\"" >> /usr/local/hbase/conf/hbase-env.sh && \ echo "export HBASE_DISABLE_HADOOP_CLASSPATH_LOOKUP=\"true\"" >> /usr/local/hbase/conf/hbase-env.sh && \
echo "JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> /usr/local/hbase/conf/hbase-env.sh echo "JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> /usr/local/hbase/conf/hbase-env.sh
COPY hbase-site.xml ~/hbase-site.xml COPY hbase-site.xml ~/hbase-site.xml
RUN mkdir -p /hadoop/zookeeper RUN mkdir -p /hadoop/zookeeper && \
RUN chown -R $USER:$USER /hadoop/ chown -R $USER:$USER /hadoop/
# Install Hive # Install Hive
RUN wget https://dlcdn.apache.org/hive/hive-3.1.3/apache-hive-3.1.3-bin.tar.gz RUN wget https://dlcdn.apache.org/hive/hive-3.1.3/apache-hive-3.1.3-bin.tar.gz && \
RUN tar -xzvf apache-hive-3.1.3-bin.tar.gz tar -xzvf apache-hive-3.1.3-bin.tar.gz && \
RUN mv apache-hive-3.1.3-bin /usr/local/hive mv apache-hive-3.1.3-bin /usr/local/hive && \
RUN echo "export HIVE_HOME=/usr/local/hive" >> ~/.bashrc && \ echo "export HIVE_HOME=/usr/local/hive" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$HIVE_HOME/bin" >> ~/.bashrc echo "export PATH=\$PATH:\$HIVE_HOME/bin" >> ~/.bashrc && \
RUN echo "HADOOP_HOME=/usr/local/hadoop" >> /usr/local/hive/bin/hive-config.sh echo "HADOOP_HOME=/usr/local/hadoop" >> /usr/local/hive/bin/hive-config.sh
# Install Flume # Install Flume
RUN wget https://archive.apache.org/dist/flume/1.9.0/apache-flume-1.9.0-bin.tar.gz RUN wget https://archive.apache.org/dist/flume/1.9.0/apache-flume-1.9.0-bin.tar.gz && \
RUN tar -xzvf apache-flume-1.9.0-bin.tar.gz tar -xzvf apache-flume-1.9.0-bin.tar.gz && \
RUN mv apache-flume-1.9.0-bin /usr/local/flume mv apache-flume-1.9.0-bin /usr/local/flume && \
RUN echo "export FLUME_HOME=/usr/local/flume" >> ~/.bashrc && \ echo "export FLUME_HOME=/usr/local/flume" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$FLUME_HOME/bin" >> ~/.bashrc echo "export PATH=\$PATH:\$FLUME_HOME/bin" >> ~/.bashrc && \
RUN sed -i '214c\ \$EXEC \$JAVA_HOME/java \$JAVA_OPTS \$FLUME_JAVA_OPTS "\${arr_java_props[@]}" -cp "\$FLUME_CLASSPATH" \\' /usr/local/flume/bin/flume-ng sed -i '214c\ \$EXEC \$JAVA_HOME/java \$JAVA_OPTS \$FLUME_JAVA_OPTS "\${arr_java_props[@]}" -cp "\$FLUME_CLASSPATH" \\' /usr/local/flume/bin/flume-ng
# Install Sqoop # Install Sqoop
RUN wget https://archive.apache.org/dist/sqoop/1.4.7/sqoop-1.4.7.bin__hadoop-2.6.0.tar.gz RUN wget https://archive.apache.org/dist/sqoop/1.4.7/sqoop-1.4.7.bin__hadoop-2.6.0.tar.gz && \
RUN tar -xzvf sqoop-1.4.7.bin__hadoop-2.6.0.tar.gz tar -xzvf sqoop-1.4.7.bin__hadoop-2.6.0.tar.gz && \
RUN mv sqoop-1.4.7.bin__hadoop-2.6.0 /usr/local/sqoop mv sqoop-1.4.7.bin__hadoop-2.6.0 /usr/local/sqoop && \
RUN echo "export SQOOP_HOME=/usr/local/sqoop" >> ~/.bashrc && \ echo "export SQOOP_HOME=/usr/local/sqoop" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$SQOOP_HOME/bin" >> ~/.bashrc echo "export PATH=\$PATH:\$SQOOP_HOME/bin" >> ~/.bashrc && \
RUN mv /usr/local/sqoop/conf/sqoop-env-template.sh /usr/local/sqoop/conf/sqoop-env.sh mv /usr/local/sqoop/conf/sqoop-env-template.sh /usr/local/sqoop/conf/sqoop-env.sh && \
RUN echo "export HADOOP_COMMON_HOME=/usr/local/hadoop" >> /usr/local/sqoop/conf/sqoop-env.sh && \ echo "export HADOOP_COMMON_HOME=/usr/local/hadoop" >> /usr/local/sqoop/conf/sqoop-env.sh && \
echo "export HADOOP_MAPRED_HOME=/usr/local/hadoop" >> /usr/local/sqoop/conf/sqoop-env.sh echo "export HADOOP_MAPRED_HOME=/usr/local/hadoop" >> /usr/local/sqoop/conf/sqoop-env.sh
# Install Zookeeper # Install Zookeeper
RUN wget https://downloads.apache.org/zookeeper/zookeeper-3.9.1/apache-zookeeper-3.9.1-bin.tar.gz RUN wget https://downloads.apache.org/zookeeper/zookeeper-3.9.1/apache-zookeeper-3.9.1-bin.tar.gz && \
RUN tar -xvf apache-zookeeper-3.9.1-bin.tar.gz tar -xvf apache-zookeeper-3.9.1-bin.tar.gz && \
RUN mv apache-zookeeper-3.9.1-bin /usr/local/zookeeper mv apache-zookeeper-3.9.1-bin /usr/local/zookeeper && \
RUN mv /usr/local/zookeeper/conf/zoo_sample.cfg /usr/local/zookeeper/conf/zoo.cfg mv /usr/local/zookeeper/conf/zoo_sample.cfg /usr/local/zookeeper/conf/zoo.cfg && \
RUN echo "export ZOOKEEPER_HOME=/usr/local/zookeeper" >> ~/.bashrc && \ echo "export ZOOKEEPER_HOME=/usr/local/zookeeper" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$ZOOKEEPER_HOME/bin" >> ~/.bashrc echo "export PATH=\$PATH:\$ZOOKEEPER_HOME/bin" >> ~/.bashrc
# Install Spark # Install Spark
ENV DEBIAN_FRONTEND=noninteractive ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y scala git apt-get install -y scala git && \
RUN wget https://archive.apache.org/dist/spark/spark-3.4.1/spark-3.4.1-bin-hadoop3.tgz wget https://archive.apache.org/dist/spark/spark-3.4.1/spark-3.4.1-bin-hadoop3.tgz && \
RUN tar -xf spark-3.4.1-bin-hadoop3.tgz tar -xf spark-3.4.1-bin-hadoop3.tgz && \
RUN mv spark-3.4.1-bin-hadoop3 /usr/local/spark mv spark-3.4.1-bin-hadoop3 /usr/local/spark && \
RUN echo "export SPARK_HOME=/usr/local/spark" >> ~/.bashrc && \ echo "export SPARK_HOME=/usr/local/spark" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$SPARK_HOME/bin:\$SPARK_HOME/sbin" >> ~/.bashrc echo "export PATH=\$PATH:\$SPARK_HOME/bin:\$SPARK_HOME/sbin" >> ~/.bashrc
# Install Pyspark # Install Pyspark
RUN pip install pyspark RUN pip install pyspark
# Install Kafka # Install Kafka
RUN wget https://downloads.apache.org/kafka/3.6.1/kafka_2.13-3.6.1.tgz RUN wget https://downloads.apache.org/kafka/3.6.1/kafka_2.13-3.6.1.tgz && \
RUN tar -xzvf kafka_2.13-3.6.1.tgz tar -xzvf kafka_2.13-3.6.1.tgz && \
RUN mv kafka_2.13-3.6.1 /usr/local/kafka mv kafka_2.13-3.6.1 /usr/local/kafka && \
RUN echo "export KAFKA_HOME=/usr/local/kafka" >> ~/.bashrc && \ echo "export KAFKA_HOME=/usr/local/kafka" >> ~/.bashrc && \
echo "export PATH=\$PATH:\$KAFKA_HOME/bin" >> ~/.bashrc echo "export PATH=\$PATH:\$KAFKA_HOME/bin" >> ~/.bashrc
# Install Postgresql # Install Postgresql
RUN apt-get install postgresql postgresql-contrib -y RUN apt-get install postgresql postgresql-contrib -y
# Connect Postgresql with sqoop # Connect Postgresql with sqoop
RUN wget https://jdbc.postgresql.org/download/postgresql-42.7.1.jar RUN wget https://jdbc.postgresql.org/download/postgresql-42.7.1.jar && \
RUN mv postgresql-42.7.1.jar /usr/local/sqoop/lib/postgresql-42.7.1.jar mv postgresql-42.7.1.jar /usr/local/sqoop/lib/postgresql-42.7.1.jar && \
RUN rm /usr/local/sqoop/lib/commons-lang3-3.4.jar rm /usr/local/sqoop/lib/commons-lang3-3.4.jar && \
RUN wget https://dlcdn.apache.org//commons/lang/binaries/commons-lang-2.6-bin.tar.gz wget https://dlcdn.apache.org//commons/lang/binaries/commons-lang-2.6-bin.tar.gz && \
RUN tar -xvf commons-lang-2.6-bin.tar.gz tar -xvf commons-lang-2.6-bin.tar.gz && \
RUN mv commons-lang-2.6/* /usr/local/sqoop/lib mv commons-lang-2.6/* /usr/local/sqoop/lib && \
RUN rm -rf commons-lang-2.6 rm -rf commons-lang-2.6 && \
RUN mkdir /usr/local/sqoop/conf/manager.d mkdir /usr/local/sqoop/conf/manager.d && \
RUN echo "org.postgresql.Driver=/usr/lib/sqoop/lib/postgresql-42.7.1.jar" > postgresql echo "org.postgresql.Driver=/usr/lib/sqoop/lib/postgresql-42.7.1.jar" > postgresql
# Copy init and restart scripts
COPY restart $HADOOP_HOME/bin/restart
COPY init $HADOOP_HOME/bin/init
COPY colors $HADOOP_HOME/bin/colors
RUN chmod +x $HADOOP_HOME/bin/restart && \
chmod +x $HADOOP_HOME/bin/colors && \
chmod +x $HADOOP_HOME/bin/init
# Cleaning up archives
RUN rm *.tar.gz && \
rm *.tgz
# Remove code in .bashrc
RUN sed -i 5,7d ~/.bashrc
# Expose necessary ports # Expose necessary ports
EXPOSE 9870 8088 9000 EXPOSE 9870 8088 9000

19
colors Normal file
View File

@@ -0,0 +1,19 @@
#!/usr/bin/env bash
FG_RED="\e[31m"
FG_GREEN="\e[32m"
FG_BROWN="\e[33m"
FG_BLUE="\e[34m"
FG_PURPLE="\e[35m"
FG_CYAN="\e[36m"
FG_GRAY="\e[37m"
BG_RED="\e[41m"
BG_GREEN="\e[42m"
BG_BROWN="\e[43m"
BG_BLUE="\e[44m"
BG_PURPLE="\e[45m"
BG_CYAN="\e[46m"
BG_GRAY="\e[47m"
RESET="\e[0m"

50
init
View File

@@ -1,19 +1,41 @@
#!/usr/bin/env bash #!/usr/bin/env bash
service ssh restart # restart ssh service source 'colors'
stop-hbase.sh # stop all processes
stop-all.sh
hdfs namenode -format # format namenodes
rm *.tar.gz # delete all tar files to save space
# start all read -p "Choose your PC name: " name
start-all.sh
start-hbase.sh
# hive initialization echo "Choose prompt color:"
hdfs dfs -mkdir /tmp echo -e "\e[0m1] \e[31muser@$name:/#\e[0m"
hdfs dfs -chmod g+w /tmp echo -e "\e[0m2] \e[32muser@$name:/#\e[0m"
hdfs dfs -mkdir -p /user/hive/warehouse echo -e "\e[0m3] \e[33muser@$name:/#\e[0m"
hdfs dfs -chmod g+w /user/hive/warehouse echo -e "\e[0m4] \e[34muser@$name:/#\e[0m"
schematool -dbType derby -initSchema echo -e "\e[0m5] \e[35muser@$name:/#\e[0m"
echo -e "\e[0m6] \e[36muser@$name:/#\e[0m"
echo -e "\e[0m7] \e[37muser@$name:/#\e[0m"
read -p "Option: " num
echo "PS1=\"\\e[3""$num""m\\u@$name:\\w# \\e[0m\"" >> ~/.bashrc
printf "${FG_BROWN}Restarting SSH... "
service ssh restart > /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Stopping all processes... "
stop-hbase.sh > /dev/nul
stop-all.sh > /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Formatting HDFS... "
hdfs namenode -format &> /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Starting up all processes... "
start-all.sh > /dev/nul
start-hbase.sh > /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Setting up Hive... "
hdfs dfs -mkdir /tmp > /dev/nul
hdfs dfs -chmod g+w /tmp > /dev/nul
hdfs dfs -mkdir -p /user/hive/warehouse > /dev/nul
hdfs dfs -chmod g+w /user/hive/warehouse > /dev/nul
schematool -dbType derby -initSchema &> /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Checking processes... "
printf "\n${FG_BLUE}$(jps | wc -l) processes.${RESET}\n"
printf "Enter ${FG_BLUE}source ~/.bashrc${RESET} to see changes!\n"

21
restart
View File

@@ -1,7 +1,16 @@
#!/usr/bin/env bash #!/usr/bin/env bash
service ssh restart
stop-hbase.sh source 'colors'
stop-all.sh
start-all.sh printf "${FG_BROWN}Restarting SSH... "
start-hbase.sh service ssh restart > /dev/nul
jps printf "${FG_GREEN}Done!\n${FG_BROWN}Stopping all processes... "
stop-hbase.sh > /dev/nul
stop-all.sh > /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Starting up all processes... "
start-all.sh > /dev/nul
start-hbase.sh > /dev/nul
printf "${FG_GREEN}Done!\n${FG_BROWN}Checking processes... "
printf "\n${FG_BLUE}$(jps | wc -l) processes.${RESET}\n"