Spark

From Chorke Wiki
Jump to navigation Jump to search
export PYSPARK_PYTHON='/usr/bin/python3';\
export SPARK_HOME='/opt/cli/spark-3.3.0-bin-hadoop3';\
export JAVA_HOME='/usr/lib/jvm/java-17-openjdk-amd64';\
export PATH=$PATH:$SPARK_HOME/bin:$SPARK_HOME/sbin
spark-shell
pyspark
http://localhost:8080/
http://localhost:7077/
http://localhost:4040/
ssh -L 8080:localhost:8080 user@spark.chorke.org
ssh -L 7077:localhost:7077 user@spark.chorke.org

Master Node

sudo apt -qq update;\
export PYSPARK_PYTHON='/usr/bin/python3';\
export SPARK_HOME='/opt/cli/spark-3.3.0-bin-hadoop3';\
export JAVA_HOME='/usr/lib/jvm/java-17-openjdk-arm64';\
bash <(curl -s 'https://cdn.chorke.org/exec/cli/bash/install/apache-spark-master/3.3.0.sh.txt')
sudo systemctl daemon-reload
sudo systemctl enable spark-master.service
sudo systemctl start  spark-master.service
sudo systemctl status spark-master.service

Worker Node

sudo apt -qq update;\
export PYSPARK_PYTHON='/usr/bin/python3';\
export SPARK_MASTER='spark://ns12-pc04:7077';\
export SPARK_HOME='/opt/cli/spark-3.3.0-bin-hadoop3';\
export JAVA_HOME='/usr/lib/jvm/java-17-openjdk-amd64';\
bash <(curl -s 'https://cdn.chorke.org/exec/cli/bash/install/apache-spark-slave/3.3.0.sh.txt')
sudo systemctl daemon-reload
sudo systemctl enable spark-slave.service
sudo systemctl start  spark-slave.service
sudo systemctl status spark-slave.service

Knowledge

ssh-keygen -b 4096 -t rsa -f ~/.ssh/id_rsa -q -N "spark@${HOSTNAME}"
readlink -f /usr/bin/java | sed "s:bin/java::"
sudo apt-get install pdsh
sudo apt-get install ssh

su -h spark
sudo -u spark -H sh -c "whoami; echo ${HOME}"
sh $SPARK_HOME/bin/spark-shell
sh $SPARK_HOME/bin/pyspark
http://127.0.0.1:8080
http://127.0.0.1:8088
http://127.0.0.1:9870
http://127.0.0.1:4040

sudo apt dist-upgrade
sudo do-release-upgrade

sudo apt --fix-broken install
sudo apt install ubuntu-desktop
[Service]
User=spark
Group=spark
Type=forking
SuccessExitStatus=143

if [ -f '/etc/os-release' ];then
         HOST_OS_ID=$(grep -oP '(?<=^ID=).+'         /etc/os-release | tr -d '"')
    HOST_OS_ID_LIKE=$(grep -oP '(?<=^ID_LIKE=).+'    /etc/os-release | tr -d '"')
    HOST_OS_VERSION=$(grep -oP '(?<=^VERSION_ID=).+' /etc/os-release | tr -d '"')
fi

References