Spark: Difference between revisions
Jump to navigation
Jump to search
| Line 60: | Line 60: | ||
| valign="top" | | | valign="top" | | ||
* [https://stackoverflow.com/questions/31450846/ Spark » Concatenate columns in DataFrame] | |||
* [https://spark.apache.org/docs/latest/structured-streaming-programming-guide.html Spark » Structured Streaming Programming] | * [https://spark.apache.org/docs/latest/structured-streaming-programming-guide.html Spark » Structured Streaming Programming] | ||
* [https://dev.to/kirekov/apache-spark-hive-and-spring-boot-testing-guide-mdp Spark » Apache Spark, Hive & Spring Boot] | * [https://dev.to/kirekov/apache-spark-hive-and-spring-boot-testing-guide-mdp Spark » Apache Spark, Hive & Spring Boot] | ||
| Line 69: | Line 70: | ||
* [https://www.baeldung.com/apache-spark Spark » Introduction] | * [https://www.baeldung.com/apache-spark Spark » Introduction] | ||
* [https://github.com/vim89/spark-spring-boot/blob/master/src/main/java/com/vitthalmirji/spring/spark/ApplicationConfig.java Spark » Spring Boot] | * [https://github.com/vim89/spark-spring-boot/blob/master/src/main/java/com/vitthalmirji/spring/spark/ApplicationConfig.java Spark » Spring Boot] | ||
| valign="top" | | | valign="top" | | ||
| Line 106: | Line 106: | ||
* [[Machine Learning]] | * [[Machine Learning]] | ||
* [https://hive.apache.org/ Apache Hive] | * [https://hive.apache.org/ Apache Hive] | ||
* [https://aerospike.com/ Aerospike] | |||
|} | |} | ||
Revision as of 22:51, 25 September 2022
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 [email protected] ssh -L 7077:localhost:7077 [email protected]
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