Deploy a local multi-node Cassandra cluster using Docker

cassandra-as-rdd-spark-sehll.scala

/*
Run Spark shell using spark-shell --packages datastax:spark-cassandra-connector:2.4.0-s_2.11 command
Check the versions compatibility on https://github.com/datastax/spark-cassandra-connector#version-compatibility
*/

import com.datastax.spark.connector._
import org.apache.spark.sql._
val spark = SparkSession.builder().
    appName("Spark SQL practice").master("local[*]").
    config("spark.cassandra.connection.host", "localhost").
    getOrCreate()
val sc = spark.sparkContext

val rdd = sc.cassandraTable("keyspace_name", "table_name")
/*
It returns and RDD
com.datastax.spark.connector.rdd.CassandraTableScanRDD[com.datastax.spark.connector.CassandraRow]

Next part, you can read it as RDD of a case class
*/

final case class CustomCaseClass(field1: Long, field2: Long, field3: String)
val merchantTxn = sc.cassandraTable[CustomCaseClass]("keyspace_name", "table_name")

start-cluster.sh

#!/bin/bash

# Run the first node and keep it in background up and running
docker run --name cassandra-1-3-0 -p 9042:9042 -d cassandra:3.0
INSTANCE1=$(docker inspect --format='{{ .NetworkSettings.IPAddress }}' cassandra-1-3-0)
echo "Instance 1: ${INSTANCE1}"

# Run the second node
docker run --name cassandra-2-3-0 -p 9043:9042 -d -e CASSANDRA_SEEDS=$INSTANCE1 cassandra:3.0
INSTANCE2=$(docker inspect --format='{{ .NetworkSettings.IPAddress }}' cassandra-2-3-0)
echo "Instance 2: ${INSTANCE2}"

# Connect to the cluster using cqlsh
# It will delete the docker container automatically once you close it
docker run -it --link cassandra-1-3-0 --rm cassandra:3.0 bash -c "exec cqlsh $INSTANCE1"

# Cleanup
# docker stop cassandra-1-3-0
# docker stop cassandra-2-3-0
# docker rm cassandra-1-3-0
# docker rm cassandra-2-3-0