Using Scylla with Spark, Hive and Superset

scylla_spark_superset

### Scylla
docker run --name some-scylla -d scylladb/scylla:2.1.3
docker cp data.cql some-scylla:/data.cql
docker exec -it some-scylla cqlsh -f data.cql

### Spark
docker run -it -p 4040:4040 -p 8080:8080 -p 8081:8081 -p 10000:10000 -h spark --name=spark -d p7hb/docker-spark
docker exec -it spark /usr/local/spark-2.2.0-bin-hadoop2.7/sbin/start-thriftserver.sh \
--conf hive.server2.thrift.bind.host=0.0.0.0 \
--conf spark.cassandra.connection.host=172.17.0.2 \
--packages datastax:spark-cassandra-connector:2.0.1-s_2.11

docker exec -it spark /usr/local/spark-2.2.0-bin-hadoop2.7/bin/beeline
!connect jdbc:hive2://localhost:10000 -n -p -e "CREATE TABLE air_quality USING org.apache.spark.sql.cassandra OPTIONS (keyspace 'mykeyspace', table 'air_quality_data');"


### SuperSet
docker run --detach -p 8088:8088 --name superset amancevice/superset:0.25.2
sleep 10
docker exec -it superset superset-init --username admin --firstname admin --lastname admin --email admin@admin.com --password 12345
docker cp HiveSparkScylla_datasource.yaml superset:/home/superset/HiveSparkScylla_datasource.yaml
docker exec superset superset import_datasources -p HiveSparkScylla_datasource.yaml



###
http://localhost:8088/superset/welcome