Supercharging Performance of Apache Spark Applications in the Cloud Data Platforms 2018

Speaker: Venkat Sowrirajan, Software Engineer, Qubole

Presentation: Spark applications are difficult to tune for optimal performance and with the use of cloud stores like S3 as truth-store makes things even more complex. This talk will cover briefly about SparkLens (Spark tuning tool), Spark with Rubix (distributed cache), direct-write for Hive tables and its performance numbers.

Learn more about.. Data Platforms Conference: https://www.dataplatforms.com Qubole: https://www.qubole.com