Hey Spark Community Members let's meet up!

http://photos4.meetupstatic.com/photos/event/a/5/f/b/600_437862491.jpeg

Join Franz Faerber and Jörg Schad to talk about on how Apache Spark jobs today are typically run on separate clusters away from the rest of the enterprise apps, Spark Integration and Hana!

Since the data volume grows into hundreds of terabytes and petabytes, data gravity forces one to reconsider that setup and integrate Hadoop into the mainstream datacenter. In so doing, one needs to ensure data locality for Hadoop jobs is maintained at all times and that the integration is seamless across CPU, memory and network resources. Mesos and Myriad solves that problem in a very elegant way by bringing Apache YARN Resource Management and Apache Mesos Resource Management to work together.

See you soon!