Abstract

With today’s increased focus on data workloads, we’re now faced with finding scalable solutions to process it quickly and accurately. This talk will cover one of the ways to tackle the big and fast data challenges: by using the SMACK Statck. We will explore each of the technologies in this stack (Apache Spark, Apache Mesos, Akka, Apache Cassandra, and of course, Apache Kafka), how they work together, and how you can get going with all of them quickly on open source DC/OS, which uses the “M” for “Mesos” under the hood. The presentation will conclude with a live stream data processing demo that we’ve open sourced using data from the Los Angeles Metro system.

Media

Slides

Photos