Apache Cassandra + Spark makeover w/ Apache Zeppelin & Scaling Cassandra at Uber
For this meetup we are excited to be joined by Patrick McFadin, Chief Evangelist for Apache Cassandra and Evan Culver, Software Engineer at Uber.
What To Bring:
Please be sure to bring your ID for check in. Security will also require guest to sign an NDA.
What You'll Learn At This Meetup:
Patrick McFadin: Is the command line getting a little dull when poking around your data? Take a look at what Apache Zeppelin can do for your data analysis! This year, the Zeppelin project has been promoted to a top level Apache project and has seen tremendous growth. A great addition to the Apache Cassandra ecosystem. Come learn about:
- Apache Zeppelin architecture and deployment methods
- Integration with Apache Cassandra
- Integration with Apache Spark
- Use cases with some live demos
That last line was right. I’m going against all good sense and try to pull of a live demo. If you love learning about new ways of looking at Cassandra and Spark data or you just want to see if I’ll fail, you won’t want to miss this one!
Evan Culver: Imagine an endless stream of geospatial data pummelling your infrastructure 24hrs a day, from every region in the world, and a growth trajectory that will keep you up at night, literally. Tie that together with the business’ bottom-line and you’ll start to understand the challenges Uber faces as we expand our presence globally.
In this talk, I’ll describe how Uber is using Cassandra to handle this onslaught of data and how we got here. I’ll talk about how we approach the problem, how we manage cross-datacenter replication and the complex rules around where data can live. I’ll share a few war stories, failures, how we monitor, tune and maintain our clusters to avoid failures, and most importantly, how we do all of this without affecting Uber’s bottom-line.
• Background of our problem domain
• Overview of our Cassandra deployment
• General tips on scaling a write heavy workload
• Monitoring and observability of the cluster
• Lessons learned
• The future: Mesos+Cassandra
*Big thank you to Uber for hosting and providing drinks!
*Food and drinks will be served, hope to see you there!
About Patrick McFadin:
Patrick McFadin is one of the leading experts of Apache Cassandra and data modeling techniques. As the Chief Evangelist for Apache Cassandra and consultant for DataStax, he has helped build some of the largest and exciting deployments in production. Previous to DataStax, he was Chief Architect at Hobsons and an Oracle DBA/Developer for over 15 years.
About Evan Culver:
Evan is a Software Engineer at Uber working on their next-generation storage architecture.