Cassandra from the Trenches: War Stories on Migrating to Cassandra at Netflix

Netflix grew up using the traditional enterprise model for scaling: monolithic web application on top of a monolithic database in a single datacenter, buying bigger boxes, stuffing more user data into session memory. It all worked great when Netflix had less than 1 million customers and rapidly growing. Then one day that model failed us, miserably. The single-point-of-failure bug hit us hard, and we were hobbled for days. Since then, Netflix has reinvented it's technology stack from top to bottom - abandoning the single, monolithic web application for tiered distributed services, as well as moving beyond our SPOF database to more resiliant architectures.

In this talk I'll be disucssing my involvement with Cassandra at Netflix, both as a programmer understanding and using this new beast as well as a devops guy trying to understand how to get it to run - and run fast as a single cluster spanning multile EC2 regions. I've been hands-on since we introduced Cassandra over a year ago, and I'll be sharing experiences I've had in the following areas:

Migrating an existing relational data model into a non-relational Cassandra model Coding implementation details Operating Cassandra in the real world (tunings, compactions, data sizes, multi-region)