Diptanu Choudhury discusses the design of Netflix’ distributed scheduler based on Mesos and Titan, focusing on bin packing algorithms, scaling in and out of clusters, fault tolerance, and redundancy.
Sandy Ryza aims to give a feel for what it is like to approach financial modeling with modern big data tools, using the Monte Carlo method for a a basic VaR calculation with Spark.
Kin Lane discusses the opportunities of deploying high value, re-mixable APIs, using Docker.
Anil Madhavapeddy explains how the OCaml module system enables the construction of a large scale OS software, and also the resulting portability benefits.
Piotr Kołaczkowski discusses how they integrated Spark with Cassandra, how it was done, how it works in practice and why it is better than using a Hadoop intermediate layer.
Dave Farley looks at a history littered with inefficient processes resulting in poor quality and failed projects, wondering how we got here, what can be done and what does good really look like?
Chris Richardson shares his experiences developing and deploying a microservices-based application.
Paul Stack describes what DevOps is and how it is a great way for the entire business to achieve their goals.
The authors present an approach for automatic translation of sequential, imperative code into a parallel MapReduce framework using Mold, translating Java code to run on Apache Spark.
Jessie Frazelle takes a look inside the tools built in Go centered around infrastructure and ops - from Docker to etcd to nsq and more.
Luke Marsden talks about building the right multi-host abstractions to get Docker into production with both a natural developer user experience and an operational user experience.
Dustin Huptas, Andreas Schmidt present some of the operational challenges met when dealing with microservices, and offer solutions from the field of automation and service discovery.