ApacheCon North America 2014

Developing Real-Time Data Pipelines with Apache Kafka http://kafka.apache.org/ is an introduction for developers about why and how to use Apache Kafka.  Apache Kafka is a publish-subscribe messaging system rethought of as a distributed commit log.  Kafka is designed to allow a single cluster to serve as the central data backbone.  A single Kafka broker can handle hundreds of megabytes of reads and writes per second from thousands of clients.  It can be elastically and transparently expanded without downtime. Data streams are partitioned and spread over a cluster of machines to allow data streams larger than the capability of any single machine and to allow clusters of coordinated consumers.  Messages are persisted on disk and replicated within the cluster to prevent data loss. Each broker can handle terabytes of messages.