Gearman: Bringing the Power of Map/Reduce to Everyday Applications*
Come learn the fundamentals of how to leverage Gearman, the open-source, distributed job queuing system. Originally designed to scale LiveJournal.com, Gearman is now faster than ever and can help you build your own scalable applications. Gearman's generic design allows it to be used as a building block for almost any use - from speeding up your website to building your own Map/Reduce cluster.
Besides being used at LiveJournal.com, Gearman is also now used by other organizations such as Yahoo! and Digg. Development is now active again with an optimized rewrite in C, along with features such as persistent message queues, queue replication, improved statistics, and advanced job monitoring. We’re also introducing new and improved client APIs, including new user-defined functions for MySQL and Drizzle. The Gearman APIs and simple server installation allow you to have your own distributed computing framework setup in a matter of minutes, which enables you to focus on your own code rather than the plumbing to make scalable system work. This session will introduce these concepts, how to get started, and then describe a few common use cases.
Eric Day currently works on the Drizzle and Gearman projects, and has been writing high-performance, multi-threaded servers and databases for most of his career. Most of his work has been done in clustered and distributed environments, always with an emphasis on efficiency and security. Eric keeps active in the open source community through speaking at conferences and user groups, as well as helping organize camps and conferences in Portland, OR. When not hacking on code, he can be found playing hockey, biking, or enjoying a good vegan meal.