A Presentation by Sulamita Garcia
Clusters are defined as a set of computers working as one to execute tasks. The applications for it has no limit: from balance requests for web services to systems for explore petroleum, the amount of saves can be from thousands to gazillions of dollars.
More then that, it is an extensive and interesting area. The Open Source community has been know as a big player in Clusters, with several of the biggest clusters in the world running Linux. And the tools available for it improve quickly. Distributed file systems, fault tolerance software, data replication, monitoring and service takeover are some of softwares developed to create those environments.
In this presentation I want to explain about how to provide this services in differents enviroments and which softwares choose for each kind of situation. We will go through the basics of Clusters, HA, LB and how to identify the pieces involved in a complete solution. Then we will show the available softwares, the advantages and not so good issues of each one, and help the administrator to create a complete environment. This presentation will show several implementations of Clusters - high availability, high processing computing and load balance - and the technologies for each one. We are going to talk about DRBD, Heartbeat, Ultramonkey, Linux Virtual Server, Global FileSystem and more.