Wednesday, May 22, 2013

Apache CloudStack and Big Data

by Sebastien Goasguen (Citrix)

Wednesday, 22.05.2013, London I, 16:30-17:15 Uhr

Apache CloudStack is a project in incubation at the Apache Software Foundation (ASF). CloudStack is an Infrastructure as a Service Solution and one of the "four sisters" with OpenStack, Eucalyptus and OpenNebula. We will first describe the CloudStack features and the CloudStack community one year after joining Apache. We will then show how CloudStack can be used to provide on-demand Elastic Big Data services. We will focus on Hadoop based clusters both installed in bare-metal mode supported by CloudStack and a fully virtualized mode to package the application environment in a portable manner. We will then show how higher leverl big-data services such as a Mahout cluster or a Storm cluster can be provisioned on-demand and leverage the auto-scaling capability of CloudStack.

Links:

• CloudStack website
• Folien / Slides (PDF)
• Folien / Slides (PPT)

• CloudStack website
• Folien / Slides (PDF)
• Folien / Slides (PPT)

About the author Sebastien Goasguen:

Open Source Cloud Computing Evangelist for Citrix. Sebastien is a committer on Apache CloudStack a project in incubation at the Apache Software Foundation. Sebastien has 15 years of experience in IT research and development working on grid computing and HPC. After a long career in academia where he researched virtualized distributed systems he joined Citrix to work on Apache CloudStack a IaaS Solution.