Rocks-A-Palooza V    

Rocks-A-Palooza IV    

Open Source Grid and Cluster Conference
  • Workshop Goals and Rocks 5.0 Enhancements This session will focus on the new features of Rocks 5.0 (V) including support for Xen-based virtual machines, enhancements/changes in the Rocks command structure, and general support for Version 5.0 of CentOS/RHEL. In addition, participants will have an opportunity to shape follow-on sessions for this year's workshop. A refresher (or introduction) to the Rocks configuration graph will be given. Participants are expected to have familiarity with previous versions of Rocks.

  • Xen VMs, Virtual Clusters and Programmatic Partitioning The internals of Xen support in Rocks will be presented and dissected in detail. A preliminary roadmap for enhanced support for completely virtualized clusters (frontends and slave nodes) will be given. New for Rocks 5.0 is the ability to fully program how a node partitions its local hard drives so that any partitioning policy can be implemented. Methods, techniques and examples of partitioning schemes will be presented.

  • Customizing Rocks through Rolls. How to Develop Your Own Rolls are the primary mechanism for customizing Rocks installations while enabling reproducibility to any number of clusters. Rolls can be commercial or open-source. ClusterCorp has produced several rolls and will describe their techniques and issues. Techniques for how Linux-based rolls are built and tested at UCSD. An introduction to the needed Rocks changes to support Solaris and Rocks-on-Solaris will be presented.

  • Extending Functionality Through the Rocks Command Line Roll Screen Development As an extension to the previous session, roll-developers can add new installation screens and have them integrated seamlessly. Nadya Williams will describe here test harness that significantly improves the development of installation screens. The Rocks command line is the way rolls extend the command structure for Rocks. The Rocks Viz Roll will be used as key example of roll-based extension to support tiled-display clusters. The Solaris command set (currently under development) will be illustrative of how Rocks commands can work across different architectures.
  • Introduction to Clusters and Rocks Overview This session will cover the basics of types and design of clusters (from Beowulf, to Tiled Walls, to High-Performance Supers). The basic philosophy and first level design of Rocks will be presented as will comparisons to some other competitive methods. Getting started on Rocks will include building of real and virtual machines in Rocks 5.0 (V).

  • Basic Management and Customization While Rocks clusters are turnkey, users always to manage and customize their cluster. Introduction of the Rocks configuration graph and how to add new packages and configuration will be covered. Other common customization scenarios will be described.

  • Introduction to Building Your Own Roll Rolls are the way to customize Rocks. The implementation of Rolls is defined and the levels of customization is presented. A detailed example of building a straightforward will be worked out during this session.

Rocks-A-Palooza III    

In the agenda, there are two tracks: one focused towards users, the other towards developers.

Attendees in the user track will walk away with in-depth knowledge of how Rocks clusters are built, used and maintained. We'll discuss the philosophies and rationales behind core Rocks services and utilities. An introduction to Rolls and Roll development will be presented. A hands-on lab will enable attendees to experiment with Rocks.

In the developer track, Roll development will be the focus. Roll internals will be presented as well as tips and techniques on how to debug and test a Roll. The main goal of this track is for attendees to walk away with a beta version of their own Roll.

Also, we'll host the kickoff meeting for the Large Cluster Working Group. This meeting will bring together application scientists, developers and administrators that run and use large clusters. The goal of this working group is to define a plan to develop the Large Cluster Roll that will benefit folks who run and use large-scale Rocks clusters. If you would like to participate in this meeting, send a note to

The following material was presented.

Rocks-A-Palooza II    

The following material was presented:

  • Invited Talks
  • ThaiGrid, SCE, and Rocks - Building a National Grid in Thailand, Putchong Uthayopas, Thai National Grid Center
  • KRocks - Korean Language Localization of Rocks, Yuchan Park, Korea Institute of Science and Technology Information
  • Building and Managing a 1000-node Rocks Cluster, Federico Sacerdoti, DE Shaw
  • Finnish Material Physics Grid using Rocks, Olli-Pekka Lehto, Finnish IT Center for Science
  • Tutorials
  • Introduction to Clusters (slides)
  • Introduction to Rocks (slides)
  • Introduction to Roll Development (slides)
  • Hands-On Labs
  • Building a Rocks Cluster (slides)
  • Cluster Management and Maintenance (slides)
  • Introduction to MPI Programming (slides)
  • Introduction to Grid Computing (slides)

Rocks-A-Palooza I    

Rocks-A-Palooza I (held at the San Diego Supercomputer Center in La Jolla, California on May 18-19, 2005), was the first in a series of annual workshops for users and developers of the Rocks Cluster Distribution.

This first workshop focused on tutorials for both beginning and advanced users. This meeting had two tracks: one for users and another for developers. The user track (1) included an introduction to clusters, grids, Rocks, and Roll development. The developer track (2) focused entirely on Roll development.

The slides for all presentations are available.