Coordinators:

Erwin Laure, CERN
Heinz Stockinger, Swiss Institute of Bioinformatics
 

The Grid Track covers several aspects of Grid computing and provides the ability to get hand-on experience with modern Grid tools. A major part will be dedicated to Grid software that is deployed by the WLCG and EGEE projects (both managed by CERN. These projects aim to deploy a large-scale research infrastructure for Grid computing spanning more than 200 sites world-wide. This infrastructure is in regular use by LHC experiments and, through the EGEE project, by several other scientific communities such as biomedicine, astro-physics, chemistry, and earth observation. The tutorials will present the Grid software architecture and discuss the interplay of basic Grid software, higher level Grid middleware, and application software.

Emphasis will be put on Grid architecture and specific middleware topics in job submission, data management and information systems. Novel Grid service technologies which are based on extensions to Web Service technologies will be introduced. This is complemented by lectures on operational aspects of Grid infrastructures as well as on optimisation techniques. In several practical exercises the students will learn how to use Grid tools for their data and/or computing intensive applications.
 

Glossary of the different acronyms: http://www.gridpp.ac.uk/gas/

Series

Type

Lecture

Description

Lecturer

Grid Technologies

Lectures

Lecture 1

Introduction to the Grid computing

An Overview about the Grid Track, it's lectures, the Grid architecture, techniques used to build Grid middleware, and major Grid infrastructures is given.

Erwin Laure
Heinz Stockinger

Lecture 2

Job Submission / Workload Management

Most of the users of the Grid software interact with the system by submitting their jobs (executable programs) to a Resource Broker which does a matchmaking on available and requested resources and then dispatches jobs to resources on the Grid. This lecture provides background about the work load management software system and details about how job submission is done.

Erwin Laure
Heinz Stockinger

Lecture 3

Data Management

One of the main objectives of a Data Grid is the management of large distributed data stores. This lecture gives an overview about replica and meta data management as well as the software tools provided to deal with data management problems.

Erwin Laure
Heinz Stockinger

Lecture 4

Information Systems

In a Grid environment, there are several hardware and software resources that can be used by end users as well as Grid services and applications. Information systems are used to keep track of resources and also to monitor the current status. Current solutions are presented in detail and how end users can interact with them.

Erwin Laure
Heinz Stockinger

Lecture 5

Grid Service Technologies

Recent advances in Grid technologies allow to move from tightly coupled Grid systems to more loosely coupled Grid Services exploiting Web Service technologies. In this lecture we introduce the basic concepts of Grid Services and their underlying standards.

Erwin Laure
Heinz Stockinger

Exercises

Exercise 1
Exercise 2

Hands-on exercise on Job submission

Practical exercises where participants will actively use Grid Software for executing their computation on the Grid.

Erwin Laure
Heinz Stockinger

Assisted by

Marc Ozonne

Exercise 3
Exercise 4

Hands-on exercise on Data Management

Practical exercises where participants will actively use Grid Software for solving data management problems, combined with computational tasks.

Erwin Laure
Heinz Stockinger

Assisted by

Marc Ozonne

Exercise 5
Exercise 6
Exercise 7

Hands-on exercise on Grid Services

Practical exercises how Grid Services technologies work, including setting up a customized Grid Service

Erwin Laure
Heinz Stockinger

Assisted by

Marc Ozonne

Prerequisite Knowledge

Desirable prerequisite

and

 references to further information

The participant should have basic understanding of :Linux shell Script as well as Java. In addition, some understanding of XML is desirable.

References

• Basic linux shell scripts
  Linux Shell Scripting Tutorial

• Basic Java
  The Java Tutorial

• XML
  XML Tutorial
  XML-RPC.com

Grid Operation

Lectures

Lecture 1

Grid Operation

Diverse application communities are expecting production like quality grids. We will introduce the goals and the issues involved in order to ensure the availability, dependability and reliability of grids. In that regard, the operation model including workflow, procedures and tools set up in the scope of the "Enabling Grids for E-sciencE" (EGEE) project and the implications of grid operations in LHC computing Grid (LCG) will be addressed.

Grid Optimization Techniques

Lectures

Grid Optimization Techniques

The main usage of Grid computing in High Energy Physics is in the field of high throughput computing, i.e. to give computing power to many users at the same time. However, in order to reach a good overall performance, several optimization techniques have to be applied.
Furthermore, the lecture also discusses classical high performance computing (massive parallel computing) and its application in the Grid.

Grid Technologies

Wrap up

Session 1

Wrap-up of Grid Technologies Track

Erwin Laure
Heinz Stockinger