Introduction to cluster computing
E. Imamagić, Damir Danijel Žagar, Srce - University Computing Centre, Croatia

Abstract:

Main goal of this tutorial is to describe computer clusters, which are common platform used for execution of parallel applications. Tutorial will focus on application execution by using cluster job management system.

First, we will make short introduction to parallel computing and cluster job management systems. Then, we will describe various types of jobs that users can execute on clusters. We will provide information how to describe, execute and manage jobs. In the end, we will describe additional tools that users can utilize to monitor their jobs.

For the tutorial, we will provide real cluster with eight compute nodes. Cluster is installed in University Computing Centre, with Rocks cluster distribution. For job management, Sun Grid Engine (SGE) system is used.

Tutorial overview

1. Introduction to clusters & parallel computing
2. Cluster environment
3. Submitting jobs
   - job description
   - batch jobs
   - interactive jobs
   - parallel jobs
   - job arrays
   - environment variables
   - advanced job description
4. Job management
   - monitoring
   - changing job description
   - suspending jobs
   - stopping jobs
5. Other tools - Ganglia monitoring
   - direct access to nodes
   - executing OS commands
   - listing processes
   - stopping processes

Biography

Emir Imamagić graduated from the Department of Electronics, Microelectronics, Computer and Intelligent Systems, Faculty of Electrical Engineering and Computing, University of Zagreb in May 2004. His research interests are high performance computing, distributed computing, computer clusters and grid systems.
Before graduation, he has worked on the AliEn Grid project at CERN, Switzerland in summer 2003 and on the MidArc middleware project at Ericsson Nicola Tesla in summer 2002. He is currently working as a researcher on the CRO-GRID Infrastructure project at University Computing Centre.