Few people who use computers have not heard of Linux®. Linux is at the heart of a revolution that is fundamentally changing many aspects of how software is written and delivered. It remains to be seen where this revolution will ultimately lead. Far less nebulous is the Linux penetration into the scientific calculation arena, or more specifically, its use in High-Performance Computing clusters.
This redbook will guide system architects and systems engineers through a basic understanding of cluster technology, terms, and Linux High-Performance Computing (HPC) clusters. We discuss some of the design guidelines used when architecting a solution and on how to install and configure a working Linux HPC cluster.
This redbook documents the building of a Linux HPC cluster on IBM Eserver xSeries hardware. Using this approach, and building a type of Beowulf cluster, we can achieve dramatic performance at a fraction of the price of previous solutions.
This redbook will also teach you the concepts and principals needed to build your own HPC cluster. The installation process is streamlined and simplified by the extensive use of scripts. Management tools are provided to easily manage a large number of compute nodes that remotely use the built-in features of Linux and the advanced management capabilities of the IBM Eserver xSeries Service Processor Network.
About The Author
Luis Ferreira (also known as “Luix”) is a Software Engineer at IBM Corp - International Technical Support Organization, Austin Center working in Linux and AIX projects. He has 18 years of experience in UNIX-based operating systems, and holds a MSc. Degree in System Engineering from Univerdade Federal do Rio de Janeiro, Brazil. Before joining the ITSO, Luis worked at Tivoli Systems as a Certified Tivoli Consultant, at IBM Brasil as a Certified IT Specialist, and at Cobra Computadores as kernel developer and software designer. His e-mail address is email@example.com.
Gregory Kettmann (also known as “Greg”) is an IT Architect working for IBM Global Services, ITS, as a Subject Matter Expert in Linux Clusters. His group, the Linux Global Solutions Group, is responsible for establishing Linux strategies and policies worldwide. Greg has 21 years of experience with IBM, the last 10 of which have been as a workstation and networking specialist. He has been involved with Linux and Linux High-Performance Computing clusters for the past several years. He earned his ET degree from NTS and his EE from CREI. His e-mail address is firstname.lastname@example.org.
Jens Ihamo is IT Specialist at the IBM Techline in Greenock, Scotland. He has more than three years of experience in xSeries and Netfinity servers from Post Sales Support and Technical Pre-Sales environments, He has been involved for four years with Linux and has worked for IBM for more than three years. His areas of expertise include networking, clustering, Fibre Channel technologies and all things Linux. He is a Red Hat Certified Engineer (RHCE), Professional Server expert (PSS) and Microsoft Certified Systems Engineer (MCSE). His e-mail address is email@example.com.