High performance clusters and grids

On operating system level, two cluster architectures exist: High performance clusters and High availability clusters.


High performance clusters are meant to create large computing power by combining many computer systems. Usually a large amount of cheap off-the-shelf PC's are used, connected by a high-speed network (gigabit Ethernet of Infiniband). This creates one large supercomputer.

These clusters are used for calculation-intensive systems, like weather prognosis, geological, nuclear of pharmaceutical investigations. The challenge is to have all systems doing useful calculations most of the time, without wasting resources and time communicating to other systems in the cluster.

0n www.top500.org a list of the world's 500 most powerful computers is published. Most of these systems really are clusters, based on a large amount of smaller systems. Many of these systems run Linux. A well-known high-performance open source project for Linux is Beowulf.


A Grid is a high-performance cluster that consists of systems that are geographically diverse. The limited bandwidth is the bottleneck when architecting grid systems. Therefore, grids can only be used for specific tasks.

The best known (and relatively old) example of a grid  is the SETI@HOME project, where a large amount of PC's of Internet users are searching for extraterrestrial life. These type of grids use the unused computer time of PC's (for instance when the computer is showing it's screensaver). Tasks to be done can be distributed through the Internet and can be calculated on the idle PC's. When a piece of calculation is finished, the result will be sent back via the Internet and a new task can be retrieved.


A more serious example of a grid is a project that is searching for a cure for cancer or the analyses of the human DNA.

Broker firms exist for commercial exploitation of grids. People can get paid for contributing computer time, and companies can pay money to get computertime on the grid. This way companies can have access to a virtual supercomputer for a relatively small amount of money, and just for the time they need it.


An important subject of grids architecture is their security. PC's running calculations should be sufficiently secured against illegal use by third parties. Also, data that is sent through the grid should not be altered and the grid infrastructure must be sure the PC's calculate their tasks as expected. Much work in this field must be done, as grids are a relatively new technology.

This entry was posted on Tuesday 01 May 2007

Earlier articles

Infrastructure as code

My Book

DevOps for infrastructure

Infrastructure as a Service (IaaS)

(Hyper) Converged Infrastructure

Object storage

Software Defined Networking (SDN) and Network Function Virtualization (NFV)

Software Defined Storage (SDS)

What's the point of using Docker containers?

Identity and Access Management

Using user profiles to determine infrastructure load

Public wireless networks

Supercomputer architecture

Desktop virtualization

Stakeholder management

x86 platform architecture

Midrange systems architecture

Mainframe Architecture

Software Defined Data Center - SDDC

The Virtualization Model

What are concurrent users?

Performance and availability monitoring in levels

UX/UI has no business rules

Technical debt: a time related issue

Solution shaping workshops

Architecture life cycle

Project managers and architects

Using ArchiMate for describing infrastructures

Kruchten’s 4+1 views for solution architecture

The SEI stack of solution architecture frameworks

TOGAF and infrastructure architecture

The Zachman framework

An introduction to architecture frameworks

How to handle a Distributed Denial of Service (DDoS) attack

Architecture Principles

Views and viewpoints explained

Stakeholders and their concerns

Skills of a solution architect architect

Solution architects versus enterprise architects

Definition of IT Architecture

What is Big Data?

How to make your IT "Greener"

What is Cloud computing and IaaS?

Purchasing of IT infrastructure technologies and services

IDS/IPS systems

IP Protocol (IPv4) classes and subnets

Infrastructure Architecture - Course materials

Introduction to Bring Your Own Device (BYOD)

IT Infrastructure Architecture model

Fire prevention in the datacenter

Where to build your datacenter

Availability - Fall-back, hot site, warm site

Reliabilty of infrastructure components

Human factors in availability of systems

Business Continuity Management (BCM) and Disaster Recovery Plan (DRP)

Performance - Design for use

Performance concepts - Load balancing

Performance concepts - Scaling

Performance concept - Caching

Perceived performance

Ethical hacking

Computer crime

Introduction to Cryptography

Introduction to Risk management

The history of UNIX and Linux

The history of Microsoft Windows

The history of Novell NetWare

The history of operating systems - MS-DOS

The history of Storage

The history of Networking

The first computers

History of servers

Tips for getting your ITAC certificate

Studying TOGAF

Is your data safe in the cloud?

Proof of concept

Who needs a consistent backup?

Measuring Enterprise Architecture Maturity

Human factors in security

Master Certified IT Architect

ITAC certification

Open group ITAC /Open CA Certification

Human factors in security

Google outage

SAS 70

TOGAF 9 - What's new?

DYA: Development without architecture

Spam is big business

Why IT projects fail

Power and cooling

Let system administrators participate in projects

The 7 Habits of Highly Effective People


A meeting with John Zachman

ITAC - IT Architect certification

Personal Information is Personal Property

The Irresistible Forces Meet the Movable Objects

Hardeningscheck and hack testing for new servers

Knowledge management

Information Lifecycle Management - What is ILM

LEAP: The Redmond trip

LEAP: The last Dutch masterclasses

What do system administrators do?

Is software ever finished?

SCADA systems

LEAP - Halfway through the Dutch masterclasses

Securing data: The Castle versus the Tank

Non-functional requirements

LEAP - Microsoft Lead Enterprise Architect Program

Reasons for making backups

Log analysis - Use your logging information

Archivering data - more than backup

Patterns in IT architecture

Layers in IT security

High performance clusters and grids

Zachman architecture model

High Availability clusters

Monitoring by system administrators

What is VMS?

IT Architecture certifications

Storage Area Networks (SAN)

Documentation for system administrators


Presentations: PowerPoint sheets are not enough

99,999% availability

Linux certification: RHCE and LPI

IT Infrastructure model

Sjaak Laan

Recommended links

Ruth Malan
Gaudi site
Esther Barthel's site on virtualization
Eltjo Poort's site on architecture


XML: RSS Feed 
XML: Atom Feed 


The postings on this site are my opinions and do not necessarily represent CGI’s strategies, views or opinions.


Copyright Sjaak Laan