This document discusses computer clusters and their architecture. A cluster consists of loosely connected computers that can be viewed as a single system. It includes nodes, a network, an operating system, and cluster middleware to allow programs to run across nodes. Clusters provide benefits like data sharing, parallel processing, and task scheduling. The architecture includes a master node that manages the cluster and computing nodes that process tasks. Beowulf clusters specifically use many connected commodity computers as nodes. The document outlines some example applications and operating systems used in clusters.

1. By: Ashraful Hoda
Ashraful.hoda01@mail.com

2. 








Introduction
History
why cluster computing?
Architecture
Clustering Concept
Several application
Operating System
Companies that use it
High performance Clusters (HPC)
2

3.  A computer cluster consists of a set of loosely connected
computers that work together so that in many respects they
can be viewed as a single system.
Cluster consists of:
 Nodes(master+computing)
 Network
 OS
 Cluster middleware: It permits
compute clustering programs
to be portable to a wide variety
of clusters.
…
Cluster Middle ware
High Speed Local Network
CPU
CPU
…
CPU
Cluster
3

4. INTRODUCTION
 Consists of many of the same or similar type of machines.
 Tightly-coupled using dedicated network connections.
 The components of a cluster are usually connected to each other
through fast local area networks, each node running its own
instance on an operating system.
 All machines share resources.
 They must trust each other so that does not require a password,
otherwise you would need to do a manual start on each machine.

5. HISTORY
 The first commercial clustering product was ARCnet, developed
by Data point in 1977.
 Digital Equipment Corporation released their VAX cluster product
in 1984 for the VAX/VMS operating system.
 The ARCnet and VAX cluster products not only supported parallel
computing, but also shared file systems and peripheral devices.
 The idea was to provide the advantages of parallel processing,
while maintaining data reliability and uniqueness.

6. Through CLUSTERS
 Data sharing
 Message passing and communication
 Task scheduling
 Node failure management
 Parallel programming
 Debugging and monitoring

7. Logical view

8. ARCHITECTURE
 It consists of a collection of interconnected stand-alone computers
cooperatively working together a single, integrated computing
resource.
 A node:

a single or multiprocessor system with memory, I/O facilities, &OS

generally 2 or more computers (nodes) connected together in a single
cabinet, or physically separated & connected via a LAN appear as a
single system to users and applications provide a cost-effective way to
gain features and benefits

9. ARCHITECTURE
 Database Replication Clusters

10. The components required to the development
of low cost clusters are:




Processors
Memory
Networking components
Motherboards, busses, and other sub-systems

11. Beowulf cluster
Start from 1994
Donald Becker of NASA assembled this cluster.
Also called Beowulf cluster
Applications like data mining, simulations, parallel processing,
weather modeling, etc


12.  A Beowulf Cluster is a computer design that uses parallel processing
across multiple computers to create cheap and powerful
supercomputers. A Beowulf Cluster in practice is usually a collection of
generic computers connected through an internal network.
 A cluster has two types of computers, a master computer, and node
computers.
 When a large problem or set of data is given to a Beowulf cluster, the
master computer first runs a program that breaks the problem into small
discrete pieces; it then sends a piece to each node to compute. As nodes
finish their tasks, the master computer continually sends more pieces to
them until the entire problem has been computed.
12

13. ( Ethernet,Myrinet….)
+ (MPI)
 Master: or service node or front node ( used to interact with users and manage the
cluster )
 Nodes : a group of computers (computing node
s)( keyboard, mouse, floppy, video…)
 Communications between nodes on an interconnect network platform
( Ethernet, Myrinet….)
 In order for the master and node computers to communicate, some sort message
passing control structure is required. MPI,(Message Passing Interface) is the most
commonly used such control.
13

14. Brief Technical Parameters:

OS:

Service node:

Computing nodes:

System Memory:



CentOS 5 managed by Rochs-cluster
1 (Intel P4 2.4 GHz)
32(Intel P4 2.4- 2.8 GHz)
1 GB per node
Network Platforms:
Gigabit Ethernet, 2 cards per node
Myrinet 2 G
Language: C, C++, Fortran, java
Compiler: Intel compiler, sun Java compiler
14

15. Science
Computation
Digital Biology
Aerospace
Resources
Exploration
15

16. High Performance Networks/Switches
a. Ethernet (10Mbps),
b. Fast Ethernet (100Mbps),
c. Gigabit Ethernet (1Gbps)
e. ATM
f. Myrinet (1.2Gbps)
g. Digital Memory Channel

17. ISSUES TO BE CONSIDERED
Cluster Networking
Cluster Software
Programming
Timing
Network Selection
Speed Selection

18. OS (Operating System )
 Three of the most commonly used OS are :

Windows
mainly used to build a High Availability Cluster or a NLB(Network Local
Balance) Cluster, provide services such as Database, File/Print,Web,Stream
Media .Support 2-4 SMP or 32 processors. Hardly used to build a Science
Computing Cluster

Redhat Linux
The most used OS for a Beowulf Cluster. provides High Performance and
Scalability / High Reliability / Low Cost ( get freely and uses inexpensive
commodity hardware )

SUN Solaris
Uses expensive and unpopular hardware
18

19. State of the art Operating Systems with
companies :
a. Linux
b. Microsoft NT
c. SUN Solaris
d. IBM AIX
e. HP UX (Illinois - PANDA)

20. 20

21.  Calculation procedure for peak performance:
 No of nodes 64
 NO. of Master Nodes : 1
 Memory RAM: 4 GB
 Hard Disk Capacity/each node : 250GB
 Storage Cap. 4 TB
 CLUSTER Software : ROCKS version 4.3
 No .of processors and cores: 2 X 2 = 4(dual core +
dual socket)
 CPU speed : 2.6 GHz
21

23. ANY
QUERIES ???