You are on page 1of 23

CLUSTER COMPUTING

TECHNOLOGY
BY : MAHESH BHOOP
NIKHIL JAMDADE
WHAT IS COMPUTING ?
1) Computing is usually defined as the activity of
using and improving computer hardware and software.

2) A computer is a machine that manipulates data


according to a set of instructions called a computer
program.
3) A computer is a programmable machine that receives
input, stores and automatically manipulates data, and
provides output in a useful format.
WHAT IS A PC CLUSTER ?
 Clustering is the use of multiple computers,
storage devices, and redundant interconnection, to
form what appears to users as a single highly
available system.

 Computer cluster technology puts clusters of


system together to provide better system reliability
and performance.
DIAGRAM :
Cluster Architecture :
NEED OF CLUSTER COMPUTING ?
Here are some signs you want to start clustering more:

 Your company has expanded.

 Your company has to use higher functioning programs.

Your departments have grown or moved to other offices.

Your tasks are becoming harder to complete with


singular computers.
Features :
Collaboration
Scientists can collaborate in real-time across dispersed locations-
Bridging isolated islands of scientific research and discovery- when
HPC clusters are based on open source and building block technology.

Scalability
HPC clusters can grow in overall capacity because processors and nodes
can be added as demand increases.

Availability
Because single points of failure can be eliminated, if any one system
component goes Down, the system as a whole or the solution (multiple
systems) stay highly available.
Ease of technology refresh
Processors, memory, disk or operating system (OS) technology can be
Easily updated, And new processors and nodes can be added or
upgraded as needed.

Affordable service and support


Compared to proprietary systems, the total cost of ownership can
be much lower. This includes service, support and training
DIFFERENT KINDS OF PC CLUSTER ?
 High Performance Computing Cluster

 Load Balancing

 High Availability
High Performance Computing Cluster
(Beowulf)
 Start from 1994
 Donald Becker of NASA assemble the world’s first
cluster with 16 sets of DX4 PCs and 10 Mb/s
Ethernet
 Also called Beowulf cluster
 Built from commodity off-the-shelf hardware
 Applications like data mining, simulations, parallel
processing, weather modelling, computer graphical
rendering, etc.
Load Balancing Cluster
 PC cluster deliver load balancing performance
 Commonly used with busy ftp and web

servers with large client base


 Large number of nodes to share load
High Availability Cluster
 Avoid downtime of services
 Avoid single point of failure
 Always with redundancy
 Almost all load balancing cluster are with HA

capability
Two Significant Aspects of HPC
 Given a fixed complexity of an algorithm,
the time consumption T will be decreased
by a factor of 1/N as N increases, where N
is the number of distributed computing
workers in the cluster.
 Increasing the number of distributed

computing workers in the cluster will enable


the cluster to handle jobs with higher
complexity while maintain almost the same
time consumption.

13
Where to Find Cluster Computing
• The need for cluster computing becomes highly important
in companies or organizations which need to have
information be more public, though only available to
trained workers

Large international corporations


Government agencies
Companies with numerous employees
Data management organizations
Hospitals and medical centers
A Successful Case Study:
“Compute Cluster Server 2003 has been a fantastic solution for us. It’s
affordable, easy to deploy and manage, and...it doesn’t require any of our
researchers to rewrite code.”
Yonael Teklu, IT Support Manager, Advanced Research Institute, Virginia Tech


Needed significant 
Upgraded existing 
Faster research time
computing resources server computers to and results
for data and statistical 64-bit version of
analysis Microsoft® Windows

Simple deployment
Server® 2003 and management

Required an
economical high- 
Purchased new

Ease of use
performance server computers to 
Improved security
computing solution create a 16-node authentication
cluster using Capacity for future

Reluctant to engage in Microsoft Windows®

complex system expansion


Compute Cluster
management Server 2003
Expectation of
Microsoft Windows Compute Cluster
 Reduce more computational cost
 Security
◦ Integration with Active Directory enables role-based security for
administration and users.
 Reliability
 Scalability
◦ “Additional compute nodes can be added to the compute cluster
by simply plugging in the nodes and connecting them.”
 Easy deployment and administration
◦ Microsoft Management Console provides a familiar administrative
and scheduling interface
 User friendly
◦ MATLAB® Applications
◦ C++ Applications, Microsoft ® Visual Studio 2005, SQL Server
2005
India in cluster computing
 PARAM 10000 - National Param
Supercomputing Facility (NPSF) at Pune and
the 1 TF (TeraFlop) PARAM Padma at the C-
DAC's Terascale Supercomputing Facility
(CTSF) at Bangalore
 PARAM with Rmax (Sustained Performance) of

37.80 TFs and Rpeak (Peak Performance) of


54.01 TFs, has been ranked at One Hundred
Nine (109th) in TOP500 Systems enlisted.
The Future is Brighter Than Ever
Computer clusters will:
 Make running a business more efficient

Save computer costs

Help to reach out to other workers in


other parts of the world

Encourage creativity among workers who


can file share
Example : Projects @ CBIL
 CBIL is a participant of caBIGTM – cancer
Biomedical Informatics Grid sponsored by
the National Cancer Institute (NCI) of the
National Institutes of Health (NIH)
 Goal of caBIGTM : demonstrate how shared

informatics platform can allow a


comprehensive, federal grid of information
to be made available to the cancer research
community.

19
Conclusions by cBIL
 Cluster computing solution will significantly
help CBIL to reduce computational cost.
 Cancer research community will get benefits

from computational efficiency using cluster


computing.
 Microsoft Windows Compute Cluster Server

2003 brings high-performance computing


(HPC) to industry standard, low cost servers,
which meets CBIL’s needs perfectly.
Benefits of Computer Clusters

 Benefits of Computer Clusters

 Reduced Cost

 Processing Power

 Improved Network Technology

 Availability
Conclusion :

1) Increase throughput for massive data processing

2) Inexpensive - uses commodity computers with lots of disks and


disk space

3) New trends in hardware and software technologies are likely to


make clusters more promising.

You might also like