GridComputing: Introduction and Overview
Student: Tripti
College: Raj Kumar Goel institute of technology for women
Abstract: This paper provides an introduction and overview of the overwhelming technology grid
computing. Rapid growth has been exhibited in last few years regarding the exponential increase in
the processing power of the computers, data storage and communication. But there still lies many
more complex and computational intensive problems, which are problems even for the
supercomputers .Heterogeneous resources are the solution to problems. Grid computing is the new
method of pooling the resources for solving large and complex problems. This paper unveil the
underlying concepts of Grid computing.
Index Terms-Grid Computing
Grid computing is the collection of computer
resources from multiple resources to reach a
common goal.
The grid can be thought of as a distributed
system with non interactive workloads that
involve a large number of files. The major goal
of distributed computing research was to give us
an easy , simple and transparent method of
access to a vast set of heterogeneous resources.
This is generally known as meta computing.
Meta computing done on local area networks is
known as Cluster computing and those which
are done on wide are networks are known as
Grid computing. This paper deals with the later
communications and storage technologies. Grid
computing is rapidly emerging as dominant
paradigm for wide area distributed computing
and the Global grid Forum 1 are investing
considerable effort in developing and enabling
seamless and secure discovery access to , and
interactions among resources , services and
applications. This potential for aggregation ,
integration and interactions has also made it
possible for scientists and engineers to conceive
a new generation of applications that enable
realistic investigation of complex scientific and
engineering problems.
evolution of grid computing from its roots in the
parallel and distributed computing to its current
state and emerging trends and visions.
The grid vision has been describes as a world in
which computational power (resources, services,
data)is readily available as electrical power and
other utilizes, in which computer services make
this computational services available to users
with different level of expertise in diverse areas ,
and in which these services can interact to
perform specified tasks efficiently and securely
with minimal human intervention. Driven by
revolutions in science and business are fueled by
A computational grids is a hardware and
software infrastructure that provides dependable,
consistent, pervasive access to computational
3.1 Characteristics of computational Grid
There are many desirable properties and features
that are required by a grid to provide users with
a computing environment. They are follows
 Heterogeneity
The grid involves a number of resources
that are varied in nature and can
encompass a large geographical distance
through various domains.
The grid should be tolerant to handle a
large number of nodes without any
performance degradation.
Adaptability or Fault tolerant
In a grid unexpected computational
aborts, hard or software fault are high .
These faults are generally handled by
resource managers.
All the user participating computers
should be protected from any malicious
characteristics and requirements. Because of
this reason we cannot have a uniform single
architecture . But in general we can identify
basic services that almost all the grid will
provide through different grids will different
approaches for the realization of services.[5]
This description of grid architecture does
provide a complete enumeration of all the
required protocols and services but it identifies
the requirements for general class of
components. This architecture organizes the
components into layers as shown in Figure2.[4]
3.2 Grid Components[8]
The major components that necessary to form a
grid are shown in Figure 1.
The components are as follows:
 User level
This layer houses the Application and
High level interfaces. Applications can
be varied and encompass large variety
of problems from chemistry to nuclear
engineering. This high level interfaces
implement an interface and protocols
allowing the applications and users to
access the middle ware services.
 Middleware Level
The major functionalities of systems
normally occur in this layer. This layer
provide many services like Resource
discovery resource scheduling and
allocation, fault tolerance , security
mechanism and load balancing. It
should provide users the transparent
view of the resources available.
 Resource Level
This layer typically provides local
services that render computational
resources like CPU cycles, storage,
computers, Networks infrastructure,
software etc.
Computational grid have to be designed so as to
serve different communities with varying char t
The layers of the grid are as follows : [5]
 Fabric Layer
This layer provide the resources ,which
could comprise computers(PC’s running
windows NT or unix), storage devices
and databases. The resources could also
be logical entity such as distributed file
system or computer pool. Excellent
fabric functionally could mean that
sophisticated complicated operations
can be accomplished . For this it could
support enquiry mechanism to discover
their state , structure and capabilities. It
should also have resource management
mechanism that provide some control of
delivered quality of service.
Connectivity Layer
This layer builds on the connectivity
layer communication and authentication
protocols enable the exchange of data
between fabric layer resources. For
communication transport , naming and
routing are required. These protocols
Can be drawn from TCP/IP protocol stack.
 Resource Layer
distinguished primarily into classes , which
This layer builds on the connectivity layer
communication and authentication protocols
to define Application Program Interfaces
(API) and software develop kit (SDK) for
secure negotiation, initiation, monitoring
and control, accounting and payment of
sharing operations. The protocols , which
the resources layer implement to achieve
the above functionality are implemented
with the help of function provided by the
fabric layer. Resource layer protocol can be
Management Protocols.
Information Protocol
This protocol is used to obtain the
necessary information about the structure
and the state of the resources.
Management Protocol
In order to negotiate the access
resources this protocol is used.
Collective Layer
This layer is different from the resource
layer in t5he sense, while resource layer
concentrates on interactions with single
resource ; this layer helps in coordinating
multiple resources . Its tasks can be varied
like directory services , Co-allocation and
scheduling , monitoring, diagnostic services,
and software discovery services.
 Application Layer
This layer consists of the user applications
and programs and which call upon another
Grid computing is an active research area and is
being worked on worldwide .
There are many projects that are being carried
out and they can be classified accordingly as :
 Mix and Match approach
Ex: Globus[6][10]
 Problem solving Environment approach
Ex: Netsolve
 Inter / www approach
 Object oriented approach.
GRID Resources can be used to solve complex
problems in many areas like high –energy
physics , biophysics , nuclear simulations,
weather monitoring and predictions , financial
analysis , chemical engineering etc.
Projects, such as SET @home and Distributed .
Net , builds grids by linking multiple low end
computational resources , like PCs, from the
internet to detect extraterrestrial intelligence and
crack security algorithms respectively.
There are many grid computational projects like
globus, netsolve, entropia, SETI [9] . condor,
legion which are constantly improving the grid
architecture and application interface . Grid
computing has serious consequences and its
implications are enormous in the field of grid
computing. Today large scale parameter study
application are using computational grid
resources to crack algorithms and search for
extraterrestrial intelligence.
[2] M.A Baker, R.Buyya and D. Laforenza, The
Grid: International Efforts In Global
Computing, SSGRR 2000 The Computer & e
Business Conference ,Italy JULY 31. 2000August 6- 2000
[3] Vincet Neri, Gilles Fedak and Franck
Cappello Xtremo Web : building an
experimental platform for Global computing
Grid 2000 December 2000. IEEE press.
[4] Foster .I., Kesselman, C. and Tuecke, S. The
Anatomy of the grid: Enabling scalable
Virtual Organizations. International Journal of
High Performance Computing Applications ,
[5] l. Foster and C. Kesselman , editors, The
Grid: Blueprint for a New Computing
Infrastructure . MORGAN Kaufmann, 1998
[7] I.Platform Computing . “ The politics of
Grid: Organizational Politics as a barrier to
implementing Grid Computing:. 2004.

grid computing - Academic Science