GRID COMPUTING

PROFILE

Name

1) ALEKYA REDDY 2)G NITISH KUMAR (3/4B.Tech CSE)

Name of the Institution Title of the Paper E - Mail

: DEPARTMENT OF COMPUTER SCIENCE

GRID COMPUTING

[email protected]

CONTENTS
PG NO ABSTRACT 1. INTRODUCTION 2. THE GRID 3. BEGINNING OF GRID 4. GRID COMPUTING CHARACTERSTICS 5. A COMMUNITY GRID MODEL 6. TYPES OF GRID 7. THE KIND OF GRID TOOLS 8. GRID COMPONENTS 9. ADVANTAGES 10. CHALLENGES OF GRID 11. CONCLUSION 12. BIBLIOGRAPHY 4 5 5 5 6 7 8 8 9 14 14 14 15

LIST OF FIGURES

FIG NO
1 2 3 4 5 6 7

NAME
Layered architecture of grid model Possible user view of Grid Security in Grid Environment Broker Service Scheduler Data Management Gram

PG NO
7 10 10 11 12 13 13

Abstract

Grid computing, emerging as a new paradigm for next-generation computing, enables the sharing, selection, and aggregation of geographically distributed heterogeneous resources for solving large-scale problems in science, engineering, and commerce. The resources in the Grid are heterogeneous and geographically distributed. Availability, usage and cost policies vary depending on the particular user, time, priorities and goals. It enables the regulation of supply and demand for resources. It provides an incentive for resource owners to participate in the Grid; and motivates the users to trade-off between deadline, budget, and the required level of quality of service. The thesis demonstrates the capability of economic-based systems for wide-area parallel and distributed computing by developing users quality-ofservice requirements-based scheduling strategies, algorithms, and systems. It demonstrates their effectiveness by performing scheduling experiments on the World-Wide Grid for solving parameter sweeptask and data parallelapplications. This paper focuses on introduction, grid definition and its evolution. It covers about grid characteristics, types of grids and an example describing a community grid model. It gives an overview of grid tools, various components, advantages followed by conclusion and bibliography.

1. INTRODUCTION
This The Grid unites servers and storage into a single system that acts as a single computer - all your power. resources applications tap into all your computing Hardware are fully

business,

government,

research, science and entertainment, integrate networking, communication, computation virtual platform in that and for the the information to provide a computation and data management same Internet virtual way

utilized and spikes in demand are met with ease. This Web site sponsored by Oracle brings you the resources you need to evaluate your adoption organization's of grid

integrates platform for

resources to form a information. The Grid is the computing and data management infrastructure that will provide the electronic. Grid infrastructure will provide us with the ability to dynamically link together resources as an ensemble to support the execution of large-scale, intensive, resourceand

technologies. The Grid is ready when you are.

2. THE GRID
The Grid is the computing management infrastructure that will provide the electronic underpinning global for a in society and data

distributed applications. Grid is a type of parallel and distributed

system that enables the sharing, selection, and aggregation geographically distributed "autonomous" resources dynamically at runtime depending on their availability, capability, performance, cost, and users' quality-of-service requirements. of

Successful paradigms

application were

developed to leverage the immense potential of shared and memory distributed

architectures. Initially it was thought that the Grid would be most useful parallel coupled distributed the Grid in extending computing clusters to

paradigms from tightly geographically systems. has for been as a the However, in practice, utilized platform more

3.

BEGINNINGS
Parallel

OF THE GRID
computing in the 1980s focused efforts algorithms, researchers on the of programs

development

integration of loosely coupled applications some components of which might be running in parallel on a lowlatency parallel machine and for linking resources computation, disparate (storage, visualization, instruments). Coordination distribution and two

and architectures that supported simultaneity. During the 1980s and 1990s, parallel powerful for processors, development software for computers mechanisms managing and and

focused on providing

communication between

execution environments for parallel machines.

fundamental concepts in Grid Computing. The first modern Grid is generally wide-area (IWAY). and a considered to be the information year Developing infrastructure WAY provided applications for the Iseminar and powerful experience for the first generation of modern Grid researchers This as of and was the Grid than projects. important, development different distributed

CHARACTERSTIC S
An computing enterprisegrid is

characterized by three primary features D i v e r s i t y ; D e c e n t r a l i z a t i o n ;

research requires a very focus computing

research. Grid research focuses on addressing the problems of and of I-WAY integration management software.

opened the door for considerable activity in the development of Grid software. 4.

GRID

COMPUTING

Traditional a n d D y n a m i s m Diversity: A typical computing grid consists of many hundreds of managed resources of various kinds including servers, Database Application storage, Servers, Servers, distributed systems have typically been managed from a central administration point. A computing grid further compounds challenges since the resources can be be even more decentralized and may geographically distributed across many different data centers within an enterprise. Dynamism: Components of a traditional application typically run in a static environment without the needing rapidly demands. computing to address changing In a grid, these

Enterprise Applications, and system services like Directory Security and Management Services, Identity Services,

however, the systems and applications need to be able to flexibly adapt to changing demand. For instance, with the late binding nature and cross-platform properties of web services, an application

and others. Managing these resources and their life cycle is a complex challenge. Decentralization:

deployed on the grid may of consist of a At constantly changing set components. different points in time, these components can be hosted on different nodes in the network. Managing dynamic an environment application in such a can be a challenging undertaking.

The

bottom

horizontal layer of the Community Grid Model consists of the hardware resources that underlie the Grid. Such resources include instruments, visualization the resource devices pool and so on. Moreover, represented by this layer is highly dynamic, both as a result of new resources being added to the mix and old resources being retired, and as a result of of the varying performance observable computers, networks, data archives,

5. A COMMUNITY OF GRID MODEL

community has begun to converge on a layered model complex required Grid that allows of the of development

system to

resources in the shared, multi-user environment of the Grid.

services and software integrate The resources.

Community Grid Model (a layered abstraction of the grid) being manner academia commercial Figure 1: Layered of the developed in a loosely coordinated throughout and sector. the

architecture 9

Community Model. The horizontal

Grid next layer

system activities such as authentication, transfer. file

6.

TYPES

OF

(common infrastructure) consists of the software services and systems, which virtualized the Grid. The key concept at the common agreement infrastructure layer is community on software, which will represent the Grid as a unified virtual platform and provide the target for more focused and next

GRID
Grid computing can be used in a variety of ways to address various kinds of application Often, requirements.

grids are categorized by the type of solutions that they best address. The three primary types of grids are Computational grid A computational grid is focused on setting aside resources specifically for computing power. In this type of grid, most of the machines are highperformance servers. Scavenging grid A scavenging grid is most commonly used with large numbers of desktop machines. Machines are scavenged for cycles available and CPU other

software applications. The

horizontal layer (user and application-focused Grid middleware, tools and services) contains software packages built atop software the common This to serves infrastructure.

enable applications to more productively use Grid resources by masking some of the complexity involved in

resources. Owners of

10

the desktop machines are usually given control over when their resources are available to participate in the grid. Data grid A data grid is responsible for housing and providing access to data not where across multiple with is organizations. Users are concerned this data

some consider this is another form of Grid computing.

7. THE KIND OF GRID TOOLS

managers, systems, applications, authorities, transfer file

located as long as they have access to the data. For example, you may have two universities doing research, life each science with

mechanisms like Grid Directory services. Systems grid capable services available Grid define topology on a be of are to systems (and in must

unique data. A data grid would allow them to share their data, manage the data, and manage security issues such as who has access to what data. Another common distributed computing model that is often associated with or confused with Grid computing is peer-topeer computing. In fact,

discovering what

them. In short, must be able to monitor) a grids order to share and collaborate. Many directory Grid

11

services implementations are based on past successful models, such as LDAP, network management protocols, indexing services.

management across chance bottlenecks.

systems of

to decrease the

DNS,

Developer tools. Every arena of computing

and

endeavor requires that tools allow to Tools grid different (file

Schedulers load

and

developers succeed. for on niches transfer,

balancers.

One of the main benefits of a grid is maximizing and this and efficiency. Schedulers load provide function more. Schedulers ensure that jobs are completed in some (priority, deadline, urgency, instance) load and distribute for and tasks data order

developers focus

balancers

communications, environment control), range and from

utilities to fullblown APIs. Security. Security grid environment can mean authentication and authorization -in other words, in a

balancers

12

controlling who/what can access a grids resources -- but it can mean a lot more. instance, message integrity message confidentiality are crucial to and financial healthcare environments and For

receptacle in the wall, a grid user should not see all of the complexities of the computing grid. Although the user interface can come in many forms and be application-specific. A grid portal provides the interface for a user to launch applications that will use the resources and services provided by the grid. From this perspective, the user sees the grid as a virtual computing resource just as the consumer sees as of the an. power receptacle on generator.

8.GRID COMPONENTS:A HIGH LEVEL PERSPECTIVE

interface to a virtual

Figure 2: Possible user view of a grid

8.2. Security A major requirement for Grid computing is security. At the base of any grid environment, there must be mechanisms to provide including authentication, authorization, The Grid data Security (GSI) of the encryption, and so on. Infrastructure component robust security,

the portal. The portal will then be responsible for signing in to the grid, either using the user's credentials for or all using a generic set of credentials portal. authorized users of the

Globus Toolkit provides security Figure 3: Security grid environment 8.3. Broker Once authenticated, the user will be launching an application. Based on the application, on and other possibly in a mechanisms. The GSI includes an OpenSSL implementation. It also provides a single signon mechanism, so that once a user is authenticated, a proxy certificate is created and used when performing actions within the grid. When designing your grid environment, you may use the GSI sign-in to grant access to the portal, or you may have your own security for

parameters provided by the user, the next step is to identify the available

14

and

appropriate

8.4. Scheduler Once the resources have been identified, the next logical step is to schedule the individual jobs to run on them. If sets of stand-alone jobs are to be executed with no then interdependencies, a specialized

resources to use within the grid. This task could be carried out by a broker broker provided function. implementation by Globus, service. Information the and Service This the service available within the information Although there is no

there is an LDAP-based information Grid commonly Monitoring Discovery (MDS). provides about resources This service is called the Service (GIS), or more

scheduler may not be required. However, if you want to reserve a specific ensure jobs resource that within or the run (for different

application concurrently inter-process

instance, if they require communication), then a job scheduler should be used to coordinate the execution of the jobs. The Globus Toolkit does not include such a scheduler, but there are several schedulers available that have been tested with and can be used in a Globus grid environment. It should

grid and their status. A broker service could be developed that utilizes MDS.

Figure 4: Broker service

also be noted that there

15

could be different levels of schedulers within a grid environment. For instance, a cluster could be represented resource. as a including moved single The If any data -application or made modules -- must be accessible to the nodes where an application's jobs will execute, then there needs to be a secure and The and to reliable various Toolkit data such This know as to Access method for moving files data nodes within the grid. Globus a contains that 8.5. Data management

cluster may have its own scheduler to help manage the nodes it contains. A higher-level scheduler might be (sometimes used to called a meta scheduler) schedule work to be done on a cluster, while the cluster's scheduler would handle the actual scheduling of work on the cluster's individual nodes.

management component provides services. component, Grid (GASS), facilities Secondary

Storage includes such as

GridFTP. GridFTP is built on top of the standard FTP protocol, but the adds GSI additional for user and functions and utilizes Figure 5: Scheduler authentication authorization.

16

Therefore, once a user has an authenticated proxy certificate, he can use the GridFTP facility to move files without having to go through a login process to every node involved. This facility provides thirdparty file transfer so that one node can initiate a file transfer between two other nodes.

Grid Allocation services launch a particular to

Resource Manager actually on a resource,

(GRAM) provides the job

check its status, and retrieve its results when it is complete.

Figure 6: Data management 8.6. Job and resource management With all the other facilities we have just discussed in place, we now get to the core set of services that help perform actual work in a grid environment. The 17 Gram

Figure 7:

8.7 Job flow in a grid environment Enabling an application for a grid environment, it is important to keep in mind these components and how they relate and

interact your

with

one grid and

logical evolution

step of

in

the the

another. Depending on implementation application requirements, there are many ways in which these pieces can be put together solution. to create a

Internet, and maturing standards and a drop in the cost of bandwidth are fueling the we're today. of the momentum experiencing Virtualization computing environment .

10. 9. ADVANTAGES
Grid computing is about to getting work to computers

CHANLLANGES OF GRID
A the word of caution should be given overly enthusiastic. The grid is not a silver bullet that can take any application and run it a 1000 times faster without the need for buying any more machines or software. Not every application is suitable or enabled for running on a grid. Some kinds simply of applications cannot be

together. Almost every organization is sitting on top of enormous, unused capacity, computing widely

distributed. Mainframes are idle 40% of the time With Grid computing, businesses can optimize computing large across enable Many computing and data resources, pool them for capacity networks, consider the and Grid next workloads, share them collaboration.

parallelized. For others, it can take a large amount of work to modify them to achieve

18

faster throughput. The configuration of a grid can greatly affect the performance, reliability, and security of an organization's computing infrastructure. For all of these reasons, for it us is to important

data processing and into information management Information databases, article, as in files, we well. this and

context covers data in storage devices. In this outline potential problems and the means of solving them in a distributed environment. .

understand how far the grid has evolved today and which features are coming tomorrow or in the distant future

12. BIBLIOGRAPHY
[1] www.ibm.com/grid/inde x.html [2] Foster, I. and Kesselman, C. (eds) (1999) The Grid: Blueprint for a New Computing Infrastructure.. San CA: Francisco, Morgan

11. CONCLUSION
Grid computing introduces concept a to new IT

infrastructures because it supports distributed computing network over a of

heterogeneous resources and is enabled by open standards. computing optimize resources, capital of works Grid to underutilized decrease expenditures, This

Kaufmann [3] Berman, F., Fox, G. and Hey, T. (2003) Grid Computing: Making the

and reduce the total cost ownership. solution extends beyond

19

Global Infrastructure a Reality. Chichester: John Wiley & Sons. [4] book, Computing: Making Global Infrastructure a Reality, http://www.grid 2002.org. the Web Site with Grid associated

20