Introduction to Grid Computing ,

Grid Computing Lexicon

Reading about grid computing can get very confusing if you don't know the lingo. Here's a quick
rundown on some of the terms you might encounter when discussing grid computing:

 Cluster: A group of networked computers sharing the same set of resources.

 Extensible Markup Language (XML): A computer language that describes other data and is
readable by computers. Control nodes (a node is any device connected to a network that can
transmit, receive and reroute data) rely on XML languages like the Web Services Description
Language (WSDL). The information in these languages tells the control node how to handle data
and applications.
 Hubs: A point within a network where various devices connect with one another.
 Integrated Development Environment (IDE): The tools and facilities computer programmers
need to create applications for a platform. The term for an application testing ground is sandbox.
 Interoperability: The ability for software to operate within completely different environments.
For example, a computer network might include both PCs and Macintosh computers. Without
interoperable software, these computers wouldn't be able to work together because of their
different operating systems and architecture.
 Open standards: A technique of creating publically available standards. Unlike proprietary
standards, which can belong exclusively to a single entity, anyone can adopt and use an open
standard. Applications based on the same open standards are easier to integrate than ones built on
different proprietary standards.
 Parallel processing: Using multiple CPUs to solve a single computational problem. This is
closely related to shared computing, which leverages untapped resources on a network to achieve
a task.
 Platform: The foundation upon which developers can create applications. A platform can be an
operating system, a computer's architecture, a computer language or even a Web site.
 Server farm: A cluster of servers used to perform tasks too complex for a single server.
 Server virtualization: A technique in which a software application divides a single physical
server into multiple exclusive server platforms (the virtual servers). Each virtual server can run its
own operating system independently of the other virtual servers. The operating systems don't
have to be the same system -- in other words, a single machine could have a virtual server acting
as a Linux server and another one running a Windows platform. It works because most of the
time, servers aren't running anywhere close to full capacity. Grid computing systems need lots of
servers to handle various tasks and virtual servers help cut down on hardware costs.
 Service: In grid computing, a service is any software system that allows computers to interact
with one another over a network.
 Simple Object Access Protocol (SOAP): A set of rules for exchanging messages written in
XML across a network. Microsoft is responsible for developing the protocol.
 State: In the IT world, a state is any kind of persistent data. It's information that continues to exist
in some form even after being used in an application. For example, when you select books to go
into an Amazon.com shopping cart, the information is stateful -- Amazon keeps track of your
selection as you browse other areas of the Web site. Stateful services make it possible to create
applications that have multiple steps but rely on the same core data.
 Transience: The ability to activate or deactivate a service across a network without affecting
other operations.
Grid computing is a term referring to the combination of computer resources from multiple
administrative domains 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. What distinguishes grid computing from
conventional high performance computing systems such as cluster computing is that grids tend to be more
loosely coupled, heterogeneous, and geographically dispersed. Although a grid can be dedicated to a
specialized application, it is more common that a single grid will be used for a variety of different
purposes. Grids are often constructed with the aid of general-purpose grid software libraries known as
middleware.

Grid size can vary by a considerable amount. Grids are a form of distributed computing whereby a “super
virtual computer” is composed of many networked loosely coupled computers acting together to perform
very large tasks. Furthermore, “distributed” or “grid” computing, in general, is a special type of parallel
computing that relies on complete computers (with onboard CPUs, storage, power supplies, network
interfaces, etc.) connected to a network (private, public or the Internet) by a conventional network
interface, such as Ethernet. This is in contrast to the traditional notion of a supercomputer, which has
many processors connected by a local high-speed computer bus.

What is a Grid?

There are many definitions exist in the literature

Foster and Kesselman, 1998

“A computational grid is a hardware and software infrastructure that provides dependable, consistent,
pervasive, and inexpensive access to high-end computational facilities”

Kleinrock 1969:

“We will probably see the spread of „computer utilities‟, which, like present electric and telephone
utilities, will service individual homes and offices across the country.”

Types of grids,

Global Grid
Drivers:
 Requirement for analysis of large data sets
 Minimal investment
Characteristics:
 No guarantee of availability or bandwidth
 Not mission critical
 Multi-teraflop capabilities
Examples:
 SETI@HOME (United Devices)
 Entropia Grid (Entropia)
 Napster

National/International Research Grid

Drivers:
 Need to analyze very large data sets
 Requirement to be exploring topical computing technology trends
  Need to better exploit existing resources
Characteristics:
 Not yet mission critical
 Managed infrastructure
Examples:
 Data Grid (Europe)
 Distributed Terascale Facility (US)
 UK e-science grid
 DAS-2 grid (Dutch Advanced School for Computing and Imaging Supercomputer)
 Unicore (Germany)

Grid Activities,

Early Grid Activities

Earlier Grid Computing efforts were aligned with the overlapping functional areas:

 Data and Computation

Functional Data Requirements for Grid Computing:

 efficient data transfer mechanisms

 data caching and/or replication mechanisms

 data discovery mechanisms

 data encryption and integrity

 Backup/restore mechanisms

Functional Computational Requirements for Grid Computing:

 mechanisms to select resources

 Understanding of current and predicted data loads

  failure detection and failover mechanisms

Current Grid Activities:

Fig: Dynamic benefits of coordinated resource sharing in a virtual organization.

E governance,

eGovernance is a network of organizations to include government, nonprofit, and private-sector entities;

in eGovernance there are no distinct boundaries.

The model for eGovernance is a one-stop portal, such as USA.gov, where citizens have access to
a variety of information and services. An ideal portal would be one for employment where a citizen
creates a profile and is presented with employment opportunities at the federal, state, local, non-profit,
and private-sectors. Generally four basic models are available-Government to Customer (Citizen),
Government to Employees, Government to Government and Government to Business, currently websites
like monster.com over these services but more often than not users are required to reenter their
information for the specific job. However, not all stakeholders have the same desired end-state which
inhibits the possibility of a one-stop portal.

e-Government (short for electronic government, also known as e-gov, digital government, online
government, or connected government) is digital interaction between a government and citizens (G2C),
government and businesses/commerce/eCommerce (G2B), and between government agencies (G2G),
Government-to-Religious Movements/Church (G2R), Government-to-Households (G2H). This digital
interaction consists of governance, information and communication technology (ICT), business process
re-engineering (BPR), and e-citizen at all levels of government (city, state/provence, national, and
international).
Essentially, the term e-Government or also known as Digital Government, refers to 'How government
utilized IT, ICT and other telecommunication technologies, to enhance the efficiency and effectiveness in
the public sector' (Jeong, 2007).

Delivery models and activities of e-Government

The primary delivery models of e-Government can be divided into:

 Government-to-Citizen or Government-to-Consumer (G2C)

 Government-to-Business (G2B)
 industry sectors (producers)

o primary farming, mining L1

o secondary manufacturing L2
o tertiary wholesale / distribution L3
o quad retail L4
o pent professional services L5
o hex financial services (neg. instruments of transfer of value/transactions, asset
classes, commodities, future contracts).

 (consumers)
 per capita
 per household
 per community
 per social group (socio-national-political, socio-national-political-religious, socio-national-
political-theological)
 per region (socio-economic-geospatial, socio-linguistic-geospatial, socio-religious-tehological-
geospatial)

 Government-to-Government (G2G)
 Government-to-Employees (G2E)
 Government-to-Religious Movements/Church (G2R)
 Government-to-Households (G2H)

Within each of these interaction domains, four kinds of activities take place:

 Pushing information over the Internet, e.g.: regulatory services, general holidays, public hearing
schedules, issue briefs, notifications, etc.
 Two-way communications between the agency and the citizen, a business, or another government
agency. In this model, users can engage in dialogue with agencies and post problems, comments,
or requests to the agency.
 Conducting transactions, e.g.: lodging tax returns, applying for services and grants.
 Governance, e.g.: online polling, voting, and campaigning.

 Potential benefits and risks of e-Government

Risks

 There are many considerations and potential implications of implementing and designing e-
government, including disintermediation of the government and its citizens, impacts on
 economic, social, and political factors, vulnerability to cyber attacks, and disturbances to the
status quo in these areas.

Hyper-surveillance

 Increased contact between government and its citizens goes both ways. Once e-government
begins to develop and become more sophisticated, citizens will be forced to interact electronically
with the government on a larger scale. This could potentially lead to a lack of privacy for civilians
as their government obtains more and more information on them. In a worse case scenario, with
so much information being passed electronically between government and civilians, a totalitarian-
like system could develop. When the government has easy access to countless information on its
citizens, personal privacy is lost.

Cost

 Although “a prodigious amount of money has been spent” on the development and
implementation of e-government, some say it has yielded only a mediocre product. The outcomes
and effects of trial Internet-based governments are often difficult to gauge or unsatisfactory.
According to Gartner, Worldwide IT spending is estimated to total $3.6 trillion in 2011 which is
5.1% increase from the year 2010($3.4 trillion).

Inaccessibility

 An e-government site that provides web access and support often does not offer the “potential to
reach many users including those who live in remote areas, are homebound, have low literacy
levels, exist on poverty line incomes.”

False sense of transparency and accountability

 Opponents of e-government argue that online governmental transparency is dubious because it is

maintained by the governments themselves. Information can be added or removed from the public
eye. To this day, very few organizations monitor and provide accountability for these
modifications. Those that do so, like the United States‟ OMBWatch and Government
Accountability Project, are often nonprofit volunteers. Even the governments themselves do not
always keep track of the information they insert and delete.

Benefits

 It is convenient and cost-effective for businesses, and the public benefits by getting easy access to
the most current information available without having to spend time, energy and money to get it.
 E-government helps simplify processes and makes access to government information more easily
accessible for public sector agencies and citizens. For example, the Indiana Bureau of Motor
Vehicles simplified the process of certifying driver records to be admitted in county court
proceedings. Indiana became the first state to allow government records to be digitally signed,
legally certified and delivered electronically by using Electronic Postmark technology. In addition
to its simplicity, e-democracy services can reduce costs. Alabama Department of Conservation &
Natural Resources, Wal-Mart and NIC developed an online hunting and fishing license service
utilizing an existing computer to automate the licensing process. More than 140,000 licenses were
purchased at Wal-Mart stores during the first hunting season and the agency estimates it will save
$200,000 annually from service.
 The anticipated benefits of e-government include efficiency, improved services, better
accessibility of public services, and more transparency and accountability.

Democratization

 One goal of e-government will be greater citizen participation. Through the internet, people from
all over the country can interact with politicians or public servants and make their voices heard.
Blogging and interactive surveys will allow politicians or public servants to see the views of the
people they represent on any given issue. Chat rooms can place citizens in real-time contact with
elected officials, their offices or provide them with the means to replace them by interacting
directly with public servants, allowing voters to have a direct impact and influence in their
government. These technologies can create a more transparent government, allowing voters to
immediately see how and why their representation in the capital is voting the way they are. This
helps voters better decide who to vote for in the future or how to help the public servants become
more productive. A government could theoretically move more towards a true democracy with
the proper application of e-government. Government transparency will give insight to the public
on how decisions are made and hold elected officials or public servants accountable for their
actions. The public could become a direct and prominent influence in government legislature to
some degree.

Environmental bonuses

 Proponents of e-government argue that online government services would lessen the need for
hard copy forms.Due to recent pressures from environmentalist groups, the media, and the public,
some governments and organizations have turned to the Internet to reduce this paper use. The
United States government utilizes the website http://www.forms.gov to provide “internal
government forms for federal employees” and thus “produce significant savings in paper.

Speed, efficiency, and convenience

 E-government allows citizens to interact with computers to achieve objectives at any time and
any location, and eliminates the necessity for physical travel to government agents sitting behind
desks and windows. Improved accounting and record keeping can be noted through
computerization, and information and forms can be easily accessed, equaling quicker processing
time. On the administrative side, access to help find or retrieve files and linked information can
now be stored in databases versus hardcopies stored in various locations. Individuals with
disabilities or conditions no longer have to be mobile to be active in government and can be in the
comfort of their own homes.

Public approval

 Recent trials of e-government have been met with acceptance and eagerness from the public.
Citizens participate in online discussions of political issues with increasing frequency, and young
people, who traditionally display minimal interest in government affairs, are drawn to e-voting
procedures.
 Although internet-based governmental programs have been criticized for lack of reliable privacy
policies, studies have shown that people value prosecution of offenders over personal
confidentiality. Ninety percent of United States adults approve of Internet tracking systems of
criminals, and fifty-seven percent are willing to forgo some of their personal internet privacy if it
leads to the prosecution of criminals or terrorists.
 Technology-specific e-Government

 There are also some technology-specific sub-categories of e-government, such as m-government

(mobile government), u-government (ubiquitous government), and g-government (GIS/GPS
applications for e-government.

E-government portals and platforms The primary delivery models of e-Government are
classified depending on who benefits. In the development of public sector or private sector portals
and platforms, a system is created that benefits all constituents. Citizens needing to renew their
vehicle registration have a convenient way to accomplish it while already engaged in meeting the
regulatory inspection requirement. On behalf of a government partner, business provides what has
traditionally, and solely, managed by government and can use this service to generate profit or
attract new customers. Government agencies are relieved of the cost and complexity of having to
process the transactions.

 To develop these public sector portals or platforms, governments have the choice to internally
develop and manage, outsource, or sign a self-funding contract. The self-funding model creates
portals that pay for themselves through convenience fees for certain e-government transactions,
known as self-funding portals.
 Social networking is an emerging area for e-democracy. The social networking entry point is
within the citizens‟ environment and the engagement is on the citizens‟ terms. Proponents of e-
government perceive government use of social networks as a medium to help government act
more like the public it serves. Examples can be found at almost every state government portal
through Facebook, Twitter, and YouTube widgets.
 Government and its agents also have the opportunity to follow citizens to monitor satisfaction
with services they receive. Through ListServs, RSS feeds, mobile messaging, micro-blogging
services and blogs, government and its agencies can share information to citizens who share
common interests and concerns. Government is also beginning to Twitter. In the state of Rhode
Island, Treasurer Frank T. Caprio is offering daily tweets of the state‟s cash flow. Interested
people can sign up at here. For a full list of state agencies with Twitter feeds, visit Real Life. Live
document. For more information, visit transparent-gov.

Grid Applications
Distributed Supercomputing

• Idea: aggregate computational resources to tackle problems that cannot be solved by a single
system

• Examples: climate modeling, computational chemistry

• Challenges include:

– Scheduling scarce and expensive resources

– Scalability of protocols and algorithms

– Maintaining high levels of performance across heterogeneous systems

High-throughput computing

• Schedule large numbers of independent tasks

 • Goal: exploit unused CPU cycles (e.g., from idle workstations)

• Unlike distributed computing, tasks loosely coupled

• Examples: parameter studies, cryptographic problems

On-demand computing

• Use Grid capabilities to meet short-term requirements for resources that cannot conveniently be
located locally

• Unlike distributed computing, driven by cost-performance concerns rather than absolute

performance

• Dispatch expensive or specialized computations to remote servers

Data-intensive computing

• Synthesize data in geographically distributed repositories

• Synthesis may be computationally and communication intensive

• Examples:

– High energy physics generate terabytes of distributed data, need complex queries to
detect “interesting” events

– Distributed analysis of Sloan Digital Sky Survey data

Collaborative computing

• Enable shared use of data archives and simulations

• Examples:

– Collaborative exploration of large geophysical data sets

• Challenges:

– Real-time demands of interactive applications

– Rich variety of interactions

Grid Computing Organizations and their roles,

Grid Architecture
• Identifies system components, specifies purpose and function, indicates interaction

– Effective VO operation require sharing relationships

• Interoperability is the core issue

– In networked environment it means common protocols

– Assure general purpose mechanism for interaction

• Grid Arch is a protocol Architecture

– Negotiation, establish, manage sharing relationship

• Standard protocol ~Standard services

– Service defined by protocol it speak and behaviour it impl.

• Grid Architecture (Layered)

We define Grid architecture in terms of a layered collection of protocols.

Fabric Layer: interface to local resources

 Fabric layer defines the resources that can be shared E.g. computational resources, data
storage, networks, catalogs

 A resource can be a Physical resource or a logical resource

 A logical resource can be implemented by their own internal protocol

 basic capabilities associated with the integration of resources:

 provide an inquiry

 provide appropriate resource management

Connectivity Layer: Manages communications

 defines core communication and authentication protocols

Authentication solution for Vo’s:

 single sign on: any multiple entities in the grid fabric to be authenticated once

 Delegation: ability to access a resource under the current user permissions

 Integration with local resource specific security solutions

 User-based trust relationships

Resource Layer: sharing of a single Resource

 Controls the secure negotiation, initiation, monitoring, sharing of operations across individual
layer.

Two primary classes of resource layer protocols

Information Protocols

Management Protocols

 negotiating access to a shared resource

 performing operation on a resource & monitoring the status of operation

Collective layer: coordinating multiple resources

 responsible for global resource management common collective services in a Grid Computing
system

 Discovery services

 Co allocation ,scheduling Services

 Community accounting and Payment Services

Application Layer: User-Defined Grid Applications

 user applications constructed by utilizing the services defined at each lower level

 each layer in the Grid Architecture provides a set of API’s and SDK’s for the higher layers of
integration

Grid Architecture (Service-oriented

Grid Architected Services

1. Provisioning & deploying components, collecting and exchanging data

 2. Supports basic method for grid services to communicate with each other

3. General framework for creation, negotiation, management of policies

4. Support, integrate and unify diff security models to enable systems to interoperate securely.

Grid computing Applications.

There are several grid computing systems, though most of them only fit part of the definition of a true
grid computing system. Academic and research organization projects account for many of the systems
currently in operation. These systems take advantage of unused computer processing power. The most
accurate term for such a network is a shared computing system.

The Search for Extraterrestrial Intelligence (SETI) project is one of the earliest grid computing systems to
gain popular attention. The mission of the SETI project is to analyze data gathered by radio telescopes in
search of evidence for intelligent alien communications. There's far too much information for a single
computer to analyze effectively. The SETI project created a program called SETI@home, which networks
computers together to form a virtual supercomputer instead.

A similar program is the Folding@home project administered by the Pande Group, a nonprofit institution
in Stanford University's chemistry department. The Pande Group is studying proteins. The research
includes the way proteins take certain shapes, called folds, and how that relates to what proteins do.
Scientists believe that protein "misfolding" could be the cause of diseases like Parkinson's or Alzheimer's.
It's possible that by studying proteins, the Pande Group may discover new ways to treat or even cure these
diseases.

Protein to Protein
The Genome Comparison Project, a research project comparing the protein sequences of more than 3,500
organisms against each other, began on Dec. 20, 2006. By July 21, 2007, the project achieved all its goals
by using a grid computing system.

There are dozens of similar active grid computing projects. Many of these projects aren't persistent, which
means that once the respective project's goals are met, the system will dissolve. In some cases, a new,
related project could take the place of the completed one.

While each of these projects has its own unique features, in general, the process of participation is the
same. A user interested in participating downloads an application from the respective project's Web site.
After installation, the application contacts the respective project's control node. The control node sends a
chunk of data to the user's computer for analysis. The software analyzes the data, powered by untapped
CPU resources. The project's software has a very low resource priority -- if the user needs to activate a
program that requires a lot of processing power, the project software shuts down temporarily. Once CPU
usage returns to normal, the software begins analyzing data again.

Eventually, the user's computer will complete the requested data analysis. At that time, the project
software sends the data back to the control node, which relays it to the proper database. Then the control
node sends a new chunk of data to the user's computer, and the cycle repeats itself. If the project attracts
enough users, it can complete ambitious goals in a relatively short time span.

As grid computing systems' sophistication increases, we'll see more organizations and corporations create
versatile networks. There may even come a day when corporations internetwork with other companies. In
that environment, computational problems that seem impossible now may be reduced to a project that
lasts a few hours. We'll have to wait and see.

Cluster Computing (Definition of a cluster)

A cluster is a type of parallel or distributed processing system, which consists of a collection of

interconnected stand-alone computers cooperatively working together as a single, integrated computing
resource.
A typical cluster:
 Network: Faster, closer connection than a typical network (LAN)
 Low latency communication protocols
 Looser connection than SMP

What’s so different about Clusters?

 Commodity Parts?
 Communications Packaging?
 Incremental Scalability?
 Independent Failure?
 Intelligent Network Interfaces?
 Complete System on every node
 virtual memory
 scheduler
 files
 Nodes can be used individually or combined...

Major issues in cluster design

 Size Scalability (physical & application)

 Enhanced Availability (failure management)
 Single System Image (look-and-feel of one system)
 Fast Communication (networks & protocols)
 Load Balancing (CPU, Net, Memory, Disk)
 Security and Encryption (clusters of clusters)
 Distributed Environment (Social issues)
 Manageability (admin. And control)
 Programmability (simple API if required)
 Applicability (cluster-aware and non-aware app.)

Cluster Middleware
 Resides Between OS and Applications and offers in infrastructure for supporting:
o Single System Image (SSI)
o System Availability (SA)
 SSI makes collection appear as single machine (globalised view of system resources). telnet
cluster.myinstitute.edu
 SA - Check pointing and process migration
 OS / Gluing Layers
o Solaris MC, UnixWare, MOSIX
o Beowulf “Distributed PID”
 Runtime Systems
 o Runtime systems (software DSM, PFS, etc.)
o Resource management and scheduling (RMS):
 CODINE, CONDOR, LSF, PBS, NQS, etc.

Cluster Computer Architecture

Cluster Programming Environment

 Shared Memory Based

o DSM
o Threads/OpenMP (enabled for clusters)
o Java threads (HKU JESSICA, IBM cJVM)
 Message Passing Based
o PVM (PVM)
o MPI (MPI)
 Parametric Computations
o Nimrod/Clustor
 Automatic Parallelising Compilers
 Parallel Libraries & Computational Kernels (NetSolve)
 Threads (PCs, SMPs, NOW..)
o POSIX Threads
o Java Threads
 MPI
o http://www-unix.mcs.anl.gov/mpi/mpich/
 PVM
o http://www.epm.ornl.gov/pvm/
 Software DSMs (Shmem)

MPI (Message Passing Interface)

 A standard message passing interface.

o MPI 1.0 - May 1994 (started in 1992)
 o C and Fortran bindings (now Java)
 Portable (once coded, it can run on virtually all HPC platforms including clusters!
 Performance (by exploiting native hardware features)
 Functionality (over 115 functions in MPI 1.0)
o Environment management, point-to-point & collective communications, process group,
communication world, derived data types, and virtual topology routines.
 Availability - a variety of implementations available, both vendor and public domain.

Cluster Programming Tools.

Nimrod - A tool for parametric modeling on clusters:

Job processing with Nimrod

Ad Hoc Mobile Network Simulation

Ad Hoc Mobile Network Simulation (C. Koop, Monash): Network performance under different
microware frequencies and different Weather conditions -- Used Nimrod

PARMON: A Cluster Monitoring Tool

Resource Utilization For PARMON

Development Tools
 Compilers
o C/C++/Java/
 Debuggers
 Performance Analysis Tools
 Visualization Tools