GRID

COMPUTING
CONTENTS:
 Introduction
 What is Grid Computing
 Characteristics of Grid
 Components of Grid
 Advantages
 Challenges
 Grid development option
 Motivations for Grid Computing
 How Grid Works
 Grid Protocol
 Strategies for Grid Application
Enablement
 Area of Application
 Summery
 References

1
 Introduction
 What is a distributed environment?
“A non-centralized network consisting of numerous
computers that can communicate with one another and that
appear to users as parts of a single, large, accessible
"storehouse" of shared hardware, software, and data”

2
 Introduction - Single Computer
•The Operating System enables
easy use of
–Input/Output devices Application
–Processor Software
–Disks
–Display
Operating
–Instruments
System

Disks, Processor,
Memory, …

3
Introduction - Local Area Network
User just perceives “shared
resources”, with no regard to
location in the organisation Application Software
LAN resources act like a single
virtual computer
Middleware (LAN O/S) presents
Middleware for sharing
that image computers, servers, printers,
…

Operating System on
each computer

Resources connected by a LAN

4
 Introduction - Grid
•Grid middleware creates the Application Software
image of the Grid being a
single virtual computer
(Ideally) Interface between app. and grid
Issues
•Heterogeneity – hardware,
software, culture Grid Middleware on each
•Scalability resource
•Reliability – tolerate
permanent partial failure Operating System on each
•Viable computing model - resource
batch processing
•Access control
–Authentication Resources connected by internet
–Authorisation
–Single sign on
5
WHAT IS GRID COMPUTING ?
 It is the distributed computing taken to the next
evolutionary level. The goal is to create the illusion of a
simple yet , large and powerful self managing virtual
computer out of a large connected heterogeneous system
sharing resources.

What is not a Grid?

 A bunch of PC’s on a network (It’s a lot more than that)
 A cluster, a network attached storage device, a network etc. (each is
an important component of grid, but by itself each does not
constitute a grid)

6
WHAT IS GRID COMPUTING ?

 Distributed Computing
 Loosely Coupled
 Heterogeneous
 Single Administrator
 Cluster Computing
 Tightly Coupled
 Homogenous
 Cooperative Working
 Grid Computing
 Large Scale
 Cross Organization
 Geographical Distribution
 Distributed Management
7
Characteristics of Grid
 Co-ordinated resource sharing
 No centralised point of control
 Different administrative domains.

 Standard, open, general-purpose protocols and interfaces

 NOT specific to an application
 support multiple VO’s

 Delivering non-trivial qualities of service

 Co-ordinated to deliver combined services,
greater than sum of the individual components

8
Components of Grid
• Resources
– networking, computers, storage, data, instruments, …
• Grid Middleware
– the “operating system of the grid”
• Virtual Organization management
– Procedures for gaining access to resources

9
Advantages :
 Virtualized Sharing of Resources
 Secure reliable access to Resources
 Autonomic management of Resources
 Proper Utilization of Resources
 Fast Computation (nearly achievable to Super Computing by
Parallel Computing)
 Virtually a very Large Capacity
 Economic
 No need of nodes homogeneity

10
Challenges
 Non-determinism
 Infrastructure dependencies
 Distributed and partial failures
 Time-outs
 Dynamic nature of the structure
 Multiple heterogeneous platforms
 Security
 The ‘Human Factor’

11
Grid development option
 A function of Business need, Technology and
Organizational flexibility

12
Grid development option
 A function of Business need, Technology and
Organizational flexibility

13
Grid development option
 A function of Business need, Technology and
Organizational flexibility

14
Motivations for Grid Computing

15
Motivations for Grid Computing

 Increase Capacity
Exploits distributed recourses to provide capacity for
high demand applications

16
Motivations for Grid Computing

 Increase Capacity
Exploits distributed resources to produce capacity for
high demand applications
 Improve Efficiency /Reduce Cost

17
Motivations for Grid Computing

 Provide Reliability / Availability

18
Motivations for Grid Computing

 Reduce “Time to Results”

19
Motivations for Grid Computing
 Provide Reliability / Availability
 Use Distributed processes
 Monitor Work Process
 Restart failed jobs

 Support Heterogeneous system

20
Motivations for Grid Computing
 Enable collaborations

21
How Grid Works?
1. Resource Sharing
2. Resource Utilization
3. Secure Access
4. The Death of Distance

1. Resource Sharing
 CPU Consideration
 Data Consideration

22
CPU – Makes Execution Parallel
Rearranging Computations to execute in Parallel on Grid

23
CPU – Programming Code Control Graph

24
How Grid Works?
2. Resource Utilization

25
How Grid Works?
3. Secure Access
 Authentication
 Authorization
 Data integrity
 Data confidentiality
 Key management
 encryption

CA - Certification Authority
The role of the CA is manage the certificate life
cycle: create, store, renew.

26
 CA - Certification Authority
 It depends on person whether to participate in Grid

Virtual Community C

Person E
Person B File server F1
(Researcher)
Compute Server C1' (Administrator) (disk A)
Person A
Person D
(Principal Investigator)
(Researcher)

Person B
Person E
(Staff) Person D File server F1 (Faculty)
Compute Server C2 Compute Server C1 (Staff) (disks A and B)
Person A Person F
(Faculty) (Faculty)
Person C
(Student) Compute Server C3
Organization A Organization B

27
CA - Certification Authority
1. Positively identify entities
requesting certificates
2. Issuing, removing, and archiving
certificates
3. Protecting the Certificate Authority
server
4. Maintaining a namespace of unique
names for certificate owners
5.Serve signed certificates to those
needing to authenticate entities

Digital Signature
28
How Grid Works? Grid Security
Site A
Site B

Grid Infrastructure
R R

Grid
Site Security
Security
Site C
29
 How Grid Works?

4. The Death of Distance

development of networking technology
 Internet economy
 optical fibers in telecommunications systems
 performance of wide area networks

has been doubling every nine months

30
 Grid Protocols
1. Fabric
2. Connectivity
3. Resource
4. Collective
5. Application

31
Grid Protocol v/s Internet Protocol

32
Grid Protocol - Fabric

33
Grid Protocol - Connectivity

34
Grid Protocol - Resource

35
Grid Protocol - Collective

36
Grid Protocol – Application Layer

37
Six Strategies for Grid Application Enablement

1. Batch Anywhere
2. Independent
Concurrent Batch
3. Parallel Batch
4. Service
5. Parallel Services
6. Tightly Coupled
parallel Program

38
Six Strategies for Grid Application Enablement
1. Batch Anywhere
Only Grid decides which node to use for the job.
The machine submitting the job might not be a node in the grid.
2. Independent Concurrent Batch
Multiple independent instances of the same application run concurrently and
independently without interface.
Databases and other resources don’t have deadlocks.
3. Parallel Batch
Take each user’s batch work, subdivides it, disperse it out to multiple nodes, collect it,
and then aggregate the result.
4. Service
Focuses on the transition from a batch to service oriented architecture.
It is not assumed that each client subdivides it’s work and spreads it over multiple service
instances.
5. Parallel Services
Service with subdivided work model of parallel batch.
Provides multiple service instance
Permits these instances to be invoked in parallel on the client’s behalf.
6. Tightly Coupled Parallel Programs
Provides intense communications and synchronization between client, server and
services.
39
 Area
of
Application

40
Area of Implementation

41
Grid Computing – Industry Applications
Unique by Industry with Common Characteristics

Primary Focus
42
Grid Project in China (river Vah)

43
Data Intensive Applications

44
Data Intensive Application
Overlapping Data Transfer with Capture and Computing

45
Many Grid development efforts — all over
the world
•UK – OGSA-DAI, RealityGrid,
•NASA Information Power Grid GeoDise, Comb-e-Chem,
•DOE Science Grid DiscoveryNet, DAME, AstroGrid,
•NSF National Virtual Observatory GridPP, MyGrid, GOLD, eDiamond,
•NSF GriPhyN Integrative Biology, …
•DOE Particle Physics Data Grid •Netherlands – VLAM, PolderGrid
•NSF TeraGrid •Germany – UNICORE, Grid proposal
•DOE ASCI Grid •France – Grid funding approved
•DOE Earth Systems Grid •Italy – INFN Grid
•DataGrid (CERN, ...) •Eire – Grid proposals
•DARPA CoABS Grid
•EuroGrid (Unicore)
•NEESGrid •Switzerland - Network/Grid proposal
•DataTag (CERN,…)
•DOH BIRN •Hungary – DemoGrid, Grid proposal
•Astrophysical Virtual
•NSF iVDGL •Norway, Sweden - NorduGrid
Observatory
•GRIP (Globus/Unicore)
•GRIA (Industrial applications)
•GridLab (Cactus Toolkit)
•CrossGrid (Infrastructure Components)
•EGSO (Solar Physics)

46
Can Your Application Benefit from
“Grid Computing”

47
CONCLUSION

The grid will bring about a revolution in the way we use

our resources. Twenty years and so, the grid will no
longer be a domain of only researchers but a tangible
entity that shall be instinct to the way we live. Uncouthly,
grid will be the next generation Internet.

48
 References
 “The Anatomy of Grid” by Foster and Kesselman
 http://www.globus.org
 http://www.ibm.com/redbooks/
 http://www.gridtoday.com
 http://www.redbooks.ibm.com
 http://www.google.com

49
Thank You

Questions?