1. UNIT 1
INTRODUCTION
ABOUT
GRID COMPUTING

2. DEFINITION
 Grid computing is the federation of computer
resources from multiple administrative domains to
reach a common goal.
 “computataional of grid is a hardware and
software infrastructure that provides
independent pervasive and inexpensive access to
high end computational capabilities”.

3.  What is Grid Computing?
 Who Needs It?
 An Illustrative Example
 Grid Users
 Current Grids

4. What is Grid Computing?
 Computational Grids
 Homogeneous (e.g., Clusters)
 Heterogeneous (e.g., with one-of-a-kind instruments)
 Cousins of Grid Computing
 Methods of Grid Computing

5. Computational Grids
 Each user A network of geographically distributed
resources including computers, peripherals, switches,
instruments, and data.
 should have a single login account to access all
resources.
 Resources may be owned by diverse organizations.

6. Computational Grids
 Grids are typically managed by grid ware.
 Grid ware can be viewed as a special type of
middleware that enable sharing and manage grid
components based on user requirements and resource
attributes (e.g., capacity, performance, availability…)

7. Cousins of Grid Computing
 Parallel Computing
 Distributed Computing
 Peer-to-Peer Computing
 Many others: Cluster Computing, Network
Computing, Client/Server Computing, Internet
Computing, etc...

8. Distributed Computing
 People often ask: Is Grid Computing a fancy new name
for the concept of distributed computing?
 In general, the answer is “no.” Distributed Computing
is most often concerned with distributing the load of a
program across two or more processes.

9. PEER2PEER Computing
 Sharing of computer resources and services by direct
exchange between systems.
 Computers can act as clients or servers depending on
what role is most efficient for the network.

10. Methods of Grid Computing
 Distributed Supercomputing
 High-Throughput Computing
 On-Demand Computing
 Data-Intensive Computing
 Collaborative Computing
 Logistical Networking

11. Distributed Supercomputing
 Combining multiple high-capacity resources on a
computational grid into a single, virtual distributed
supercomputer.
 Tackle problems that cannot be solved on a single
system.

12. High-Throughput Computing
 Uses the grid to schedule large numbers of loosely
coupled or independent tasks, with the goal of putting
unused processor cycles to work.

13. On-Demand Computing
 Uses grid capabilities to meet short-term requirements
for resources that are not locally accessible.
 Models real-time computing demands.

14. Collaborative Computing
 Concerned primarily with enabling and enhancing
human-to-human interactions.
 Applications are often structured in terms of a virtual
shared space.

15. Logistical Networking
 Global scheduling and optimization of data
movement.
 Contrasts with traditional networking, which does not
explicitly model storage resources in the network.
 Called "logistical" because of the analogy it bears with
the systems of warehouses, depots, and distribution
channels.

16. Who Needs Grid Computing?
 A chemist may utilize hundreds of processors to screen
thousands of compounds per hour.
 Teams of engineers worldwide pool resources to
analyze terabytes of structural data.
 Meteorologists seek to visualize and analyze petabytes
of climate data with enormous computational
demands.

17. An Illustrative Example
 Tiffany Moisan, a NASA research scientist, collected
microbiological samples in the tidewaters around
Wallops Island, Virginia.
 She needed the high-performance microscope located
at the National Center for Microscopy and Imaging
Research (NCMIR), University of California, San
Diego.

18.  She sent the samples to San Diego and used NPACI’s
Telescience Grid and NASA’s Information Power Grid
(IPG) to view and control the output of the
microscope from her desk on Wallops Island. Thus, in
addition to viewing the samples, she could move the
platform holding them and make adjustments to the
microscope.

19. CONT…..
 The microscope produced a huge dataset of images.
 This dataset was stored using a storage resource broker
on NASA’s IPG.
 Moisan was able to run algorithms on this very dataset
while watching the results in real time.

20. Grid Users
 Grid developers
 Tool developers
 Application developers
 End Users
 System Administrators

21. Grid Developers
 Very small group.
 Implementers of a grid “protocol” who provides the
basic services required to construct a grid.

22. Tool Developers
 Implement the programming models used by
application developers.
 Implement basic services similar to conventional
computing services:
 User authentication/authorization
 Process management
 Data access and communication

23. Application Developers
 Construct grid-enabled applications for end-users who
should be able to use these applications without
concern for the underlying grid.
 Provide programming models that are appropriate for
grid environments and services that programmers can
rely on when developing (higher-level) applications.

24. System Administrators
 Balance local and global concerns.
 Manage grid components and infrastructure.
 Some tasks still not well delineated due to the high
degree of sharing required.

25. ADVANTAGE
 Can solve larger, more complex problems in a shorter
time
 Easier to collaborate with other organizations
 Make better use of existing hardware

26. DISADVANTAGE
 Grid software and standards are still evolving
 Learning curve to get started
 Non-interactive job submission

27. The grid- Present, Past, Future
 Number of derivatives in grid computing. Share resources and different
architecture.
1. Compute Grids
2. Data Grids
3. Science Grids
4. Access Grids
5. Knowledge Grids
6. Cluster Grids
7. Terra Grids
8. Commodity Grids

28. 1. Compute Grids vendors:
 Grid Gain - Professional Open Source
 JPPF - Open Source
2. Data Grids vendors:
 Oracle Coherence- Commercial
 GemStone- Commercial
 GigaSpaces – Commercial
 JBossCache - Professional Open Source
 EhCache- Open Source

29. Data
Functional data requirements for Grid Computing applications are:
•To integrate multiple distributed, heterogeneous, and independently
managed data sources.
•Data transfer mechanisms
•Data caching and/or replication mechanisms to minimize network
traffic.
•Data discovery mechanisms
•Data encryption and integrity
•Backup/restore mechanisms and policies

30. Computation
Functional computational requirements for grid applications are:
•Independent management of computing resources.
•Intelligently and transparently select computing resources.
•Availability, dynamic resource configuration,
•Failure detection and failover mechanisms.
•Secure resource management, access, and integrity.

31. Computational and Data Grids
Data requirements in the early grid solutions:
 Discover data.
 Databases, utilizing meta-data and other attributes of the data.
 The provisioning of computing facilities for high-speed data movement.
 Flexible data access and data filtering capabilities.

32. Current Grid Activities
 Sharing of resources can be different in present grid.
1. Computing power
2. Data
3. Hardware
4. Software
5. Network services

33. Dynamic benefits of coordinated resource sharing in a virtual
organization.

34. The usage patterns found within each of the virtual organizations.
 A virtual organization for weather prediction. For example, this virtual
organization requires resources such as weather prediction software
applications to perform the mandatory environmental simulations associated
with predicting weather.
 A virtual organization for financial modeling. For example, this virtual
organization requires resources such as software modeling tools for
performing a multitude of financial analytics, virtualized blades to run the
above software, and access to data storage facilities for storing and
accessing data.

35. Number of requirements for Grid Computing architecture
Three categories
1. Resource categories
2. Virtual organization
3. Users/Applications

36. Providing facilities for the following scenarios:
 Dynamic discovery of computing resources, based on their capabilities and
functions.
 Immediate allocation and provisioning of these resources, based on their
availability and the user demands or requirements.
 The management of these resources to meet the required service level agreements
(SLAs).
 The provisioning of multiple autonomic features for the resources, such as self-
diagnosis, self-healing, self-configuring, and self-management.
 The provisioning of secure access methods to the resources, and bindings with the
local security mechanisms based upon the autonomic control policies.

37. Virtual organization must be capable of providing facilities for:
 Virtual task forces, or groups, to solve specific problems associated with the virtual
organization.
 Dynamic collection of resources from heterogeneous providers based upon users' needs and
the sophistication levels of the problems.
 Dynamic identification and automatic problem resolution of a wide variety of troubles, with
automation of event correlation, linking the specific problems to the required resource and
service providers.
 The dynamic provisioning and management capabilities of the resources required meeting the
SLAs.
 The formation of a secured federation (or governance model) and common management model
for all of the resources respective to the virtual organization.
 The secure delegation of user credentials and identity mapping to the local domain(s).
 The management of resources, including utilization and allocation, to meet a budget and other
economic criteria.

38. Users/applications typically found in Grid Computing environments must
be able to perform the following characteristics:
 The clear and unambiguous identification of the problem
 The identification and mapping of the resources
 The ability to sustain the required levels of QoS, while adhering to the
anticipated and necessary SLAs.
 The capability to collect feedback regarding resource status, including
updates for the environment's respective applications.

39. GRID APPLICATIONS
 Grid computing applications can be aligned to have a
common needs
 Application partitioning that involves breaking the
problem into discrete pieces
 Discovery and scheduling of tasks and workflow
 Data communication distributing the problem data
where and when it is required
 Provisioning and Distributing application codes to
specific system nodes

40. Contd…
 Results management assisting in the decision process of
the environment
 Autonomic features such as self-configuration, self-
optimization , self-recovery and self management
Let us explore some of these Grid application and their
usage pattern

41. Schedulers
 Responsible for management of jobs such as allocating
the resource needed for any specific job , parallel
execution of tasks, data management and service level
management
 Schedulers form the hierarchical structures , with
meta schedulers as the root and other schedulers as
the leaves
 Meta schedulers or cluster schedulers for parallel
execution

42. Scheduler embodies local , meta-
level and cluster schedulers
LOCAL
Diagram : SCHEDUL
ER
JOB
META JOB META
SCHEDUL SCHEDULE
USER ER R
JOB
CLUSTER
SCHEDULE
R

43. Contd…
 Jobs submitted to the grid computing applications are
evaluated based on the ir service level requirement
 It involves the complex work flow management and
data movement activities to occur on a regular basis

44. Contd…
 There are schedulers that must provide capabilities for
areas such as
 Advanced resource reservation
 SLA validation and enforcement
 Monitoring job execution and status
 Rescheduling and corrective action

45. Resource Broker
 It providing the paring service between the service
requester and service provider
 This paring enables the selection of best available
resource
 It will collect the information from the respective
resources and uses this information for paring purpose

46. Resource Broker
Diagram:
RESOURCE BROKER
SELECT RESOURCE INFORMATION
RESOURCE
1
USER
SELECT SCHEDULER
EXECUTE TASK INFORMATION
SCHEDULER RESOURCE
2
EXECUTE TASK

47. Contd…
 Resource broker provides the feed back to the users on
the available resource
 Resource broker may select the suitable scheduler for
the execution of tasks

48. Contd…
 The paring process in a resource broker involves
allocation and support functions such as
 Allocate appropriate resource for task execution
 Support users deadline and budget constraints for
scheduling optimizations

49. Load balancing
 Load balancing features must always be integrated
into any system in order to avoid processing delays and
over commitment of resource
 Load balancing may be built in connection with
resource broker and schedulers
 The level of load balancing involves partitioning of
jobs ,identifying the resource and queueing of the jobs

50. Contd…
 Used to running the parallel jobs in parallel
 It support failure detection and management
 It redistribute the jobs to other resource if needed

51. Grid portals
 Grid portals are like the web portals
 grid portals provide the uniform access to the grid resources
 Grid portals provide
1. Resource access
2. Scheduling capabilities
3. monitoring statusinformation

52. Contd…
 some examples of grid portals capabilities are
1. Querying database
2. File transfer facilities
3. Manage job through job status feed back
4. Security management
5. Provide personalized solution

53. Integrated solutions
 It is the combination of existing advanced middleware
and application functionalities combined to provide
high performance results across the grid computing
environment
 It support more complex utilization of grid such as the
coordinated and optimized resource sharing,
enhanced security management, cost optimization ,etc
 It achieves the level of flexibility utilizing
infrastructure provided by application and
middleware frame works

54. GRID INFRASTRUCTURE
 GRID infrastructure forms the core foundation for
the successful grid applications
Grid computing infrastructure component must
address several potentially complicated areas in
many stages of implementation , they are
1. Security
2. Resource management
3. Information services
4. Data management

55. Diagram:
GRID APPLICATIONS
G G
R R
I I
D RES INF D
DAT M
M OUR OR
A I
I CE MAT
D SECU ION D
MA D
D RITY MA NAG
L NAG SER L
EME E
E EME VICE
NT W
W NT S
A A
R R
E E
HOSTING ENVIRONMENT

56. Security
 Heterogeneous nature of resources – complicated
polices - complex security schemes
 These computing resources are hosted in differing
security domains and Heterogeneous
platforms
 Security requirements – data integrity , confidentiality
and information privacy

57. Contd…
 The grid computing data exchange must be protected
using secure communication channels including
SSL/TLS
 Secure message exchange mechanisms such as WS-
Security
 Security infrastructure – grid security infrastructure
(GSI)

58. Resource management
 Resource management scenarios are
1. Resource discovery
2. Resource monitoring
3. Fault isolation
4. Resource provisioning
5. Resource monitoring
6. Autonomic capabilities
7. Service level management activities

59. Contd…
 Resource management area is the selection of correct
resource from grid resource pool
 Fully based on SLA

60. Information services
 Providing valuable information respective to grid
computing infrastructure resources
 Service are entirely depends on resource availability,
capacity and utilization
 The information is valuable and mandatory feedback
respective to resource managers
 Grid solutions are constructed to reflect portals
 Metrics are helpful in SLA

61. Data management
 Data forms the single most important asset in a grid
computing system
 Data maybe – input to the resource – output from the
resource
 Data must be near to the computation where it is used
 Data storage mechanisms – Storage Area Network
(SAN) ,network file system, virtual database

62. contd…
 Developers and providers must factor into decision
are related to selecting the most appropriate data
management mechanism for grid computing
infrastructure
This includes size of –
1. data repositories
2. resource geographical distribution
3. security requirements
4. schemes for replication
5. caching facilities