Grid computing

Profesor:Petrit Shala Presented by: Fatos Rexhepi

May 2012

HISTORY
The term grid computing originated in the early 1990s for making computer power as easy to access as an electric power grid The ideas of the grid were brought together by Ian Foster, Carl Kesselman. Initially Globus Toolkit was designed incoorporating storage management, security provisioning, data movement, monitoring e.t.c. In 2007 the term cloud computing came into popularity, which is conceptually similar to the canonical Foster definition of grid computing

DEFINATION
Grid computing is the application of several computers to a single problem at the same time It allows flexible resource sharing among geographically distributed computing resources in multiple administrative domains It is basically used for Grid applications rich in graphics and multimedia.

Controlled shell and controlled desktop mechanisms are used to restrict the user to execute only authorized commands and applications

INTRODUCTION
Grid computing depends on software to divide and apportion pieces of a program among several computers It can also be thought of as form of networkdistributed parallel processing. It can be small confined to a network of computer workstations or it can be a large, public collaboration across many companies or networks.

DESIGN CONSIDERATION
Distributed grids can be formed from computing resources belonging to multiple indivisuals Computers which are actually Performing the calculations might not be entirely trustworthy. Measures were introduced to prevent participants from producing misleading results, and from using the system as an attack vector. Measures include assigning work randomly to different nodes and checking that at least two different nodes report the same answer for a given work unit.

DESIGN CONSIDERATION
There is no way to guarantee that nodes will not drop out of the network at random times. Uing different platforms with many languages, leads to tradeoff between investment in software development and the number of platforms that can be supported Cross platform languages can reduce the need to make this tradeoff, though potentially at the expense of high performance on any given node

MARKET SEGMENTATION
The segmentation of the Grid computing market, two perspectives need to be considered: the provider side and the user side:

The Provider Side The overall Grid market comprises several specific markets. Like Grid middleware market, The market for Grid-enabled applications, The utility computing market, and the software-as-aService (SaaS) market.

MARKET SEGMENTATION
The Provider Side Grid middleware is installed and integrated into the existing infrastructure of the involved companies Major Grid middlewares are Globus Toolkit, gLite, and UNICORE Major players in the utility computing market are Sun Microsystems, IBM, and HP. SaaS uses a Pay As You Go (PAYG) model or a subscription model that is based on usage.

MARKET SEGMENTATION
The user side For companies on the demand or user side of the Grid computing market, the different segments have significant implications for their IT deployment strategy. CPU scavenging CPU-scavenging, creates a "grid" from the unused resources in a network of participants It saves instruction cycles that would otherwise be wasted at night, during lunch, or even in the scattered seconds throughout the day

GRID COMPONENTS
Schedulers Schedulers are types of applications responsible for the management of jobs. Allocation of resources needed for any specific job. partitioning of jobs to schedule parallel execution of tasks, data management The jobs submitted to Grid Computing schedulers are evaluated based on their service-level requirements Rescheduling and corrective actions of partial failover situations

GRID COMPONENTS
Resource Broker It provides pairing services between the service requester and the service provider. This pairing enables the selection of best available resources from the service provider for the execution of a specific task In general cases, the resource broker may select the suitable scheduler for the resource execution task It uses the resource information in pairing process

GRID COMPONENTS
Load Balancing Concerned distribution of workload among the resources in a Grid Computing environment. Integrated to avoid processing delays and over commitment of resources. These kinds of applications can be built in connection with schedulers and resource managers. This level of load balancing involves partitioning of jobs, identifying the resources, and queuing of the jobs

GRID COMPONENTS
Grid Portals Provides uniform access to the grid resources. For example, capabilities for Grid Computing resource authentication, remote resource access, scheduling capabilities, and monitoring status information Integrated Solutions combination of the existing advanced middleware and application functionalities, combined to provide more coherent and high performance

GRID SECURITY MECHANISM

The security in current Grid systems is designed to protect a user and a host system from a potentially malicious third party
Authentication It identifies each entity and ensure that no third party is involved
Authorization Ensures that the user is allowed to use the remote Grid resources Automation Used to implement many of the design goals of Grid computing, such as single sign-on, virtual organizations, and interaction among multiple administrative domains.

NEW SECURITY SCENARIOS

New approach to scoping Grid security issues is proposed in the context of three generic scenarios: Mutual trust Distrusted user Mutual distrust

NEW SECURITY SCENARIOS

Mutual Trust User trusts the resource provider to keep his data and activities secret and not interfere; and the resource provider trusts the user not to act maliciously Mutual authentication ensures that the source of any request is really the user and that the user is issuing the requests to the correct resource provider Security of the mutual authentication process depends on the secrecy of the private keys belonging to the user, resource, and any certificate authorities.

NEW SECURITY SCENARIOS

Distrusted user
The next Grid scenario of partial trust is when the user trusts the resource provider, but the resource provider does not necessarily trust the user. Usually the local user accounts are appropriately restricted by the operating system. This makes the operating system the first line of defense . The owner of the system may want to restrict Grid users further than other local users on the host. The controlled shell can be designed with a fail-safe mechanism such that if some potential intrusion or modification is detected, the user would be locked out

NEW SECURITY SCENARIOS

Mutual distrust The last Grid scenario is when the user may also distrust the resource provider. This scenario can arise in many ways
The owners of the resource may themselves be malicious and intentionally use their access to the host to violate the protection the external user expects. The user may desire some form of confirmation that his data has not been compromise as well as confirmation that it has been deleted with no copies kept after the job is completed.

OUR GRID
OurGrid is a web-based community for sharing computing power. Members join OurGrid by downloading a lightweight client which runs tasks on their computer . The tasks may be part of an application submitted by any OurGrid member. OurGrid members can not choose which application to donate their spare computing power The client code runs the tasks in a sandbox ,which isolates the tasks from the rest of the computer. It is designed to work for up to 10 000 computers.

CURRENT PROJECTS AND APPLICATIONS

Grids offer a way to solve Grand Challenge problems Earthquake simulation Climate/weather modeling Financial modeling
There is a well-known project called distributed.net, which was started in 1997 and has run a number of successful projects in its history. Another well-known project is the World Community Grid, its mission is to create the largest public computing grid that benefits humanity.

Thank you !!!