Grid Computing��and��Alternative Distributed Computing Solutions

Noman Islam

k060991@nu.edu.pk

Oct, 2007

NU-FAST, Karachi

Introduction

The defining characteristic of a grid [1]:

“The essence of grid computing lies in the efficient and optimal utilization of a wide range of heterogeneous, loosely coupled resources in an organization tied to sophisticated workload management capabilities or information virtualization”

A Three Point Check List for Grids [4]

1. Coordinates resources that are not subject to centralized control
• A Grid integrates and coordinates resources and users that live within different control domains
2. Uses standard, open, general-purpose protocols and interfaces
• built from multi-purpose protocols and interfaces that address such fundamental issues as authentication, authorization, resource discovery, and resource access

​

A Three Point Check List for Grids [4]

3. Deliver nontrivial qualities of service
• Allows its constituent resources to be used in a coordinated fashion to deliver various qualities of service to meet complex user demands, so that the utility of the combined system is significantly greater than that of the sum of its parts

​

Grid Fills a Crucial Gap [1]

Introduction to Cluster Computing

• A group of tightly coupled computers that work together closely so that in many respects they can be viewed as though they are a single computer
• They are often connected to each other through fast LAN
• Cluster Categories
• High-availability (HA) clusters
• Load-balancing clusters
• High-performance computing (HPC) cluster

An example of Cluster

Grid Vs Cluster Computing

• The key difference between grids and traditional clusters are that grids connect collections of computers which do not fully trust each other, or which are geographically dispersed
• Grid computing is optimized for workloads which consist of many independent jobs or packets of work, which do not have to share data between the jobs during the computation process. Grids serve to manage the allocation of jobs to computers which will perform the work independently of the rest of the grid cluster. Resources such as storage may be shared by all the nodes, but intermediate results of one job do not affect other jobs in progress on other nodes of the grid.

Grid Vs Cluster Computing

• Grids consist of heterogeneous resources (integrates storage, networking, and computation resources) where as clusters have computational resources
• Clusters usually contain a single type of processor and operating system; grids can contain machines from different vendors running various operating systems

Grid Vs Cluster Computing

• Grids are dynamic by their nature. Clusters typically contain a static number of processors and resources; resources come and go on the grid. Resources are provisioned onto and removed from the grid on an ongoing basis
• Grids are inherently distributed over a local, metropolitan, or wide-area network. Usually, clusters are physically contained in the same complex in a single location; grids can be (and are) located everywhere. Cluster interconnect technology delivers extremely low network latency

Grid Vs Cluster Computing

• Grids offer increased scalability. Physical proximity and network latency limit the ability of clusters to scale out; due to their dynamic nature, grids offer the promise of high scalability
• But Cluster and grid computing are becoming completely complementary. Many grids incorporate clusters among the resources they manage. Indeed, a grid user may be unaware that his workload is in fact being executed on a remote cluster. And while there are differences between grids and clusters, these differences afford them an important relationship because there will always be a place for clusters -- certain problems will always require a tight coupling of processors

Grid Vs Cluster Computing

• As networking capability and bandwidth advances, problems that were previously the exclusive domain of cluster computing will be solvable by grid computing. It is vital to comprehend the balance between the inherent scalability of grids and the performance advantages of tightly coupled interconnections that clusters offer

Introduction to P2P

• P2P is a class of applications that takes advantage of resources-storage, cycles, content, human presence - available at the edges of the Internet
• A pure peer-to-peer network does not have the notion of clients or servers, but only equal peer nodes that simultaneously function as both "clients" and "servers" to the other nodes on the network.

Grid Vs P2P

• Grid were motivated by the requirements of professional communities needing to access remote resources, federate datasets, and/or pool computers for large-scale simulations and data analyses. It was initially developed to address the needs of scientific collaborations, commercial interest is growing
• P2P has been popularized by grass roots, mass-culture file-sharing and highly parallel computing applications that scale in some instances to hundreds of thousands of nodes

Grid Vs P2P

• Grid integrate resources that are more powerful, more diverse, and better connected than the typical P2P
• Grid resource - cluster, storage system, database, or scientific instrument administered in an organized fashion according to some well defined policy.
• P2P often deal with intermittent participation and highly variable behavior.
• Major resources are home computers.

Grid Vs P2P

• Grid often involves only modest numbers of participants. The amount of activity can be large.
• Early Grid implementations did NOT address scalability and self management as priorities
• P2P has far larger communities

​

Grid Vs P2P

• In Grid, works have been done associated with creating and operating persistent, multipurpose infrastructure services for authentication, authorization, discovery, resource access, data movement...Less effort has been devoted to managing participation in the absence of trust
• P2P offers much scalability, fault tolerance, self-configuration, automatic problem determination. P2P system have tended to focus on the integration of simple resources (individual computers) by protocols. The persistence properties of such infrastructures are not specifically engineered but are rather emergent properties

Grid Vs P2P

• P2P system lacks a central point of management; this makes it ideal for providing anonymity. Grid environments, on the other hand, usually have some form of centralized management and security (for instance, in resource management or workload scheduling).
• Lack of centralization means:
• More scalable
• More tolerant of single-point failures than grid computing systems. (Although grids are much more resilient than tightly coupled distributed systems, a grid inevitably includes some key elements that can become single points of failure)
• The key to building grid computing systems is finding a balance between decentralization and manageability -- not an easy chore

​

Grid Vs P2P

• Also, while an important characteristic of grid computing is that resources are dynamic, in P2P systems the resources are much more dynamic in nature and generally are more fleeting than resources on a grid
• A final distinction between the two systems is standards -- the general lack of standards in the P2P world contrasts with the host of standards in the grid universe. And, thanks to entities like the Global Grid Forum, the grid universe has a mechanism for refining existing standards and creating new ones

Common Object Request Broker Architecture

Grid Vs CORBA

• CORBA
• OGSA and CORBA, both are based on the concept of service-oriented architecture (SOA)
• CORBA assumes object orientation (after all, it is part of the name), but grid computing does not
• There are also issues of interoperability among different platforms in CORBA

​

Distributed Computing Environment

• The Distributed Computing Environment (DCE) is a software system developed in the early 1990s by a consortium that included Apollo Computer (later part of Hewlett-Packard), IBM, Digital Equipment Corporation, and others. The DCE supplies a framework and toolkit for developing client/server applications. The framework includes a remote procedure call (RPC) mechanism known as DCE/RPC, a naming (directory) service, a time service, an authentication service, an authorization service and a distributed file system (DFS) known as DCE/DFS

Grid Vs DCE

• Not so much an architecture but an environment, DCE facilitates distributed computing; grid computing (in the form of OGSA) is more of an end-to-end architecture designed to encapsulate many of the intricacies of the mechanics of distributed computing

Conclusion

• We have examined Grid Computing and its importance at Enterprise Level
• Also an analysis of the similarities and differences between grid computing and four major distributed computing systems
• Based on the benefits of these paradigms, we can expect these approaches to eventually converge

References

[1] “Perspectives on grid: Grid computing -- Next-generation distributed computing”, Matt Haynos, Program Director, Grid Marketing and Strategy, IBM, http://users.cs.cf.ac.uk/David.W.Walker/IGDS/GridCourse.htm

​

[2] Grid Vs Peer-to-Peer, Yin Chen, http://freewebs.com/yinchenagain/doc/p2p.pdf

​

[3] Wikpedia, the Free Encyclopedia, http://www.wikipedia.org

​

[4] ‘What is the Grid? A Three Point Check List’, Ian Foster, 2002

​

​