Term Paper: Computer Clustering

Pages: 8 (2319 words)  ·  Bibliography Sources: 1+  ·  Level: College Senior  ·  Topic: Education - Computers  ·  Buy This Paper


[. . .] When it rejoins the cluster, it acquires resources in the normal way. In most cases, STOMITH operations are performed via smart power switches that are controlled through either a network or serial connection, which remove power from the errant node for a brief period of time.

The most appropriate method for avoiding split brain, resource-based fencing or STOMITH, depends upon several factors. First the method available varies from vendor to vendor. And, it depends on the type of shared storage in use for the cluster. The STONITH approach is used primarily by quorum disk systems to solve the split-brain problem, but it also could be used by systems employing reservations (Leng, T., Stanton, C. And Zaibak (2001). A quorum system is a collection of sets (quorums), every two of which intersect (Naor and Wool). Quorum systems have been frequently used for many applications in distributed systems such as mutual exclusion, data replication and dissemination of information.

Although clustering has seen its share of challenges, most can be resolved and success abounds. Now, companies are looking at the next wave of innovation for resource use called grid computing. Grid computing requires the use of software that can divide and farm out pieces of a program to as many as several thousand computers. Grid computing can be thought of as distributed and large-scale cluster computing and as a form of network-distributed parallel processing (Grid computing). It can either be confined to the network of computer workstations within a corporation or it can be a public collaboration known as a form of peer-to-peer computing. The following quote explains the main difference between clustering and grid computing:

Whereas distributed or cluster computing pools the processing resources of a series of computers of all shapes and sizes, grid computing takes this concept one step further, allowing for detailed scheduling, high levels of service and distributed control." (Douglas, 2002)

The value proposition is that on the back end there is more dynamic resource provisioning than was possible with cluster computing, and on the front end it is now possible to acquire resources from different locations rather than dealing with static operations. In other words, it's now a lot easier to share, select and aggregate geographically distributed resources. The grand vision of grid computing is to virtualize computing, with the goal of creating a utility computing model over a distributed set of resources.

The best known project using grid computing is the project run through Berkley University (Douglas, 2002). This project has inspired nearly four million computer owners around their world to offer up some of their processing power on their personal computers for an attempt to detect signals from an extraterrestrial civilization. Four years after its launch, the software is running across at least 127 operating systems in 226 different countries, and has churned out half a billion results. And grid banks are being explored where resources from different organizations can become part of the cooperative shared environment.

Clustering has been one of the beneficial innovations in technology. They have fulfilled their promise for improving parallel processing, batch processing, load balancing and high availability. Now, the first stage of grid computing is cluster grids, or just clusters. Because grid computing is distributed and heterogeneous, some experts dispute that clusters should actually be considered grids. Despite these objections, there's little doubt that clusters have been critical in the development of grid computing. Computer operations are well on their way to becoming virtualized to help IT organizations further cut costs and increase the use of their existing infrastructure.


Beowulf clusters compared to Base One's batch job servers Retrieved May 2, 2004 from Web site: http://www.boic.com/beowulf.htm

Burleson, D. Requirements for parallel clusters. Retrieved May 1, 2004 from Web site: http://www.fast-track.cc/teas_ft_rac07.htm

Cluster computing. Retrieved May 1, 2004 from Web site: http://search390.techtarget.com/sDefinition/0,sid10_gci762034,00.html

D'Souza, Marco (2001, April 13). Meeting high-availability through clustering. ZDNet. Retrieved May 2, 2004 from Web site: http://www.zdnetindia.com/biztech/services/whitepapers/stories/19538.html

Douglas, J. (2002, August 9). Australian grid computing: creating science fact. ZDNet. Retrieved May 2, 2004 from Web site: http://www.zdnet.com.au/news/business/0,39023166,20267287-1,00.htm

Grid computing. Retrieved May 2, 2004 from Web site: http://searchcio.techtarget.com/sDefinition/0,sid19_gci773157,00.html

Leng, T., Stanton, C. And Zaibak (2001). Architecting Linux high-availability clusters - part 2. Retrieved May 1, 2004 from Web site: http://www1.us.dell.com/content/topics/global.aspx/power/en/ps1q01_linux?c=us&cs=555&l=en&s=biz

Naor, M. And Wool, A. The load, capacity and availability of quorum systems. Retrieved May 1, 2004 from Web site: http://www.wisdom.weizmann.ac.il/~naor/PAPERS/quor_abs.html

Server farm. Retrieved May 2, 2004 from Web site: http://whatis.techtarget.com/definition/0,sid9_gci213707,00.html

Shah, R. (199, August 9). Taking parallel processing to a new level. CNN. Retrieved May 2, 2004 from Web site: http://www.cnn.com/TECH/computing/9908/09/parallel.idg/

Sun product documentation. Retrieved May 1, 2004 from Web site: http://docs.sun.com/db/doc/805-0317/6j0c93ff6?a=view [END OF PREVIEW]

Four Different Ordering Options:

Which Option Should I Choose?

1.  Buy the full, 8-page paper:  $26.88


2.  Buy & remove for 30 days:  $38.47


3.  Access all 175,000+ papers:  $41.97/mo

(Already a member?  Click to download the paper!)


4.  Let us write a NEW paper for you!

Ask Us to Write a New Paper
Most popular!

Advanced Data Clustering Methods of Mining Web Documents Term Paper

Extracting Information Sentiment From Blogs Research Proposal

Effects of Technology on Personal Relationships Dissertation

Transition of Traditional Relational Database Technology Capstone Project

Current Event Analysis -- Apple's Product Innovation Term Paper

View 33 other related papers  >>

Cite This Term Paper:

APA Format

Computer Clustering.  (2004, May 1).  Retrieved March 23, 2019, from https://www.essaytown.com/subjects/paper/computer-clustering-involves-use/6414591

MLA Format

"Computer Clustering."  1 May 2004.  Web.  23 March 2019. <https://www.essaytown.com/subjects/paper/computer-clustering-involves-use/6414591>.

Chicago Format

"Computer Clustering."  Essaytown.com.  May 1, 2004.  Accessed March 23, 2019.