Sunday, October 21, 2007

The End of Grid Computing?

In the year 2003 the MIT Technology review ranked "Grid Computing" among the 10 Emerging Technologies That Will Change the World [1].
We are now four years later and something is not going well with "Grid Computing".
An indication that there is a problem can easily be seen by looking at the "Google Trends" plot for the term "Grid Computing":


(click on the image to get the current trend).
This finding can be compared with another buzz word, "Virtualization", which is older than "Grid Computing" and yet is gaining more and more momentum:


There is however one exception. The Academic Grid is still having lot's of glory thanks to the huge heavily funded European (EGEE) and other US projects. When LHC data will start to be taken at CERN it will reach it's top importance. But, it seems that for other scientific projects Grid Computing is not going to be such a success. It will remain as "Nice to have" but will never replace High-Performance Computing (HPC) on one hand and classical distributed computing tools such as Condor [2] which exists for more than 20 years on the other hand.
Once the governmental fundings will be removed then all the hype of the academic Grid Computing will decline very quickly as well.
As was pointed in an interesting talk by Fabrizio Gagliardi about the future of grid computing, at the GridKa07 School, other kinds of Grid Computing infrastructures that will stand on stable financial ground may emerge as the successors, for example Amazon's S3 and EC2 and the joint IBM and Google's cloud computing.



[1] http://www.technologyreview.com/Infotech/13060/page6/

[2] http://www.cs.wisc.edu/condor

10 comments:

Anonymous said...

Dear Guy:

I don't think you can read too much into Google Trends. Certainly it captures the fact that "virtualization" has replaced "grid" as the most popular industry buzzword. But given that industry has used grid mostly to mean "cluster" (e.g., Oracle 10-G, SGE), that doesn't say too much about grid per se.

Measuring adoption and impact is nevertheless an important goal. Thus we have integrated usage reporting mechanisms into our Globus software. We see continued growth in use, as captured by metrics such as service deployments. We're now trying to understand the underlying usage modalities. I suspect that many are concerned with "eResearch" functions other than "federating computers"--e.g., on-demand access to computing [on HPC systems and/or EC2], data distribution, service publication and composition, etc. Do these functions count as "grid"? They do according to our article "The Anatomy of the Grid"--and if you look at the goals of projects such as D-Grid.

Regards -- Ian Foster.

Bert said...

Grid as a technology has never had more interest, but it's not "the grid" in the academic sense.

Rather, grid is becoming a common architecture in utility computing services like 3tera's AppLogic and Amazon's EC2. I can assure you that users definitely think of these services as grid. However, such systems are more readily adopted than traditional grid architectures and can be applied to a wide array of applications beyond HPC.

So, as utility computing moves forwards, grid technology is the foundation on which it's being built.

Anonymous said...

Gartner's 10 strategic technologies for 2008 - FYI:
http://www.gartner.com/it/page.jsp?id=530109

Ziva

Departamento de Supercomputo-UNAM said...

I agree with Ian in the sense that grid technologies are still being in incremetal usage, and also think are going to be a very important component of future computational infrastrucutres.

However, I also agree with the "decline" of grid technologies in the sense they were suposed to be a replacement for big computers, bringing a kind of "cheap supercomputing" or "P2P" access to a broader range of resources.

Anonymous said...

Dear all,

I believe there was an initial misunderstanding about grid computing. It was perceived as the evolution of traditional distributed computing: something everybody could use every day, such as the web, email and P2P. When the people realized that they instead need large scale problems in order to use grids effectively, their interest went off. Indeed, the majority of the people usually does not need computing power simply because they do not have difficult problems to solve. However, it is also true that both the scientific and many business communities have been taking advantage of grid computing in the last ten years. And they will certainly continue to do so. The main difference is that, in the latter case, there are plenty of computational resources and people with the expertise/skills required to compile, deploy and configure grid middleware. Therefore grid computing is still alive and in quite good shape, it's just a matter of understanding usage patterns as already better explained by Ian. Of course, I also agree that the term grid computing is now increasingly meant to be utility computing, but we have already witnessed the same transition from metacomputing to grid computing, from the network is the computer to the grid is the computer etc. Not a big surprise.

Best regards,
Massimo Cafaro

walterstewart said...

It was a grave error, in the early part of this decade, to read too much into the marketing "hype" around grid. It is an equally grave error, today, to read too much into the transfer of that marketing hype to virtualization. Infrastructure for the knowledge economy will be created by a mix of many technologies. Grid, virtualization, distributed computing, and likely many yet to be "hyped" concepts will be there in a mix determined by need and by imagination about how real value can be created.

Walter Stewart

Anonymous said...

Dear Guy:

Please be also reminded that many use now different terms other than "Grid" computing. Cyberinfrastructure, cloud computing, and others come in mind. Even the term virtualization is related to Grid computing (e.g. virtual organization) ;-) We see today also a diversification and specialization of terminology aligned with Grid computing. This reflects also Ians view who has given other examples of popular words related to Grid computing.

Gregor von Laszewski - Rochester Institute of Technology

Gold Guide for World of Warcraft said...

good post :)

gfh said...

We always Wow Power Leveling and world of warcraft gold

Anonymous said...

I'm the kind of guy who loves to try innovative things. Right now I am making my personal photovoltaic panels. I am doing it all by myself without the aid of my staff. I'm utilizing the internet as the only way to acheive that. I stumbled upon a truly awesome website which explains how to contruct solar panels and wind generators. The site explains all the steps required to building solar panels.

I am not exactly sure about how correct the information given there is. If some experts over here who have xp with these things can have a see and give your feedback in the thread it will be great and I would extremely value it, cause I truly would love to try [URL=http://solar-panel-construction.com/diy-solar-panel-construction-is-it-really-possible]solar panel construction[/URL].

Tnx for reading this. You people are the best.