Wednesday, November 28, 2007

Paradigm Shift

Without sounding too much like an analyst and over-generalizing the tech industry as a whole, I really believe we are in the middle of a paradigm shift for technology. I’m old enough to remember mainframes, but never operated or administered them (unless doing COBOL programming in college counts). So there was the mainframe era, the client/server era and whatever-we’re-in-now era. I’ve loved the concept of utility computing ever since the hype (and over-hyping) began. I think it has a ton of potential and some really important concepts and intelligent people behind it. As many others have pointed out, the internet companies have contributed a significant amount to changing architectures used in IT. Perhaps they can be credited for driving much of the needed change that allowed for such enormous scalability (there, the words paradigm shift AND scalability should sit well for the search engine spiders :) A comment from a Gartner session yesterday summed it up nicely…. “cloud computing has ‘some’ degree of truth to it, but also a lot of fog”.

I’ll keep this post as short as possible so I don’t blab on too long and lose readers (assuming you have made it this long). I wanted to link to some utility computing and virtualization articles I liked and then make a few links out to some thoughts on data center containers/black box (DataCenter in a box part IIIa).

Bert Armijo and Peter Nickolov from 3Tera wrote an article recently on Fishtrain about services that virtualization needs adapt to the utility computing model. It is a very good article about future concepts and why virtualization is “not a complete utility computing solution”

The additional service that I would add is security. I’ve been a big fan of Christopher Hoff’s blog that frequently discusses virtualization security and potential vulnerability attack angles. And speaking of innovative technologies and industry shifts, check an excellent post on Security and Disruptive Innovation part III. Security needs to be improved in virtualization, but even more so as it spans across a utility computing implementation.

Network World also ran an interesting article on virtualization security and the realization that many are coming to for their implementations and how some have not even started their implementation because of security issues.

Because I am in the data center business I always digress to the physical part of the infrastructure when the ‘virtual’ data center is mentioned. To me there is no such thing as a virtual data center because it is the one true ‘real’, tangible asset in the infrastructure equation. So when I read about Amazon EC2 and 3Tera, I love the utility computing concepts and having infrastructure virtualized across physical data centers. Of course, with my recent white paper on site selection I also automatically assume geographically disperse data center locations to account for BCP plans and risk avoidance.

A final paradigm shift item I’ll mention is workload lifecycle and management. I don’t know if I completely understand it yet, but I have spent a fair amount of time on the Platespin web site and feel they have a very complete set of products. As it relates to a new and better way to deploy, manage and control your infrastructure I would recommend anyone gives their products a consideration. There is also a decent joint presentation from Dell, Microsoft and Platespin on their respective technologies here

Ok, so there is the paradigm shift in infrastructure architecture and deployment options. Let’s go up a level and look at the data center as a whole. If you’ve read my blog for any amount of time you know I am intrigued, interested, and perplexed by the container model that Rackable, Sun, APC and others have come out with and Google patented, but was dropped as a research project.

There are some interesting comments on the Slashdot post about Intel Data Centers. Some of the interesting points I noticed from these comments are:

1. Chuck Thacker from Microsoft has a very interesting PowerPoint presentation on data centers as a container model. It is a 26 slide presentation full of their research and insight to the topic.

2. There are references to the recent news about Sun’s BlackBox being used underground in Japan and using Geo-exchange for cooling and heat exchange.

3. A user comment: The reason a "data center in a box" sounds so attractive is that the amortization schedules are different for IT equipment and buildings. If building infrastructure can last its advertised 25-30 year life then a tilt-up or factory assembled type of building structure is more cost-effective than containerized data centers architecturally.”

The thing I have always been thinking about, and that was brought up many times in the Slashdot comments, was just what in the world was the practical application of the data center container? With Google, Sun, Microsoft and others seriously looking at it and doing such deep research on the possibilities, you simply have to think that there is something that they have found that makes business sense and that they have justified.

More later --- back to the Gartner conference for now…..

No comments: