Just a quick post to give some background on the Gartner Data Center Conference that I am currently attending. During the opening comments and first keynote they took a few polls of the audience.
I think these are important --- to profile the average attendee and show real data about the industry. Here is what was covered so far:
Poll Question: What is the make up of your Data Center?
Responses:
40% Mainframe, Linux, Unix, Windows
25% Unix, Linux, Windows
10% Mainfram, Unix, Windows
10% Unix, Windows
(I couldn't write fast enough to get the rest :) )
Poll Question: Do you have server consolidation projects?
Responses:
1. No Plans -- 3%
2. Looking into it -- 17%
3. Project Under way -- 50%
4. Already completed a project, may do another -- 30%
Poll Question: How long have you worked in IT?
Responses:
< 2 yrs: 1%
2-5yrs: 2%
5-10yrs: 8%
11-20yrs: 35%
21-30yrs: 40%
31-40yrs: 13%
40+yrs: 1%
Poll Question: Do you have a long term strategy for Infrastructure and Operations?
Responses:
Yes: 42%
No: 37%
Unsure: 21%
Tuesday, November 27, 2007
Sunday, November 25, 2007
HSBC Questioning $1 billion Niagra County Data Center
The Niagra Gazette reports that global banking giant HSBC is reconsidering the $1 billion data center it had planned for Cambria, NY. The data center would add 56 jobs, averaging $76k and would add $14.5 million in property tax collections.
HSBC is not terminating the project, but just looking at alternate sites in the county (otherwise they will give up the $89.5 million in tax breaks. The bank indicated that current business climate was the reason for them to step back and stay in planning phase for a while.
In January of this year Data Center Knowledge reported the plans for the 275,000 sq. ft. facility.
Check out the Niagra Gazette article here
HSBC is not terminating the project, but just looking at alternate sites in the county (otherwise they will give up the $89.5 million in tax breaks. The bank indicated that current business climate was the reason for them to step back and stay in planning phase for a while.
In January of this year Data Center Knowledge reported the plans for the 275,000 sq. ft. facility.
Check out the Niagra Gazette article here
Saturday, November 24, 2007
BroadGroup - 1mil sq ft of Fresh Capacity
BroadGroup Consultancy (London) announced build plans that include more than 1 million square feet of data center capacity. Most of the planned capacity, it was stated, will serve one or more large companies. Other projects for the space included managed services by ISP's, colocation and disaster recovery planning.
A little over a month ago BroadGroup predicted the constant demand for European data centers.
BroadGroup is an independent consultancy based in London and focuses on analyzing and interpreting business strategy. BroadGroup also runs the data centre portal datacentres.com
Check out the WHIR article here
A little over a month ago BroadGroup predicted the constant demand for European data centers.
BroadGroup is an independent consultancy based in London and focuses on analyzing and interpreting business strategy. BroadGroup also runs the data centre portal datacentres.com
Check out the WHIR article here
Labels:
BroadGroup,
colocation,
data centre
Thursday, November 22, 2007
Happy Thanksgiving

Happy Thanksgiving!
Just wanted to wish everyone well this Thanksgiving. I'm heading to the Gartner Data Center Conference on Monday and will of course report all that I can in what time allows
Also--check out Network World's Top IT Turkeys of 2007. :)
Monday, November 12, 2007
Parallel Computing and Cognitive Fitness
I just finished reading the article "Cognitive Fitness" in the November 2007 issue of Harvard Business Review. The article covers new research in neuroscience about staying sharp and exercising your brain. One of the items you often find in these articles and research is to learn something completely new and/or something you don't normally deal with.
After reading this article I went back to surfing the web.....and came across some information on parallel computing. Perfect! This is something that I've always considered out of my realm of comprehension, yet I have always been very interested in it. As an added bonus there are some insights to draw in the data center industry and links to information about Google!
First -- Microsoft. Microsoft has made a couple of moves this year to indicate a trend in parallel computing and perhaps a tie-in to container-style data centers....stay with me, I'll get to that. In July of this year EETimes.com interviewed Burton Smith about programming languages and parallel computing. Smith oversees research in programming languages for parallel hardware architectures.
EETimes.com also had an interesting article about a month ago on the Cloud Computing initiative for Google and IBM. Google's Christophe Bisciglia explained:
The other Google link I found returned me to the 'brain workout' I was receiving by reading about parallel computing. Check out the slides and presentations on Distributed Systems and Cluster Computing at Google -- here
Ok, so now the container angle. Caveat---remember I'm a newbie for the parallel computing topic, so tell me if I'm way off here. Google's infrastructure is more or less, clusters of networked CPU's orchestrated for various tasks and applications. Microsoft hints at similar items when talking about writing programming languages for parallel computing. Why not call a fully-loaded container of computers a cluster, write 'internet-scale' applications that will be able to reference multiple clusters (i.e.: thousands of CPUs across different containers) and still utilize the multi-core processors within each computer. Ok -- I know, this is essentially what Google does now across their data centers -- but why not change up the data center model. Place compute units (in this case, a full container) at geographically disperse locations and then reference them with an parallel-optimized OS or language. The benefit to shipping containers in this case is not having the high up-front costs involved with building the mega data centers that they are today, and they can move the containers to where the cheap power and land are without too much trouble. With such dense computing and more raw power than form factor, the container is a good fit, and the portability and quick build time are added benefits. I still advocate that security is an absolute must add-on for shipping container parks, but retro-fit a warehouse and BYOUG (bring your own UPS and Generator).
Ok -- that's enough brain exercising for one night (maybe a couple).
After reading this article I went back to surfing the web.....and came across some information on parallel computing. Perfect! This is something that I've always considered out of my realm of comprehension, yet I have always been very interested in it. As an added bonus there are some insights to draw in the data center industry and links to information about Google!
First -- Microsoft. Microsoft has made a couple of moves this year to indicate a trend in parallel computing and perhaps a tie-in to container-style data centers....stay with me, I'll get to that. In July of this year EETimes.com interviewed Burton Smith about programming languages and parallel computing. Smith oversees research in programming languages for parallel hardware architectures.
Multicore processors are driving a historic shift to a new parallel architecture for mainstream computers. But a parallel programming model to serve those machines will not emerge for five to 10 years, according to experts from Microsoft Corp.Then, last Friday, Microsoft Research hired veteran supercomputer researcher Dan Reed. Reed's mission is to take a "green field approach" to the spiraling power and reliability requirements of large data centers.
"There is a sea change in computing coming at the intersection of multicore and large data centers, and working on this is one of the most exciting things I can imagine doing," said Reed. There's no single path to the parallel programming models needed to support tomorrow's multi core processors, said Reed. "It will take a variety of efforts in areas such as functional languages, transactional memory, extensions of existing languages and new higher level tool kits," he said.And as we all know now, Microsoft is building 'mega data centers' to support the massive computing infrastructure required for internet-scale initiatives and Microsoft Research.
EETimes.com also had an interesting article about a month ago on the Cloud Computing initiative for Google and IBM. Google's Christophe Bisciglia explained:
"It's no longer enough to program one machine well; to tackle tomorrow's challenges, students need to be able to program thousands of machines to manage massive amounts of data in the blink of an eye."The Google/IBM initiative is to advance large-scale distributed computing by providing hardware, software and services to Universities. Google is providing several hundred of their custom-built computers, while IBM will provide its BladeCenter and Sytem X Servers. The initiative (and article) are pretty interesting; check it out here
The other Google link I found returned me to the 'brain workout' I was receiving by reading about parallel computing. Check out the slides and presentations on Distributed Systems and Cluster Computing at Google -- here
Ok, so now the container angle. Caveat---remember I'm a newbie for the parallel computing topic, so tell me if I'm way off here. Google's infrastructure is more or less, clusters of networked CPU's orchestrated for various tasks and applications. Microsoft hints at similar items when talking about writing programming languages for parallel computing. Why not call a fully-loaded container of computers a cluster, write 'internet-scale' applications that will be able to reference multiple clusters (i.e.: thousands of CPUs across different containers) and still utilize the multi-core processors within each computer. Ok -- I know, this is essentially what Google does now across their data centers -- but why not change up the data center model. Place compute units (in this case, a full container) at geographically disperse locations and then reference them with an parallel-optimized OS or language. The benefit to shipping containers in this case is not having the high up-front costs involved with building the mega data centers that they are today, and they can move the containers to where the cheap power and land are without too much trouble. With such dense computing and more raw power than form factor, the container is a good fit, and the portability and quick build time are added benefits. I still advocate that security is an absolute must add-on for shipping container parks, but retro-fit a warehouse and BYOUG (bring your own UPS and Generator).
Ok -- that's enough brain exercising for one night (maybe a couple).
Labels:
cloud computing,
EETimes,
Google,
IBM,
microsoft,
parallel computing
Sunday, November 11, 2007
Intel IT (and shipping containers, Part III)
About a year ago I listened to HP discuss their consolidation plans of reducing their data centers to a few key hubs. Recently, Intel has published some of the details surrounding their consolidation plans. Brently Davis has a nice YouTube video explaining the details.

Intel also launched their new power-efficient Penryn processors today.
A little while back I received my Winter 2008 issue of Premier IT -- Intel's magazine for sharing best practices. It is a pretty nice magazine -- usually vendor magazines are 80%+ a pure marketing vehicle, but Intel's is actually quite infomative. The "Transforming Intel IT" article in this issue was particularly interesting. I continue to be hung up on the exact use of the shipping container model for data centers. I still picture trailer parks full of black boxes and fiber hooked up as if they are getting HBO. :)
I have a number of items (and links) queued up for a longer post on shipping containers, the Google patent of the modular data center, and potential (practical) uses of the container model, but for now, I wanted to point out the interesting quotes from this Intel magazine article.
The article explains that Intel is evaluating all types of innovation......
We’ve determined that our compute servers operate quite well at a higher ambient temperature than do other systems such as storage; by comparison, the storage environment requires much cooler temperatures (10 percent to 20 percent lower) and more floor space per unit. By segmenting storage systems into smaller rooms that are tuned to the specific needs of storage,The second item is about containers:
we could run the compute servers at higher temperatures, around 80 degrees Fahrenheit.
The cost of building a new data center is extremely high—between USD 40 million and USD 60 million. As an alternative, we are considering placing high-density servers on racks in a container similar to those you see on container ships and trucks. We estimate that the same server capacity in this container solution will reduce facility costs by 30 percent to 50 percent versus a brick-and-mortar installation. Because it’s a small, contained environment, cooling costs are far less than for traditional data centers. Even if we build a warehouse-like structure to house the containers (thus addressing security and environmental concerns), the cost is dramatically less per square foot. In fact, the difference is so great that with this solution, brick-and-mortar data centers may become a thing of the past.The site requires (free) registration, but once logged in, the article can be found here
Finally -- a presentation on their site for the energy efficiency opportunity had a cool slide on delivering data center optimization:
2002
3.7 TFlops
25 racks
512 servers
1000 sq. ft
128 kW
2007
3.7 TFlops
1 rack
53 blades
40 sq.ft
21 kW
Labels:
consolidation,
container,
Google,
innovation,
intel,
modular
Thursday, November 08, 2007
Gartner Data Center Conference
Just a quick post to say that I will be attending the 26th annual Gartner Data Center Conference. This is being held in Las Vegas, Nov.27-30. I have my schedule ready to go and am really excited about attending this conference.
If anyone else will be attending and would like to meet up -- drop me an email.

If anyone else will be attending and would like to meet up -- drop me an email.

Labels:
conference,
gartner
IBM
For whatever reason, I've been surfing a lot lately on IBM. IBM is an absolutely enormous company and have their hands in just about everything. Here are some of the things I have been looking at lately:
- IT facilities assessment, design, and construction services
- IBM Grid
- Deep Computing - Capacity On Demand
- Ideas International - a nice summary of the IBM 2007 Analyst Conference
- IBM System X
Today, System x is the second largest server group in IBM (based on revenue) next to the System z, and by 2011 IBM expects it to be the largest server group
Labels:
IBM
Sunday, November 04, 2007
Symantec State of the Data Center Report 2007
Last Tuesday Symantec (SYMC) announced the release of their 2007 State of the Data Center Report. The international study surveyed managers of Global 2000 and other large companies. The magazines, web sites and company white papers are constantly full of industry statistics and trend monitoring, but I think this report did a nice job of doing the legwork necessary to get real data from those facing the issues in the data center today and presenting it in a clear and concise manner. I think one sentence in the paper summarizes the main point nicely:
Essentially, data center managers are being asked to deliver more high-quality services in an increasingly complicated environment, yet their budgets are relatively flat. As a result, data center managers find they adopt cost containment strategies that make use of new technologies, including virtualization, and new management approaches, such as those that automate routine processes.
Here are some of the highlights that I gleamed from reading the report:
- Of the five issues (of factors impacting today's Data Centers) I think #2 and #5 are the big ones (in my mind). #2 is staffing and #5 is Disaster Recovery/Business Continuity Planning. Staffing has been noted several times in the press and is obviously becoming a large issue that managers must deal with.
- Better preparedness for a disaster now versus two years ago was listed by 53% of the repsondents. When thinking of locations for your DR and BCP plans, don't forget my Site Selection white paper.
- Not surprising, the always fun statistic proved true once again for a cause of downtime. Twenty-eight percent of respondents listed "change or human error"as a chief reason for downtime. Although some stories have down played ITIL, I think for this reason alone you will see an increased usage of the ITIL guidelines in data centers. This obviously plays into the staffing issues raised as well.
- The report has good information on virtualization plans. I think it will be interesting to see how Microsoft fits into this market in the near future. I don't believe they will pose a serious threat to VMWare, but will most likely balance out the market a little more and have a decent percentage. VMWare was the top product listed in the U.S. but almost half of Asia-Pacific respondents are using Microsoft virtualization, with only 35% going to VMWare. I haven't finished watching it yet, but here is a video of Eric Traut from Microsoft, presenting on Microsoft's virtualization technologies (it also mentions Windows 7).
- The outsourcing statistics were interesting. Fourty-two percent of U.S. managers said they utilize outsourcing, while 61% of non-U.S. organizations are. "Among the most common tasks outsourced by both U.S. and non-U.S. organizations are server maintenance, backups, storage management, archiving, and business continuity."
Labels:
report,
staffing,
symantec,
virtualization
Friday, November 02, 2007
Chicago Colo Armed Robery
Many years ago I remember CI Host as being a reputable, large hosting company in the industry. It seems as though they have gone down hill in recent years, and this recent event makes the bad even worse.
They have had at least four intrusions to their data centers in the last two years!! In the most recent event intruders apparently cut through the walls with a power saw. At least 20 servers were stolen and a night manager was tazered. To make matters worse, CI Host staff was not quick to alert customers or even admit the breach.
I predict a mass exodus from this facility (old DC pun intended)
Check out the article at The Register here
They have had at least four intrusions to their data centers in the last two years!! In the most recent event intruders apparently cut through the walls with a power saw. At least 20 servers were stolen and a night manager was tazered. To make matters worse, CI Host staff was not quick to alert customers or even admit the breach.
I predict a mass exodus from this facility (old DC pun intended)
Check out the article at The Register here
Wednesday, October 31, 2007
Brocade SAN Solution at U of Iowa
Brocade had a press release out yesterday explaining how their SAN directors had been implemented recently. I've always liked Brocade products, thought this was an interesting case study and thought I would see if my brother was paying attention to the blog. :)
Two 48000 Directors are the foundation of the SAN (Storage Area Network) and will scale to as many as 384 concurrently active 4 Gbit/sec ports in a single domain.
Check out the new/press release at CNN here
Two 48000 Directors are the foundation of the SAN (Storage Area Network) and will scale to as many as 384 concurrently active 4 Gbit/sec ports in a single domain.
Check out the new/press release at CNN here
First LEED Gold Certification

The first Gold Certification for LEED (Leadership in Energy and Environmental Design) has been earned by Digital Realty Trust. The project was for a Fortune Global 500 company (i.e.: someone that could afford it) in Chicago.
The data center is 20,000 sq.ft of raised floor with 4000 kW of available IT load. They started this certification process more than a year ago and have several other projects expecting certifications soon.
Check out the press release here
Labels:
Chicago,
Digital Realty Trust,
leed
Monday, October 29, 2007
The HD Web
A short while back I explained what a cool company Akamai was. Back in February of this year I made my prediction for 2007. Well, Akamai continues to blow me away, and I think the prediction was perhaps a little ahead of the market (hey Verizon, how long until I get FiOS?!!)
I forget where I ran across it, but Akamai has a new web site to showcase High Definition video capabilities through their network. It really is pretty amazing, and gets me excited for watching HD over the internet (as soon as the fiber comes to my house).
Check out their site here and cool explanation of it all here.
I forget where I ran across it, but Akamai has a new web site to showcase High Definition video capabilities through their network. It really is pretty amazing, and gets me excited for watching HD over the internet (as soon as the fiber comes to my house).
Check out their site here and cool explanation of it all here.
Sunday, October 28, 2007
Green Data Center
Of the hundreds of articles we've all seen this year on the environment, saving energy, new energy sources and "the green data center", I wanted to point out two recent items I have read that I thought were particularly good.
The print version of the October 15th issue of EWeek ("The Green Issue"), has a lot of good information, statistics and news. I couldn't find a direct link to the issue, but here is their 5 Steps to Green IT.
Secondly, Matt Stansberry at Tech Target is releasing a chapter at a time of his E-book, The Green Data Center: Energy Efficient Computing in the 21st Century. The chapters I have read so far are excellent. Matt has a lot of good information, stats and industry trends. I am anxious for the chapters to come.
The print version of the October 15th issue of EWeek ("The Green Issue"), has a lot of good information, statistics and news. I couldn't find a direct link to the issue, but here is their 5 Steps to Green IT.
Secondly, Matt Stansberry at Tech Target is releasing a chapter at a time of his E-book, The Green Data Center: Energy Efficient Computing in the 21st Century. The chapters I have read so far are excellent. Matt has a lot of good information, stats and industry trends. I am anxious for the chapters to come.
Labels:
environment,
Eweek,
Green,
Tech Target
Tuesday, October 23, 2007
HP's Dynamic Smart Cooling
Just a quick link to an article about HP debuting their new 'smart' India data center. They claim it has achieved a 40% energy savings due to using their technologies and methodologies.
Check out the San Jose Mercury News article here
Check out the San Jose Mercury News article here
Labels:
energy savings,
hp
Data Center Outsourcing
I ran across a link in my email recently that was interesting, so I continued reading it. EDS has received a "Strong-Positive" rating from Gartner. This comes from the 2007 release of their "MarketScope for Data Center Outsourcing, North America".
EDS was one of 17 companies evaluated and manages over 100 data centers worldwide. Check out their press release here
I of course didn't have a spare $1,995 laying around for the full report, so I searched around - and found a good summary of the report. Unisys was listed on the report ("Positive" rating) and had the summary on their web site. There were a few companies I didn't recognize. I suppose I think too much of the colo companies and not those providing a data center as an outsourced service.
I wish I was able to purchase the report - it looks very thorough and does a nice job of spelling out the evaluation criteria and market segment. Here are some of the companies (with links) that were evaluated in the report:
Acxiom
ACS
Atos Origin
CapGemeni
CGI
CSC
EDS
HP
IBM
Infocrossing
Maintech
Northrup Grumman
Perot Systems
Savvis
Siemens
Sungard
Unisys
Vericenter (recently acquired by Sungard)
EDS was one of 17 companies evaluated and manages over 100 data centers worldwide. Check out their press release here
I of course didn't have a spare $1,995 laying around for the full report, so I searched around - and found a good summary of the report. Unisys was listed on the report ("Positive" rating) and had the summary on their web site. There were a few companies I didn't recognize. I suppose I think too much of the colo companies and not those providing a data center as an outsourced service.
I wish I was able to purchase the report - it looks very thorough and does a nice job of spelling out the evaluation criteria and market segment. Here are some of the companies (with links) that were evaluated in the report:
Acxiom
ACS
Atos Origin
CapGemeni
CGI
CSC
EDS
HP
IBM
Infocrossing
Maintech
Northrup Grumman
Perot Systems
Savvis
Siemens
Sungard
Unisys
Vericenter (recently acquired by Sungard)
Tuesday, October 16, 2007
DC Site Selection
A long while back I mentioned that I was working on a site selection post for the blog. As I was working on it, I decided it was worthy of more than just a post.
I am happy to announce that I have finished a white paper on the topic of Data Center Site Selection. I welcome any and all comments and hope it is informative and helpful.
If you decide to link to the paper, I would ask that you link to this post instead of directly to the PDF.
Link: http://datacenterlinks.blogspot.com/2007/10/dc-site-selection.html
I am happy to announce that I have finished a white paper on the topic of Data Center Site Selection. I welcome any and all comments and hope it is informative and helpful.
If you decide to link to the paper, I would ask that you link to this post instead of directly to the PDF.
Link: http://datacenterlinks.blogspot.com/2007/10/dc-site-selection.html
Rath Consulting
October 2007
October 2007
Labels:
site selection
Sunday, October 14, 2007
Good Code and Computing Overhead
Alistair Croll over at Earth2Tech has an excellent article on coding practices, coding complexity and the effect it has on the data center. It shows how complex our applications have come and all of the different components that go in to making it run.
I'm not sure I could do it justice in discussing or quoting, so check it out here.
I'm not sure I could do it justice in discussing or quoting, so check it out here.
Labels:
applications,
coding,
Green
Netapp DoD Data Migration
Enterprise Storage Forum has a pretty interesting story on the Defense Contract Management Agency (DCMA) going from 18 data centers to 2. They virtualized the middleware and consolidated data with Network Appliance's Virtual File Manager (VFM).
Check out the article here
In addition to consolidating the servers, DCMA also needed to set up a common file system that would work across the enterprise. For this it created a File Area Network (FAN) using software and storage appliances from Network Appliance. DCMA has more than 300TB of storage.I think we will continue to see stories like this as large projects are under way to consolidate, virtualize and setup common file systems and platforms across the enterprise.
Check out the article here
Labels:
FAN,
netapp,
storage,
virtualization
Monday, October 08, 2007
Server Farm Goes Solar
Server farm company AISO (Affordable Internet Services Online) has built a 2,000 sq. ft. facility, banked with solar panels that generate 12 kilowatts of electricity. Located south of Las Angeles they claim to be 100% solar powered.
Check out the CNN article here and AISO site with further details on the implementation here.
To slash energy consumption, AISO.net switched from 120 individual servers to four IBM blades running virtualization software that lets one computer do the work of multiple machines. The cooling system cranks up for only about 10 minutes an hour, and when the outside temperature drops to 60 degrees, air is sucked into the building to cool the servers. Solar tubes built into the roof illuminate the facility's interior.
Check out the CNN article here and AISO site with further details on the implementation here.
Subscribe to:
Posts (Atom)