Server Specs - A SearchDataCenter.com blog

Server Specs:

 

A SearchDataCenter.com blog


The blog for all things data center, including, design and infrastructure, Unix, Linux, mainframes and x86 servers, power and cooling efficiency, information technology (IT) service management, server consolidation and virtualization and more.

Explosion at The Planet wins them 3,500 new customers?

On May 31, an explosion at Web hosting company The Planet affected about 7,500 customers, 2,600 of which experienced downtime for at least 3-4 days.

Between June 8 and July 8, The Planet gained about 3,500 new customers, according to Netcraft, which was the third-highest gain of the 50 hosters that Netcraft tracks.

So what gives?

I came across this little tidbit via Rich Miller, who wrote about Web hosters’ uptime over at Data Center Knowledge. That got me poking around the Netcraft Web site, where I found the section about “Sites on the Move.” Seeing as we had covered the electrical explosion at The Planet, I was curious how many customers they lost in the aftermath. They did lose quite a few — almost 900 — but their net change in customers was around 3,400 on the positive side, something I certainly wasn’t expecting.

A couple possible explanations. Management at The Planet kept an open dialog throughout all the downtime, which for some customers was almost a week. Doug Erwin, the company’s CEO, did two or three podcasts that they posted on The Planet’s Web site, detailing the reasons for the outage and any updates on what the company was doing to fix the problem. And one of The Planet’s message boards was dedicated to updates on the problem, which were quite frequent shortly after the explosion, and then waning off as more customers got back online.

Another, possibly simpler explanation? Many of The Planet’s customers are just looking to get their personal Web sites or some simple business Web sites online. As a result, they don’t do much research into the Web hoster of choice, and it’s fair to say that many of the 3,500 new customers probably didn’t even know about the explosion.

Cloud computing is the future for data centers; resistance is futile

http://www.research.att.com/files/grid_computing_technology.gif

I noticed a common theme at the string of computing conferences I’ve attended in the past couple of months: The future of the data center is going to be cloud computing, and resistance is futile.

I heard this from VMware Inc.’s President and Chief Executive Officer Diane Greene during her keynote at the JP Morgan Technology Conference in Boston in May, and the point was driven into the ground during the Enterprise 2.0 Conference there in June. I heard these predictions repeated during the annual Red Hat Summit and the USENIX 08 conferences, also held in Red Sox Nation last month.

Major league players in the data center space like VMware Inc. are putting their efforts into cloud computing because of predictions that it will eventually be the mainstream way information is handled and software vendors are starting to introduce products to manage cloud computing environments.

David Patterson, a professor of computer science at U.C. Berkeley, said during his keynote speech at USENIX that cloud computing is part of the data center evolution already under way.

“In addition to the processor evolution [from single-core to dual- and now quad-core processors], on a larger scale, there are a number of changes happening in the data center; flash memory is replacing mechanical disks, we have software as a service, and utility computing [a.k.a. cloud computing] is being used to outsource the data center,” Patterson said.

The advantages of cloud computing are clear, he said.

“With cloud computing, you put $0 down for your own data center, and pay as you go, and there is no penalty for scale up, which happens instantly. It allows fast scale up with no dead or idle CPUs, and no provisioning is required,” Patterson said.

This is especially appealing to data centers that have maxed out their power resources, but need to increase their infrastructure.

Though cloud computing is considered an immature technology, it really isn’t. The chief architect of the Xen project, Ian Pratt, said during his session at USENIX, called Xen and the Art if Virtualization, that the folks at Cambridge University who started the XenoServer project with him back in 1999 were architecting it under the cloud computing concept.

Though their ideas about what the cloud would look like differ from what we see today, the concept was similar: Develop a public infrastructure for wide-area distributed computing that can be used by people across the world.

“We originally thought there would be data centers all over the world, and clients would be able to choose a location, perhaps close to another IP address they wanted to interact with,” Pratt said. “The other difference is, we thought the machines would be owned by many different merchants, and there would be a broker acting as a third party recommending the different vendors, and those brokers would take a fee.”

Instead, we have companies like Amazon.com, Google and Salesforce.com offering the complete cloud computing environments , but Pratt expects this to change.

“I think we will see cloud computing move in the direction where it will become more open instead of all of the hardware, software and networking being located at and owned by a Google or Amazon.”

Today, most cloud computing providers host x86-compatible applications on virtualized servers, and most support only the Linux OS, according to Cambridge, Mass.-based Forrester Research Inc. To keep costs low, many cloud providers use a Xen-based hypervisor. Charges for usage are usually based on CPU hours, gigabits consumed and gigabits per second transferred rather than on a monthly service fee.

Specifically, Amazon charges 10 cents per compute hour used and 15 cents per gigabyte of storage. According to Forrester, that translates into about $70 to $150 per month for a fully utilized Amazon server, versus the average $400 a month that it costs an enterprise to run a server.

The benefits aside, IT pros are apprehensive about taking their mission critical apps out of their secure data centers and putting them into something as translucent sounding as cloud computing. This fear was quite evident during the Enterprise 2.0 conference event called “An Evening in the Clouds.” A panel of IT pros sat and listed to Google, Amazon and Salesforce as they fluffed cloud computing, and then they voiced their many concerns.

Is it secure? Is it reliable? Does it perform better than my existing data center?

The answer from all the cloud computing providers was, of course, a resounding “yes.”

But not all applications are available in the cloud, so it isn’t for every company. The cloud computing environment also lacks government standards, which makes some users nervous.

“I wouldn’t suggest moving all of your apps over to the cloud today, but hopefully one day all will be right in the world,” said Jeff Keltner, the business development manager at Google Apps.

Find the right data center colo

Data Center Map is a nice Google mashup that maps colocation and hosting companies throughout the world. Enter a location, such as Chicago, and the site will hone in on all the facilities in that area. It’s pretty handy if you’re looking to outsource some or all of your data center infrastructure and would like to do it close to home.

The site is run by ActiveWebs, a Danish web hosting company, and looks to be funded mostly by Google ads. Most of the listings are in the U.S., and the one for Chicago includes 350 East Cermak, run by Digital Realty Trust, which we did a story on recently for its LEED certification.

This is also a good site for those managed hosting and colo companies out there. You can get your place listed for free here.

Peak 10 expands to Georgia

Data center operator Peak 10, Inc.announced the acquisition of a 33,000 square foot facility in the Atlanta, Georgia suburb of Norcross last week. 

It has acquired a 33,000-square-foot facility in Norcross, a suburb of Atlanta. A third of the property has already been outfitted for use as a data center and the company has room to grow inside the space, according to reports.

The company runs data centers in Florida, North Carolina, Kentucky and Tennessee. In February, Peak 10 entered the Richmond, Va. marketplace with its acquisition of data center and managed hosting operator, bayMountain. 

The company operates eleven data center facilities with a customer portfolio that includes Global Knowledge, Pergo, Churchill Downs, LendingTree and the Jacksonville Jaguars. 

The new facility, which is being upgraded, will be fully operational in September 2007.

Amazon: Data centers are a pain in the SaaS

Are data centers worth the trouble?

SAN FRANCISCO, CALIF — Tuesday, August 6 2007 at the Next Generation Data Center Conference, Amazon.com Chief Technology Officer, Werner Vogels lead off the event with a keynote outlining why he hates data centers.

According to Vogels, IT trade rags are telling you how cool and exciting data centers are, with examples of high profile companies investing vast amounts of time, money and intellectual effort into engineering them.

The elephant in the room, according to Vogels, is that building data centers requires technologists and engineering staff to spend 70% of their efforts on undifferentiated heavy lifting.

Vogels suggests companies use their staff for building things that can differentiate them from competitors, rather than banging their heads against the oftentimes frustrating, unprofitable business of data center infrastructure maintenance.

Vogels used the recent generator failure at hosting company 365 Main as an example, explaining that even the best data center infrastructure plans fall through. He noted the complexity of UPS systems, data center fire suppression and cooling — and asked the audience why a company would want to be responsible for maintaining such sophisticated equipment and systems that have nothing to do with distributing their products.

“And we haven’t even talked about bandwidth. Network is this dirty little secret,” Vogels said. “If you run big data centers, you worry — can I get enough bandwidth going out of our data centers? Data centers are not only limited by the number of servers you can get in them, but by the bandwidth you can get out.”

After your infrastructure is set up, what about the servers themselves? “You will lose 8-10% of your disks per year — given” Vogels said. “You won’t lose your data, but your performance goes down the drain. Every year, you will be replacing 4,000 disks. You never knew that when you decided to start running your company.”

Having to manage multiple data centers is a true pain, according to Vogels. And you can forget about trying to scale these things.

Vogels’ presentation devolved into a blatant pitch for Amazon’s new SaaS products. But he raised an interesting question — are data centers worth the trouble? Daniel Golding, an analyst at Tier 1 Research, recently said only 50 global businesses — mainly in financial and Internet services — would build their own data centers while everyone else will outsource the task in the future.

Let me know what you think in the comments section.

Equinix coming to Europe

Equinix announced today that it will buy IXEurope Plc, a European data center colocation company, for almost a half-billion dollars.

According to the Equinix press release, IXEurope has 14 data centers that make up almost 400,000 square feet of data center space. The $482 million deal brings Equinix onto the European continent; the company is already spread out across the United States and eastern Asia.

The move expands Equinix’s total footprint to more than 3,000,000 square feet of data center space. Just this week I interviewed an executive about the unique Equinix colocation data centers.

Choosing a third party for a data center strategy: Ask the expert-Charles King

Question from user:
We are a growing company and need a 3rd party to put together a long term data center strategy. Should a company our size build a tier 1,2,3,4 data center? What else should we be looking for?

Answer from Charles King:
Let’s take your second question first. What you should be looking for is a data center strategy/solution;
1) adequate enough to satisfy your current business needs and technical performance requirements, and
2) flexible and powerful enough to meet your projected future requirements.
Before proceeding, your business and IT organizations need to sit down in a quiet space and hash out their relative hopes, needs, and expectations. Take your time, don’t mince words, and make sure that everyone is engaged in the process. You’ll be living with the results for a long time to come.

After your internal processes conclude, bring in third party consultants/vendors including preferred vendors and companies with good reputations for data center design/implementation. Keep your eyes and minds open. Long term strategizing offers some great opportunities to consider and embrace ideas and solutions that you might never have thought of otherwise.

The differences between Tier 1-4 really come down to matters of availability, reliability, and cost. It isn’t possible to make blanket pronouncements without knowing more about your budget, business needs, and the platforms and applications you need to support. Good luck!

More from Charles King’s Ask the expert page.