This blog post was written by Mark Schlack, vice president of editorial, TechTarget.

What kind of network works best for high-density virtual machine (VM) farms? Can you run OLTP databases on VMs? If you put your email server on a VM, what should you beware of?

It’s hard to find answers to those kinds of questions, and answers often start with “It depends.” But the questions are important, indeed critical, for some shops as they scale up. For that reason, we are launching an e-zine this week called Virtual Data Center.

If you’re looking for a deeper dive into some of the thornier questions about virtualization and the new data center being built around it, this is for you. Take the first issue: It features an article by a veteran integrator of Oracle and VMware that makes the case for putting production databases on virtual machines. The article gets into what you need to do to make that work. Similarly, a second article gets into creating a storage architecture for VM farms.

Our goal is to create, magazine-style articles that can go further than tips or blog posts in analyzing these issues. It’s free and will appear six times a year. Each issue will address an application area and a technology issue. The authors will be experts, frequently with direct hands-on experience.

We’ll also follow up articles with blog posts and survey research that’s part of each article. You can take our survey on virtual databases here as well as our survey on storage in virtual environments.

Northern California utility Pacific Gas and Electric Co. has made headlines by finding novel ways to offer rebates for energy efficiency in the data center. Last week PG&E hosted utility companies from all over the country to brainstorm ideas for new rebate programs and other methods to curtail IT energy consumption.

According to the PG&E Website, the Utility IT Energy Efficiency Coalition comprises over 24 utilities from across the US and Canada that are primed to address the high tech, data center, and IT infrastructure markets. California utilities are well represented, with Southern California Edison, San Diego Gas and Electric, the Sacramento Municipal Utility District, City of Palo Alto, and Los Angeles Department of Water and Power attending the meeting. Utilities from the Pacific Northwest, Texas, New York, and Canada also participated.

We talked to PG&E’s Mark Bramfitt, supervisor of the customer energy efficiency program for the high tech market about the programs that they’ve had in place so far. Surprisingly, the server virtualization program hasn’t been quite as sucessful as I would have imagined. “The uptake on the virtualization program is a little slower than we wanted,” Bramiftt said. “We’ve received 60 applications in so far.” PG&E has had a number of calls from customers that say “we just did it”. But unfortunately, customers need to come to PG&E before a virtualization project to get the funding. Bramfitt is working on offering a rebate to customers so they can get incentives after the fact.

On the upside, PG&E is seeing a lot of success with its new construction incentives. The Bay Area is currently experiencing a data center construction boom. And Bramfitt is convincing many of them to install air-side and water-side economizers. For more on economizers, check out our case study on United Parcel Service.

“We’re about to pay a customer a $1.4 million incentive [for economizers],” Bramfitt said. “It’s going to be one of the biggest checks we’ve ever written for a new construction.”

MTechnology, a research firm that runs probabilistic risk assessment analyses of electric power sources, has released a study finding that flywheel-based uninterruptible power supply (UPS) systems are more reliable than the more common battery-based UPS during short outages of 10 seconds or less.

The study was paid for by Active Power, a flywheel-based UPS company, so you can take the conclusions for what you think they’re worth. Martin Olsen, the product manager and development director at Active Power, said that they “made it very clear that (MTechnology) would be doing the study, and to make it as objective as possible. That’s what they do for a living.”

Flywheel-based UPS systems have gained some traction in data centers as an alternative or complement to battery-based UPS. Terremark, a large data center colocation company, just recently installed flywheels instead of batteries at a new campus in Virginia. How it works is the primary utility power gets the mechanical flywheel spinning. When the utility power cuts out, inertia keeps the flywheel spinning at thousands of rotations per minute. That rotation is harnessed into power that can support the data center for short periods of time until either the utility power returns or the switch is made to backup generators.

The MTechnology study compared a flywheel UPS to double-conversion battery UPS and found that the flywheel was almost seven times more reliable than the battery UPS during short outages (10 seconds or less). During longer outages, failure rates were about the same.

The people I speak with about virtualization projects always list the same reasons for going virtual; they don’t have enough space in their data center to add more physical servers, they can’t afford power and cooling bills, they want to consolidate physical machines, and they want to consolidate physical people.

That’s right; the majority of people I speak with - employers and employees alike - say nonchalantly that they deploy virtual machines to avoid deploying more IT staff. While this is great for corporations, it doesn’t sound so good for IT job seekers.

A few examples; I went to a VMware Inc. User Group meeting in Boston on March 27, and one user gave a presentation about the virtualization project he oversaw at the paper manufacturing company called SAPPi in Maine.

“One reason we wanted to virtualize is we needed to lower our IT headcount. We needed to get rid of high end support and just keep desktop support,” the systems engineer/presenter said.

Similarly, at the growing law firm Owen Bird Law Corp. in Vancouver, British Columbia, Stephen Bakerman, the sole IT staffer, went with Virtual Iron virtualization to avoid adding more physical servers and having to hire more staff to help him manage it all.

“The cost savings is probably $100,000, and the time savings for me are incredible. Once everything is virtualized, I can run everything from my desktop remotely from my office or at home. I don’t have to hire someone else, and I would have if we kept adding servers,” Bakerman said.

Another company called QualComm Inc virtualized 60% of its data center environment and saw a similar side effect. At the VMware Virtualization Seminar Series in Providence, RI Feb 26, VMware presented a case study of the wireless technology company showing how it started with 1,200 servers and consolidated down to 100 (12:1 ratio) physical servers, increasing data center space and cutting back on power and cooling. That’s great. And the cherry on top? They have not had to increase their IT staff at all in 2.5 years.

Sure, I get how cool virtualization is, and the benefits it brings from a savings and management stand-point, but is anyone else concerned those IT college kids who dream of days spent engineering systems won’t be able to find a job? or is anyone worried about those system administrators who might get consolidated from many to few along with their servers?

I’m interested in hearing from IT folks; is virtualization leading to a virtual job market?

Organizations ranging from corporate entities to the federal government are simultaneously, furiously working to fill the gaping void in the green data center certifications and awards space, striving to replace LEED as the de-facto standard for green data centers.

The proposed accolades run the gamut from professional development/personal achievement awards due to be announced by The Uptime Institute this month, to official stamps of approval from the U.S. Department of Energy.

Ben Stewart, senior vice president of facilities at the hosting firm Terremark, has been watching the development closely. According to Stewart, once a credible certification is available, hosting companies will have to pursue them to be competitive.

“We’re already doing things toward that end,” Stewart said. “We’re monitoring what’s going on through the Green grid, The Uptime Institute, and the EPA… so when the programs do become available, we’re able to put our signature on the bottom and submit the paperwork.”

On the other hand, Stewart doesn’t expect the rest of the data center community to be quite as aggressive, simply because they won’t have the same benefit. “For companies like us and [hosting company] 365 Main — being green, comparing ourselves to the rest of the industry and making ourselves better is good for business,” Stewart said.

But colocation hosting data centers are a small percentage of the data center market, and Stewart said, unless the utilities offer more incentives, the majority of data center operators aren’t going to jump through hoops unless there is something in it for them.

“We’re trying to attract customers to our facility, to show we’re leading edge,” Stewart said. “With a company like Citibank, people don’t equate them with their data center.”

Stewart isn’t your typical facilities guy — he’s definitely leading edge, and he’s about to take that ethic to the next level. “We’re building a new data center in Amsterdam at Schipol Airport and we’re looking at using the waste heat to de-ice the runways,” he said. “Europe is so far ahead of us on this stuff — they’ve given us five ways to put our waste heat to use rather than exhaust it. We’re learning an awful lot.”

Green IT = Smarter air conditioning
Data center efficiency isn’t real sexy when it comes down to it — unless you think Plexiglas, bristled grommets and caulk are sexy, in which case, this is definitely the Web site for you.

Primarily, the organizations pushing for greener computing are focusing on the infrastructure efficiencies in the data center — whittling away at the amount of cooling needed per unit of computing power. And that’s about as sophisticated as it gets.

There are definitely bigger fish to fry (like reducing the amount of servers needed for a certain job, thereby reducing the amount of overall power consumption), but infrastructure is one of the only places in IT where people seem to have any agreement.

The holy grail of green IT is determining what amounts to “useful work”. It’s pretty simple to determine how much power Server X uses, and how much power it takes to keep it cool. But how do you measure the usefulness of the work Server X produces?

How much do you lose to bloatware (inefficient code)? How “useful” is the server that runs an application twice a month? And what determines “useful” anyway, revenue dollars, per CPU cycle, per watt?

You can bet these questions will be debated for years to come.

It’s one thing when you’re building a new data center to be worried about whether the gen-sets will get there on time, or whether the utility will be able to provide you enough power, or if you’ll get the go-ahead from the fire marshal that you need.

It’s quite another to be delayed because 150 feral cats are standing in the way.

That’s the story the Los Angeles Times had earlier this week. The county government was planning on tearing down an old, abandoned Downey, Calif. building that it owned to put up a new state-of-the-art data center complete with environmentally friendly features like a green roof and berms to handle storm runoff.

But the felines are deep in the middle of a defiant sit-in. And you know how cats are. They don’t listen very well.

As the story goes, construction on the building isn’t expected to start for at least another year. Still, when designing a new $68 million county data center, it’s never too early to start planning, especially when the planning involves displacing scores of feral cats.

“We’ve been back and forth with [the county] trying to find a resolution,” said Linda East (a feline lover who regularly feeds the feral cats). “We all know they have to be relocated. It’s just, where do you put so many cats?”

This could end up being a happy story for all. The county is working with the cat feeders to get them relocated, possibly to local barns where they can fight off the rat problems there. That would probably be a better spot for them than inside a tangled web of cables under the data center raised floor.

The photos were taken by Francine Orr at the L.A. Times.

The federal Environmental Protection Agency, which is in the midst of developing an Energy Star rating for servers, also has its sights set on creating one for data center facilities.

The Energy Star program is a familiar one now to American households — they’re the yellow stickers on televisions, washing machines, ceiling fans and dozens of other appliances that show how energy efficient they are. But a lesser known program is the Energy Star’s rating system for commercial buildings. And now the EPA wants to bring that system to computer rooms in a program it is calling the Data Center Infrastructure Rating.

To develop it, the EPA must collect 12 months of data on the energy use of existing data centers, and it’s looking to the industry for help. It is asking organizations to monitor and submit details about their data center energy use starting in the beginning of June and lasting until June of 2009. All the companies participating will be kept anonymous for the purpose of the study, and will be required to submit energy use data to the EPA on a quarterly basis from an Excel spreadsheet.

All of this data center energy use data the EPA collects will then go into its formation of the Energy Star data center protocol next year. For more information, visit the Energy Star’s data center site.

Intel Corp. introduced two low-voltage 45 nanometer (nm) quad-core Xeon processors today that run at 50 watts, or 12.5 watts per core, and frequencies up to 2.50 GigaHertz (GHz).

The Intel Xeon Processor L5400 Series is built on 45nm manufacturing and a transistor formula that, combined, boosts performance and reduces power consumption.

The Quad-Core Intel Xeon L5400 processors are as much as 25% faster and have a 50% larger cache size than Intel’s previous-generation low-voltage Quad-Core Intel Xeon processors introduced last March, while maintaining the 50-watt thermal envelope. The quad-core L5420 and L5410 processors run at 2.50 GHz and 2.33 GHz, respectively, and have 12 megabytes (MB) of on-die cache and dedicated 1333 MHz front side buses (FSB).

Vendors supporting the L5400 and L5210 series include Asus, Dell, Fujitsu, Fujitsu-Siemens, Gigabyte, HP, Hitachi, IBM, Microstar, NEC, Quanta, Rackable, Supermicro, Tyan and Verari.

Next quarter, Intel will also begin shipping a new dual-core low-voltage processor with a 40-watt rating and clock speed of 3 GHz, with a 6 MB cache size and a 1333 MHz FSB.

The Intel Quad-Core Xeon processor L5420 is $380 per 1,000 units and the Intel Quad-Core L5410 is priced at $320 per 1,000 units.

In a recent podcast, Uptime Institute founder and executive director Kenneth Brill talked about the dire power situation today’s data center industry is in. Specifically, Brill said that Uptime research has found that the top third of all data center sites it looked at (meaning about 50 sites that averaged 60,000 square feet in size) had a 24% compound annual growth rate in power consumption in 2006 and 2007. That’s a huge jump from the 7.5% energy growth rate from 1999 to 2005 for those same data centers.

Why does this matter? In the report on data center energy consumption that the EPA sent to Congress in August, it reported that the energy growth rate in data centers would be 15.7% from 2006 to 2010, an increase it estimated would require the building of 10 1,000-megawatt power plants, which are nothing to sneeze at in terms of acquiring the permits and actually building the facilities. This was data that Brill said he previously ignored this data as “somewhat alarmist.” But with Uptime’s recent research of its own sites, he’s no longer doing that.

“I can absolutely tell you that the top third of data centers in the Site Uptime Network in 2006 and 2007 is experiencing a 24% compound annual compound growth rate in their power consumption, which is unprecedented,” he said.

Brill estimates that 30 more 1,000-megawatt power plants will need to be built by 2015 just to support this IT energy growth. Brill continued in his talk to say that there is no “technology silver bullet” that will make building data center facilities cheaper when looking at its power capacity compared to price. What he instead suggests is a “tuning up” of what users already have.

“There are opportunities for efficiency improvements all over, but it requires tuning up things and that is something that we as human beings seem to be constitutionally unable to do,” he said. “We seem to prefer buying new stuff instead of tuning up what we already have, and yet tuning up what we already have is the most profitable thing we could do.”

Intel Corp.’s Senior Vice President and General Manager, Digital Enterprise Group, Pat Gelsinger previewed Intel’s upcoming processor technologies this week, including details of a six-core processor due out later this year.

Gelsinger also detailed Intel’s new Itanium processor, codenamed Tukwila, as well as Nehalem and Larrabee, a future processor slated to have eight cores.

I’ll interrupt the oohing and ahhing here to note that Sun Microsystems Inc. has had an eight-core processor, Niagara, since 2006 and came out with an updated version, Niagara 2, or UltraSPARC T2, in August of 2007 for commodity servers.

But back to Intel’s big news; Intel plans to release its first 6-core, 45nm processor, code named Dunnington, later this year. The processor will feature a single-die with six cores and will be socket-compatible with the Caneland platform. Intel’s first 45nm processor, announced in November 2007, was a quad-core.

Dunnington will support FlexMigration technology, which supports live virtual machine (VM) migration across both 65nm and 45nm high-k Intel Core microarchitecture-based servers, so users who invested in 65nm quad-core Xeon processors recently won’t lose their investment.

Tukwila, meanwhile, is Intel’s next Itanium processor. With four cores, 30MB total cache, Quickpath interconnects, a dual Integrated Memory Controller and Remote Access Service features, the silicon holds 2 billion transistors and is expected to hold more than double the performance potential than current Itanium processors.

As for Nehalem, future versions will have from two to eight cores, with Simultaneous Multi-threading, resulting in 4 to 16 thread capability. Nehalem also supports four times the memory bandwidth than Intel’s highest-performance Xeon processor-based systems of today, with up to 8 MB level-3 cache, 731 million transistors, and QuickPath interconnects up to 25.6GB per second, Intel reported.

Meanwhile, Sunnyvale, Calif.-based Advanced Micro Device’s (AMD) 65nm quad-core Opteron processor, code-named Barcelona, will finally begin shipping in April after coming to a major standstill. The company told the world to expect shipments in September 2007, but discovered an errata and put off mass shipments of the processor.

AMD announced its plans for 45nm processors, code-named Shanghai, earlier this month and expects those quad-core processors to begin shipping later this year.