The Environmental Protection Agency’s Energy Star program is trying to collect information from anyone with a data center to help the EPA get a sense of what’s happening nationally with data center energy consumption. In this video from the Uptime Institute Symposium, the EPA’s Andrew Fanara discusses how data center managers can participate in the program, by measuring their energy efficiency in a standardized way.

You can download the forms for the National Data Center Energy Efficiency Information Program from the EPA’s data center Web site.

Sydney, Australia based-Ideas International Inc. has launched an open source-style website to compare and rate the functional capabilities of blade servers on Monday, April 7.

The IT research and analysis company’s new site for Collaborative Product Evaluation looks at medium-sized blade servers and will include enterprise-level blade server data by mid-summer, said Jim Burton, the vice president and senior analyst for entry-level servers and blades at Ideas International.

The site lets users compare various components of the servers that fall under the umbrellas of platform functionality, environmental footprint, virtualization functions, reliability, serviceability and manageability, and deployment considerations.

The information is based on the hardware specifications, interviews with end users, and performance data, Burton said.

“We establish the appropriate ratings, but it is an open source-style website, so users can affect these ratings too,” Burton said. Of course, Ideas International give the user feedback a credibility rating, so only statements supported by concrete data can actually bring a rating up or down, he said.

The site is pretty handy if you are on the market for blade servers, especially because the site allows you to make comparisons based on your priorities. If you need power efficiency, you can compare boxes based on that alone. Same goes for factors like “green-ness,” cost, networking and so forth, said Burton.

Ideas International also has evaluation sites for x86 virtual machine platforms and plans to create evaluation sites for Unix-based systems and Linux in the near future, so keep an eye out for those.

This is pretty impressive; colocation provider 365 Main has been taking advantage of Pacific Gas & Electic Corp.’s (PG&E) power saving program and saved $54,000 in utility costs at its San Francisco data center in 2007.

In all, 365 Main saved 7,477 kWh in 2007 by curtailing power usage below its energy-consumption baseline.

How did they do it? The first step 365 Main takes is inviting their utility provider, PG&E, into their data center at the start of each year for an energy audit to find areas where efficiencies can be added, said Miles Kelly, VP of corporate strategy at 365 Main.

“For example, this year we expanded the areas that utilize motion controlled lighting in the data center and also reinsulated the condenser water lines for the buildings massive air conditioning system. We also reduce lighting levels in public areas during peak days,” Kelly said.

The data center host also adjusted their weekly and monthly generator test schedules to peak days, which reduces their utility consumption by about 8% during test periods. “This adjustment of the testing schedule allows us to reduce utility consumption without ever affecting the reliability or N+1 redundancy of our power system,” Kelly said.

PG&E has gotten a lot of attention this past year for its part in promoting power savings in data centers. Their Critical Peak Pricing (CPP) program encourages data centers to cut back power consumption by offering seasonal discounts to customers that reduce or shift their energy usage away from peak periods.

In addition to savings incentives, PG&E also works with companies like IBM to consolidate servers, reduce heat and cooling requirements in data centers.

And 365 Main has been pretty aggressive in the “green” data center effort as well, if not for the public relations benefits alone. Earlier this year, 365 Main promised to build all its future data centers in line withLEED certification, which is basically a nice label the U.S. Green Building Council gives to companies that make an effort to be environmentally responsible. The standard is said to be tough for power hungry data center to meet though, and is most commonly achieved in buildings with lots of office space.

There’s been tons of clamour from environmental interest groups warning data center managers that if steps aren’t taken to reduce consumption, power availability problems will continue to grow and costs will rise, and several vendors and industry organizations have developed online tools to measure data center efficiency and promote power savings.

One of the many tools is from West Kingston, R.I.-based American Power Conversion (APC), a power and cooling services company, which has a free Web-based tool that rates data center power efficiency.

So, come on people. Let’s save some power.

Measuring dollars to servers: A lot of the talk about data center efficiency is about the costs. Energy and data center real estate cost a lot of money. But what are the servers worth? How much money is the computer making for your company? Jonathan Koomey, from Lawrence Berkeley National Labs and Stanford University, developed the recent measurements of server energy use. He says we need to prod industries to come up with a value for servers or computing units rather than just focus on the costs. In this podcast from the Uptime Institute Data Center Design Charrette, he describes how that could be accomplished.

Pitt Turner from ComputerSite Engineering Inc. and the Uptime Institute explains different ways to measure IT energy consumption in this podcast from the Data Center Design Charrette in Santa Fe, N.M., last week. Turner weighs the pros and cons of measuring at the uninterruptible power supply, or UPS, versus the power distribution unit to determine how much energy is going to servers and how much power is going to the data center infrastructure.

SANTA FE, N.M. — Last week at the Uptime Institute Data Center Design Charrette, I spoke with Roger Schmidt, distinguished technologist at IBM and chairman of ASHRAE Technical Committe 9.9 about ASHRAE’s role in standardizing a process for data center managers to measure their physical infrastructure energy use. A lot of data center managers want to reduce energy consumption but don’t have the tools or processes to measure their usage. In this podcast, Schmidt outlines ASHRAE’s role in dealing with this problem.

Data center design consultants, analyst firms and industry groups have lobbied the U.S. Green Building Council to develop a data center standard for its LEED (Leadership in Energy and Environmental Design) rating system for green buildings. But to no avail: USGBC has no plans to address data center facilities. The current LEED rating system does not address the particular needs of the data center environment — you don’t get LEED points for operating your data center efficiently, but you can get one for a bike rack — old news.

Nonetheless, more companies are looking for ways to score points on corporate social responsibility checklists, and municipalities and governments are turning to USGBC’s LEED and mandating it as a design standard. The metric is available, and people get it — imperfect or not.

The LEED system is based on several “green” practices, and if you do things right you get points. So why not copy the LEED format which has been widely accepted and apply it to data centers? Give data centers three points for using server virtualization for server consolidation, three points for implementing blanking panels and sealing off bypass airflow.

Some groups like the Green Grid are looking into this type of points system for the future. Is this something that will work? What are the drawbacks?

While it looks like IT-centric organizations are going to be forced to reinvent the wheel with the green data center certification, it may not be too late to get USGBC on board. Where IT organizations haven’t had much luck lobbying USGBC, you might. End users that are looking into LEED-certified data center facilities need to put pressure on the organization as well.

Check out our LEED data center articles:

UPDATE: I was talking to Joe Prisco from IBM this week and he has developed a points-based system for determining data center energy efficiency or green-ness. His checklist (and how to use it) will be published in the December issue of the ASHRAE journal magazine. Keep your eyes out for that in your mailbox, and we’ll try to get a link to an electronic copy up as soon as it is available. Prisco hopes the USGBC or The Green Grid will adopt his recommendations and ASHRAE may publish a book in the future on his work.

This week I am reporting from the Uptime Institute’s Data Center Design Charrette 2007, and I can tell you this is not a typical data center conference. Last night’s kickoff event was a panel discussion that took place in a church. We sat in weathered wooden pews in the New Mexico Museum of Art in Santa Fe and listened to the best minds in the IT industry outline the challenge to reducing data center energy consumption.

The attendees are data center managers, vendors and consulting engineers. The plan is to discuss the controversial issues in greening the data center and generate end-user feedback on new technologies and metrics.

There are three discussions going on at this event:

1. One group is delving into the issue of defining the benefits of alternating current (AC) versus direct current (DC) power distribution in the data center.

2. Another group is tackling the recommended temperature and humidity tolerance for servers. Can servers withstand broader ranges of cooling and humidity than currently recommended by vendors and the American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE)? Can we harden the hardware to withstand less energy-intensive cooling? And what are the operational cost benefits?

3. Lastly, a group is responding to the Uptime Institute’s most recent green data center measurement strategy, which lays out four metrics for developing a holistic look at energy consumption.

Check in throughout the week for more reporting on the findings and user responses to these data center design questions.

Data center facility costs have grown from the traditional 1% to 3% of IT’s total budget to 5% to 15% today, the Uptime Institute reports.

At the same time, traditional IT total cost of ownership (TCO) calculations and cost justifications have either ignored or significantly underestimated the “true TCO,” because they fail to correctly capture and allocate both the capital and operating expenses of a data center in their planning analysis.

The problem with underestimating energy costs is that when CIOs order new hardware, they later discover that they lack the infrastructure capacity to handle it, the Uptime Institute reports.

For example, a major global financial institution purchased $15 million worth of blade servers, only to discover that the new or upgraded facilities necessary to handle the power and cooling requirements required an additional $50 million in unplanned and unbudgeted investment, said Ken Brill, founder and executive director of Uptime Institute.

IBM’s Deep Computing and Data Center Capacity on Demand business units commissioned the Uptime Institute to develop a True TCO Calculator and a white paper.

The institute will present its white paper, “A simple model for determining true total cost of ownership for data centers,” at its annual Design Charrette 2007 held this week in Santa Fe, N.M. The white paper and the associated True TCO Calculator offer a comprehensive framework for modeling the real lifecycle costs of building and operating a data center, the institute says.

The TCO paper and calculator looks at site infrastructure capital costs, computer equipment costs, energy bills, and other operating expenses to characterize the estimated costs to build and operate a new data center.

Also, the Green Grid released downloadable data center efficiency metrics that look pretty useful.

It sure would make life a lot easier if the data centers we manage existed entirely within two dimensions; which seems to be the world that server manufacturers think we live in. To them, the only two specifications of size that matter are height and width. They could care less about that forgotten dimension, DEPTH.

Every time a new server appears on the market the very first spec I check is depth. Width is a given, and heights are limited to a very narrow range (1U, 2U, etc), but the makers of gear destined for the data center seem to think they’ve been given a free pass go as deep as they please. This drives me and I can only assume my peers in the community, crazy! Nothing would please me more than to get a bunch of Dell, IBM, HP, Apple, etc server hardware engineers into a room … and then flood it with Halon. Oh, OK maybe not halon… I’d probably hit them with FM200 and then when they come to take them for a tour of a data center and show them the error of their ways.

My biggest beef here is the 1U servers that seem to be growing to absurd depths. The worst offenders I’m dealing with at the moment are Dell’s 1950 and Apple’s latest version of the Xserve. Both arrive at 30″ (76.2cm) or longer. I’m sure there are others that have reached these lengths too. They have roughly the same form factor as the flight deck of an aircraft carrier. 1U x ~18″ x REEEEAAAAALLLLLLLYYYYY LOOOOOOONG. Attach a catapult and you could be launching Maverick and Iceman in their Tomcats to intercept the inbound bogeys.

When 1U servers started appearing they were rather compact, akin in form factor to your average Ethernet switch. 1U x ~18″ x ~12″. Some, such as the old Cobalt “RAQ” web servers (remember those?) could be stacked on both sides of a 2-post rack for a total of 84 servers in under 6sq’ of floor space. When the larger players started shipping 1U boxes, they ranged in depth from 20″ to 24″ (51cm - 61cm) on average. This was the same, or a bit longer than the average 2U and 4U boxes that preceded them, but still manageable. They could fit in 2-post or 4-post racks. But about five years ago 1U servers started getting longer and longer.

How does this affect us? Density of course. While having nothing but 1U servers would seem to be a step towards higher density that is really only true if you live in a two-dimensional world. If your servers are now over twice as deep as they once were entire rows of datacenters have to be moved farther apart to accommodate them. Logically if your rows of racks are farther apart, the number of racks you can install in your datacenter shrinks.

Additionally cabinets keep getting deeper to accommodate these longer and longer servers. It used to be that any server could be mounted in a 2-post rack. Cabinets were only needed if extra security was desired. Now the manufacturers of server EXPECT you to mount them inside cabinets. No flexibility in mounting is offered… except maybe cage nuts or tapped.

I remember when a cabinet averaged 32″ (81cm) deep. Many of today’s servers won’t even fit in a 32″ deep cabinet. Well, they might fit, but you won’t be able to close the doors anymore! The cabinets we’re buying for our data center are now 42″ (107cm) deep. That adds almost two feet (61 cm) to every aisle in the facility. That means you can fit fewer aisles. By my top-of-my-head math that means you lose two full aisles for every 5000 sq’ of data center. Depending on the number of racks-per-aisle, that can add up to a LOT of servers you lose by having these outrageously long boxes.

There are many facilities, primarily older colocation datacenters that limit how much power-per-rack you can use, so frequently you see 42U cabinets with MAYBE 14U of space that is usable. Why even bother with 1U servers then? Your cooling is messed up by all the empty space. You might as well go back to the big 4U servers of yesteryear and pack ‘em in. But nobody makes those anymore. The only time you see servers larger than 1U is when they are serious power hogs, packed with drives and CPU. So we’re back to square one.

Two recent events triggered this rant:

A customer sent a new Apple Xserve to us to replace their old Apple Xserve. The old one was a G5 unit, the new one a Dual-Core Xeon unit. Both we and the customer thought this would be an easy swap… power down, unplug, and pull out the old one, slide in the new one plug in and power up. Minimal downtime. Unfortunately the new one is two inches longer, the ports (network and power) have swapped sides, and the rack mounting hardware is completely different. What should have been a 5 minute operation turned into a multi-hour ordeal.

The next event, which sent me over the top is a new client had 32 Dell 1950’s shipped to our facility, along with an APC Netshelter cabinet and powerstrips to plug it all in. Upon arriving for assembly we noted that the rackmounting rails provided by Dell stuck out in the back of the 32″ (81cm) deep 1950 by an additional 3″ (7.6cm). So now the total depth of the servers amounted to 35″ (89cm). There was no longer enough room at the back of the cabinet to mount the power strips. Comparing these to previously installed Dell 1950 servers they did not have rails this long. What does this mean? Is Dell planning on making their next rackmount servers even LONGER? How long before we see 36″ long servers?

Do server designers ever try to actually rackmount their gear? Do they account for cables, power strips, etc? It seems to me that the unrestricted lengthening of the standard 1U server is becoming completely counter-productive to the original design goal of the 1U server, namely density of computing in the minimum amount of space. They’ve gained rackspace at the expense of usable FLOOR space. In the balance sheet of datacenter operations floor space is WAY more expensive than rackspace. I want my floor space back.

Does this frustrate you as much as it frustrates me?