Energy Star Program for Data Centers

The EPA announced that they are expanding the Energy Star Program to include data centers; the measurements are expected to be finalized in June 2010.

The EPA is hoping that the new Energy Star rating for data centers will become a selling point for data centers. The new rating is based largely (but not completely) on the PUE (or Power Usage Effectiveness). William Kosik wrote an article in the September 2007 issue of Engineered Systems Magazine that explains PUE quite well and in detail.

Google talks about their efforts for power-efficient computing in their data centers in some depth; it’s very interesting.

IBM also announced just recently that they are building a new data center in Research Triangle Park where they will test effect of various temperature levels in the data center – and will cool it with outside air as well.

This is definitely an exciting time for data center power research; seems that there is something new every day.

Data Centers: Weta Digital, New Zealand

Weta Digital, the special effects company behind Lord of the Rings, King Kong (2005), X-Men, and Avatar is in the news again.

Data Center Knowledge has an article about their data center, as well as another one about it last year.

Information Management also had an article about it, as well as a blog post by Jim Ericson.

HP even has a video about their use of HP blades in their cluster.

Some of the more interesting things about their data center include:

  • The use of water-cooling throughout.
  • Using external heat exchangers to release heat.
  • Using blades in a clustered configuration.

This is just the beginning. While this data center is not as radical as the others discussed here recently, the data center is more in the realm of current possibilities. There are photographs in the current Data Center Knowledge article as well.

An Experimental Underground Data Center: Iron Mountain’s Room 48

Iron Mountain has converted an old mine in Pennsylvania to a computing facility, part of which includes an experimental energy-efficient data center that uses geothermal conditions to improve cooling.

ComputerWorld wrote an article about their tour of the facility, including Room 48 where the experimental data center is housed. The power distribution transformers and the air conditioning units are outside the data center, rather than inside it. It also relies on the extreme pressure differential between the hot and cold aisle to move the air, making the data center very quiet (in contrast to the usual data center).

The data center in Room 48 operates at between 70 and 72 degrees Fahrenheit, and operates 200 watts per square foot (more than 50% above the usual 125 watts per square foot).

This data center is truly remarkable.

A Data Center in a Silo

The CLUMEQ project is designing a supercomputer, and has several sites already built. One of these, a site in Quebec, was built in an old silo that used to contain a van de Graaf generator.

An article in the McGill Reporter from several years ago described the supercomputer installation at Montreal.

The new CLUMEQ Collossus (as the Quebec installation is called) was described in an article in Data Center Knowledge. The design has all of the computers (Sun blades) are in a circle with the core being a “hot core” and the cool air being drawn from the rim.

A Book Review: “Green IT”

The book Green IT: Reduce Your Information System’s Environmental Impact While Adding to the Bottom Line by Velte, Velte, and Elsenpeter is extremely interesting. Unlike some other books that might go in this direction, this is not a book of theory, nor of political change, nor of persuasion. This is a book for IT staff about how to create a “green” data center and more.

Because of the nature of IT, going “green” can mostly be summed up in one word: electricity. A vast amount of what makes an IT department “green” consists of using less electricity wherever possible. This includes such areas as the corporate data center, the corporate desktops, and much more.

However, the book also gives significant attention to the other big environmental impact of computing: paper. There are a lot of ways to reduce paper use, and this book seems to cover all of them.

The book is in five parts: part I explains why to implement conservation in IT; part II talks about consumption; part III discusses what we as IT users can do individually to help the environment; part IV covers several corporate case studies; and part V expounds on the process of becoming “green” and how to stay that way.

It would have been nice to see more information about how the authors exemplified their suggestions during the creation of the book. The only hint of any environmentally sound practices is the recycled paper logo on the back cover (100% post-consumer fiber). That leaves more questions: did they use thin clients? Did they work from home? Did they use soy ink? Perhaps lastly, where is the e-book?

There is a web site that is set up for the book, but the current breadth of the site is disappointingly anemic. Some of the best web sites for Green IT would be Dell Earth, Intel, as well as IBM’s Green IT and Energy, the Environment, and IBM web sites.

It was interesting to note that HP’s Eco Solutions web site is “heavy” compared to the others – that is, it requires much more processing power to display, and requires a lot more time to download – which translates into more power consumption to view the web site. In addition, IBM and HP are the #1 and #2 in Computerworld’s list of Top Green-IT Vendors – whereas Dell is #6… HP also topped Newsweek’s 2009 list of Greenest Big Companies in America (along with IBM, Intel, and Dell in the top 5).

Hardware Design and the User

A good piece of (computer) hardware shows attention to the user and to user interface design (although not in the software sense). I have had an experience in contrasts of late that show what a difference good hardware engineering can make.

I have been working with the Toshiba Portege M100 laptop, and have found its design to be “interesting” to say the least. The LED lights that describe all of the various details commonly found on the outside cannot easily be seen when the system is in operation: they are pointing towards the ceiling on the top of the open display lid. The mouse buttons are confusing: there is no left/right button – rather, the “right” button is on the bottom and the “left” button is on the top of the two larger buttons. The purpose of the two tiny buttons are unclear.

The batteries and their installation is also an interesting study. The latch to “unlock” the battery is a slider with a locking mechanism in the middle: it is hard to describe. You’ve never seen anything like it, and operating it can be, at least initially, mystifying. There is also no way to determine whether a battery is charged or dead by looking at it.

This machine, the Toshiba Portege M100, can be contrasted with the HP nc4010. Batteries on the nc4010 have a four-LED light display which not only shows the state of the battery, but also provides (for the battery wizards!) an error display (but good luck determining what the error displays are…). The batteries snap into place and are set to go; removing a battery is a matter of moving a spring-loaded latch right next to the battery that shows a battery symbol. The battery symbol is built into the case itself in relief: this prevents the logo from “rubbing off”. Similar symbols can be found for RAM, hard disk, battery #2 (travel battery), and keyboard.

The capability of using a second battery shows foresight on the part of the designers as well: there is no obvious way that the M100 could take a second battery.

Instead of a sliding catch to unlock the top lid like the M100, there is the more commonly seen pushbutton latch. Several LEDs are built into the front edge of the machine – on the corner, so that the displays can be seen both from the top and from the front – that is, these LEDs can be seen easily by the user whether the machine is in operation or not.

Even the logo on the top of the computer itself shows attention (or lack thereof) to detail. The logo on the Portege M100 is only readable to the user (who presumably owns the machine); the HP, like Apple, has their logo large and in the middle and readable to passersby when the machine is open. Apple took this one step further and lit up the logo!

Another common mistake is the port cover on the back of the machine. The Compaq Armada E500, for instance, like so many of its kind, has a large one that goes nearly the entire length of the back of the laptop. Toshiba uses a small one with no obvious way to open it: instead of pulling it down from the top, it is opened by pressing down near the hinge, though there is no description of how to do this on the machine itself.

In all cases, these “latches” or covers will often get broken off and disappear. The HP nc4010 has no cover/latch in the back – thus nothing to break off.

Once again, all ports on the back of HP nc4010 are labeled by labels in relief built directly into the plastic; the Toshiba M100 labels nearly all of them with painted on labeling.

Even the plastic itself shows an attention to detail: the M100 uses a silver-painted white plastic; the nc4010 uses black plastic with no paint. This means that as the machine gets older, the Toshiba M100 will show evidence of the white plastic underneath as the paint is worn away – and the HP shows none of this.

The HP nc4010 is not without its mistakes: there are several painted labels, and there is a PCMCIA insert that can be lost. On the nc4010 the speakers point to away from the listener to the left and to the right – the Compaq Armada E500, though bigger, put them in the front pointing directly up at the listener on the left and right sides.

This sort of engineering can be seen in other areas as well: how hard is it to repair the product, for instance? Many servers – Sun and HP servers in particular – can be easy to maintain. However, consider the Apple laptop: pulling one apart (to replace a hard drive for instance) can require removing 30 or more screws – a definite mistake. Does pulling the system apart require special tools – or any tools at all? Some servers can be maintained, at least in part, without any tools at all – replace PCI cards, install memory, install or replace hard drives – all without tools.

All of this design is not specifically user interface design, but the fundamentals are the same: consider the user, consider what will happen in the future, and consider how the system will be used. In my experience, HP and Compaq have both been excellent in their design engineering.

What are your thoughts and experiences?

Data Center Resources (and the Data Center in a Box)

There is an excellent resource (blog?) titled The Server Rack FAQ which has excellent articles, many complete with videos. The writing is excellent and the site appears to be quite comprehensive.

There is another blog called Data Center Links which has lots of good news as well as a good but not overwhelming set of links. Go check the links out!

There is also the Data Center Knowledge web site which seems to be an excellent and frequently updated news source relating to data center topics.

One topic seems to be hot: data centers in a container. Sun came out a while ago with the Sun Modular Datacenter (also known as Project Blackbox). HP has the Performance Optimized Datacenter (POD). Data Center Knowledge has a nice video about the HP POD. There’s also a nice discussion with HP about the POD from NetworkWorld. Dell announced that they will be powering Microsoft’s cloud initiative with data center containers.

Sun Microsystems has a lot of videos, including many about their data center in a box – including a tour or two, as well as an intriguing test of the durability and operational capability of the data center in a box.

Even IBM is in the market with their Enterprise Modular Data Center (EMDC). CNET had a nice article on IBM’s EMDC, as did DataKnowledge.

This is definitely an exciting area to watch.

An up-coming conference is the Data Center World conference in Las Vegas, Nevada on March 8-12, 2009. I can’t speak authoritatively to whether it is good or bad, but I would say given the presenters and topics and so forth, it sounds like a conference to consider.

There are a couple of journals that might be worth checking out: the Data Centre Management journal from the United Kingdom and the Data Center Journal in the United States.

Automation: Live and Breathe It!

Automation should be second nature to a system administrator. I have a maxim that I try to live by: “If I can tell someone how to do it, I can tell a computer how to do it.” I put this into practice by automating everything I can.

Why is this so important? If you craft every machine by hand, then you wind up with a number of problems (or possible problems):

  • Each machine is independently configured, and each machine is different. No two machines will be alike – which means instead of one machine replicated one hundred times, you’ll have one hundred different machines.
  • Problems that exist on a machine may or may not exist on another – and may or may not get fixed when found. If machine alpha has a problem, how do you know that machine beta or machine charlie don’t have the same problem? How do you know the problem is fixed on all machines? You don’t.
  • How do you know all required software is present? You don’t. It might be present on machine alpha, but not machine delta.
  • How do you know all software is up to date and at the same revision? You don’t. If machine alpha and machine delta both have a particular software, maybe it is the same one and maybe not.
  • How do you know if you’ve configured two machines in the same way? Maybe you missed a particular configuration requirement – which will only show up later as a problem or service outage.
  • If you have to recover any given machine, how do you know it will be recovered to the same configuration? Often, the configuration may or may not be backed up – so then it has to be recreated. Are the same packages installed? The same set of software? The same patches?

To avoid these problems and more, automation should be a part of every system wherever possible. Automate the configuration – setup – reconfiguration – backups – and so forth. Don’t miss anything – and if you did, add the automation as soon as you know about it.

Things like Perl, TCL, Lua, and Ruby are all good for this.

Other tools that help tremendously in this area are automatic installation tools: Red Hat Kickstart (as well as Spacewalk), Solaris Jumpstart, HP’s Ignite-UX, and OpenSUSE Autoyast. These systems can, if configured properly, automatically install a machine unattended.

When combined with a tool like cfengine or puppet, these automatic installations can be nearly complete – from turning the system on for the very first time to full operation without operator intervention. This automated install not only improves reliability, but can free up hours of your time.

The Green500 List

The Green 500 ListFor many years now, there has been a list of the Top 500 supercomputers in the world as measured by computational speed. But is speed the only metric that a supercomputer should be measured by?

Almost certainly not. In recent years, the discussion has changed as awareness of data center energy consumption has become an important topic. These top supercomputers are, in many cases, egregious offenders of energy consumption.

Thus, the Green 500 list was born: a list of supercomputers (taken from the Top 500) arranged by energy efficiency. This makes for interesting reading, and helps raise the awareness that computational power is not the only reason to buy a computer.

System Administration and the Environment

Today is Blog Action Day, and the focus is on the environment. What does this mean to a system administrator who works with computers in the data center all day?

Lots. There are at least two areas where you can help daily: data center electricity use, and paper use.

Data Center Electrical Use

The data center is becoming responsible for an ever increasing amount of electricity use, and generators are already maxed out in many locations in the country. Electricity generation often relies on coal or fossil fuels or perhaps nuclear generation, all of which pose risks of one sort or another. Electricity generation spews pollution into the air, and degrades our air quality.

Reducing electricity usage in the data center will not only reduce the need for electricity, it can also reduce your corporate electric bill.

There are many ways to do this. One is to use virtual servers wherever possible and practical. Virtual servers can be added to a machine with no increase in electrical use, and with other improvements as well. Virtual servers can simplify maintenance, restoration, and more.

Another way is to get rid of old (or very old) systems and replace them with something more current. At one company I worked for, an IBM System 36 was replaced by an AS/400 Advanced 36 – and the electric cost savings were tremendous. Older systems take more power than the newer replacements, as new power-saving technology is introduced.

The technology industry has an initiative called The Green Grid to help foster reduction in data center electricity use as well. Intel Corporation has an initiative of their own, as well as being partners with Google in the Climate Savers Computing Initiative. Dell Computer Corporation has an extensive environmental program designed to help the company be environmentally conscious on all levels. The chip-maker AMD is also pushing its energy-efficiency program to help reduce data center energy use.

In fact, AMD sponsored a study by Jonathan Koomey, a professor at Stanford and a scientist from Lawrence Berkeley National Laboratory (LBNL) which studied extensively power use by data centers. InformationWeek reported on this study. Koomey has been actively studying power usage for some time; a previous study was reported on by Science@Berkely Lab Magazine sometime in 2001 or 2002.

On Dec. 6, 2006, SiliconValley.com reported (from an article by Sarah Jane Tribble of the Mercury News) on a meeting between many of the technology companies (such as IBM, Cisco, SGI, Google, Sun Microsystems, HP) and the federal government focused on what they called “the upcoming energy crisis” driven by IT energy consumption.

Paper

Paper, while being a renewable resource, is taking its toll on the trees that exist on our planet (along with the need for lumber world-wide). The biggest problem is that trees are being consumed faster than they can be regenerated – trees take many years to grow, and only minutes to take down.

Another problem with standard white paper (as is used in the office) is that actual paper production is a very messy and chemically intensive process – the bleaching of the paper (making it white instead of the generic brown or tan) is the worst. With the most irresponsible companies, the chemical results may go back into the river; others will put the chemicals into barrels and store it somewhere.

Reducing paper usage by not printing, and using recycled paper will help preserve the forests of America and of the world.

….and of the Industry….

While the individual system administrator won’t be able to do much about this, the computer industry is a new source of pollution that hasn’t gone noticed very much – in particular, chip manufacturing. The chemical remains from chip manufacturing are positively horrendous and quite caustic – a well-known portion of the manufacturing process requires the use of an etchant which etches away portions of metal or other products to leave the traces in the chip or circuit board. However, chip manufacturers are taking note and making changes to become less polluting.