Joe Clabby, the president of Clabby Analytics, recently took a trip down to Brazil to visit with Hoplon Infotainment, the maker of a massively multiplayer online role-playing game that is supported by the mainframe architecture. When you think online gaming, you probably don’t think the mainframe is supporting it, but Hoplon is doing just that.

Clabby, who took his son down there to scope out the gaming quality, took a video of his trip. If you can endure the lax film editing, mentions of delicious fried egg sacs, and difficult-to-see whiteboard explanations by Hoplon’s CEO, the video is actually worth checking out. You can also view Clabby’s other YouTube videos from his Brazil trip.

Nearly a year after Intel Corp. introduced its Xeon quad-core processor, Advanced Micro Devices (AMD) finally crossed the finish line releasing its Opteron quad-core chip September 10.

Now we need a new race to watch. Let’s look at 45 nm technology.

Illuminata Analyst Gordon Haff wrote a blog from the Intel Developer Forum in San Francisco last week about the Intel/AMD competition, saying Intel plans to beat AMD to the punch once again by coming out with 45nm high-k metal gate-based transistors later this year.

In fact, Intel’s slogan at the show should have been “Onward to 45nm” because the company made such a huge deal out of the technology, Haff said.

“Intel can hardly be unaware of the salutary marketing effects of banging the 45nm drum. With AMD beginning to ship its new 65nm Barcelona parts, Intel’s ability to hold up wafers containing 45nm parts that it intends to ship by the end of the year can’t help but suggest that Intel is in a strong competitive position. That it also showed off an early 32nm test wafer only added to the impression,” Haff said.

AMD plans to enter its own 45 nm processor to the market in 2008. Of course, an AMD spokesperson claims it isn’t a big deal that Intel plans to into 45 nm first, since AMD’s existing 65 nm processors are better than Intel’s current and future processors, no matter how few nanometers Intel uses.

“We’re not surprised that Intel breathlessly spoke of their 45 nm manufacturing plans, as they’re trying to draw attention away from the fact that they are more than year behind AMD in x86 architecture design,” said AMD spokesman Phil Hughes. “The fact is that customers don’t buy nanometers. Customers buy innovative solutions to address their business needs.”

The irony here is that when AMD was talking smack about Intel for slapping two dual core processor together to make a quad-core chip instead of putting all four cores on a single die, Intel pointed to customer buying habits as well.

“There is no advantage of going from two to one, and end users don’t care if there is one piece of silicon or two,” Intel’s Nick Knupffer said.

But back to 45 nm.

AMD’s Hughes said, “While Intel will claim an advantage based on a number (45 being lower than 65), the reality is that the AMD Opteron processor is more efficient [than Intel’s Xeon] and Intel is using manufacturing to mask the inefficiencies of their design.”

“Our current 90nm platforms consume less power than [Intel’s] 65nm platforms, so obviously you can’t just look at the transistor size and make a blanket assumption about the benefits.”

I think most users know better to assume anything when it comes to processor technologies. Or do they?

At AFCOM’s Data Center World show in Dallas (actually Grapevine) last week, I decided to ask some folks what their definition of a “green data center” was. There has been a lot of focus around energy efficiency in the data center lately, and that was reflected in the conference with sessions as well as the Andrew Fanara keynote.

But rather than having just vendors drive the definition for what a green data center is, I felt it was important to get a bunch of different perspectives. We at TechTarget have our own definition of a green data center. At the show, I talked to the AFCOM president, a user, a researcher and a vendor to get their definitions:

“When I take a look at the greening of the data center, I look at it as an ecosystem. But how do you green a server? Do you just get rid of it? I don’t believe it’s practical to just go out and start spending money. You can probably save up to 40% in operating costs by just doing proactive things in the data center. You can green in many different areas, in the whole data center. So I say it’s an ecosystem.”
- AFCOM president William DiBella

“Something that’s taking advantage to cut power costs, save money and clean up the environment.”
- Steve Slowiak, data center operations manager for the University of Illinois Chicago Hospital

“I think my definition would be what computer science folks would probably say, and that is in terms of MIPS per watt of cooling. Ideally you would want that to be as high as possible. It does depend on your perspective of the problem. A more holistic view might compare the IT power to the power to HVAC, which is similar. Because what does a data center do? It gets electrons most efficiently to where they need to be. Everything you provide to the facility ends up as heat that needs to be cooled. So essentially you have to look at the efficiencies of the cooling equipment.”
- Yogendra Joshi, professor at the Georgia Institute of Technology, who co-presented an AFCOM session entitled, “The Pros and Cons of Allowing Humidity to Float”

“A facility providing compute resources that are in harmony with the environment supplying those resources.”
- Gregory Clark, director of global data centers and facility planning for Computer Sciences Corp. (CSC)

IBM and Missouri State University are teaming up to create a new college IT curriculum: Bachelor of Science in IT Service Management. The new degree program in the Department of Computer Information Systems (CIS) is the school’s attempt to bring real-world relevance to its CIS program.

According to Professor Ron Dattero from Missouri State, MSU had over 1,000 students enrolled in the CIS around Y2K. But in recent years, enrollment dropped to 300. Dattero said the school had to do something, so it turned to Big Blue to revamp its program to make it more attractive to job seekers.

Traditional CIS curricula focus on coding, database analysis, mathematics and engineering — but oftentimes these skill sets don’t translate to the job market. Skills like project management, software distribution, and fault management are more aligned with what the industry is looking for.

Paul Kontogiorgis, IT Services Curriculum Program Director at IBM helped MSU build its new curriculum around IT services. He said that academia has not had an introduction to the real business of IT since the early 1990s.

“Academia and industry have not collaborated on common interests,” Kontogiorgis said. “Businesses go to research facilities to make quick money, but have done little on preparing the future for academia. Academics have limited industry experience.”

This new program from IBM and MSU attempts to bridge that gap and bring new relevant coursework to CIS students. According to Kontogiorgis and Dattero, the hottest skills are: Fault or problem management (monitoring network, storage, server platforms and applications), IT project management and change management.

Dattero is also working to bring ITIL certification into the curriculum. The effort is still under negotiation, but Dattero is working on getting university stakeholders to help fund ITIL and certification and examinations.

Traditionally, companies pay for their employees to spend three days (20 hours) cramming in an ITIL foundation course from a third party testing firm. But students at MSU could have the luxury of a whole semester (45 hours) to study ITIL and according to Dattero, walk away with a better depth of understanding of ITIL service management principles.

“The number of professionals certified in ITIL is really going up,” Dattero said. “We need to have pros coming out of the schools, rather than companies trying to produce people with service management foundations.”

Are traditional CIS programs relevant? Should companies be doing professional development (like ITIL certification) or should that be a college level requirement? Which university has the best IT management program in the US? Leave me your feedback in the comments section.

A new study by Opengate Data Systems, a data center availability consulting company, found that a 5 kw/rack data center would shut down in about three minutes if a power outage caused there to be no cooling. For a 10 kw/rack data center, the time is even shorter: about one minute.

The study on data center power outages was commissioned by Active Power, which makes flywheel and other non-battery based UPS devices for the data center. Much of the study was meant to promote Active Power’s CoolAir UPS, which can provide backup power and cooling in case of a shut down. But the data from Opengate is still pretty interesting.

A new Forrester Research Inc. report by Stephanie Balaouras examines the lack of progress made in data center disaster recovery since the September 11 attacks in 2001 and, more recently Hurricane Katrina in 2005.

According the report’s summary drawn from Forrester’s Enterprise And SMB Hardware Survey,about 27% of enterprises in North America And Europe in Q3 of 2007 do not have a recovery site. Additionally, “23% of enterprises never test their disaster recovery plans, and 40% test their plans once per year.” Balaouras says this data points to a failure to make the business case for disaster recovery.

Disaster recovery author and Data Center Decisions 2007 presenter Greg Schulz agrees that the business case for DR isn’t being argued effectively and that in many cases it’s more cost effective to take the one-time hit and rebuild than to spend little by little over time. “It’s like when people operate without insurance - they just hope that they can get by and that nothing will happen - especially in smaller businesses.”

Schulz also argues that data center disaster recovery media coverage colors planning perceptions. “People located along the coasts are better prepared because those areas are always in the news. But companies that locate or outsource to the midwest are just as bad or worse because they think just because they’re out of the hurricane zones that they’re in the clear. But they still have to be prepared.”

DALLAS - Data Center World, the semiannual conference put on by AFCOM, which stands for the Association For Computers Operations Management, kicked off here in Dallas this week.

Before the keynote address yesterday by the EPA’s Andrew Fanara, AFCOM officials took the stage to talk about what’s going on with their organization. In the past year, the group has seen a little shuffle, with Jill Eckhaus moving from the role of president to CEO, and William DiBella, the founder of Connectivity Technologies, moving into the position of AFCOM president.

Eckhaus took the stage to talk a little bit about Data Center World, saying that it is 15% bigger this year over last, and has been named one of the fastest growing tradeshows by Tradeshow Week magazine. She said the reason for that is the data center is growing so fast, and its managers are hungry for ways to run it smoothly.

“The data center is like a business, and as a person in charge of a data center, you are in charge of running your business,” she said.

She also said that the AFCOM Web site has been redesigned and that the group plans to put out plenty of publications in the coming year, including four handbooks on pertinent data center topics such as power and cooling.

Here at AFCOM’s Data Center World show in Dallas, I went to a session on data center EPOs, which is short for Emergency Power Off. Basically it’s that big red button by the exit door in your data center that you should never, ever touch.

Better yet, don’t even put one in. Yes, you heard that right. The speaker, Richard Sawyer from EYP Misson Critical Facilities, said that some data centers don’t even need an EPO. It all relates to the difference between codes and standards as set out by the National Fire Protection Agency (NFPA). Codes you have to follow; standards, not so much.

So if you don’t have cables underneath a raised floor, have IT equipment cable boxes secured to your floor and don’t state that you’re following NFPA 75, you don’t need an EPO. Sawyer also went into how an EPO should be designed (think rotary switch instead of a button and with lots of horns and lights attached when you’re about to turn it) and what some are doing to try to change the federal codes around data center EPOs.

As part of his presentation, Sawyer talked about some of the disasters he has seen out there with data center EPOs. Among them: one EPO located directly behind a copy machine, so that if someone lifted the lid up, the button could get hit; another one had a Post-It Note attached that read, “Do Not Touch.” Sawyer relayed one story of a service technician who backed into an EPO while unpacking equipment in the data center. The cost: two mainframes, two minicomputers and 20 other servers failed; there was a two-hour outage; and the company ended up spending $100,000 to upgrade its EPO.

Tell us about your data center EPO disasters (or successes) in the comments section.

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?

Hewlett-Packard this week introduced “Shorty,” a smaller blade chassis looking to capture the attention of smaller companies in a similar way that the BladeCenter S aims to. It’s 10.5 inches high, fits eight blades and can plug into a standard 110-volt wall outlet. All in all, it’s a pretty good mini-BladeSystem.

Called the c3000, the chassis has its own MySpace page. Seriously. It must be a way to get “them kids” excited, right? The page lists as its hero the HP BladeSystem c7000 and has this to say in the About Me section:

I prefer working with smaller businesses like this over larger corporations because you feel like you’re taking the world by storm together, all while perched atop a Web 2.0 platform. It’s nothing short of electric.

The chassis also has diverse music tastes: Johnny Cash, Modest Mouse, and The Roots are all on the list. As of Friday afternoon, the page had seven friends (including Tom), most if not all of which are public relations people.

First of all, MySpace? Everyone knows MySpace is old, man. Facebook is where it’s at. And what’s next? Maybe the chassis will sign up for a Twitter account — “just got shipped out of the warehouse” and “user sliding blades in, and oooh, it feels so good” will be the requisite entries.