docs/2012_Survey_Stansberry.pdf
Originally posted on the Mission Critical Magazine Blog. Used by permission.
And Tune in Next Week for the Thrilling Conclusion
Some New York Rangers fans and Washington Capitals fans recently relearned an old lesson: Don’t leave a game before it is over. Someone might score a tying goal with just a few seconds left. Television networks have spent decades honing corny lines meant to keep viewers watching the screen right to the end of every episode.
Data center conference organizers don’t do that, and professionals like me miss an awful lot of good sessions on the last day of an event.
Not this time. The last two sessions of this week’s Uptime Institute Symposium were the conference highlights, both of which I attended. The penultimate session featured Uptime founder Ken Brill and Stanford University’s Jonathon Koomey describing the havoc wreaked by comatose servers in data centers. Brill suggested that as many as 30 percent of all servers could be described as doing no useful work, and he presented server utilization rates that supported his hypothesis. He said
Both Koomey and Brill seemed to agree that the 30 percent figure would prove consistent across the entire installed base of 30,000,000 servers, noting that significant energy savings would accrue from merely upping the utilization rates of this equipment. Koomey said, “The problems that limit energy efficiency in data centers are about people, not technology.”
Brill wore a ridiculous foam hat marked up with a summary of the results Uptime’s Server Roundup and also to celebrate the achievement of AOL, which decommissioned and recycled the largest number and percentage of its servers among the entrants. In total, AOL cleared out 9,484 servers – a 26 percent turnover in server assets. The move saved the organization $5.05 million in utility, maintenance and licensing costs and earned it $1.2 million from asset sales and reclamation. Brill reported that AOL believes it could retire even more servers in another phase. In total, more than 20,000 servers were decommissioned and recycled by program entrants.
Ken’s antics extreme may have been extreme, but years after industry first identified this problem what’s left but ridicule and contests as a way to get these servers out of service? Ken is usually not subtle, and I think he found a subversive new way to make a good point.
Either way, the content of this session was excellent.
Uptime Publications Director Matt Stansbury topped them just a few minutes later, as he shared the results of Uptime’s industry survey (attached). His 30-minute talk described a virtual census of the industry or at least as close as I have seen to date. Uptime saw trends towards DCIM, cloud services, and modular deployments, even compared to last year. They also identified barriers to further adoption.
For instance, 64 percent of the 1100 respondents still identify security as the number one impediment to going to the cloud, with compliance (27 percent), cost (24 percent), and lack of management expertise (20 percent) in the next tier.
Uptime found that cost (64 percent) was also the number one barrier to more DCIM implementations. Other barriers were distant runners up.
These include:
- Systems are not easy to integrate into existing facilities (31 percent)
- Difficulty populating existing databases (26 percent)
- Existing methods are sufficient (25 percent)
Regular readers know that I believe our industry would benefit from more open-ness and transparency. Industry research tends to be done by consultants and vendors who understandably tend to treat this information as proprietary after spending lots of time and money compiling it. Uptime is no exception, but the access they gave me for readers is a good step towards the openness I think we need.
Needless to say I was delighted when 451 Research CEO Martin McCarthy and Stansberry allowed me to observe Thursday’s Charrette. My trip had gone into triple overtime!
451’s Hank Seader moderated a morning-long session during which an impressive group of 30 panelists worked through the second phase of definitions geared to developing a process for evaluating IT infrastructure investments. The goal is to develop a common language for executives to communicate across multiple business units and disciplines and to provide a framework or methodology for making effective digital infrastructure investments.
451 Research invited a select group of data center professionals known to the them through their membership, support, or participation in 451 Research programs, and these men and women debated the meaning of finance, opportunity, and risk, which were identified as the hardest of six areas a previous panel had defined in a closed event in Orlando in January, with the others being risk, compliance, and sustainable.
I am not at liberty to say much more about this FORCSS meeting, but I plan to press my opportunity to add at least a little transparency to this process by providing progress reports. I am convinced that Uptime is onto something here, and I want to make sure that the industry understands the final product and accepts or rejects it based on its merits.
If you don't know what I'm talking about, I can't explain it; and if you do know what I'm talking about, I have no need to explain it. Yes, today is Towel Day, celebrated around the world to honor the late author Douglas Adams.
"A towel, it says, is about the most massively useful thing an interstellar hitchhiker can have. Partly it has great practical value - you can wrap it around you for warmth as you bound across the cold moons of Jaglan Beta; you can lie on it on the brilliant marble-sanded beaches of Santraginus V, inhaling the heady sea vapours; you can sleep under it beneath the stars which shine so redly on the desert world of Kakrafoon; use it to sail a mini raft down the slow heavy river Moth; wet it for use in hand-to- hand-combat; wrap it round your head to ward off noxious fumes or to avoid the gaze of the Ravenous Bugblatter Beast of Traal (a mindboggingly stupid animal, it assumes that if you can't see it, it can't see you - daft as a bush, but very ravenous); you can wave your towel in emergencies as a distress signal, and of course dry yourself off with it if it still seems to be clean enough.
More importantly, a towel has immense psychological value. For some reason, if a strag (strag: non-hitch hiker) discovers that a hitch hiker has his towel with him, he will automatically assume that he is also in possession of a toothbrush, face flannel, soap, tin of biscuits, flask, compass, map, ball of string, gnat spray, wet weather gear, space suit etc., etc. Furthermore, the strag will then happily lend the hitch hiker any of these or a dozen other items that the hitch hiker might accidentally have "lost". What the strag will think is that any man who can hitch the length and breadth of the galaxy, rough it, slum it, struggle against terrible odds, win through, and still knows where his towel is is clearly a man to be reckoned with."
Here's my Top 10 Reasons you need a towel in the data center.
10) That cold aisle is way to cold. Wrap yourself up.
9) That hot aisle is making you sweat. You need to dry off.
8) Use it to make a sack to carry your tools.
7) Nobody has refilled the napkin dispenser in the break room. Argh!
6) It was sunny when you entered the DC. Now, 36 hours later, it's raining outside. You can cover your head.
5) Proof of concept for cold aisle (or hot aisle) containment.
4) Lay it out on the raised floor and imagine you are on a tropical island beach.
3) Use it to bury your head in frustration for project taking longer than expected.
2) Twirl it over your head and sing "We are the Champions" when your project is complete.
1) Two words: Snap War!
What is EnergyWise?
Customers wanted energy solutions from Cisco, they responded by developing EnergyWise. EnergyWise is a technology foundation based on switches and routers that also extends to non foundation products (PC’s, building controls) or anything that draws power. Using third party partners, Cisco can offer centralized monitoring, auditing and control of network attached devices. This allows the existing network to become a platform for energy command and control.
Why use EnergyWise?
If you have an existing Cisco network infrastructure then the time and cost is minimal to obtain, monitor and control power information from any EneryWise compatible device on your network.
What Server Technology Products are Supported in Energy Wise?
Any Server Technology intelligent rack mount Power Distribution Unit (PDU) – with or without POPS/PIPS technology – is certified and interoperable as an endpoint within the Cisco EnergyWise client technology to capture device power information within the existing EnergyWise infrastructure. Server Technology is the only EnergyWise PDU supplier to offer both in-feed and outlet (device) power information.
Why use a certified Cisco IVT tested and approved supplier like Server Technology?
The principle objective of Interoperability Verification Testing (IVT) is to provide Cisco CDN program partners with an approved, consistent and comprehensive verification methodology for the interoperability of their applications with Cisco technology, EnergyWise SDK/API. Testing is focused on functionality and compliance with EnergyWise SDK/API. The IVT test activities between third party devices and applications and the Cisco IVT test bed determines whether the implementation of third party devices uses the SDK functions in a correct manner and provides responses to EnergyWise queries as well as pass command and controls in a way that is compliant with the EnergyWise protocol. The device or application under test must satisfy all the mandatory requirements, and selected optional requirements in order to pass the test.
Visit us at Cisco Live in San Diego on June 12th – 14th.
*Image Credit - Cisco
I love San Diego. Not only because of the perfect weather, the craft beer scene, the zoo, the sea, and the culture, but also because it’s this year’s location for Cisco Live!. Cisco Live! is seriously one of the fastest growing trade shows in the industry. I have been there the last few years and can testify that it is one of the most exciting large scale trade shows you can ever attend. The quality of the sessions, exhibitors, and overall knowledge base is overall just first-rate. If you are running Cisco gear anywhere on your network, then you need to attend this show.
Server Technology will be there yet again! Stop by booth 634 and talk with our cabinet PDU power experts.
This year we are also going to be talking about a major achievement: Server Technology’s Intelligent Rack Mount Power Distribution Units Now Cisco® EnergyWise™ Certified. Server Technology’s cabinet PDUs now integrate even better into your Cisco ecosystem. Monitoring every piece of equipment in the rack has never been easier. For more on cabinet PDUs and EnergyWise™, stop by our booth and talk with one of our power experts.
If you have not yet registered for Cisco Live!, we can help.
Join us at Cisco Live and save $100 on your registration! Discover what you make possible at the industry’s premier event for technology professionals.
At Cisco Live, networking and communications professionals from around the world gather to discover what they make possible. No other event offers the same combination of in-depth technical education and training, insight into emerging technology and business trends, and the opportunity to connect with colleagues who share your interests and challenges.
We’re inviting you to join us at this one-of-a-kind event — and save $100 on your registration. We’ll be a part of Cisco Live’s World of Solutions at the live conference in San Diego, so come visit us in 634. At the World of Solutions, you can explore companies that make up the extended Cisco ecosystem. You’ll have a chance to speak with experts on a variety of solutions to find out how to enhance and extend your Cisco implementation. For more information about Cisco Live 2012 visit: www.cisco.com/offer/ciscolive2012/214416_2
Register today and save.
As a Cisco Live sponsor, Server Technology is also offering you – one of our most important customers — a discount on full conference passes. Go to https://www.ciscolive2012.com/portal/ to register. Just enter the code wosdiscount when prompted, and you’ll save $100 on your full conference registration.
We hope you will join us at Cisco Live 2012!
Posted by
Marc Cram on Wed, May 16, 2012 @ 03:48 PM
“Security is mostly a superstition. It does not exist in nature, nor do the children of men as a whole experience it. Avoiding danger is no safer in the long run than outright exposure. Life is either a daring adventure, or nothing.” Helen Keller
WiFi, Bluetooth, WiMAX, and LTE are prevalent wireless technology acronyms that are bandied about in the daily lexicon of the IT and communications industries. The cognoscenti of these fields will extol the virtues of their respective products, based primarily on their areas of expertise, without always bothering to explain the ramifications of employing a given technology.
RF interfaces, by their very nature, are omnidirectional. Radio waves propagate in all directions unless guided either by an antenna or a waveguide. Hence, they are more difficult to contain, whether in a data center or elsewhere. The benefit of RF communications within the data center is the ease with which it can be scaled, and the reduced use of copper wiring. WiFi and Bluetooth are two good examples of this.
Server Technology was one of the first power strip manufacturers to support a wireless interface to our products. In partnership with RF Code, Server Technology developed a means by which the data center manager can remotely and automatically collect power consumption data from the IT load of his data center without concern about someone hacking in and taking control over the infrastructure. The RF Code interface is a one-way communications protocol that sends power consumption data back to a central collection point, thus facilitating a simplified IT load measurement for PUE calculations.
Contact your local Server Technology sales rep for a demonstration of the power of the RF Code and Server Technology solution. To learn more, visit http://www.servertech.com/solutions/wire_free_power_monitoring_with_server_tech_and_rf_code
When it comes to data center management, what was once lumped under the umbrella of data center monitoring has now become one of the largest standalone categories today – data center power. Because let’s face it; every data center provider out there is pounding the pavement to find the best ways to curb data center power consumption.
“Things have really changed in the past 10 years with regard to data center power,” Mark Harris, said vice president of marketing at Server Technology. “Power itself has become a critical system requirement. It’s no longer a generic category within the data center. People actually care greatly about the quality and reliability and intelligence of the PDUs they’re installing, because of the impact on uptime, energy efficiency, capacity and the bottom line.”
Accordingly, Harris will be joined by Bobby Brown, vice president of operations at GoGrid this week at Uptime Institute Symposium, taking place in Santa Clara, Calif., through May 17, to discuss data center power and management in a session titled “Power as a Mission Critical System.” The session will explore recent green IT and sustainability initiatives, required regulatory mandates, and what made GoGrid enlist the help of Server Technology (News - Alert), a leading provider of data center power distribution units.
GoGrid, a cloud hosting and hybrid hosting provider, first enlisted the help of Server Technology when it realized that its brands of PDUs were not as mature as they could be. Conversely, GoGrid was in search of PDUs that could manage remote data centers, could provide long-term reliability, and exhibited higher density and minimal physical impacts. Further, the company was hoping to develop an understanding about rack level power usage and pro-active power management and to leverage its relationship with its chosen co-lo, Equinix (News 
- Alert), for acquisition, familiarity, and support.
That’s where Server Technology came in.
By deploying Server Technology’s Sentry Power System (Sentry PDU hardware and Sentry Power Manager software), GoGrid was able to push out its own products faster and enjoy cost savings and increased efficiencies.
In addition to shedding light on its partnership with GoGrid at Uptime Institute, Server Technology is looking forward to providing some insights as to where the industry is headed and where Server Technology fits into these emerging trends.
“PDUs are becoming less ‘commodity’ in nature when it comes to overall value,” Harris said. “Sure, the technology of the strip itself looks similar at a feature by feature level, but there is a ton of business value that you must look for when selecting PDUs. The vendor’s overall reliability and business practices, the vendor’s investments in quality engineering designs for hotter and higher power PDUs, the availability of PDUs in a wealth of configurations, the expertise of the vendors sales and support teams ‘after the sale’, overall PDU reliability over long periods of time (years), the concept of a PDU supplier being a fully functional component of maturing DCIM strategies and the need for vendors like Server Technology to specifically engineer ‘DCIM-Ready’ solutions (like our Sentry CDUs and Sentry Power Manager). The industry IS adopting DCIM over the coming year, and the ability for PDU vendors to directly support these needs ‘out of the box’ will be essential.”
Moreover Data Center Infrastructure Management (DCIM) is transforming the way that data centers will run, specifically in that data center equipment choices that are made today have to live and need to support the next generation of data center management.
For more information on Server Technology's Sentry Power System, visit www.servertech.com/solutions
We have seen a lot of data centers built in locations that were previously used for other purposes. I saw this article in the Las Vegas Sun about using the Yucca Mountain (no longer slated as a Nuclear Waste) Repository to store something else - Data.
I don't know how much Yucca Mountain comes up as a topic of discussion elsewhere, but in Nevada, this has been a perennial discussion centered around safety of nuclear waste storage. Since it has effectively been a debacle to the tune of some $20B, I'm happy to hear something of value might come from it.
As I see data centers going into all kinds of unusual locations and see the growth of data and communications needs continuing unabated, I can't help but see every unoccupied commercial building as a future data center. Every time I pass a long-out-of-business grocery store, factory, or strip mall, I imagine seeing generators in the back and chillers on the roof. Maybe it's just me, or maybe it is inevitably the future.
What do you think?
When the University of Hawaii School of Ocean and Earth Science and Technology (SOEST) needed a way to power the world’s deepest cabled ocean observatory, it knew it needed a little help.
And, when it decided to re-task an old AT&T voice cable to connect an underwater observatory so that the SOEST people could continuously monitor a spot in the ocean called Station Aloha (22°15’ North, 158° W), SOEST decided to enlist the help of Server Technology.
For SOEST, there were a few problems the university was facing, including the fact that it was 100 kilometers north of the island of Oahu, and five kilometers deep, which meant that service calls were very difficult to perform. Moreover, even the control systems at the land end of the cable were in a very limited access space that is a cable landing station, according to university officials.
Accordingly, SOEST decided to deploy a Server Technology CW-8H1 IP controllable power distribution unit. With the data center power distribution unit in place, if some of SOEST’s custom software gets into an unknown state and hangs, there's no need to create a special visit request and have a tech drive a couple hours to reboot. Instead, the engineering tech can remotely access the Web interface on the PDU and power cycle the computer.
"It sounds simple, but being able to logically tie multiple outlets together, track power usage, and monitor the environment with temp/humidity probes; all translates to uninterrupted data streams to help the scientists of the Aloha Cabled Observatory learn about our changing environment at Station Aloha,” Brian Chee of SOEST said.
Server Technology’s CW-8H1 IP controllable power distribution unit was able to help SOEST tie multiple outlets together, track their power usage, monitor the environment, and remotely manage and reboot the server if needed.
Server Technology’s Switched 8 units (CW-8H1 IP) were the answer to SOEST’s challenges. They can remotely manage and reboot the equipment through the cabinet power distribution unit (CDU), get the power and environmental data they need as well as group multiple outlets together.
It’s great that we could help support the underwater observatory – it’s certainly one of the more unique implementations of our product.
For more information on Server Technology PDUs, visit www.servertech.com
As the official Cabinet-level power Distribution Unit (CDU) provider for Interop, Server Technology is actively involved in the Network Operation Center (NOC) that manages and monitors all InteropNET equipment. A wide variety of management tools are used in the NOC to monitor all aspects of the network and IT gear health. These include applications for receiving syslog messages, receiving SNMP Traps, monitoring all traffic (valid and invalid), and much more.
Specific to Server Technology is Sentry Power Manager (SPM), our tool for monitoring and managing status of all CDUs--which includes tracking current (amp) levels, power (watt) levels, temperature and humidity levels within the equipment cabinet, energy consumed (watt-hours), and many other metrics. As I write this from the NOC, SPM is collecting data from CDUs in 33 different cabinets full of various IT gear. Four cabinets are present in the NOC arena and 29 cabinets are distributed throughout the Mandalay Bay Convention Center and beyond. All is healthy at the moment, and I expect this to remain true for the remainder of the expo. Interop really does select top-notch vendors, and the staff from each are truly experts in their respective fields.
So far, there's only been one repeating alarm state captured by SPM from the CDUs: low relative humidity! We're in Las Vegas, smack dab in the middle of a desert, so low humidity is expected. According to Wikipedia, the typical low annual relative humidity in Las Vegas is 21%, but today we're seeing only approximately 12% to 15% in most areas and as low a 8% in others. Yesterday, pre-expo, we observed relative humidity as low as 4% in two cabinets. It sure is dry here! I'm used to it--being that Server Technology is headquartered in Reno, Nevada and I've acclimated over many years--but I'm certain there will be a quite a few cracked lips on exhibitors and visitors alike by the time they head home. Some empty wallets too.
High humidity and potential for condensation are the typical concerns surrounding humidity and electronics, but low humidity presents challenges as well. Static electricity is the key concern, which can result in a variety of difficult-to-diagnose errors when discharges occur. We're all being quite careful and keeping ourselves grounded when near the IT gear, but the occasional zzzap when someone touches a cabinet is still commonplace. True data centers can avoid low humidity through use of items such as humidifiers, but Interop is a temporary venue. The convention center is just far too large to consider active corrective measures. But thanks to the Server Technology CDUs and the attached combination temperature/humidity probes, and SPM that allows us to see the warnings with just a glance, we're dealing with it through prudence rather than reacting to unexpected faults.
Time to go get a glass of water. Hyrdate or die is what I've heard.
As you read this, Monday May 7th, 2012, I will be setting up Server Technology’s booth at Interop (booth 2351 represent) for the 4th time in 4 years. I love Interop because the show draws such a large diverse IT crowd, lots of good vendors, and the show atmosphere itself has a lot of energy. It’s a genuinely fun time. To top it off, Server Tech has been the official cabinet power distribution unit (CDU) provider to the Interop Net (both Vegas and New York) for the last 4 years. Only best of breed solutions are allowed into the Interop Net and so we are very pleased to be chosen year after year. Its quiet an honor.
Interop is one of the leading IT conferences in the country with tons of valuable sessions, educational tracks, and professional knowledge sharing avenues. Another great thing about Interop is that entry to the expo hall is very inexpensive, or sometimes free, and because of this lots of people attend the expo. This invites an interesting crowd and the vendors respond accordingly with some good-humored show gimmicks as well. In past years I have seen some pretty wacky stuff and I hope that this year is no different. Here are a few things I hope to see this week:
1) A boxing match. Yes. This has happened, on more than one year. An actual amateur boxing match was held in the expo.
2) A magic show. Multiple booths last year hired their own magicians to put on shows in their booths. Some of the shows are actually good, but some are super cheesy – I’m ok with either.
3) A game show. In the past, a few vendors have opted to host game shows instead of just having a basic presentation.
4) Models. aka booth babes. It’s Vegas after all. Many vendors employee models to help drive traffic to their booths.
5) Swag grabbers. These are the people that attend the show just to grab free swag, and don’t actually care about IT, data center, etc. They usually are carrying at least 3 backpacks or bags.
6) Mullets.
7) Hawaiian shirts.
8) Free beer.
9) Sports cars. Yes, inside the show room. Someone always finds an excuse to bring some.
10) Someone napping against the wall in the entry hall.
11) I expect to meet a person from each continent (not counting Antarctica).
12) Styrofoam rockets being launched from somewhere, but nobody knows where.
13) A person who ends up in the expo hall but has no idea what the expo is about or where they are.
14) A cash grab booth.
