Datacenters as corporate welfare: maximum incentives for minimum jobs.

Vern Burke, SwiftWater Telecom
Biddeford. Maine

I’ve just been reading the piece about the lawsuit over the proposed Verizon data center in New York. This story highlights exactly what is wrong with the mega-datacenter feeding frenzy that’s been going on and just how out of control it’s gotten.

The main complaint of the lawsuit is massive cutting of corners in the approval process for this datacenter. Can anyone seriously argue building a million square feet of sprawling mostly single story building has no environmental impact? How about water consumption and release for cooling all those servers? How about air quality requires for all the diesel backup generators for all those servers? I notice that even Microsoft has to get air quality permits for generators in their West Coast datacenters, I wonder what makes Verizon so special that they don’t make any environmental impact doing the same thing.

The characterization of a datacenter as just “a giant warehouse for computers” is a bit astonishing to me. If Verizon managed to convince everyone there was nothing more to a datacenter than that, I’m certainly impressed. Either that or these officials do know better but they think this explanation will suffice for everyone else who doesn’t know any better (move along, nothing to see here!).

Bad as this sort of thing looks, the ugliest part of this are the public subsidies. North Carolina has been a great state for ridiculous giveaways to attract huge datacenters with flashy corporate names and a tiny amount of jobs but this deal makes them look like amateurs. We now know that the going rate for buying jobs with public money is $3.1M each ($614M), surpassing the Yahoo datacenter deal at $2.1M a job. Do the math, how long would it take a modestly paying IT job to pay back $3.1M? And to do this on a 20 year basis? Given the usual life span of datacenters, that’s well more than the likely lifespan of any datacenter being built today, just due to the rapid pace of technology change. Divide it out, for workers to even make $3.1M in wages over 20 years means every job would have to pay in excess of $150,000 a year.

I’ve often remarked that I could do more good for the local community with 1/100th the subsidies being lavished on these projects. Unfortunately, I’m a small operator and the huge flashy photo op projects with famous names attached lend themselves to the publicity (over)hype much better, just as long as you don’t look at the math behind them.

It’s time to stop and do a sanity check on this whole process.

Email or call me or visit the SwiftWater Telecom web site for green data center services today.

Tuesday data center tidbits: #datacenter “mistakes” and natural gas

First up today is reading a list of data center “mistakes”. The first mistake is fooling around trying to calculate an ROI for PUE. The bottom line of a data center is work out for money in. PUE is marginally useful for telling if you’re improving the data center but stop misusing it as if it was a pronouncement from on high.

Second up is a piece considering whether data centers should be situated near natural gas supplies. That’s kind of a duh question. If you’re going to use fuel cells or conventional generators to power your facility, of course. On the other hand, I wouldn’t bet on this becoming the next big thing right off and I wouldn’t let it overwhelm other energy efficiency criteria. Otherwise, you could very likely end up following the Pied Piper of the next great thing that never materializes.

Email or call me or visit the SwiftWater Telecom web site for cloud computing services.

Vern

Cloud computing and data centers, the numbers add up just fine.

I was just reading an article about the government’s 1200 data centers with only 7% server utilization and one claiming the government’s cloud computing numbers don’t add up. For probably the first time ever, it’s not the government that’s slinging the fuzzy math.

First, Vivek Kundra revealed the state of the government’s data centers. How in the HECK do you get that far off track? Is someone really setting the “build new data center” trigger at 7% utilization? I’m assuming that since this is the case, little or no other efficiency measures are in place in these data centers either. What an absolutely phenomenal waste of money and energy, even by that icon of inefficiency the federal government’s usual standards.

On top of this, we find that the TSA was planning to spend $600,000 to launch a blog. To launch a blog. To launch ONE blog. I’ll give you a moment to absorb that. It’s difficult for me to fathom the idea of spending $600.000 for ONE blog when you can grab a free copy of WordPress, slap it on a less than $1000 server, and, in an afternoon, have a perfectly top notch blog up and cooking. What is wrong with these people’s thought processes?

On the other side of the coin, we find an argument against the government’s cost saving numbers from dumping much of this horde of horrendously under utilized data centers in favor of cloud computing. The argument is that nobody is providing “detailed numbers” on precisely where the cost savings are.

The economics of cloud computing and virtualization are well established. Put the workload of 10 physical servers (a fairly conservative ratio) on one physical server, reduce your capital expenditure 90%, reduce your data center requirements 90%, reduce your power consumption and expense, and reduce your manpower requirement. These benefits of cloud computing are not vague or reasonably refutable.

So, is it a good reason to claim “the numbers don’t add up” unless you know down to the penny how much of the saving comes from power usage reduction versus manpower reduction? Should we poo poo this because we don’t know the precise percentage of saving between less IT equipment and less data center space?

Bean counting didn’t save us from getting into this mess and it’s grown to drastic proportions when you talk about a $600,000 blog. I see a lot of this going on in business adoption of cloud computing and virtualization also, pick nits over pennies when you’re bleeding $100 bills.

It’s time to embrace the savings of cloud computing, even if you can’t tuck all the pennies neatly in pigeon holes. Savings are savings and that’s the bottom line.

Let us show you the REAL savings, email or call me or visit the SwiftWater Telecom web site for cloud computing services!

Vern

Greenpeace and cloud computing cluelessness.

This afternoon, I was reading about Greenpeace’s rant about cloud computing contributing to climate change and here. I’ve seen cloudwashing as a marketing and hype tactic, but this is the first time I’ve seen it as an environmental cause.

I don’t think that anyone can really argue that it’s not better to use renewable power sources wherever possible. It’s also quite interesting to me that there’s such a difference in the percentage of renewable energy available from different physical locations. I also agree that Facebook’s siting decision for their Oregon data center is peculiar, given all the hype about the green-ness (greenocity?) of the facility. On the other hand, there are a few things that Greenpeace is WAY out to lunch on.

I’m a bit confused about the idea that cloud computing data center operators can somehow pressure or force power suppliers to change their mix of generating facilities. I know that Google, Microsoft, and Amazon are pretty much the 900lb gorillas of the industry and they can drive a lot of things (including buffaloing states into giving them massive tax breaks for job creation that never materializes). But how in the world do they force the local power co to do anything?

The next thing is, if they’re going to single out cloud computing as the problem, let’s have some numbers on just cloud computing alone, not mixed in with any other data center services. Cloud computing is a problem compared to just what, exactly?

It’s certainly true the demand for cloud computing services is growing at an enormous rate and that the power being consumed by cloud computing services is growing along with it. It’s also true that, assuming a conservative ratio of 10:1 for virtualization, cloud computing has and will continue to slow the energy growth required to service this demand compared to the bad old days of underutilized dedicated servers for everything, not only in terms of the gross reduction in servers required but the reduced energy requirements for the entire facility. Certainly makes criticizing cloud computing as not green sound pretty ridiculous.

The real issue here isn’t cloud computing or the increase in demand for cloud computing services, or even whether the data center operators can (by some unknown mechanism) force the power co to change its generating mix. The real issue is the massive corporate tax break giveaways from the states that skew the economics and entice these facilities to areas with lousy power portfolios. When it comes right down to it, the dollar talks the loudest.

Any way you slice it, cloud computing is working to mitigate a problem not of it’s making. Focus on the real problem and stop blaming something that’s actually helping.

Email or call me or visit the SwiftWater Telecom web site for cloud computing services and green data center services!

Vern

Opinion: data centers, economic development, and anti small business.

I’m going to take a break from the tech writing for a minute and talk a bit about data center politics, economic development, and anti small business attitudes.

Recent data center news has been full of an endless litany of massive corporate giveaways ranging from multimillions to tens of millions of dollars to attract gargantuan data center projects that generate relatively few jobs (Microsoft’s massive 700,000 sq ft Chicago data center only requires 40 employees). I’m sure Facebook, Google, Microsoft, and others of that size wouldn’t miss a million or so on a large project, but they have states falling all over themselves to lard on the goodies. It seems that the prevailing attitude is that something is only good if it has a giant corporation with a famous name attached to it.

There are tens of millions of square feet of empty facilities in this country that would make excellent data center space (Biddeford, ME where I am has a million square feet of Type IV of former mill space). The buildings are immensely strong, equipped with tremendous power facilities, and a green slam dunk by reusing the embodied carbon represented in them, but nobody in positions of power seems to be able to come up with a better idea reuse for them than subsidized condos, artist’s studios, or retail space (coincidentally pricing everything way out of the range of the average small business in the process). It’s either that or allow them to sit empty until they fall victim to vandalism, arson, or deteriorate to the point of no return.

Small data center operators not only provide a useful service and jobs that really benefit their community, they also act as a force multiplier by attracting and supporting the growth of other high tech business in the same facility. Unfortunately, the trend is not only to not support small local operators but to subsidize their massive corporate competitors and place the very facilities that would benefit them far out of reach.

So, what is lacking in these facilities that should be subsidized to make them fully useful? Simply, Internet connectivity. Pull in fiber and you now have an investment that’s far more valuable to the community for far less money than the corporate presents. Give me $250,000 and I’ll produce larger and longer lasting results for the local community and the state than the $3,000,000 gift that one huge new data center got.

I’m not sure where this blind eye and disdain towards small operators came from, but it’s time to stop it, put the money where it will actually do some good, and stop chasing the big name rock star publicity.

Call or email me or visit the SwiftWater Telecom web site for green data center and cloud computing services minus the hype.

Vern

Friday data center tidbits.

The tax break incentives in the data center war are getting absolutely crazy. Virginia throws in 10 years of no sales tax on IT equipment, North Carolina ups the ante with $10.3 million for Apple. Given the small number of people actually employed in these facilities, do they really gain more than they give out in corporate welfare?

Have you ever been inspired to write haiku about a data center? Personally, I’ve been inspired to write a few unprintable things by a few of them.

Are you looking for cloud computing, virtual server, or virtual workstation/virtual desktop services? Email or call me, or visit the SwiftWater Telecom web site to see how we can help you!

Vern

The virtual data center, whose “cloud” is it anyway?

I’ve been reading this morning about “opening the cloud”. I don’t think I’ve ever seen such total misunderstanding about what “the cloud” really is.

First of all, there is no “the cloud” (I cringe every time I hear that said). Google has a cloud, Amazon has a cloud, SwiftWater Telecom has a cloud (that’s us ). There is no giant, amorphous, entity identifiable as “the cloud” (it’s almost as bad as hearing people talk about “the Google”).

Next is the idea of wresting “the cloud” away from corporate and government control, as if there’s something inherently wrong with “cloud capitalism”. Companies that provide cloud based services are not just “organizing” things on “the cloud”. The money for servers, facilities, and software for a cloud don’t magically appear from nowhere. If you want a free cloud with no corporate attachment, ante up and build one yourself, then you can give it away for free to whoever you like.

The idea that Google’s fight with China, which has devolved to censorship of Google’s search engine results, has anything to do with fighting for control of “the cloud” is ridiculous. It has everything to do with censorship, not with any legitimate security concern of China. And yes, Google owns their cloud that they provide Gmail from. It’s Google’s right to operate their facilities the way they see fit, it’s their property.

I don’t really know what to say about the idea that Google is creating a “cloud” of 10 million books (all I can picture is getting rained on by encyclopedias). I’m not commenting on Google’s plan to put books online, but I’m not sure what the connection is between digitizing books and using cloud powered services to store or disseminate them. Calling Wikipedia a “cloud” is just as incomprehensible.

I don’t believe there’s any lack of competition in cloud computing, as asserted by the article. There’s no way that “the Google” can stop me from building a cloud, acquiring customers for my cloud, or control the content or services of my cloud (I havn’t gotten any cease and desist letters from them yet). I don’t know how any corporate entity could possibly manage to control “the cloud”, you might as well try to take over the entire Internet (What are we going to do tonight, Brain? The same thing we do every night, Pinky. Try to take over the world!)

The fact is, cloud computing advances all the social agendas listed. You can use someone’s cloud powered apps (SaaS, software as a service), you can use a cloud to develop and run your own apps (PaaS, platform as a service), or you can have a cloud powered virtual server of your very own (IaaS, infrastructure as a service). All this comes with far lower cost and lower barrier to entry. People who could never have afforded a data center dedicated or co-located server can now have their own virtual server, completely under their control. Doesn’t sound much like evil corporations trying to rule the cloud, does it?

It’s time to embrace cloud computing and stop babbling about mythical corporate overlords. This isn’t Skynet and the Terminators aren’t on their way.

Vern

Tuesday data center tidbits.

First up today is reading about WAN optimizing as an on demand service for data center virtual cloud tenants. I’m not sure how this could really apply to a cloud. Certainly not a public cloud, since all the cloud tenants are effectively sharing a massive LAN (albeit likely VPNd). I guess you could refer to the uplinks from a private cloud as WAN, I’m still not sure how or why you’d apply this. As much as the cloud resembles just a large bunch of physical computers, not everything translates across.

Next up is reading about 5 barriers to total virtualization. The question is asked, what kind of mission critical apps can “safely” be virtualized? The short answer is, any of them! Unless you have something the requires draconian security protocols (such as being able to lay your hand on the exact physical disk that holds the data) or is such a server hog that it won’t fit within the capacity of a virtual machine, it should be fair game!

Finally, there’s the piece about states giving away the tax revenue to attract massive data center projects. Aside from a temporary bump in construction jobs, where’s the benefit? Not from employment (Microsoft runs 700K sq ft with only 45 people), not from taxes (already gave those away). In the meantime, they ignore smaller locally based business that might actually do the community some good, in the name of chasing the big name publicity op.

Vern

The virtual data center, nomadic virtual machines.

Tonight I’ve been reading about security implications of migrating virtual machines between physical hosts in the data center cloud. I think this is far from the awful problem the authors make it out to be.

Live migration of virtual machines between hosts in a cloud provides large benefits in reliability. Migration allows virtual machines to be moved from hosts requiring maintenance, they can be moved to avoid imminent disaster, or moved to balance loads across the cloud. This gives us maximum uptime and the most consistent performance for the virtual machines.

The first objection to this migration is to insure the migrated virtual machine retains all of its security settings, storage access, and etc. This is a bit of a red herring to me. These are either things under control of the virtual machine (the cloud hosts couldn’t manipulate them anyways) or they are things that, if wrong, wouldn’t allow the virtual machine to continue to run. Not a security risk by any means.

The second objection is that any facilities such as load balancers have to know the virtual machine migrated. Not at all. Considering Xen Cloud Platform (which we use for our cloud), virtual machines retain their IP settings and the MAC addresses of their virtual interfaces. No external system has any idea whatsoever which virtual machine is running on which physical cloud host, or even which are virtual machines or physical machines. It’s all completely transparent.

Since no outside application that interfaces with the virtual machine, be it load balancer, firewall, etc has any way of knowing where the virtual actually lives in the cloud, there’s nothing to migrate when the virtual migrates.

The cloud does indeed demand uniformity of the equipment in it, but that has nothing to do with migrating virtuals and everything to do with basic cloud functionality. XCP, for example, will not permit physical hosts to join the cloud unless they match in terms of CPU, memory, and Ethernet ports. It doesn’t matter who the vendor is or even that the hardware is an across the board full match as long as those items match.

Migrating virtual machines isn’t as hard as you might think.

Vern, SwiftWater Telecom

virtual data center cloud service

Wednesday data center tidbits.

I’ve just been reading about data center carbon reporting issues today. The handwriting is on the wall. Co-location data center operators darned well better have a method in place to measure the customer’s power consumption and a clause in the colo contract allowing the data center operator to apportion any carbon taxes back to the data center customer, otherwise, it’s going to get ugly.

From the same article I see APC say ““If we can give data centre managers just 20-percent accuracy on measuring the units of energy used by each server or application, that’s pretty darn good…”. Leaving data center operators to eat the carbon taxes on 80% of their customers power consumption is pretty darn good? I guess it beats eating 100% of it.

Vern, SwiftWater Telecom

virtual private servers