Slashdot Mirror


What Kind of Data Center Can You Build With $500M?

coondoggie writes "So, if the government gave your company $500 million to spend on building a new data center what would you buy and how would you build it? Well, the Social Security Administration is about to find out. As part of the stimulus bill, or the American Recovery and Reinvestment Act of 2009, the SSA got the tidy little sum to replace its National Computer Center. The SSA in fact says it will need closer to $800 million to fund a new IT infrastructure, including the new data center — the physical building, power and cooling infrastructure, IT hardware, and systems applications. (This is addition to a $72 million backup facility currently under construction in Durham, North Carolina)."

204 comments

  1. The Unfortunate Reality of Maintaining Legacy by eldavojohn · · Score: 4, Insightful

    I will start with the assumption that this data center must be non-homogeneous. Get an assessment of all the projects that are using the current system you're going to replace (you know, the one with 36 million lines of COBOL code?). Because the number one priority of the customer (other projects) is going to be the lengthy transition from that to current technology. Prepare yourselves for this: Some of the projects aren't going to have any funding to do jackshit. Which means that the awesome spaghetti coded current system that's held together with COBOL duct tape needs to remain intact in some form. Not ideal situation but an uncomfortable truth. I'm thinking you would want to set aside 10% or $50 million or so for this (just throwing out a figure).

    --
    My work here is dung.
    1. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 5, Interesting

      As someone who maintains (part of) that 36 million lines of COBOL code, it's not as spaghetti as you might think. Many parts of it are quite clean, they just haven't been touched in years but they're simple and they work. The problem is, we're facing a demographic time bomb. The folks who wrote the system got hired in a huge spree in the 60s and 70s, and are reaching retirement age with full government pensions. Lots of them retire and come back as contractors, but we're still losing a lot of them.

    2. Re:The Unfortunate Reality of Maintaining Legacy by jellomizer · · Score: 5, Insightful

      I think more colleges as part of their Computer Science Elective they should be a class on Legacy System Maintenance. Legacy systems are not as bad as everyone makes them out to be. As well for the most part languages such as COBOL and FORTRAN are really not that hard to follow and learn. In many ways they are easier then the newer languages, as they are designed to do particular things and do them well, and not like C,C++,Java,.NET try to be the end all be all language. The old code is usually focused on the business logic while newer code seems to be working more with trying to get the formatting correct, and being well organized and modularized (which is a good thing too). But the old code you get PROCESS_CLAIM.CBL all the code that you need to process the claims are there, so when you fix the code there the problem is fixed. Having done a lot of work in FORTRAN myself I have found that there isn't that much spaghetti going on. Yes there is the GOTO statement but it is usually limited to ERROR cases where if something critical failes it GOTO ErrorNum and displays the error and quits the app.

      For these legacy apps normally when something needs to be changed is because there was a change in the business process not because of a bug.

      --
      If something is so important that you feel the need to post it on the internet... It probably isn't that important.
    3. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      I would start with the assumption that the datasync must be able to survive a zombie apocalypse, and allow the person who maintains it to survive it as well.

    4. Re:The Unfortunate Reality of Maintaining Legacy by MobyDisk · · Score: 2, Funny

      The problem is not that the COBOL coders are retiring. The problem is that the government made the decision to rewrite the code 20 years too late. Everybody else knew the language was dead.

      If this were a commercial company, they would go out of business for making such a stupid decision.

    5. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 1

      Not a bad idea, but in order to maintain proficiency, you have to use the skill. And then we have the experience gap between a person who was living those legacy languages instead vs. just visiting the code or picking up a few credit hours in college.

      The problem exists because employers have been devaluing legacy skills for a long time. The bean counters thought the problem would be solved via Y2K, with sweeping technology upgrades justified by the aging code (at least that was the view from the 19th hole). But in many cases, the code was simply patched. And many of the Y2K patches are temporary, using pivot years in lieu of 4 digit conversion because it was expedient to do so.

    6. Re:The Unfortunate Reality of Maintaining Legacy by AlecC · · Score: 2, Interesting

      There are plenty of not-out-of business companies still running COBOL for good reason. Admittedly, many of them are banks who are now going out of business, but not because of their COBOL. Look how much money IBM's mainframe division is still quietly making: many of these are COBOL engines.

      --
      Consciousness is an illusion caused by an excess of self consciousness.
    7. Re:The Unfortunate Reality of Maintaining Legacy by jcr · · Score: 2, Informative

      COBOL's a hell of a lot simpler than C++ or Java, and training people to read it well enough to rewrite legacy apps in a modern language just isn't that hard.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    8. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      Shouldn't this be mod'd 'Funny'? If it ain't broke, why fix it?

    9. Re:The Unfortunate Reality of Maintaining Legacy by SatanicPuppy · · Score: 4, Insightful

      As someone who maintains COBOL driven legacy systems, I disagree. Why teach that stuff in college? Those jobs are much more rare than other programming gigs, and they tend to be held by lifers (I inhereted mine when 2 people hit retirement age, and the third decided she didn't want to do it alone). If you DO get one of those jobs, the learning code for the obscure hand-coded systems is going to be vastly higher than the language.

      COBOL isn't that hard to pick up. Maintaining legacy crap code is the same whether it's VB or COBOL or RPG, and the vast vast majority of your headaches will come from environmental quirks (old school databases with fixed width data, packed binary decimal numbers that no one uses anymore, etc).

      The biggest problem with COBOL in the modern world is that its designed in reverse. It treats CPU cycles and RAM like they're the most precious things on earth, so a program will make live changes as it goes along (to conserve RAM and minimize disk IO), and is designed to fail in a dirty state (in the middle of everything, so you can't re-run it) on the chance that it'll preserve cycles. It's a real maintenance headache.

      --
      ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
    10. Re:The Unfortunate Reality of Maintaining Legacy by elrous0 · · Score: 1

      Screw all that complicated stuff. I have two words for them: gold toilets.

      --
      SJW: Someone who has run out of real oppression, and has to fake it.
    11. Re:The Unfortunate Reality of Maintaining Legacy by EvilBudMan · · Score: 1

      1.) Word

      BIG IRON

    12. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      Here in Brazil we are facing the very same problem. Our "SAA" keeps records of about 100 million people and pay every month 25 million others. It's already a work in progress and it due to the next two years. I think governaments should talk and trade these kind of expertise.

    13. Re:The Unfortunate Reality of Maintaining Legacy by Atzanteol · · Score: 1

      Nothing like gold on gold eh?

      --
      "Ignorance more frequently begets confidence than does knowledge"

      - Charles Darwin
    14. Re:The Unfortunate Reality of Maintaining Legacy by castironpigeon · · Score: 1

      If this were a commercial company, they would go out of business for making such a stupid decision.

      More likely they'd get a bailout.

      --
      mmmm...forbidden donut
    15. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      The US gov't IS out of business... We're bankrupt. No one has the balls to say it on camera, but every person with common sense knows what it means when (money in) - (money out) is consistently 0.

    16. Re:The Unfortunate Reality of Maintaining Legacy by SatanicPuppy · · Score: 1

      Learning curve...

      Coffee's sitting right in front of me, but it's too hot to drink...

      --
      ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
    17. Re:The Unfortunate Reality of Maintaining Legacy by thePowerOfGrayskull · · Score: 4, Insightful

      Everybody* else knew the language was dead.**

      *everybody: the disturbingly large subset of programmers who are unaware that COBOL and FORTRAN still power the vast majority of the financial and healthcare infrastructures of the world.

      **dead: working quietly in the background without need of constant updates and maintenance

    18. Re:The Unfortunate Reality of Maintaining Legacy by thePowerOfGrayskull · · Score: 3, Insightful

      The US gov't IS out of business... We're bankrupt. No one has the balls to say it on camera, but every person with common sense knows what it means when (money in) - (money out) is consistently 0.

      Every person indeed does: if we had a government that had "(money in) - (money out) = 0", "efficient" and "well run" would be the words you're looking for.

      Here in the real world "(money in) - (money out) = -11,000,000,000,000" and counting.

    19. Re:The Unfortunate Reality of Maintaining Legacy by bdenton42 · · Score: 4, Insightful

      There is nothing wrong with a functional 20 year out of date COBOL application. It is a bigger waste of company/governmental resources to rewrite it just because you want to use the language flavor of the month.

      So they should have rewritten it in 'C' 20 years ago, then of course you have to go OO and rewrite it to C++ 15 years ago, then Java was really cool so 10 years ago rewrite again, and now M$ has taken over the world so we better port it to .NET today, but you've just wasted 4 projects to simply get the existing functionality and your company is out of business (or added 0.0001% more to the national debt if you are the government).

      There are very good reasons to port old projects but just doing it because it's 20 years out of date is not one of them.

    20. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      The reason that they don't teach COBOL or any other real programming languages in college is today's youth can't grasp the basic concept of counting to eight, let alone learn basic logic needed to build a reliable program.
      If it can't be done with a mouse, they don't want anything to do with it.

    21. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      I wish I could have put it better... but I don't think anyone could.

      And it's so true.

    22. Re:The Unfortunate Reality of Maintaining Legacy by acvh · · Score: 1

      re: your "designed in reverse" observation. Right on. And not only that, but many organizations still use those metrics of cpu cycles and I/O to bill internal clients for running reports. Which explains why people here in my current office are afraid to request reports.

    23. Re:The Unfortunate Reality of Maintaining Legacy by ckaminski · · Score: 1

      I will tell you from hard-fought experience that rewriting massive DP type applications that worked mostly perfectly in COBOL, RPG and PL/SQL to Java is not necessarily the easiest thing in the world. Too much involved in frameworks, and the asynchronous nature of the web. I've seen enough such projects fail.

    24. Re:The Unfortunate Reality of Maintaining Legacy by mmaniaci · · Score: 2, Interesting

      NO! They already teach us enough superfluous crap to make me wish I was a business major.

      What colleges need to do is stop teaching history lessons and begin teaching students how to learn on their own. Face it, your job will not mimic what you learned in college no matter how good the school was, or how good of a student you were. Real life != school life.

      Don't give a man a fish. Don't teach a man to fish. Teach a man to learn how to fish.

    25. Re:The Unfortunate Reality of Maintaining Legacy by countach · · Score: 1

      To some extent you are right. WHen you rewrite it there is a 50% chance you will stuff it up worse, and it costs a whole hell of a lot of money.

      On the other hand there could be competitive advantages and/or productivity advantages to moving from a batch COBOL world to an online, always-on, web enabled modern infrastructure. How many times have we rung some company or ggovernment department, and they couldn't do something half rational because their computer system was way out of date?

    26. Re:The Unfortunate Reality of Maintaining Legacy by ksheff · · Score: 1

      I've read that around 70-75% of business code is in COBOL. It's not just old 20+ yr old programs either. There are still plenty of companies cranking out new programs in that language. At the time I wrote this, MicroFocus' stock price was about 319GBp. Not to shabby for a company selling development tools for a 'dead' language.

      --
      the good ground has been paved over by suicidal maniacs
    27. Re:The Unfortunate Reality of Maintaining Legacy by Scannerman · · Score: 1

      Its Not that likely that rewriting the code will actually improve anything.

      Remember that most of that code was written when programming labour was (relatively) cheap and hardware was expensive.

      Its likely to have been checked and optimised to a much higher degree than we consider justifiable these days.

      Chances of screwing things up and introducing significant new bugs are close to 100%

    28. Re:The Unfortunate Reality of Maintaining Legacy by Tired+and+Emotional · · Score: 2, Interesting

      Classic COBOL is something of a special case:

      No real user types. There were things you could do to fake this but its hard to maintain.

      Very limited procedure capability. There is a perform A through B capability (so the extent of the routine is defined at the call site! - but there is a way to avoid that using SECTIONs or internal labels) but there is no way to pass parameters - other than as global data. You can also write a subroutine as a separate compilation unit.

      Modifiable (at run time) GOTO statements. Nobody in their right mind would allow this in new code even back in the late seventies (well, I wouldn't at least) but there was a lot of legacy code written by people not in their right mind. If I remember correctly PERFORMing a bunch of code would mess with the last paragraph so that if you subsequently fell through that code it would not in fact fall through. Doing this is, of course, evil, but see remarks above.

      A large number of subsets. The language allowed you to subset. For example, one really nice feature was the report writer that would allow you to bang out a report program in a couple of hours, but lots of processors did not implement it. I actually had my own report program generator to avoid this problem.

      What all this means is while its not that much easier to write bad programs in COBOL than in other languages, if you work at it, you can really make life difficult for someone coming to clean up your mess later.

      --
      Squirrel!
    29. Re:The Unfortunate Reality of Maintaining Legacy by MobyDisk · · Score: 1

      The original poster was talking how they had COBOL code to maintain, and no one to work on it.

      As someone who maintains (part of) that 36 million lines of COBOL code...

    30. Re:The Unfortunate Reality of Maintaining Legacy by SatanicPuppy · · Score: 1

      Heh. One of the systems I maintain is an old MPE/iX server. Real P.O.S, and it's from an era so far back that when you ran a job, what it usually output was a print queue file.

      This stuff is extremely difficult to explain to people. The system wasn't written to output files...Why would it be? What would users do with them? Their terminals didn't even have disk drives! It's only real output went to a printer!

      So now, people say things like, "Well can you give me this in excel?" and we say things like, "Well, I can put it in excel, but it's going to look like a text file pasted into an excel document..." And they just don't get it. Talk to programmers:

      Me: "Yea, I was running a billing job today, and it crashed"
      Them: "Did you re-run it?"
      Me: "Sure, after I restored the database from a backup tape."
      Them: "...Da wha?"

      Or alternately: "Sure, but I had to manually edit the source code so it would pick up from where it left off, rather than starting over from scratch."

      It's just not the modern world. All our modern servers waste cycles all day long, but we're wedded to our goddamn legacy crap, and it takes vast amounts of time to do the same stuff.

      --
      ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
    31. Re:The Unfortunate Reality of Maintaining Legacy by khallow · · Score: 1

      I disagree here. A number of counterarguments spring to mind. First, code maintenance is a key part of any successful software's lifecycle (and even some failures too). While jobs maintaining ancient legacy code are relatively rare, jobs upgrading from legacy code are probably much more common. A course in maintaining legacy code also would give a programmer some more appreciation both for writing maintainable code for future generations (after all, it is a demonstration that your code may still be around in 50 or 100 years) and for seeing that the latest and greatest software isn't always necessary or desired. Ie, it's less important that the business's mission critical code is written in COBOL and runs on three PDP-11's in a basement somewhere, and infinitely more important that it never goes down. Weren't we complaining a couple weeks back about the arrogant, young whippersnappers coming out of college these days? An arrogant, young whippersnapper that has tasted the cream of history's programming languages (and more importantly, the horrors of maintaining the resulting code) at least has a bit more cause for being arrogant.

      Some people will desire stable jobs. Maintaining legacy code may be a hard job to get, but it will have inordinate appeal simply because it's not like the 2-4 year long gigs that seem common in the IT world.

    32. Re:The Unfortunate Reality of Maintaining Legacy by MobyDisk · · Score: 1

      There is nothing wrong with a functional 20 year out of date COBOL application.

      Tell that to the manager who can't hire anyone because they refuse to work on COBOL code. Which, was the issue the original poster brought up.

      That is like saying "There's nothing wrong with leaving data on these 8-inch floppy disks! There are perfectly fine!" Until you find out one day that there's no hardware that can read them.

      There is something very wrong with leaving something in a language so old that no one is willing to maintain it. If they rewrote it in C 20 years ago, then they would have a pool people willing to work on it today. And yes, they probably should be porting it to something else, so that in 20 years they still have people who can work on it.

    33. Re:The Unfortunate Reality of Maintaining Legacy by Fulcrum+of+Evil · · Score: 1

      Tell that to the manager who can't hire anyone because they refuse to work on COBOL code. Which, was the issue the original poster brought up.

      I doubt that very much. I'd work on COBOL for the right price.

      That is like saying "There's nothing wrong with leaving data on these 8-inch floppy disks! There are perfectly fine!" Until you find out one day that there's no hardware that can read them.

      Easy enough to virtualize hardware.

      --
      "We returned the General to El Salvador, or maybe Guatemala, it's difficult to tell from 10,000 feet"
    34. Re:The Unfortunate Reality of Maintaining Legacy by bdenton42 · · Score: 1

      On the other hand there could be competitive advantages and/or productivity advantages to moving from a batch COBOL world to an online, always-on, web enabled modern infrastructure.

      That certainly would qualify as a good reason to port. But knowing how complex financial systems actually work in the real world I think you are more likely to see an online, always-on, web enabled modern infrastructure glued onto the frontend of a database being updated by batch COBOL in the backend.

    35. Re:The Unfortunate Reality of Maintaining Legacy by Anonymous Coward · · Score: 0

      No, a (money in) - (money out) = SomePositiveValue would be efficient and well-run because it would provide a safety margin for the inevitable time when those first two values change, That would avoid having to fiddle around with tax percentages or cut critical services the first time the economy hiccups. Or borrow money.

    36. Re:The Unfortunate Reality of Maintaining Legacy by jcr · · Score: 1

      I cited Java as an example of a complicated language that a lot of people use; I don't advocate it as a replacement when porting large COBOL systems.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    37. Re:The Unfortunate Reality of Maintaining Legacy by Elbis.Reverri · · Score: 1

      Don't give a man a fish. Don't teach a man to fish. Teach a man to learn how to fish.

      First teach the man what the fish is - otherwise he might become a C-graded business major.

      That's what history, literature and all of those "useless" baseline subjects early on are for, in my opinion.

      I agree that learning on one's own is a very important skill. What I do not agree with is that it is in a college's responsibility (or capacity, for that matter) to get it into the heads of those who do not want to listen.

      A month or two of the sufficiently exhausting and boring summer work at about the age of 14 might be much more convincing than these people in the college with their books. And would vividly portray the difference between the school life and real life.

    38. Re:The Unfortunate Reality of Maintaining Legacy by Nefarious+Wheel · · Score: 1
      The problem isn't in the COBOL, the problem is in the CICS. The only viable alternative to supporting code designed for IBM's CICS OLTP platform was, for the longest time, Sun, who had a CICS emulator of sorts. All those bloody DSECT's...

      Of course this gives rise to the question -- who wants to switch from IBM to Oracle?

      (steps carefully away)

      --
      Do not mock my vision of impractical footwear
    39. Re:The Unfortunate Reality of Maintaining Legacy by SatanicPuppy · · Score: 1

      In my experience, the legacy stuff should mostly be overhauled, and thrown out...Very rarely have I seen legacy code from 20-30 years ago that is appropriate to modern systems, and worse, it requires hardware or virtual environments that are extremely wasteful of resources.

      I'm not particularly young, I've got more than a decade in the field, and a good chunk of that has been taken up with various legacy applications, from Y2K all the way up to the crap I have to support now.

      By and large, it's not good code. Things are hard coded that should never, in a million years, be hard coded. It's a maintenance disaster. I'm slowly replacing what I can, and the response has been very positive. Most people appreciate the difference in speed and just simply being able to do things that are extremely difficult in a legacy cobol environment.

      --
      ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
    40. Re:The Unfortunate Reality of Maintaining Legacy by khallow · · Score: 1

      But that bad code won't be instantly overhauled and thrown out. As I see it, while legacy code maintenance is sort of an extreme situation, it exhibits a host of real world problems that will face any IT professional multiple times over their career. The worst of these is that sometimes you have to deal with situations that are far from optimal with very limited resources and authority to do anything about it. As you say, you're slowly replacing what you can and getting positive response. Sometimes that's the best possible outcome.

    41. Re:The Unfortunate Reality of Maintaining Legacy by SatanicPuppy · · Score: 1

      Agreed. I guess what I'm saying is, that you should transition whenever possible.

      I do agree, however, that budgetary constraints often make it impossible to shift to something "new", and really, you can shift to the next best thing every 5 years, and it'll cost you a mint, and not necessarily provide you with any real benefits.

      --
      ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
  2. A really strong neural net... by Anonymous Coward · · Score: 2, Funny

    At $8.95/45 specimens (http://sciencekit.com/harvester-ants%2C-live/p/IG0034483/), the newly constructed Hex would have the most powerful neural net we've ever seen!

    But that wouldn't leave any money for the clacks...

  3. A big one by funehmon · · Score: 0, Offtopic

    No, really. That's it.

    1. Re:A big one by jo42 · · Score: 1

      Simply hand over $400 million to the chuckleheads at Google and keep $100 million for yourself.

    2. Re:A big one by mehemiah · · Score: 1

      clearly someone has mode points and NO sense of humor.

  4. Mimicking Private Industry? by eldavojohn · · Score: 4, Insightful

    Could you approach Google and ask them to license their ideas on server and data 'pod' technology for your sharded databases? I'm not saying build the whole thing like this but with $500 million, you could probably have a large section to search and sharded databases that mimics Google. I don't think there's anything wrong with following the leader in that department. This probably isn't the best solution for relational databases so I would think another architecture would be in place for your MySQL and Postgres traditional database layouts. And that would be just huge centralized servers running virtualized instances of Linux with MySQL or Postgres.

    --
    My work here is dung.
    1. Re:Mimicking Private Industry? by JonahsDad · · Score: 1

      Don't license Google's ideas. Instead, use Google's data centers in place of building your own. Just need a Google SSA (Beta), and it won't cost the government a penny.

    2. Re:Mimicking Private Industry? by Anonymous Coward · · Score: 0

      Google isn't the only one doing this. Sun is/was doing this too http://www.serverwatch.com/hreviews/article.php/3670621

    3. Re:Mimicking Private Industry? by Anonymous Coward · · Score: 0

      Totally agree. Anyhow, Google got all the personal data they need about us already, so they probably know more about each American than the SSA...

    4. Re:Mimicking Private Industry? by Zemplar · · Score: 1

      MySQL for critical financial data, are you mad? MySQL is fine for simple stuff, but if you need critical reliability with MySQL and have to use InnoDB ($$) and other performance killers on MySQL to make it reliable, just use Postgres if you want the best open source database. Otherwise, use Oracle, or hell, even SQL Server.

    5. Re:Mimicking Private Industry? by cayenne8 · · Score: 1
      "I don't think there's anything wrong with following the leader in that department. This probably isn't the best solution for relational databases so I would think another architecture would be in place for your MySQL and Postgres traditional database layouts. And that would be just huge centralized servers running virtualized instances of Linux with MySQL or Postgres."

      This is the govt. You're not gonna see mysql (really not gonna see this one for such a large datastore) nor postgres. It'll either be Oracle (I'd put my money on that), or maybe even DB2...depends on which contractor wins.

      If they go with DB2, likely they'll use AIX as the OS. However, they might be going with RHEL as an OS, linux has finally made it as a valid choice in the fed. gov. for and operating system. But aside from Linux and Apache...supported by a commercial company...you're not likely to see any other open source software used.

      Actually, I would have voted Oracle and Sun/Solaris as my best guess....not sure where they'd go now with the ORacle buyout.

      --
      Light travels faster than sound. This is why some people appear bright until you hear them speak.........
    6. Re:Mimicking Private Industry? by Prof.Phreak · · Score: 1

      This probably isn't the best solution for relational databases...

      Actually... that's exactly the architectures many enterprise scale relational databases take (not the transactional type ones, but data warehousing ones); which conceptually are mostly SQL interfaces to map-reduce...

      --

      "If anything can go wrong, it will." - Murphy

    7. Re:Mimicking Private Industry? by Anonymous Coward · · Score: 0

      Son, go back to kindergarten.

      While some of their apps may use MySQL (or more likely, Oracle or Sybase) for data storage the vast majority will be ISAM or flat text files with fixed length records.

      For real time (aka transactional) systems, their are probably running some derivative of CICS with MQ-Series.

      Lord, how I hate the spirit of Web 2.0.

    8. Re:Mimicking Private Industry? by Anonymous Coward · · Score: 0

      I think going to Google would be a fantastic idea, but they are likely to say no. Unless it was a join venture and Google housed government data? haha. But hey we have a private federal bank don't we? Who do Americans trust more - Googlers or Government? I know where my money is.

  5. Die Hard 4 by Anonymous Coward · · Score: 3, Funny

    Die Hard 4 pretty much set the standard for design here.

    1. Re:Die Hard 4 by nicolas.kassis · · Score: 1

      yeah, but I couldn't find the waiting room with the coffee machine.

  6. Why build one... by Bandman · · Score: 4, Interesting

    ...when you could have two for twice as much?

    OK, actually two 250 million dollar datacenters, but I love that quote from Contact.

    Why tie up that much money in one site when you could build two world class structures and have full redundancy?

    1. Re:Why build one... by Anonymous Coward · · Score: 5, Interesting

      I concur. There are 3 empty data centers along the I-81 corridor (within 2-3 hours of DC) that stand empty, reminders of the dot com bust. Why build new when you can retrofit an existing center.

    2. Re:Why build one... by untouchableForce · · Score: 2

      I believe it's actually Why build one when you can have two for twice the price. The twice and the price kinda rhyme so it rolls off the tongue a bit better and is more movieesque.

      --
      Moderation is not supposed to be used as an indicator of agreement.
    3. Re:Why build one... by timelorde · · Score: 5, Insightful

      Because they're not in my Congressional district?

    4. Re:Why build one... by JoeMerchant · · Score: 1

      I'd go for 5 @ $100M apiece - A-F in Vermont, G-K in Ohio....

    5. Re:Why build one... by necro81 · · Score: 2, Interesting

      reminders of the dot com bust. Why build

      I could think of three reasons:
      * Because those data centers are probably 10 years old already?
      * Because government data centers may have different requirements than internet startups?
      * Because 2-3 hours is too far away for social security administrators to drop by for a quick visit?

    6. Re:Why build one... by zerocool^ · · Score: 1

      There's nothing wrong inherently with a 10 year old datacenter. Guys, 2000 was 10 years ago. It isn't like we're talking about datacenters from the paleolithic era.

      If you already have a building with 5 or 10 megawatts of power run to it from the utility company, and already having some generators hanging around, why not use it? It's not like there have been quantum leaps in cooling or fire suppression or generator technology or how raised floor is put together.

      So what, you have to go and buy 30 million bucks worth of power switching, 10 million worth of UPS switching and batteries, and maybe 30 million worth of chillers and cooling apparatus. Then, slap a $500,000 raised floor, drop in a couple of gigabits of fiber transport, and hire a contractor to run the power and networking, and you'll have $400 million left to spend on racks and racks of Dell R710's or whatever strikes your fancy. Better than building a building from scratch.

      There are lots of government facilities "around" DC that aren't "in" DC, by the way, Herndon and Fairfax are full of them (just look for the unassuming buildings with the black fence and gated access that's back from the road in office parks).

      --
      sig?
    7. Re:Why build one... by Dare+nMc · · Score: 1

      that was my first thought to, if I were given that amount of money to build a data center, a second location with some testing facilities on site for me to work at, close access to silicon supplies, and a salt water bath for corrosion testing (thinking Bahamas type location, some research money/ time needed.) of course a steam chamber, and a cooling pool would all be needed, for ummm maintaining a constant atmosphere. I might even look over some ideas from bill gates $125 million dollar reference design

  7. We don't need no stinkin' data center. by Anonymous Coward · · Score: 2, Funny

    Build? I'd take it as a retention bonus and retire. I just want to immulate our most sucessful bankers.

    1. Re:We don't need no stinkin' data center. by Ogive17 · · Score: 1

      Build? I'd take it as a retention bonus and retire. I just want to immulate our most sucessful bankers.

      I wonder if the emphasis was intended...

      --
      "Action without philosophy is a lethal weapon; philosophy without action is worthless."
    2. Re:We don't need no stinkin' data center. by Bandman · · Score: 2, Funny

      the typo was really close to immolate...probably psychological

    3. Re:We don't need no stinkin' data center. by jank1887 · · Score: 1

      emulate? Anyway, I'd say it would be more of a telecom industry emulation. Promise one thing, say nevermind but pocket the cash anyway, never be held accountable.

    4. Re:We don't need no stinkin' data center. by Opportunist · · Score: 1

      I think it's really time to get religious again, but I tend to think more along the lines of the Maya and such. Let's immolate a manager a day until the gods of economy look favorable on us again.

      I'm damn sure that would work really, really quickly...

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  8. A really big one by dingo_kinznerhook · · Score: 0, Redundant

    At the price of 8.95/45 ants (http://sciencekit.com/harvester-ants%2C-live/p/IG0034483/), we could build the biggest neural net for Hex that the world has ever seen! But then again, we'd need to leave some funds for the clacks...

    --
    "God does not play Minecraft with the world." - Albert Einstein
    1. Re:A really big one by dingo_kinznerhook · · Score: 0

      My bad... this was reposted by me 'cause it looked like it failed when posting as "Anonymous Coward."

      --
      "God does not play Minecraft with the world." - Albert Einstein
  9. Sharks with frikken lasers by Anonymous Coward · · Score: 0

    Finally! An appropriate Slashdot story to respond with the Sharks meme!
    Yeah... I spend $499 million on computers/networks/power/air conditioning/ etc.
    But definitely $1 million dollars would be on Sharks with Frikken lasers

    1. Re:Sharks with frikken lasers by Bandman · · Score: 2, Funny

      Exactly.

      Just copy the general ideas of this datacenter in Sweden.

      Sharks and laser beams would fit right in.

    2. Re:Sharks with frikken lasers by pyster · · Score: 0

      Hi Stim

  10. How about a location first by schwit1 · · Score: 4, Insightful

    Putting the operation in a location that is cost effective would make the taxpayers very happy. The DC area is too expensive. Maybe an old missile facility in Wyoming or the Dakotas.

    1. Re:How about a location first by Anonymous Coward · · Score: 0

      I hope they start with defining the level of service requiered, also.

    2. Re:How about a location first by Anonymous Coward · · Score: 0

      Putting the operation in a location that is cost effective would make the taxpayers very happy. The DC area is too expensive. Maybe an old missile facility in Wyoming or the Dakotas.

      Good luck staffing it in that case.

    3. Re:How about a location first by duckintheface · · Score: 4, Interesting

      Look at the locations where Google is putting it's new data centers. They are in rural parts of the Carolinas on property adjacent to power plants. Google negotiates uninterruptable power contracts in fast growing states on cheap land.

      --
      "He took a duck in the face at 250 knots." -- William Gibson, Pattern Recognition
    4. Re:How about a location first by JoeMerchant · · Score: 2, Informative

      Your location also needs some competent staffing....

    5. Re:How about a location first by Anonymous Coward · · Score: 1, Insightful

      Look for job postings at some of these remote facilities - lots of jobs out there, because rural industry is very risky to the employee.

      If your employer pulls up roots, then its likely that you and your spouse lose both incomes at once and your home value drops precipitously and there are no other jobs for 50 miles around.

      That happened to my parents when I was growing up - it was a great place for my parents for 20 years. Then the major employer slashed employment. We, along with hundreds of others, had to abandon our house, the township went belly-up, and virtually everyone and everything moved away. The population of the township is now something like 20, with its central business being a gas station.

    6. Re:How about a location first by SirKron · · Score: 2, Insightful

      You can also negotiate allowing the power company use of your backup generators for their needs if during peak load times.

    7. Re:How about a location first by Anonymous Coward · · Score: 0

      Which is exactly why it needs to be located outside the DC area. The two agencies I have dealt with, BATFE and OPM, have gotten significantly better results by moving work from their DC offices to WV and central PA, respectively.

      There's a large facility in PA that is built in an old limestone mine that is working very well for the government. Well insulated, easier to control physical access and cheaper to build.

    8. Re:How about a location first by Anonymous Coward · · Score: 0

      Putting the operation in a location that is cost effective would make the taxpayers very happy.

      Taxpayers are never happy.

    9. Re:How about a location first by Anonymous Coward · · Score: 0

      The new Google Data Center is in Goose Creek, SC, which is just outside Charleston/North Charleston. This area actually has quite a large Tech. workforce, with consulting firms, programming firms, and SPAWAR.

      Just because it's not silicon valley doesn't mean you can;t find qualified people.

    10. Re:How about a location first by G-Man · · Score: 1

      As of 2007, based on median income 10 out of the 20 wealthiest counties in the nation were located in the DC metro area. As recently as 2000, it was only five. So now that the economy has tanked, where should we spend stimulus money? Why, in the wealthiest part of the country, where all our 'public servants' live. All hail Versailles on the Potomac!

    11. Re:How about a location first by Anonymous Coward · · Score: 0

      you mean an underground facility that was once a cold war military installation? Like this one: http://www.infobunker.com

    12. Re:How about a location first by Anonymous Coward · · Score: 0

      If Dr. Evil can find minions to work under a remote volcano, relocating a few techs and admins to Wyoming shouldn't be that big of a deal. On the plus side, you could probably install some of those giant wind turbines (what, 5 mil each?) and have more than enough power to take care of all the cooling and power you would ever need, and then some.

    13. Re:How about a location first by EvilBudMan · · Score: 1

      Or an old abandoned salt mine. Perhaps they could do that at Yucca Mountain. There is already sunk cost there.

      We have some brand new abandoned data centers here too.

      I think up the road from DC into WV and not Northern VA would be the way to go. Cheap and located close to the decision makers.

       

    14. Re:How about a location first by Buelldozer · · Score: 1

      So you contend there's no competent people in Wyoming or the Dakotas?

  11. Mantraps by n1ckml007 · · Score: 2
    1. Re:Mantraps by Bandman · · Score: 1

      I would definitely include mantraps in any new datacenter design, but I know of other datacenters that have them already. Some of them even have sensors to ensure that only one person at a time is in the trap. Crazy stuff.

    2. Re:Mantraps by Lehk228 · · Score: 1

      gotta watch out for those, consult admiral akbar as needed.

      --
      Snowden and Manning are heroes.
    3. Re:Mantraps by PitaBred · · Score: 1

      Hopefully not just weight sensors. Most NOC employees I've seen are at either end of the weight spectrum, very seldom in the middle.

  12. Something modest by IWantMoreSpamPlease · · Score: 4, Funny

    Then spend the rest on hookers and blow.

    Hey, the gov't does that all the time, why are you staring at me like that??

    --
    So rise up, all ye lost ones, as one, we'll claw the clouds.
    1. Re:Something modest by Miseph · · Score: 1

      Yeah, I've heard that Congressional party leaders are traditionally selected by a meeting of the senior critters over lines of coke on a stripper's tits.

      --
      Try not to take me more seriously than I take myself.
  13. Ummm.... by Wanon · · Score: 3, Insightful

    This is a really really bad place to ask how to spend $500000000....

    1. Re:Ummm.... by Opportunist · · Score: 2, Funny

      Yeah, he could have asked the government or investment bankers...

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    2. Re:Ummm.... by jo42 · · Score: 1

      Invest the $500 million with Madoff for a year. At 1% per month, you'd have $60 million more the next year to build even a bigger data center!

  14. ..near an industry that can use hot water. by paul.schulz · · Score: 4, Interesting

    Find an industry that would otherwise need a gas fired boiler and on-sell the heat.

    Other options:
    - Heated public swimming pool
    - Source of community/public heating

    1. Re:..near an industry that can use hot water. by jonnat · · Score: 1

      Find an industry that would otherwise need a gas fired boiler and on-sell the heat.

      To generate even low pressure steam at 75 psig, water should be heated to around 160C (320F), which is not possible with the heat extracted from a datacenter. (Even if it was possible, the largest energy input for steam production is the phase change. Also, steam producers usually operate in a closed loop with condensate returning to the boiler at temperatures close to saturation)

      The challenge to recuperating the thermal energy from datacenters lies on the low temperatures generated.

  15. Ask Google by mcwop · · Score: 2, Informative

    I bet they could do it for less, and on schedule.
    http://www.engadget.com/2009/04/02/googles-data-center-secrets-revealed/

    --

    "I don't think it's selfish, to eat defenseless shellfish." -NOFX

  16. What Kind of Data Center Can You Build With $500M? by Rik+Sweeney · · Score: 5, Funny

    Data Center: $10M*

    Hookers and Beer: $490M

    *I reckon I could get that down to $6M by cutting corners though, so that's another $4M for the beer :)

  17. pfffff thats easy by hviniciusg · · Score: 0, Redundant

    A bewolf cluster of all the ideas above plus the sharks whit friking lasers.

  18. Simple by Opportunist · · Score: 4, Funny

    200m for me, 200m for you, 100m for the guy in India who builds a data center.

    --
    We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    1. Re:Simple by Anonymous Coward · · Score: 0

      200m for me, 200m for you, 100m for the guy in India who builds a data center.

      $10M for the guy in India. That's equivalent to paying him $200M if he had to buy his groceries in the USA.

      Lower prices, Everyday!

    2. Re:Simple by Anonymous Coward · · Score: 0

      International I.T. outsourcing has punched a gaping hole in the tech sector of the U.S. economy.

      Here's a context in which to talk about the problem:

      "Will the United States send $500 million more American jobs to India, or use this money to help repair the American tech industry?"

    3. Re:Simple by Anonymous Coward · · Score: 0

      "Will the United States send $500 million more American jobs to India, or use this money to help repair the American tech industry?"

      "Who can then use that money to outsource more of their work to India".

  19. Easy by EvilDrMike · · Score: 0
    You get whatever I can get for $50 off ebay and a bill for slightly less than $500M for consultancy fees.

    EDM.

  20. I don't know... by Cornwallis · · Score: 5, Insightful

    ...but I'll bet you $500 million that: 1) It won't be nearly enough money; 2) It will be obsolete before it is finished; 3) It won't be finished before Social Security runs completely out of money (which will coincide nicely with my scheduled retirement); 4) [Fill in the blank]

    1. Re:I don't know... by Anonymous Coward · · Score: 0

      agree, 'specially about the money running out :(

    2. Re:I don't know... by Anonymous Coward · · Score: 0

      Profit!

      Captcha: Virtue.

    3. Re:I don't know... by PitaBred · · Score: 1

      Wait... you expect your social security contributions to be going anywhere BUT a black hole? Silly person.

  21. OR,,,, by phrostie · · Score: 2, Insightful

    or they could contract it out to google.
    someone who knows how to manage large data centers correctly.

    1. Re:OR,,,, by Bandman · · Score: 1

      It would be nice, but I think there's policy in place to put out for bidders, and I doubt google would bid or be the lowest, if they did.

    2. Re:OR,,,, by CraftyJack · · Score: 1

      Lowest bid isn't usually the selection criteria. It's usually 'best value to the government', which leaves some wiggle room.

  22. How government would do it by Anonymous Coward · · Score: 3, Insightful

    Dislaimer: I have worked for a contractor to the Air Force, and I have some insight as to government bidding, contracting, and results.

    Well, if I were responsible for results, I would get requirements from staff, send out RFPs, hire the best people, manage the project, and deliver on time and on budget a state-of-the-art data center.

    If I worked for the government, I would do the following:
      - Find a company I would like to work for as a six-figure lobbyist, and hire them without regard to experience or practicality. I will have personal contacts with the CEO, and if I don't, I soon will.
      - Get my "requirements" from that company, and have them provide the solution they specialize in without looking at my environment.
      - I would not supervise them. I am too important for that.
      - I would ask for more money as the project spirals out of control. The government would give it to me.
      - The project would drag on for a decade, would never finish, and would ultimately get scrapped. I wouldn't care, because I now work for the vendor, lobbying the government for more projects. I get my own private limo and driver, and I don't have to declare it on my taxes, unless I want a very visible government job again.

    Someone might raise a fuss in the public about this, but all that proves is that the government need more money to fix it.

    P.S. The contractor I worked for beat out a lower-bidding, "women-owned", "development-zoned", and much more local company. By any government calculus, the local company should have won the bid hands-down. But there were, shall we say, non-written reasons the local company lost and the gigantic out-of-state, double-the-bid, next door to DC company won.

    1. Re:How government would do it by Anonymous Coward · · Score: 0

      But there were, shall we say, non-written reasons the local company lost and the gigantic out-of-state, double-the-bid, next door to DC company won.

      I'll say it; it was the women-owned angle.

      But seriously, I once worked for a woman-owned company. Management was stupid, they thought they could do no wrong and they were always right (even in matters where they had no knowledge) just because they weren't men.

    2. Re:How government would do it by EvilBudMan · · Score: 1

      Politics, politics, politics.

      We'll I would like to start a company that you are trying to find. Six figures seems like a bargain so when do we have a deal?

      Or everyone could have their hands in the till, make money, even if it gets scraped like that Ultimate Warfighter scheme. They couldn't cancel one thing because everything was supposed to be able to work together. Is that what your talking about?

      It really seems like there is a lot of sunk cost without much to show for it, like the F-22. We could make quite a few more of them and I think we should because we have already paid for the development. Now you have the F-35. It's not cheap and it is bigger than a F-105 which was a huge single engine fighter of the Vietnam era.

      This stuff has been common since I can remember. I never could play because I just didn't know whom or how to approach a situation that is legal bribery. But if you want to run a business, you have to know how to grease the wheels. That's where the failure point of most small business really is.

      This data center that the government wants to build is pretty much off the shelf, but you are right they will go for a custom design just exactly like you said from what I have seen.

    3. Re:How government would do it by jdigriz · · Score: 1

      So what you're saying is we need to pay government employees more so private industry won't be able to easily bribe them to act against America's interests? I'm all for that.

    4. Re:How government would do it by t35t0r · · Score: 1

      "women-owned"? Let me guess, Microway.

    5. Re:How government would do it by Anonymous Coward · · Score: 0

      I see we worked for the same Air Force. You left out a few things, like "Ensure things required to do the job aren't in the contract, then bitch about being requested to do things 'not in the contract'. Demand more money when the contract is re-negotiated."

      Sorry I have to post anonymously... turns out it's not so easy for vets to go back to school in California, so I still need to be able to work as a contractor.

  23. Build a cloud facility by spike2131 · · Score: 2, Interesting

    Commodity hardware
    Full virtualization at the OS level
    And a second, mirrored data center on the other side of the country

    --
    SpyDock: Scientific Python in a Docker container
    1. Re:Build a cloud facility by Anonymous Coward · · Score: 0

      For 500m you probably could build a CloudBase - Captain Scarlet style.

      http://images.google.co.uk/images?hl=en&safe=active&um=1&ei=mp35SfqmO8HL-Ab1nZmuAg&sa=X&oi=spell&resnum=0&ct=result&cd=1&q=captain+scarlet+cloudbase&spell=1

  24. Easy ... by Anonymous Coward · · Score: 1, Funny

    I'd by 5 Macs ...

    (I love Macs, but damn ...)

  25. Me, personally? by JoeMerchant · · Score: 1

    For $500M I'd go for a nice laptop, on a beach, on my own private island. Maybe a NAS system with a few TB of storage and WiFi coverage for the island, couple of big screens on dedicated computers here and there, and possibly a cluster of Core i7 boxes to play with some heavy crunching.

    All told, $499.5M could go toward the real-estate and construction costs, staff, transportation, etc. $500K would cover my compute hardware needs quite nicely.

    When you analyze what the SSA ends up doing with $500M, you might find a shockingly similar pattern of administrative and facilities overhead.

  26. hmmm.... by eXFeLoN · · Score: 0

    a couple of tickets to a non-extradition country please. and an italian sportscar that gets really shitty gas mileage. fuck you tree hugging hippies.

    --
    My other sig is a knife wound.
  27. whats the point? by nimbius · · Score: 1

    its basically a madness engine if its for social security....

    that having been said i would secure my place as a microsoft certified partner early!

    --
    Good people go to bed earlier.
  28. WOODLAWN!!!11! by spywhere · · Score: 1

    The AC beat me to it: the Woodlawn data warehouse is diagrammed perfectly in Live Free or Die Hard.

    They could hire Justin Long (and John Hodgman?) to conduct guided tours...

  29. Not much on actual assets by MessyBlob · · Score: 1

    A lot of it will probably go to umbrella consultancy fees: spend $100m to learn how to spend $450m wisely among 'carefully chosen suppliers'. Yes, I know that adds up to $550m.

  30. Re:Hire more H-1bs! by value_added · · Score: 1

    To build a new data center for the Social Security Administration all you need is $200M for immigration lawyers to draft legislation to lift the H-1b cap, $200M to buy Congressmen to pass it

    I really don't get your point (or the joke, if there is one), but it's worth pointing out that influencing elected officials doesn't cost millions (short of large scale lobbying campaigns). If you glance at the political contributions received by influential politicians, you'll see amounts that are generally small.

    To take one influential and well monied example, Chuck Schumer largest contributor was Citigroup. Obviously, the subject of how money gets collected and targeted is more complicated, but you can go down the list and see for yourself how most contributions are in the thousands or tens of thousands of dollars.

    Now if you want to complain about the corrosive influence of money, stop to consider that the cost of a campaign (read "keeping your job") can be more or less attributable to voters needing TV commercials (non free in the US) to be informed and persuaded. Like most things, the cause and solution to most problem are found in the mirror.

  31. Why do they need a data center that large? by ciellarg · · Score: 4, Funny

    Congress has already bankrupted the SSA fund, so all they need is one computeer that can add and subtract "0" very quickly....unless they need something that can divide by zero :)

    1. Re:Why do they need a data center that large? by EvilBudMan · · Score: 1

      They need a system that works with imaginary numbers.

  32. Great! $500M to prop up the Ponzi scheme... by Anonymous Coward · · Score: 0

    I'll never see a dime of the money that's being extracted from me under threat of force by my own government under the pretense of caring for me in my old age, but at least the fat, seeping, sore-encrusted pussies in Congress and the White House can carry on the charade a little longer and keep raiding the Social Security Trust to finance deficit spending. Hey Obama, here's a reality check: our children will NOT look upon this time as the time America turned the corner into a new era of prosperity and enlightenment. They will look upon it as the time their parents robbed them blind and sold them into financial servitude to China.

    1. Re:Great! $500M to prop up the Ponzi scheme... by LVSlushdat · · Score: 1

      I know.. Don't feed the AC's... But THIS AC hit the nail dead on the head... I'm 59 and under normal circumstances, I'd be looking at retiring in about 6 years... but I've got a funny feeling that's not gonna happen... My 401K is now a .001K thanks to Wall Street, and how does anyone live on the monthly SS stipend? I know.. Dog food?? I want to thank the fat fuckin' criminals in DC for the last 50 years who have totally fucked this country up...
      Let's have a round of applause for these shitheads... Whether they have an R or a D after their name, they should be behind bars...

      --
      THANK YOU, Edward Snowden!! Americans owe you a debt of gratitude (whether they know it or not..)
  33. an underground bunker full of supercomputers by DragonTHC · · Score: 1

    and yes, they'll play doom.

    seriously though, I'd buy google data crates. one to match each US representative and then I'd place them across the US in those areas, which is the best indicator of population coverage.

    Then I'd spend the leftovers on an underground lair.

    --
    They're using their grammar skills there.
  34. Be Realistic. Dont be a 90s dotbomb. by pyster · · Score: 1, Insightful

    There are tons of already built data centers that have been abandoned. They already have much of the infrastructure required and just need some TLC. Using these already built data centers will allow one to have more than one data center, very important for disaster recovery, multi homing, and impressing your customers with your size. I would avoid building a new building from the ground up. Its a cost that will add no value considering the number of buildings available that can be repurposed.

    Make strong investments to make sure you can meet you power requires and can readily add more power in a reasonable amount of time. This includes battery piles, back up generators, fuel storage, and maybe even solar panels. Investigate new energy efficient cooling.

    It's also important that your data center have easy access to multiple carriers. Look for buildings that used to be ISP central in the late 90s and early 00's. Often these buildings will also already have supporting infrastructure.

    DO NOT BY INTO HYPE. Not everything needs to be cat6e or fiber. Use these were required and use cheaper technologies that have specs that will meet the requirement.

    Invest services that will add value to your customers. DNS, backups, router maint, firewall sevices, remote hands, terminal services, etc... Dont be afraid to sell your customer shelves, servers, etc... But for god sake, give them screws if they ask. This simple gesture goes a long way to make you not look like small time asshats.

    One of the biggest investments you can make is in a person who has real experience in the area and has the ability to get things done. Without someone who understands power, cooling, how to terminate various connections, telco, racks, project management, etc. your project is doomed to failure. Investing in a NOC that isnt full of monkeys will also be a great benefit. (keep them engaged with training and give them a sense of worth and you will create a team loyal to you. Abuse them and they will talk shit to anyone who listens). And your sales engine has to be stocked with people who can sell the services you are selling and can answer basic questions about those services. It might be a good idea to prove that you can sell these services before even breaking ground on the data center to begin with.

    Don't over invest and over build. Plan for the future, and use profits to build the next stage. Look at what is coming down the sales pipe and try to predict when you need to add on. Buy customer cabinets and wire them only after the sale has been made.

    This could be a great time to invest in experimental technologies for cooling, or to avoid cooling, solar power, etc. It all depends on what the building you find can and will accommodate. But its the bottom line you must always consider. Lots of dotbombs had grand ideas and good intentions and ended up just pissing away all their investors money. Dont dech your NOC out like it was the helm of the enterprise. Dont have large screen TVs and projectors displaying data that the NOC gets alerts on their work stations for.

    Oh, and seriously, dont be a jerk about letting your customers use the bathroom, vending machines, and whatever. And have some comfortable couches in the vending area that support rest and work. Some of your customers are going to pull all nighters and there is nothing worse than having to sleep on the floor in a puddle of your own waste chewing on a pizza crust found in the trash.

    Have real test gear on hand. If you cannot test a t1, ds3, dsl, pots, ethernet/fiber/coax, throughput, etc you will cause your employees and customers a lot of grief. I'd also put some money aside for a fiber fusion splicer, but dont buy it until you need it.

    Data centers can be extremely profitable. I know of one company who I believe had their data centers initial investment paid for with just a few customers in 4 months, after that they began to see profit. Those times might be a bit off, but not by much. (The data center in question I am talking about is in cleveland/garfield. Another option might be to partner with a successful company in another area.)

  35. I'd do the right thing... by steveb964 · · Score: 3, Funny

    Cardboard box, tin cans and string.

    I'd then proceed to give the rest to support the bailout of the severely ailing and deserving auto and financial institutions.

    sb

    1. Re:I'd do the right thing... by Opportunist · · Score: 2, Funny

      Once you're done bailing out the deservingauto and financial institutions, you should still have about 499m left (let's assume you bought a LOT of boxes, tin cans and a few miles of string...).

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    2. Re:I'd do the right thing... by steveb964 · · Score: 1

      Well played, well played ;)

      I didn't catch what you did there until I read it a couple of times.

      -sb

  36. Good money after bad... by rgviza · · Score: 0, Offtopic

    Rather than dumping more money into social security, they should cash everyone out with what's left and shut it down.

    Socialism is a losing proposition; I say cut our losses and spend that money on converting from an income tax to a flat sales tax, which would get rid of the IRS too.

    -Viz

    --
    Don't kid yourself. It's the size of the regexp AND how you use it that counts.
    1. Re:Good money after bad... by maxume · · Score: 1

      If you want to leave old people hanging, "cashing out" would net everyone $0. If you don't want to do that, "cashing out" would cost thousands of dollars per person.

      --
      Nerd rage is the funniest rage.
    2. Re:Good money after bad... by LatencyKills · · Score: 1, Offtopic

      Why is this modded funny? It's just about the only solution that makes any real sense. Close social security, and people who really need it end up on welfare instead. How would that be any different from "means testing" which is what is almost certain to happen anyway? The alternative seems to be to (a) tax present workers to death, virtually guarenteeing that they'll need SS when they retire, and then wash, rinse, and repeat with the next generation or (b) prop up SS by printing more fake government money and let the next generation figure out how to repay the debt (hint: see (a)).

      --
      Jealously hoarding mod points since 2007.
    3. Re:Good money after bad... by ckaminski · · Score: 1

      I'll tell you what, I'll happily cash out now and give my share (negative or not) to those already retired or within 10 years of the retirement age, to stop future garnishments from being removed from my paycheck.

      I like the *IDEA* of social security, a way of paying into the Treasury and earning a nice 3-5% on money, just as a hedge against inflation. I *LIKE* that idea. I don't like funding it with my children's paychecks, however.

    4. Re:Good money after bad... by maxume · · Score: 1

      I'd be pretty okay with that. I think the only political possibility is to choose to opt out of future benefits in exchange for paying in slightly less.

      --
      Nerd rage is the funniest rage.
  37. Re:a mote by Keeper+Of+Keys · · Score: 1

    Just a mote?! Must be microscopic sharks...

  38. A distributed data center approach by idontagreeWhy · · Score: 1

    Give away almost 5000 pcs or maybe more.....
    With conditions pc must remain on 24/7 , they must pay for Internet service - and allow use of grid computing software.

    http://boinc.berkeley.edu/
    http://setiathome.berkeley.edu/
    cooling cost - almost 0
    power cost - almost 0

    Mark

  39. What to do with $500 Million? by baKanale · · Score: 1

    What kind of data center would I build with $500M? I don't know, but I imagine it might look something like this...

  40. James Bond Data Center by carkb · · Score: 1

    Of course you would want to have a moat filled with Sharks with Frick'en Laser Beams mounted to their heads!!

  41. Re:Hire more H-1bs! by Baldrson · · Score: 1

    If it's that cheap to buy Congressmen then just reallocate $150M from buying Congressmen to buy more H-1bs so we can dispense with the datacenter entirely: Just have a huge call center with people instead of 'pooterz! More Green Jobs!

  42. Re:a mote by mehemiah · · Score: 1

    *Sigh* judging from your rating no one got this Austin Powers reference

  43. Since you asked... by Anonymous Coward · · Score: 0

    Just the other day I was doing back-of-the-envelope calculations about what you could do with huge amounts of storage.

    With drive space costing around $100/terabyte some interesting things seem quite feasible, for example IMDB has around 700,000 titles listed. A full DVD rip of each and every one would use around 5 petabytes at a cost of a little over half a million dollars. Half a billion buys you enough space for a 2 hour biography of every living person on the planet, but you would have to use 700mb rips :)

  44. perhaps a more basic question... by Anonymous Coward · · Score: 0

    What kind of data does the social security administration have that requires a $500 million dollar data center? For $500 million you can get yourself an AWFUL lot of computing power, but I have to think that the VAST majority of the processing that we're talking about here is simple accounting and administrativa.

  45. Re:Hire more H-1bs! by mehemiah · · Score: 1

    To build a new data center for the Social Security Administration all you need is $200M for immigration lawyers to draft legislation to lift the H-1b cap, $200M to buy Congressmen to pass it

    I really don't get your point (or the joke, if there is one), but it's worth pointing out that influencing elected officials doesn't cost millions (short of large scale lobbying campaigns).

    Are you the bum with no sense of humor thats modding all the Cynics as trolls? If I must explain, he says that you can you can build a huge data center with immigrants and old XP boxes networked together. Yes, there Do exist Windows Clusters

  46. Re:Hire more H-1bs! by Hijacked+Public · · Score: 1

    Voters don't need TV commercials, the candidate does because his opponent has them.

    Also, if you don't think politicians are a step ahead of a law they passed to 'open' campaign contribution information you are fooling yourself.

    --
    "Sacrifice for the good of The State" - The State
  47. Servers in the sky by oren · · Score: 1

    http://www.server-sky.com/

    The idea is to launch a lot (zillions) of tiny (grams) solar-powered servers to orbit. This means you have no power of cooling issues. It sounds pretty crazy on the face of it, but if it costs ~$1G to build a data center, it may actually be economical. There are a ton of practical issues, of course - the site goes into them in some detail.

  48. This gives new meaning to... by Anonymous Coward · · Score: 0

    Distributed Computing. They will in fact need a much larger and more powerful datacenter to handle the "distribution" load proposed by B.O.

  49. OH GIVE ME A BREAK! by Anonymous Coward · · Score: 0

    For $500million I could build a supercomputer AND put a man on the moon. The only data centers that cost more than $1million are the pa-cheese-mo Micro$oft + Oracle + .

  50. Re:a mote by Anonymous Coward · · Score: 0

    Homonym... ho..ho..homonym.

    MOAT! IT'S A MOAT! NOT A FUCKING MOTE!

    rage off.

    I don't know what irritates me more, the fact that the FP used the wrong word or the fact that someone else read it back with the same error thus canceling the mis-meaning.

  51. I do know by copponex · · Score: 1

    Here.

    Trustees Reports issued over the last several years have indicated that Social Security's Old-Age, Survivors, and Disability Insurance (OASDI) Trust Funds would become insolvent sometime in the next 30 to 40 years under the intermediate set of economic and demographic assumptions provided in each report. Various proposals have addressed this long-range solvency problem. These proposals are generally intended to restore, or largely restore, solvency for the long-range period (the next 75 years).

    So, we need to come up with some changes to the system in order to keep it solvent in 40 years. This is not an emergency. Recent market events have once again illustrated what a terrible idea it is to tie retirement to something as volatile as the stock market.

    And, like all of the fiscal nightmare scenarios cooked up lately, it's easily fixed by reducing our military spending. Here are the contracts we awarded just yesterday, which totals $1,250,643,816.00. And that only reports contracts worth less than 5 million dollars.

    1. Re:I do know by Cornwallis · · Score: 1

      Or they could do something really novel like let *me* handle *my* own money bypassing SS entirely. Kinda like, oh...Congress is allowed.

    2. Re:I do know by CorporateSuit · · Score: 2, Funny

      Or they could do something really novel like let *me* handle *my* own money bypassing SS entirely.

      Careful, you try not paying your taxes and Obama will tap you as a cabinet member so fast your head will spin.

      --
      I am the richest astronaut ever to win the superbowl.
  52. Besides hookers and blow... by rAiNsT0rm · · Score: 1

    Seriously I would give my business to the vendors and hardware manufacturers who are committed to America. Force the equipment to be made here, with U.S. labor start to finish and supported by U.S. labor until the contract expires.

    You want to get the country back on track, rather than just giving handouts force the change to happen with the money already being spent.

    That said, I would ensure it is heavy on virtualization and solid blade servers/chassis. A nod needs to be given to "green-ness" and every effort to create the absolute best all around solution for the money.

    I hate when just because something is government numbers like $500MILLION (half a BILLION dollars) is looked at like chicken scratch. It is a lot of money, more than many have to build data centers that do as much of not more. Stop acting like everything in government HAS to cost so damn much and it will!

    --
    http://teasphere.wordpress.com - A little spot of tea
    1. Re:Besides hookers and blow... by stubob · · Score: 1

      Is it even possible to build a "Made in America" computer?

      --
      Planning to be moderated ± 1: Bad Pun.
  53. $500M *GOVERNMENT* Data Center? by Anonymous Coward · · Score: 0

    Well, since it's government money and a government agency's data center... For starters, it had better be designed from the ground up to provide easy, effortless and unfettered access for all the Federal law enforcement agencies to be able to snoop thru any and all data contained inside it... with impunity, and completely disregarding any confidentiality of any citizen's data.

  54. Re:Hire more H-1bs! by Anonymous Coward · · Score: 0

    So true. The biggest hard sell in the world is when ad agencies convince businesses they really need their services because "all your competitors use us!"

  55. Re:What Kind of Data Center Can You Build With $50 by Pitr · · Score: 1

    I don't have any mod points at the moment, but if I did, I'm not sure if I should mod this "Funny" or "Insightful"...

    --

    --Not to be worried, Pitr fix.
  56. What to buy?? by scrappy64 · · Score: 0

    Avocent Data Center Solutions!! (shameless self promoting).

  57. 3 Servers = $10M by Anonymous Coward · · Score: 0

    I've bought (3) $3.5M servers for a single project, that didn't include storage ($1.5M) or software ($10M+).
    $10M doesn't go as far as you think.

    In data centers, you need gas turbine generators, battery banks, redundant power feeds from different substations, cooling, dust suppression, EM measurement, power cable management, network cable management, airflow design, noise design, vibration management, and policies, testing, and procedures to maintain all this stuff.

    Then you build the core network for different network zones - keeping your backup areas as far from the internet as possible. Just a few network zones:
    - Internet Web
    - Internet DB
    - Internet Server Management
    - Internet Server Backup

    - Internal Web/DB
    - Internal Management
    - Internal Backup

    - Protected Web/DB
    - Internal Management
    - Internal Backup

    - RASM Gateways

    - Network Management and configuration

    As you can see, this gets complicated for an enterprise. If you don't do these, I'd have concerns about your security.

    1. Re:3 Servers = $10M by Anonymous Coward · · Score: 0

      I've bought (3) $3.5M servers for a single project, that didn't include storage ($1.5M) or software ($10M+).

      hahaha. seriously. i would have loved to be the one selling that to you.

    2. Re:3 Servers = $10M by khallow · · Score: 1

      Well, we can go back to Social Security and point out that unfortunately, our costs turned out to be much higher than expected due to the user changing the requirements. Cost plus contracts for the win! Besides who spends just $490 million on hookers and beer?

  58. Re:a mote by digitig · · Score: 1

    It would have been easier to spot had the poster known the difference between "mote" and "moat". I for one couldn't tell what the poster was on about, because I naively thought "mote" meant "mote".

    --
    Quidnam Latine loqui modo coepi?
  59. Virtualize It. by Anonymous Coward · · Score: 0

    I'm not going to say 'go green', but you have the opportunity for fully a redudant virtualized environment. Power, Cooling, and likes...

    Get some nice Type 1 Taclanes in there.

    O yea, harden the crap out of the systems. Take away their employees' thumb drives like they did mine.

  60. Did some work there in '99 by bryan1945 · · Score: 1

    Or around '99. Anyway, one of our jobs was replacing token ring with ethernet! I'm talking replacing the fat cables. Ugh, that was fun. Their closets were horrendous. We had to rewire the phones, too, for some reason I forget now. The server room was completely under-AC'd. (At least they had a raised floor). All kinds of conduit issues, electrical issues (underpowered circuits, non-grounded circuit boxes). The building itself was ok, but would have to be gutted, and I'm not sure if the infrastructure would be able to handle current, modern equipment even then. I know it sounds like a lot of money, but it's probably a better move in the long term. This is purely from an equipment and infrastructure viewpoint that I saw.

    --
    Vote monkeys into Congress. They are cheaper and more trustworthy.
  61. Think Shoeless Joe here.. by Anonymous Coward · · Score: 0

    Build it and they will come...
        With the economy in flux, the staff will move to cheap parts of the US.. even with the wind, cold, and rednecks to deal with.

    1. Re:Think Shoeless Joe here.. by ksheff · · Score: 1

      No, they can just hire people from the surrounding universities. They most often leave those states to find employment in their field and would be happy to stay (or move back).

      --
      the good ground has been paved over by suicidal maniacs
  62. why release the figure by Anonymous Coward · · Score: 0

    i like to ask the govt to first assess what they are after. saying hey everybody i have 500million bank account isn't really going to create much competition. it just cost the people more money.

  63. Hawaii! by Anonymous Coward · · Score: 0

    It's not what you build, it is where you build it!

  64. The important thing to ask... by Anonymous Coward · · Score: 0

    But will it run crysis?

  65. Re:a mote by Arthur+Grumbine · · Score: 1

    Wow. You are really butt-hurt about not being modded Funny for your anonymously-posted, misspelled, generic joke.

    --
    Now that I think about it, I'm pretty sure everything I just said is completely wrong.
  66. What's It Storing? Your Benefits Data by 1sockchuck · · Score: 1

    This is a project they should get right. Social Security's data centers maintain earning and benefits information for nearly every American worker, processing 75 million transactions per day. "All of our plans depend upon a strong, 21st century data center," the agency said in a recent document describing its needs. See Data Center Knowledge for more on this. Regarding the location, the agency says the new facility would need to be within 40 miles of its current location due to "data linkages" - presumably a reference to the ability to perform real-time active-active backup, where distance limitations of storage networking protocols come into play.

  67. Swimming Pool! by Anonymous Coward · · Score: 0

    One with a really nice rooftop swimming pool!

    IT folks should have the good life occasionally. Unfortunately, with most IT shops, you might have to ask Bubba to put the suntan lotion on your back.

  68. Re:What Kind of Data Center Can You Build With $50 by Anonymous Coward · · Score: 0

    What? No blackjack? What kind of bender unit are you?

  69. The Government, Improving. by SEWilco · · Score: 1

    As this is a government project, for that much money they can buy ten laptops with the required three-button Teflon-ball mice and ergonomic anti-Teflon mousepads.

  70. What I'd give them for 500 Million by Anonymous Coward · · Score: 0

    The same thing they will get from any other contractor.

    1) a proposal filled with moving forward market speak, technobabble and vague promises of eventual digital valhalla.

    2) cost overrun reports and inflationary figures.

    3) bank the additional 500 Million

    4) have the project scrapped after 3-5 years.

  71. Ask Google - appropriate! by Chris+Pimlott · · Score: 1

    Yes, don't you hate it when people don't ask google first?

  72. Wyoming? Two words: by modecx · · Score: 1

    Wind power.

    --
    Constitutional rights may be respected, repealed, or modified; but they must never be ignored.
  73. That depends ... by PPH · · Score: 1

    ... on management's competence. I used to work for a company that burned through about $300 million one one IT project. Effectively, it was all lost (I say 'effectively' because the project exists in the form of a couple of servers, just so they don't have to write down 0.3 billion on an annual report and have the BOD see it). Hire these people and $500 million will get the footings poured.

    "What? You want the walls and roof? That's gonna cost you more. By the way, that's a nice little Social Security Administration ya' got there, buddy. It'd be a shame if something happened to it (Heh, heh)."

    --
    Have gnu, will travel.
  74. Give me the money and I will tell you by Anonymous Coward · · Score: 0

    Give me the money and I will tell you... from various resorts from around the world how the project is being delayed.

  75. Old Tech Costs? by thogard · · Score: 1

    Was it cheaper when they did it all with paper files?

    1. Re:Old Tech Costs? by davburns · · Score: 1

      Was it cheaper when they did it all with paper files?

      Yes, but mostly because there were a lot fewer people back then. (Remember, that even sorting is O(N log N) -- and you have to do that to get the right papers in the right files. I would guess that there needs to be lots of O(N^2) operations to catch fraud. 300,000 Americans is a big N.

    2. Re:Old Tech Costs? by davburns · · Score: 1

      300,000 Americans is a big N.

      Erm, 300,000,000.

  76. Yeah, it's not like they can just print more money by hudsonhawk · · Score: 1

    I mean what do you think our government is, a government?

  77. FTFY by prisoner-of-enigma · · Score: 1

    "So, if the government forcibly took $500 million from working families nationwide to spend on unneeded pork project in some Congress-critter's district what would you buy and how would you build it?

    There, I fixed that for you.

    --
    In the end they will lay their freedom at our feet and say to us, Make us your slaves, but feed us. - Fyodor Dostoyevsky
  78. Soup to nuts versus soup to nuts... by Anonymous Coward · · Score: 0

    Hmm, let's think about this shall we?

    If DATABASE = DB2 (IBM)
    and if IBM offers 'end to end' solution,
    then OS = AIX (IBM)

    Wouldn't Oracle owning Sun Microsystems have a similar result?

    If DATABASE = Oracle (Oracle)
    and if Oracle offers 'end to end' solution,
    then OS = Solaris (Oracle)

  79. I'd start by by bugs2squash · · Score: 1

    delaying the program, take advantage of Moore's Law.
    Then I's spend $100MM on having someone develop better servers that don;t need so much infrastructure (cooling, power, space).
    Only then would I start looking for a building.

    --
    Nullius in verba
  80. Re:a mote by RicardoGCE · · Score: 1

    Isn't "homophone" the word you're looking for?

  81. HPOD by pbhj · · Score: 1

    Did anyone mention HP POD, appears to be an off-the-shelf containerised server farm like Google's except that you can buy them - http://www.hp.com/go/pod.

    One big shelf, electric and cold water.

  82. Heat Exchanger/AC Hybrid by Vastad · · Score: 1

    I wish to add that one should seriously consider a heat exchanger/AC hybrid system for temperature management rather than pure AC.

    You'll save a ton on electricity bills, lower electricity consumption and reduce maintennance and use of refrigerant. It's all very ecologically friendly as well as having the more important bottom-line: Cost savings.
    I don't see it mentioned, but if this data center is in a climate that does experience cold seasons, then you automatically have central heating redirecting the data center heat to any neighbouring buildings. If you want to look really long term, you might even look into some sort of heat pump that will create electricity for the building, or to sell back to the utility company.

  83. Re:a mote by mehemiah · · Score: 1

    I wasn't the one who posted it, its just that there was an earlier post who was also modded troll when I thought it was funny. In the mean time, TODAY I have mod points now but I've already commented so I can't mod this comment (or post)

  84. Re:a mote by mehemiah · · Score: 1

    I read enough on the Internet to understand most spelling errors.