Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror
×
Slashdot.org News

Welcome to the New Slashdot Chicago Cluster 149

Thanks to everyone who tested on Friday, as well as to all of SourceForge's netops crew, our corporate overlords at SourceForge for paying the bill, and of course all the engineers on Slashteam- Jamie McCarthy, Tim Vroom, Chris Nandor, Chris Brown, and Scott Collins, we are now running on the new iron in a cage in Chicago. We'll run a story in a few days about the ridiculously overpowered new hardware we have now, but now is the part of sprockets where we dance.
This discussion has been archived. No new comments can be posted.

Welcome to the New Slashdot Chicago Cluster

Comments Filter:
  • by schon ( 31600 ) on Saturday May 24, 2008 @10:17PM (#23533307)

    now is the part of sprockets where we dance.
    Touch my monkey!
  • Down time? (Score:2, Interesting)

    by russlar ( 1122455 )
    I tried to log on around 2300 EDT Saturday, and the connection timed out. Was the downtime planned, or did Neal eat the wires again?
  • Slashdot moves to the true center of the Tech Universe!

    We expect to see the entire Slashdot team at Bluesfest and Taste this year.
    • Re:Finally! (Score:5, Insightful)

      by JWSmythe ( 446288 ) <jwsmythe@@@jwsmythe...com> on Saturday May 24, 2008 @11:49PM (#23533739) Homepage Journal

          Chicago is the center of the universe? :)

          Actually, my work is considering where to move it's servers. It involves a HUGE amount of fact finding. Chicago is one of the places they want stuff, but that's for customer reasons, not for "center of the universe" reasons. Our locations are chosen based on current customer usage, and statistical information I gathered at previous jobs. When you have 8 million users/day from around the world, those demographics stick in your head real well. :)

          In my research, I found the best places to be are.

          New York City. 111 8th ave, 60 Hudson, or 25 Broadway. The selection would be based on provider interconnects and availability. Some providers service all three locations with their own private interconnects, so it really doesn't matter.

          Los Angeles. One Wilshire, or one of a few select locations nearby, again with private interconnects to One Wilshire.

          Miami. Near or at 1 NE First St.

          Chicago. Near or at 427 S La Salle St

          The runners up are:

          Chicago
          San Jose
          Amsterdam
          Frankfurt
          London
          Paris
          Tokyo/Osaka

          In time, I'd like to have equipment in all of those locations. Or we can go the Akamai route, and put stuff anywhere there's a rack. :) I swear, they're everywhere I've had an opportunity to wander the colo space.

          For just about any provider of English based contact, the rankings of customer location by major geographic area are:

          North East United States
          South East United States
          Europe
          Western United States

          Obviously that would be skewed for the content. For example, a Japanese speaking site, with local interest content would be best placed near JPNAP in Tokyo or Osaka. Likewise, a Russian site with say daily weather reports of Siberia would probably want to be in Chelyabinsk, Russia, and you probably want to use Rostelecom.

          I noticed that Slashdot is now using Savvis. They were offering an amazingly cheap deal on bandwidth recently. I wasn't actively pursuing the bandwidth side, I was looking for the physical location side where my providers of choice would be. I'd be willing to bet they're in the Telegraph building. I'm curious now to who's suite they're in. :)
      • Indeed, all of my traceroutes from all over end terminating via Savvis, and that makes me cry.
      • by jbengt ( 874751 )
        "Chicago. Near or at 427 S La Salle St"

        Out of curiousity, what is there that makes that location appealing?
        Looking on Google maps, I do see a lot of what looks like dry-coolers on the roof. (resolution isn't good enough to tell for sure, they may be condensing units)
        By coincidence, last summer my company bid on a job for a major financial company across the street from there, though we withdrew at the last moment due to concerns about the scope.

        • by SIGBUS ( 8236 )
          427 S. LaSalle St. is the old Telegraph Building, once a major Western Union facility. Nowadays, it's a big co-lo center, with various data providers and CLECs.

        • Sigbus got it. It's a major telecom building. All the big players that I've looked at are in there. As far as I can tell, that's the MAE-Central IX. It if's not that building, it's one damned close. :)

          Across the street is usually good in internet terms. They'd just have big fiber run under the street, and be very happily connected. More than likely, that building would be lit up too.

          My building of choice for LA isn't actually One Wilshire, but a building 6
      • Akamai is everywhere because that's the whole point of their business. They cache content for their customers, and their software finds the nearest server to an individual client, and uses that as a mirror. This is fast (not many router hops to get to your nearest akamai server) but needs a ton of servers all over the place. Akamai thus has a ton of servers, all over the place.
      • Los Angeles. One Wilshire, or one of a few select locations nearby, again with private interconnects to One Wilshire.

        Yeah, about that: keep in mind that One Wilshire sits right on top of the (very active) Wilshire fault. The building is supposed to be seismic-safe up to 7.0 on the Richter scale, but it's still something to consider when weighing your options.

        I used to work at a place in Beverly Hills that sat on the other end of the Wilshire fault. When I pointed out to my boss that his choice for the new data center sat on the same faultline as the office, he about crapped himself. Ah, memories, they'll keep me warm in

        • I was out there for a few years. The building we used had direct fiber to One Wilshire, but their building was suppose to be save to a 9.0 earthquake. In their advertising they say the building will only shift 3/4" in a 9.0 earthquake. Hopefully they never have to prove it. :)

          I only felt a few while I was there. A shaking 3.5 while I was in Glendale, and a rolling 4.0 while I was in Northridge. Rolling earthquakes are weird if you're on the second floor. :) I rolled away from my desk
  • ... several times.... before it took.

    Congrats. And hopefully it won't be the kind of upgrade the last four ISPs I've delt with did..... an upgrade to less... quite the opposite of the claims.
    • by kesuki ( 321456 )
      you think having to try several times is bad... try not being able to log in at all with your browser of choice and being told 'firefox works though' as if i should switch from opera to firefox because slash has a horrible login bug somehow? great just great.
  • Obvious question... (Score:5, Interesting)

    by JustinOpinion ( 1246824 ) on Saturday May 24, 2008 @10:24PM (#23533347)
    So... what is going to happen to the old hardware? Are you going to going to scrap them? Hand them over to sourceforge? Sell them to another company?

    Or auction them off to your readership for charity?
    • by Precision ( 1410 ) * on Saturday May 24, 2008 @10:31PM (#23533375) Homepage
      Most of the old hardware is exactly that.. really old hardware.. some will be repurposed.. but most will be scrapped.
      • Re: (Score:2, Funny)

        by nospam007 ( 722110 )
        In Chicago servers get stolen, perhaps you should keep them a bit longer.
        • by Jeff DeMaagd ( 2015 ) on Sunday May 25, 2008 @12:10AM (#23533837) Homepage Journal
          What you need to do is switch the faceplates so it looks like the old hardware has the new faceplates, so you can stand to lose the "new" hardware without really losing anything of value.
          • Re: (Score:3, Funny)

            by Provocateur ( 133110 )
            So when will you break the news to The Robotic Overlord that he is NOT really new, but made of scrap parts, and we only had a new faceplate riveted in, and implanted 1 Gig's worth of fake memories, huh? Huh?

            So that when he asks, Is this all true? You reply with a sardonic tone, Remember all those dupes?
      • It can handle a constant slashdotting. It cant be that bad. :P
      • "Scrapped" has such an ugly, ungreen conotation.

        I hope slashdot talks with computer recyclers about the cast-offs. Places like Free Geek [freegeek.org] in Portland OR use volunteers to break systems down into reusable components, test them, and reassemble what still has some life let in it into working FOSS-based systems. Junk that can't be re-used is recycled in appropriately. A couple of tons of obsolete or failed CPUs sitting in large bin is a sight to behold, and is worth a fair bit for the gold content.

        Most of th

    • Re: (Score:2, Funny)

      by az1324 ( 458137 )
      I heard Twitter might be in the market.
      • Only so he can find something else to install GNU/Linux on so he can praise it to high heavens.

        What were we talking about again? ;)
  • OH NO! (Score:2, Funny)

    Oh no! Cowboy neal's porno cluster is up and running, its a damn shame to see 100tb of porn just laying around....
    • Re: (Score:3, Insightful)

      If only there were a large, dedicated community of introverts who could help him!

      The only down side is that we might scare away NewYorkCountryLawyer since he has morals and standards. There's a good chance we'd get a lot of RIAA lawyers to the site, though...
  • SourceForge (Score:5, Funny)

    by friedo ( 112163 ) on Saturday May 24, 2008 @10:31PM (#23533373) Homepage
    So now that SourceForge has upgraded Slashdot's fancy-pants hardware, when are they actually going to make sourceforge.net not suck so much?

    Just kidding. I love you guys.

    But seriously, sourceforge.net sucks balls.
    • If they could just put the link to project's web page in project's summary... Each time I find an interesting project I have to manually type someproject.sourceforge.net in the address bar. Fixing only this will actually improve searching for stuff by 200%.
    • Re: (Score:3, Insightful)

      by rho ( 6063 )

      I hate it when SF automatically starts a download. Most of the time I'm not downloading to my local machine, I just want the download link so I can paste it in a terminal window for wget.

      It's weird to me because you just KNOW SF is aware that this is annoying and useless. Click a link to download. Don't javascript the download. Morons.

      • by ahaning ( 108463 )
        I found last night that you can actually wget the prdownloads link and it will download the file rather than the webpage linking to all the mirrors. Pretty nice. I also have no idea what the "pr" in "prdownloads" means.
      • by zobier ( 585066 )
        NoScript, duh!
  • Here they have come across the body of a server, which in itself is not so disturbing. Until it is turned over to reveal... Ants!

  • by Hacksaw ( 3678 ) on Saturday May 24, 2008 @10:33PM (#23533389) Homepage Journal
    Upgrades are hard and require smarts and planning. Congratulations, I wish you good ROI.
  • by SethJohnson ( 112166 ) on Saturday May 24, 2008 @10:35PM (#23533393) Homepage Journal


    Do you guys have a description of the migration steps hidden away in a journal somewhere?

    Appreciatively,

    Seth
    • Well, it looks like they're in the new Equinix facility that's about 2 miles from my house right now.

      Anyone care to pass me the cage number so I can go visit my hardware and take some pics? ;-)
  • by I Like Pudding ( 323363 ) on Saturday May 24, 2008 @10:35PM (#23533395)
    For I am but a head in a rusty metal box.
  • Search? (Score:2, Informative)

    by Das Auge ( 597142 )
    Well, the search feature isn't working.
  • We'll run a story in a few days about the ridiculously overpowered new hardware we have now, but now is the part of sprockets where we dance.

    All we need is a fake story on the new Apple Newton v2 covered in grits to see how overpowered it is. :P

    • Re: (Score:3, Funny)

      by corsec67 ( 627446 )
      Add Natalie Portman as the spokesperson, and that would indeed be quite a test of new hardware.
      • Add Natalie Portman as the spokesperson, and that would indeed be quite a test of new hardware.

        But I don't know if getting hot grits in the ports is a good thing or a bad thing.
  • ... on yer new loot. Getting new over powered stuff is fun in games or in real life.
  • Sprockets? (Score:3, Insightful)

    by Doofus ( 43075 ) on Saturday May 24, 2008 @10:47PM (#23533457)
    How many people are going to get the Sprockets reference? I can't tell if I'm laughing at the reference, or laughing at myself for finding it strangely amusing. It's frightening that a reference, on Slashdot, to a 20-year-old SNL skit makes me chuckle. Zoiks.
    • by dwater ( 72834 )
      SNL?
  • False. (Score:5, Funny)

    by Kwirl ( 877607 ) <kwirlkarphys@gmail.com> on Saturday May 24, 2008 @10:51PM (#23533467)
    In the computer world, there is no such thing as 'ridiculously overpowered'.

    Can your servers run Crysis on max settings? :P lol
  • Paying the bills (Score:4, Interesting)

    by LinuxInDallas ( 73952 ) on Saturday May 24, 2008 @10:56PM (#23533487)
    Speaking of paying the bills, I have always wondered what it costs to maintain a website like Slashdot. Does anyone know what the cost of webhosting a site this large might be?
    • by Slashdot Suxxors ( 1207082 ) on Sunday May 25, 2008 @12:04AM (#23533811)
      100 Gold a month.
    • Re:Paying the bills (Score:5, Informative)

      by azuretek ( 708981 ) <azuretek@YEATSgmail.com minus poet> on Sunday May 25, 2008 @01:16AM (#23534049) Homepage
      Having worked for many large websites that have a boat load of visitors every day I think I can give a little insight. (As well as having worked for many web hosting datacenters)

      More than likely they have a good deal on bandwdith, assume they use 500Mbps a month, a traceroute from seattle shows they're using at least savvis as one provider. We can safely say they're probably paying no more than $18.00USD per month per Mbps. These are prices a small time carrier might get, they may be paying more and who knows how many other providers they're paying for or if they just buy a blend from their colo center.

      Lets put that price at: $9000/month so far

      Then you factor in the floor usage, normally you can get a full rack for about 2000 with 40a. I'm willing to bet they use at least 60a per rack, add in another 500. Plus they say they have a cage, they charge extra per square foot, a guess would put the cage at an extra 1000 per month.

      So I'd say about 3 racks with a cage would cost around: $8500/month

      So far the total is about $17,500.

      Now if they staffed their own people and didn't have any outside monitoring or anything of that nature that might be the total cost. In reality they probably have a contract with their provider for one site maintenance, 24/7 on site support, hardware replacement and the likes.

      At my current place of employ we pay 30,000/mo a month for that kind of service, I think we're a bit above what one would normally pay but we have a pretty high up time SLA.

      Add another 10,000 a month for maintenance/support/supply contracts.

      Grand total I'd say is about $27,000/month USD. It might be higher or lower depending on their deal with their providers but normally for a standard colo deal it's around that price.

      I've seen sites pay out well above that (100,000+) for colocation and have an awesome return.
      • by Timmmm ( 636430 )
        > they use 500Mbps a month Megabits per second per month? Right...
      • by kesuki ( 321456 )
        "Add another 10,000 a month for maintenance/support/supply contracts."

        but, what does cowboyneil do then? I thought he was their primary hardware guy, and maybe they have a second guy so he doesn't have to be on call 24/7

        it's not just slashdot, they run sourceforge everything2, the OSDN, loads of complex websites.

        i doubt they'd pay $10,000 a month when they already have a dedicated hardware guy on the payroll.
  • Moving your site to a more central location in the states will improve my page loads - thanks /.

  • by Mostly a lurker ( 634878 ) on Saturday May 24, 2008 @11:17PM (#23533587)

    ... we are now running on the new iron in a cage in Chicago.
    While geeks have often struck me as a little weird, I have not previously seen them treated as actively dangerous. I hope they let you out soon.
  • by Lacrocivious Acropho ( 741314 ) on Saturday May 24, 2008 @11:20PM (#23533603)
    Congratulations on your new cage! That sounds odd when said. I don't contribute much, apart from exposing /. to those who might benefit but haven't yet found it. I will take this opportunity to say "Thank you!" for more than a decade of the single most entertaining, informative, rewarding, gee-whiz stuff I have gotten from any site, ever. You guys do a splendid job, and I hope you will continue that effort, and that culture, forever.
  • Seems like /. would have wanted to do more stress stesting than just one day over a holiday weekend here in the states. Hope that the new cluster can stand up once next Tuesday hits!

    Also, thanks for the relocation as well. My page loads are much faster than from the old location in Santa Clara.
  • Dugg! (Score:2, Insightful)

    by sonchat ( 819093 )
    can you guys host digg on it too? Digg is too slow.
  • I have plenty of my own suspicions, but what was wrong with being based in California?

    Logistical? Political? Tax (dis)advantages?

    Just curious.

  • by account_deleted ( 4530225 ) on Sunday May 25, 2008 @01:40AM (#23534139)
    Comment removed based on user account deletion
    • So now even the dead accounts can mod. Neat.

      A good Chicago joke.

      I'd include a reference to the post office "where submissions made to an overload server are stored on a pallet and thrown away when the pile gets too high".

      And something about the Cubs, of course.
  • Nice move guys. Doing this sorta stuff is never fun but at least it is over now...time to party.

  • Tim Vroom is OBVIOUSLY just a stage name. Nobody is that fast!
  • IPv6 please (Score:5, Interesting)

    by ptudor ( 22537 ) * on Sunday May 25, 2008 @06:00AM (#23535015) Homepage Journal
    Greetings Germanic Dancers,

    Could you please add an IPv6 VIP to slashdot now that you've got this move out of the way? I mean, it's 2008 already :)

    Have you ran any stats on your dns logs to see what percentage are requests for quad-As?

    If you're nervous about suddenly blackholing because of misconfigured remote sites, perhaps you could add an ipv6beta.slashdot.org site à la ipv6.google.com? Or, I read of a long-running test a website had been running where a third of clients were served a one-pixel image from a hostname with a single AAAA record, another third a dual record, and finally a single A record to test against reachability problems.

    So, I'm sure you're all smart and working on it and I'll just have to keep patiently waiting, but I'll be so pleased when your v6 integration matches undeadly.org.
  • by brianc ( 11901 )

    the ridiculously overpowered new hardware we have now
    That was posted nearly two hours ago! That's ancient technology
    by now...

Solutions are obvious if one only has the optical power to observe them over the horizon. -- K.A. Arsdall

Working...