Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Linux Business United States Science

Linux To Power NWS's Storm Prediction System 154

Posted by timothy from the mind-the-ups-batteries-please dept.
Mr. Plow writes "The National Weather Service is migrating to Linux-based IBM workstations and has purchased 900 IBM computers and 160 servers to do so." He includes links to coverage at Forbes (a Reuters wire service story there), Government Computer News, and Computerworld.
This discussion has been archived. No new comments can be posted.

Linux To Power NWS's Storm Prediction System More

Linux To Power NWS's Storm Prediction System

Comments Filter:

  • Of course... (Score:5, Funny)

    by kinnell ( 607819 ) on Wednesday December 10, 2003 @05:43AM (#7678620)
    With windows all you see is blue

    • Re:Of course... (Score:4, Funny)

      by Ske ( 211063 ) on Wednesday December 10, 2003 @05:46AM (#7678630)
      and with IBM it is BIG blue...

    • Windows (Score:5, Insightful)

      by RevMike ( 632002 ) <revMike@gmail. c o m> on Wednesday December 10, 2003 @06:01AM (#7678682) Journal

      Of course... With windows all you see is blue

      Of course, the NWS is using Linux to replace HP-UX workstations.

      • Of course what would really help is if they got off TCL/TK for half their apps...
      • Correct, but Windows NT/2000/XPPro was supposed to be the replacement for Unix workstations. Linux may not be taking market share directly from Windows, but it is taking market share that Windows was supposed to get (according to MS' PR department, anyway).
    • That's why some people use Sun [sun.com].

    • Actualy I see a storm brewing from the Redmond area. It could be a big one.
      • Why Redmond? This move is killing more proprietary Unix boxes, not Windows boxes.
        • More desks needing apps. The biggest thing keeping Redmond on the desktop is off the shelf software selecton. When the Linus Apps section gets bigger at Best Buy then the Apple section, then MS will be really worried.

          MS would prefer nobody uses a non-MS desktop (server also, but that is a big battlezone now).
          • Is there an Apple section at Best Buy? I guess I hadn't noticed one locally. But since I can only afford Macs capable of running OS 9, I buy my Mac software on eBay.

          • The biggest thing keeping Redmond on the desktop is off the shelf software selecton.

            I beg to differ.
            The biggest thing keeping Redmond in the desktop is the fact that the VAST majority of desktop users (not you or me, but the USERS) don't know what an OS is, don't know there are others, don't know they can change it, don't give a damn.
            And the truth is, they shouldn't.

            The desktop will still be an uphill battle long after the servers and the workstations are sewn up.
            This battle will be won like Stalingrad:
            • majority of desktop users don't know what an OS is
              When Linux machines are sold in places other than just Walmart (retail stores) and people can come in and play with them and discover multiple desktops, multiple users, network firewalls (IP chains, not XP killing all local network file and print sharing), and the biggest badest collection of included games and applications for 1/2 the money, then they will gain attention.

              I mean, how many MS users bought an apple I-Pod? How did they percieve it was the be
              • I really wish you were right, but it's just wishful thinking.
                Linux is great for the geek desktop, and for the corporate desktop. Your desktop, my desktop.
                The home user just doesn't care.

                That and high prices has been the best driving force to put Linux on the desktop. They are working very hard to make it robust and have less BSOD's, but they are nor fixing the high cost.

                And about cost: maybe you live in a very law abiding part of the world, but the home user DOES NOT PAY for software. He just makes an
                • If MS really cracks down on piracy, then you'll be right, but for now..

                  Actualy, been too close to exactly this. It's the part of the EULA that permits them to request an audit. Follow that with the Portland Oregon Public schools being requested for this audit. I know, there was lots of egg on face from the bad publicity, but do you think smaller businesses have a chance? I'd rather not find out.

                  I disagree with any EULA that permits an envasion of my home or business. I simply do not have the resourc
    • You know what they say...

      Every blue screen has a beige lining.

  • linux to power.... (Score:4, Funny)

    by mrsev ( 664367 ) <mrsev@ELIOTspymac.com minus poet> on Wednesday December 10, 2003 @05:46AM (#7678629)
    ... I use electricity for power. Should I change to this "linux". Maybe linux is more secure.

  • One Problem... (Score:5, Funny)

    by JamesD_UK ( 721413 ) on Wednesday December 10, 2003 @05:46AM (#7678631) Homepage
    Who wants reports favourable to penguins?
    • Dude - you have a really nice eye. Your photography is quite good. I commend you.
      • I'll check back later, looks like we are killing your server.

        I saw only Black and White before the site slowed. B&W is a great medium, one that is hard to master, you have what it takes.

        Keep up the great work.

  • Bravo (Score:3, Interesting)

    by enodev ( 692876 ) on Wednesday December 10, 2003 @05:47AM (#7678633) Homepage
    Now I'll now 185 seconds earlier that a flash just struck my home :-).

    The previous systems contained Hewlett-Packard PA-RISC processors with clock speeds ranging from 100 to 120 MHz. Although those specifications aren't directly comparable to the 2.4-GHz clock speeds of the dual Intel Pentium 4 Xeon processors, the new workstations, which have 2G of RAM each, run the various AWIPS applications noticeably faster than their predecessors, Piercy said.

    For instance, one AWIPS app that used to take more than 60 seconds to start up now loads in 18 seconds, he said.

    That's a increase of about 48 times of computing power and the app just loads 3 times that fast? Something has to be seriously wrong with this setup!

    • Re:Bravo (Score:5, Insightful)

      by kinnell ( 607819 ) on Wednesday December 10, 2003 @05:53AM (#7678659)
      That's a increase of about 48 times of computing power and the app just loads 3 times that fast? Something has to be seriously wrong with this setup!

      Startup times are affected more by disk access times than processor speed. Disk access times don't increase anywhere near as fast as processor clock frequencies.

      • Re:Bravo (Score:1, Redundant)

        by enodev ( 692876 )
        I suppose they've upgraded their data storage system as well (160 servers...). And application load time is also greatly depend on memory, cache size and linear transfer time. Just skipping 2 generations of computer evolution should really bring you more than a factor 3. But then again they probably start it just once a day.

    • Re:Bravo (Score:3, Informative)

      by Silvers ( 196372 )
      The poster above about the disk times in application load performance is right now, however also...

      You make the mistake of assuming a 1:1 ratio of CPI (clock cycles/instruction) between each of the two systems, compounded by a difference in the number of instructions needed to complete a certain task, followed by the amount of parallel pipes in each processor... etc etc etc

    • Re:Bravo (Score:3, Insightful)

      by AmVidia HQ ( 572086 )
      load times is a wrong benchmark to pick, it doesn't show proccessing power well. Load times are mostly disk-bound.

      Load times more than 3x faster IS a LOT faster. And no doubt they will have many many times faster actual data crunching speed.

    • Re:Bravo (Score:2, Insightful)

      by ocelotbob ( 173602 )
      Read that quote again:

      ...Although those specifications aren't directly comparable to the 2.4-GHz clock speeds of the dual Intel Pentium 4 Xeon processors...

      The old machines were RISC boxes which were pretty damn quick on a Mhz per Mhz basis. While I wouldn't classify them as fast, they're definitely not 24 times slower. Given the clock cycle efficiency of the processors, I'd imagine that all things considered, the new boxes probably have at best ~20-30 times the raw computing power. Now, add things like d

    • Re:Bravo (Score:2, Informative)

      by Xenolith ( 538304 )
      There are still old HP systems running the database and application servers. That is part of the reason. These systems will be replaced shortly as well with x86 architecture. Hopefully with up to date and better optimized database software.

      Assuming it is the application I am thinking of... it was more like 5 minutes to start up, not 60 seconds. Yes, the HP systems were ancient (relatively).

  • Hmmm... I don't need that many computers to forecast many SCO lawsuits in their future.

  • Interesting (Score:5, Interesting)

    by frankthechicken ( 607647 ) on Wednesday December 10, 2003 @05:52AM (#7678657) Journal
    Interesting, according to this [newsforge.com]

    Linux first appeared on the NWS scene in 1995 in the form of Slackware

    And in comparison to their previous HP-UX systems:-

    . . .the switch has helped increase data processing speed.

    "The performance that we measure with our benchmark has increased by over 100% since we completed phase one of our Linux migration," happily boasts Piercy.
    • Some of these speed increase quotes in stories are far from interesting. If they replaced the systems with the latest HP workstations, doubtless they'd see a great speed increase as well. It's not exactly newsworthy to read 'company upgrades systems with newer systems and they are faster than the old ones'.
      • If they replaced the systems with the latest HP workstations, doubtless they'd see a great speed increase as well. It's not exactly newsworthy to read 'company upgrades systems with newer systems and they are faster than the old ones'.

        How about the fact they replaced $30,000 HP/UX PA-RISC systems with $5,000 Linux/i386 systems and were impressed with the upgrade? Actually these numbers are made up, but are the rough size of the price difference.

        • Re:Interesting (Score:5, Interesting)

          by 4of12 ( 97621 ) on Wednesday December 10, 2003 @09:14AM (#7679538) Homepage Journal

          That's the key issue.

          The purchase price of high performance RISC machines has always been O(US$10^4) and the acquisition cycle a period of several years.

          While you can still get high performance RISC workstations for those prices, it doesn't make any sense when comparing price/performance.

          In 1993, PC's significantly underperformed RISC machines, so paying 5-8 times the prices was worth it.

          In 2003, PC's perform equitably to the best RISC workstations: you need a really good reason not get a really great Linux workstation for $6-8K instead of high-end RISC hardware for $20-100K.

          • O(US$10^4) would that be US$(10^4) or, would that be UUUUSSSS$$$$10000?
          • Don't forget (900+160)*$699=$740,940.00
          • "In 2003, PC's perform equitably to the best RISC workstations: you need a really good reason not get a really great Linux workstation for $6-8K instead of high-end RISC hardware for $20-100K."

            That figure is not counting power consumption requirements/costs though.

            Chips such as the PowerPC970 (ie the "G5") are RISC-based, and the University of Virginia did find that PowerMac G5's were price competitive to x86 based "solutions." Thus affordable RISC-based solutions are possible.

            And as for the XEON, check
        • That would be news, but only if we knew what the price of the HPUX upgrade would have been. The fact they've done it suggests it made technical and financial sense, or at least one of the two. Sun's prices have come down massively recently, making them a lot more competitive on the server, at least, although they only have a single cpu lower cost workstation now.

          Still it is a good story!

  • So what's the forecast? (Score:4, Interesting)

    by trystanu ( 691619 ) on Wednesday December 10, 2003 @05:55AM (#7678666) Homepage
    Unsettled weather for the duration of the migration?

    Are forecasts really getting better as computer power increases? I know that Metrology is always in need of more computer cycles to model the weather, but have forecasts actually improved with this power? Are there any success statistics around?

    • Re:So what's the forecast? (Score:5, Funny)

      by SpaceLifeForm ( 228190 ) on Wednesday December 10, 2003 @06:04AM (#7678695)
      They keep saying that the 5 day forecast is just as in-accurate as before, but now, they know this fact with more accuracy than ever before.
    • Well, since Edward Lorenz and his discovery of chaos, many of the current weather prediction systems are chaotic, and thus the forecast becomes less accurate over a longer time period.

      Like many chaotic equations, the systems of weather patterns follow a `normal' path for a period of time before becoming chaotic. So this method is useful in predicting specific weather patterns for as long as 5 days in advance. After this point though the chaotic nature of the systems become apparent, with different scenar

    • Re:So what's the forecast? (Score:5, Informative)

      by Xenolith ( 538304 ) on Wednesday December 10, 2003 @06:16AM (#7678742) Homepage
      Well, to throw one stat out at you. In 1987, the NWS had a probability of detection score for tornadoes of 25%. This past year it was nearly 80%. Now given, part of that improvement is better trained employees and an excellent skywarn/spotter network. But yes, bigger and better computers are helping to improve the NWS mission.

      • Re:So what's the forecast? (Score:2, Informative)

        by Anonymous Coward
        In 1987, the NWS had a probability of detection score for tornadoes of 25%. This past year it was nearly 80%. Now given, part of that improvement is better trained employees and an excellent skywarn/spotter network.

        *cough*cough* You sure that wouldn't have something to do with NWS fielding the WSR-88D (aka NexRAD) doppler radars? there is a boatload of information one can extract from that data. One of the particulars is the tornado vortex signature (TVS) which usually forms anywhere from 15 to 30 minutes

  • We have are workstations already (Score:5, Informative)

    by Xenolith ( 538304 ) on Wednesday December 10, 2003 @05:59AM (#7678675) Homepage
    I'm a NWS forecaster. We have our new workstations... they are pretty darn nifty. They are dual Xeons (2.4 ghz) running RedHat 7.2. These are much improved over the old HPs, which were J200 (overview [openpa.net]). The bad news is that the database and application servers are still the old HPs. These are scheduled to be replaced in the near future as well.

    • Did you have to fight for getting Linux onto your desktop or was there the cost motivation to push it along?

      My impression is that any beaurocratic organization would be loathe to consider anything but Microsoft on the grounds that selecting Microsoft is safe. Examples of this would be trying to use Linux in large companies.

      • I'm a meterologist, not computer dude. But my guess is that since the software was already written in a unix environment (HPUX), choosing Linux made it the logical choice.

      • Re:We have are workstations already (Score:5, Insightful)

        by girouette ( 309616 ) on Wednesday December 10, 2003 @07:52AM (#7679018)
        The computing context is similar where I work (Meteorological Service of Canada). There is a big difference between the forecaster's (technical) desktop and the clerical desktop. Our technical desktop never belonged to MS WIndows. Cost remains a concern, obviously, which is why we are moving away from proprietary Unix.

        For what it's worth, our next-generation workstation is going to be java-based. (Joint effort with a handful of European countries led by Germany.) http://www.dwd.de/de/Technik/Projekte/NinJo/ (German language)

        Dunno about the NWS, but for our clerical desktop to move away from Microsoft would be nothing short of miraculous.

        • Microsoft at the NWS (Score:1, Interesting)

          by Anonymous Coward
          The NWS used to have a very inexpensive site license contract with Corel for their word processing software - it fact, it was the "official" standard for internal document exchange; you could still get MIS Word/Project/Excel etc. but it was still pretty expensive even with the government discount. Keeping track of licenses was also a problem with the Microsoft software. (Interestingly, the Corel WordPerfect software used to have versions that would run on both Windows and Unix). I don't know if using Corel

      • Re:We have are workstations already (Score:1, Informative)

        by Anonymous Coward
        Did you have to fight for getting Linux onto your desktop or was there the cost motivation to push it along?

        It was a combination... cost was a big driver, but also that the developers of the new AWIPS apps pushed it that way.

        These aren't your normal desktops. They run very custom applications [noaa.gov] and in some cases have three LCD monitors per CPU.

        That said, Forecasters will normally have a Windoze box to the side for surfing the web, email, etc.

    • running RedHat 7.2

      Do you have a Progeny support contract [slashdot.org] too ?

    • Oi! Shouldn't you be working?!
    • Exactly how old are the HPs? That page says all the expansion are in the form if EISA slots rather than PCI or some HP proprietary bus slots.

    • The times they are a'changing (Score:2, Interesting)

      by Anonymous Coward
      I used to work as a Sys Admin for the NWS a a few years back where we used AWIPS(the forecast folks were in another building) - and even then the HP workstations were costly and slow. AWIPS was a closed system and we didn't directly do any development on them but because NWS had hardware contracts with HP we had to usually purchase their equipment. The problem was that the HP workstations/servers were so expensive (especially compared to PCs) that the office I worked for couldn't afford to upgrade them - w

  • Dear NWS (Score:2, Interesting)

    by Anonymous Coward
    Dear NWS,

    As I understand, you've recently upgraded your workstations to some slick IBM machines running Linux. Congrats. Now, about your old workstations. I'd be willing to take the off your hands, I won't even charge anything. I just want to see them go to a good home, not some dumpster behind your building -- ya know, [insert their address here].

    Thank you,
    Me.

    Fortress of Insanity [homeunix.org]

  • Linux replacing Unix : just standard evolution (Score:4, Interesting)

    by slb ( 72208 ) * on Wednesday December 10, 2003 @06:05AM (#7678698) Homepage
    What would have been far more interesting is a Windows to Linux migration with the same improvement in performance and TCO.

  • Maybe this will help Linux's respectability (Score:5, Interesting)

    by Maestro4k ( 707634 ) on Wednesday December 10, 2003 @06:08AM (#7678704) Journal
    Having someone big and respected like the NWS using Linux and announcing it publically should help Linux's respectability quotient in the US a lot. I'm glad to see this happening, both because it increases Linux's usage out there, and because it'll save us money (IIRC, the NWS is taxpayer funded), and probably lead to more accurate forecasts. It seems every time the computers they use get faster/more powerful, the forecasts get better. :)
    • NASA and the Department of Energy use Linux, and have for years. They use Linux Beowulf clusters for computational fluid dynamics. Most of them have an SCI [dolphinics.com] backbone for inter-node communications. Although, I guess nowadays for CFD you might as well write multithreaded code that's compatible with OpenMosix and, instead of spending a ton of $ on a cluster, run the simulations on your employees' workstations.

      Oh, and you might as well not bother imagining a Beowulf cluster of those babies... it's been done.

  • Important to mention... (Score:5, Informative)

    by Anonymous Coward on Wednesday December 10, 2003 @06:09AM (#7678711)
    That the migration is from HP UX boxes to Linux, not from Windows as some people might assume.
    • You are right and you are right and you are right :-)

      It doesn't really matter, though. Success is not measured against how many people and institutions switch from Windows to Linux, but against success stories of the use of Linux as a platform and software on top of it.

      Free Software is about freedom, and that includes other's right to use whatever they want as long as we (I) am free to use what I want.

      It is as simple as that :-)

  • My weather man well, frog (Score:3, Funny)

    by snkmoorthy ( 665423 ) on Wednesday December 10, 2003 @06:58AM (#7678860) Journal
    My frog, actually croakes and stares at the open window, whenever it is going to rain, otherwise he just stares at the TV - although I have started noticing recently, that he doesn't care much about rain if Sex in the City is on.

    --Sig here--

  • lies (Score:4, Interesting)

    by n0k14 ( 719810 ) on Wednesday December 10, 2003 @07:23AM (#7678929)
    Almost every day I read about a department, agency, company or even country switching to linux. I rarely read about switching from linux back to windows. Where is this inconceivebly high implementation and training cost for linux that micosoft keeps whining about?
    • There is a magical stone which makes soup taste good. You take the stone and add to it carrot, potatoes, onions, and perhaps beef, if you like. Boil them in water, and the stone makes everything taste good.
    • Echo chamber.

      You are only reading Slashdot, where Windows->Linux conversions are highly-publicized.

      Note: I love Linux, and can't stand using Windows, but that doesn't make this statement any less true.
    • RTFA, this is a HP-UX to Linux conversion.

      My tinfoil hat theory: x86 Linux is eating into the market share of proprietary Unix faster than it is for Windows, and MS knows it has a better chance of convincing people to switch if they don't have to dump their hardware.
  • I'm curious about the expected practical outcome of this change. Presumably, they would be using the same prediction routines, but on faster boxes.

    Would this mean that they would get the same predictions, just a little faster?

    Would more capable machines mean that they could run some more-complex versions of the prediction routines they run now? Say, with more grid points, or smaller time divisions?

    Are the current prediction routines OS-dependent, so that they'll have to be ported to the new Linux OS? Is

  • Why not using distributed.net... (Score:4, Interesting)

    by Ummite ( 195748 ) on Wednesday December 10, 2003 @08:12AM (#7679138)
    Why not using free systems like distributed.net, wich is 1) more powerfull and 2) free. People would be glad to help predict better weather, since actually they can't predict correctly 24h in advance ....
    • Timliness is everything with the weather.

      It's difficult to predict when a distributed process will finish... someone out there decides to shut their machine down and go home... what happens?

      You wait for the the response to time out and then send it out to another node.

      Meanwhile the weather has come and gone, houses are destroyed and people might be dead.

      Something like distributed net would work fine for running, say, a global model for next year, or ten years out.

      AWIPS is used by forecasters to p

    • Solutions like distributed.net where you have a variable number of available CPU cycles is bad because you NEED to be able to certain that a numeric model run will complete on time.

      The second more important reason is that distributed computing with low bandwidth like distributed.net, GIMPS, Seti@Home, forecasting cannot be packaged into the same sort of small request packets and process, and return the answer, because weather forecasting is based upon computational fluid dynamics in essances, you need to s

  • hi (Score:1, Interesting)

    by Anonymous Coward
    The US Air Force's New Tactical Forecast System runs on Red Hat 7.1. I think there is just one server at every base.

    When someone told me they wanted to accredit the NTFS system, I was like, WTF?
  • they forecast.

    That is all.

    • From dictionary.com [reference.com]:

      fore-cast (forkst, fr-)

      v. forecast, or forecasted forecasting, forecasts
      v. tr.

      1. To estimate or calculate in advance, especially to predict (weather conditions) by analysis of meteorological data. See Synonyms at predict.
      2. To serve as an advance indication of; foreshadow: price increases that forecast inflation.

      Emphasis mine.

      Yes, they *do* predict.

  • I took a field trip (science camp) to the Wilmington NWS station in NC. The guy said they used about 80% linux (not Unix) boxes for work. This was back in July...
  • IBM also has the contract [noaa.gov] for the central supercomputing facilitity.
  • Anybody else think 'not work safe' when they read the title?
  • never mind
  • I've worked at the National Center for Atmospheric Research (NCAR) for about 2 years now. And even when I first started Linux was the dominant force, and looked as if it had been for quite some time. All of the Software Engineers, and some of the scientists & managers have debian linux on their desktop. The rest have some form of windows.

    We use linux in development, when creating large clusters to run weather models on, and when deploying systems in the field. It's the clear first choice in OS (whe
  • I'm an armchair weather researcher, and I have this question to ask: Why does NWS not make the executable or source code to AWIPS available to the public? I understand it runs on most modern UNIX's from the notes I've looked at, i.e. HP/UX, Solaris and Linux.

    We are indirectly paying the government for the development of NWS's weather platform but yet we, as consumers as information don't have access to the same platform for viewing that information? I use the NWS web site at least 4 times a day, look

Slashdot Top Deals

As you will see, I told them, in no uncertain terms, to see Figure one. -- Dave "First Strike" Pare

Close