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

 



Forgot your password?
typodupeerror
DEAL: For $25 - Add A Second Phone Number To Your Smartphone for life! Use promo code SLASHDOT25. Also, Slashdot's Facebook page has a chat bot now. Message it for stories and more. Check out the new SourceForge HTML5 Internet speed test! ×
IBM

IBM's $45 Linux Server (Well, Kinda) 142

Wedman sent us a snippet from a newsletter from OpenSourceIT that starts off by saying that IBM will announce a new pricing scheme for Linux on the S/390 mainframes: Soon they'll cost $125k. For another $20k you can get virtual machine software to run multiple copies of Linux on the same box. David Boyes, a consultant who works with the S/390, managed to boot 41,500 Linux servers on one mainframe. Although he notes that you may not be able to run that many in real life. ;) (if someone can find an actual link for this, please post it) That just cracks me up: I mean, the debate about forking apache to handle requests is one thing, but hell, why not just boot your own OS for each request!
This discussion has been archived. No new comments can be posted.

IBMs $45 Linux Server (Well, Kinda)

Comments Filter:
  • by Anonymous Coward
    Alex Stark is IBM's key technical lead for Linux design on the 390. Btw, linuxplanet.com asked him about perf, and he responded: "The answer is forty-two!", which is pretty cool. (The fact he is an homonym of me is nice too). Cheers, --fred
  • by Anonymous Coward
    The new owners of the Commodore/Amiga legacy have announced that they have ported Linux to the older Commodore and Amiga platforms.

    This port is an attempt to demonstrate the awesome power of these legacy platforms.

    Company insiders estimated by clustering 10**8 Commodore 64, 128 and original Amigas into a Beowulf cluster, companies can achieve the equivalent raw processing power of a IBM S/390 mainframe.
  • Actually, the reason I said that was because the exact thing happened when I was in college. Then their was the time plant ops decided to save money or something and shut down the AC to the machine room - the mainframe made a panic call and shut itself off.

    In a perfect world, no power outages, but I'm sure most would agree college is not a perfect world. :)
  • The idea of running multiple copies of an operating system on one box is not new and, yes, it can be very useful. I know that Unisys has been doing this for years on their A-Series machines running their MCP operating system. (MCP-anyone remember Tron?) It is an interesting concept that allows the administrator to do active load balancing by moving resources such as processors or I/O from one instance of the OS to another or even set up one instance as a backup in case of a failure. The biggest advantage is to be able to reduce the cost of operating several servers by running them all in the same box and by sharing resources. Very cool stuff.

    Unysys's latest machine, the ES7000, can support up to 8 partitions (that is hopefully going to increase in the future) and currently only runs Windows. Windows does not support dynamicly moving resources between partitions at this time but that is something that is being worked on. Another project currently under way is adding support for MCP to the ES7000 and several Unix variants.

  • The machine comes with 1000 copies of Windows95 pre-installed, and you have to pay for them, even if you tell them you don't want Windows95. :)
  • Actaully, if you are talking about massive transaction processing, the mainframes and other large systems (like the AS/400) are the best at what they do, and are actually rather cost-efficient. PC-style hardware has fairly awful I/O performance, which is what really matters for the big iron. Processor power is needed more for application serving, etc.. You can do a lot with big pipes. Sun systems have had great I/O capabilities for a while now, even with slower processors than PC equivalents, and AS/400 and S/390 go far beyond that. Not to mention that the reliability numbers on a 'frame are astounding... but when you a have a bunch of processors that do nothing but handle error recovery, it's no wonder why you don't see problems.

    Actually, there's a good reason for Mainframes to still exist- I ran across someone (a VP at a major corporation) who thought that an "empty" 48xCPU Tandem cluster could beat a loaded-down UNIVAC 1100/80 1x1. The UNIVAC still came out ahead by (IIRC) about 20:1.

    Mainframes excel at single thread performance- when dealing with a database, there are some phases that MUST be done single thread (which is why "append new row" is the most expensive operation in a DBMS); For instance, for a sort operation you can split up the sort process across all of the CPUs you have but there is still a merge phase that MUST be single threaded.

    Likewise, a mainframe takes no prisoners in providing the maximum I/O bandwidth and connectiviy (disk farms, folks...).

    Mind you, I still think machines that can use 120VAC are great, but I'd _love_ to see some more S/390s on eBay for approx $1K- though I'm thinking that my electric meter will explode...

  • Well there are lots of cheap S/390's some even as low as 125K but it's like getting a barebones PC you have to add DASD, I/O controllers, Channels, RAM, etc etc. What does a used 3745 or 3172mod3 cost?

    Does anyone know what kind of machine and how much of it was used to IPL 41k system images? Poughkeepsie doesn't just hand out large 'spare' mainframes for people to test on.
  • Avg sysadmin overhead is 1 HC/25-35 machines for a distributed environment vs. ~1HC/service function in the S/390 world. That is, you have <1 RACF admin, <1 sysadmin, 1-2+ DB admins for the box regardless of the number of VM's on it. That's why people run S/390's. The real savings is in the labor. Plus if you expend some extra effort to consolidate console ops and messages through Tivoli agents or something similar then most of the grunt work can be eliminated altogether. Since 85% of the total cost of ownership is labor which averages out to US$140K/HC/yr fully loaded with benefits, if you can save on people that are no longer are responsible for scads of PC shaped machines then the cost efficiencies are enormous.
  • ahh the resurgance of mainframes :) Soon we will all have air conditioned rooms w/special fire extingusihers so we can run 41k copies of Linux on our refridgerator :)
  • I read in one of the old magazines for the Commodores that there were about 10 million C-64s, so we're a bit short even for large values of 1.0x10^6 and small values of 1.0*10^8.

    However, there was Project LUnix [netsurf.de] to provide 64s and 128s with a multitasking OS. 0.37 BogoMIPS, baby!

  • Hell, I have plenty of Karma to burn... Check out today's User Friendly [userfriendly.org]. Us trolls will love it!

  • I don't use this user account for trolling.
  • Can you imagine... a beowulf cluster of virtual machines all running on the same machine *grin* (just think about the loss from overhead... it's a joke people).

    Actually, it's probably not really a joke. Someone planning to implement a Beowulf cluster or studying how to implement a Beowulf for an application might want to do it on one of these just to get the hands-on experience without purchasing a whole bunch of hardware.
  • This will be a great thing for larger companies wanting to be virtual servers or co-location facilities. They can run each linux server for the client allowing them to have shell level access with complete safety. If they screw it up you just load another session from backup. You never have to worry about screwing up the master server.

    Kindof be nice to house 1000+ "machines" in only 1 box. Lacks redundancy but hey doesn't everything in computing nowadays.
  • Hell, run a Crey. :-)
    MSstate.edu has a crey, over 600 users and hardly a load. Old? ya, whatever d00d. it STILL will outperform any of the most modern highest end servers now. Load 14000 linuxs' up on it !!!! kick ass.
  • can you actually use all of those copies at once?

    Yupp, you could instantly form the biggest team for SETI@home
  • WE replaced our Amdahl system last year with a shiny new S/390. One of the nice things was the
    about of raised floor we were able to recapture.

    The Amdahl consisted of 6 large refrigerator sized boxes. The S/390 is a single unit about 3 x 3 x 4.5 feet.
  • Folks, you are focusing too much on the Linux part and ignoring everything else here.

    Most large financial firms with a serious web presence have a mixture of mainframes (4 or 5), like those 390s, and 200 or 300 A/S 400s. During the day, the web servers are busy, handling transactions, while the mainframes are realtvly idle. At night, the mainframes do batch jobs, while the web servers are quiet. The result of this is that at any point in the day, millions of dollars worth of hardware is doing nothing!

    Enter hot-swappable O/Ses. Replace those A/S400s with a few more 390s. Now, during the day you can devote most of those cycles to linux web servers, running only the amount of O/S390 you need for transaction processing. reverse the situation during the night. And, if you need a sudden increase in the number of webservers at 2am, just boot a few more instances.

    This whole process saves tons of money. Less hardware, fewer SAs, smaller data centers, less wasted resources.

    You guys want Linux to hit the big time? IBM is now going to be pushing Linux as part of an offering that will save companies like E*Trade and Schwab and Wells Fargo and BofA and every other finaincial institution millions of dollars a year.

    Linux just hit the big time.
  • I currently rent a "virtual server" from Adgrafix. Their virtual server let me set up my own web server, but as I have no root access, I have to ask the admins kindly every time I want them to restart my server.

    With IBM's new stuff, someone could start selling real virtual servers with root access and everything, giving customers _full_ control of an Internet connected server.

    If prices are reasonable (far below a dedicated server), I'll gladly sign up as the first customer. That's a promise!

  • Another plus of mainframes over PCs is reliability. Sure you can just take any old PC and install Linux on it, but beefing that PC up so that when a hard drive, network card, or cpu dies it doesn't crash can get pretty pricey itself. Mainframes however have been doing this for years. Not to mention there are a great many large companies out there who would much rather have one mainframe in their server room rather than a couple of hundred PCs.

    And of course it's just cool :)
  • Oh yeah. On the x86, we used windows and Bochs, which was a great combo. The semester before, people were having to reboot to dos on the windows boxen. They were only p-120s, and it was a pretty painfull process.
    --
    then it comes to be that the soothing light at the end of your tunnel is just a freight train coming your way
  • if one VM takes a dive, nothing else is affected.
    avoids having all hosted web sites being crashed by software on one. sheesh.
    there's a lot of accounting reasons as well, mainframe time can still be expensive.
    also, chicks dig it.
  • *laugh*

    Never has my signature seemed more appropriate. ;)

    |
    |
    V
  • Sorry, the first poster had it right. MVS (now OS/390, as you point out) is the other S/390 operating system. MVS (OS/390) can't run a virtual machine, and can't run Linux. VM's purpose is to run many, many virtual machines, and you can run an OS in any of those virtual machines. CMS, VMS, OS/390, Linux, other VM systems, all on the same box. But all this has been covered elsewhere.
  • This wasn't a marketing ploy anyway; just a tech guy who installed Linux on S390 and wanted to see how many copies he could run before things got unacceptably slow. Just like most of us geeks... he got a new toy and wanted to push it to its limits... :-)

    Garg
  • The S/390 provides the redundnacy... you can yank a few processors out of there, and you probably wouldn't even notice...

    as for a extended power outage where your generator fails... well, that's another problem.
    --
  • Having several VMs can be rather useful. You 'dedicate' a section of your mainframe to a specific task, give it a set amount of resources, and off you go. Running 41,500 copies of linux is just one of those "because I can" kind of things...

    --
  • Yup, all sizes, from the new 250, all the way to the new 840 (that's a big horkin' machine)...

    All the ones around here don't have the nice black covers on them... but maybe that's because I happen to spend time in a lab where we develop these things ;-)

    --
  • >also, chicks dig it.

    "Hey, baby.... check out my big iron." ;-)

    --
  • Right... or you could say that a cluster is just a lower-bandwith, less fault-tolerant mainframe (usually with more MIPS, though)...

    --
  • >I wonder if IBM needs beta testers (-: I'd re-wire my house if they sent me a demo unit.

    I hope you have a nice big entry from the power company. The machine and AC might melt your puny 160A entry path 8^)

    --
  • >If IBM took their S/390 technology and scaled it down, they would have a PC-killer device.

    Get a small AS/400 - lots of I/O cabability, smaller footprint, still scalable. It's not exactly what you are looking for in a desktop - no AGP slot ;-)

    --
  • Hmmm... don't have that one yet 8^)

    Maybe I'll have to propose a Dual-PPC Netfinity, with high-speed internal I/O...

    Or, you could just set up a caching RAID controller and that will help ease the disk I/O somewhat - how 'bout 8 10krpm U2W drives in a stripe set... that'd be nice. Not all you need is some higher bandwith through the chipset...

    --
  • I'll have to check that out - thanks.

    --
  • Right, there are boards from a number of manufacturers that have that - add another 32bits onto the transfer, and crank up the speed.

    64/66 PCI is also helpful for this sort of thing, and would be a great increase. 64bit especially (included in Alphas, Netfinities, and a whole bunch of other things) makes it possible to mix older and newer cards on one bus. A 66MHz bus will get slowed down by a 33MHz card in it, since everybody has to play by the same rules. PCI-X is a better answer yet, but it tends to make devices a little more pricey.

    ATA-100 is a waste of time. SCSI is a better answer.


    --
  • $145,000 / 41,500 = $3.4939759036/box

    so, you can say $3.50 linux box!

    where'd $45 come from?
  • Seriously. If their beta team got drunk and send me one of these machines, I'd have the entry put in. My house is on commercial property, so I could probably swing it. It would cost me a fortune to run, but I could lease out space on it.

    *Drool* free s/390
  • by es-mo ( 57502 )

    11223 is trolling... The advantages of mainrames in terms of brute processing power, reliability, etc., are well known. I'm not claiming categorically that they outstrip PC's; there are applications much better run on PC's. There are, however, many applications for which a mainframe is the only sensible choice.

    I work with mainframes every day. They aren't exactly the monstrous monolithic beasts that we picture from yesteryear. They can be pretty darn nimble. And wherever transactions, reliability, paralleleism, or sheer number of simultaneous connections is needed, they kick any PC's butt.

  • That sounds like a nightmare for managing the systems resources. Why would you want to? You'd 41000 different instances to monitor.
  • Fast I/O won't let me decode DIVX....

    Besides, the PC world has fast enough IO.. PCI hardware raid with 7 UW/SCSI drives will shoot enough data at a processor to keep it happy..
  • IBM Linux Server! Only $45 after $2,000 mail-in rebate! Act now! Supplies limited!
  • i thought linux was free :)

    Mike Roberto
    - GAIM: MicroBerto
  • by tve ( 95573 )
    I wouldn't want operators smoking videocards anyway, but that's just me.
  • by skwog ( 101252 )
    So then wouldn't you need 'superroot' to one up the power of root on each OS?
  • $125,000 + $20,000 = $145,000 towards IBM.


    This gives us the ablity to run 41,500 linux machines.

    (125,000 + 20,000) / 41,500 = ~$3.50 per linux machine.

    Sounds like a bargain to me.

    :-)

    Vanguard
  • I am tremendously excited by this news. I must admit that I thought that the $99 for my Linux 6.2 was a little on the expensive side.
  • Actually, the thing is, lots of shops have excess mainframe capacity they weren't using. This lets them throw another OS up to use the spare capacity. With the advantage that it's isolated, with the uptime of a mainframe.

    As someone who is responsible for several of IBM's big iron aix boxes, I can say that reliability is an issue, and this development is a good thing. In the scheme of things, mainframes are pretty cheap compared to other comparably sized systems...
  • > Stuff the CPU in the back seat of the car
    > and toss the cables in the trunk, and head
    > on over to your local Linux User Group (LUG).
    > By the end of the day, you're running the
    > latest Linux kernel

    Installing Linux on a CPU alone.
    No motherboard
    No hdd
    No mem

    The progress we've made ;)
  • The point of David's experiment was to show that is was possible, which, as almost everyone on /. should know, is very different from practical.

    Running 100 is completely feasible though.
    $145K/100 = $1450.
    $1450 is about the price of a decentally stocked PC. And when you add in the lack of rack space, networking equipment, power, etc, combine that with the amazing stability of an S/390 (something like minutes of hardware downtime per year, if that), you have a heck of a deal.

    Now, in all fairness, $145K is the price if someone with an S/390 wanted to give it an extra processor to play with Linux/VIF on. A real ISP would have to buy a new S/390, probably would buy real VM, not VIF, and spend a lot more. Of course, if you raise the number to 1000, the numbers work even if the price is $1,450,000.
  • PCI hardware raid with 7 UW/SCSI drives will shoot enough data at a processor to keep it happy.

    Hardly. At that point the PCI bus is the bottleneck. Think about it: 33MHz, or even 66MHz gives any CPU time to yawn. To really keep the CPU(s) busy you need several PCI buses feeding one or more higher-speed backplanes which in turn feed the CPUs.

  • Oh, the networking driver does rock.. It amounts to something like a 10,000T Ethernet card, shoved across the bus.

    This got me to thinking. In a situation like this, where you have massive bandwidth with high reliability, wouldn't it make sense to cobble together some sort of networking that didn't have the overhead or complexity of a TCP/IP stack? Keep the socket API/ABI, but let the bits flow faster.

  • =====
    AND, with virtual hosting, some user cracks root, and every account on that machine can be comprimised. With this, someone cracks root on one of the 20,000 instances, and whoever maintains that instance gets screwed, but the other 19,999 users are unaffected.
    =====

    Until the cracker uses the same exploit to compromise the other 19,999 linux instances.

    maru
  • What about VAX/VMS boxes?

    I know a couple of Universities that are stuck with them (and have no idea what do to with them - other than let the CS students play..)

  • by Anonymous Coward
    Phone calls to IBM tech support?
  • Nope. Different beast. Cray machines are designed for high speed calculation. Also (and I'm sure somebody will jump in here to correct me), Cray can only handle a single operating system image. No support for virtual machines. IBM mainframes specialize in I/O, and business logic, not number crunching. And, the Cray cannot handle multi-terabyte databases, which is IBM's bread and butter.


    ...phil
  • by martin ( 1336 )
    ok so now the Linux boys can get their hands on the M/F. But why, surely a cluster of 41,000 PC's will still be cheaper than buying a huge great MF and the gubbins you need to support it??

    AND I'd like to know if anyone in the real world (ie outside of IBM's labs and Universities) actually use this for anything other than street cred points.

    MF's are very expensive to run and even clocking up a few mins of CPU can cost the business huge amounts....

    Just wondering why bother? apart from the obvious "because its there"
  • And when you have to bring the mainframe down due to some moron cutting power mains or some other reason, all 41,000 customers lose service.

    I miss IBM mainframes, the are so cool to play with...ah...college days.
  • IBM just recently announced that they will be selling extra CPUs to their current mainframe users for $125k if they only want to run Linux on them.

    http://news.cnet.com/news/0-1003-202-2371079.htm l

    I guess that's quite a bargain, they normally charge twice that much. :)

    Keep in mind that's just for the processor board, you also have to buy the chassis and memory and disk and... oh I'm sure it's a multi million $ bill when you're all done. :)
  • What was realy funy was that IBM had a huge planetwide "Linux/390 Install fest" [linuxplanet.com] over the last few weaks.
  • Got too many customers, won't be able to handle new requests for VM's, or upgrade the QOS for the old ones? That's cool. Just slap in some more processors.

    What's that? No, you don't have to reboot.

    PC's may make a great solution for individual desktop computing, but these mainframes kinda rule. :)
  • What better use of 40,000+ linux "machines" than to build a really big Beowulf cluster.

    The I suppose it's not terribly efficient to virtualize a million machines just to tie them all back into one big system. Oh well, it would be fun to try.
  • It's already built into the operating system. It's called IUCV, "Inter User Communications Vehicle." Basically, it's a connection based, lossless communications protocol that directly moves data between address spaces. Very slick.

  • Linux on a IBM mainframe was posted on slashdot a while back. [slashdot.org] There are also linux ibm s/390 resources here. [ibm.com]
  • I've seen the debate start over wether this achievement is useless or not, and it's a good question.

    But, useless or not, it's also pretty cool ;) Part of the fun of technology is playing skunkworks and experimenting and trying out new things. Sure you get useless stuff, but you also get some real gems.

    Besides, I recall that at one point we'd never need hard drives, or we'd never need more than 640 KB of memory . . . I'm sure someone'll find a use for this one way or another.
  • postage and handling.
  • IT doesn't lack redundancy at all.
    The s/390 is fully redundant. Fault tolerant memory (we're talking way beyond ECC here....). THe machine can detect memory errors and route around them.
    Fault tolerant processors, fault tolerant coprocessors.. *everything* is realtime fault tolerant.
    This machine is *designed* to stay up for a decade, with zero downtime. Nil. Nada. This *IS* a mainframe, a real mainframe. Not some little desktop box.
  • 1) Because this is what the mainframe is *designed* to do. It's not meant to run one single user-level OS. IT runs VM, whichi is designed to do just this. It means you can bang right on the hardware, but virtualized, to protect others who are also using it's massive resources.

    2) The point of having 41,500 virtual machines is that each VM is *rock stable*. NOt stable as in 'linux is stable' but stable as in solid concrete nuclear bomb shelter stable. THe 41500 is a test number; in reality you would run maybe a few thousand at most. The point? A hosting provider can provide a linux box to *each* customer! full root access and everything.. go nuts they can say!

  • "I thought that the PC vs. mainframe debate was settled years ago, and the PC won."

    Yep, it was--on the desktop. People with serious reliablity and performance needs (like banks and gov't agencies) still use mainframes.
    --
  • I believe that the correct way of phrasing this is that "IBM supplies a Linux Server running on mainframe hardware, pricing starts at $125,000 but drops to $45 in high volumes"

  • However, I suspect that we'll see people offering virtual hosting within an instance, which kind of defeats the purpose, but also allows, say 100 users to be hosted on an instance, which allows for 2million sites to be hosted on one machine.

    Sweet JESUS! Somebody get to work on IPv8 right NOW!
  • Actaully, if you are talking about massive transaction processing, the mainframes and other large systems (like the AS/400) are the best at what they do, and are actually rather cost-efficient. PC-style hardware has fairly awful I/O performance, which is what really matters for the big iron. Processor power is needed more for application serving, etc.. You can do a lot with big pipes. Sun systems have had great I/O capabilities for a while now, even with slower processors than PC equivalents, and AS/400 and S/390 go far beyond that. Not to mention that the reliability numbers on a 'frame are astounding... but when you a have a bunch of processors that do nothing but handle error recovery, it's no wonder why you don't see problems.

    Most people might run maybe one or two VMs with linux, since that could provide a simple way to interface with the rest of the machine for some apps, but obviously, the power of the mainframe doesn't lie in its ability to run linux... it just happens to be a fun little add-on.

    --
  • Ah, but those other 19,999 instances are independently configured, so there's a good chance that the exploit won't exist on all/most/more than one of the instances.

    Plus, it might not even be linux running on some/most/all of the instances.
  • What's so cool about this is that IBM is charging a flat rate for customers to install this on their systems, regardless of how much it is used. Previously, all IBM operating software has been billed on a monthly basis (essentially, you "rent" the operating system), on a pricing scale depending on how many processors you had, how many virtual machine partitions you had, etc.

  • the S/390 runs VM (Virtual Machine).

    Actually, it would be closer to say it runs OS/3x0/Linux, which in turn runs MVS/Hercules, (A S/3x0 emulator for Linux) which in turn runs OS/3x0/Linux. Whew, that was a mouthful!

    the machine can virtual within virtual within virtual with no real penalty.

    Yep. No penalty, save a tiny amount of MVS overhead. But it's not quite VMware in hardware. MVS is required, but the hardware is designed to help MVS out.

    Oh, the networking driver does rock.. It amounts to something like a 10,000T Ethernet card, shoved across the bus. Granted, you can only talk to other machines on the virtual network, that is, inside the S/3x0. Add a single firewall/router session bound to and piping out the real Ethernet feature and you're set tho. ;)

  • This will never get moderated up, but for those who read down here, the S/390 cpu's that will run ONLY linux, not the ibm mainframe Os microcode, will cost 125,000 USD. These machines will still require at least one REGULAR s/390 CPU, which will run you about 350,000 USD by itself. Never mind the rest of the box. Bottom line, you're still looking at 3/4 of a million to run linux on a Mainframe, so don't get worked up because you have an extra 1/4 million to blow.
  • Soon they'll cost $125k. For another $20k you can get virtual machine software to run multiple copies of Linux on the same box. David Boyes, a consultant who works with the S/390, managed to boot 41,500 Linux servers on one mainframe.

    $125,000 + $20,000 = $145,000 (so far, no $45 server)
    $145,000 / 41,500 = $3.50 (lot less than $45)

    For the ''server'' to cost $45, that would imply running 3222 (.2 repeating) servers. Is this to be the expected number in that case? I couldn't find this anywhere.

    --

  • I've got to think Taco knows the answer to that, and he's just trolling.

    Anyways, that's obviously not an efficient way to do things. One virtual machine per customer is more likely what you would do with this. (Not to limit one per customer - some customers might actually need more than one, but still, that's the basic idea.) Running a buch of virtual linux boxes isn't going to do anything good for performance, of course, but within reason it shouldn't do much bad either, and you have the advantage of customizing each virtual box individually for it's intended use... different customers won't affect each others machines any more than they would if they each had a physical dedicated server.

    And it should be very nice from a security standpoint too, you don't expose the real base OS to the outside world at all, all network traffic goes through one of the virtual linux boxes, and an exploit that compromises one doesn't affect the rest.

    Someone will doubtless post the obligatory beowulf cluster comment by the time I press the submit button - of course this is silly. You will get better performance by not imposing the overhead of a virtual beowulf cluster and just dedicating the same resources to a single virtual uber-box.

    Performancewise, mainframes are a mixed bag - you can't justify the expense if you are mainly concerned with number-crunching tasks, because a real physical beowulf cluster of alpha boxes, for example, will have a lot more bang for the buck there. Mainframes != supercomputers, they are totally different animals. The mainframes strength is IO, however, so this sort of setup could be very cost effective for massive database applications, web server farms, and the like.

  • AFAIK it's about avoiding single points of failure - if one thing breaks/crashes, something else takes over.
    Kind of like a cluster in a box.
  • I wonder if IBM needs beta testers (-: I'd re-wire my house if they sent me a demo unit.

    You'd probably hae to get rid of that closet in the corner to fit it into your bedroom. This is not the type of machine to fit under your desk (unless you like your desk 8ft off the ground that is :-) ).

    That said, you're probably a little too late. IBM has been helping companies set up Linux [linuxplanet.com] (Suse 6.4 I believe) on their S/390's during July so I think that the boat has sailed. Still they'll be playing with the apps for a while yet - I know DB2 is about to be used on that platform, which will be interesting. I'm certain there will be more news sooner or later as well.

    Cheers,

    Toby Haynes.

  • The one *huge* weakness that PCs have is their bandwidth and internal bus speeds. They have the processing now, yes, but the problem is actually moving the information.

    Of course, price is also an object, so that's why PCs usually win. As for comparing an IBM S/390 to a dual proc Alpha server; it's kind of like trying to compare an oil tanker with a waterskiing boat. It's just not fair to either one to compare them.

  • I know that I would MUCH rather pay for an S/390 than for the equivalent processing power in PC boxen. I also know that I would MUCH rather administer 1 of these than hundreds of those. That and my AC/Power can cope much better. I think that all in all, I'd be WAY happier with one of these with a decent stack of software running on it than with a handful of PCs.



  • Damn, if you could do this on an H70, my life would be SOOOO much easier. This is exactly the kind of thing I need at work.
    "The axiom 'An honest man has nothing to fear from the police'
  • I have used a uk isp called DSVR [dsvr.co.uk] who seem to be running very high spec linux boxes with virtual machines running on them.

    I'm not quite sure how contained each machine was but every customer was certainly given their own copy of apache etc... and it seemed to work pretty well.
  • Isn't anyone going to ask if I can imagine a beowulf cluster of these?
  • Actually AS/400's don't have to be big - I've got one on my desk in front of me. A model 150, it's the same size as a PC, but in black with a red flash...

    Single user AS/400s - For when a Sparc isn't exclusive enough.

  • by jeffry_smith ( 5065 ) on Tuesday August 01, 2000 @08:17AM (#889439)
    No, actually, if you're using VIF (Virtual Image Facility), you don't need the regular S/390 CPU (which is the same as the Linux one, except for the licensing). You can get into the game for easily less than $250K. Admittedly, it's a small mainframe, but it's into the game. And, running VIF, you can give each of your developers a separate Linux box on the box.
  • by Psiren ( 6145 ) on Tuesday August 01, 2000 @04:31AM (#889440)
    Okay, can someone tell me what the advantage is between having one kernel running, using all the resources, and multiple kernels sharing them. Is it a limit with Linux's ability to use all those processors/memory etc? Or is there a performance advantage doing it this way?
  • by finkployd ( 12902 ) on Tuesday August 01, 2000 @05:24AM (#889441) Homepage
    There aren't going to be any official links yet, this was pre-announced at SHARE (www.share.org) in Boston last week. The official announcement should come later this week.

    Along with the new pricing scheme, a new product was announced. Called the Virtual Image Facility (this is what costs $20k), it is basically a stripped down version of the old VM OS for the s/390 with some administrative capabilities thrown in for good measure.

    Currently Linux only runs on an s/390 in one of three ways, as the only OS on the mainframe, in an LPAR (logical partition, which you are limited to 15 on any given s/390) or as a guest under VM, which is what allows you to run as many as you want (40,000+). The new VIF will allow you to have the benefits of running linux under VM, while actually running under an LPAR (which most shops seem to do, VM is slowly vanishing)

    On a side note, Linux was very well represented at this SHARE, with dozens of sessions specifically targed towards Linux. IBM also stressed it's committment to Linux on several occations. My favorite quote was:

    "The Penguin is your friend" - Tom Rosamilia, VP s/390 Software Development, IBM

    I've found most mainframers seem very open toward Linux (with reservations, these guys are used to reliability and fault tolerance that blowns Linux out of the water). I suspect the reason for this is that the open source development style harkens back to the days many of them remember when IBM released source code for mainframe products (the MVT and HASP days).

    Finkployd
  • LinuxPlanet [linuxplanet.com] has just postet an article about this here [linuxplanet.com].

    IBM has just held an installfest which they talk about, and they talk with Peter McCaffrey, System/390 Program Director and it looks like IBM is pretty serious about it.

    They also talks about what classes of applications performs well on their mainframe and about possible customers.
  • by mindstrm ( 20013 ) on Tuesday August 01, 2000 @04:52AM (#889443)
    I don't know the links offhand, but info about Linux on the s/390 has been posted to /. twice before, a month or so ago.

    And the 41000 copies, as indicated, but perhaps not emphasized... the guy said that 41000 copies was theoretical, not practical. YOu would not have enough cycles left to actually *DO* anything with that many going.... it was just a test.

    But even a few thousand...

    IBM, from what I recall, has a neat internal networking driver so the VMs can talk to each other at extremely high speed, which is cool.

    The basic idea is that full virtual linux machines can be deployed in minutes, can be cloned, backed up, all kinds of neat mainframe advantages, all on a machine that reall *IS* designed for 0% downtime. No more racks and racks of linux machines... just a fat mainframe.

    For those who don't know (and for those who do, correct me if I'm wrong please), the S/390 runs VM (Virtual Machine). The design is such that VM can virtualize itself multiple times over with minimal loss in speed. WE're talking VMWare at the hardware level here... the machine can virtual within virtual within virtual with no real penalty.
  • by mindstrm ( 20013 ) on Tuesday August 01, 2000 @04:58AM (#889444)
    Personal Computer -vs- Mainframe? PC won? I think not.

    Mainframes are no longer simply 'fast'. PCs can be really fast too.. so can clusters. If all you want is number crunching... perhaps you don't need a mainframe.

    WHere the s/390 will SMASH an alpha to bits is on IO. THis thing can MOVE data like you would not believe.

    As for performance.. these things have multiple processors I believe, and can be scaled greatly.

    IBm has engineered a great solution here. THis isn't simply 'installing linux on an s/390' this is 'running hundreds or thousands' of virtual, fully-working linux systems on one machine.

    So the ISP would provide a full linux box to each customer for their site, to do with as they pleased... completely virtual, but hte customer owuldn't see the difference. THe s/390 will control exactly how much resources are sent to each individual instance of linux, so you can have both a) tiers of service and b) performance GUARANTEES. Combined with bandwidth management, this ROCKS. Oh.. you want a faster machine? WE'll just add more cycles to your VM for more money...

    This *IS* sweet, from the ISP angle.
  • by kmcardle ( 24757 ) <kmcardle@@@adelphia...net> on Tuesday August 01, 2000 @04:46AM (#889445)
    but what's a mainframe running Linux gonna do for you?
    Stability and speed. For I/O throughput, nothings going to match big iron. IBM has been cranking these things out since the 60's, and they really do know what they are doing.

    A really good use would be teaching an operating systems class. Each student would get a virtual machine to play with. Easy to crash, and easy to start right back up. You get the experience of working with a 'real' machine, but not all of the headaches that come from constant reboots. I've taken an OpSys class on both the 390 and x86, and on both I had virtual machines to play with, and it was a nice change of pace to be able to crash the virtual machine rather than the real one. The mainframe had the distinct advantage of being able to host all of the comp sci classes and only start to slow down near the end of the semester. It would only start to be noticeably slow when both CPUs got up to 90% utilization. Not bad for a machine with only 16 megs of physical RAM.
    --
    then it comes to be that the soothing light at the end of your tunnel is just a freight train coming your way
  • by es-mo ( 57502 ) on Tuesday August 01, 2000 @05:07AM (#889446) Homepage

    Advantages:

    • Virtual hosting. No more racks.
    • Ease of configuration.
    • Every user gets their own copy of Linux.
    • Billing purposes: you know exactly what application (er, copy of Linux) ran for such and such an amount of time.
    • Transaction-based environments: With applications popping their heads up and down to handle brief and frequent transactions, it's better to let MVS take care of the headaches of swapping Linux images in and out of memory than to use Linux to handle that.

    Disadvantages: If all you need is brute processing power (i.e., you aren't doing any transaction-oriented stuff), then run a single copy; you'll get better mileage.

  • by AntiPasto ( 168263 ) on Tuesday August 01, 2000 @04:31AM (#889447) Journal
    that this is sort-of kind-of denoting some kind of drop in price in hardware.... anyone venture to say that this sort of pricing, and general concept will lead to the "neighborhood" linux box? Granted it'll probably definately lead to a resurgance of mainframe computing, as we've been hearing a lot of linux/mainframe stories lately.

    ----

  • by TheTomcat ( 53158 ) on Tuesday August 01, 2000 @05:00AM (#889448) Homepage
    That just cracks me up: I mean, the debate about forking apache to handle requests is one thing, but hell, why not just boot your own OS for each request!

    I read the article on booting 40000+ linuxii on one box almost a year ago, so I might be a little sketchy, but if I remember correctly:

    The issue is booting an independent copy of the OS for each 'instance' of a server, NOT FOR EACH REQUEST. This means that they could run, maybe 20,000 machines that look independent on one shared machine, each of the 20,000 virtual machines running independently of the others. 20,000 root accounts, 20,000 userbases, 20,000 sets of allocated memory, etc., all running simultaneously, off of the same machine.

    Right now, web hosts can offer cheap web hosting (virtual hosting), where each user shares the OS, and with properly set permissions, and limited user functionality, this is relatively secure. This is generally run off of one, or a small group of IPs all pointing at the same machine, and the webserver figures out which 'instance' of itself should return what resource to the requester.

    The problem is that, for instance, if I need to do something outside of my user-sandbox, I can't, or I need to have someone else do it.

    This whole multiple instances of one OS one one bigass machine, appears to the user as a co-location. They don't have to worry about other users screwing with their stuff. Essentially, my instance of the OS on that machine is the same thing as my own box being hosted at the ISP.

    AND, with virtual hosting, some user cracks root, and every account on that machine can be comprimised. With this, someone cracks root on one of the 20,000 instances, and whoever maintains that instance gets screwed, but the other 19,999 users are unaffected.

    However, I suspect that we'll see people offering virtual hosting within an instance, which kind of defeats the purpose, but also allows, say 100 users to be hosted on an instance, which allows for 2million sites to be hosted on one machine.

    I wonder if IBM needs beta testers (-: I'd re-wire my house if they sent me a demo unit.
  • by yakfacts ( 201409 ) on Tuesday August 01, 2000 @06:12AM (#889449)

    I disagreee. PCs are cheap both in price and quality. The best-quality components are much better, but they still fail enough that with 100, 10000, or 41000 you will have several with problems at any one time.

    Even with the best server-grade components, the PCs will be far less reliable. And I would bet that 10000 server-grade PCs would cost as much as one of these mainframes. If you own the mainframe, the cost-per-minute charges don't apply (remember that IBM sells now-a-days), and while you need more-expensive operators, you need fewer of them as they are not swapping hard drives and smoking video cards every 20 minutes.

    For a long time I advocated clusters of PCs for any application. Clusters have some great uses, but so does real hardware.

  • by finkployd ( 12902 ) on Tuesday August 01, 2000 @05:29AM (#889450) Homepage
    One University (speak up if you know) is actually running thousands of seperate linux guests under VM on their s/390 and giving EVERY student their own Linux box to play with.

    I'm under the assumption that they have some method of dealing with security in a central way so that everyone isn't running tftp and the dreaded r servers.

    Finkployd
  • by FascDot Killed My Pr ( 24021 ) on Tuesday August 01, 2000 @04:30AM (#889451)
    Don't fork the OS for each web request--fork one for each customer. Think about it--you buy ONE mainframe and ONE copy of Linux. You can 41,000 customers each with their own "machine". They can do whatever they want with it, including configuring the security themselves. It doesn't matter if they do it wrong, the other 40,999 customers aren't affected (with the possible exception of bandwidth).
    --
  • by tiny69 ( 34486 ) on Tuesday August 01, 2000 @04:56AM (#889452) Homepage Journal
    This would be great for hot swapping. You could literally have 100's of spares, waiting for a problem.

    You could even implement a good response system to security break-ins. Any time someone logs in as or su's to root, indicate there is an error and swap to one of the hot spares. So what if the cracker trashes the one he is on. Switch to a backup.

    Of course in this situation, you would need 100's of spares if someone is a little persistant.

  • by Carnage4Life ( 106069 ) on Tuesday August 01, 2000 @04:33AM (#889453) Homepage Journal
    David Boyes, a consultant who works with the S/390, managed to boot 41,500 Linux servers on one mainframe. Although he notes that you may not be able to run that many in real life. ;) (if someone can find an actual link for this, please post it)

    The story on NetworkWorldFusion News [nwfusion.com]

    The story on Fairfax IT [fairfax.com.au]

    A reprint of the story from LinuxPlanet [4th.com]

In the realm of scientific observation, luck is granted only to those who are prepared. - Louis Pasteur

Working...