back to article IBM pitches bite-sized $135k LinuxONE box for smaller biz types

IBM has pushed out a new member of its LinuxONE enterprise-grade Linux lineup that it hopes will appeal to small and medium-sized businesses, but the price tag is unlikely to recommend it to many buyers in this market. The LinuxONE systems are powered by the same Telum processor as IBM's z16 mainframe family, but are built to …

  1. karlkarl Silver badge

    "The company said that customers who move Linux workloads from an x86 server setup to an IBM LinuxONE 4 Express could save over 52 percent on total cost of ownership over five years."

    Just... How?

    1. EricM

      By not paying IBM?

      Just an idea ...

    2. ChoHag Silver badge

      Abandon your redundant array of inexpensive servers in favour of someone else's big expensive server with added lock-in.

    3. Mainframe Bloke

      Savings modes

      Fewer software licences mainly, as there are vastly fewer cores (typically less than one eighth, sometimes as few as one twelfth).

      Also less power usage and other environmentals, which are admittedly only a fraction of the software savings, but still something saved.

      And finally, fewer admin costs, which again are admittedly only a fraction of the software savings but again still something saved.

      Things like uptime benefits, ease of implementation of integrated facilities which are extra elsewhere (encryption, inferencing, compression) are harder to quantify but still of value.

      1. EricM

        Re: Savings modes

        > Fewer software licences mainly, as there are vastly fewer cores

        Fewer cores means less processing power.

        One can also get X64 servers with less cores.

        Or are you trying to claim her, that one core in this box is as powerful as 8-12 X64 cores?

        > Also less power usage and other environmentals,

        Citation needed ...

        > And finally, fewer admin costs,

        Citation urgently needed. Maintanance&Admin cost for specialized hardware typically comes at a premium over bread-and-butter X64 gear.

        1. Peter Gathercole Silver badge

          Re: Savings modes

          I don't think that it is 8-12 times the power in terms of raw compute, but one of the things you may note with many VM technologies is that you end up with a lot of the CPU sitting idle a lot of the time. Most stand-alone, and many VM systems over provision each VM, to make sure that they can service the peaks in demand.

          The VM and Linux implementation on IBM Mainframes is very, very good at making use of currently unused capacity, as long as you mix your workloads accordingly. It is even better than IBM's PowerVM implementation, which allows unused CPU resource in one LPAR to be 'borrowed' by other LPARs when needed. With Mainframe, the CPU time is not even provisioned to the LPAR unless it is needed.

          This means that you can essentially thin-provision your systems, but still get the same amount of work done.

          It seems to me that the current wider thinking in system design is that you don't alter resource allocation on demand to VMs, but that you just spin up more VMs to cope with the load. Well, the Linux VM mainframe implementation can do this with astonishingly fast start-up speeds, but it is often more normal to allow the VM itself to have more resource allocated dynamically at peak demand. This hugely simplifies the application design, as you can keep to a single-server application deployment that eliminates all of the load balancing and synchronisation technologies that you need with a distributed implementation, saving you the resource that that requires. And with the high availability, you don't even need to go wide to provide resilience.

          The one area where this dynamic resource allocation falls down is that per-CPU software licensing struggles to cope with such a model.

          1. TheWeetabix Bronze badge

            Re: Savings modes

            Any x86 or other cpu farm will see efficiencies if they properly mix workloads to maximize processor usage. If they aren’t seeking that efficiency with their current set up chances are they won’t seek it with this box either..

    4. Mike Schwab

      How to save money

      Run 200 server images on this small starter systems. Ramp it up to 200 cores and run 3,000 images.

    5. TheWeetabix Bronze badge

      Back of my ass math

      makes me go …. Server is 135k, and lets say savings are 50% to make it easy on my arse… so in 5 years you'd have to have both a 270K spend on x86s (azure maybe?) and a small enough workload you’d only need one…. Unless you're absolutely filthy with lucre for overprovisioning gear, this is a joke with a bad punchline.

  2. EricM
    WTF?

    1TB, 16 cores, 135k$? for SMB's ???

    maybe Quantum-something, "AI" and the attached fine collection of Snake-Oils explain this price tag.

    From the link :

    IBM LinuxONE 4 is the latest iteration of IBM LinuxONE enterprise servers with on-chip AI inferencing and industry-first quantum-safe technologies.

    Clicking on "quantum-safe" lands you on a full pool of snake oil :

    - IBM Quantum Safe Explorer

    - IBM Quantum Safe Advisor

    - IBM Quantum Safe Remediator

    Can run anything every other Linux server can run, too. Just much more expensive...

    1. Anonymous Coward
      Anonymous Coward

      Re: 1TB, 16 cores, 135k$? for SMB's ???

      Clicking on "quantum-safe" lands you on a full pool of snake oil ...

      Indeed.

      Very expensive snake oil.

      Will wonders never cease?

      .

    2. TheWeetabix Bronze badge

      Re: 1TB, 16 cores, 135k$? for SMB's ???

      Im certain there was a tiny trademark symbol you missed. Quantum safe<tm> dishwashing detergent for instance.

      Perhaps its time to start registering “quantum compatible” and other trademarks and make a few quid.

  3. unimaginative
    Go

    SMEs, as defined these days, are not tiny businesses. IN the UK it is less than 250 employees, in the US it is a lot more.

    So you are getting something that might well run all your server needs for very possibly less than $1,000 per employee. Assume it lasts five years that works out at less than $20 per employee per month.

    1. VicMortimer Silver badge
      Stop

      It's a small, slow server for FAR too much money. It's buzzword nonsense.

      If it had any actual advantage over systems that cost 10% of what IBM is asking, they'd be showing benchmarks, not slinging buzzwords. And they aren't, they're just spouting more nonsense.

    2. EricM
      Stop

      Re: run all your server needs one on server

      That one is simple: Don't.

      You will only be able to meet your Failover and D/R spec with one server, if your requirment is: "I don't care"

    3. TheWeetabix Bronze badge

      Assuming

      one machine can service that many users at a time. With modern workloads im not convinced.

  4. Crypto Monad Silver badge

    There are people who want "mainframes" for boring business applications, with boring but incredibly good uptime.

    Then there are people who are doing AI workloads.

    Is there really any crossover between these two?

    1. Tomato42
      IT Angle

      Banks do AI inferencing for fraud protection, and they want the AI models to run fast...

  5. ChoHag Silver badge

    Is it the fabled linux desk?

    1. Roo
      Windows

      No, it's the Linux Closet, where deviant Linuxen stay hidden from public view.

  6. Anonymous Coward
    Anonymous Coward

    So move all your legacy *nix midrange stuff to errrrmm a midrange? No thanks.

  7. ldo

    “High I/O Workloads”

    This does sound like an area where mainframes have traditionally excelled. If I/O dominates over CPU usage, then this would not be a job for a supercomputer.

  8. Bebu
    Windows

    PS/2+Microchannel again?

    This time proprietary hardware to run an open source OS with a different processor architecture - more like a PS/2 with a TMS9900 mcpu.

    A purchaser would want to ensure that any closed source or legacy binaries (source lost) can be ported or could run under an emulator.

    University research environments typically run open source and in house developed code so that wouldn't be a problem. So as the article conjectured this rather than SMEs is the real market although at the price might be a hard sell against a rack of Dell servers. ;)

    My guess its an IBM hope that offering their hardware plus their Redhat OS they can flog their software and services on top but I cannot see too many customer wishing to return to IBM's good old days.

  9. Anonymous Coward
    Anonymous Coward

    Ummm.....about the rest of the "high availability" configuration......

    Quote: "....designed to offer high availability...."

    .....but no mention of the necessary "high availability" network? Really? How much does that cost? And do IBM provide it too? I think we should be told!!

    1. Peter Gathercole Silver badge

      Re: Ummm.....about the rest of the "high availability" configuration......

      It's quite possible to provide a resilient network for these systems. You just have to be prepared for the higher number of network cards that are required to provide two (or more) 'legs' on separate network switches to provide it. It's not that difficult, and in the higher-end midrange systems, we've been doing just that for decades. And of course almost all major components of these systems will be 'hot' swappable.

      Also, remember that the I/O is virtualized so not all the LPARs have their own network cards, it is done through the Hypervisor to dedicated I/O servers (in Power land we call them VIOS, or Virtual I/O Servers), and using multiple instances of these, you can come up with some hugely resilient solutions.

      Of course, they don't give you physical or geographic isolation, but that is another question entirely.

      1. Anonymous Coward
        Anonymous Coward

        Re: Ummm.....about the rest of the "high availability" configuration......

        @Peter_Gathercole

        Quote: "...separate network switches ... It's not that difficult ..."

        Last time I looked, my network provider only had one POP locally.....and they wanted serious extra money to back-haul to a another (somewhat distant) POP.

        It may not be difficult.....but surely $135K is only the start of a MUCH bigger bill.

        1. Peter Gathercole Silver badge

          Re: Ummm.....about the rest of the "high availability" configuration......

          I don't understand. If you're talking about the POP as being your drawback, then you're really talking about geo-distributed systems, which was not what I was talking about.

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Other stories you might like