back to article Microsoft gives Hyper-V ceilings a Herculean hike

Microsoft has announced new scalability ceilings for its Hyper-V hypervisor. "Please read carefully. These are not typos," wrote Jeff Woolsey, Microsoft's principal program manager for Azure Stack HCI, Windows Server and hybrid cloud. That warning came in the first of a series of Xeets in which Woolsey revealed that VMs under …

  1. Korev Silver badge

    Maybe a dumb question... If you're so concerned about performance that you need two thousand CPUs and a couple of hundred TB of RAM wouldn't you be running on bare metal anyway, why is this necessary?

    1. 43300 Silver badge

      I was about to post the same point!

      The main benefit of virtualisation is being able to run multiple VMs on a host. If that level of power is required then it's probably going to be the only VM on there, so why not just cut out the virutalisation layer?

      1. Anonymous Coward
        Anonymous Coward

        Because "stuff" can share that bare metal hardware. The over head of Hyper-V is minimal anyway. It was always one of the better (if not the best) scaling hypervisors for IOs vs bare metal.

        1. 43300 Silver badge

          If there's any capacity left to share, with a VM that size running, then it's going to be a bloody powerful piece of hardware!

          1. NeilPost

            Isn’t there diminishing returns on managing the multi/tasking for up to 2,048 CPU’s and actually getting the job done ??

            1. Jou (Mxyzptlk) Silver badge

              That depends on your scenario. From 2048 CPUs you can spare one, four or sixteen for coordination and preparing the threads, and you'd still have 99.99% scaling efficiency. The OS itself has no problem, due to some famous optimizations which came with Windows 7 which were improved with every subsequent Windows version (hey Windows kernel coders, you do an amazing job! Lend some of your powers to the UI and Teams guys!).

      2. Anonymous Coward
        Anonymous Coward

        VM live migrate

        A good use case to run a hypervisor even for a single VM is to be able to move the image to another hardware server with no downtime.

        Obvs. Most people run multiple Vms anyway.

    2. Spazturtle Silver badge

      Windows 11 doesn't run on bare metal, when you install it on your computer it installs a lite version of hyper-v as the base with Windows 11 running on top of that. Windows 10 on compatible machines does the same. On any modern system you are already running Windows in a VM.

      1. 43300 Silver badge

        OK, to an extent that's true but adding the full set of hypervisor services for user-managed VMs seems pointless at the sort of power level being discussed here. Bare metal (or as close to it as possible within the design of the OS) would normally make more sense.

        1. Spazturtle Silver badge

          You could have multiple VMs with just only one running at any given time, say you are renting the system out. Each VM would have it's own virtual TPM which would mean you don't need to wipe the system's TPM every time a different customer rents it.

          1. 43300 Silver badge

            If you are renting out capacity for that sort of VM, you are a major cloudy provider and probably aren't going to be hosting on Hyper-V.

      2. Anonymous Coward
        Anonymous Coward

        Not quite. IF you enable Virtualisation Based Security and Hypervisor-Enforced Code Integrity (HVCI) then the Kernel runs "like" a VM but it's not Hyper-V and most of Windows is not "in a VM".

        1. Jou (Mxyzptlk) Silver badge

          Correct response, I was just about to write the same. But why as AC?

          1. DS999 Silver badge

            Maybe he posts under his real name and he's supposed to be working instead of hanging out in El Reg's forums

            1. Jou (Mxyzptlk) Silver badge

              Might be true. However: If the employer uses THAT kind of monitoring it may be time to switch the dictator...

          2. Anonymous Coward
            Anonymous Coward

            I always post as AC as I have a clause in my contract that states I cannot discuss my employer or clients. Even if I don't mention names it may be possible to infer something from one of my posts. Rather than trying to decide which posts need to be anonymous or not I just find it simpler to post everything anonymously.

        2. Mike Pellatt

          You are in a maze of twisty virtualisations, all different.

        3. FIA Silver badge

          Are you sure? This page implies that the OS is virtualised (albeit with direct hardware access).

          "In addition, if you have Hyper-V enabled, those latency-sensitive, high-precision applications may also have issues running in the host. This is because with virtualization enabled, the host OS also runs on top of the Hyper-V virtualization layer, just as guest operating systems do. However, unlike guests, the host OS is special in that it has direct access to all the hardware, which means that applications with special hardware requirements can still run without issues in the host OS."

    3. DJohnson

      A fair question, but the answer is 'portability'. The only glimpse the guest OS has of the real hardware is the CPU make & model. The rest is all an abstraction, so at any point in the future you can shift to a new/different system (even with wildly different hardware) and the VM will be blissfully unaware. You don't need to hope and pray that 1) the OS doesn't complain about X and Y changing, or 2) the admin updating config items doesn't miss one.

    4. aerogems Silver badge

      Because at some point in the future, this will likely be considered small. It was within living memory that 1MB of RAM was considered massive, or a 10MB HDD was considered to be like having a McMansion of storage.

      So, instead of making small tweaks every couple of years, they just did about a decades worth in one go.

    5. Jou (Mxyzptlk) Silver badge

      Mobility, independency from the hardware layer.

      Intel network cards making problems? Change them. Don't need to change a thing in the host. Including the hardware-fingerprint activation of some special software.

    6. Anonymous Coward
      Anonymous Coward

      I would always recommend everything to be virtual even if one VM per host. This means I don't need to automate a physical build, don't need to test different driver and firmware sets for each hardware model, and I can still use one method for DR replication and failover

    7. phuzz Silver badge

      Partly I assume this is because Azure is running on HyperV under the hood, but it's also so that in the future when a host server has ten thousand CPU threads and petabytes of memory, it can run piddly little Tb workloads.

  2. Anonymous Coward
    Anonymous Coward

    it might be able to run Vista then

  3. Pascal Monett Silver badge

    So it's a cloud option, right ?

    Because there ain't no motherboard that can handle that level of hardware.

    I shudder to think of the monthly cost for someone who actually signs up for 2000 CPUs and 240TB of RAM. Some beancounter somewhere is going to have a heart attack.

    1. 43300 Silver badge

      Re: So it's a cloud option, right ?

      If you were creating a monster VM like that in Azure, it would be directly in Azure itself, not within a Server 2025 VM running on Azure.

      1. Jou (Mxyzptlk) Silver badge

        Re: So it's a cloud option, right ?

        There is no "in Azure itself", it is all Hyper-V there. Has been for a long time, including the machines where you can get 20% or 25% of an installed GFX card. Even if it is only one VM and it takes the whole machine, it is still Hyper-V.

        1. 43300 Silver badge

          Re: So it's a cloud option, right ?

          I think you missed the point. I am well aware that Azure runs on a customised version of Hyper-V. My point was that this news article is about Hyper-V capacities within Server 2025. If you were running a monster VM like that on Azure you would be running it directly on Azure (which has been able to handle monster VMs for some time), not using nested virtualisation within Server 2025.

      2. SilentButViolent

        Re: So it's a cloud option, right ?

        Not necessarily. You.may be running an application that can't be moved to the cloud for either technical or regulatory reasons.

    2. Jou (Mxyzptlk) Silver badge

      Re: So it's a cloud option, right ?

      The cloud stuff is mostly optional after quite some complaints about "why is OneDrive, copilot and Azure-Arc installed and active by default? Available fine, but please not active!" complains, with a few (including me) pointing to trust issues on those.

  4. Zippy´s Sausage Factory

    "VMs under Hyper-V in Windows Server 2025 can run 2,048 virtual CPUs and 240 TB of memory."

    Today the limit of Hyper-V. Tomorrow: minimum recommended spec for Windows 12.

    I'll see myself out.

  5. mikus

    This is Microsoft's way of trying to remind people they still make a hypervisor, same way they beg you not to download Chrome when it's the only thing you use IE/Edge for. Most well-heeled Microsoft-y admins pay VMWare today for *good* virtualization, but with Broadcom pissing on everyone now, they need another easy button since being allergic to Linux usually. Anyone that isn't afraid of Linux will just use KVM or KVM-based solutions.

    1. Anonymous Coward
      Anonymous Coward

      Since Edge is Chromium based why bother downloading chrome? Edge uses less resources as well.

      1. Anonymous Coward
        Anonymous Coward

        Cant say that in here among the Edge haters...

      2. Anonymous Coward
        Anonymous Coward

        I don't understand why anybody would download Chrome. Edge exists only to download Firefox.

  6. original_rwg


    And of course Hyper -V never has any vulnerabilities that would require a restart after patching....

    1. Jou (Mxyzptlk) Silver badge

      Re: Immune

      There is no hypervisor which did not have a security issue. But check the CVE statistics. Hyper-V has less problems than VMware. As for the other hypervisor based virtualization beside VMware und Hyper-V: Where it the link to the Reg article with the statistics again....

  7. Ace2 Silver badge

    “It just makes sense for Microsoft to make sure its platform can handle those requirements.”

    We know what their normal QA is like. What do you suppose the QA on a 240TB RAM VM was? “Good news! It booted!”

    How many systems that size could MS possibly own - 2 or 3?

  8. Doctor Syntax Silver badge

    That's an awful lot when you consider 640K is enough for anyone.

    1. Jou (Mxyzptlk) Silver badge

      You have to direct that to IBM not Microsoft. They created that limit when designing those machines and setting the de-facto standard, for example which memory area is mapped to video and so on.

  9. Curious

    For SMEs, is the windows server cost per core having much of an effect on the server hardware that they buy?

    i.e.buying dual 8 core CPUs rather than dual 24 cores, to avoid +10K in per core Datacenter licenses?

    1. Jou (Mxyzptlk) Silver badge

      AFAIK it changed to CPU core count, so one fat 16 core is as expensive and two 8 core. And in quite some cases a 16 core CPU is faster than a dual 8 core.

      But be aware: That might have already changed again....

      1. 43300 Silver badge

        It was Server 2012 or 2012 R2 (can't remember which) which moved server licenses from per physical box to per physical CPU. From Server 2016 onwards it's been per physical CPU core (with a minimum of 16 cores as I recall).

        1. Jou (Mxyzptlk) Silver badge

          Not any more. They switched to core count, a year or two ago. I can still remember our sales guys pushing our customers to buy before Microsoft "optimizes" their licensing again. And before that there was an option to have it cheaper with dual 8-core CPU. And before that your Server 2016 scheme applies. And before that <error stack exceeded>.

          1. 43300 Silver badge

            Yes, that's what I wrote - "per physical CPU core".

  10. DaemonProcess

    More network required

    68 virtual network adapters isn't anything like enough.

    192 would be better.

  11. C.M.R...


    The reason we regularly use a hypervisor when only one guest is needed on the host is for mission critical 24/7 applications. Do it with a cluster of two (or more) hosts and you can update the hardware without any impact on the guest OS, simply by moving it to another host.

    1. Jou (Mxyzptlk) Silver badge

      Re: 24/7

      A thing not to ignore: Microsoft added "Share Nothing Livemigration" with Server 2012. So you don't even need a cluster. Not even Active Directory. But most do it with a cluster and and AD (hopefully separate, like I so), for obvious reasons :D.

  12. ldo

    Not Enough Drive Letters

    No way this cloud version of Hyper-V is Windows-based. It must be Linux-based.

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