David Wade wrote:

> Simon Clubley wrote:
>
>> Do the VM environments emulate missing hardware instructions with reasonable
>> performance levels ?
>
> With current Hypervisors, I believe the answer is "No" The OS only sees the
> features a CPU has.

often a subset of features, so that at boot time, the guest doesn't use features
that are not available on all nodes in a cluster, so allowing live migration to
older hosts within the cluster.

On 7/12/2022 1:37 AM, John Wallace wrote:
> On 11/07/2022 21:25, Phillip Helbig (undress to reply) wrote:
>> In article <tahokr$1ou3j$1@dont-email.me>, Simon Clubley
>> <clubley@remove_me.eisner.decus.org-Earth.UFP> writes:
>>
>>>> What BestBuy PoS X86 box, that won't carry Billy Tax, capable of
>>>> running OpenVM
>>>> cost meS?
>>
>> Why does hardware without Windows installed have to pay anything to
>> MicroSoft?
>
> Volume manufacturers of PCs have often been able to get significantly
> cheaper MS licence prices by committing to install and ship Windows on
> every "PC" they sell. If they don't do that, their overall cost of
> Windows will increase (and maybe they'll get audited...).

> I don't know if this principle still applies, but it did when I followed
> these things. It wasn't often talked about in public though.

The practice of charging PC manufacturers a license for all PC's sold
with or without DOS/Windows and the usage of a different prices
depending on whether PC's are sold with other OS as well supposedly
ended in 1994 with a voluntarily agreement that the following
year got approved the the supreme court.

Arne

On 2022-07-11, Phillip Helbig (undress to reply) <helbig@asclothestro.multivax.de> wrote:
> In article <tahokr$1ou3j$1@dont-email.me>, Simon Clubley
><clubley@remove_me.eisner.decus.org-Earth.UFP> writes:
>
>> > What BestBuy PoS X86 box, that won't carry Billy Tax, capable of running OpenVM
>> > cost meS?
>
> Why does hardware without Windows installed have to pay anything to
> MicroSoft?
>

Please watch your quoting in future Phillip as I didn't write that.

Thanks,

Simon.

--
Simon Clubley, clubley@remove_me.eisner.decus.org-Earth.UFP
Walking destinations on a map are further away than they appear.

On 2022-07-12, Phillip Helbig (undress to reply) <helbig@asclothestro.multivax.de> wrote:
> In article <tai4p9$1qa36$1@dont-email.me>, "Robert A. Brooks" <FIRST.LAST@vmssoftware.com> writes:
>> On 7/11/2022 4:25 PM, Phillip Helbig (undress to reply) wrote:
>> > In article <tahokr$1ou3j$1@dont-email.me>, Simon Clubley
>> > <clubley@remove_me.eisner.decus.org-Earth.UFP> writes:
>> >
>> >>> What BestBuy PoS X86 box, that won't carry Billy Tax, capable of running OpenVM
>> >>> cost meS?
>> >
>> > Why does hardware without Windows installed have to pay anything to
>> > MicroSoft?
>>
>>
>> Simon didn't write that.
>>

Thanks for pointing that out.

>
> I didn't claim that he did. The text he wrote is marked as a quotation,
> using a standard format which has been around for decades. And I'm not
> claiming that you wrote what I wrote or what VAXman wrote because you
> quoted us. I don't think that anyone is confused.
>

You deleted Brian's from line from the article body and left mine in place.

You should have left Brian's from line in place and then it would not
have been confusing.

If you want to talk standard formats, then the standard format is to
always identify who quote a quoted section of text.

Simon.

--
Simon Clubley, clubley@remove_me.eisner.decus.org-Earth.UFP
Walking destinations on a map are further away than they appear.

On 2022-07-12, Andy Burns <usenet@andyburns.uk> wrote:
> David Wade wrote:
>
>> Simon Clubley wrote:
>>
>>> Do the VM environments emulate missing hardware instructions with reasonable
>>> performance levels ?
>>
>> With current Hypervisors, I believe the answer is "No" The OS only sees the
>> features a CPU has.
>
> often a subset of features, so that at boot time, the guest doesn't use features
> that are not available on all nodes in a cluster, so allowing live migration to
> older hosts within the cluster.
>

So we are indeed back to running the VM instances on Intel machines
(just as VSI says) so that PCID is available to VMS.

Thanks to everyone for clarifying.

Simon.

--
Simon Clubley, clubley@remove_me.eisner.decus.org-Earth.UFP
Walking destinations on a map are further away than they appear.

In article <tajquj$21qj7$1@dont-email.me>, Simon Clubley
<clubley@remove_me.eisner.decus.org-Earth.UFP> writes:

> On 2022-07-11, Phillip Helbig (undress to reply) <helbig@asclothestro.multivax.de> wrote:
> > In article <tahokr$1ou3j$1@dont-email.me>, Simon Clubley
> ><clubley@remove_me.eisner.decus.org-Earth.UFP> writes:

[The following, since quoted more than that below, is what Simon was
quoting.]

> >> > What BestBuy PoS X86 box, that won't carry Billy Tax, capable of running OpenVM
> >> > cost meS?

[The following was written by Simon (quoted twice since quoting me
quoting him).]

> > Why does hardware without Windows installed have to pay anything to
> > MicroSoft?

[The rest also written by Simon.]

> Please watch your quoting in future Phillip as I didn't write that.
>
> Thanks,
>
> Simon.
>
> --
> Simon Clubley, clubley@remove_me.eisner.decus.org-Earth.UFP
> Walking destinations on a map are further away than they appear.

Folks, usenet quoting schemes have been in place for decades. What is
the fuss? It is clear that the "blabla writes:" at the beginning
applies to stuff quoted ONCE below. The rest is just there for context.
Usually it does more harm than good to include who quoted what, since
those following the thread have already read it and the original post
can be retrieved if necessary. Why all the fuss all of a sudden?

Phillip Helbig (undress to reply) schrieb am 12.07.2022 um 22:02:
> In article <tajquj$21qj7$1@dont-email.me>, Simon Clubley
> <clubley@remove_me.eisner.decus.org-Earth.UFP> writes:
>
>> On 2022-07-11, Phillip Helbig (undress to reply) <helbig@asclothestro.multivax.de> wrote:
>>> In article <tahokr$1ou3j$1@dont-email.me>, Simon Clubley
>>> <clubley@remove_me.eisner.decus.org-Earth.UFP> writes:
>
> [The following, since quoted more than that below, is what Simon was
> quoting.]
>
>>>>> What BestBuy PoS X86 box, that won't carry Billy Tax, capable of running OpenVM
>>>>> cost meS?
>
> [The following was written by Simon (quoted twice since quoting me
> quoting him).]
>
>>> Why does hardware without Windows installed have to pay anything to
>>> MicroSoft?
>
> [The rest also written by Simon.]
>
>> Please watch your quoting in future Phillip as I didn't write that.
>>
>> Thanks,
>>
>> Simon.
>>
>> --
>> Simon Clubley, clubley@remove_me.eisner.decus.org-Earth.UFP
>> Walking destinations on a map are further away than they appear.
>
> Folks, usenet quoting schemes have been in place for decades.

right. They help the reader to follow the text.

> Folks, usenet quoting schemes have been in place for decades. What is
> the fuss? It is clear that the "blabla writes:" at the beginning
> applies to stuff quoted ONCE below. The rest is just there for context.
> Usually it does more harm than good to include who quoted what, since
> those following the thread have already read it and the original post
> can be retrieved if necessary. Why all the fuss all of a sudden?

fwiw - because you quoted Brian but removed the line showing that the
text was from Brian - which is a bit confusing. You cut down the quote
anyway, but you should keep the relevant parts which describe who wrote
the quoted text. If you quote some text, the attribution should remain
in place.

Hans.

In article <tahq1i$1ou3j$4@dont-email.me>,
Simon Clubley <clubley@remove_me.eisner.decus.org-Earth.UFP> wrote:
>On 2022-07-11, Dave Froble <davef@tsoft-inc.com> wrote:
>> On 7/11/2022 2:03 PM, Simon Clubley wrote:
>>> Rather than one of the above boxes however, I would follow VSI's advice
>>> on what hardware they recommend to host your VMs running VMS. For example,
>>> take note of the fact you can only use Intel CPUs for now and cannot use
>>> AMD CPUs. (Unless that has changed _very_ recently).
>>
>> You maybe getting mixed up. Running a VM doesn't care about mfg. Or maybe I'm
>> mixed up.
>
>Do the VM environments emulate missing hardware instructions with reasonable
>performance levels ?
>
>For example, what happens when the VM software is being run on a box without
>PCID support ?

Typically the Hypervisor (both the VMM and other emulation
components) define a "platform" that they emulate, that consists
of IO devices, CPU features, etc. This is what they expose to
the guest. On machines that fully support this virtual platform,
emulation is very efficient; on machines that do not fully
support the platform, trap-and-emulate techniques are used,
which is usually less efficient but very often the use of these
features is rare.

On x86, CPUID (which is often used to probe what CPU features
the machine supports) causes an unconditional trap into the
hypervisor, and the hypervisor emulates the instruction, so the
guest only sees what the HV wants it to see. Of course, the
guest can ignore that and try to use some features that the
underlying machine exposes without coordinating with the HV,
but this often fails. It also fails on real hardware, too, so
one doesn't lose much when the guest "cheats", but the error
cases can be abstruse.

Similarly with PCI config space, writes to the APIC's ICR, etc.

- Dan C.