From: Wei Huang <wei@redhat.com>
To: Paolo Bonzini <pbonzini@redhat.com>, afaerber@suse.de
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH 1/1] target-i386: prevent users from setting threads>1 for AMD CPUs
Date: Tue, 07 Oct 2014 19:41:52 -0500 [thread overview]
Message-ID: <54348850.9080808@redhat.com> (raw)
In-Reply-To: <54345CC8.8050806@redhat.com>
On 10/07/2014 04:36 PM, Paolo Bonzini wrote:
> Il 07/10/2014 23:16, Wei Huang ha scritto:
>> It isn't a bug IMO. I tested various combinations; and current QEMU
>> handles it very well. It converts threads=n to proper
>> CPUID_0000_0001_EBX[LogicalProcCount] and CPUID_8000_0008_ECX[NC]
>> accordingly for AMD.
>
> So if it ain't broken, don't fix it. :)
>
>>> I am worried that the default CPU is an AMD one when KVM is disabled,
>>> and thus "qemu-system-x86_64 -smp threads=2" will likely be broken.
>>
>> "-smp threads=2" will be rejected by the patch.
>
> Yeah, I am afraid that is an incompatible change, and one more reason
> not to do this. AMD not selling hyperthreaded processors does not mean
> that they could not be represented properly with the CPUID leaves that
> AMD processors support.
I am OK with either way. The key question is: should QEMU presents
CPUIDs strictly as specified by the command line or QEMU can tweak a
little bit on behalf of end-users? For instance, if end-users say "-smp
8,cores=2,threads=2,sockets=2", they meant "two socket, each has two
2-hyperthread cores". Current QEMU will convert CPUID as "two socket,
each has 4 cores". My patch will forbid the tweaking...
-Wei
>
> Paolo
>
>> Unless the meaning of
>> threads is not limited to threads-per-core, shouldn't end users use
>> "-smp 2" in this case or something like "-smp 2,cores=2,sockets=1"?
>
next prev parent reply other threads:[~2014-10-08 0:42 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-07 19:44 [Qemu-devel] [PATCH 1/1] target-i386: prevent users from setting threads>1 for AMD CPUs Wei Huang
2014-10-07 20:58 ` Paolo Bonzini
2014-10-07 21:16 ` Wei Huang
2014-10-07 21:36 ` Paolo Bonzini
2014-10-08 0:41 ` Wei Huang [this message]
2014-10-08 7:47 ` Paolo Bonzini
2014-10-09 20:22 ` Wei Huang
2014-10-09 21:08 ` Paolo Bonzini
2014-10-09 22:16 ` Eduardo Habkost
2014-10-21 15:11 ` Wei Huang
-- strict thread matches above, loose matches on Subject: below --
2014-10-07 19:17 Wei Huang
2014-10-07 19:42 ` Wei Huang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=54348850.9080808@redhat.com \
--to=wei@redhat.com \
--cc=afaerber@suse.de \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).