From: Eduardo Habkost <ehabkost@redhat.com>
To: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: Re: invtsc + migration + TSC scaling
Date: Tue, 18 Oct 2016 19:05:14 -0200 [thread overview]
Message-ID: <20161018210514.GC5057@thinpad.lan.raisama.net> (raw)
In-Reply-To: <20161018205213.GA2511@potion>
On Tue, Oct 18, 2016 at 10:52:14PM +0200, Radim Krčmář wrote:
[...]
> The main problem is that QEMU changes virtual_tsc_khz when migrating
> without hardware scaling, so KVM is forced to get nanoseconds wrong ...
>
> If QEMU doesn't want to keep the TSC frequency constant, then it would
> be better if it didn't expose TSC in CPUID -- guest would just use
> kvmclock without being tempted by direct TSC accesses.
Isn't enough to simply not expose invtsc? Aren't guests expected
to assume the TSC frequency can change if invtsc isn't set on
CPUID?
--
Eduardo
WARNING: multiple messages have this Message-ID (diff)
From: Eduardo Habkost <ehabkost@redhat.com>
To: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: Re: [Qemu-devel] invtsc + migration + TSC scaling
Date: Tue, 18 Oct 2016 19:05:14 -0200 [thread overview]
Message-ID: <20161018210514.GC5057@thinpad.lan.raisama.net> (raw)
In-Reply-To: <20161018205213.GA2511@potion>
On Tue, Oct 18, 2016 at 10:52:14PM +0200, Radim Krčmář wrote:
[...]
> The main problem is that QEMU changes virtual_tsc_khz when migrating
> without hardware scaling, so KVM is forced to get nanoseconds wrong ...
>
> If QEMU doesn't want to keep the TSC frequency constant, then it would
> be better if it didn't expose TSC in CPUID -- guest would just use
> kvmclock without being tempted by direct TSC accesses.
Isn't enough to simply not expose invtsc? Aren't guests expected
to assume the TSC frequency can change if invtsc isn't set on
CPUID?
--
Eduardo
next prev parent reply other threads:[~2016-10-18 21:05 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-14 21:20 invtsc + migration + TSC scaling Eduardo Habkost
2016-10-14 21:20 ` [Qemu-devel] " Eduardo Habkost
2016-10-17 9:47 ` Marcelo Tosatti
2016-10-17 9:47 ` [Qemu-devel] " Marcelo Tosatti
2016-10-17 14:50 ` Radim Krčmář
2016-10-17 14:50 ` [Qemu-devel] " Radim Krčmář
2016-10-17 16:24 ` Paolo Bonzini
2016-10-17 16:24 ` [Qemu-devel] " Paolo Bonzini
2016-10-17 21:11 ` Eduardo Habkost
2016-10-17 21:11 ` [Qemu-devel] " Eduardo Habkost
2016-10-17 23:58 ` Marcelo Tosatti
2016-10-17 23:58 ` [Qemu-devel] " Marcelo Tosatti
2016-10-18 13:41 ` Paolo Bonzini
2016-10-18 13:41 ` [Qemu-devel] " Paolo Bonzini
2016-10-18 17:09 ` Marcelo Tosatti
2016-10-18 17:09 ` [Qemu-devel] " Marcelo Tosatti
2016-10-18 20:52 ` Radim Krčmář
2016-10-18 20:52 ` [Qemu-devel] " Radim Krčmář
2016-10-18 21:05 ` Eduardo Habkost [this message]
2016-10-18 21:05 ` Eduardo Habkost
2016-10-19 13:27 ` Radim Krčmář
2016-10-19 13:27 ` [Qemu-devel] " Radim Krčmář
2016-10-19 13:55 ` Eduardo Habkost
2016-10-19 13:55 ` [Qemu-devel] " Eduardo Habkost
2016-10-19 15:42 ` Radim Krčmář
2016-10-19 15:42 ` [Qemu-devel] " Radim Krčmář
2016-10-19 17:42 ` Eduardo Habkost
2016-10-19 17:42 ` [Qemu-devel] " Eduardo Habkost
2016-10-18 13:48 ` Radim Krčmář
2016-10-18 13:48 ` [Qemu-devel] " Radim Krčmář
2016-10-18 13:36 ` Radim Krčmář
2016-10-18 13:36 ` [Qemu-devel] " Radim Krčmář
2016-10-18 13:38 ` Radim Krčmář
2016-10-18 13:38 ` [Qemu-devel] " Radim Krčmář
2016-10-17 17:20 ` Marcelo Tosatti
2016-10-17 17:20 ` [Qemu-devel] " Marcelo Tosatti
2016-10-18 13:27 ` Radim Krčmář
2016-10-18 13:27 ` [Qemu-devel] " Radim Krčmář
2016-10-18 9:04 ` Dr. David Alan Gilbert
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=20161018210514.GC5057@thinpad.lan.raisama.net \
--to=ehabkost@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rkrcmar@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.