All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: "Xen-Devel (E-mail)" <xen-devel@lists.xensource.com>,
	Keir Fraser <keir.fraser@eu.citrix.com>
Subject: Re: [PATCH/RFC] report hardware tsc frequency even for emulated tsc
Date: Mon, 30 Nov 2009 13:06:44 -0800	[thread overview]
Message-ID: <4B1433E4.5070604@goop.org> (raw)
In-Reply-To: <b6df895c-0174-40af-9604-bf76816ee8dd@default>

On 11/30/09 12:51, Dan Magenheimer wrote:
> As long as the "illusion" provided via both rdtsc and
> pvclock are consistent, it works.
>   

OK, I see.  Rather than always emulating 1GHz, make it emulate some
other arbitrary speed depending on the initial native CPU speed.

> I wasn't aware of that.  My proposal could allow for that but
> the specific proposed patch doesn't.  It could only be
> done I think if one didn't care about the TSC hz rate
> given to apps... if that's true, just turn off TSC emulation.
>   

I don't think its worth doing.  In many ways a VCPU is like a Transmeta
CPU: they never ran at any particular speed, but with some
power/performance policy setting.  The tsc ran at a fixed rate that had
no particular relationship to how fast instructions get executed.

> Good point.  OTOH, if one cared to do something to change
> tsc emulation, one would need to be privileged to relaunch
> the domain.
>   

Well, they'd need some interface to start domains at all.  You could
imagine something like a VPS hosting service where the user can control
their own domains via a web GUI, and "tsc emulation" would be a checkbox
(buried deeping in an advanced options page, one presumes).

And you could also imagine that this patch would be a boon to them,
because it would eliminate the "you said you had 2.4GHz hosts but
/proc/cpuinfo only says 1GHz" questions/complaints...

    J

      reply	other threads:[~2009-11-30 21:06 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-30 15:55 [PATCH/RFC] report hardware tsc frequency even for emulated tsc Dan Magenheimer
2009-11-30 19:21 ` Jeremy Fitzhardinge
2009-11-30 20:51   ` Dan Magenheimer
2009-11-30 21:06     ` Jeremy Fitzhardinge [this message]

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=4B1433E4.5070604@goop.org \
    --to=jeremy@goop.org \
    --cc=dan.magenheimer@oracle.com \
    --cc=keir.fraser@eu.citrix.com \
    --cc=xen-devel@lists.xensource.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.