All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nico Schottelius <nico-mutt@schottelius.org>
To: george anzinger <george@mvista.com>
Cc: Nico Schottelius <nicos-mutt@pcsystems.de>,
	Joshua Uziel <uzi@uzix.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: cpu speed is 165mhz instead of real 650mhz
Date: Fri, 2 Aug 2002 05:57:01 +0200	[thread overview]
Message-ID: <20020802035701.GA311@schottelius.org> (raw)
In-Reply-To: <3D3F0A5E.E548C8DA@mvista.com>

[-- Attachment #1: Type: text/plain, Size: 2171 bytes --]

Once again I am on a 147Mhz system....

george anzinger [Wed, Jul 24, 2002 at 01:13:18PM -0700]:
> Nico Schottelius wrote:
> > Joshua Uziel [Wed, Jul 24, 2002 at 03:27:09AM -0700]:
> > > * Nico Schottelius <nicos-mutt@pcsystems.de> [020724 02:03]:
> > > > This periodicly appears in my system. The Kernel seems to misdetect the
> > > > right cpu speed and then it's running only at 165mhz.
> > > > I don't really understand why this happens, there's no acpi enabled, which
> > > > caused this failure the last time.
> > >
> > > Is this a notebook computer?  Is it that you're sometimes booting it up
> > > while the system is unplugged (ie. on battery)?
> > 
> > yes,it is, but slowing down to 500 mhz is the only  available speedstep
> > option.
> > 
> > 165 or similar is not supported (afaik) by the bios/processor.
> > 
> The cpu speed is detected by comparing the TSC against the
> PIT.

I don't even now any of these both.

> The PIT is used to drive the clock.  If it is wrong by
> this much you should see time drifting like mad.

Hey, you are right! Instead of 13 o'clock it's 5 o'clock.
What todo now ? I am staying on this downclocked system, if you
need some more informations.

> If the TSC
> is wrong, you should see errors in the sub 1/HZ correction
> applied to get_time_of_day().
> You could detect this by
> looping on a get_time_of_day() call and noticing that time
> slides ahead 3/HZ seconds and then back each tick.  What
> would be happening is that the interpolation code would be
> taking the fast TSC (i.e. 500MHZ when it thought it was 165)
> and be pushing time out beyond the next tick value.  Each
> tick this would reset and be replayed.  If neither of these
> is happening, the reported value is most likely what is
> really going on.

Nice explanation. I think I understood 85 % of it :)

Nico

-- 
Changing mail address: please forget all known @pcsystems.de addresses.

Please send your messages pgp-signed and/or pgp-encrypted (don't encrypt mails
to mailing list!). If you don't know what pgp is visit www.gnupg.org.
(public pgp key: ftp.schottelius.org/pub/familiy/nico/pgp-key)

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

  reply	other threads:[~2002-08-02 10:24 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-07-24 11:01 cpu speed is 165mhz instead of real 650mhz Nico Schottelius
2002-07-24 10:27 ` Joshua Uziel
2002-07-24 13:16   ` Nico Schottelius
2002-07-24 20:13     ` george anzinger
2002-08-02  3:57       ` Nico Schottelius [this message]
  -- strict thread matches above, loose matches on Subject: below --
2002-07-24 11:39 Nico Schottelius

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=20020802035701.GA311@schottelius.org \
    --to=nico-mutt@schottelius.org \
    --cc=george@mvista.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nicos-mutt@pcsystems.de \
    --cc=uzi@uzix.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 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.