From: Pavel Machek <pavel@ucw.cz>
To: Georg Schild <dangertools@gmx.net>
Cc: linux-kernel@vger.kernel.org
Subject: Re: cpu throttling powernow-k8 and acpi in kernel
Date: Mon, 3 Jan 2005 10:42:46 +0100 [thread overview]
Message-ID: <20050103094245.GD2473@openzaurus.ucw.cz> (raw)
In-Reply-To: <41D80CAB.1060903@gmx.net>
Hi!
> I have an acer aspire 1501 lmi with amd64 @3000+. i am running a
> gentoo 64bit dist with vanilla 2.6.10 kernel on it.
>
> i encounter some problems with the speed throttling of the cpu. this
> kind of cpu has 3 steps which a gouvernor can reach, 1800, 1600 and
> 800Mhz. i am using the ondemand gouvernor. so far this works quite
> good, ondemand puts it at 800 until i do something. as it should be.
> i have also CONFIG_ACPI_PROCESSOR=y and CONFIG_ACPI_THERMAL=y
> enabled. when acpi thinks the temperature is too high (95 for cpu)
> it throttles the cpu down to 800Mhz, no care what ondemand tells it.
> okay, why not, is a good protection for overheating. but i don't
> think the cpu has 95, i have run the laptop much hotter once, and
> there was no downthrottling. it cannot be that i am not able to
> compile a simple package without getting a critical temperature. i am
> watching the temps in gkrellm and this leads me to the thing that
> there is something wrong with it cause it jumps a bit when the temps
> are getting higher and one thing more, when the laptop is doing
> nothing, e.g. over night, screen is off, cpu is at 800 the temp is
> still at about 55 and more, how can that be? but i cannot disable
> the two acpi-options mentionend above. at first the cpu runs at 800,
> no problem, fan is almost off. but when i start e.g. a compilation
> first the fan starts spinning up a bit, the cpu goes to 1800mhz but
> after a while the fan gives all the speed it is able to, much noise,
> and after one or 2 minutes the laptop switches off immediate.
>
It seems your machine indeed is overheating. Modern cpus produce a lot
of heat.
55C idle temperature seems okay. Open machine and attach your
own temperature sensor to cpu to verify...
Pavel
--
64 bytes from 195.113.31.123: icmp_seq=28 ttl=51 time=448769.1 ms
next prev parent reply other threads:[~2005-01-04 14:21 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-02 15:00 cpu throttling powernow-k8 and acpi in kernel Georg Schild
2005-01-02 22:53 ` Guennadi Liakhovetski
2005-01-03 7:02 ` Georg Schild
2005-01-03 9:42 ` Pavel Machek [this message]
2005-01-04 14:29 ` Georg Schild
2005-01-04 12:11 ` Georg Schild
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=20050103094245.GD2473@openzaurus.ucw.cz \
--to=pavel@ucw.cz \
--cc=dangertools@gmx.net \
--cc=linux-kernel@vger.kernel.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.