Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 12 Dec 2007 20:25:40 -0800
From:      Nate Lawson <nate@root.org>
To:        Ken Menzel <kenm@icarz.com>
Cc:        freebsd-acpi@freebsd.org
Subject:   Re: CURRENTand releng_7 kernel makes the system run very very hot
Message-ID:  <4760B444.4020302@root.org>
In-Reply-To: <13a701c83ce4$e94bfb20$8adb7bd1@icarz.com>
References:  <13a701c83ce4$e94bfb20$8adb7bd1@icarz.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Ken Menzel wrote:
> It has been suggested to me to move this thread from current to acpi.
>> From what I can tell the CPU's do not halt on idle.  Top -SH from a 
> system booted for a few hours on releng_7 or on current shows hours of
> time used where as releng_6 used only minutes or seconds.  This is
> causing some sytems to overheat.
> 
> I am trying to compile all the relevant information in this e-mail. If I
> have missed  anything please let me kow.  I can also provide ssh access
> to a developer who would like to see the problem.  I see the problem on
> both AMD64 kernel and i386 kernel single and multi processor.
> 
> Here is information I have gather so far:  Is there anything else needed
> for the PR?

Based on the information you sent privately, I don't see anything wrong.
 acpi_cpu_idle() is calling acpi_cpu_c1() as expected.  There is no
interrupt storm according to vmstat -i.  So the question now is, "why
doesn't the HLT instruction actually work?"  Perhaps there is some CPU
errata or BIOS configuration option you need to change to enable C1?

What does sysctl dev.cpu say?

-- 
Nate



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4760B444.4020302>