Re: SMP problems with -CURRENT? (and BETA5)

From: Adam K Kirchhoff <adamk_at_voicenet.com>
Date: Mon, 20 Sep 2004 20:26:04 -0400
David D.W. Downey wrote:

>On Mon, 20 Sep 2004 17:52:25 -0400, Adam K Kirchhoff <adamk_at_voicenet.com> wrote:
>  
>
>>Adam K Kirchhoff wrote:
>>
>>    
>>
>>>Oliver Brandmueller wrote:
>>>
>>>      
>>>
>>>>Hi again.
>>>>
>>>>On Mon, Sep 20, 2004 at 03:36:03PM +0200, Oliver Brandmueller wrote:
>>>>        
>>>>
>>Well, booting with HTT disabled still doesn't work for me, which is
>>making me think this isn't SMP related anymore...  My boot stalls with:
>>
>>acpi_cpu: throttling enabled, 8 steps (100% to 12.5%), currently 100.0%
>>ad0: 39083MB <Maxtor 5T040H4/TAH71DP0> [79408/16/63] at ata0-master UDMA100
>>ad1: 117246MB <Maxtor 6Y120L0/YAR41VW0> [238216/16/63] at ata0-slave UDMA100
>>ATAPI_RESET time = 40us
>>ad2: 76345MB <MAXTOR 6L080J4/A93.0500> [155114/16/63] at ata1-master UDMA100
>>acd0: DVDROM <Pioneer DVD-ROM ATAPIModel DVD-120/1.22> at ata1-slave UDMA66
>>
>>Ideas?
>>
>>    
>>
>
>
>OK i have seen that before. it's the ACPI code doing CPU throttling.
>(OK, obviously, hehe.)
>
>What i don't understand and haven't solved is why it throttles so
>early (for me) to the point that int he middle of a compile (which is
>definitely NOT when you want it done <grin>) when the load on the
>system, is definitely high enough to keep throttling from being
>needed. It's almost like (and anyone working on the ACPI code PLEASE
>do comment) whatever variable is responsible for the timing AND the
>differential for check times is screwy.
>
>That's all I have for now, meanwhile time for me to beat my head on
>why the hell BETA5 is screwing up on an installworld with touch: file
>not found for newvars.sh which exists in the directory it's trying TO
>copy from.
>
>  
>

What makes you think it's the cpu throttling that's causing the lockups 
for me?  It does say "acpi_cpu: throttling enabled, 8 steps (100% to 
12.5%)"  but it continues on the same line with "currently 100%"  Maybe 
I'm reading it wrong but that would indicate to me that it's still 
running at 100%....

In fact, I just checked and BETA4, which works fine, also displays the 
same line about cpu throttling.

Any other ideas?  I'd really like to make sure that this problem doesn't 
continue beyond BETA5 :-)  Anything I can do to make sure this gets 
resolved (before I go and send a problem report)?

Adam
Received on Mon Sep 20 2004 - 22:26:42 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:12 UTC