From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1752362Ab3GEFnM (ORCPT <rfc822;w@1wt.eu>);
	Fri, 5 Jul 2013 01:43:12 -0400
Received: from mail-pd0-f172.google.com ([209.85.192.172]:59008 "EHLO
	mail-pd0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751130Ab3GEFnL (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Fri, 5 Jul 2013 01:43:11 -0400
Message-ID: <51D65D4A.1080706@gmail.com>
Date: Fri, 05 Jul 2013 13:44:42 +0800
From: Light <sgsdxzy@gmail.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130620 Thunderbird/17.0.7
MIME-Version: 1.0
To: linux-kernel@vger.kernel.org
Subject: Re: Intel_pstate: One Core always 100% C0 state and never scale down
References: <51D4EF6C.9040808@gmail.com>
In-Reply-To: <51D4EF6C.9040808@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 07/04/2013 11:43 AM, Light wrote:
> I am using a laptop with Intel Ivy bridge core i7 3610QM. I updated my 
> kernel to 3.10 and started to use intel_pstate as scaling driver:
> #cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_driver
> intel_pstate
>
> However I find that one of my four cores is always in C0 state even 
> when there is no activities. I monitored it using i7z:
> Core [core-id]  :Actual Freq (Mult.)      C0%   Halt(C1)%  C3 % C6 %   
> C7 %  Temp
>         Core 1 [0]:       3288.24 (32.97x)      99.7       0 0       
> 0       0    83
>         Core 2 [1]:       3138.62 (31.47x)         1       0 0       
> 0    99.7    74
>         Core 3 [2]:       3175.46 (31.84x)         1    0.891 0       
> 0      99    76
>         Core 4 [3]:       3177.34 (31.86x)         1    0.21 0       
> 0    99.3    71
>
> Also cpu frequencies never scale down, resulting in very high temp.
> #cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
> powersave
>
> It does say powersave, and my cpu is capable of 1.20Ghz to 3.30Ghz
>
> I don't know if I misconfigured or misunderstood something. Can 
> someone tell me why?
> Thanks!
Switching to dynticks Idle fixed the problem. But I am still wondering 
if it were a bug with full dynticks...