From mboxrd@z Thu Jan  1 00:00:00 1970
Message-ID: <50C76DAC.6020603@wanadoo.fr>
Date: Tue, 11 Dec 2012 18:30:20 +0100
From: Thierry Bultel <thierry.bultel@wanadoo.fr>
MIME-Version: 1.0
References: <50C1EF04.1090506@wanadoo.fr> <50C236B9.3030507@xenomai.org>
	<50C4EF5A.3030502@wanadoo.fr> <50C524A6.6020006@xenomai.org>
	<50C5F784.6040801@wanadoo.fr> <50C6076F.7050505@xenomai.org>
	<50C60E6A.1080307@wanadoo.fr> <50C61DF3.8030703@xenomai.org>
	<50C62B41.1060308@wanadoo.fr> <50C63069.1010607@xenomai.org>
	<50C63FF3.6040409@wanadoo.fr> <50C643DC.1080901@xenomai.org>
	<50C64F79.8070101@wanadoo.fr> <50C65296.9070508@xenomai.org>
	<50C75094.3070906@wanadoo.fr> <50C75307.8020400@xenomai.org>
	<50C758F0.4060805@wanadoo.fr> <50C76468.6030100@xenomai.org>
In-Reply-To: <50C76468.6030100@xenomai.org>
Content-Type: text/plain; charset="utf-8"; format="flowed"
Content-Transfer-Encoding: 8bit
Subject: Re: [Xenomai] iMX6q 1Hz tick
List-Id: Discussions about the Xenomai project <xenomai.xenomai.org>
List-Unsubscribe: <http://www.xenomai.org/mailman/options/xenomai>,
	<mailto:xenomai-request@xenomai.org?subject=unsubscribe>
List-Archive: <http://www.xenomai.org/pipermail/xenomai>
List-Post: <mailto:xenomai@xenomai.org>
List-Help: <mailto:xenomai-request@xenomai.org?subject=help>
List-Subscribe: <http://www.xenomai.org/mailman/listinfo/xenomai>,
	<mailto:xenomai-request@xenomai.org?subject=subscribe>
To: Gilles Chanteperdrix <gilles.chanteperdrix@xenomai.org>
Cc: xenomai@xenomai.org

Le 11/12/2012 17:50, Gilles Chanteperdrix a écrit :
> On 12/11/2012 05:01 PM, Thierry Bultel wrote:
>> Le 11/12/2012 16:36, Gilles Chanteperdrix a écrit :
>>> On 12/11/2012 04:26 PM, Thierry Bultel wrote:
>>>> Gilles,
>>>>
>>>> another issue (likely related, and that may help to diagnose) that I can
>>>> see is that time is completely wrong;
>>>>
>>>> For instance:
>>>>
>>>>
>>>> [root@buildroot ~]# time sleep 10
>>>>
>>>> real	0m10.009s
>>>> user	0m0.002s
>>>> sys	0m0.013s
>>>>
>>>> The system says that it spent 10 secs but I actually measured 25 secs.
>>>
>>> No, that is likely because you have CONFIG_CPU_FREQ or CONFIG_CPU_IDLE
>>> enabled.
>>>
>>
>> Thanks, yes this was CONFIG_CPU_FREQ
>
> Ok, and when running at full speed, do the timer thread always take 20%
> cpu ?
>

It is much better. I only have 1.3% of CPU load.
Also the target seems really stable now. Thanks a lot, again.

The only remaining 'weird' issue is that the iMX Timer Tick counter in 
/proc/interrupts does not increase whereas it does when CONFIG_IPIPE is 
set to NO. It is not really a blocking issue, but I would like to 
understand why.